[2/3] hive git commit: HIVE-12338: Add webui to HiveServer2 (Jimmy, reviewed by Mohit, Szehon, Lefty)
http://git-wip-us.apache.org/repos/asf/hive/blob/2c0c191c/service/src/resources/hive-webapps/static/css/bootstrap.min.css -- diff --git a/service/src/resources/hive-webapps/static/css/bootstrap.min.css b/service/src/resources/hive-webapps/static/css/bootstrap.min.css new file mode 100755 index 000..0f6fbcd --- /dev/null +++ b/service/src/resources/hive-webapps/static/css/bootstrap.min.css @@ -0,0 +1,9 @@ +/*! + * Bootstrap v3.0.0 + * + * Copyright 2013 Twitter, Inc + * Licensed under the Apache License v2.0 + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Designed and built with all the love in the world by @mdo and @fat. + *//*! normalize.css v2.1.0 | MIT License | git.io/normalize */article,aside,details,figcaption,figure,footer,header,hgroup,main,nav,section,summary{display:block}audio,canvas,video{display:inline-block}audio:not([controls]){display:none;height:0}[hidden]{display:none}html{font-family:sans-serif;-webkit-text-size-adjust:100%;-ms-text-size-adjust:100%}body{margin:0}a:focus{outline:thin dotted}a:active,a:hover{outline:0}h1{margin:.67em 0;font-size:2em}abbr[title]{border-bottom:1px dotted}b,strong{font-weight:bold}dfn{font-style:italic}hr{height:0;-moz-box-sizing:content-box;box-sizing:content-box}mark{color:#000;background:#ff0}code,kbd,pre,samp{font-family:monospace,serif;font-size:1em}pre{white-space:pre-wrap}q{quotes:"\201C" "\201D" "\2018" "\2019"}small{font-size:80%}sub,sup{position:relative;font-size:75%;line-height:0;vertical-align:baseline}sup{top:-0.5em}sub{bottom:-0.25em}img{border:0}svg:not(:root){overflow:hidden}figure{margin:0}fieldset{padding:.35em .625em .75em;margin:0 2px;border:1px solid #c0c0c0}legend{padding:0;border:0}button,input,select,textarea{margin:0;font-family:inherit;font-size:100%}button,input{line-height:normal}button,select{text-transform:none}button,html input[type="button"],input[type="reset"],input[type="submit"]{cursor:pointer;-webkit-appearance:button}button[disabled],html input[disabled]{cursor:default}input[type="checkbox"],input[type="radio"]{padding:0;box-sizing:border-box}input[type="search"]{-webkit-box-sizing:content-box;-moz-box-sizing:content-box;box-sizing:content-box;-webkit-appearance:textfield}input[type="search"]::-webkit-search-cancel-button,input[type="search"]::-webkit-search-decoration{-webkit-appearance:none}button::-moz-focus-inner,input::-moz-focus-inner{padding:0;border:0}textarea{overflow:auto;vertical-align:top}table{border-collapse:collapse;border-spacing:0}@media print{*{color:#000!important;text-shadow:none!important;background:transparent!important;box-shadow:none!important}a,a:visited{text-decorati on:underline}a[href]:after{content:" (" attr(href) ")"}abbr[title]:after{content:" (" attr(title) ")"}.ir a:after,a[href^="javascript:"]:after,a[href^="#"]:after{content:""}pre,blockquote{border:1px solid #999;page-break-inside:avoid}thead{display:table-header-group}tr,img{page-break-inside:avoid}img{max-width:100%!important}@page{margin:2cm .5cm}p,h2,h3{orphans:3;widows:3}h2,h3{page-break-after:avoid}.navbar{display:none}.table td,.table th{background-color:#fff!important}.btn>.caret,.dropup>.btn>.caret{border-top-color:#000!important}.label{border:1px solid #000}.table{border-collapse:collapse!important}.table-bordered th,.table-bordered td{border:1px solid #ddd!important}}*,*:before,*:after{-webkit-box-sizing:border-box;-moz-box-sizing:border-box;box-sizing:border-box}html{font-size:62.5%;-webkit-tap-highlight-color:rgba(0,0,0,0)}body{font-family:"Helvetica Neue",Helvetica,Arial,sans-serif;font-size:14px;line-height:1.428571429;color:#333;background-color:#fff}input,button,select ,textarea{font-family:inherit;font-size:inherit;line-height:inherit}button,input,select[multiple],textarea{background-image:none}a{color:#428bca;text-decoration:none}a:hover,a:focus{color:#2a6496;text-decoration:underline}a:focus{outline:thin dotted #333;outline:5px auto -webkit-focus-ring-color;outline-offset:-2px}img{vertical-align:middle}.img-responsive{display:block;height:auto;max-width:100%}.img-rounded{border-radius:6px}.img-thumbnail{display:inline-block;height:auto;max-width:100%;padding:4px;line-height:1.428571429;background-color:#fff;border:1px solid #ddd;border-radius:4px;-webkit-transition:all .2s ease-in-out;transition:all .2s ease-in-out}.img-circle{border-radius:50%}hr{margin-top:20px;margin-bottom:20px;border:0;border-top:1px solid #eee}.sr-only{position:absolute;width:1px;height:1px;padding:0;margin:-1px;overflow:hidden;clip:rect(0 0 0 0);border:0}p{margin:0 0 10px}.lead{margin-bottom:20px;font-size:16.098px;font-weight:200;line-height:1.4}@media(min-w
[1/3] hive git commit: HIVE-12338: Add webui to HiveServer2 (Jimmy, reviewed by Mohit, Szehon, Lefty)
Repository: hive Updated Branches: refs/heads/master a51e5d4e2 -> 2c0c191cd http://git-wip-us.apache.org/repos/asf/hive/blob/2c0c191c/service/src/resources/hive-webapps/static/css/hive.css -- diff --git a/service/src/resources/hive-webapps/static/css/hive.css b/service/src/resources/hive-webapps/static/css/hive.css new file mode 100644 index 000..b8c9f54 --- /dev/null +++ b/service/src/resources/hive-webapps/static/css/hive.css @@ -0,0 +1,24 @@ +/** + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/* General styling */ +body { padding-top: 60px; } +.logo img { float: right; } +.inner_header { margin-bottom: 1em; } +section { margin-bottom: 3em; } + http://git-wip-us.apache.org/repos/asf/hive/blob/2c0c191c/service/src/resources/hive-webapps/static/fonts/glyphicons-halflings-regular.eot -- diff --git a/service/src/resources/hive-webapps/static/fonts/glyphicons-halflings-regular.eot b/service/src/resources/hive-webapps/static/fonts/glyphicons-halflings-regular.eot new file mode 100755 index 000..87eaa43 Binary files /dev/null and b/service/src/resources/hive-webapps/static/fonts/glyphicons-halflings-regular.eot differ http://git-wip-us.apache.org/repos/asf/hive/blob/2c0c191c/service/src/resources/hive-webapps/static/fonts/glyphicons-halflings-regular.svg -- diff --git a/service/src/resources/hive-webapps/static/fonts/glyphicons-halflings-regular.svg b/service/src/resources/hive-webapps/static/fonts/glyphicons-halflings-regular.svg new file mode 100755 index 000..5fee068 --- /dev/null +++ b/service/src/resources/hive-webapps/static/fonts/glyphicons-halflings-regular.svg @@ -0,0 +1,228 @@ + +http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd; > +http://www.w3.org/2000/svg;> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + \ No newline at end of file http://git-wip-us.apache.org/repos/asf/hive/blob/2c0c191c/service/src/resources/hive-webapps/static/fonts/glyphicons-halflings-regular.ttf -- diff --git a/service/src/resources/hive-webapps/static/fonts/glyphicons-halflings-regular.ttf b/service/src/resources/hive-webapps/static/fonts/glyphicons-halflings-regular.ttf new file mode 100755 index 000..be784dc Binary files /dev/null and b/service/src/resources/hive-webapps/static/fonts/glyphicons-halflings-regular.ttf differ http://git-wip-us.apache.org/repos/asf/hive/blob/2c0c191c/service/src/resources/hive-webapps/static/fonts/glyphicons-halflings-regular.woff -- diff --git a/service/src/resources/hive-webapps/static/fonts/glyphicons-halflings-regular.woff b/service/src/resources/hive-webapps/static/fonts/glyphicons-halflings-regular.woff new file mode 100755 index 000..2cc3e48 Binary files /dev/null and b/service/src/resources/hive-webapps/static/fonts/glyphicons-halflings-regular.woff differ http://git-wip-us.apache.org/repos/asf/hive/blob/2c0c191c/service/src/resources/hive-webapps/static/hive_logo.jpeg -- diff --git a/service/src/resources/hive-webapps/static/hive_logo.jpeg b/service/src/resources/hive-webapps/static/hive_logo.jpeg new file mode 100644 index 000..8c4a5df Binary files /dev/null and b/service/src/resources/hive-webapps/static/hive_logo.jpeg differ http://git-wip-us.apache.org/repos/asf/hive/blob/2c0c191c/spark-client/pom.xml -- diff --git a/spark-client/pom.xml b/spark-client/pom.xml index 9d2b418..0405016 100644 ---
[3/3] hive git commit: HIVE-12338: Add webui to HiveServer2 (Jimmy, reviewed by Mohit, Szehon, Lefty)
HIVE-12338: Add webui to HiveServer2 (Jimmy, reviewed by Mohit, Szehon, Lefty) Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/2c0c191c Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/2c0c191c Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/2c0c191c Branch: refs/heads/master Commit: 2c0c191cdd6b2d1aebe4502e24cc2b3d041bf3ca Parents: a51e5d4 Author: Jimmy XiangAuthored: Thu Nov 19 08:10:29 2015 -0800 Committer: Jimmy Xiang Committed: Sun Nov 29 09:55:09 2015 -0800 -- common/pom.xml | 5 + .../org/apache/hadoop/hive/conf/HiveConf.java | 5 + .../hive/http/AdminAuthorizedServlet.java | 45 ++ .../java/org/apache/hive/http/ConfServlet.java | 101 + .../java/org/apache/hive/http/HttpServer.java | 316 ++ .../org/apache/hive/http/JMXJsonServlet.java| 412 +++ pom.xml | 1 + ql/pom.xml | 6 + service/pom.xml | 56 +++ .../hive/service/cli/operation/Operation.java | 2 +- .../service/cli/operation/OperationManager.java | 26 +- .../service/cli/operation/SQLOperation.java | 8 +- .../service/cli/session/HiveSessionBase.java| 4 + .../service/cli/session/HiveSessionImpl.java| 12 + .../service/cli/session/SessionManager.java | 16 +- .../apache/hive/service/server/HiveServer2.java | 47 +++ .../hive-webapps/hiveserver2/hiveserver2.jsp| 186 + .../hive-webapps/hiveserver2/index.html | 20 + .../static/css/bootstrap-theme.min.css | 10 + .../hive-webapps/static/css/bootstrap.min.css | 9 + .../resources/hive-webapps/static/css/hive.css | 24 ++ .../fonts/glyphicons-halflings-regular.eot | Bin 0 -> 14079 bytes .../fonts/glyphicons-halflings-regular.svg | 228 ++ .../fonts/glyphicons-halflings-regular.ttf | Bin 0 -> 29512 bytes .../fonts/glyphicons-halflings-regular.woff | Bin 0 -> 16448 bytes .../hive-webapps/static/hive_logo.jpeg | Bin 0 -> 5616 bytes spark-client/pom.xml| 6 + 27 files changed, 1529 insertions(+), 16 deletions(-) -- http://git-wip-us.apache.org/repos/asf/hive/blob/2c0c191c/common/pom.xml -- diff --git a/common/pom.xml b/common/pom.xml index ee74282..72bb550 100644 --- a/common/pom.xml +++ b/common/pom.xml @@ -56,6 +56,11 @@ ${commons-lang.version} + org.eclipse.jetty.aggregate + jetty-all + ${jetty.version} + + joda-time joda-time ${joda.version} http://git-wip-us.apache.org/repos/asf/hive/blob/2c0c191c/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java -- diff --git a/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java b/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java index db942b0..9e805bd 100644 --- a/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java +++ b/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java @@ -1847,6 +1847,11 @@ public class HiveConf extends Configuration { HIVE_SERVER2_PARALLEL_COMPILATION("hive.driver.parallel.compilation", false, "Whether to\n" + "enable parallel compilation between sessions on HiveServer2. The default is false."), +// HiveServer2 WebUI +HIVE_SERVER2_WEBUI_BIND_HOST("hive.server2.webui.host", "0.0.0.0", "The host address the HiveServer2 WebUI will listen on"), +HIVE_SERVER2_WEBUI_PORT("hive.server2.webui.port", 10002, "The port the HiveServer2 WebUI will listen on"), +HIVE_SERVER2_WEBUI_MAX_THREADS("hive.server2.webui.max.threads", 50, "The max HiveServer2 WebUI threads"), + // Tez session settings HIVE_SERVER2_TEZ_DEFAULT_QUEUES("hive.server2.tez.default.queues", "", "A list of comma separated values corresponding to YARN queues of the same name.\n" + http://git-wip-us.apache.org/repos/asf/hive/blob/2c0c191c/common/src/java/org/apache/hive/http/AdminAuthorizedServlet.java -- diff --git a/common/src/java/org/apache/hive/http/AdminAuthorizedServlet.java b/common/src/java/org/apache/hive/http/AdminAuthorizedServlet.java new file mode 100644 index 000..5d957c2 --- /dev/null +++ b/common/src/java/org/apache/hive/http/AdminAuthorizedServlet.java @@ -0,0 +1,45 @@ +/** + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file +
hive git commit: HIVE-12497: Remove HADOOP_CLIENT_OPTS from hive script (Prasanth Jayachandran reviewed by Gopal V)
Repository: hive Updated Branches: refs/heads/master 2c0c191cd -> 0a96201f2 HIVE-12497: Remove HADOOP_CLIENT_OPTS from hive script (Prasanth Jayachandran reviewed by Gopal V) Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/0a96201f Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/0a96201f Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/0a96201f Branch: refs/heads/master Commit: 0a96201f268a8cf0efe71d960f8814592d30d756 Parents: 2c0c191 Author: Prasanth JayachandranAuthored: Sun Nov 29 16:53:20 2015 -0600 Committer: Prasanth Jayachandran Committed: Sun Nov 29 16:53:20 2015 -0600 -- bin/ext/version.sh | 2 +- bin/hive | 23 ++- 2 files changed, 19 insertions(+), 6 deletions(-) -- http://git-wip-us.apache.org/repos/asf/hive/blob/0a96201f/bin/ext/version.sh -- diff --git a/bin/ext/version.sh b/bin/ext/version.sh index bb6449d..b6a237b 100644 --- a/bin/ext/version.sh +++ b/bin/ext/version.sh @@ -27,7 +27,7 @@ version () { # hadoop 20 or newer - skip the aux_jars option and hiveconf CLASS=org.apache.hive.common.util.HiveVersionInfo - exec $HADOOP jar $JAR $CLASS + exec $HADOOP jar $JAR $CLASS 2>> ${STDERR} } version_help () { http://git-wip-us.apache.org/repos/asf/hive/blob/0a96201f/bin/hive -- diff --git a/bin/hive b/bin/hive index 47d99f7..4818667 100755 --- a/bin/hive +++ b/bin/hive @@ -25,6 +25,8 @@ bin=`cd "$bin"; pwd` . "$bin"/hive-config.sh +TMP_USER_DIR="/tmp/${USER}" +STDERR="${TMP_USER_DIR}/stderr" SERVICE="" HELP="" while [ $# -gt 0 ]; do @@ -193,18 +195,29 @@ if [ "$HADOOP_HOME" == "" ]; then exit 4; fi -# to avoid errors from log4j2 automatic configuration loading -export HADOOP_CLIENT_OPTS="$HADOOP_CLIENT_OPTS -Dlog4j.configurationFile=hive-log4j2.xml " - HADOOP=$HADOOP_HOME/bin/hadoop if [ ! -f ${HADOOP} ]; then echo "Cannot find hadoop installation: \$HADOOP_HOME or \$HADOOP_PREFIX must be set or hadoop must be in the path"; exit 4; fi +if [ ! -d ${TMP_USER_DIR} ]; then + mkdir -p ${TMP_USER_DIR} 2> /dev/null + if [ $? -ne 0 ]; then +STDERR="/dev/tty" + fi +fi + +if [ "${STDERR}" != "/dev/null" ] && [ ! -f ${STDERR} ]; then + touch ${STDERR} 2> /dev/null + if [ $? -ne 0 ]; then +STDERR="/dev/tty" + fi +fi + # Make sure we're using a compatible version of Hadoop if [ "x$HADOOP_VERSION" == "x" ]; then -HADOOP_VERSION=$($HADOOP version | awk -F"\t" '/Hadoop/ {print $0}' | cut -d' ' -f 2); +HADOOP_VERSION=$($HADOOP version 2>> ${STDERR} | awk -F"\t" '/Hadoop/ {print $0}' | cut -d' ' -f 2); fi # Save the regex to a var to workaround quoting incompatabilities @@ -253,7 +266,7 @@ HBASE_BIN=${HBASE_BIN:-"$(which hbase)"} if [[ -n $HBASE_BIN ]] ; then # exclude ZK, PB, and Guava (See HIVE-2055) # depends on HBASE-8438 (hbase-0.94.14+, hbase-0.96.1+) for `hbase mapredcp` command - for x in $($HBASE_BIN mapredcp | tr ':' '\n') ; do + for x in $($HBASE_BIN mapredcp 2>> ${STDERR} | tr ':' '\n') ; do if [[ $x == *zookeeper* || $x == *protobuf-java* || $x == *guava* ]] ; then continue fi
[83/91] [abbrv] hive git commit: HIVE-12307 - Streaming API TransactionBatch.close() must abort any remaining transactions in the batch(Eugene Koifman, reviewed by Alan Gates)
HIVE-12307 - Streaming API TransactionBatch.close() must abort any remaining transactions in the batch(Eugene Koifman, reviewed by Alan Gates) Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/f1ac5a39 Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/f1ac5a39 Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/f1ac5a39 Branch: refs/heads/spark Commit: f1ac5a391a18fccf724249038fca73e7b55854e2 Parents: 6d4dfa4 Author: Eugene KoifmanAuthored: Thu Nov 26 11:48:03 2015 -0800 Committer: Eugene Koifman Committed: Thu Nov 26 11:48:29 2015 -0800 -- .../streaming/AbstractRecordWriter.java | 32 ++- .../hcatalog/streaming/ConnectionError.java | 3 +- .../streaming/DelimitedInputWriter.java | 2 +- .../hive/hcatalog/streaming/HiveEndPoint.java | 211 +-- .../hcatalog/streaming/StrictJsonWriter.java| 2 +- .../hcatalog/streaming/TransactionBatch.java| 1 + .../hcatalog/streaming/TransactionError.java| 2 +- .../hive/hcatalog/streaming/TestStreaming.java | 167 +++ .../hadoop/hive/ql/io/orc/OrcRecordUpdater.java | 3 + 9 files changed, 344 insertions(+), 79 deletions(-) -- http://git-wip-us.apache.org/repos/asf/hive/blob/f1ac5a39/hcatalog/streaming/src/java/org/apache/hive/hcatalog/streaming/AbstractRecordWriter.java -- diff --git a/hcatalog/streaming/src/java/org/apache/hive/hcatalog/streaming/AbstractRecordWriter.java b/hcatalog/streaming/src/java/org/apache/hive/hcatalog/streaming/AbstractRecordWriter.java index 5c15675..0c6b9ea 100644 --- a/hcatalog/streaming/src/java/org/apache/hive/hcatalog/streaming/AbstractRecordWriter.java +++ b/hcatalog/streaming/src/java/org/apache/hive/hcatalog/streaming/AbstractRecordWriter.java @@ -65,6 +65,8 @@ public abstract class AbstractRecordWriter implements RecordWriter { final AcidOutputFormat outf; private Object[] bucketFieldData; // Pre-allocated in constructor. Updated on each write. + private Long curBatchMinTxnId; + private Long curBatchMaxTxnId; protected AbstractRecordWriter(HiveEndPoint endPoint, HiveConf conf) throws ConnectionError, StreamingException { @@ -98,6 +100,12 @@ public abstract class AbstractRecordWriter implements RecordWriter { } } + /** + * used to tag error msgs to provied some breadcrumbs + */ + String getWatermark() { +return partitionPath + " txnIds[" + curBatchMinTxnId + "," + curBatchMaxTxnId + "]"; + } // return the column numbers of the bucketed columns private List getBucketColIDs(List bucketCols, List cols) { ArrayList result = new ArrayList(bucketCols.size()); @@ -164,22 +172,32 @@ public abstract class AbstractRecordWriter implements RecordWriter { throws StreamingIOFailure, SerializationError { try { LOG.debug("Creating Record updater"); + curBatchMinTxnId = minTxnId; + curBatchMaxTxnId = maxTxnID; updaters = createRecordUpdaters(totalBuckets, minTxnId, maxTxnID); } catch (IOException e) { - LOG.error("Failed creating record updater", e); - throw new StreamingIOFailure("Unable to get new record Updater", e); + String errMsg = "Failed creating RecordUpdaterS for " + getWatermark(); + LOG.error(errMsg, e); + throw new StreamingIOFailure(errMsg, e); } } @Override public void closeBatch() throws StreamingIOFailure { -try { - for (RecordUpdater updater : updaters) { +boolean haveError = false; +for (RecordUpdater updater : updaters) { + try { +//try not to leave any files open updater.close(false); } - updaters.clear(); -} catch (IOException e) { - throw new StreamingIOFailure("Unable to close recordUpdater", e); + catch(Exception ex) { +haveError = true; +LOG.error("Unable to close " + updater + " due to: " + ex.getMessage(), ex); + } +} +updaters.clear(); +if(haveError) { + throw new StreamingIOFailure("Encountered errors while closing (see logs) " + getWatermark()); } } http://git-wip-us.apache.org/repos/asf/hive/blob/f1ac5a39/hcatalog/streaming/src/java/org/apache/hive/hcatalog/streaming/ConnectionError.java -- diff --git a/hcatalog/streaming/src/java/org/apache/hive/hcatalog/streaming/ConnectionError.java b/hcatalog/streaming/src/java/org/apache/hive/hcatalog/streaming/ConnectionError.java index ffa51c9..03f6a44 100644 --- a/hcatalog/streaming/src/java/org/apache/hive/hcatalog/streaming/ConnectionError.java +++
[08/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out -- diff --git a/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out b/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out index 2c14065..fa80956 100644 --- a/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out +++ b/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out @@ -134,10 +134,14 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE -Spark HashTable Sink Operator - keys: -0 key (type: int) -1 key (type: int) +Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator +keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Local Work: Map Reduce Local Work @@ -153,27 +157,31 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE -Map Join Operator - condition map: - Inner Join 0 to 1 - keys: -0 key (type: int) -1 key (type: int) - outputColumnNames: _col0, _col1, _col7 - input vertices: -0 Map 1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator -expressions: _col0 (type: int), _col1 (type: string), _col7 (type: string) -outputColumnNames: _col0, _col1, _col2 +Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator +condition map: + Inner Join 0 to 1 +keys: + 0 _col0 (type: int) + 1 _col0 (type: int) +outputColumnNames: _col0, _col1, _col3 +input vertices: + 0 Map 1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE -File Output Operator - compressed: false +Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator +compressed: false +Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE +table: +input format: org.apache.hadoop.mapred.TextInputFormat +output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat +serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work @@ -211,10 +219,14 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE -Spark HashTable Sink Operator - keys: -0 _col0 (type: int) -1 key (type: int) +Select Operator + expressions: key (type: int) +
[25/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/llap/tez_smb_1.q.out -- diff --git a/ql/src/test/results/clientpositive/llap/tez_smb_1.q.out b/ql/src/test/results/clientpositive/llap/tez_smb_1.q.out index 8e7078f..f6323f2 100644 --- a/ql/src/test/results/clientpositive/llap/tez_smb_1.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_smb_1.q.out @@ -128,11 +128,15 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: s3 + alias: s1 Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE +Select Operator + expressions: key (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE Map Operator Tree: TableScan alias: s1 @@ -140,22 +144,26 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE -Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: -0 key (type: int) -1 key (type: int) - Statistics: Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE - Group By Operator -aggregations: count() -mode: hash -outputColumnNames: _col0 -Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE -Reduce Output Operator - sort order: +Select Operator + expressions: key (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator +condition map: + Inner Join 0 to 1 +keys: + 0 _col0 (type: int) + 1 _col0 (type: int) +Statistics: Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE +Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator +sort order: +Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +value expressions: _col0 (type: bigint) Execution mode: llap Reducer 2 Execution mode: uber @@ -203,14 +211,32 @@ STAGE PLANS: Stage: Stage-1 Tez Edges: -Reducer 2 <- Map 1 (SIMPLE_EDGE) -Reducer 3 <- Map 5 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Reducer 3 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 5 <- Map 4 (SIMPLE_EDGE) A masked pattern was here Vertices: Map 1 Map Operator Tree: TableScan + alias: vt1 + Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE + Filter Operator +predicate: key is not null (type: boolean) +Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE +Select Operator + expressions: key (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator +key expressions: _col0 (type: int) +sort order: + +Map-reduce partition columns: _col0 (type: int) +Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE +Execution mode:
[03/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual3.q.out -- diff --git a/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual3.q.out b/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual3.q.out index 180787b..b1850b6 100644 --- a/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual3.q.out +++ b/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual3.q.out @@ -81,12 +81,16 @@ STAGE PLANS: Filter Operator predicate: p_name is not null (type: boolean) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE -Reduce Output Operator - key expressions: p_name (type: string) - sort order: + - Map-reduce partition columns: p_name (type: string) +Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: p_partkey (type: int), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + Reduce Output Operator +key expressions: _col1 (type: string) +sort order: + +Map-reduce partition columns: _col1 (type: string) +Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE +value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Map 3 Map Operator Tree: TableScan @@ -95,12 +99,16 @@ STAGE PLANS: Filter Operator predicate: p2_name is not null (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE -Reduce Output Operator - key expressions: p2_name (type: string) - sort order: + - Map-reduce partition columns: p2_name (type: string) +Select Operator + expressions: p2_partkey (type: int), p2_name (type: string), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: p2_partkey (type: int), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) + Reduce Output Operator +key expressions: _col1 (type: string) +sort order: + +Map-reduce partition columns: _col1 (type: string) +Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE +value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Map 4 Map Operator Tree: TableScan @@ -109,12 +117,16 @@ STAGE PLANS: Filter Operator predicate: p3_name is not null (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE -Reduce Output Operator - key expressions: p3_name (type: string) - sort order: + - Map-reduce partition columns: p3_name (type: string) +Select Operator + expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) +
[64/91] [abbrv] hive git commit: HIVE-12331 : Remove hive.enforce.bucketing & hive.enforce.sorting configs (Ashutosh Chauhan via Jason Dere)
http://git-wip-us.apache.org/repos/asf/hive/blob/5562fae7/ql/src/test/results/clientpositive/spark/smb_mapjoin_12.q.out -- diff --git a/ql/src/test/results/clientpositive/spark/smb_mapjoin_12.q.out b/ql/src/test/results/clientpositive/spark/smb_mapjoin_12.q.out index eeb18b0..93a7ca4 100644 --- a/ql/src/test/results/clientpositive/spark/smb_mapjoin_12.q.out +++ b/ql/src/test/results/clientpositive/spark/smb_mapjoin_12.q.out @@ -139,6 +139,8 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Spark + Edges: +Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1) A masked pattern was here Vertices: Map 1 @@ -165,37 +167,14 @@ STAGE PLANS: expressions: _col0 (type: int), _col7 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 825 Data size: 8764 Basic stats: COMPLETE Column stats: NONE -File Output Operator - compressed: false - GlobalTableId: 1 - A masked pattern was here - NumFilesPerFileSink: 1 - Static Partition Specification: ds=1/ +Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 825 Data size: 8764 Basic stats: COMPLETE Column stats: NONE - A masked pattern was here - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: -SORTBUCKETCOLSPREFIX TRUE -bucket_count 16 -bucket_field_name key -columns key,value -columns.comments -columns.types int:string - A masked pattern was here -name default.test_table3 -partition_columns ds -partition_columns.types string -serialization.ddl struct test_table3 { i32 key, string value} -serialization.format 1 -serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - A masked pattern was here - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.test_table3 - TotalFiles: 1 - GatherStats: true - MultiFileSpray: false + tag: -1 + value expressions: _col1 (type: string) + auto parallelism: false Path -> Alias: A masked pattern was here Path -> Partition: @@ -249,6 +228,44 @@ STAGE PLANS: name: default.test_table1 Truncated Path -> Alias: /test_table1/ds=1 [a] +Reducer 2 +Needs Tagging: false +Reduce Operator Tree: + Select Operator +expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) +outputColumnNames: _col0, _col1 +Statistics: Num rows: 825 Data size: 8764 Basic stats: COMPLETE Column stats: NONE +File Output Operator + compressed: false + GlobalTableId: 1 + A masked pattern was here + NumFilesPerFileSink: 16 + Static Partition Specification: ds=1/ + Statistics: Num rows: 825 Data size: 8764 Basic stats: COMPLETE Column stats: NONE + A masked pattern was here + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: +SORTBUCKETCOLSPREFIX TRUE +bucket_count 16 +bucket_field_name key +columns key,value +columns.comments +columns.types int:string + A masked pattern was here +name default.test_table3 +partition_columns ds +partition_columns.types string +serialization.ddl struct test_table3 { i32 key, string value} +
[50/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/auto_join26.q.out -- diff --git a/ql/src/test/results/clientpositive/auto_join26.q.out b/ql/src/test/results/clientpositive/auto_join26.q.out index 94ab76f..5f9531b 100644 --- a/ql/src/test/results/clientpositive/auto_join26.q.out +++ b/ql/src/test/results/clientpositive/auto_join26.q.out @@ -28,11 +28,11 @@ STAGE PLANS: Stage: Stage-6 Map Reduce Local Work Alias -> Map Local Tables: -$hdt$_0:$hdt$_1:x +$hdt$_0:$hdt$_0:x Fetch Operator limit: -1 Alias -> Map Local Operator Tree: -$hdt$_0:$hdt$_1:x +$hdt$_0:$hdt$_0:x TableScan alias: x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -67,24 +67,20 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col1 + outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator -expressions: _col1 (type: string) -outputColumnNames: _col0 + Group By Operator +aggregations: count(1) +keys: _col0 (type: string) +mode: hash +outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE -Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 +Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator -key expressions: _col0 (type: string) -sort order: + -Map-reduce partition columns: _col0 (type: string) -Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE -value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/auto_join32.q.out -- diff --git a/ql/src/test/results/clientpositive/auto_join32.q.out b/ql/src/test/results/clientpositive/auto_join32.q.out index 161ab6b..9b32047 100644 --- a/ql/src/test/results/clientpositive/auto_join32.q.out +++ b/ql/src/test/results/clientpositive/auto_join32.q.out @@ -35,21 +35,25 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: -s +$hdt$_0:s Fetch Operator limit: -1 Alias -> Map Local Operator Tree: -s +$hdt$_0:s TableScan alias: s Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: name is not null (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - HashTable Sink Operator -keys: - 0 name (type: string) - 1 name (type: string) + Select Operator +expressions: name (type: string) +outputColumnNames: _col0 +Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE +HashTable Sink Operator + keys: +0 _col0 (type: string) +1 _col0 (type: string) Stage: Stage-2 Map Reduce @@ -60,25 +64,29 @@ STAGE PLANS: Filter Operator predicate: name is not null (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Map Join Operator -condition map: - Inner Join 0 to 1 -keys: - 0 name (type: string) - 1 name (type: string) -outputColumnNames: _col0, _col8 + Select Operator +expressions: name (type: string), registration (type: string) +outputColumnNames: _col0,
[13/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/smb_mapjoin_25.q.out -- diff --git a/ql/src/test/results/clientpositive/smb_mapjoin_25.q.out b/ql/src/test/results/clientpositive/smb_mapjoin_25.q.out index c0a8959..441338e 100644 --- a/ql/src/test/results/clientpositive/smb_mapjoin_25.q.out +++ b/ql/src/test/results/clientpositive/smb_mapjoin_25.q.out @@ -46,6 +46,9 @@ POSTHOOK: query: load data local inpath '../../data/files/smbbucket_3.rc' overwr POSTHOOK: type: LOAD A masked pattern was here POSTHOOK: Output: default@smb_bucket_3 +Warning: Shuffle Join JOIN[27][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[9][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[22][tables = [$hdt$_1, $hdt$_2]] in Stage 'Stage-4:MAPRED' is a cross product PREHOOK: query: explain select * from (select a.key from smb_bucket_1 a join smb_bucket_2 b on (a.key = b.key) where a.key = 5) t1 left outer join (select c.key from smb_bucket_2 c join smb_bucket_3 d on (c.key = d.key) where c.key=5) t2 on (t1.key=t2.key) where t2.key=5 PREHOOK: type: QUERY @@ -68,123 +71,107 @@ STAGE PLANS: Filter Operator predicate: (key = 5) (type: boolean) Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator -key expressions: 5 (type: int) -sort order: + -Map-reduce partition columns: 5 (type: int) + Select Operator Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: NONE +Reduce Output Operator + sort order: + Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: NONE TableScan alias: b Statistics: Num rows: 51 Data size: 206 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key = 5) (type: boolean) + predicate: (5 = key) (type: boolean) Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator -key expressions: 5 (type: int) -sort order: + -Map-reduce partition columns: 5 (type: int) + Select Operator Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: NONE +Reduce Output Operator + sort order: + Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: -0 key (type: int) -1 key (type: int) +0 +1 Statistics: Num rows: 28 Data size: 114 Basic stats: COMPLETE Column stats: NONE - Select Operator -expressions: 5 (type: int) -outputColumnNames: _col0 -Statistics: Num rows: 28 Data size: 114 Basic stats: COMPLETE Column stats: NONE -File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator +compressed: false +table: +input format: org.apache.hadoop.mapred.SequenceFileInputFormat +output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat +serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) + sort order: Statistics: Num rows: 28 Data size: 114 Basic stats: COMPLETE Column stats: NONE TableScan Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) + sort order: Statistics: Num rows: 29 Data size: 118 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: - Left Outer Join0 to 1 + Inner Join 0 to 1 keys: -0 _col0 (type: int) -1 _col0 (type: int) -
[63/91] [abbrv] hive git commit: HIVE-9599 : remove derby, datanucleus and other not related to jdbc client classes from hive-jdbc-standalone.jar (Ashutosh Chauhan via Thejas Nair)
HIVE-9599 : remove derby, datanucleus and other not related to jdbc client classes from hive-jdbc-standalone.jar (Ashutosh Chauhan via Thejas Nair) Signed-off-by: Ashutosh ChauhanProject: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/1b6600de Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/1b6600de Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/1b6600de Branch: refs/heads/spark Commit: 1b6600de0f908170061628a6b5ed4f072012cc96 Parents: b7281ce Author: Ashutosh Chauhan Authored: Wed Nov 18 15:00:30 2015 -0800 Committer: Ashutosh Chauhan Committed: Tue Nov 24 15:06:23 2015 -0800 -- jdbc/pom.xml | 52 1 file changed, 52 insertions(+) -- http://git-wip-us.apache.org/repos/asf/hive/blob/1b6600de/jdbc/pom.xml -- diff --git a/jdbc/pom.xml b/jdbc/pom.xml index ea961a4..f8d7dfd 100644 --- a/jdbc/pom.xml +++ b/jdbc/pom.xml @@ -189,6 +189,58 @@ org.antlr:* org.slf4j:slf4j-log4j12 log4j:* + antlr:* + aopalliance:* + asm:* + com.google.code.gson:* + com.google.inject:* + com.google.inject.extensions:* + com.jamesmurty.utils:* + com.jcraft:* + com.jolbox:* + commons-beanutils:* + commons-cli:* + commons-dbcp:* + commons-digester:* + commons-el:* + commons-httpclient:* + commons-io:* + commons-net:* + commons-pool:* + com.google.code.findbugs:* + com.google.protobuf:* + com.sun.xml.bind:* + com.thoughtworks.paranamer:* + com.twitter:* + io.netty:* + javax.activation:* + javax.inject:* + javax.jdo:* + javax.mail:* + javax.servlet:* + javax.servlet.jsp:* + javax.transaction:* + javax.xml.bind:* + javax.xml.stream:* + jline:* + joda-time:* + net.java.dev.jets3t:* + org.apache.commons:commons-math3 + org.apache.curator:* + org.apache.derby:* + org.apache.directory.api:* + org.apache.directory.server:* + org.apache.geronimo.specs:* + org.apache.zookeeper:* + org.codehaus.jackson:* + org.codehaus.jettison:* + org.datanucleus:* + org.fusesource.leveldbjni:* + org.htrace:* + org.mortbay.jetty:* + org.xerial.snappy:* + tomcat:* + xmlenc:*
[12/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/spark/auto_join_stats.q.out -- diff --git a/ql/src/test/results/clientpositive/spark/auto_join_stats.q.out b/ql/src/test/results/clientpositive/spark/auto_join_stats.q.out index d72b4f3..71fe68e 100644 --- a/ql/src/test/results/clientpositive/spark/auto_join_stats.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_join_stats.q.out @@ -50,10 +50,14 @@ STAGE PLANS: Filter Operator predicate: UDFToDouble(key) is not null (type: boolean) Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE -Spark HashTable Sink Operator - keys: -0 (_col0 + _col5) (type: double) -1 UDFToDouble(key) (type: double) +Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator +keys: + 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) + 1 UDFToDouble(_col0) (type: double) Local Work: Map Reduce Local Work @@ -71,24 +75,32 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE -Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) +Select Operator + expressions: key (type: string) + outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator +key expressions: _col0 (type: string) +sort order: + +Map-reduce partition columns: _col0 (type: string) +Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map 3 Map Operator Tree: TableScan - alias: src2 + alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE -Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) +Select Operator + expressions: key (type: string) + outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator +key expressions: _col0 (type: string) +sort order: + +Map-reduce partition columns: _col0 (type: string) +Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reducer 2 Local Work: Map Reduce Local Work @@ -97,34 +109,30 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 key (type: string) - 1 key (type: string) -outputColumnNames: _col0, _col5 + 0 _col0 (type: string) + 1 _col0 (type: string) +outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col0 + _col5) is not null (type: boolean) + predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean) Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 (_col0 + _col5) (type: double) - 1 UDFToDouble(key) (type: double) -outputColumnNames: _col0, _col5, _col10 + 0 (UDFToDouble(_col0)
[20/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/multiMapJoin2.q.out -- diff --git a/ql/src/test/results/clientpositive/multiMapJoin2.q.out b/ql/src/test/results/clientpositive/multiMapJoin2.q.out index 46b717f..dee81c2 100644 --- a/ql/src/test/results/clientpositive/multiMapJoin2.q.out +++ b/ql/src/test/results/clientpositive/multiMapJoin2.q.out @@ -2079,21 +2079,25 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: -y +$hdt$_1:y Fetch Operator limit: -1 Alias -> Map Local Operator Tree: -y +$hdt$_1:y TableScan alias: y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator -keys: - 0 key (type: string) - 1 key (type: string) + Select Operator +expressions: key (type: string) +outputColumnNames: _col0 +Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE +HashTable Sink Operator + keys: +0 _col0 (type: string) +1 _col0 (type: string) Stage: Stage-2 Map Reduce @@ -2104,22 +2108,26 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 63 Data size: 635 Basic stats: COMPLETE Column stats: NONE - Map Join Operator -condition map: - Inner Join 0 to 1 -keys: - 0 key (type: string) - 1 key (type: string) -Statistics: Num rows: 69 Data size: 698 Basic stats: COMPLETE Column stats: NONE -Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator -sort order: + Select Operator +expressions: key (type: string) +outputColumnNames: _col0 +Statistics: Num rows: 63 Data size: 635 Basic stats: COMPLETE Column stats: NONE +Map Join Operator + condition map: + Inner Join 0 to 1 + keys: +0 _col0 (type: string) +1 _col0 (type: string) + Statistics: Num rows: 69 Data size: 698 Basic stats: COMPLETE Column stats: NONE + Group By Operator +aggregations: count() +mode: hash +outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE -value expressions: _col0 (type: bigint) +Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/multi_join_union.q.out -- diff --git a/ql/src/test/results/clientpositive/multi_join_union.q.out b/ql/src/test/results/clientpositive/multi_join_union.q.out index 466f34b..76c837f 100644 --- a/ql/src/test/results/clientpositive/multi_join_union.q.out +++ b/ql/src/test/results/clientpositive/multi_join_union.q.out @@ -53,36 +53,40 @@ src12 b ON (a.key = b.key) JOIN (SELECT * FROM (SELECT * FROM src13 UNION ALL SELECT * FROM src14)a )c ON c.value = b.value POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-7 is a root stage - Stage-5 depends on stages: Stage-7 - Stage-0 depends on stages: Stage-5 + Stage-8 is a root stage + Stage-6 depends on stages: Stage-8 + Stage-0 depends on stages: Stage-6 STAGE PLANS: - Stage: Stage-7 + Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: -a +$hdt$_0:a Fetch Operator limit: -1 -c-subquery1:a-subquery1:src13 +$hdt$_2-subquery1:$hdt$_2-subquery1:src13 Fetch Operator limit: -1 -c-subquery2:a-subquery2:src14 +$hdt$_2-subquery2:$hdt$_2-subquery2:src14 Fetch Operator limit: -1
[47/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/auto_sortmerge_join_6.q.out -- diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_6.q.out b/ql/src/test/results/clientpositive/auto_sortmerge_join_6.q.out index 853f641..0c8aa21 100644 --- a/ql/src/test/results/clientpositive/auto_sortmerge_join_6.q.out +++ b/ql/src/test/results/clientpositive/auto_sortmerge_join_6.q.out @@ -103,35 +103,43 @@ STAGE PLANS: Filter Operator predicate: (key is not null and value is not null) (type: boolean) Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator -condition map: - Inner Join 0 to 1 -keys: - 0 key (type: int) - 1 key (type: int) -outputColumnNames: _col1 -Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) + Select Operator +expressions: key (type: int), value (type: string) +outputColumnNames: _col0, _col1 +Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE +Sorted Merge Bucket Map Join Operator + condition map: + Inner Join 0 to 1 + keys: +0 _col0 (type: int) +1 _col0 (type: int) + outputColumnNames: _col1 + Reduce Output Operator +key expressions: _col1 (type: string) +sort order: + +Map-reduce partition columns: _col1 (type: string) TableScan alias: c Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: value is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator -key expressions: value (type: string) -sort order: + -Map-reduce partition columns: value (type: string) + Select Operator +expressions: value (type: string) +outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE +Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: 0 _col1 (type: string) -1 value (type: string) +1 _col0 (type: string) Group By Operator aggregations: count() mode: hash @@ -206,35 +214,43 @@ STAGE PLANS: Filter Operator predicate: (key is not null and value is not null) (type: boolean) Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator -condition map: - Inner Join 0 to 1 -keys: - 0 key (type: int) - 1 key (type: int) -outputColumnNames: _col1 -Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) + Select Operator +expressions: key (type: int), value (type: string) +outputColumnNames: _col0, _col1 +Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE +Sorted Merge Bucket Map Join Operator + condition map: + Inner Join 0 to 1 + keys: +0 _col0 (type: int) +1 _col0 (type: int) + outputColumnNames: _col1 + Reduce Output Operator +key expressions: _col1 (type: string) +sort order: + +Map-reduce partition columns: _col1 (type: string) TableScan alias: d Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: value is not null (type:
[89/91] [abbrv] hive git commit: HIVE-12338: Add webui to HiveServer2 (Jimmy, reviewed by Mohit, Szehon, Lefty)
HIVE-12338: Add webui to HiveServer2 (Jimmy, reviewed by Mohit, Szehon, Lefty) Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/2c0c191c Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/2c0c191c Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/2c0c191c Branch: refs/heads/spark Commit: 2c0c191cdd6b2d1aebe4502e24cc2b3d041bf3ca Parents: a51e5d4 Author: Jimmy XiangAuthored: Thu Nov 19 08:10:29 2015 -0800 Committer: Jimmy Xiang Committed: Sun Nov 29 09:55:09 2015 -0800 -- common/pom.xml | 5 + .../org/apache/hadoop/hive/conf/HiveConf.java | 5 + .../hive/http/AdminAuthorizedServlet.java | 45 ++ .../java/org/apache/hive/http/ConfServlet.java | 101 + .../java/org/apache/hive/http/HttpServer.java | 316 ++ .../org/apache/hive/http/JMXJsonServlet.java| 412 +++ pom.xml | 1 + ql/pom.xml | 6 + service/pom.xml | 56 +++ .../hive/service/cli/operation/Operation.java | 2 +- .../service/cli/operation/OperationManager.java | 26 +- .../service/cli/operation/SQLOperation.java | 8 +- .../service/cli/session/HiveSessionBase.java| 4 + .../service/cli/session/HiveSessionImpl.java| 12 + .../service/cli/session/SessionManager.java | 16 +- .../apache/hive/service/server/HiveServer2.java | 47 +++ .../hive-webapps/hiveserver2/hiveserver2.jsp| 186 + .../hive-webapps/hiveserver2/index.html | 20 + .../static/css/bootstrap-theme.min.css | 10 + .../hive-webapps/static/css/bootstrap.min.css | 9 + .../resources/hive-webapps/static/css/hive.css | 24 ++ .../fonts/glyphicons-halflings-regular.eot | Bin 0 -> 14079 bytes .../fonts/glyphicons-halflings-regular.svg | 228 ++ .../fonts/glyphicons-halflings-regular.ttf | Bin 0 -> 29512 bytes .../fonts/glyphicons-halflings-regular.woff | Bin 0 -> 16448 bytes .../hive-webapps/static/hive_logo.jpeg | Bin 0 -> 5616 bytes spark-client/pom.xml| 6 + 27 files changed, 1529 insertions(+), 16 deletions(-) -- http://git-wip-us.apache.org/repos/asf/hive/blob/2c0c191c/common/pom.xml -- diff --git a/common/pom.xml b/common/pom.xml index ee74282..72bb550 100644 --- a/common/pom.xml +++ b/common/pom.xml @@ -56,6 +56,11 @@ ${commons-lang.version} + org.eclipse.jetty.aggregate + jetty-all + ${jetty.version} + + joda-time joda-time ${joda.version} http://git-wip-us.apache.org/repos/asf/hive/blob/2c0c191c/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java -- diff --git a/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java b/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java index db942b0..9e805bd 100644 --- a/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java +++ b/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java @@ -1847,6 +1847,11 @@ public class HiveConf extends Configuration { HIVE_SERVER2_PARALLEL_COMPILATION("hive.driver.parallel.compilation", false, "Whether to\n" + "enable parallel compilation between sessions on HiveServer2. The default is false."), +// HiveServer2 WebUI +HIVE_SERVER2_WEBUI_BIND_HOST("hive.server2.webui.host", "0.0.0.0", "The host address the HiveServer2 WebUI will listen on"), +HIVE_SERVER2_WEBUI_PORT("hive.server2.webui.port", 10002, "The port the HiveServer2 WebUI will listen on"), +HIVE_SERVER2_WEBUI_MAX_THREADS("hive.server2.webui.max.threads", 50, "The max HiveServer2 WebUI threads"), + // Tez session settings HIVE_SERVER2_TEZ_DEFAULT_QUEUES("hive.server2.tez.default.queues", "", "A list of comma separated values corresponding to YARN queues of the same name.\n" + http://git-wip-us.apache.org/repos/asf/hive/blob/2c0c191c/common/src/java/org/apache/hive/http/AdminAuthorizedServlet.java -- diff --git a/common/src/java/org/apache/hive/http/AdminAuthorizedServlet.java b/common/src/java/org/apache/hive/http/AdminAuthorizedServlet.java new file mode 100644 index 000..5d957c2 --- /dev/null +++ b/common/src/java/org/apache/hive/http/AdminAuthorizedServlet.java @@ -0,0 +1,45 @@ +/** + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + *
[56/91] [abbrv] hive git commit: HIVE-12456: QueryId can't be stored in the configuration of the SessionState since multiple queries can run in a single session (Aihua Xu, reviewed by Mohit)
HIVE-12456: QueryId can't be stored in the configuration of the SessionState since multiple queries can run in a single session (Aihua Xu, reviewed by Mohit) Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/2604cf26 Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/2604cf26 Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/2604cf26 Branch: refs/heads/spark Commit: 2604cf26ae36c4211bf155e2032398cc7344f641 Parents: f90d798 Author: Aihua XuAuthored: Mon Nov 23 12:20:39 2015 -0500 Committer: Aihua Xu Committed: Mon Nov 23 12:20:39 2015 -0500 -- .../cli/operation/ExecuteStatementOperation.java | 15 +-- .../hive/service/cli/operation/Operation.java| 19 +++ .../hive/service/cli/operation/SQLOperation.java | 4 ++-- .../service/cli/session/HiveSessionImpl.java | 1 - 4 files changed, 18 insertions(+), 21 deletions(-) -- http://git-wip-us.apache.org/repos/asf/hive/blob/2604cf26/service/src/java/org/apache/hive/service/cli/operation/ExecuteStatementOperation.java -- diff --git a/service/src/java/org/apache/hive/service/cli/operation/ExecuteStatementOperation.java b/service/src/java/org/apache/hive/service/cli/operation/ExecuteStatementOperation.java index 3f2de10..b3d9b52 100644 --- a/service/src/java/org/apache/hive/service/cli/operation/ExecuteStatementOperation.java +++ b/service/src/java/org/apache/hive/service/cli/operation/ExecuteStatementOperation.java @@ -18,7 +18,6 @@ package org.apache.hive.service.cli.operation; import java.sql.SQLException; -import java.util.HashMap; import java.util.Map; import org.apache.hadoop.hive.ql.processors.CommandProcessor; @@ -29,13 +28,11 @@ import org.apache.hive.service.cli.session.HiveSession; public abstract class ExecuteStatementOperation extends Operation { protected String statement = null; - protected Map confOverlay = new HashMap (); public ExecuteStatementOperation(HiveSession parentSession, String statement, Map confOverlay, boolean runInBackground) { -super(parentSession, OperationType.EXECUTE_STATEMENT, runInBackground); +super(parentSession, confOverlay, OperationType.EXECUTE_STATEMENT, runInBackground); this.statement = statement; -setConfOverlay(confOverlay); } public String getStatement() { @@ -57,14 +54,4 @@ public abstract class ExecuteStatementOperation extends Operation { } return new HiveCommandOperation(parentSession, statement, processor, confOverlay); } - - protected Map getConfOverlay() { -return confOverlay; - } - - protected void setConfOverlay(Map confOverlay) { -if (confOverlay != null) { - this.confOverlay = confOverlay; -} - } } http://git-wip-us.apache.org/repos/asf/hive/blob/2604cf26/service/src/java/org/apache/hive/service/cli/operation/Operation.java -- diff --git a/service/src/java/org/apache/hive/service/cli/operation/Operation.java b/service/src/java/org/apache/hive/service/cli/operation/Operation.java index d13415e..25cefc2 100644 --- a/service/src/java/org/apache/hive/service/cli/operation/Operation.java +++ b/service/src/java/org/apache/hive/service/cli/operation/Operation.java @@ -21,11 +21,14 @@ import java.io.File; import java.io.FileNotFoundException; import java.io.IOException; import java.util.EnumSet; +import java.util.HashMap; +import java.util.Map; import java.util.Set; import java.util.concurrent.Future; import java.util.concurrent.TimeUnit; import com.google.common.collect.Sets; + import org.apache.hadoop.hive.common.metrics.common.Metrics; import org.apache.hadoop.hive.common.metrics.common.MetricsConstant; import org.apache.hadoop.hive.common.metrics.common.MetricsFactory; @@ -50,8 +53,8 @@ import org.apache.logging.log4j.ThreadContext; public abstract class Operation { // Constants of the key strings for the log4j ThreadContext. - private static final String QUERYID = "QueryId"; - private static final String SESSIONID = "SessionId"; + public static final String SESSIONID_LOG_KEY = "sessionId"; + public static final String QUERYID_LOG_KEY = "queryId"; protected final HiveSession parentSession; private OperationState state = OperationState.INITIALIZED; @@ -67,6 +70,7 @@ public abstract class Operation { protected volatile Future backgroundHandle; protected OperationLog operationLog; protected boolean isOperationLogEnabled; + protected Map confOverlay = new HashMap (); private long operationTimeout; private long lastAccessTime; @@ -75,7
[55/91] [abbrv] hive git commit: HIVE-12409 make sure SessionState.initTxnMgr() is thread safe (Eugene Koifman, reviewed by Jason Dere)
HIVE-12409 make sure SessionState.initTxnMgr() is thread safe (Eugene Koifman, reviewed by Jason Dere) Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/f90d798e Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/f90d798e Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/f90d798e Branch: refs/heads/spark Commit: f90d798e830d56745c8bc0cfee35741ed66aab90 Parents: 695d905 Author: Eugene KoifmanAuthored: Mon Nov 23 08:20:06 2015 -0800 Committer: Eugene Koifman Committed: Mon Nov 23 08:20:06 2015 -0800 -- ql/src/java/org/apache/hadoop/hive/ql/session/SessionState.java | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) -- http://git-wip-us.apache.org/repos/asf/hive/blob/f90d798e/ql/src/java/org/apache/hadoop/hive/ql/session/SessionState.java -- diff --git a/ql/src/java/org/apache/hadoop/hive/ql/session/SessionState.java b/ql/src/java/org/apache/hadoop/hive/ql/session/SessionState.java index ff875df..5c69fb6 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/session/SessionState.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/session/SessionState.java @@ -400,7 +400,7 @@ public class SessionState { * @return transaction manager * @throws LockException */ - public HiveTxnManager initTxnMgr(HiveConf conf) throws LockException { + public synchronized HiveTxnManager initTxnMgr(HiveConf conf) throws LockException { if (txnMgr == null) { txnMgr = TxnManagerFactory.getTxnManagerFactory().getTxnManager(conf); }
[86/91] [abbrv] hive git commit: HIVE-12008: Hive queries failing when using count(*) on column in view (Yongzhi Chen, reviewed by Szehon ho)
HIVE-12008: Hive queries failing when using count(*) on column in view (Yongzhi Chen, reviewed by Szehon ho) Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/a51e5d4e Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/a51e5d4e Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/a51e5d4e Branch: refs/heads/spark Commit: a51e5d4e261d6eb334497f768059829e36a99fd3 Parents: 7984738 Author: Yongzhi ChenAuthored: Sun Nov 29 01:06:22 2015 -0500 Committer: Yongzhi Chen Committed: Sun Nov 29 01:06:22 2015 -0500 -- .../hadoop/hive/ql/exec/UnionOperator.java | 8 +- .../hive/ql/optimizer/ColumnPrunerProcCtx.java | 2 +- .../clientpositive/unionall_unbalancedppd.q | 57 ++- .../results/clientpositive/spark/union16.q.out | 16 +- .../results/clientpositive/spark/union2.q.out | 16 +- .../results/clientpositive/spark/union9.q.out | 16 +- .../clientpositive/spark/union_view.q.out | 24 -- .../results/clientpositive/tez/union2.q.out | 28 +- .../results/clientpositive/tez/union9.q.out | 40 +-- .../tez/vector_null_projection.q.out| 4 - .../test/results/clientpositive/union16.q.out | 354 --- ql/src/test/results/clientpositive/union2.q.out | 32 +- ql/src/test/results/clientpositive/union9.q.out | 46 ++- .../results/clientpositive/union_view.q.out | 24 -- .../clientpositive/unionall_unbalancedppd.q.out | 261 +++--- .../clientpositive/vector_null_projection.q.out | 4 - 16 files changed, 388 insertions(+), 544 deletions(-) -- http://git-wip-us.apache.org/repos/asf/hive/blob/a51e5d4e/ql/src/java/org/apache/hadoop/hive/ql/exec/UnionOperator.java -- diff --git a/ql/src/java/org/apache/hadoop/hive/ql/exec/UnionOperator.java b/ql/src/java/org/apache/hadoop/hive/ql/exec/UnionOperator.java index a49097c..ddb23ee 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/exec/UnionOperator.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/exec/UnionOperator.java @@ -62,13 +62,16 @@ public class UnionOperator extends Operator implements Serializable { int parents = parentOperators.size(); parentObjInspectors = new StructObjectInspector[parents]; parentFields = new List[parents]; +int columns = 0; for (int p = 0; p < parents; p++) { parentObjInspectors[p] = (StructObjectInspector) inputObjInspectors[p]; parentFields[p] = parentObjInspectors[p].getAllStructFieldRefs(); + if (p == 0 || parentFields[p].size() < columns) { +columns = parentFields[p].size(); + } } // Get columnNames from the first parent -int columns = parentFields[0].size(); ArrayList columnNames = new ArrayList(columns); for (int c = 0; c < columns; c++) { columnNames.add(parentFields[0].get(c).getFieldName()); @@ -81,7 +84,8 @@ public class UnionOperator extends Operator implements Serializable { } for (int p = 0; p < parents; p++) { - assert (parentFields[p].size() == columns); + //When columns is 0, the union operator is empty. + assert (columns == 0 || parentFields[p].size() == columns); for (int c = 0; c < columns; c++) { if (!columnTypeResolvers[c].updateForUnionAll(parentFields[p].get(c) .getFieldObjectInspector())) { http://git-wip-us.apache.org/repos/asf/hive/blob/a51e5d4e/ql/src/java/org/apache/hadoop/hive/ql/optimizer/ColumnPrunerProcCtx.java -- diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/ColumnPrunerProcCtx.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/ColumnPrunerProcCtx.java index b18a034..7befd3b 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/ColumnPrunerProcCtx.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/ColumnPrunerProcCtx.java @@ -108,7 +108,7 @@ public class ColumnPrunerProcCtx implements NodeProcessorCtx { prunList = joinPrunedColLists.get(child).get((byte) tag); } else if (child instanceof UnionOperator) { List positions = unionPrunedColLists.get(child); -if (positions != null && positions.size() > 0) { +if (positions != null) { prunList = new ArrayList<>(); RowSchema oldRS = curOp.getSchema(); for (Integer pos : positions) { http://git-wip-us.apache.org/repos/asf/hive/blob/a51e5d4e/ql/src/test/queries/clientpositive/unionall_unbalancedppd.q -- diff --git a/ql/src/test/queries/clientpositive/unionall_unbalancedppd.q b/ql/src/test/queries/clientpositive/unionall_unbalancedppd.q index 360ad11..a704860 100644 ---
[05/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/spark/groupby_sort_1_23.q.out -- diff --git a/ql/src/test/results/clientpositive/spark/groupby_sort_1_23.q.out b/ql/src/test/results/clientpositive/spark/groupby_sort_1_23.q.out index 8d3f0d8..6c57ff2 100644 --- a/ql/src/test/results/clientpositive/spark/groupby_sort_1_23.q.out +++ b/ql/src/test/results/clientpositive/spark/groupby_sort_1_23.q.out @@ -2748,20 +2748,24 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE -Group By Operator - aggregations: count(1) - keys: key (type: string) - mode: final - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator -key expressions: _col0 (type: string) -sort order: + -Map-reduce partition columns: _col0 (type: string) +Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Group By Operator +aggregations: count(1) +keys: _col0 (type: string) +mode: final +outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE -tag: 0 -value expressions: _col1 (type: bigint) -auto parallelism: false +Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + tag: 0 + value expressions: _col1 (type: bigint) + auto parallelism: false Path -> Alias: A masked pattern was here Path -> Partition: @@ -2825,20 +2829,24 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE -Group By Operator - aggregations: count(1) - keys: key (type: string) - mode: final - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator -key expressions: _col0 (type: string) -sort order: + -Map-reduce partition columns: _col0 (type: string) +Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Group By Operator +aggregations: count(1) +keys: _col0 (type: string) +mode: final +outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE -tag: 1 -value expressions: _col1 (type: bigint) -auto parallelism: false +Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + tag: 1 + value expressions: _col1 (type: bigint) + auto parallelism: false Path -> Alias: A masked pattern was here Path -> Partition: @@ -3113,20 +3121,24 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE -
[82/91] [abbrv] hive git commit: HIVE-12496 : Open ServerTransport After MetaStore Initialization (Nemon Lou via Ashutosh Chauhan)
HIVE-12496 : Open ServerTransport After MetaStore Initialization (Nemon Lou via Ashutosh Chauhan) Signed-off-by: Ashutosh ChauhanProject: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/6d4dfa40 Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/6d4dfa40 Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/6d4dfa40 Branch: refs/heads/spark Commit: 6d4dfa40bc6a70c7b4d7de0241b1868937d66b00 Parents: a9d3b09 Author: Nemon Lou Authored: Thu Nov 26 11:44:34 2015 -0800 Committer: Ashutosh Chauhan Committed: Thu Nov 26 11:44:34 2015 -0800 -- .../java/org/apache/hadoop/hive/metastore/HiveMetaStore.java| 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) -- http://git-wip-us.apache.org/repos/asf/hive/blob/6d4dfa40/metastore/src/java/org/apache/hadoop/hive/metastore/HiveMetaStore.java -- diff --git a/metastore/src/java/org/apache/hadoop/hive/metastore/HiveMetaStore.java b/metastore/src/java/org/apache/hadoop/hive/metastore/HiveMetaStore.java index a835f6a..00602e1 100644 --- a/metastore/src/java/org/apache/hadoop/hive/metastore/HiveMetaStore.java +++ b/metastore/src/java/org/apache/hadoop/hive/metastore/HiveMetaStore.java @@ -5978,8 +5978,6 @@ public class HiveMetaStore extends ThriftHiveMetastore { boolean useCompactProtocol = conf.getBoolVar(ConfVars.METASTORE_USE_THRIFT_COMPACT_PROTOCOL); useSasl = conf.getBoolVar(HiveConf.ConfVars.METASTORE_USE_THRIFT_SASL); - TServerTransport serverTransport = tcpKeepAlive ? - new TServerSocketKeepAlive(port) : new TServerSocket(port); TProcessor processor; TTransportFactory transFactory; @@ -6027,6 +6025,9 @@ public class HiveMetaStore extends ThriftHiveMetastore { LOG.info("Starting DB backed MetaStore Server"); } } + + TServerTransport serverTransport = tcpKeepAlive ? +new TServerSocketKeepAlive(port) : new TServerSocket(port); TThreadPoolServer.Args args = new TThreadPoolServer.Args(serverTransport) .processor(processor)
[60/91] [abbrv] hive git commit: HIVE-12411: Remove counter based stats collection mechanism (Pengcheng Xiong, reviewed by Ashutosh Chauhan)
HIVE-12411: Remove counter based stats collection mechanism (Pengcheng Xiong, reviewed by Ashutosh Chauhan) Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/ab98ffc2 Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/ab98ffc2 Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/ab98ffc2 Branch: refs/heads/spark Commit: ab98ffc2688abbc75de13524ca46848e566354ef Parents: 306a640 Author: Pengcheng XiongAuthored: Tue Nov 24 17:09:40 2015 +0800 Committer: Pengcheng Xiong Committed: Tue Nov 24 17:09:40 2015 +0800 -- .../hadoop/hive/common/StatsSetupConst.java | 13 - .../org/apache/hadoop/hive/conf/HiveConf.java | 8 +- data/conf/llap/hive-site.xml| 2 +- data/conf/spark/standalone/hive-site.xml| 2 +- data/conf/spark/yarn-client/hive-site.xml | 2 +- data/conf/tez/hive-site.xml | 4 +- .../hive/ql/stats/CounterStatsAggregator.java | 82 .../ql/stats/CounterStatsAggregatorSpark.java | 58 --- .../ql/stats/CounterStatsAggregatorTez.java | 79 .../hive/ql/stats/CounterStatsPublisher.java| 66 --- .../hadoop/hive/ql/stats/StatsFactory.java | 11 - .../test/queries/clientpositive/index_bitmap3.q | 1 - .../queries/clientpositive/index_bitmap_auto.q | 1 - .../test/queries/clientpositive/stats_counter.q | 16 - .../clientpositive/stats_counter_partitioned.q | 45 -- .../clientpositive/llap/stats_counter.q.out | 102 .../llap/stats_counter_partitioned.q.out| 465 --- .../clientpositive/spark/stats_counter.q.out| 102 .../spark/stats_counter_partitioned.q.out | 465 --- .../results/clientpositive/stats_counter.q.out | 102 .../stats_counter_partitioned.q.out | 465 --- .../clientpositive/tez/metadataonly1.q.out | 72 +-- .../clientpositive/tez/optimize_nullscan.q.out | 90 ++-- .../clientpositive/tez/stats_counter.q.out | 102 .../tez/stats_counter_partitioned.q.out | 465 --- 25 files changed, 88 insertions(+), 2732 deletions(-) -- http://git-wip-us.apache.org/repos/asf/hive/blob/ab98ffc2/common/src/java/org/apache/hadoop/hive/common/StatsSetupConst.java -- diff --git a/common/src/java/org/apache/hadoop/hive/common/StatsSetupConst.java b/common/src/java/org/apache/hadoop/hive/common/StatsSetupConst.java index 0a44bde..2ff76ee 100644 --- a/common/src/java/org/apache/hadoop/hive/common/StatsSetupConst.java +++ b/common/src/java/org/apache/hadoop/hive/common/StatsSetupConst.java @@ -31,19 +31,6 @@ import java.util.Map; public class StatsSetupConst { public enum StatDB { -counter { - @Override - public String getPublisher(Configuration conf) { -return "org.apache.hadoop.hive.ql.stats.CounterStatsPublisher"; } - @Override - public String getAggregator(Configuration conf) { -if (HiveConf.getVar(conf, HiveConf.ConfVars.HIVE_EXECUTION_ENGINE).equals("tez")) { - return "org.apache.hadoop.hive.ql.stats.CounterStatsAggregatorTez"; -} else if (HiveConf.getVar(conf, HiveConf.ConfVars.HIVE_EXECUTION_ENGINE).equals("spark")) { - return "org.apache.hadoop.hive.ql.stats.CounterStatsAggregatorSpark"; -} -return "org.apache.hadoop.hive.ql.stats.CounterStatsAggregator"; } -}, fs { @Override public String getPublisher(Configuration conf) { http://git-wip-us.apache.org/repos/asf/hive/blob/ab98ffc2/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java -- diff --git a/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java b/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java index f48403b..fffedd9 100644 --- a/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java +++ b/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java @@ -1354,10 +1354,10 @@ public class HiveConf extends Configuration { // Statistics HIVESTATSAUTOGATHER("hive.stats.autogather", true, "A flag to gather statistics automatically during the INSERT OVERWRITE command."), -HIVESTATSDBCLASS("hive.stats.dbclass", "fs", new PatternSet("counter", "custom", "fs"), +HIVESTATSDBCLASS("hive.stats.dbclass", "fs", new PatternSet("custom", "fs"), "The storage that stores temporary Hive statistics. In filesystem based statistics collection ('fs'), \n" + "each task writes statistics it has collected in a file on the filesystem, which will be aggregated \n" + -"after the job has finished. Supported values are fs (filesystem), counter, and custom as defined in
[07/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/spark/bucketsortoptimize_insert_2.q.out -- diff --git a/ql/src/test/results/clientpositive/spark/bucketsortoptimize_insert_2.q.out b/ql/src/test/results/clientpositive/spark/bucketsortoptimize_insert_2.q.out index bcef03c..d8ade07 100644 --- a/ql/src/test/results/clientpositive/spark/bucketsortoptimize_insert_2.q.out +++ b/ql/src/test/results/clientpositive/spark/bucketsortoptimize_insert_2.q.out @@ -113,10 +113,14 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE -Spark HashTable Sink Operator - keys: -0 key (type: int) -1 key (type: int) +Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator +keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Local Work: Map Reduce Local Work @@ -134,26 +138,30 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 42 Data size: 368 Basic stats: COMPLETE Column stats: NONE -Map Join Operator - condition map: - Inner Join 0 to 1 - keys: -0 key (type: int) -1 key (type: int) - outputColumnNames: _col0, _col1, _col7 - input vertices: -0 Map 1 - Statistics: Num rows: 46 Data size: 404 Basic stats: COMPLETE Column stats: NONE - Select Operator -expressions: _col0 (type: int), concat(_col1, _col7) (type: string) -outputColumnNames: _col0, _col1 +Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 42 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Map Join Operator +condition map: + Inner Join 0 to 1 +keys: + 0 _col0 (type: int) + 1 _col0 (type: int) +outputColumnNames: _col0, _col1, _col4 +input vertices: + 0 Map 1 Statistics: Num rows: 46 Data size: 404 Basic stats: COMPLETE Column stats: NONE -Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) +Select Operator + expressions: _col0 (type: int), concat(_col1, _col4) (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 46 Data size: 404 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Reduce Output Operator +key expressions: _col0 (type: int) +sort order: + +Map-reduce partition columns: _col0 (type: int) +Statistics: Num rows: 46 Data size: 404 Basic stats: COMPLETE Column stats: NONE +value expressions: _col1 (type: string) Local Work: Map Reduce Local Work Reducer 3 @@ -285,10 +293,14 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE -Spark HashTable Sink Operator - keys: -0 key (type: int) -1 key (type: int) +Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator +
[26/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/llap/hybridgrace_hashjoin_1.q.out -- diff --git a/ql/src/test/results/clientpositive/llap/hybridgrace_hashjoin_1.q.out b/ql/src/test/results/clientpositive/llap/hybridgrace_hashjoin_1.q.out index 36a032a..3b634be 100644 --- a/ql/src/test/results/clientpositive/llap/hybridgrace_hashjoin_1.q.out +++ b/ql/src/test/results/clientpositive/llap/hybridgrace_hashjoin_1.q.out @@ -788,38 +788,46 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 263 Data size: 6248 Basic stats: COMPLETE Column stats: NONE -Map Join Operator - condition map: - Inner Join 0 to 1 - keys: -0 key (type: string) -1 key (type: string) - input vertices: -1 Map 3 - Statistics: Num rows: 289 Data size: 6872 Basic stats: COMPLETE Column stats: NONE - Group By Operator -aggregations: count() -mode: hash -outputColumnNames: _col0 -Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE -Reduce Output Operator - sort order: +Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 263 Data size: 6248 Basic stats: COMPLETE Column stats: NONE + Map Join Operator +condition map: + Inner Join 0 to 1 +keys: + 0 _col0 (type: string) + 1 _col0 (type: string) +input vertices: + 1 Map 3 +Statistics: Num rows: 289 Data size: 6872 Basic stats: COMPLETE Column stats: NONE +Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator +sort order: +Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +value expressions: _col0 (type: bigint) Execution mode: llap Map 3 Map Operator Tree: TableScan - alias: p2 + alias: p1 Statistics: Num rows: 525 Data size: 12474 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 263 Data size: 6248 Basic stats: COMPLETE Column stats: NONE -Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) +Select Operator + expressions: key (type: string) + outputColumnNames: _col0 Statistics: Num rows: 263 Data size: 6248 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator +key expressions: _col0 (type: string) +sort order: + +Map-reduce partition columns: _col0 (type: string) +Statistics: Num rows: 263 Data size: 6248 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Reducer 2 Execution mode: uber @@ -900,39 +908,47 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 263 Data size: 6248 Basic stats: COMPLETE Column stats: NONE -Map Join Operator - condition map: - Inner Join 0 to 1 - keys: -0 key (type: string) -1 key (type: string) - input vertices: -1 Map 3 - Statistics: Num rows: 289 Data size: 6872 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true - Group By Operator -
[78/91] [abbrv] hive git commit: HIVE-8396 : Hive CliDriver command splitting can be broken when comments are present (Elliot West, reviewed by Sergey Shelukhin)
HIVE-8396 : Hive CliDriver command splitting can be broken when comments are present (Elliot West, reviewed by Sergey Shelukhin) Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/0ae374a3 Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/0ae374a3 Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/0ae374a3 Branch: refs/heads/spark Commit: 0ae374a320d1cae523ba2b434800e97692507db8 Parents: 454c2ca Author: Sergey ShelukhinAuthored: Wed Nov 25 15:13:27 2015 -0800 Committer: Sergey Shelukhin Committed: Wed Nov 25 15:13:27 2015 -0800 -- cli/src/java/org/apache/hadoop/hive/cli/CliDriver.java | 3 +++ 1 file changed, 3 insertions(+) -- http://git-wip-us.apache.org/repos/asf/hive/blob/0ae374a3/cli/src/java/org/apache/hadoop/hive/cli/CliDriver.java -- diff --git a/cli/src/java/org/apache/hadoop/hive/cli/CliDriver.java b/cli/src/java/org/apache/hadoop/hive/cli/CliDriver.java index e04f247..e77b7f1 100644 --- a/cli/src/java/org/apache/hadoop/hive/cli/CliDriver.java +++ b/cli/src/java/org/apache/hadoop/hive/cli/CliDriver.java @@ -770,6 +770,9 @@ public class CliDriver { if (!prefix.equals("")) { prefix += '\n'; } + if (line.trim().startsWith("--")) { +continue; + } if (line.trim().endsWith(";") && !line.trim().endsWith("\\;")) { line = prefix + line; ret = cli.processLine(line, true);
[39/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/correlationoptimizer5.q.out -- diff --git a/ql/src/test/results/clientpositive/correlationoptimizer5.q.out b/ql/src/test/results/clientpositive/correlationoptimizer5.q.out index 7f2e19f..d33ca0f 100644 --- a/ql/src/test/results/clientpositive/correlationoptimizer5.q.out +++ b/ql/src/test/results/clientpositive/correlationoptimizer5.q.out @@ -125,29 +125,37 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 727 Data size: 2908 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator -key expressions: key (type: int) -sort order: + -Map-reduce partition columns: key (type: int) + Select Operator +expressions: key (type: int) +outputColumnNames: _col0 Statistics: Num rows: 727 Data size: 2908 Basic stats: COMPLETE Column stats: NONE +Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 727 Data size: 2908 Basic stats: COMPLETE Column stats: NONE TableScan alias: y Statistics: Num rows: 1447 Data size: 5791 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 724 Data size: 2897 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator -key expressions: key (type: int) -sort order: + -Map-reduce partition columns: key (type: int) + Select Operator +expressions: key (type: int) +outputColumnNames: _col0 Statistics: Num rows: 724 Data size: 2897 Basic stats: COMPLETE Column stats: NONE +Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 724 Data size: 2897 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: -0 key (type: int) -1 key (type: int) +0 _col0 (type: int) +1 _col0 (type: int) outputColumnNames: _col0 Statistics: Num rows: 799 Data size: 3198 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -180,10 +188,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0, _col3 + outputColumnNames: _col0, _col2 Statistics: Num rows: 878 Data size: 3517 Basic stats: COMPLETE Column stats: NONE Select Operator -expressions: _col0 (type: int), _col3 (type: string) +expressions: _col0 (type: int), _col2 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 878 Data size: 3517 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -217,34 +225,42 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 27 Data size: 108 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator -key expressions: key (type: int) -sort order: + -Map-reduce partition columns: key (type: int) + Select Operator +expressions: key (type: int) +outputColumnNames: _col0 Statistics: Num rows: 27 Data size: 108 Basic stats: COMPLETE Column stats: NONE +Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 27 Data size: 108 Basic stats: COMPLETE Column stats: NONE TableScan alias: n Statistics: Num rows: 2 Data size: 280 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 1 Data size: 140 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator -key expressions: key (type: int) -sort order: + -Map-reduce partition columns: key (type: int) + Select Operator +expressions: key (type: int),
[19/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/ppd_join5.q.out -- diff --git a/ql/src/test/results/clientpositive/ppd_join5.q.out b/ql/src/test/results/clientpositive/ppd_join5.q.out index 0807559..1b46ed5 100644 --- a/ql/src/test/results/clientpositive/ppd_join5.q.out +++ b/ql/src/test/results/clientpositive/ppd_join5.q.out @@ -32,7 +32,7 @@ POSTHOOK: Lineage: t1.id1 SIMPLE [] POSTHOOK: Lineage: t1.id2 SIMPLE [] POSTHOOK: Lineage: t2.d SIMPLE [] POSTHOOK: Lineage: t2.id SIMPLE [] -Warning: Shuffle Join JOIN[10][tables = [a, b, c]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[16][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: explain select a.*,b.d d1,c.d d2 from t1 a join t2 b on (a.id1 = b.id) @@ -58,31 +58,39 @@ STAGE PLANS: Filter Operator predicate: (id1 is not null and id2 is not null) (type: boolean) Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator -key expressions: id1 (type: string), id2 (type: string) -sort order: ++ -Map-reduce partition columns: id1 (type: string), id2 (type: string) + Select Operator +expressions: id1 (type: string), id2 (type: string) +outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE +Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE TableScan alias: b Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (id is not null and (d <= 1)) (type: boolean) + predicate: ((d <= 1) and id is not null) (type: boolean) Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator -key expressions: id (type: string), id (type: string) -sort order: ++ -Map-reduce partition columns: id (type: string), id (type: string) + Select Operator +expressions: id (type: string), d (type: int) +outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE -value expressions: d (type: int) +Reduce Output Operator + key expressions: _col0 (type: string), _col0 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col0 (type: string) + Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: -0 id1 (type: string), id2 (type: string) -1 id (type: string), id (type: string) - outputColumnNames: _col0, _col1, _col6 +0 _col0 (type: string), _col1 (type: string) +1 _col0 (type: string), _col0 (type: string) + outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -98,17 +106,21 @@ STAGE PLANS: Reduce Output Operator sort order: Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col6 (type: int) + value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: int) TableScan -alias: c +alias: b Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (d <= 1) (type: boolean) Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator -sort order: + Select Operator +expressions: d (type: int) +outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE -value expressions: d (type: int) +Reduce Output Operator + sort
[49/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/auto_sortmerge_join_1.q.out -- diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_1.q.out b/ql/src/test/results/clientpositive/auto_sortmerge_join_1.q.out index f1aadef..85a685b 100644 --- a/ql/src/test/results/clientpositive/auto_sortmerge_join_1.q.out +++ b/ql/src/test/results/clientpositive/auto_sortmerge_join_1.q.out @@ -157,23 +157,27 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator -condition map: - Inner Join 0 to 1 -keys: - 0 key (type: string) - 1 key (type: string) -Position of Big Table: 1 -BucketMapJoin: true -Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator -sort order: -tag: -1 -value expressions: _col0 (type: bigint) -auto parallelism: false + Select Operator +expressions: key (type: string) +outputColumnNames: _col0 +Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE +Sorted Merge Bucket Map Join Operator + condition map: + Inner Join 0 to 1 + keys: +0 _col0 (type: string) +1 _col0 (type: string) + Position of Big Table: 1 + BucketMapJoin: true + Group By Operator +aggregations: count() +mode: hash +outputColumnNames: _col0 +Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: A masked pattern was here Path -> Partition: @@ -274,8 +278,8 @@ STAGE PLANS: name: default.bucket_big name: default.bucket_big Truncated Path -> Alias: -/bucket_big/ds=2008-04-08 [b] -/bucket_big/ds=2008-04-09 [b] +/bucket_big/ds=2008-04-08 [$hdt$_1:b] +/bucket_big/ds=2008-04-09 [$hdt$_1:b] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -379,23 +383,27 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator -condition map: - Inner Join 0 to 1 -keys: - 0 key (type: string) - 1 key (type: string) -Position of Big Table: 0 -BucketMapJoin: true -Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator -sort order: -tag: -1 -value expressions: _col0 (type: bigint) -auto parallelism: false + Select Operator +expressions: key (type: string) +outputColumnNames: _col0 +Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE +Sorted Merge Bucket Map Join Operator + condition map: + Inner Join 0 to 1 + keys: +0 _col0 (type: string) +1 _col0 (type: string) + Position of Big Table: 0 + BucketMapJoin: true + Group By Operator +aggregations: count() +mode: hash +outputColumnNames: _col0 +Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: A masked pattern was here Path -> Partition: @@ -496,8 +504,8 @@ STAGE PLANS: name: default.bucket_big name: default.bucket_big Truncated Path -> Alias: -/bucket_big/ds=2008-04-08 [a] -/bucket_big/ds=2008-04-09 [a] +/bucket_big/ds=2008-04-08 [$hdt$_0:a] +
[65/91] [abbrv] hive git commit: HIVE-12331 : Remove hive.enforce.bucketing & hive.enforce.sorting configs (Ashutosh Chauhan via Jason Dere)
http://git-wip-us.apache.org/repos/asf/hive/blob/5562fae7/ql/src/test/results/clientpositive/alter_numbuckets_partitioned_table.q.out -- diff --git a/ql/src/test/results/clientpositive/alter_numbuckets_partitioned_table.q.out b/ql/src/test/results/clientpositive/alter_numbuckets_partitioned_table.q.out deleted file mode 100644 index b1dfd7c..000 --- a/ql/src/test/results/clientpositive/alter_numbuckets_partitioned_table.q.out +++ /dev/null @@ -1,553 +0,0 @@ -PREHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.20,0.20S) -create table tst1(key string, value string) partitioned by (ds string) clustered by (key) into 10 buckets -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -POSTHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.20,0.20S) -create table tst1(key string, value string) partitioned by (ds string) clustered by (key) into 10 buckets -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@tst1 -PREHOOK: query: alter table tst1 clustered by (key) into 8 buckets -PREHOOK: type: ALTERTABLE_CLUSTER_SORT -PREHOOK: Input: default@tst1 -PREHOOK: Output: default@tst1 -POSTHOOK: query: alter table tst1 clustered by (key) into 8 buckets -POSTHOOK: type: ALTERTABLE_CLUSTER_SORT -POSTHOOK: Input: default@tst1 -POSTHOOK: Output: default@tst1 -PREHOOK: query: describe formatted tst1 -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@tst1 -POSTHOOK: query: describe formatted tst1 -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@tst1 -# col_name data_type comment - -keystring -value string - -# Partition Information -# col_name data_type comment - -ds string - -# Detailed Table Information -Database: default - A masked pattern was here -Retention: 0 - A masked pattern was here -Table Type:MANAGED_TABLE -Table Parameters: - A masked pattern was here - -# Storage Information -SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -InputFormat: org.apache.hadoop.mapred.TextInputFormat -OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat -Compressed:No -Num Buckets: 8 -Bucket Columns:[key] -Sort Columns: [] -Storage Desc Params: - serialization.format1 -PREHOOK: query: insert overwrite table tst1 partition (ds='1') select key, value from src -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@tst1@ds=1 -POSTHOOK: query: insert overwrite table tst1 partition (ds='1') select key, value from src -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@tst1@ds=1 -POSTHOOK: Lineage: tst1 PARTITION(ds=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: tst1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: describe formatted tst1 partition (ds = '1') -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@tst1 -POSTHOOK: query: describe formatted tst1 partition (ds = '1') -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@tst1 -# col_name data_type comment - -keystring -value string - -# Partition Information -# col_name data_type comment - -ds string - -# Detailed Partition Information -Partition Value: [1] -Database: default -Table: tst1 - A masked pattern was here -Partition Parameters: - COLUMN_STATS_ACCURATE true - numFiles1 - numRows 500 - rawDataSize 5312 - totalSize 5812 - A masked pattern was here - -# Storage Information -SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -InputFormat:
[24/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out -- diff --git a/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out b/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out index e9192a3..10b4168 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out @@ -210,41 +210,49 @@ STAGE PLANS: alias: srcpart filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator -key expressions: ds (type: string) -sort order: + -Map-reduce partition columns: ds (type: string) + Select Operator +expressions: ds (type: string) +outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE +Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Map 4 Map Operator Tree: TableScan alias: srcpart_date - filterExpr: (ds is not null and (date = '2008-04-08')) (type: boolean) + filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE Filter Operator -predicate: (ds is not null and (date = '2008-04-08')) (type: boolean) +predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE -Reduce Output Operator - key expressions: ds (type: string) - sort order: + - Map-reduce partition columns: ds (type: string) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator -keys: _col0 (type: string) -mode: hash + Reduce Output Operator +key expressions: _col0 (type: string) +sort order: + +Map-reduce partition columns: _col0 (type: string) +Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Select Operator +expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE -Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds +Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 + Dynamic Partitioning Event Operator +Target Input: srcpart +Partition key expr: ds +Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE +Target column: ds +Target Vertex: Map 1 Execution mode: vectorized, llap Reducer 2 Execution mode: llap @@ -253,8 +261,8 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 ds (type: string) - 1 ds (type: string) + 0 _col0 (type: string) + 1 _col0 (type: string) Statistics: Num rows: 2200 Data size:
[14/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/skewjoinopt4.q.out -- diff --git a/ql/src/test/results/clientpositive/skewjoinopt4.q.out b/ql/src/test/results/clientpositive/skewjoinopt4.q.out index 1d2a5a4..28fb7df 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt4.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt4.q.out @@ -62,43 +62,47 @@ STAGE PLANS: Filter Operator predicate: (key is not null and (key = '2')) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator -key expressions: key (type: string) -sort order: + -Map-reduce partition columns: key (type: string) + Select Operator +expressions: key (type: string), val (type: string) +outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE -value expressions: val (type: string) +Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) TableScan alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key is not null and (key = '2')) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator -key expressions: key (type: string) -sort order: + -Map-reduce partition columns: key (type: string) + Select Operator +expressions: key (type: string), val (type: string) +outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE -value expressions: val (type: string) +Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: -0 key (type: string) -1 key (type: string) - outputColumnNames: _col0, _col1, _col5, _col6 +0 _col0 (type: string) +1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE - Select Operator -expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) -outputColumnNames: _col0, _col1, _col2, _col3 -Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE -File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator +compressed: false +table: +input format: org.apache.hadoop.mapred.SequenceFileInputFormat +output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat +serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -133,40 +137,44 @@ STAGE PLANS: Filter Operator predicate: (key is not null and (not (key = '2'))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator -key expressions: key (type: string) -sort order: + -Map-reduce partition columns: key (type: string) + Select Operator +expressions: key (type: string), val (type: string) +outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE -value expressions: val (type: string) +Reduce Output Operator +
[31/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/llap/bucket_map_join_tez1.q.out -- diff --git a/ql/src/test/results/clientpositive/llap/bucket_map_join_tez1.q.out b/ql/src/test/results/clientpositive/llap/bucket_map_join_tez1.q.out index 1f1bf3d..814c947 100644 --- a/ql/src/test/results/clientpositive/llap/bucket_map_join_tez1.q.out +++ b/ql/src/test/results/clientpositive/llap/bucket_map_join_tez1.q.out @@ -135,12 +135,16 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE -Reduce Output Operator - key expressions: key (type: int) - sort order: + - Map-reduce partition columns: key (type: int) +Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + Reduce Output Operator +key expressions: _col0 (type: int) +sort order: + +Map-reduce partition columns: _col0 (type: int) +Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE +value expressions: _col1 (type: string) Execution mode: llap Map 2 Map Operator Tree: @@ -150,28 +154,32 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE -Map Join Operator - condition map: - Inner Join 0 to 1 - keys: -0 key (type: int) -1 key (type: int) - outputColumnNames: _col0, _col1, _col7 - input vertices: -0 Map 1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true - Select Operator -expressions: _col0 (type: int), _col1 (type: string), _col7 (type: string) -outputColumnNames: _col0, _col1, _col2 +Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator +condition map: + Inner Join 0 to 1 +keys: + 0 _col0 (type: int) + 1 _col0 (type: int) +outputColumnNames: _col0, _col1, _col3 +input vertices: + 0 Map 1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE -File Output Operator - compressed: false +HybridGraceHashJoin: true +Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator +compressed: false +Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE +table: +input format: org.apache.hadoop.mapred.TextInputFormat +output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat +serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: llap Stage: Stage-0 @@ -229,11 +237,15 @@ STAGE PLANS: Filter Operator predicate: key
[45/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/auto_sortmerge_join_9.q.out -- diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_9.q.out b/ql/src/test/results/clientpositive/auto_sortmerge_join_9.q.out index bbfa756..31a1b29 100644 --- a/ql/src/test/results/clientpositive/auto_sortmerge_join_9.q.out +++ b/ql/src/test/results/clientpositive/auto_sortmerge_join_9.q.out @@ -68,19 +68,23 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator -condition map: - Inner Join 0 to 1 -keys: - 0 key (type: int) - 1 key (type: int) -Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator -sort order: -value expressions: _col0 (type: bigint) + Select Operator +expressions: key (type: int) +outputColumnNames: _col0 +Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE +Sorted Merge Bucket Map Join Operator + condition map: + Inner Join 0 to 1 + keys: +0 _col0 (type: int) +1 _col0 (type: int) + Group By Operator +aggregations: count() +mode: hash +outputColumnNames: _col0 +Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -144,23 +148,27 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator -condition map: - Inner Join 0 to 1 -keys: - 0 key (type: int) - 1 key (type: int) + Select Operator +expressions: key (type: int) outputColumnNames: _col0 -Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator -key expressions: _col0 (type: int) -sort order: + -Map-reduce partition columns: _col0 (type: int) -value expressions: _col1 (type: bigint) +Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE +Sorted Merge Bucket Map Join Operator + condition map: + Inner Join 0 to 1 + keys: +0 _col0 (type: int) +1 _col0 (type: int) + outputColumnNames: _col0 + Group By Operator +aggregations: count() +keys: _col0 (type: int) +mode: hash +outputColumnNames: _col0, _col1 +Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -241,29 +249,30 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator -condition map: - Inner Join 0 to 1 -keys: - 0 key (type: int) - 1 key (type: int) + Select Operator +expressions: key (type: int) outputColumnNames: _col0 -Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator -key expressions: _col0 (type: int) -sort order: + -Map-reduce partition
[38/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/cross_product_check_2.q.out -- diff --git a/ql/src/test/results/clientpositive/cross_product_check_2.q.out b/ql/src/test/results/clientpositive/cross_product_check_2.q.out index 6910b40..57d1498 100644 --- a/ql/src/test/results/clientpositive/cross_product_check_2.q.out +++ b/ql/src/test/results/clientpositive/cross_product_check_2.q.out @@ -93,7 +93,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[17][bigTable=?] in task 'Stage-5:MAPRED' is a cross product +Warning: Map Join MAPJOIN[22][bigTable=?] in task 'Stage-5:MAPRED' is a cross product PREHOOK: query: explain select * from B d1 join B d2 on d1.key = d2.key join A PREHOOK: type: QUERY POSTHOOK: query: explain select * from B d1 join B d2 on d1.key = d2.key join A @@ -107,60 +107,68 @@ STAGE PLANS: Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: -a +$hdt$_0:d1 Fetch Operator limit: -1 -d1 +$hdt$_2:a Fetch Operator limit: -1 Alias -> Map Local Operator Tree: -a - TableScan -alias: a -Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE -HashTable Sink Operator - keys: -0 -1 -d1 +$hdt$_0:d1 TableScan alias: d1 Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 5 Data size: 48 Basic stats: COMPLETE Column stats: NONE + Select Operator +expressions: key (type: string), value (type: string) +outputColumnNames: _col0, _col1 +Statistics: Num rows: 5 Data size: 48 Basic stats: COMPLETE Column stats: NONE +HashTable Sink Operator + keys: +0 _col0 (type: string) +1 _col0 (type: string) +$hdt$_2:a + TableScan +alias: a +Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE +Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 key (type: string) - 1 key (type: string) + 0 + 1 Stage: Stage-5 Map Reduce Map Operator Tree: TableScan -alias: d2 +alias: d1 Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 5 Data size: 48 Basic stats: COMPLETE Column stats: NONE - Map Join Operator -condition map: - Inner Join 0 to 1 -keys: - 0 key (type: string) - 1 key (type: string) -outputColumnNames: _col0, _col1, _col5, _col6 -Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Select Operator +expressions: key (type: string), value (type: string) +outputColumnNames: _col0, _col1 +Statistics: Num rows: 5 Data size: 48 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: -0 -1 - outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Select Operator -expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) +0 _col0 (type: string) +1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Map Join Operator +condition map: + Inner Join 0 to 1 +keys: + 0 + 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
[68/91] [abbrv] hive git commit: HIVE-12329 :Turn on limit pushdown optimization by default (Ashutosh Chauhan via Prasanth J)
http://git-wip-us.apache.org/repos/asf/hive/blob/daf46aa7/ql/src/test/results/clientpositive/tez/vector_cast_constant.q.java1.7.out -- diff --git a/ql/src/test/results/clientpositive/tez/vector_cast_constant.q.java1.7.out b/ql/src/test/results/clientpositive/tez/vector_cast_constant.q.java1.7.out index 12920d2..bcbdf06 100644 --- a/ql/src/test/results/clientpositive/tez/vector_cast_constant.q.java1.7.out +++ b/ql/src/test/results/clientpositive/tez/vector_cast_constant.q.java1.7.out @@ -161,6 +161,7 @@ STAGE PLANS: key expressions: _col0 (type: int) sort order: + Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: decimal(14,4)) Reducer 3 Execution mode: vectorized http://git-wip-us.apache.org/repos/asf/hive/blob/daf46aa7/ql/src/test/results/clientpositive/tez/vector_char_2.q.out -- diff --git a/ql/src/test/results/clientpositive/tez/vector_char_2.q.out b/ql/src/test/results/clientpositive/tez/vector_char_2.q.out index 8545608..f88ee91 100644 --- a/ql/src/test/results/clientpositive/tez/vector_char_2.q.out +++ b/ql/src/test/results/clientpositive/tez/vector_char_2.q.out @@ -106,6 +106,7 @@ STAGE PLANS: key expressions: _col0 (type: char(20)) sort order: + Statistics: Num rows: 250 Data size: 49500 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint), _col2 (type: bigint) Reducer 3 Execution mode: vectorized @@ -234,6 +235,7 @@ STAGE PLANS: key expressions: _col0 (type: char(20)) sort order: - Statistics: Num rows: 250 Data size: 49500 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint), _col2 (type: bigint) Reducer 3 Execution mode: vectorized http://git-wip-us.apache.org/repos/asf/hive/blob/daf46aa7/ql/src/test/results/clientpositive/tez/vector_char_simple.q.out -- diff --git a/ql/src/test/results/clientpositive/tez/vector_char_simple.q.out b/ql/src/test/results/clientpositive/tez/vector_char_simple.q.out index be38775..617620c 100644 --- a/ql/src/test/results/clientpositive/tez/vector_char_simple.q.out +++ b/ql/src/test/results/clientpositive/tez/vector_char_simple.q.out @@ -79,6 +79,7 @@ STAGE PLANS: key expressions: _col0 (type: char(10)) sort order: + Statistics: Num rows: 500 Data size: 99000 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: char(20)) Execution mode: vectorized Reducer 2 @@ -179,6 +180,7 @@ STAGE PLANS: key expressions: _col0 (type: char(10)) sort order: - Statistics: Num rows: 500 Data size: 99000 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: char(20)) Execution mode: vectorized Reducer 2 @@ -282,6 +284,7 @@ STAGE PLANS: Reduce Output Operator sort order: Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE +TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: int) Execution mode: vectorized Reducer 2 http://git-wip-us.apache.org/repos/asf/hive/blob/daf46aa7/ql/src/test/results/clientpositive/tez/vector_coalesce.q.out -- diff --git a/ql/src/test/results/clientpositive/tez/vector_coalesce.q.out b/ql/src/test/results/clientpositive/tez/vector_coalesce.q.out index c492113..1142485 100644 --- a/ql/src/test/results/clientpositive/tez/vector_coalesce.q.out +++ b/ql/src/test/results/clientpositive/tez/vector_coalesce.q.out @@ -41,6 +41,7 @@ STAGE PLANS: key expressions: null (type: double), _col1 (type: string), _col2 (type: int), _col3 (type: float), _col4 (type: smallint), _col5 (type: string) sort order: ++ Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE +TopN Hash Memory Usage: 0.1 Execution mode:
[84/91] [abbrv] hive git commit: HIVE-12465: Hive might produce wrong results when (outer) joins are merged (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
HIVE-12465: Hive might produce wrong results when (outer) joins are merged (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan) Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/79847387 Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/79847387 Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/79847387 Branch: refs/heads/spark Commit: 79847387699b803506ecd8b03ecc8790ee229751 Parents: f1ac5a3 Author: Jesus Camacho RodriguezAuthored: Tue Nov 24 17:20:05 2015 +0100 Committer: Jesus Camacho Rodriguez Committed: Fri Nov 27 10:10:46 2015 +0100 -- .../hadoop/hive/ql/parse/SemanticAnalyzer.java | 2 +- ql/src/test/queries/clientpositive/mergejoin.q | 12 + .../test/results/clientpositive/mergejoin.q.out | 548 +++ .../results/clientpositive/tez/mergejoin.q.out | 548 +++ 4 files changed, 1109 insertions(+), 1 deletion(-) -- http://git-wip-us.apache.org/repos/asf/hive/blob/79847387/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java -- diff --git a/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java b/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java index 1b7873d..0ff6001 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java @@ -2265,7 +2265,7 @@ public class SemanticAnalyzer extends BaseSemanticAnalyzer { if (rightCondAl1.size() != 0) { QBJoinTree leftTree = joinTree.getJoinSrc(); List leftTreeLeftSrc = new ArrayList(); -if (leftTree != null) { +if (leftTree != null && leftTree.getNoOuterJoin()) { String leftTreeRightSource = leftTree.getRightAliases() != null && leftTree.getRightAliases().length > 0 ? leftTree.getRightAliases()[0] : null; http://git-wip-us.apache.org/repos/asf/hive/blob/79847387/ql/src/test/queries/clientpositive/mergejoin.q -- diff --git a/ql/src/test/queries/clientpositive/mergejoin.q b/ql/src/test/queries/clientpositive/mergejoin.q index 6cd3929..82e1c93 100644 --- a/ql/src/test/queries/clientpositive/mergejoin.q +++ b/ql/src/test/queries/clientpositive/mergejoin.q @@ -132,3 +132,15 @@ select * from (select * from tab where tab.key = 0)a join (select * from tab_part where tab_part.key = 98)b on a.key = b.key full outer join tab_part c on b.key = c.key; + +set hive.cbo.enable = false; + +select * from +(select * from tab where tab.key = 0)a +full outer join +(select * from tab_part where tab_part.key = 98)b join tab_part c on a.key = b.key and b.key = c.key; + +select * from +(select * from tab where tab.key = 0)a +join +(select * from tab_part where tab_part.key = 98)b full outer join tab_part c on a.key = b.key and b.key = c.key; http://git-wip-us.apache.org/repos/asf/hive/blob/79847387/ql/src/test/results/clientpositive/mergejoin.q.out -- diff --git a/ql/src/test/results/clientpositive/mergejoin.q.out b/ql/src/test/results/clientpositive/mergejoin.q.out index 65f5ef5..e4a9e5b 100644 --- a/ql/src/test/results/clientpositive/mergejoin.q.out +++ b/ql/src/test/results/clientpositive/mergejoin.q.out @@ -3787,3 +3787,551 @@ NULLNULLNULLNULLNULLNULL97 val_97 2008-04-08 NULL NULLNULLNULLNULLNULL97 val_97 2008-04-08 NULL NULLNULLNULLNULLNULL98 val_98 2008-04-08 NULL NULLNULLNULLNULLNULL98 val_98 2008-04-08 +Warning: Shuffle Join JOIN[9][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product +PREHOOK: query: select * from +(select * from tab where tab.key = 0)a +full outer join +(select * from tab_part where tab_part.key = 98)b join tab_part c on a.key = b.key and b.key = c.key +PREHOOK: type: QUERY +PREHOOK: Input: default@tab +PREHOOK: Input: default@tab@ds=2008-04-08 +PREHOOK: Input: default@tab_part +PREHOOK: Input: default@tab_part@ds=2008-04-08 + A masked pattern was here +POSTHOOK: query: select * from +(select * from tab where tab.key = 0)a +full outer join +(select * from tab_part where tab_part.key = 98)b join tab_part c on a.key = b.key and b.key = c.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tab +POSTHOOK: Input: default@tab@ds=2008-04-08 +POSTHOOK: Input: default@tab_part +POSTHOOK: Input: default@tab_part@ds=2008-04-08 + A masked pattern was here +Warning: Shuffle Join JOIN[9][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product +PREHOOK: query: select *
[62/91] [abbrv] hive git commit: HIVE-12175: Upgrade Kryo version to 3.0.x (Prasanth Jayachandran reviewed by Ashutosh Chauhan)
HIVE-12175: Upgrade Kryo version to 3.0.x (Prasanth Jayachandran reviewed by Ashutosh Chauhan) Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/b7281ce6 Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/b7281ce6 Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/b7281ce6 Branch: refs/heads/spark Commit: b7281ce6a61bcfbd398fd691cddc38c4f1a61f64 Parents: c6a835c Author: Prasanth JayachandranAuthored: Tue Nov 24 12:43:46 2015 -0600 Committer: Prasanth Jayachandran Committed: Tue Nov 24 12:43:46 2015 -0600 -- itests/qtest-accumulo/pom.xml | 2 +- pom.xml | 6 +- ql/pom.xml | 36 +++-- .../apache/hadoop/hive/ql/exec/Utilities.java | 145 +-- .../org/apache/hadoop/hive/ql/plan/MapWork.java | 15 -- .../apache/hadoop/hive/ql/plan/ReduceWork.java | 5 - spark-client/pom.xml| 28 ++-- .../hive/spark/client/rpc/KryoMessageCodec.java | 11 +- 8 files changed, 185 insertions(+), 63 deletions(-) -- http://git-wip-us.apache.org/repos/asf/hive/blob/b7281ce6/itests/qtest-accumulo/pom.xml -- diff --git a/itests/qtest-accumulo/pom.xml b/itests/qtest-accumulo/pom.xml index 7403a15..f7325dc 100644 --- a/itests/qtest-accumulo/pom.xml +++ b/itests/qtest-accumulo/pom.xml @@ -123,7 +123,7 @@ - com.esotericsoftware.kryo + com.esotericsoftware kryo ${kryo.version} test http://git-wip-us.apache.org/repos/asf/hive/blob/b7281ce6/pom.xml -- diff --git a/pom.xml b/pom.xml index c6df4a5..c38c10f 100644 --- a/pom.xml +++ b/pom.xml @@ -144,7 +144,7 @@ 3.5.2 20090211 4.11 -2.22 +3.0.3 0.9.3 0.9.3 2.4 @@ -228,8 +228,8 @@ -com.esotericsoftware.kryo -kryo +com.esotericsoftware +kryo-shaded ${kryo.version} http://git-wip-us.apache.org/repos/asf/hive/blob/b7281ce6/ql/pom.xml -- diff --git a/ql/pom.xml b/ql/pom.xml index 9420a62..d893099 100644 --- a/ql/pom.xml +++ b/ql/pom.xml @@ -72,8 +72,8 @@ - com.esotericsoftware.kryo - kryo + com.esotericsoftware + kryo-shaded ${kryo.version} @@ -594,16 +594,20 @@ spark-core_${scala.binary.version} ${spark.version} true - - -org.slf4j -slf4j-log4j12 - - -commmons-logging -commons-logging - - + + + com.esotericsoftware.kryo + kryo + + + org.slf4j + slf4j-log4j12 + + + commmons-logging + commons-logging + + com.sun.jersey @@ -746,7 +750,9 @@ org.apache.hive:hive-serde org.apache.hive:hive-llap-client org.apache.hive:hive-metastore - com.esotericsoftware.kryo:kryo + com.esotericsoftware:kryo-shaded + com.esotericsoftware:minlog + org.objenesis:objenesis org.apache.parquet:parquet-hadoop-bundle org.apache.thrift:libthrift org.apache.thrift:libfb303 @@ -779,6 +785,10 @@ com.esotericsoftware org.apache.hive.com.esotericsoftware + + org.objenesis + org.apache.hive.org.objenesis + http://git-wip-us.apache.org/repos/asf/hive/blob/b7281ce6/ql/src/java/org/apache/hadoop/hive/ql/exec/Utilities.java -- diff --git a/ql/src/java/org/apache/hadoop/hive/ql/exec/Utilities.java b/ql/src/java/org/apache/hadoop/hive/ql/exec/Utilities.java index 9dbb45a..8b8cf6d 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/exec/Utilities.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/exec/Utilities.java @@ -37,6 +37,8 @@ import java.io.InputStream; import java.io.OutputStream; import java.io.Serializable; import java.io.UnsupportedEncodingException; +import java.lang.reflect.Array; +import java.lang.reflect.Field; import java.net.URI; import java.net.URL; import java.net.URLClassLoader; @@ -87,8 +89,6 @@ import org.apache.commons.lang.StringUtils; import org.apache.commons.lang.WordUtils; import org.apache.commons.lang3.StringEscapeUtils; import
[30/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/llap/constprog_dpp.q.out -- diff --git a/ql/src/test/results/clientpositive/llap/constprog_dpp.q.out b/ql/src/test/results/clientpositive/llap/constprog_dpp.q.out index 72a5d0d..a1addb7 100644 --- a/ql/src/test/results/clientpositive/llap/constprog_dpp.q.out +++ b/ql/src/test/results/clientpositive/llap/constprog_dpp.q.out @@ -38,76 +38,79 @@ union all select 2 as id from tb2 limit 1) b on a.id=b.id POSTHOOK: type: QUERY -Plan not optimized by CBO due to missing statistics. Please check log for more details. +Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Union 2 (CONTAINS) -Map 5 <- Union 2 (CONTAINS) -Reducer 3 <- Union 2 (SIMPLE_EDGE) -Reducer 4 <- Map 6 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Map 3 <- Union 4 (CONTAINS) +Map 6 <- Union 4 (CONTAINS) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) +Reducer 5 <- Union 4 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 - Reducer 4 llap - File Output Operator [FS_16] + Reducer 2 llap + File Output Operator [FS_17] compressed:false Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} -Merge Join Operator [MERGEJOIN_20] +Merge Join Operator [MERGEJOIN_21] | condition map:[{"":"Left Outer Join0 to 1"}] -| keys:{"0":"id (type: int)","1":"_col0 (type: int)"} +| keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"} | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE -|<-Map 6 [SIMPLE_EDGE] llap -| Reduce Output Operator [RS_12] -| key expressions:id (type: int) -| Map-reduce partition columns:id (type: int) +|<-Map 1 [SIMPLE_EDGE] llap +| Reduce Output Operator [RS_13] +| key expressions:_col0 (type: int) +| Map-reduce partition columns:_col0 (type: int) | sort order:+ | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE -| TableScan [TS_11] -|alias:a +| Select Operator [SEL_1] +|outputColumnNames:["_col0"] |Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE -|<-Reducer 3 [SIMPLE_EDGE] llap - Reduce Output Operator [RS_13] +|TableScan [TS_0] +| alias:a +| Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE +|<-Reducer 5 [SIMPLE_EDGE] llap + Reduce Output Operator [RS_14] key expressions:_col0 (type: int) Map-reduce partition columns:_col0 (type: int) sort order:+ Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Limit [LIM_10] + Limit [LIM_11] Number of rows:1 Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Select Operator [SEL_9] + Select Operator [SEL_10] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - |<-Union 2 [SIMPLE_EDGE] -|<-Map 1 [CONTAINS] llap -| Reduce Output Operator [RS_8] + |<-Union 4 [SIMPLE_EDGE] +|<-Map 3 [CONTAINS] llap +| Reduce Output Operator [RS_9] | sort order: | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE | value expressions:_col0 (type: int) -| Limit [LIM_7] +| Limit [LIM_8] |Number of rows:1 |Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE -|Select Operator [SEL_1] +|Select Operator [SEL_3] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE -|
[40/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/correlationoptimizer13.q.out -- diff --git a/ql/src/test/results/clientpositive/correlationoptimizer13.q.out b/ql/src/test/results/clientpositive/correlationoptimizer13.q.out index d652d87..8771f1c 100644 --- a/ql/src/test/results/clientpositive/correlationoptimizer13.q.out +++ b/ql/src/test/results/clientpositive/correlationoptimizer13.q.out @@ -65,11 +65,11 @@ STAGE PLANS: Statistics: Num rows: 171 Data size: 3819 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c3 (type: string), c1 (type: int) -outputColumnNames: c3, c1 +outputColumnNames: _col0, _col1 Statistics: Num rows: 171 Data size: 3819 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) - keys: c3 (type: string), c1 (type: int) + keys: _col0 (type: string), _col1 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 171 Data size: 3819 Basic stats: COMPLETE Column stats: NONE @@ -112,7 +112,7 @@ STAGE PLANS: key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 43 Data size: 960 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 312 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint) Reduce Operator Tree: Join Operator @@ -159,26 +159,26 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan -alias: x1 +alias: x Statistics: Num rows: 1028 Data size: 22964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((c2 > 100) and c1 is not null) and c3 is not null) (type: boolean) - Statistics: Num rows: 86 Data size: 1921 Basic stats: COMPLETE Column stats: NONE + predicate: c2 > 100) and (c1 < 120)) and c1 is not null) and c3 is not null) (type: boolean) + Statistics: Num rows: 29 Data size: 647 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c3 (type: string), c1 (type: int) -outputColumnNames: c3, c1 -Statistics: Num rows: 86 Data size: 1921 Basic stats: COMPLETE Column stats: NONE +outputColumnNames: _col0, _col1 +Statistics: Num rows: 29 Data size: 647 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) - keys: c3 (type: string), c1 (type: int) + keys: _col0 (type: string), _col1 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 86 Data size: 1921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 647 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: int) -Statistics: Num rows: 86 Data size: 1921 Basic stats: COMPLETE Column stats: NONE +Statistics: Num rows: 29 Data size: 647 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator @@ -186,11 +186,11 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 43 Data size: 960 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: int), _col0 (type: string), _col2 (type: bigint) outputColumnNames: _col0, _col1, _col2 -Statistics: Num rows: 43 Data size: 960 Basic stats: COMPLETE Column stats: NONE +Statistics: Num rows: 14 Data size: 312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/correlationoptimizer4.q.out -- diff --git
[69/91] [abbrv] hive git commit: HIVE-12329 :Turn on limit pushdown optimization by default (Ashutosh Chauhan via Prasanth J)
http://git-wip-us.apache.org/repos/asf/hive/blob/daf46aa7/ql/src/test/results/clientpositive/smb_mapjoin_15.q.out -- diff --git a/ql/src/test/results/clientpositive/smb_mapjoin_15.q.out b/ql/src/test/results/clientpositive/smb_mapjoin_15.q.out index 64a3ea2..8608187 100644 --- a/ql/src/test/results/clientpositive/smb_mapjoin_15.q.out +++ b/ql/src/test/results/clientpositive/smb_mapjoin_15.q.out @@ -124,6 +124,8 @@ STAGE PLANS: key expressions: _col0 (type: int) sort order: + tag: -1 +TopN: 10 +TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string) auto parallelism: false Path -> Alias: @@ -382,6 +384,8 @@ STAGE PLANS: key expressions: _col0 (type: int) sort order: + tag: -1 +TopN: 10 +TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: string) auto parallelism: false Path -> Alias: @@ -588,6 +592,8 @@ STAGE PLANS: key expressions: _col0 (type: int) sort order: + tag: -1 +TopN: 10 +TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: string) auto parallelism: false Path -> Alias: @@ -827,6 +833,8 @@ STAGE PLANS: sort order: + Statistics: Num rows: 137 Data size: 1984 Basic stats: COMPLETE Column stats: NONE tag: -1 +TopN: 10 +TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: string) auto parallelism: false Local Work: http://git-wip-us.apache.org/repos/asf/hive/blob/daf46aa7/ql/src/test/results/clientpositive/spark/auto_join_without_localtask.q.out -- diff --git a/ql/src/test/results/clientpositive/spark/auto_join_without_localtask.q.out b/ql/src/test/results/clientpositive/spark/auto_join_without_localtask.q.out index a234ff5..932fdcc 100644 --- a/ql/src/test/results/clientpositive/spark/auto_join_without_localtask.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_join_without_localtask.q.out @@ -65,6 +65,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 Reducer 3 Reduce Operator Tree: Select Operator @@ -238,6 +239,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 Reducer 4 Reduce Operator Tree: Select Operator @@ -411,6 +413,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 Reducer 4 Reduce Operator Tree: Select Operator http://git-wip-us.apache.org/repos/asf/hive/blob/daf46aa7/ql/src/test/results/clientpositive/spark/bucketmapjoin7.q.out -- diff --git a/ql/src/test/results/clientpositive/spark/bucketmapjoin7.q.out b/ql/src/test/results/clientpositive/spark/bucketmapjoin7.q.out index a99cb74..84f68a3 100644 --- a/ql/src/test/results/clientpositive/spark/bucketmapjoin7.q.out +++ b/ql/src/test/results/clientpositive/spark/bucketmapjoin7.q.out @@ -262,6 +262,8 @@ STAGE PLANS: sort order: ++ Statistics: Num rows: 378 Data size: 1514 Basic stats: COMPLETE Column stats: NONE tag: -1 + TopN: 1 + TopN Hash Memory Usage: 0.1 auto parallelism: false Local Work: Map Reduce Local Work http://git-wip-us.apache.org/repos/asf/hive/blob/daf46aa7/ql/src/test/results/clientpositive/spark/ctas.q.out
[59/91] [abbrv] hive git commit: HIVE-12411: Remove counter based stats collection mechanism (Pengcheng Xiong, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/ab98ffc2/ql/src/test/results/clientpositive/stats_counter_partitioned.q.out -- diff --git a/ql/src/test/results/clientpositive/stats_counter_partitioned.q.out b/ql/src/test/results/clientpositive/stats_counter_partitioned.q.out deleted file mode 100644 index 626dcff..000 --- a/ql/src/test/results/clientpositive/stats_counter_partitioned.q.out +++ /dev/null @@ -1,465 +0,0 @@ -PREHOOK: query: -- partitioned table analyze - -create table dummy (key string, value string) partitioned by (ds string, hr string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@dummy -POSTHOOK: query: -- partitioned table analyze - -create table dummy (key string, value string) partitioned by (ds string, hr string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@dummy -PREHOOK: query: load data local inpath '../../data/files/kv1.txt' into table dummy partition (ds='2008',hr='12') -PREHOOK: type: LOAD - A masked pattern was here -PREHOOK: Output: default@dummy -POSTHOOK: query: load data local inpath '../../data/files/kv1.txt' into table dummy partition (ds='2008',hr='12') -POSTHOOK: type: LOAD - A masked pattern was here -POSTHOOK: Output: default@dummy -POSTHOOK: Output: default@dummy@ds=2008/hr=12 -PREHOOK: query: load data local inpath '../../data/files/kv1.txt' into table dummy partition (ds='2008',hr='11') -PREHOOK: type: LOAD - A masked pattern was here -PREHOOK: Output: default@dummy -POSTHOOK: query: load data local inpath '../../data/files/kv1.txt' into table dummy partition (ds='2008',hr='11') -POSTHOOK: type: LOAD - A masked pattern was here -POSTHOOK: Output: default@dummy -POSTHOOK: Output: default@dummy@ds=2008/hr=11 -PREHOOK: query: analyze table dummy partition (ds,hr) compute statistics -PREHOOK: type: QUERY -PREHOOK: Input: default@dummy -PREHOOK: Input: default@dummy@ds=2008/hr=11 -PREHOOK: Input: default@dummy@ds=2008/hr=12 -PREHOOK: Output: default@dummy -PREHOOK: Output: default@dummy@ds=2008/hr=11 -PREHOOK: Output: default@dummy@ds=2008/hr=12 -POSTHOOK: query: analyze table dummy partition (ds,hr) compute statistics -POSTHOOK: type: QUERY -POSTHOOK: Input: default@dummy -POSTHOOK: Input: default@dummy@ds=2008/hr=11 -POSTHOOK: Input: default@dummy@ds=2008/hr=12 -POSTHOOK: Output: default@dummy -POSTHOOK: Output: default@dummy@ds=2008/hr=11 -POSTHOOK: Output: default@dummy@ds=2008/hr=12 -PREHOOK: query: describe formatted dummy partition (ds='2008', hr='11') -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@dummy -POSTHOOK: query: describe formatted dummy partition (ds='2008', hr='11') -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@dummy -# col_name data_type comment - -keystring -value string - -# Partition Information -# col_name data_type comment - -ds string -hr string - -# Detailed Partition Information -Partition Value: [2008, 11] -Database: default -Table: dummy - A masked pattern was here -Partition Parameters: - COLUMN_STATS_ACCURATE true - numFiles1 - numRows 500 - rawDataSize 5312 - totalSize 5812 - A masked pattern was here - -# Storage Information -SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -InputFormat: org.apache.hadoop.mapred.TextInputFormat -OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat -Compressed:No -Num Buckets: -1 -Bucket Columns:[] -Sort Columns: [] -Storage Desc Params: - serialization.format1 -PREHOOK: query: describe formatted dummy partition (ds='2008', hr='12') -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@dummy -POSTHOOK: query: describe formatted dummy partition (ds='2008', hr='12') -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@dummy -# col_name data_type comment - -keystring -value string
[34/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/join_cond_pushdown_unqual3.q.out -- diff --git a/ql/src/test/results/clientpositive/join_cond_pushdown_unqual3.q.out b/ql/src/test/results/clientpositive/join_cond_pushdown_unqual3.q.out index b0258b8..094f646 100644 --- a/ql/src/test/results/clientpositive/join_cond_pushdown_unqual3.q.out +++ b/ql/src/test/results/clientpositive/join_cond_pushdown_unqual3.q.out @@ -76,61 +76,66 @@ STAGE PLANS: Filter Operator predicate: p_name is not null (type: boolean) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator -key expressions: p_name (type: string) -sort order: + -Map-reduce partition columns: p_name (type: string) + Select Operator +expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) +outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE -value expressions: p_partkey (type: int), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) +Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: p2_name is not null (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator -key expressions: p2_name (type: string) -sort order: + -Map-reduce partition columns: p2_name (type: string) + Select Operator +expressions: p2_partkey (type: int), p2_name (type: string), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) +outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE -value expressions: p2_partkey (type: int), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) +Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p3 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: p3_name is not null (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator -key expressions: p3_name (type: string) -sort order: + -Map-reduce partition columns: p3_name (type: string) + Select Operator +expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) +outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE -value expressions: p3_partkey (type: int), p3_mfgr (type:
[33/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/join_filters_overlap.q.out -- diff --git a/ql/src/test/results/clientpositive/join_filters_overlap.q.out b/ql/src/test/results/clientpositive/join_filters_overlap.q.out index f52cf26..1d04f37 100644 --- a/ql/src/test/results/clientpositive/join_filters_overlap.q.out +++ b/ql/src/test/results/clientpositive/join_filters_overlap.q.out @@ -104,46 +104,58 @@ STAGE PLANS: alias: a Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE GatherStats: false -Reduce Output Operator - key expressions: key (type: int) - sort order: + - Map-reduce partition columns: key (type: int) +Select Operator + expressions: key (type: int), value (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: value (type: int) - auto parallelism: false + Reduce Output Operator +key expressions: _col0 (type: int) +sort order: + +Map-reduce partition columns: _col0 (type: int) +Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE +tag: 0 +value expressions: _col1 (type: int) +auto parallelism: false TableScan -alias: b +alias: a Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (value = 50) (type: boolean) Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator -key expressions: key (type: int) -sort order: + -Map-reduce partition columns: key (type: int) + Select Operator +expressions: key (type: int), 50 (type: int) +outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE -tag: 1 -value expressions: value (type: int) -auto parallelism: false +Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + tag: 1 + value expressions: _col1 (type: int) + auto parallelism: false TableScan -alias: c +alias: a Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (value = 60) (type: boolean) Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator -key expressions: key (type: int) -sort order: + -Map-reduce partition columns: key (type: int) + Select Operator +expressions: key (type: int), 60 (type: int) +outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE -tag: 2 -value expressions: value (type: int) -auto parallelism: false +Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + tag: 2 + value expressions: _col1 (type: int) + auto parallelism: false Path -> Alias: A masked pattern was here Path -> Partition: @@ -192,7 +204,7 @@ STAGE PLANS: name: default.a name: default.a Truncated Path -> Alias: -/a [a, b, c] +/a [$hdt$_0:a, $hdt$_1:a, $hdt$_2:a] Needs Tagging: true Reduce Operator Tree: Join Operator @@ -206,37 +218,33 @@ STAGE PLANS: 1 2 keys: -0 key (type: int) -1 key (type: int) -2 key (type: int) - outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 +0 _col0 (type: int) +1 _col0 (type: int) +
[09/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/spark/bucket_map_join_spark3.q.out -- diff --git a/ql/src/test/results/clientpositive/spark/bucket_map_join_spark3.q.out b/ql/src/test/results/clientpositive/spark/bucket_map_join_spark3.q.out index fed923c..4133fda 100644 --- a/ql/src/test/results/clientpositive/spark/bucket_map_join_spark3.q.out +++ b/ql/src/test/results/clientpositive/spark/bucket_map_join_spark3.q.out @@ -173,11 +173,15 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 15 Data size: 1583 Basic stats: COMPLETE Column stats: NONE -Spark HashTable Sink Operator - keys: -0 key (type: int) -1 key (type: int) - Position of Big Table: 1 +Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 15 Data size: 1583 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator +keys: + 0 _col0 (type: int) + 1 _col0 (type: int) +Position of Big Table: 1 Local Work: Map Reduce Local Work Bucket Mapjoin Context: @@ -252,48 +256,52 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE -Map Join Operator - condition map: - Inner Join 0 to 1 - keys: -0 key (type: int) -1 key (type: int) - outputColumnNames: _col0, _col1, _col7 - input vertices: -0 Map 1 - Position of Big Table: 1 - Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE - BucketMapJoin: true - Select Operator -expressions: _col0 (type: int), _col1 (type: string), _col7 (type: string) -outputColumnNames: _col0, _col1, _col2 +Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE + Map Join Operator +condition map: + Inner Join 0 to 1 +keys: + 0 _col0 (type: int) + 1 _col0 (type: int) +outputColumnNames: _col0, _col1, _col3 +input vertices: + 0 Map 1 +Position of Big Table: 1 Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE -File Output Operator - compressed: false - GlobalTableId: 1 - A masked pattern was here - NumFilesPerFileSink: 1 +BucketMapJoin: true +Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE - A masked pattern was here - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: -bucket_count -1 -columns key,value1,value2 -columns.comments -columns.types string:string:string - A masked pattern was here -name default.bucketmapjoin_tmp_result -serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2} -serialization.format 1 -serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - A masked pattern was here -
[04/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual1.q.out -- diff --git a/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual1.q.out b/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual1.q.out index 5a77830..2eb0c3b 100644 --- a/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual1.q.out +++ b/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual1.q.out @@ -79,12 +79,16 @@ STAGE PLANS: Filter Operator predicate: p_name is not null (type: boolean) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE -Reduce Output Operator - key expressions: p_name (type: string) - sort order: + - Map-reduce partition columns: p_name (type: string) +Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: p_partkey (type: int), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + Reduce Output Operator +key expressions: _col1 (type: string) +sort order: + +Map-reduce partition columns: _col1 (type: string) +Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE +value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Map 3 Map Operator Tree: TableScan @@ -93,12 +97,16 @@ STAGE PLANS: Filter Operator predicate: p2_name is not null (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE -Reduce Output Operator - key expressions: p2_name (type: string) - sort order: + - Map-reduce partition columns: p2_name (type: string) +Select Operator + expressions: p2_partkey (type: int), p2_name (type: string), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: p2_partkey (type: int), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) + Reduce Output Operator +key expressions: _col1 (type: string) +sort order: + +Map-reduce partition columns: _col1 (type: string) +Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE +value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Map 4 Map Operator Tree: TableScan @@ -107,12 +115,16 @@ STAGE PLANS: Filter Operator predicate: p3_name is not null (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE -Reduce Output Operator - key expressions: p3_name (type: string) - sort order: + - Map-reduce partition columns: p3_name (type: string) +Select Operator + expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) +
[18/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/skewjoin.q.out -- diff --git a/ql/src/test/results/clientpositive/skewjoin.q.out b/ql/src/test/results/clientpositive/skewjoin.q.out index 22a9421..13c4470 100644 --- a/ql/src/test/results/clientpositive/skewjoin.q.out +++ b/ql/src/test/results/clientpositive/skewjoin.q.out @@ -101,15 +101,14 @@ STAGE PLANS: predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator -expressions: key (type: string), value (type: string) -outputColumnNames: _col0, _col1 +expressions: key (type: string) +outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) TableScan alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -117,14 +116,15 @@ STAGE PLANS: predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator -expressions: key (type: string) -outputColumnNames: _col0 +expressions: key (type: string), value (type: string) +outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: @@ -133,10 +133,10 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col1, _col2 + outputColumnNames: _col0, _col2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator -expressions: UDFToInteger(_col2) (type: int), _col1 (type: string) +expressions: UDFToInteger(_col0) (type: int), _col2 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -175,9 +175,9 @@ STAGE PLANS: keys: 0 reducesinkkey0 (type: string) 1 reducesinkkey0 (type: string) - outputColumnNames: _col1, _col2 + outputColumnNames: _col0, _col2 Select Operator -expressions: UDFToInteger(_col2) (type: int), _col1 (type: string) +expressions: UDFToInteger(_col0) (type: int), _col2 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -595,15 +595,14 @@ STAGE PLANS: predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator -expressions: key (type: string), value (type: string) -outputColumnNames: _col0, _col1 +expressions: key (type: string) +outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -611,14 +610,15 @@ STAGE PLANS: predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
[02/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/spark/join_filters_overlap.q.out -- diff --git a/ql/src/test/results/clientpositive/spark/join_filters_overlap.q.out b/ql/src/test/results/clientpositive/spark/join_filters_overlap.q.out index 0f9d1ae..7ac16d0 100644 --- a/ql/src/test/results/clientpositive/spark/join_filters_overlap.q.out +++ b/ql/src/test/results/clientpositive/spark/join_filters_overlap.q.out @@ -109,14 +109,18 @@ STAGE PLANS: alias: a Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE GatherStats: false - Reduce Output Operator -key expressions: key (type: int) -sort order: + -Map-reduce partition columns: key (type: int) + Select Operator +expressions: key (type: int), value (type: int) +outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE -tag: 0 -value expressions: value (type: int) -auto parallelism: false +Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE + tag: 0 + value expressions: _col1 (type: int) + auto parallelism: false Path -> Alias: A masked pattern was here Path -> Partition: @@ -169,21 +173,25 @@ STAGE PLANS: Map 3 Map Operator Tree: TableScan - alias: b + alias: a Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (value = 50) (type: boolean) Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE -Reduce Output Operator - key expressions: key (type: int) - sort order: + - Map-reduce partition columns: key (type: int) +Select Operator + expressions: key (type: int), 50 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE - tag: 1 - value expressions: value (type: int) - auto parallelism: false + Reduce Output Operator +key expressions: _col0 (type: int) +sort order: + +Map-reduce partition columns: _col0 (type: int) +Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE +tag: 1 +value expressions: _col1 (type: int) +auto parallelism: false Path -> Alias: A masked pattern was here Path -> Partition: @@ -232,25 +240,29 @@ STAGE PLANS: name: default.a name: default.a Truncated Path -> Alias: - /a [b] + /a [a] Map 4 Map Operator Tree: TableScan - alias: c + alias: a Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (value = 60) (type: boolean) Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE -Reduce Output Operator - key expressions: key (type: int) - sort order: + - Map-reduce partition columns: key (type: int) +Select Operator + expressions: key (type: int), 60 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE - tag: 2 - value expressions: value (type: int) - auto parallelism: false + Reduce Output Operator +key expressions: _col0 (type: int) +
[66/91] [abbrv] hive git commit: HIVE-12331 : Remove hive.enforce.bucketing & hive.enforce.sorting configs (Ashutosh Chauhan via Jason Dere)
http://git-wip-us.apache.org/repos/asf/hive/blob/5562fae7/ql/src/test/queries/clientpositive/delete_all_non_partitioned.q -- diff --git a/ql/src/test/queries/clientpositive/delete_all_non_partitioned.q b/ql/src/test/queries/clientpositive/delete_all_non_partitioned.q index 9110dcc..82c18e2 100644 --- a/ql/src/test/queries/clientpositive/delete_all_non_partitioned.q +++ b/ql/src/test/queries/clientpositive/delete_all_non_partitioned.q @@ -1,6 +1,6 @@ set hive.support.concurrency=true; set hive.txn.manager=org.apache.hadoop.hive.ql.lockmgr.DbTxnManager; -set hive.enforce.bucketing=true; + create table acid_danp(a int, b varchar(128)) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='true'); http://git-wip-us.apache.org/repos/asf/hive/blob/5562fae7/ql/src/test/queries/clientpositive/delete_all_partitioned.q -- diff --git a/ql/src/test/queries/clientpositive/delete_all_partitioned.q b/ql/src/test/queries/clientpositive/delete_all_partitioned.q index f082b6d..122b3e2 100644 --- a/ql/src/test/queries/clientpositive/delete_all_partitioned.q +++ b/ql/src/test/queries/clientpositive/delete_all_partitioned.q @@ -1,6 +1,6 @@ set hive.support.concurrency=true; set hive.txn.manager=org.apache.hadoop.hive.ql.lockmgr.DbTxnManager; -set hive.enforce.bucketing=true; + create table acid_dap(a int, b varchar(128)) partitioned by (ds string) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='true'); http://git-wip-us.apache.org/repos/asf/hive/blob/5562fae7/ql/src/test/queries/clientpositive/delete_orig_table.q -- diff --git a/ql/src/test/queries/clientpositive/delete_orig_table.q b/ql/src/test/queries/clientpositive/delete_orig_table.q index fd23f4b..88cc830 100644 --- a/ql/src/test/queries/clientpositive/delete_orig_table.q +++ b/ql/src/test/queries/clientpositive/delete_orig_table.q @@ -1,6 +1,6 @@ set hive.support.concurrency=true; set hive.txn.manager=org.apache.hadoop.hive.ql.lockmgr.DbTxnManager; -set hive.enforce.bucketing=true; + dfs ${system:test.dfs.mkdir} ${system:test.tmp.dir}/delete_orig_table; dfs -copyFromLocal ../../data/files/alltypesorc ${system:test.tmp.dir}/delete_orig_table/0_0; http://git-wip-us.apache.org/repos/asf/hive/blob/5562fae7/ql/src/test/queries/clientpositive/delete_tmp_table.q -- diff --git a/ql/src/test/queries/clientpositive/delete_tmp_table.q b/ql/src/test/queries/clientpositive/delete_tmp_table.q index eb6c095..c7d8aa6 100644 --- a/ql/src/test/queries/clientpositive/delete_tmp_table.q +++ b/ql/src/test/queries/clientpositive/delete_tmp_table.q @@ -1,6 +1,6 @@ set hive.support.concurrency=true; set hive.txn.manager=org.apache.hadoop.hive.ql.lockmgr.DbTxnManager; -set hive.enforce.bucketing=true; + create temporary table acid_dtt(a int, b varchar(128)) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='true'); http://git-wip-us.apache.org/repos/asf/hive/blob/5562fae7/ql/src/test/queries/clientpositive/delete_where_no_match.q -- diff --git a/ql/src/test/queries/clientpositive/delete_where_no_match.q b/ql/src/test/queries/clientpositive/delete_where_no_match.q index 8ed979d..f13dd73 100644 --- a/ql/src/test/queries/clientpositive/delete_where_no_match.q +++ b/ql/src/test/queries/clientpositive/delete_where_no_match.q @@ -1,6 +1,6 @@ set hive.support.concurrency=true; set hive.txn.manager=org.apache.hadoop.hive.ql.lockmgr.DbTxnManager; -set hive.enforce.bucketing=true; + create table acid_dwnm(a int, b varchar(128)) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='true'); http://git-wip-us.apache.org/repos/asf/hive/blob/5562fae7/ql/src/test/queries/clientpositive/delete_where_non_partitioned.q -- diff --git a/ql/src/test/queries/clientpositive/delete_where_non_partitioned.q b/ql/src/test/queries/clientpositive/delete_where_non_partitioned.q index dac5375..de1ca36 100644 --- a/ql/src/test/queries/clientpositive/delete_where_non_partitioned.q +++ b/ql/src/test/queries/clientpositive/delete_where_non_partitioned.q @@ -1,6 +1,6 @@ set hive.support.concurrency=true; set hive.txn.manager=org.apache.hadoop.hive.ql.lockmgr.DbTxnManager; -set hive.enforce.bucketing=true; + create table acid_dwnp(a int, b varchar(128)) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='true'); http://git-wip-us.apache.org/repos/asf/hive/blob/5562fae7/ql/src/test/queries/clientpositive/delete_where_partitioned.q -- diff --git
[85/91] [abbrv] hive git commit: HIVE-12008: Hive queries failing when using count(*) on column in view (Yongzhi Chen, reviewed by Szehon ho)
http://git-wip-us.apache.org/repos/asf/hive/blob/a51e5d4e/ql/src/test/results/clientpositive/union9.q.out -- diff --git a/ql/src/test/results/clientpositive/union9.q.out b/ql/src/test/results/clientpositive/union9.q.out index ec7ab35..5f54210 100644 --- a/ql/src/test/results/clientpositive/union9.q.out +++ b/ql/src/test/results/clientpositive/union9.q.out @@ -24,73 +24,67 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s1 -Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE +Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: value (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Union -Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE +Statistics: Num rows: 1500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Group By Operator aggregations: count(1) mode: hash outputColumnNames: _col0 -Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) TableScan alias: s1 -Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE +Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: value (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Union -Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE +Statistics: Num rows: 1500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Group By Operator aggregations: count(1) mode: hash outputColumnNames: _col0 -Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) TableScan alias: s1 -Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE +Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: value (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Union -Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE +Statistics: Num rows: 1500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE
[77/91] [abbrv] hive git commit: HIVE-12473 : DPP: UDFs on the partition column side does not evaluate correctly (Sergey Shelukhin, reviewed by Gopal V)
HIVE-12473 : DPP: UDFs on the partition column side does not evaluate correctly (Sergey Shelukhin, reviewed by Gopal V) Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/454c2cae Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/454c2cae Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/454c2cae Branch: refs/heads/spark Commit: 454c2cae4f0a3db1f225da6c283c161fe09bfb87 Parents: 74c0c97 Author: Sergey ShelukhinAuthored: Wed Nov 25 12:15:29 2015 -0800 Committer: Sergey Shelukhin Committed: Wed Nov 25 12:15:29 2015 -0800 -- .../ql/exec/tez/DynamicPartitionPruner.java | 40 ++-- 1 file changed, 29 insertions(+), 11 deletions(-) -- http://git-wip-us.apache.org/repos/asf/hive/blob/454c2cae/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/DynamicPartitionPruner.java -- diff --git a/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/DynamicPartitionPruner.java b/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/DynamicPartitionPruner.java index b67ac8d..60b71aa 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/DynamicPartitionPruner.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/DynamicPartitionPruner.java @@ -18,6 +18,12 @@ package org.apache.hadoop.hive.ql.exec.tez; +import org.apache.hadoop.hive.serde2.typeinfo.PrimitiveTypeInfo; + +import org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc; + +import org.apache.hadoop.hive.ql.plan.ExprNodeGenericFuncDesc; + import java.io.DataInputStream; import java.io.IOException; import java.io.InputStream; @@ -242,25 +248,37 @@ public class DynamicPartitionPruner { LOG.debug(sb.toString()); } -ObjectInspector oi = - PrimitiveObjectInspectorFactory.getPrimitiveWritableObjectInspector(TypeInfoFactory -.getPrimitiveTypeInfo(si.fieldInspector.getTypeName())); +ObjectInspector targetOi = findTargetOi(si.partKey, si.columnName); +Converter converter = ObjectInspectorConverters.getConverter( +PrimitiveObjectInspectorFactory.javaStringObjectInspector, targetOi); -Converter converter = -ObjectInspectorConverters.getConverter( -PrimitiveObjectInspectorFactory.javaStringObjectInspector, oi); - -StructObjectInspector soi = -ObjectInspectorFactory.getStandardStructObjectInspector( -Collections.singletonList(columnName), Collections.singletonList(oi)); +StructObjectInspector soi = ObjectInspectorFactory.getStandardStructObjectInspector( +Collections.singletonList(columnName), Collections.singletonList(targetOi)); @SuppressWarnings("rawtypes") ExprNodeEvaluator eval = ExprNodeEvaluatorFactory.get(si.partKey); -eval.initialize(soi); +eval.initialize(soi); // We expect the row with just the relevant column. applyFilterToPartitions(converter, eval, columnName, values); } + private ObjectInspector findTargetOi(ExprNodeDesc expr, String columnName) { +if (expr instanceof ExprNodeColumnDesc) { + ExprNodeColumnDesc colExpr = (ExprNodeColumnDesc)expr; + // TODO: this is not necessarily going to work for all cases. At least, table name is needed. + // Also it's not clear if this is going to work with subquery columns and such. + if (columnName.equals(colExpr.getColumn())) { +return PrimitiveObjectInspectorFactory.getPrimitiveWritableObjectInspector( +(PrimitiveTypeInfo)colExpr.getTypeInfo()); + } +} +for (ExprNodeDesc child : expr.getChildren()) { + ObjectInspector oi = findTargetOi(child, columnName); + if (oi != null) return oi; +} +return null; + } + @SuppressWarnings("rawtypes") private void applyFilterToPartitions(Converter converter, ExprNodeEvaluator eval, String columnName, Set values) throws HiveException {
[91/91] [abbrv] hive git commit: Merge branch 'master' into spark
Merge branch 'master' into spark Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/79035f1c Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/79035f1c Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/79035f1c Branch: refs/heads/spark Commit: 79035f1c520bbc9a900723b5b9c065b67fde636d Parents: eddb8ca 0a96201 Author: Xuefu ZhangAuthored: Sun Nov 29 16:05:29 2015 -0800 Committer: Xuefu Zhang Committed: Sun Nov 29 16:05:29 2015 -0800 -- accumulo-handler/pom.xml|8 +- ant/pom.xml |6 + .../java/org/apache/hive/beeline/BeeLine.java | 13 +- .../apache/hive/beeline/cli/TestHiveCli.java|1 + beeline/src/test/resources/hive-site.xml|5 + bin/ext/version.sh |2 +- bin/hive| 23 +- .../org/apache/hadoop/hive/cli/CliDriver.java | 11 + common/pom.xml | 28 +- .../hadoop/hive/common/StatsSetupConst.java | 13 - .../hive/common/metrics/LegacyMetrics.java | 27 +- .../hive/common/metrics/common/Metrics.java | 28 +- .../common/metrics/common/MetricsConstant.java |6 + .../common/metrics/common/MetricsScope.java | 33 + .../metrics/metrics2/CodahaleMetrics.java | 41 +- .../org/apache/hadoop/hive/conf/HiveConf.java | 96 +- .../apache/hadoop/hive/ql/log/PerfLogger.java | 27 + .../apache/hive/common/util/BloomFilter.java| 18 +- .../org/apache/hive/common/util/Murmur3.java| 107 +- .../hive/http/AdminAuthorizedServlet.java | 45 + .../java/org/apache/hive/http/ConfServlet.java | 101 + .../java/org/apache/hive/http/HttpServer.java | 316 ++ .../org/apache/hive/http/JMXJsonServlet.java| 412 +++ .../hive/common/metrics/MetricsTestUtils.java | 61 + .../hive/common/metrics/TestLegacyMetrics.java | 46 +- .../metrics/metrics2/TestCodahaleMetrics.java | 14 +- .../apache/hive/common/util/TestMurmur3.java| 45 +- data/conf/hive-site.xml |5 + data/conf/llap/hive-site.xml|7 +- data/conf/spark/standalone/hive-site.xml|7 +- data/conf/spark/yarn-client/hive-site.xml |6 +- data/conf/tez/hive-site.xml |9 +- .../hive/hbase/HiveHBaseTableInputFormat.java | 10 + .../test/results/positive/hbase_queries.q.out | 13 +- .../src/test/templates/TestHBaseCliDriver.vm| 63 +- .../templates/TestHBaseNegativeCliDriver.vm | 64 +- .../mapreduce/FosterStorageHandler.java | 37 + .../hive/hcatalog/mapreduce/InputJobInfo.java |8 +- .../rcfile/RCFileMapReduceInputFormat.java |8 +- .../rcfile/TestRCFileMapReduceInputFormat.java |4 +- .../streaming/AbstractRecordWriter.java | 51 +- .../hcatalog/streaming/ConnectionError.java |3 +- .../streaming/DelimitedInputWriter.java |5 +- .../hive/hcatalog/streaming/HiveEndPoint.java | 211 +- .../hcatalog/streaming/StrictJsonWriter.java| 11 +- .../hcatalog/streaming/TransactionBatch.java|1 + .../hcatalog/streaming/TransactionError.java|2 +- .../hive/hcatalog/streaming/TestStreaming.java | 175 +- .../streaming/mutate/StreamingAssert.java |2 + hplsql/pom.xml |5 - itests/hive-unit/pom.xml|7 + ...estDDLWithRemoteMetastoreSecondNamenode.java |3 +- .../hive/ql/txn/compactor/TestCompactor.java| 246 +- .../org/apache/hive/jdbc/TestJdbcDriver2.java | 89 +- .../hive/jdbc/miniHS2/TestHs2Metrics.java | 116 + itests/qtest-accumulo/pom.xml |2 +- .../test/resources/testconfiguration.properties | 23 +- .../hadoop/hive/hbase/HBaseTestSetup.java |9 +- .../org/apache/hadoop/hive/ql/QTestUtil.java| 11 +- jdbc/pom.xml| 52 + .../hive/llap/io/api/impl/LlapInputFormat.java | 40 +- .../hadoop/hive/metastore/HiveMetaStore.java|9 +- .../hive/metastore/MetaStoreDirectSql.java | 12 + .../metastore/txn/CompactionTxnHandler.java | 170 +- .../hadoop/hive/metastore/txn/TxnHandler.java | 533 +++- .../metastore/txn/TestCompactionTxnHandler.java | 37 - .../hive/metastore/txn/TestTxnHandler.java | 10 +- packaging/pom.xml | 15 +- pom.xml | 15 +- ql/pom.xml | 42 +- .../java/org/apache/hadoop/hive/ql/Driver.java | 30 +- .../org/apache/hadoop/hive/ql/ErrorMsg.java |8 +- .../org/apache/hadoop/hive/ql/exec/DDLTask.java |5 +- .../hadoop/hive/ql/exec/FetchOperator.java | 10 +-
[11/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_3.q.out -- diff --git a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_3.q.out b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_3.q.out index 23530bd..ff57c08 100644 --- a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_3.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_3.q.out @@ -142,26 +142,30 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 29 Data size: 2906 Basic stats: COMPLETE Column stats: NONE -Sorted Merge Bucket Map Join Operator - condition map: - Inner Join 0 to 1 - keys: -0 key (type: string) -1 key (type: string) - Position of Big Table: 1 - Statistics: Num rows: 31 Data size: 3196 Basic stats: COMPLETE Column stats: NONE - BucketMapJoin: true - Group By Operator -aggregations: count() -mode: hash -outputColumnNames: _col0 -Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE -Reduce Output Operator - sort order: +Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 29 Data size: 2906 Basic stats: COMPLETE Column stats: NONE + Sorted Merge Bucket Map Join Operator +condition map: + Inner Join 0 to 1 +keys: + 0 _col0 (type: string) + 1 _col0 (type: string) +Position of Big Table: 1 +Statistics: Num rows: 31 Data size: 3196 Basic stats: COMPLETE Column stats: NONE +BucketMapJoin: true +Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Reduce Output Operator +sort order: +Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +tag: -1 +value expressions: _col0 (type: bigint) +auto parallelism: false Path -> Alias: A masked pattern was here Path -> Partition: @@ -214,7 +218,7 @@ STAGE PLANS: name: default.bucket_big name: default.bucket_big Truncated Path -> Alias: - /bucket_big/ds=2008-04-08 [b] + /bucket_big/ds=2008-04-08 [$hdt$_1:b] Reducer 2 Needs Tagging: false Reduce Operator Tree: @@ -326,26 +330,30 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 29 Data size: 2906 Basic stats: COMPLETE Column stats: NONE -Sorted Merge Bucket Map Join Operator - condition map: - Inner Join 0 to 1 - keys: -0 key (type: string) -1 key (type: string) - Position of Big Table: 0 - Statistics: Num rows: 31 Data size: 3196 Basic stats: COMPLETE Column stats: NONE - BucketMapJoin: true - Group By Operator -aggregations: count() -mode: hash -outputColumnNames: _col0 -Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE -Reduce Output Operator - sort order: +Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 29 Data size: 2906 Basic stats: COMPLETE Column stats: NONE + Sorted Merge Bucket Map Join Operator +condition
[51/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan) Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/7dab21ac Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/7dab21ac Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/7dab21ac Branch: refs/heads/spark Commit: 7dab21acffdd43e80e6fefb5011139bbf30fa541 Parents: 55b589e Author: Jesus Camacho RodriguezAuthored: Sat Nov 14 09:12:49 2015 +0100 Committer: Jesus Camacho Rodriguez Committed: Fri Nov 20 23:31:11 2015 +0100 -- .../test/results/positive/hbase_queries.q.out | 12 +- .../ql/optimizer/calcite/HiveRelOptUtil.java| 40 + .../rules/HiveAggregateProjectMergeRule.java| 13 +- .../translator/SqlFunctionConverter.java|8 + .../hadoop/hive/ql/parse/CalcitePlanner.java| 169 +- .../hadoop/hive/ql/parse/SemanticAnalyzer.java | 16 - ql/src/test/queries/clientpositive/mergejoin.q |9 + .../bucket_mapjoin_mismatch1.q.out | 36 +- .../clientnegative/join_nonexistent_part.q.out |1 - .../annotate_stats_join_pkfk.q.out | 230 +- .../archive_excludeHadoop20.q.out |1 + .../results/clientpositive/archive_multi.q.out |1 + .../results/clientpositive/auto_join1.q.out | 12 +- .../results/clientpositive/auto_join10.q.out| 12 +- .../results/clientpositive/auto_join11.q.out| 12 +- .../results/clientpositive/auto_join14.q.out|8 +- .../results/clientpositive/auto_join24.q.out| 54 +- .../results/clientpositive/auto_join26.q.out| 30 +- .../results/clientpositive/auto_join32.q.out| 153 +- .../clientpositive/auto_join_filters.q.out | 12 +- .../clientpositive/auto_join_nulls.q.out|2 +- .../auto_join_reordering_values.q.out | 152 +- .../clientpositive/auto_join_stats.q.out| 392 ++-- .../clientpositive/auto_join_stats2.q.out | 214 +- .../clientpositive/auto_smb_mapjoin_14.q.out| 145 +- .../clientpositive/auto_sortmerge_join_1.q.out | 240 +- .../clientpositive/auto_sortmerge_join_10.q.out | 103 +- .../clientpositive/auto_sortmerge_join_11.q.out | 124 +- .../clientpositive/auto_sortmerge_join_12.q.out | 177 +- .../clientpositive/auto_sortmerge_join_14.q.out | 152 +- .../clientpositive/auto_sortmerge_join_15.q.out | 152 +- .../clientpositive/auto_sortmerge_join_2.q.out | 198 +- .../clientpositive/auto_sortmerge_join_3.q.out | 234 +- .../clientpositive/auto_sortmerge_join_4.q.out | 234 +- .../clientpositive/auto_sortmerge_join_5.q.out | 232 +- .../clientpositive/auto_sortmerge_join_6.q.out | 1140 -- .../clientpositive/auto_sortmerge_join_7.q.out | 242 +- .../clientpositive/auto_sortmerge_join_8.q.out | 242 +- .../clientpositive/auto_sortmerge_join_9.q.out | 1240 +- .../clientpositive/bucket_map_join_spark1.q.out | 206 +- .../clientpositive/bucket_map_join_spark2.q.out | 206 +- .../clientpositive/bucket_map_join_spark3.q.out | 206 +- .../clientpositive/bucket_map_join_spark4.q.out | 236 +- .../bucketsortoptimize_insert_2.q.out | 218 +- .../bucketsortoptimize_insert_4.q.out | 112 +- .../bucketsortoptimize_insert_5.q.out | 142 +- .../bucketsortoptimize_insert_6.q.out | 554 +++-- .../bucketsortoptimize_insert_7.q.out | 48 +- .../bucketsortoptimize_insert_8.q.out | 76 +- .../cbo_rp_cross_product_check_2.q.out | 468 ++-- .../results/clientpositive/cbo_rp_join1.q.out | 60 +- .../clientpositive/cbo_rp_lineage2.q.out| 18 +- .../clientpositive/column_access_stats.q.out| 84 +- .../results/clientpositive/constprog2.q.out | 20 +- .../clientpositive/constprog_partitioner.q.out | 10 +- .../clientpositive/correlationoptimizer1.q.out | 886 .../clientpositive/correlationoptimizer11.q.out | 120 +- .../clientpositive/correlationoptimizer13.q.out | 26 +- .../clientpositive/correlationoptimizer4.q.out | 972 .../clientpositive/correlationoptimizer5.q.out | 248 +- .../clientpositive/correlationoptimizer9.q.out | 250 +- .../results/clientpositive/create_view.q.out|2 +- .../clientpositive/cross_product_check_1.q.out | 252 ++- .../clientpositive/cross_product_check_2.q.out | 332 +-- .../results/clientpositive/decimal_join2.q.out | 90 +- .../clientpositive/dynamic_rdd_cache.q.out | 265 ++- .../encryption_join_unencrypted_tbl.q.out | 98 +- ...on_join_with_different_encryption_keys.q.out | 102 +- .../clientpositive/explain_logical.q.out| 142 +- .../clientpositive/explain_rearrange.q.out | 288 +-- .../clientpositive/filter_join_breaktask.q.out | 86 +-
[37/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/explain_rearrange.q.out -- diff --git a/ql/src/test/results/clientpositive/explain_rearrange.q.out b/ql/src/test/results/clientpositive/explain_rearrange.q.out index a4671d3..ead3024 100644 --- a/ql/src/test/results/clientpositive/explain_rearrange.q.out +++ b/ql/src/test/results/clientpositive/explain_rearrange.q.out @@ -80,23 +80,27 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Sorted Merge Bucket Map Join Operator -condition map: - Inner Join 0 to 1 -keys: - 0 key (type: int) - 1 key (type: int) + Select Operator +expressions: key (type: int) outputColumnNames: _col0 -Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator -key expressions: _col0 (type: int) -sort order: + -Map-reduce partition columns: _col0 (type: int) -value expressions: _col1 (type: bigint) +Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE +Sorted Merge Bucket Map Join Operator + condition map: + Inner Join 0 to 1 + keys: +0 _col0 (type: int) +1 _col0 (type: int) + outputColumnNames: _col0 + Group By Operator +aggregations: count() +keys: _col0 (type: int) +mode: hash +outputColumnNames: _col0, _col1 +Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -247,23 +251,27 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Sorted Merge Bucket Map Join Operator -condition map: - Inner Join 0 to 1 -keys: - 0 key (type: int) - 1 key (type: int) + Select Operator +expressions: key (type: int) outputColumnNames: _col0 -Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator -key expressions: _col0 (type: int) -sort order: + -Map-reduce partition columns: _col0 (type: int) -value expressions: _col1 (type: bigint) +Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE +Sorted Merge Bucket Map Join Operator + condition map: + Inner Join 0 to 1 + keys: +0 _col0 (type: int) +1 _col0 (type: int) + outputColumnNames: _col0 + Group By Operator +aggregations: count() +keys: _col0 (type: int) +mode: hash +outputColumnNames: _col0, _col1 +Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -345,23 +353,27 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Sorted Merge Bucket Map Join Operator -condition map: - Inner Join 0 to 1 -keys: - 0 key (type: int) - 1 key (type: int) + Select Operator +expressions: key (type: int) outputColumnNames: _col0 -
[17/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/skewjoin_mapjoin5.q.out -- diff --git a/ql/src/test/results/clientpositive/skewjoin_mapjoin5.q.out b/ql/src/test/results/clientpositive/skewjoin_mapjoin5.q.out index 261802b..0ac90df 100644 --- a/ql/src/test/results/clientpositive/skewjoin_mapjoin5.q.out +++ b/ql/src/test/results/clientpositive/skewjoin_mapjoin5.q.out @@ -69,21 +69,25 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: -b +$hdt$_1:b Fetch Operator limit: -1 Alias -> Map Local Operator Tree: -b +$hdt$_1:b TableScan alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator -keys: - 0 _col0 (type: string) - 1 key (type: string) + Select Operator +expressions: key (type: string), val (type: string) +outputColumnNames: _col0, _col1 +Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE +HashTable Sink Operator + keys: +0 _col0 (type: string) +1 _col0 (type: string) Stage: Stage-4 Map Reduce @@ -105,20 +109,16 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 _col0 (type: string) - 1 key (type: string) + 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE -Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 +File Output Operator + compressed: false Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator -compressed: false -Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE -table: -input format: org.apache.hadoop.mapred.TextInputFormat -output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat -serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: t1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -136,20 +136,16 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 _col0 (type: string) - 1 key (type: string) + 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE -Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 +File Output Operator + compressed: false Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator -compressed: false -Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE -table: -input format: org.apache.hadoop.mapred.TextInputFormat -output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat -serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde:
[90/91] [abbrv] hive git commit: HIVE-12497: Remove HADOOP_CLIENT_OPTS from hive script (Prasanth Jayachandran reviewed by Gopal V)
HIVE-12497: Remove HADOOP_CLIENT_OPTS from hive script (Prasanth Jayachandran reviewed by Gopal V) Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/0a96201f Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/0a96201f Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/0a96201f Branch: refs/heads/spark Commit: 0a96201f268a8cf0efe71d960f8814592d30d756 Parents: 2c0c191 Author: Prasanth JayachandranAuthored: Sun Nov 29 16:53:20 2015 -0600 Committer: Prasanth Jayachandran Committed: Sun Nov 29 16:53:20 2015 -0600 -- bin/ext/version.sh | 2 +- bin/hive | 23 ++- 2 files changed, 19 insertions(+), 6 deletions(-) -- http://git-wip-us.apache.org/repos/asf/hive/blob/0a96201f/bin/ext/version.sh -- diff --git a/bin/ext/version.sh b/bin/ext/version.sh index bb6449d..b6a237b 100644 --- a/bin/ext/version.sh +++ b/bin/ext/version.sh @@ -27,7 +27,7 @@ version () { # hadoop 20 or newer - skip the aux_jars option and hiveconf CLASS=org.apache.hive.common.util.HiveVersionInfo - exec $HADOOP jar $JAR $CLASS + exec $HADOOP jar $JAR $CLASS 2>> ${STDERR} } version_help () { http://git-wip-us.apache.org/repos/asf/hive/blob/0a96201f/bin/hive -- diff --git a/bin/hive b/bin/hive index 47d99f7..4818667 100755 --- a/bin/hive +++ b/bin/hive @@ -25,6 +25,8 @@ bin=`cd "$bin"; pwd` . "$bin"/hive-config.sh +TMP_USER_DIR="/tmp/${USER}" +STDERR="${TMP_USER_DIR}/stderr" SERVICE="" HELP="" while [ $# -gt 0 ]; do @@ -193,18 +195,29 @@ if [ "$HADOOP_HOME" == "" ]; then exit 4; fi -# to avoid errors from log4j2 automatic configuration loading -export HADOOP_CLIENT_OPTS="$HADOOP_CLIENT_OPTS -Dlog4j.configurationFile=hive-log4j2.xml " - HADOOP=$HADOOP_HOME/bin/hadoop if [ ! -f ${HADOOP} ]; then echo "Cannot find hadoop installation: \$HADOOP_HOME or \$HADOOP_PREFIX must be set or hadoop must be in the path"; exit 4; fi +if [ ! -d ${TMP_USER_DIR} ]; then + mkdir -p ${TMP_USER_DIR} 2> /dev/null + if [ $? -ne 0 ]; then +STDERR="/dev/tty" + fi +fi + +if [ "${STDERR}" != "/dev/null" ] && [ ! -f ${STDERR} ]; then + touch ${STDERR} 2> /dev/null + if [ $? -ne 0 ]; then +STDERR="/dev/tty" + fi +fi + # Make sure we're using a compatible version of Hadoop if [ "x$HADOOP_VERSION" == "x" ]; then -HADOOP_VERSION=$($HADOOP version | awk -F"\t" '/Hadoop/ {print $0}' | cut -d' ' -f 2); +HADOOP_VERSION=$($HADOOP version 2>> ${STDERR} | awk -F"\t" '/Hadoop/ {print $0}' | cut -d' ' -f 2); fi # Save the regex to a var to workaround quoting incompatabilities @@ -253,7 +266,7 @@ HBASE_BIN=${HBASE_BIN:-"$(which hbase)"} if [[ -n $HBASE_BIN ]] ; then # exclude ZK, PB, and Guava (See HIVE-2055) # depends on HBASE-8438 (hbase-0.94.14+, hbase-0.96.1+) for `hbase mapredcp` command - for x in $($HBASE_BIN mapredcp | tr ':' '\n') ; do + for x in $($HBASE_BIN mapredcp 2>> ${STDERR} | tr ':' '\n') ; do if [[ $x == *zookeeper* || $x == *protobuf-java* || $x == *guava* ]] ; then continue fi
[70/91] [abbrv] hive git commit: HIVE-12329 :Turn on limit pushdown optimization by default (Ashutosh Chauhan via Prasanth J)
HIVE-12329 :Turn on limit pushdown optimization by default (Ashutosh Chauhan via Prasanth J) Signed-off-by: Ashutosh ChauhanProject: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/daf46aa7 Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/daf46aa7 Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/daf46aa7 Branch: refs/heads/spark Commit: daf46aa768bdb6745fe1509bcf98aad537be367b Parents: 5562fae Author: Ashutosh Chauhan Authored: Tue Nov 3 17:26:00 2015 -0800 Committer: Ashutosh Chauhan Committed: Tue Nov 24 18:11:41 2015 -0800 -- .../org/apache/hadoop/hive/conf/HiveConf.java | 4 +-- .../clientpositive/annotate_stats_select.q.out | 4 +++ .../auto_join_without_localtask.q.out | 3 +++ .../results/clientpositive/bucket_groupby.q.out | 10 .../results/clientpositive/bucketmapjoin7.q.out | 2 ++ ql/src/test/results/clientpositive/cp_sel.q.out | 3 ++- ql/src/test/results/clientpositive/ctas.q.out | 12 + .../results/clientpositive/ctas_colname.q.out | 2 ++ .../dynpart_sort_opt_vectorization.q.out| 3 +++ .../dynpart_sort_optimization.q.out | 3 +++ .../encryption_insert_partition_dynamic.q.out | 2 ++ .../test/results/clientpositive/gby_star.q.out | 4 +++ .../results/clientpositive/groupby1_limit.q.out | 2 ++ .../results/clientpositive/groupby2_limit.q.out | 1 + .../groupby7_noskew_multi_single_reducer.q.out | 2 ++ ...pby_complex_types_multi_single_reducer.q.out | 2 ++ .../groupby_multi_single_reducer.q.out | 1 + .../results/clientpositive/input11_limit.q.out | 1 + .../results/clientpositive/input14_limit.q.out | 2 ++ .../results/clientpositive/input1_limit.q.out | 2 ++ .../test/results/clientpositive/input22.q.out | 1 + .../test/results/clientpositive/input25.q.out | 2 ++ .../test/results/clientpositive/input26.q.out | 2 ++ .../results/clientpositive/input3_limit.q.out | 2 ++ .../results/clientpositive/input4_limit.q.out | 2 ++ .../results/clientpositive/input_part10.q.out | 1 + .../insert1_overwrite_partitions.q.out | 2 ++ .../insert2_overwrite_partitions.q.out | 2 ++ .../results/clientpositive/insert_into1.q.out | 3 +++ .../results/clientpositive/insert_into2.q.out | 3 +++ .../results/clientpositive/insert_into3.q.out | 4 +++ .../results/clientpositive/insert_into4.q.out | 2 ++ .../results/clientpositive/insert_into5.q.out | 1 + .../results/clientpositive/insert_into6.q.out | 1 + .../test/results/clientpositive/join_vc.q.out | 1 + .../results/clientpositive/lateral_view.q.out | 3 +++ .../clientpositive/lateral_view_explode2.q.out | 2 ++ .../clientpositive/lateral_view_noalias.q.out | 4 +++ .../clientpositive/lateral_view_onview.q.out| 3 +++ .../clientpositive/load_dyn_part14.q.out| 3 +++ ql/src/test/results/clientpositive/merge4.q.out | 2 ++ .../nonreserved_keywords_insert_into1.q.out | 3 +++ .../results/clientpositive/orc_createas1.q.out | 1 + .../clientpositive/orc_predicate_pushdown.q.out | 6 + ql/src/test/results/clientpositive/order.q.out | 2 ++ ql/src/test/results/clientpositive/order2.q.out | 1 + .../parquet_predicate_pushdown.q.out| 8 ++ ql/src/test/results/clientpositive/pcr.q.out| 2 ++ .../test/results/clientpositive/regex_col.q.out | 1 + .../results/clientpositive/script_pipe.q.out| 1 + .../clientpositive/select_as_omitted.q.out | 1 + .../clientpositive/skewjoin_noskew.q.out| 1 + .../results/clientpositive/smb_mapjoin_13.q.out | 4 +++ .../results/clientpositive/smb_mapjoin_15.q.out | 8 ++ .../spark/auto_join_without_localtask.q.out | 3 +++ .../clientpositive/spark/bucketmapjoin7.q.out | 2 ++ .../results/clientpositive/spark/ctas.q.out | 12 + .../groupby7_noskew_multi_single_reducer.q.out | 1 + ...pby_complex_types_multi_single_reducer.q.out | 2 ++ .../spark/groupby_multi_single_reducer.q.out| 1 + .../clientpositive/spark/input1_limit.q.out | 2 ++ .../clientpositive/spark/insert_into1.q.out | 3 +++ .../clientpositive/spark/insert_into2.q.out | 3 +++ .../clientpositive/spark/insert_into3.q.out | 18 - .../results/clientpositive/spark/join_vc.q.out | 1 + .../spark/lateral_view_explode2.q.out | 2 ++ .../clientpositive/spark/load_dyn_part14.q.out | 1 + .../results/clientpositive/spark/order.q.out| 2 ++ .../results/clientpositive/spark/order2.q.out | 1 + .../test/results/clientpositive/spark/pcr.q.out | 2 ++ .../clientpositive/spark/script_pipe.q.out | 1 + .../clientpositive/spark/skewjoin_noskew.q.out | 1 + .../clientpositive/spark/smb_mapjoin_13.q.out | 4 +++
[72/91] [abbrv] hive git commit: HIVE-12463: VectorMapJoinFastKeyStore has Array OOB errors (Gopal V, reviewed by Sergey Shelukhin)
HIVE-12463: VectorMapJoinFastKeyStore has Array OOB errors (Gopal V, reviewed by Sergey Shelukhin) Signed-off-by: Gopal VProject: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/f1803799 Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/f1803799 Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/f1803799 Branch: refs/heads/spark Commit: f180379955bce04e81c4f799f16d184d74f7ef4c Parents: 6325122 Author: Gopal V Authored: Wed Nov 25 01:01:15 2015 -0800 Committer: Gopal V Committed: Wed Nov 25 01:01:15 2015 -0800 -- .../mapjoin/fast/VectorMapJoinFastKeyStore.java | 17 ++--- .../apache/hadoop/hive/serde2/WriteBuffers.java | 69 ++-- 2 files changed, 38 insertions(+), 48 deletions(-) -- http://git-wip-us.apache.org/repos/asf/hive/blob/f1803799/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/mapjoin/fast/VectorMapJoinFastKeyStore.java -- diff --git a/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/mapjoin/fast/VectorMapJoinFastKeyStore.java b/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/mapjoin/fast/VectorMapJoinFastKeyStore.java index 58af4eb..efdcd43 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/mapjoin/fast/VectorMapJoinFastKeyStore.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/mapjoin/fast/VectorMapJoinFastKeyStore.java @@ -30,7 +30,6 @@ public class VectorMapJoinFastKeyStore { private WriteBuffers writeBuffers; - private WriteBuffers.ByteSegmentRef byteSegmentRef; private WriteBuffers.Position readPos; /** @@ -141,17 +140,11 @@ public class VectorMapJoinFastKeyStore { } // Our reading is positioned to the key. -writeBuffers.getByteSegmentRefToCurrent(byteSegmentRef, keyLength, readPos); - -byte[] currentBytes = byteSegmentRef.getBytes(); -int currentStart = (int) byteSegmentRef.getOffset(); - -for (int i = 0; i < keyLength; i++) { - if (currentBytes[currentStart + i] != keyBytes[keyStart + i]) { -// LOG.debug("VectorMapJoinFastKeyStore equalKey no match on bytes"); -return false; - } +if (!writeBuffers.isEqual(keyBytes, keyStart, readPos, keyLength)) { + // LOG.debug("VectorMapJoinFastKeyStore equalKey no match on bytes"); + return false; } + // LOG.debug("VectorMapJoinFastKeyStore equalKey match on bytes"); return true; } @@ -159,7 +152,6 @@ public class VectorMapJoinFastKeyStore { public VectorMapJoinFastKeyStore(int writeBuffersSize) { writeBuffers = new WriteBuffers(writeBuffersSize, AbsoluteKeyOffset.maxSize); -byteSegmentRef = new WriteBuffers.ByteSegmentRef(); readPos = new WriteBuffers.Position(); } @@ -167,7 +159,6 @@ public class VectorMapJoinFastKeyStore { // TODO: Check if maximum size compatible with AbsoluteKeyOffset.maxSize. this.writeBuffers = writeBuffers; -byteSegmentRef = new WriteBuffers.ByteSegmentRef(); readPos = new WriteBuffers.Position(); } } http://git-wip-us.apache.org/repos/asf/hive/blob/f1803799/serde/src/java/org/apache/hadoop/hive/serde2/WriteBuffers.java -- diff --git a/serde/src/java/org/apache/hadoop/hive/serde2/WriteBuffers.java b/serde/src/java/org/apache/hadoop/hive/serde2/WriteBuffers.java index b47456e..5900428 100644 --- a/serde/src/java/org/apache/hadoop/hive/serde2/WriteBuffers.java +++ b/serde/src/java/org/apache/hadoop/hive/serde2/WriteBuffers.java @@ -282,32 +282,33 @@ public final class WriteBuffers implements RandomAccessOutput { return true; } - /** - * Compares part of the buffer with a part of an external byte array. - * Does not modify readPoint. - */ - public boolean isEqual(byte[] left, int leftLength, long rightOffset, int rightLength) { -if (rightLength != leftLength) { - return false; + private final boolean isEqual(byte[] left, int leftOffset, int rightIndex, int rightFrom, int length) { +if (length == 0) { + return true; } -int rightIndex = getBufferIndex(rightOffset), rightFrom = getOffset(rightOffset); +// invariant: rightLength = leftLength +// rightOffset is within the buffers byte[] rightBuffer = writeBuffers.get(rightIndex); -if (rightFrom + rightLength <= wbSize) { +if (rightFrom + length <= wbSize) { // TODO: allow using unsafe optionally. - for (int i = 0; i < leftLength; ++i) { -if (left[i] != rightBuffer[rightFrom + i]) { + // bounds check first, to trigger bugs whether the first byte matches or not + if (left[leftOffset + length - 1] != rightBuffer[rightFrom + length - 1]) { +return false; + } + for
[16/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/skewjoinopt1.q.out -- diff --git a/ql/src/test/results/clientpositive/skewjoinopt1.q.out b/ql/src/test/results/clientpositive/skewjoinopt1.q.out index f3aa0f7..b863188 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt1.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt1.q.out @@ -62,43 +62,47 @@ STAGE PLANS: Filter Operator predicate: (key is not null and ((key = '2') or (key = '3'))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator -key expressions: key (type: string) -sort order: + -Map-reduce partition columns: key (type: string) + Select Operator +expressions: key (type: string), val (type: string) +outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE -value expressions: val (type: string) +Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) TableScan alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key is not null and ((key = '2') or (key = '3'))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator -key expressions: key (type: string) -sort order: + -Map-reduce partition columns: key (type: string) + Select Operator +expressions: key (type: string), val (type: string) +outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE -value expressions: val (type: string) +Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: -0 key (type: string) -1 key (type: string) - outputColumnNames: _col0, _col1, _col5, _col6 +0 _col0 (type: string) +1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE - Select Operator -expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) -outputColumnNames: _col0, _col1, _col2, _col3 -Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE -File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator +compressed: false +table: +input format: org.apache.hadoop.mapred.SequenceFileInputFormat +output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat +serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -133,40 +137,44 @@ STAGE PLANS: Filter Operator predicate: (key is not null and (not ((key = '2') or (key = '3' (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator -key expressions: key (type: string) -sort order: + -Map-reduce partition columns: key (type: string) + Select Operator +expressions: key (type: string), val (type: string) +outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE -value expressions: val (type: string) +
[15/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/skewjoinopt16.q.out -- diff --git a/ql/src/test/results/clientpositive/skewjoinopt16.q.out b/ql/src/test/results/clientpositive/skewjoinopt16.q.out index 937a65d..15b3e62 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt16.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt16.q.out @@ -64,41 +64,45 @@ STAGE PLANS: Filter Operator predicate: ((key is not null and val is not null) and (((key = '2') and (val = '12')) or (key = '3'))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator -key expressions: key (type: string), val (type: string) -sort order: ++ -Map-reduce partition columns: key (type: string), val (type: string) + Select Operator +expressions: key (type: string), val (type: string) +outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE +Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE TableScan alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key is not null and val is not null) and (((key = '2') and (val = '12')) or (key = '3'))) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator -key expressions: key (type: string), val (type: string) -sort order: ++ -Map-reduce partition columns: key (type: string), val (type: string) + Select Operator +expressions: key (type: string), val (type: string) +outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE +Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: -0 key (type: string), val (type: string) -1 key (type: string), val (type: string) - outputColumnNames: _col0, _col1, _col5, _col6 +0 _col0 (type: string), _col1 (type: string) +1 _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE - Select Operator -expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) -outputColumnNames: _col0, _col1, _col2, _col3 -Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE -File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator +compressed: false +table: +input format: org.apache.hadoop.mapred.SequenceFileInputFormat +output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat +serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -133,38 +137,42 @@ STAGE PLANS: Filter Operator predicate: ((key is not null and val is not null) and (not (((key = '2') and (val = '12')) or (key = '3' (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator -key expressions: key (type: string), val (type: string) -sort order: ++ -Map-reduce partition columns: key (type: string), val (type: string) + Select Operator +expressions: key (type: string), val (type: string) +
[61/91] [abbrv] hive git commit: HIVE-12509: Regenerate q files after HIVE-12017 went in (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
HIVE-12509: Regenerate q files after HIVE-12017 went in (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan) Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/c6a835c4 Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/c6a835c4 Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/c6a835c4 Branch: refs/heads/spark Commit: c6a835c432ac161611ee75eab3cbb34cda414de3 Parents: ab98ffc Author: Jesus Camacho RodriguezAuthored: Tue Nov 24 17:08:20 2015 +0100 Committer: Jesus Camacho Rodriguez Committed: Tue Nov 24 17:14:48 2015 +0100 -- .../results/clientpositive/subquery_notin.q.out | 328 ++- .../subquery_notin_having.q.java1.7.out | 94 +++--- .../clientpositive/tez/explainuser_1.q.out | 171 +- .../tez/tez_dynpart_hashjoin_3.q.out| 150 - .../clientpositive/tez/tez_smb_empty.q.out | 38 ++- 5 files changed, 398 insertions(+), 383 deletions(-) -- http://git-wip-us.apache.org/repos/asf/hive/blob/c6a835c4/ql/src/test/results/clientpositive/subquery_notin.q.out -- diff --git a/ql/src/test/results/clientpositive/subquery_notin.q.out b/ql/src/test/results/clientpositive/subquery_notin.q.out index 552999d..56553fd 100644 --- a/ql/src/test/results/clientpositive/subquery_notin.q.out +++ b/ql/src/test/results/clientpositive/subquery_notin.q.out @@ -1,4 +1,4 @@ -Warning: Shuffle Join JOIN[23][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[20][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: -- non agg, non corr explain select * @@ -18,70 +18,64 @@ where src.key not in ) POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-4 - Stage-4 is a root stage + Stage-3 is a root stage + Stage-1 depends on stages: Stage-3 + Stage-2 depends on stages: Stage-1 Stage-0 depends on stages: Stage-2 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-3 Map Reduce Map Operator Tree: TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE -Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator -key expressions: _col0 (type: string) -sort order: + -Map-reduce partition columns: _col0 (type: string) -Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE -value expressions: _col1 (type: string) - TableScan -alias: src -Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key > '2') (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + predicate: ((key > '2') and key is null) (type: boolean) + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator -expressions: key (type: string) -outputColumnNames: _col0 -Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE -Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE +Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE +Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator +sort order: +Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +value expressions: _col0 (type: bigint) Reduce Operator Tree: -Join Operator - condition map: - Left Outer Join0 to 1 - keys: -0 _col0 (type: string) -1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows:
[54/91] [abbrv] hive git commit: HIVE-12389 CompactionTxnHandler.cleanEmptyAbortedTxns() should safeguard against huge IN clauses (Eugene Koifman, reviewed by Jason Dere)
HIVE-12389 CompactionTxnHandler.cleanEmptyAbortedTxns() should safeguard against huge IN clauses (Eugene Koifman, reviewed by Jason Dere) Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/695d905b Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/695d905b Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/695d905b Branch: refs/heads/spark Commit: 695d905bd3fb27ffb04b28e11d5bd7210321b755 Parents: 8e9bae2 Author: Eugene KoifmanAuthored: Mon Nov 23 08:18:07 2015 -0800 Committer: Eugene Koifman Committed: Mon Nov 23 08:18:07 2015 -0800 -- .../metastore/txn/CompactionTxnHandler.java | 47 .../hadoop/hive/metastore/txn/TxnHandler.java | 11 +++-- .../hive/ql/txn/compactor/TestInitiator.java| 5 ++- 3 files changed, 38 insertions(+), 25 deletions(-) -- http://git-wip-us.apache.org/repos/asf/hive/blob/695d905b/metastore/src/java/org/apache/hadoop/hive/metastore/txn/CompactionTxnHandler.java -- diff --git a/metastore/src/java/org/apache/hadoop/hive/metastore/txn/CompactionTxnHandler.java b/metastore/src/java/org/apache/hadoop/hive/metastore/txn/CompactionTxnHandler.java index 5e4c7be..3e0e656 100644 --- a/metastore/src/java/org/apache/hadoop/hive/metastore/txn/CompactionTxnHandler.java +++ b/metastore/src/java/org/apache/hadoop/hive/metastore/txn/CompactionTxnHandler.java @@ -361,14 +361,13 @@ public class CompactionTxnHandler extends TxnHandler { "marking compaction entry as clean!"); } -//todo: add distinct in query -s = "select txn_id from TXNS, TXN_COMPONENTS where txn_id = tc_txnid and txn_state = '" + +s = "select distinct txn_id from TXNS, TXN_COMPONENTS where txn_id = tc_txnid and txn_state = '" + TXN_ABORTED + "' and tc_database = '" + info.dbname + "' and tc_table = '" + info.tableName + "'"; if (info.partName != null) s += " and tc_partition = '" + info.partName + "'"; LOG.debug("Going to execute update <" + s + ">"); rs = stmt.executeQuery(s); -Set txnids = new HashSet(); +List txnids = new ArrayList<>(); while (rs.next()) txnids.add(rs.getLong(1)); if (txnids.size() > 0) { @@ -437,23 +436,21 @@ public class CompactionTxnHandler extends TxnHandler { "txn_state = '" + TXN_ABORTED + "'"; LOG.debug("Going to execute query <" + s + ">"); rs = stmt.executeQuery(s); -Set txnids = new HashSet(); +List txnids = new ArrayList<>(); while (rs.next()) txnids.add(rs.getLong(1)); -if (txnids.size() > 0) { - StringBuilder buf = new StringBuilder("delete from TXNS where txn_id in ("); - boolean first = true; - for (long tid : txnids) { -if (first) first = false; -else buf.append(", "); -buf.append(tid); - } - buf.append(")"); - String bufStr = buf.toString(); - LOG.debug("Going to execute update <" + bufStr + ">"); - int rc = stmt.executeUpdate(bufStr); - LOG.info("Removed " + rc + " empty Aborted transactions: " + txnids + " from TXNS"); - LOG.debug("Going to commit"); - dbConn.commit(); +close(rs); +if(txnids.size() <= 0) { + return; +} +for(int i = 0; i < txnids.size() / TIMED_OUT_TXN_ABORT_BATCH_SIZE; i++) { + List txnIdBatch = txnids.subList(i * TIMED_OUT_TXN_ABORT_BATCH_SIZE, +(i + 1) * TIMED_OUT_TXN_ABORT_BATCH_SIZE); + deleteTxns(dbConn, stmt, txnIdBatch); +} +int partialBatchSize = txnids.size() % TIMED_OUT_TXN_ABORT_BATCH_SIZE; +if(partialBatchSize > 0) { + List txnIdBatch = txnids.subList(txnids.size() - partialBatchSize, txnids.size()); + deleteTxns(dbConn, stmt, txnIdBatch); } } catch (SQLException e) { LOG.error("Unable to delete from txns table " + e.getMessage()); @@ -469,6 +466,18 @@ public class CompactionTxnHandler extends TxnHandler { cleanEmptyAbortedTxns(); } } + private static void deleteTxns(Connection dbConn, Statement stmt, List txnIdBatch) throws SQLException { +StringBuilder buf = new StringBuilder("delete from TXNS where txn_id in ("); +for(long txnid : txnIdBatch) { + buf.append(txnid).append(','); +} +buf.setCharAt(buf.length() - 1, ')'); +LOG.debug("Going to execute update <" + buf + ">"); +int rc = stmt.executeUpdate(buf.toString()); +LOG.info("Removed " + rc + " empty Aborted transactions: " + txnIdBatch + " from TXNS"); +LOG.debug("Going to commit"); +dbConn.commit(); + } /**
[22/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/mergejoins_mixed.q.out -- diff --git a/ql/src/test/results/clientpositive/mergejoins_mixed.q.out b/ql/src/test/results/clientpositive/mergejoins_mixed.q.out index 023f755..def3b91 100644 --- a/ql/src/test/results/clientpositive/mergejoins_mixed.q.out +++ b/ql/src/test/results/clientpositive/mergejoins_mixed.q.out @@ -29,39 +29,55 @@ STAGE PLANS: TableScan alias: a Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE -Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) +Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: value (type: string) + Reduce Output Operator +key expressions: _col0 (type: string) +sort order: + +Map-reduce partition columns: _col0 (type: string) +Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE +value expressions: _col1 (type: string) TableScan -alias: b +alias: a Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE -Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) +Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: value (type: string) + Reduce Output Operator +key expressions: _col0 (type: string) +sort order: + +Map-reduce partition columns: _col0 (type: string) +Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE +value expressions: _col1 (type: string) TableScan -alias: c +alias: a Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE -Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) +Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: value (type: string) + Reduce Output Operator +key expressions: _col0 (type: string) +sort order: + +Map-reduce partition columns: _col0 (type: string) +Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE +value expressions: _col1 (type: string) TableScan -alias: d +alias: a Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE -Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) +Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: value (type: string) + Reduce Output Operator +key expressions: _col0 (type: string) +sort order: + +Map-reduce partition columns: _col0 (type: string) +Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE +value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: @@ -69,23 +85,19 @@ STAGE PLANS: Left Outer Join1 to 2 Left Outer Join0 to 3 keys: -0 key (type: string) -1 key (type: string) -2 key (type: string) -3 key (type: string) - outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11, _col15, _col16 +0 _col0 (type: string) +1 _col0 (type: string) +2 _col0 (type: string) +3 _col0 (type: string) + outputColumnNames: _col0, _col1,
[23/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/louter_join_ppr.q.out -- diff --git a/ql/src/test/results/clientpositive/louter_join_ppr.q.out b/ql/src/test/results/clientpositive/louter_join_ppr.q.out index 65fe291..cb2edde 100644 --- a/ql/src/test/results/clientpositive/louter_join_ppr.q.out +++ b/ql/src/test/results/clientpositive/louter_join_ppr.q.out @@ -968,42 +968,42 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan -alias: b -Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE +alias: a +Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: (UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) > 10.0)) and (UDFToDouble(key) < 20.0)) and key is not null) (type: boolean) - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + predicate: (UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) and (UDFToDouble(key) > 15.0)) and (UDFToDouble(key) < 25.0)) and key is not null) (type: boolean) + Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 -Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE +Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE tag: 0 value expressions: _col1 (type: string) auto parallelism: false TableScan -alias: a -Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE +alias: b +Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: (UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) and (UDFToDouble(key) > 15.0)) and (UDFToDouble(key) < 25.0)) and key is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + predicate: (UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) > 10.0)) and (UDFToDouble(key) < 20.0)) and key is not null) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 -Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE +Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE tag: 1 value expressions: _col1 (type: string) auto parallelism: false @@ -1147,9 +1147,9 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: -/src [$hdt$_1:$hdt$_1:a] -/srcpart/ds=2008-04-08/hr=11 [$hdt$_0:$hdt$_0:b] -/srcpart/ds=2008-04-08/hr=12 [$hdt$_0:$hdt$_0:b] +/src [$hdt$_0:$hdt$_0:a] +/srcpart/ds=2008-04-08/hr=11 [$hdt$_1:$hdt$_1:b] +/srcpart/ds=2008-04-08/hr=12 [$hdt$_1:$hdt$_1:b] Needs Tagging: true Reduce Operator Tree: Join Operator @@ -1158,34 +1158,30 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3, _col4 + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 6 Data size: 69 Basic stats: COMPLETE Column stats: NONE -
[81/91] [abbrv] hive git commit: HIVE-12503 : GBY-Join transpose rule may go in infinite loop (Ashutosh Chauhan via Jesus Camacho Rodriguez)
HIVE-12503 : GBY-Join transpose rule may go in infinite loop (Ashutosh Chauhan via Jesus Camacho Rodriguez) Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/a9d3b096 Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/a9d3b096 Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/a9d3b096 Branch: refs/heads/spark Commit: a9d3b096b216677ec59ab68f749de5077e0d4e51 Parents: 9a1f769 Author: Ashutosh ChauhanAuthored: Thu Nov 26 11:39:50 2015 -0800 Committer: Ashutosh Chauhan Committed: Thu Nov 26 11:40:55 2015 -0800 -- .../rules/HiveAggregateJoinTransposeRule.java | 17 ++- .../queries/clientpositive/cbo_rp_auto_join1.q | 2 +- .../clientpositive/cbo_rp_auto_join1.q.out | 125 +- .../clientpositive/groupby_join_pushdown.q.out | 128 +-- 4 files changed, 138 insertions(+), 134 deletions(-) -- http://git-wip-us.apache.org/repos/asf/hive/blob/a9d3b096/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveAggregateJoinTransposeRule.java -- diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveAggregateJoinTransposeRule.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveAggregateJoinTransposeRule.java index c59af39..8cbaed0 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveAggregateJoinTransposeRule.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveAggregateJoinTransposeRule.java @@ -17,6 +17,7 @@ package org.apache.hadoop.hive.ql.optimizer.calcite.rules; import org.apache.calcite.linq4j.Ord; +import org.apache.calcite.plan.RelOptCost; import org.apache.calcite.plan.RelOptRuleCall; import org.apache.calcite.plan.RelOptUtil; import org.apache.calcite.rel.RelNode; @@ -295,15 +296,13 @@ public class HiveAggregateJoinTransposeRule extends AggregateJoinTransposeRule { Mappings.apply(mapping, aggregate.getGroupSet()), Mappings.apply2(mapping, aggregate.getGroupSets()), newAggCalls); } -call.transformTo(r); -// Add original tree as well for potential alternative transformation. -// This is modeled after LoptOptimizeJoinRule::findBestOrderings() in -// which rule adds multiple transformations and Planner picks the cheapest one. -// Hep planner will automatically pick the one with lower cost among two. -// For details, see: HepPlanner:applyTransformationResults() -// In this case, if ndv is close to # of rows, i.e., group by is not resulting -// in any deduction, doing this transformation is not useful. -call.transformTo(aggregate); + +// Make a cost based decision to pick cheaper plan +RelOptCost afterCost = RelMetadataQuery.getCumulativeCost(r); +RelOptCost beforeCost = RelMetadataQuery.getCumulativeCost(aggregate); +if (afterCost.isLt(beforeCost)) { + call.transformTo(r); +} } /** Computes the closure of a set of columns according to a given list of http://git-wip-us.apache.org/repos/asf/hive/blob/a9d3b096/ql/src/test/queries/clientpositive/cbo_rp_auto_join1.q -- diff --git a/ql/src/test/queries/clientpositive/cbo_rp_auto_join1.q b/ql/src/test/queries/clientpositive/cbo_rp_auto_join1.q index b906db2..cbfb5d5 100644 --- a/ql/src/test/queries/clientpositive/cbo_rp_auto_join1.q +++ b/ql/src/test/queries/clientpositive/cbo_rp_auto_join1.q @@ -3,7 +3,7 @@ set hive.stats.fetch.column.stats=true; ; set hive.exec.reducers.max = 1; - +set hive.transpose.aggr.join=true; -- SORT_QUERY_RESULTS CREATE TABLE tbl1(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS; http://git-wip-us.apache.org/repos/asf/hive/blob/a9d3b096/ql/src/test/results/clientpositive/cbo_rp_auto_join1.q.out -- diff --git a/ql/src/test/results/clientpositive/cbo_rp_auto_join1.q.out b/ql/src/test/results/clientpositive/cbo_rp_auto_join1.q.out index 6537a8a..59a2f12 100644 --- a/ql/src/test/results/clientpositive/cbo_rp_auto_join1.q.out +++ b/ql/src/test/results/clientpositive/cbo_rp_auto_join1.q.out @@ -933,8 +933,10 @@ select count(*) from POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 + Stage-2 depends on stages: Stage-1, Stage-4 + Stage-3 depends on stages: Stage-2 + Stage-4 is a root stage + Stage-0 depends on stages: Stage-3 STAGE PLANS: Stage: Stage-1 @@ -947,41 +949,67 @@ STAGE PLANS: predicate: (key + 1) is not null (type: boolean) Statistics: Num rows: 5 Data
[48/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/auto_sortmerge_join_4.q.out -- diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_4.q.out b/ql/src/test/results/clientpositive/auto_sortmerge_join_4.q.out index 013bc07..17212b8 100644 --- a/ql/src/test/results/clientpositive/auto_sortmerge_join_4.q.out +++ b/ql/src/test/results/clientpositive/auto_sortmerge_join_4.q.out @@ -153,23 +153,27 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 14 Data size: 1425 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator -condition map: - Inner Join 0 to 1 -keys: - 0 key (type: string) - 1 key (type: string) -Position of Big Table: 1 -BucketMapJoin: true -Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator -sort order: -tag: -1 -value expressions: _col0 (type: bigint) -auto parallelism: false + Select Operator +expressions: key (type: string) +outputColumnNames: _col0 +Statistics: Num rows: 14 Data size: 1425 Basic stats: COMPLETE Column stats: NONE +Sorted Merge Bucket Map Join Operator + condition map: + Inner Join 0 to 1 + keys: +0 _col0 (type: string) +1 _col0 (type: string) + Position of Big Table: 1 + BucketMapJoin: true + Group By Operator +aggregations: count() +mode: hash +outputColumnNames: _col0 +Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: A masked pattern was here Path -> Partition: @@ -222,7 +226,7 @@ STAGE PLANS: name: default.bucket_big name: default.bucket_big Truncated Path -> Alias: -/bucket_big/ds=2008-04-08 [b] +/bucket_big/ds=2008-04-08 [$hdt$_1:b] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -326,23 +330,27 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 14 Data size: 1425 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator -condition map: - Inner Join 0 to 1 -keys: - 0 key (type: string) - 1 key (type: string) -Position of Big Table: 0 -BucketMapJoin: true -Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator -sort order: -tag: -1 -value expressions: _col0 (type: bigint) -auto parallelism: false + Select Operator +expressions: key (type: string) +outputColumnNames: _col0 +Statistics: Num rows: 14 Data size: 1425 Basic stats: COMPLETE Column stats: NONE +Sorted Merge Bucket Map Join Operator + condition map: + Inner Join 0 to 1 + keys: +0 _col0 (type: string) +1 _col0 (type: string) + Position of Big Table: 0 + BucketMapJoin: true + Group By Operator +aggregations: count() +mode: hash +outputColumnNames: _col0 +Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: A masked pattern was here Path -> Partition: @@ -395,7 +403,7 @@ STAGE PLANS: name: default.bucket_big name: default.bucket_big Truncated Path -> Alias: -/bucket_big/ds=2008-04-08 [a] +/bucket_big/ds=2008-04-08 [$hdt$_0:a] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -499,7 +507,7 @@ STAGE PLANS: Stage: Stage-6
[79/91] [abbrv] hive git commit: HIVE-12476: Metastore NPE on Oracle with Direct SQL (Jason Dere, reviewed by Sushanth Sowmyan)
HIVE-12476: Metastore NPE on Oracle with Direct SQL (Jason Dere, reviewed by Sushanth Sowmyan) Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/31cc894d Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/31cc894d Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/31cc894d Branch: refs/heads/spark Commit: 31cc894dfc53df23e9ef981942cec4317967d00b Parents: 0ae374a Author: Jason DereAuthored: Wed Nov 25 15:20:51 2015 -0800 Committer: Jason Dere Committed: Wed Nov 25 15:20:51 2015 -0800 -- .../hadoop/hive/metastore/MetaStoreDirectSql.java | 12 1 file changed, 12 insertions(+) -- http://git-wip-us.apache.org/repos/asf/hive/blob/31cc894d/metastore/src/java/org/apache/hadoop/hive/metastore/MetaStoreDirectSql.java -- diff --git a/metastore/src/java/org/apache/hadoop/hive/metastore/MetaStoreDirectSql.java b/metastore/src/java/org/apache/hadoop/hive/metastore/MetaStoreDirectSql.java index 08153ca..d76e77f 100644 --- a/metastore/src/java/org/apache/hadoop/hive/metastore/MetaStoreDirectSql.java +++ b/metastore/src/java/org/apache/hadoop/hive/metastore/MetaStoreDirectSql.java @@ -646,6 +646,10 @@ class MetaStoreDirectSql { public void apply(Partition t, Object[] fields) { t.putToParameters((String)fields[1], (String)fields[2]); }}); +// Perform conversion of null map values +for (Partition t : partitions.values()) { + t.setParameters(MetaStoreUtils.trimMapNulls(t.getParameters(), convertMapNullsToEmptyStrings)); +} queryText = "select \"PART_ID\", \"PART_KEY_VAL\" from \"PARTITION_KEY_VALS\"" + " where \"PART_ID\" in (" + partIds + ") and \"INTEGER_IDX\" >= 0" @@ -673,6 +677,10 @@ class MetaStoreDirectSql { public void apply(StorageDescriptor t, Object[] fields) { t.putToParameters((String)fields[1], (String)fields[2]); }}); +// Perform conversion of null map values +for (StorageDescriptor t : sds.values()) { + t.setParameters(MetaStoreUtils.trimMapNulls(t.getParameters(), convertMapNullsToEmptyStrings)); +} queryText = "select \"SD_ID\", \"COLUMN_NAME\", \"SORT_COLS\".\"ORDER\" from \"SORT_COLS\"" + " where \"SD_ID\" in (" + sdIds + ") and \"INTEGER_IDX\" >= 0" @@ -810,6 +818,10 @@ class MetaStoreDirectSql { public void apply(SerDeInfo t, Object[] fields) { t.putToParameters((String)fields[1], (String)fields[2]); }}); +// Perform conversion of null map values +for (SerDeInfo t : serdes.values()) { + t.setParameters(MetaStoreUtils.trimMapNulls(t.getParameters(), convertMapNullsToEmptyStrings)); +} return orderedResult; }
[73/91] [abbrv] hive git commit: HIVE-12469 : Bump Commons-Collections dependency from 3.2.1 to 3.2.2. to address vulnerability (Ashutosh Chauhan via Sergio Pena, Reuben Kuhnert)
HIVE-12469 : Bump Commons-Collections dependency from 3.2.1 to 3.2.2. to address vulnerability (Ashutosh Chauhan via Sergio Pena, Reuben Kuhnert) Signed-off-by: Ashutosh ChauhanProject: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/5a5e2490 Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/5a5e2490 Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/5a5e2490 Branch: refs/heads/spark Commit: 5a5e249040386f21ca0cc1eebdaca50180989d76 Parents: f180379 Author: Ashutosh Chauhan Authored: Thu Nov 19 11:06:37 2015 -0800 Committer: Ashutosh Chauhan Committed: Wed Nov 25 09:49:19 2015 -0800 -- accumulo-handler/pom.xml | 8 +++- ant/pom.xml | 6 ++ common/pom.xml | 6 +- hplsql/pom.xml | 5 - pom.xml | 8 +++- 5 files changed, 25 insertions(+), 8 deletions(-) -- http://git-wip-us.apache.org/repos/asf/hive/blob/5a5e2490/accumulo-handler/pom.xml -- diff --git a/accumulo-handler/pom.xml b/accumulo-handler/pom.xml index 759c718..9d5185b 100644 --- a/accumulo-handler/pom.xml +++ b/accumulo-handler/pom.xml @@ -39,7 +39,13 @@ org.apache.accumulo accumulo-core - + + +commons-collections +commons-collections + + + org.apache.accumulo accumulo-fate http://git-wip-us.apache.org/repos/asf/hive/blob/5a5e2490/ant/pom.xml -- diff --git a/ant/pom.xml b/ant/pom.xml index a1f7921..9706572 100644 --- a/ant/pom.xml +++ b/ant/pom.xml @@ -53,6 +53,12 @@ org.apache.velocity velocity ${velocity.version} + + +commons-collections +commons-collections + + http://git-wip-us.apache.org/repos/asf/hive/blob/5a5e2490/common/pom.xml -- diff --git a/common/pom.xml b/common/pom.xml index cd14581..ee74282 100644 --- a/common/pom.xml +++ b/common/pom.xml @@ -91,7 +91,11 @@ ${hadoop.version} true - + +commons-collections +commons-collections + + org.slf4j slf4j-log4j12 http://git-wip-us.apache.org/repos/asf/hive/blob/5a5e2490/hplsql/pom.xml -- diff --git a/hplsql/pom.xml b/hplsql/pom.xml index 0aa647b..6329002 100644 --- a/hplsql/pom.xml +++ b/hplsql/pom.xml @@ -39,11 +39,6 @@ ${guava.version} -commons-collections -commons-collections -3.2.1 - - commons-cli commons-cli ${commons-cli.version} http://git-wip-us.apache.org/repos/asf/hive/blob/5a5e2490/pom.xml -- diff --git a/pom.xml b/pom.xml index c38c10f..34bdbf6 100644 --- a/pom.xml +++ b/pom.xml @@ -111,6 +111,7 @@ 3.2.9 1.2 1.4 +3.2.2 1.9 1.1 3.0.1 @@ -303,7 +304,12 @@ commons-codec ${commons-codec.version} - + +commons-collections +commons-collections +${commons-collections.version} + + commons-httpclient commons-httpclient ${commons-httpclient.version}
[57/91] [abbrv] hive git commit: HIVE-12489 : Analyze for partition fails if partition value has special characters (Thomas Friedrich via Ashutosh Chauhan)
HIVE-12489 : Analyze for partition fails if partition value has special characters (Thomas Friedrich via Ashutosh Chauhan) Signed-off-by: Ashutosh ChauhanProject: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/0c1de975 Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/0c1de975 Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/0c1de975 Branch: refs/heads/spark Commit: 0c1de975f896d7a6e4a0f55ac0416dc75ea9c8e5 Parents: 2604cf2 Author: Thomas Friedrich Authored: Fri Nov 20 13:55:00 2015 -0800 Committer: Ashutosh Chauhan Committed: Mon Nov 23 11:46:19 2015 -0800 -- .../ql/parse/ColumnStatsSemanticAnalyzer.java | 6 +-- .../queries/clientpositive/analyze_tbl_part.q | 12 + .../clientpositive/analyze_tbl_part.q.out | 52 3 files changed, 67 insertions(+), 3 deletions(-) -- http://git-wip-us.apache.org/repos/asf/hive/blob/0c1de975/ql/src/java/org/apache/hadoop/hive/ql/parse/ColumnStatsSemanticAnalyzer.java -- diff --git a/ql/src/java/org/apache/hadoop/hive/ql/parse/ColumnStatsSemanticAnalyzer.java b/ql/src/java/org/apache/hadoop/hive/ql/parse/ColumnStatsSemanticAnalyzer.java index 543bc0f..832a5bc 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/parse/ColumnStatsSemanticAnalyzer.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/parse/ColumnStatsSemanticAnalyzer.java @@ -199,7 +199,7 @@ public class ColumnStatsSemanticAnalyzer extends SemanticAnalyzer { if (partColType.equals(serdeConstants.STRING_TYPE_NAME) || partColType.contains(serdeConstants.VARCHAR_TYPE_NAME) || partColType.contains(serdeConstants.CHAR_TYPE_NAME)) { - returnVal = "'" + partVal + "'"; + returnVal = "'" + escapeSQLString(partVal) + "'"; } else if (partColType.equals(serdeConstants.TINYINT_TYPE_NAME)) { returnVal = partVal+"Y"; } else if (partColType.equals(serdeConstants.SMALLINT_TYPE_NAME)) { @@ -212,10 +212,10 @@ public class ColumnStatsSemanticAnalyzer extends SemanticAnalyzer { returnVal = partVal + "BD"; } else if (partColType.equals(serdeConstants.DATE_TYPE_NAME) || partColType.equals(serdeConstants.TIMESTAMP_TYPE_NAME)) { - returnVal = partColType + " '" + partVal + "'"; + returnVal = partColType + " '" + escapeSQLString(partVal) + "'"; } else { //for other usually not used types, just quote the value - returnVal = "'" + partVal + "'"; + returnVal = "'" + escapeSQLString(partVal) + "'"; } return returnVal; http://git-wip-us.apache.org/repos/asf/hive/blob/0c1de975/ql/src/test/queries/clientpositive/analyze_tbl_part.q -- diff --git a/ql/src/test/queries/clientpositive/analyze_tbl_part.q b/ql/src/test/queries/clientpositive/analyze_tbl_part.q index c9e45b6..ecf1389 100644 --- a/ql/src/test/queries/clientpositive/analyze_tbl_part.q +++ b/ql/src/test/queries/clientpositive/analyze_tbl_part.q @@ -15,3 +15,15 @@ ANALYZE TABLE src_stat_part partition (partitionId) COMPUTE STATISTICS for colum describe formatted src_stat_part.key PARTITION(partitionId=1); describe formatted src_stat_part.value PARTITION(partitionId=2); + +create table src_stat_string_part(key string, value string) partitioned by (partitionName string); + +insert overwrite table src_stat_string_part partition (partitionName="p'1") +select * from src1; + +insert overwrite table src_stat_string_part partition (partitionName="p\"1") +select * from src1; + +ANALYZE TABLE src_stat_string_part partition (partitionName="p'1") COMPUTE STATISTICS for columns key, value; + +ANALYZE TABLE src_stat_string_part partition (partitionName="p\"1") COMPUTE STATISTICS for columns key, value; \ No newline at end of file http://git-wip-us.apache.org/repos/asf/hive/blob/0c1de975/ql/src/test/results/clientpositive/analyze_tbl_part.q.out -- diff --git a/ql/src/test/results/clientpositive/analyze_tbl_part.q.out b/ql/src/test/results/clientpositive/analyze_tbl_part.q.out index 40b926c..464bdf7 100644 --- a/ql/src/test/results/clientpositive/analyze_tbl_part.q.out +++ b/ql/src/test/results/clientpositive/analyze_tbl_part.q.out @@ -81,3 +81,55 @@ POSTHOOK: Input: default@src_stat_part # col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment value string
[41/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/correlationoptimizer1.q.out -- diff --git a/ql/src/test/results/clientpositive/correlationoptimizer1.q.out b/ql/src/test/results/clientpositive/correlationoptimizer1.q.out index c5c9d9c..4a09600 100644 --- a/ql/src/test/results/clientpositive/correlationoptimizer1.q.out +++ b/ql/src/test/results/clientpositive/correlationoptimizer1.q.out @@ -31,35 +31,35 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan -alias: y -Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE +alias: x +Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 -Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE +Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE TableScan -alias: x -Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE +alias: y +Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 -Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE +Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -67,24 +67,20 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col1 + outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator -expressions: _col1 (type: string) -outputColumnNames: _col0 + Group By Operator +aggregations: count(1) +keys: _col0 (type: string) +mode: hash +outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE -Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator -compressed: false -table: -input format: org.apache.hadoop.mapred.SequenceFileInputFormat -output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat -serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe +File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -186,35 +182,35 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan -
[88/91] [abbrv] hive git commit: HIVE-12338: Add webui to HiveServer2 (Jimmy, reviewed by Mohit, Szehon, Lefty)
http://git-wip-us.apache.org/repos/asf/hive/blob/2c0c191c/service/src/resources/hive-webapps/static/css/bootstrap.min.css -- diff --git a/service/src/resources/hive-webapps/static/css/bootstrap.min.css b/service/src/resources/hive-webapps/static/css/bootstrap.min.css new file mode 100755 index 000..0f6fbcd --- /dev/null +++ b/service/src/resources/hive-webapps/static/css/bootstrap.min.css @@ -0,0 +1,9 @@ +/*! + * Bootstrap v3.0.0 + * + * Copyright 2013 Twitter, Inc + * Licensed under the Apache License v2.0 + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Designed and built with all the love in the world by @mdo and @fat. + *//*! normalize.css v2.1.0 | MIT License | git.io/normalize */article,aside,details,figcaption,figure,footer,header,hgroup,main,nav,section,summary{display:block}audio,canvas,video{display:inline-block}audio:not([controls]){display:none;height:0}[hidden]{display:none}html{font-family:sans-serif;-webkit-text-size-adjust:100%;-ms-text-size-adjust:100%}body{margin:0}a:focus{outline:thin dotted}a:active,a:hover{outline:0}h1{margin:.67em 0;font-size:2em}abbr[title]{border-bottom:1px dotted}b,strong{font-weight:bold}dfn{font-style:italic}hr{height:0;-moz-box-sizing:content-box;box-sizing:content-box}mark{color:#000;background:#ff0}code,kbd,pre,samp{font-family:monospace,serif;font-size:1em}pre{white-space:pre-wrap}q{quotes:"\201C" "\201D" "\2018" "\2019"}small{font-size:80%}sub,sup{position:relative;font-size:75%;line-height:0;vertical-align:baseline}sup{top:-0.5em}sub{bottom:-0.25em}img{border:0}svg:not(:root){overflow:hidden}figure{margin:0}fieldset{padding:.35em .625em .75em;margin:0 2px;border:1px solid #c0c0c0}legend{padding:0;border:0}button,input,select,textarea{margin:0;font-family:inherit;font-size:100%}button,input{line-height:normal}button,select{text-transform:none}button,html input[type="button"],input[type="reset"],input[type="submit"]{cursor:pointer;-webkit-appearance:button}button[disabled],html input[disabled]{cursor:default}input[type="checkbox"],input[type="radio"]{padding:0;box-sizing:border-box}input[type="search"]{-webkit-box-sizing:content-box;-moz-box-sizing:content-box;box-sizing:content-box;-webkit-appearance:textfield}input[type="search"]::-webkit-search-cancel-button,input[type="search"]::-webkit-search-decoration{-webkit-appearance:none}button::-moz-focus-inner,input::-moz-focus-inner{padding:0;border:0}textarea{overflow:auto;vertical-align:top}table{border-collapse:collapse;border-spacing:0}@media print{*{color:#000!important;text-shadow:none!important;background:transparent!important;box-shadow:none!important}a,a:visited{text-decorati on:underline}a[href]:after{content:" (" attr(href) ")"}abbr[title]:after{content:" (" attr(title) ")"}.ir a:after,a[href^="javascript:"]:after,a[href^="#"]:after{content:""}pre,blockquote{border:1px solid #999;page-break-inside:avoid}thead{display:table-header-group}tr,img{page-break-inside:avoid}img{max-width:100%!important}@page{margin:2cm .5cm}p,h2,h3{orphans:3;widows:3}h2,h3{page-break-after:avoid}.navbar{display:none}.table td,.table th{background-color:#fff!important}.btn>.caret,.dropup>.btn>.caret{border-top-color:#000!important}.label{border:1px solid #000}.table{border-collapse:collapse!important}.table-bordered th,.table-bordered td{border:1px solid #ddd!important}}*,*:before,*:after{-webkit-box-sizing:border-box;-moz-box-sizing:border-box;box-sizing:border-box}html{font-size:62.5%;-webkit-tap-highlight-color:rgba(0,0,0,0)}body{font-family:"Helvetica Neue",Helvetica,Arial,sans-serif;font-size:14px;line-height:1.428571429;color:#333;background-color:#fff}input,button,select ,textarea{font-family:inherit;font-size:inherit;line-height:inherit}button,input,select[multiple],textarea{background-image:none}a{color:#428bca;text-decoration:none}a:hover,a:focus{color:#2a6496;text-decoration:underline}a:focus{outline:thin dotted #333;outline:5px auto -webkit-focus-ring-color;outline-offset:-2px}img{vertical-align:middle}.img-responsive{display:block;height:auto;max-width:100%}.img-rounded{border-radius:6px}.img-thumbnail{display:inline-block;height:auto;max-width:100%;padding:4px;line-height:1.428571429;background-color:#fff;border:1px solid #ddd;border-radius:4px;-webkit-transition:all .2s ease-in-out;transition:all .2s ease-in-out}.img-circle{border-radius:50%}hr{margin-top:20px;margin-bottom:20px;border:0;border-top:1px solid #eee}.sr-only{position:absolute;width:1px;height:1px;padding:0;margin:-1px;overflow:hidden;clip:rect(0 0 0 0);border:0}p{margin:0 0 10px}.lead{margin-bottom:20px;font-size:16.098px;font-weight:200;line-height:1.4}@media(min-w
[42/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/cbo_rp_lineage2.q.out -- diff --git a/ql/src/test/results/clientpositive/cbo_rp_lineage2.q.out b/ql/src/test/results/clientpositive/cbo_rp_lineage2.q.out index 41f3d09..09b981b 100644 --- a/ql/src/test/results/clientpositive/cbo_rp_lineage2.q.out +++ b/ql/src/test/results/clientpositive/cbo_rp_lineage2.q.out @@ -461,26 +461,26 @@ PREHOOK: Input: default@src1 PREHOOK: Input: default@src2 PREHOOK: Output: database:default PREHOOK: Output: default@dest2 -{"version":"1.0","engine":"mr","database":"default","hash":"386791c174a4999fc916e300b5e76bf2","queryText":"create table dest2 as select * from src1 JOIN src2 ON src1.key = src2.key2","edges":[{"sources":[4],"targets":[0],"edgeType":"PROJECTION"},{"sources":[5],"targets":[1],"edgeType":"PROJECTION"},{"sources":[6],"targets":[2],"edgeType":"PROJECTION"},{"sources":[7],"targets":[3],"edgeType":"PROJECTION"},{"sources":[4,6],"targets":[0,1,2,3],"expression":"(src1.key = src2.key2)","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.dest2.key"},{"id":1,"vertexType":"COLUMN","vertexId":"default.dest2.value"},{"id":2,"vertexType":"COLUMN","vertexId":"default.dest2.key2"},{"id":3,"vertexType":"COLUMN","vertexId":"default.dest2.value2"},{"id":4,"vertexType":"COLUMN","vertexId":"default.src1.key"},{"id":5,"vertexType":"COLUMN","vertexId":"default.src1.value"},{"id":6,"vertexType":"COLUMN","vertexId":"default.src2.key2"},{"id":7,"vertexType":"COLUMN","vertex Id":"default.src2.value2"}]} +{"version":"1.0","engine":"mr","database":"default","hash":"386791c174a4999fc916e300b5e76bf2","queryText":"create table dest2 as select * from src1 JOIN src2 ON src1.key = src2.key2","edges":[{"sources":[4],"targets":[0],"edgeType":"PROJECTION"},{"sources":[5],"targets":[1],"edgeType":"PROJECTION"},{"sources":[6],"targets":[2],"edgeType":"PROJECTION"},{"sources":[7],"targets":[3],"edgeType":"PROJECTION"},{"sources":[4],"targets":[0,1,2,3],"expression":"src1.key is not null","edgeType":"PREDICATE"},{"sources":[4,6],"targets":[0,1,2,3],"expression":"(src1.key = src2.key2)","edgeType":"PREDICATE"},{"sources":[6],"targets":[0,1,2,3],"expression":"src2.key2 is not null","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.dest2.key"},{"id":1,"vertexType":"COLUMN","vertexId":"default.dest2.value"},{"id":2,"vertexType":"COLUMN","vertexId":"default.dest2.key2"},{"id":3,"vertexType":"COLUMN","vertexId":"default.dest2.value2"},{"id":4,"vertexType":"COLUMN","v ertexId":"default.src1.key"},{"id":5,"vertexType":"COLUMN","vertexId":"default.src1.value"},{"id":6,"vertexType":"COLUMN","vertexId":"default.src2.key2"},{"id":7,"vertexType":"COLUMN","vertexId":"default.src2.value2"}]} PREHOOK: query: insert overwrite table dest2 select * from src1 JOIN src2 ON src1.key = src2.key2 PREHOOK: type: QUERY PREHOOK: Input: default@src1 PREHOOK: Input: default@src2 PREHOOK: Output: default@dest2 -{"version":"1.0","engine":"mr","database":"default","hash":"e494b771d94800dc3430bf5d0810cd9f","queryText":"insert overwrite table dest2 select * from src1 JOIN src2 ON src1.key = src2.key2","edges":[{"sources":[4],"targets":[0],"edgeType":"PROJECTION"},{"sources":[5],"targets":[1],"edgeType":"PROJECTION"},{"sources":[6],"targets":[2],"edgeType":"PROJECTION"},{"sources":[7],"targets":[3],"edgeType":"PROJECTION"},{"sources":[4,6],"targets":[0,1,2,3],"expression":"(src1.key = src2.key2)","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.dest2.key"},{"id":1,"vertexType":"COLUMN","vertexId":"default.dest2.value"},{"id":2,"vertexType":"COLUMN","vertexId":"default.dest2.key2"},{"id":3,"vertexType":"COLUMN","vertexId":"default.dest2.value2"},{"id":4,"vertexType":"COLUMN","vertexId":"default.src1.key"},{"id":5,"vertexType":"COLUMN","vertexId":"default.src1.value"},{"id":6,"vertexType":"COLUMN","vertexId":"default.src2.key2"},{"id":7,"vertexType":"COLUMN", "vertexId":"default.src2.value2"}]} +{"version":"1.0","engine":"mr","database":"default","hash":"e494b771d94800dc3430bf5d0810cd9f","queryText":"insert overwrite table dest2 select * from src1 JOIN src2 ON src1.key = src2.key2","edges":[],"vertices":[]} PREHOOK: query: insert into table dest2 select * from src1 JOIN src2 ON src1.key = src2.key2 PREHOOK: type: QUERY PREHOOK: Input: default@src1 PREHOOK: Input: default@src2 PREHOOK: Output: default@dest2 -{"version":"1.0","engine":"mr","database":"default","hash":"efeaddd0d36105b1013b414627850dc2","queryText":"insert into table dest2 select * from src1 JOIN src2 ON src1.key =
[87/91] [abbrv] hive git commit: HIVE-12338: Add webui to HiveServer2 (Jimmy, reviewed by Mohit, Szehon, Lefty)
http://git-wip-us.apache.org/repos/asf/hive/blob/2c0c191c/service/src/resources/hive-webapps/static/css/hive.css -- diff --git a/service/src/resources/hive-webapps/static/css/hive.css b/service/src/resources/hive-webapps/static/css/hive.css new file mode 100644 index 000..b8c9f54 --- /dev/null +++ b/service/src/resources/hive-webapps/static/css/hive.css @@ -0,0 +1,24 @@ +/** + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/* General styling */ +body { padding-top: 60px; } +.logo img { float: right; } +.inner_header { margin-bottom: 1em; } +section { margin-bottom: 3em; } + http://git-wip-us.apache.org/repos/asf/hive/blob/2c0c191c/service/src/resources/hive-webapps/static/fonts/glyphicons-halflings-regular.eot -- diff --git a/service/src/resources/hive-webapps/static/fonts/glyphicons-halflings-regular.eot b/service/src/resources/hive-webapps/static/fonts/glyphicons-halflings-regular.eot new file mode 100755 index 000..87eaa43 Binary files /dev/null and b/service/src/resources/hive-webapps/static/fonts/glyphicons-halflings-regular.eot differ http://git-wip-us.apache.org/repos/asf/hive/blob/2c0c191c/service/src/resources/hive-webapps/static/fonts/glyphicons-halflings-regular.svg -- diff --git a/service/src/resources/hive-webapps/static/fonts/glyphicons-halflings-regular.svg b/service/src/resources/hive-webapps/static/fonts/glyphicons-halflings-regular.svg new file mode 100755 index 000..5fee068 --- /dev/null +++ b/service/src/resources/hive-webapps/static/fonts/glyphicons-halflings-regular.svg @@ -0,0 +1,228 @@ + +http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd; > +http://www.w3.org/2000/svg;> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + \ No newline at end of file http://git-wip-us.apache.org/repos/asf/hive/blob/2c0c191c/service/src/resources/hive-webapps/static/fonts/glyphicons-halflings-regular.ttf -- diff --git a/service/src/resources/hive-webapps/static/fonts/glyphicons-halflings-regular.ttf b/service/src/resources/hive-webapps/static/fonts/glyphicons-halflings-regular.ttf new file mode 100755 index 000..be784dc Binary files /dev/null and b/service/src/resources/hive-webapps/static/fonts/glyphicons-halflings-regular.ttf differ http://git-wip-us.apache.org/repos/asf/hive/blob/2c0c191c/service/src/resources/hive-webapps/static/fonts/glyphicons-halflings-regular.woff -- diff --git a/service/src/resources/hive-webapps/static/fonts/glyphicons-halflings-regular.woff b/service/src/resources/hive-webapps/static/fonts/glyphicons-halflings-regular.woff new file mode 100755 index 000..2cc3e48 Binary files /dev/null and b/service/src/resources/hive-webapps/static/fonts/glyphicons-halflings-regular.woff differ http://git-wip-us.apache.org/repos/asf/hive/blob/2c0c191c/service/src/resources/hive-webapps/static/hive_logo.jpeg -- diff --git a/service/src/resources/hive-webapps/static/hive_logo.jpeg b/service/src/resources/hive-webapps/static/hive_logo.jpeg new file mode 100644 index 000..8c4a5df Binary files /dev/null and b/service/src/resources/hive-webapps/static/hive_logo.jpeg differ http://git-wip-us.apache.org/repos/asf/hive/blob/2c0c191c/spark-client/pom.xml -- diff --git a/spark-client/pom.xml b/spark-client/pom.xml index 9d2b418..0405016 100644 --- a/spark-client/pom.xml +++ b/spark-client/pom.xml @@ -54,6 +54,12 @@
[35/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/join_cond_pushdown_unqual1.q.out -- diff --git a/ql/src/test/results/clientpositive/join_cond_pushdown_unqual1.q.out b/ql/src/test/results/clientpositive/join_cond_pushdown_unqual1.q.out index c1c2105..3a004ea 100644 --- a/ql/src/test/results/clientpositive/join_cond_pushdown_unqual1.q.out +++ b/ql/src/test/results/clientpositive/join_cond_pushdown_unqual1.q.out @@ -74,58 +74,66 @@ STAGE PLANS: Filter Operator predicate: p_name is not null (type: boolean) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator -key expressions: p_name (type: string) -sort order: + -Map-reduce partition columns: p_name (type: string) + Select Operator +expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) +outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE -value expressions: p_partkey (type: int), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) +Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: p2_name is not null (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator -key expressions: p2_name (type: string) -sort order: + -Map-reduce partition columns: p2_name (type: string) + Select Operator +expressions: p2_partkey (type: int), p2_name (type: string), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) +outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE -value expressions: p2_partkey (type: int), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) +Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p3 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: p3_name is not null (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator -key expressions: p3_name (type: string) -sort order: + -Map-reduce partition columns: p3_name (type: string) + Select Operator +expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) +outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE -value expressions: p3_partkey (type: int), p3_mfgr (type:
[80/91] [abbrv] hive git commit: HIVE-12501 : LLAP: don't use read(ByteBuffer) in IO (Sergey Shelukhin, reviewed by Prasanth Jayachandran)
HIVE-12501 : LLAP: don't use read(ByteBuffer) in IO (Sergey Shelukhin, reviewed by Prasanth Jayachandran) Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/9a1f7692 Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/9a1f7692 Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/9a1f7692 Branch: refs/heads/spark Commit: 9a1f76928900a6697d9efe74f28b7183d2979a1d Parents: 31cc894 Author: Sergey ShelukhinAuthored: Wed Nov 25 17:25:06 2015 -0800 Committer: Sergey Shelukhin Committed: Wed Nov 25 17:25:06 2015 -0800 -- .../hive/ql/io/orc/RecordReaderUtils.java | 43 +--- 1 file changed, 11 insertions(+), 32 deletions(-) -- http://git-wip-us.apache.org/repos/asf/hive/blob/9a1f7692/ql/src/java/org/apache/hadoop/hive/ql/io/orc/RecordReaderUtils.java -- diff --git a/ql/src/java/org/apache/hadoop/hive/ql/io/orc/RecordReaderUtils.java b/ql/src/java/org/apache/hadoop/hive/ql/io/orc/RecordReaderUtils.java index 6f3a3e9..0caeb1b 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/io/orc/RecordReaderUtils.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/io/orc/RecordReaderUtils.java @@ -327,47 +327,26 @@ public class RecordReaderUtils { len -= read; off += read; } - } else if (doForceDirect) { -file.seek(base + off); -ByteBuffer directBuf = ByteBuffer.allocateDirect(len); -readDirect(file, len, directBuf); -range = range.replaceSelfWith(new BufferChunk(directBuf, range.getOffset())); } else { +// Don't use HDFS ByteBuffer API because it has no readFully, and is buggy and pointless. byte[] buffer = new byte[len]; file.readFully((base + off), buffer, 0, buffer.length); -range = range.replaceSelfWith(new BufferChunk(ByteBuffer.wrap(buffer), range.getOffset())); +ByteBuffer bb = null; +if (doForceDirect) { + bb = ByteBuffer.allocateDirect(len); + bb.put(buffer); + bb.position(0); + bb.limit(len); +} else { + bb = ByteBuffer.wrap(buffer); +} +range = range.replaceSelfWith(new BufferChunk(bb, range.getOffset())); } range = range.next; } return prev.next; } - public static void readDirect(FSDataInputStream file, - int len, ByteBuffer directBuf) throws IOException { -// TODO: HDFS API is a mess, so handle all kinds of cases. -// Before 2.7, read() also doesn't adjust position correctly, so track it separately. -int pos = directBuf.position(), startPos = pos, endPos = pos + len; -try { - while (pos < endPos) { -int count = SHIMS.readByteBuffer(file, directBuf); -if (count < 0) throw new EOFException(); -assert count != 0 : "0-length read: " + (endPos - pos) + "@" + (pos - startPos); -pos += count; -assert pos <= endPos : "Position " + pos + " > " + endPos + " after reading " + count; -directBuf.position(pos); - } -} catch (UnsupportedOperationException ex) { - assert pos == startPos; - // Happens in q files and such. - RecordReaderImpl.LOG.error("Stream does not support direct read; we will copy."); - byte[] buffer = new byte[len]; - file.readFully(buffer, 0, buffer.length); - directBuf.put(buffer); -} -directBuf.position(startPos); -directBuf.limit(startPos + len); - } - static List getStreamBuffers(DiskRangeList range, long offset, long length) { // This assumes sorted ranges (as do many other parts of ORC code.
[76/91] [abbrv] hive git commit: HIVE-12487 : Fix broken MiniLlap tests (Aleksei Statkevich via Ashutosh Chauhan)
HIVE-12487 : Fix broken MiniLlap tests (Aleksei Statkevich via Ashutosh Chauhan) Signed-off-by: Ashutosh ChauhanProject: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/74c0c97e Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/74c0c97e Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/74c0c97e Branch: refs/heads/spark Commit: 74c0c97e393a421e96a0f0ba2859fba35cbdd745 Parents: 3cb23b9 Author: Aleksei Statkevich Authored: Sat Nov 21 23:44:00 2015 -0800 Committer: Ashutosh Chauhan Committed: Wed Nov 25 10:10:47 2015 -0800 -- .../org/apache/hadoop/hive/ql/exec/tez/HiveSplitGenerator.java | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) -- http://git-wip-us.apache.org/repos/asf/hive/blob/74c0c97e/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/HiveSplitGenerator.java -- diff --git a/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/HiveSplitGenerator.java b/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/HiveSplitGenerator.java index 532d242..8ebfe69 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/HiveSplitGenerator.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/HiveSplitGenerator.java @@ -140,7 +140,7 @@ public class HiveSplitGenerator extends InputInitializer { TezMapReduceSplitsGrouper.TEZ_GROUPING_SPLIT_MIN_SIZE, TezMapReduceSplitsGrouper.TEZ_GROUPING_SPLIT_MIN_SIZE_DEFAULT); final long preferredSplitSize = Math.min(blockSize / 2, minGrouping); - HiveConf.setLongVar(conf, HiveConf.ConfVars.MAPREDMINSPLITSIZE, preferredSplitSize); + HiveConf.setLongVar(jobConf, HiveConf.ConfVars.MAPREDMINSPLITSIZE, preferredSplitSize); LOG.info("The preferred split size is " + preferredSplitSize); }
[44/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/bucket_map_join_spark1.q.out -- diff --git a/ql/src/test/results/clientpositive/bucket_map_join_spark1.q.out b/ql/src/test/results/clientpositive/bucket_map_join_spark1.q.out index 870ecdd..0e4d630 100644 --- a/ql/src/test/results/clientpositive/bucket_map_join_spark1.q.out +++ b/ql/src/test/results/clientpositive/bucket_map_join_spark1.q.out @@ -178,7 +178,7 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: -a +$hdt$_0:a Fetch Operator limit: -1 Partition Description: @@ -229,7 +229,7 @@ STAGE PLANS: name: default.srcbucket_mapjoin_part name: default.srcbucket_mapjoin_part Alias -> Map Local Operator Tree: -a +$hdt$_0:a TableScan alias: a Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE @@ -238,11 +238,15 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator -keys: - 0 key (type: int) - 1 key (type: int) -Position of Big Table: 1 + Select Operator +expressions: key (type: int), value (type: string) +outputColumnNames: _col0, _col1 +Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE +HashTable Sink Operator + keys: +0 _col0 (type: int) +1 _col0 (type: int) + Position of Big Table: 1 Stage: Stage-4 Map Reduce @@ -255,45 +259,49 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE - Map Join Operator -condition map: - Inner Join 0 to 1 -keys: - 0 key (type: int) - 1 key (type: int) -outputColumnNames: _col0, _col1, _col7 -Position of Big Table: 1 -Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE -Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col7 (type: string) - outputColumnNames: _col0, _col1, _col2 + Select Operator +expressions: key (type: int), value (type: string) +outputColumnNames: _col0, _col1 +Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE +Map Join Operator + condition map: + Inner Join 0 to 1 + keys: +0 _col0 (type: int) +1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col3 + Position of Big Table: 1 Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE - File Output Operator -compressed: false -GlobalTableId: 1 - A masked pattern was here -NumFilesPerFileSink: 1 + Select Operator +expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) +outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE - A masked pattern was here -table: -input format: org.apache.hadoop.mapred.TextInputFormat -output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat -properties: - bucket_count -1 - columns key,value1,value2 - columns.comments - columns.types string:string:string - A masked pattern was here - name default.bucketmapjoin_tmp_result - serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - A masked pattern was here -serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -name: default.bucketmapjoin_tmp_result -
[52/91] [abbrv] hive git commit: HIVE-12436 : Default hive.metastore.schema.verification to true (Ashutosh Chauhan via Sushanth Sowmyan)
HIVE-12436 : Default hive.metastore.schema.verification to true (Ashutosh Chauhan via Sushanth Sowmyan) Signed-off-by: Ashutosh ChauhanProject: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/7f4379ab Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/7f4379ab Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/7f4379ab Branch: refs/heads/spark Commit: 7f4379ab0d9afc8ab305e7d5151984882b95cdcc Parents: 7dab21a Author: Ashutosh Chauhan Authored: Tue Nov 17 10:46:45 2015 -0800 Committer: Ashutosh Chauhan Committed: Fri Nov 20 14:49:56 2015 -0800 -- .../src/test/org/apache/hive/beeline/cli/TestHiveCli.java| 1 + beeline/src/test/resources/hive-site.xml | 5 + common/src/java/org/apache/hadoop/hive/conf/HiveConf.java| 2 +- data/conf/hive-site.xml | 5 + data/conf/llap/hive-site.xml | 5 + data/conf/spark/standalone/hive-site.xml | 5 + data/conf/spark/yarn-client/hive-site.xml| 4 data/conf/tez/hive-site.xml | 5 + .../src/main/java/org/apache/hadoop/hive/ql/QTestUtil.java | 8 ++-- 9 files changed, 33 insertions(+), 7 deletions(-) -- http://git-wip-us.apache.org/repos/asf/hive/blob/7f4379ab/beeline/src/test/org/apache/hive/beeline/cli/TestHiveCli.java -- diff --git a/beeline/src/test/org/apache/hive/beeline/cli/TestHiveCli.java b/beeline/src/test/org/apache/hive/beeline/cli/TestHiveCli.java index 21ba690..53dfa1d 100644 --- a/beeline/src/test/org/apache/hive/beeline/cli/TestHiveCli.java +++ b/beeline/src/test/org/apache/hive/beeline/cli/TestHiveCli.java @@ -278,6 +278,7 @@ public class TestHiveCli { public void setup() { System.setProperty("datanucleus.fixedDatastore", "false"); System.setProperty("datanucleus.autoCreateSchema", "true"); +System.setProperty("hive.metastore.schema.verification", "false"); cli = new HiveCli(); redirectOutputStream(); initFromFile(); http://git-wip-us.apache.org/repos/asf/hive/blob/7f4379ab/beeline/src/test/resources/hive-site.xml -- diff --git a/beeline/src/test/resources/hive-site.xml b/beeline/src/test/resources/hive-site.xml index b2347c7..615d4ed 100644 --- a/beeline/src/test/resources/hive-site.xml +++ b/beeline/src/test/resources/hive-site.xml @@ -34,6 +34,11 @@ false + + hive.metastore.schema.verification + false + + javax.jdo.option.ConnectionURL jdbc:derby:;databaseName=${test.tmp.dir}/metastore_db;create=true http://git-wip-us.apache.org/repos/asf/hive/blob/7f4379ab/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java -- diff --git a/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java b/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java index 09f3c3e..f48403b 100644 --- a/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java +++ b/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java @@ -540,7 +540,7 @@ public class HiveConf extends Configuration { METASTORE_AUTO_CREATE_SCHEMA("datanucleus.autoCreateSchema", false, "creates necessary schema on a startup if one doesn't exist. set this to false, after creating it once"), METASTORE_FIXED_DATASTORE("datanucleus.fixedDatastore", true, "Dictates whether to allow updates to schema or not."), -METASTORE_SCHEMA_VERIFICATION("hive.metastore.schema.verification", false, +METASTORE_SCHEMA_VERIFICATION("hive.metastore.schema.verification", true, "Enforce metastore schema version consistency.\n" + "True: Verify that version information stored in metastore matches with one from Hive jars. Also disable automatic\n" + " schema migration attempt. Users are required to manually migrate schema after Hive upgrade which ensures\n" + http://git-wip-us.apache.org/repos/asf/hive/blob/7f4379ab/data/conf/hive-site.xml -- diff --git a/data/conf/hive-site.xml b/data/conf/hive-site.xml index d15cc17..2ebb1c4 100644 --- a/data/conf/hive-site.xml +++ b/data/conf/hive-site.xml @@ -69,6 +69,11 @@ + hive.metastore.schema.verification + false + + + javax.jdo.option.ConnectionURL jdbc:derby:;databaseName=${test.tmp.dir}/junit_metastore_db;create=true http://git-wip-us.apache.org/repos/asf/hive/blob/7f4379ab/data/conf/llap/hive-site.xml -- diff --git a/data/conf/llap/hive-site.xml
[46/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/auto_sortmerge_join_8.q.out -- diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_8.q.out b/ql/src/test/results/clientpositive/auto_sortmerge_join_8.q.out index e3bb51d..5596ef0 100644 --- a/ql/src/test/results/clientpositive/auto_sortmerge_join_8.q.out +++ b/ql/src/test/results/clientpositive/auto_sortmerge_join_8.q.out @@ -170,23 +170,27 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator -condition map: - Inner Join 0 to 1 -keys: - 0 key (type: string) - 1 key (type: string) -Position of Big Table: 1 -BucketMapJoin: true -Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator -sort order: -tag: -1 -value expressions: _col0 (type: bigint) -auto parallelism: false + Select Operator +expressions: key (type: string) +outputColumnNames: _col0 +Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE +Sorted Merge Bucket Map Join Operator + condition map: + Inner Join 0 to 1 + keys: +0 _col0 (type: string) +1 _col0 (type: string) + Position of Big Table: 1 + BucketMapJoin: true + Group By Operator +aggregations: count() +mode: hash +outputColumnNames: _col0 +Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: A masked pattern was here Path -> Partition: @@ -287,8 +291,8 @@ STAGE PLANS: name: default.bucket_big name: default.bucket_big Truncated Path -> Alias: -/bucket_big/ds=2008-04-08 [b] -/bucket_big/ds=2008-04-09 [b] +/bucket_big/ds=2008-04-08 [$hdt$_1:b] +/bucket_big/ds=2008-04-09 [$hdt$_1:b] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -394,23 +398,27 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator -condition map: - Inner Join 0 to 1 -keys: - 0 key (type: string) - 1 key (type: string) -Position of Big Table: 0 -BucketMapJoin: true -Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator -sort order: -tag: -1 -value expressions: _col0 (type: bigint) -auto parallelism: false + Select Operator +expressions: key (type: string) +outputColumnNames: _col0 +Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE +Sorted Merge Bucket Map Join Operator + condition map: + Inner Join 0 to 1 + keys: +0 _col0 (type: string) +1 _col0 (type: string) + Position of Big Table: 0 + BucketMapJoin: true + Group By Operator +aggregations: count() +mode: hash +outputColumnNames: _col0 +Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: A masked pattern was here Path -> Partition: @@ -511,8 +519,8 @@ STAGE PLANS: name: default.bucket_big name: default.bucket_big Truncated Path -> Alias: -/bucket_big/ds=2008-04-08 [a] -/bucket_big/ds=2008-04-09 [a] +/bucket_big/ds=2008-04-08 [$hdt$_0:a] +
[32/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/join_star.q.out -- diff --git a/ql/src/test/results/clientpositive/join_star.q.out b/ql/src/test/results/clientpositive/join_star.q.out index a75b48d..09db1f6 100644 --- a/ql/src/test/results/clientpositive/join_star.q.out +++ b/ql/src/test/results/clientpositive/join_star.q.out @@ -139,21 +139,25 @@ STAGE PLANS: Stage: Stage-4 Map Reduce Local Work Alias -> Map Local Tables: -dim1 +$hdt$_1:dim1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: -dim1 +$hdt$_1:dim1 TableScan alias: dim1 Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: f1 is not null (type: boolean) Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator -keys: - 0 d1 (type: int) - 1 f1 (type: int) + Select Operator +expressions: f1 (type: int), f2 (type: int) +outputColumnNames: _col0, _col1 +Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +HashTable Sink Operator + keys: +0 _col2 (type: int) +1 _col0 (type: int) Stage: Stage-3 Map Reduce @@ -164,25 +168,29 @@ STAGE PLANS: Filter Operator predicate: d1 is not null (type: boolean) Statistics: Num rows: 4 Data size: 49 Basic stats: COMPLETE Column stats: NONE - Map Join Operator -condition map: - Inner Join 0 to 1 -keys: - 0 d1 (type: int) - 1 f1 (type: int) -outputColumnNames: _col0, _col1, _col8 -Statistics: Num rows: 4 Data size: 53 Basic stats: COMPLETE Column stats: NONE -Select Operator - expressions: _col0 (type: int), _col1 (type: int), _col8 (type: int) - outputColumnNames: _col0, _col1, _col2 + Select Operator +expressions: m1 (type: int), m2 (type: int), d1 (type: int) +outputColumnNames: _col0, _col1, _col2 +Statistics: Num rows: 4 Data size: 49 Basic stats: COMPLETE Column stats: NONE +Map Join Operator + condition map: + Inner Join 0 to 1 + keys: +0 _col2 (type: int) +1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col4 Statistics: Num rows: 4 Data size: 53 Basic stats: COMPLETE Column stats: NONE - File Output Operator -compressed: false + Select Operator +expressions: _col0 (type: int), _col1 (type: int), _col4 (type: int) +outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 4 Data size: 53 Basic stats: COMPLETE Column stats: NONE -table: -input format: org.apache.hadoop.mapred.TextInputFormat -output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat -serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +File Output Operator + compressed: false + Statistics: Num rows: 4 Data size: 53 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work @@ -225,35 +233,43 @@ STAGE PLANS: Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: -dim1 +$hdt$_1:dim1 Fetch Operator limit: -1 -dim2 +$hdt$_2:dim2 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: -dim1 +$hdt$_1:dim1 TableScan alias: dim1 Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: f1 is not null (type: boolean) Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator -keys: - 0 d1 (type: int) - 1 f1 (type: int)
[75/91] [abbrv] hive git commit: HIVE-12498: ACID: Setting OrcRecordUpdater.OrcOptions.tableProperties() has no effect (Prasanth Jayachandran reviewed by Eugene Koifman)
HIVE-12498: ACID: Setting OrcRecordUpdater.OrcOptions.tableProperties() has no effect (Prasanth Jayachandran reviewed by Eugene Koifman) Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/3cb23b9e Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/3cb23b9e Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/3cb23b9e Branch: refs/heads/spark Commit: 3cb23b9e4b0a0e2a8edc3c2f5ee040e5ad01142d Parents: 4201179 Author: Prasanth JayachandranAuthored: Wed Nov 25 12:10:02 2015 -0600 Committer: Prasanth Jayachandran Committed: Wed Nov 25 12:10:02 2015 -0600 -- .../hadoop/hive/ql/io/orc/OrcRecordUpdater.java | 3 +- .../hive/ql/io/orc/TestOrcRecordUpdater.java| 58 ++-- 2 files changed, 54 insertions(+), 7 deletions(-) -- http://git-wip-us.apache.org/repos/asf/hive/blob/3cb23b9e/ql/src/java/org/apache/hadoop/hive/ql/io/orc/OrcRecordUpdater.java -- diff --git a/ql/src/java/org/apache/hadoop/hive/ql/io/orc/OrcRecordUpdater.java b/ql/src/java/org/apache/hadoop/hive/ql/io/orc/OrcRecordUpdater.java index 67c5a11..ee31c23 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/io/orc/OrcRecordUpdater.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/io/orc/OrcRecordUpdater.java @@ -247,7 +247,8 @@ public class OrcRecordUpdater implements RecordUpdater { writerOptions = ((OrcOptions) options).getOrcOptions(); } if (writerOptions == null) { - writerOptions = OrcFile.writerOptions(options.getConfiguration()); + writerOptions = OrcFile.writerOptions(options.getTableProperties(), + options.getConfiguration()); } writerOptions.fileSystem(fs).callback(indexBuilder); if (!options.isWritingBase()) { http://git-wip-us.apache.org/repos/asf/hive/blob/3cb23b9e/ql/src/test/org/apache/hadoop/hive/ql/io/orc/TestOrcRecordUpdater.java -- diff --git a/ql/src/test/org/apache/hadoop/hive/ql/io/orc/TestOrcRecordUpdater.java b/ql/src/test/org/apache/hadoop/hive/ql/io/orc/TestOrcRecordUpdater.java index 22030b4..973cc40 100644 --- a/ql/src/test/org/apache/hadoop/hive/ql/io/orc/TestOrcRecordUpdater.java +++ b/ql/src/test/org/apache/hadoop/hive/ql/io/orc/TestOrcRecordUpdater.java @@ -18,6 +18,15 @@ package org.apache.hadoop.hive.ql.io.orc; +import static org.junit.Assert.assertEquals; +import static org.junit.Assert.assertNull; + +import java.io.ByteArrayOutputStream; +import java.io.DataInputStream; +import java.io.File; +import java.io.PrintStream; +import java.util.Properties; + import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.FileSystem; import org.apache.hadoop.fs.Path; @@ -33,12 +42,6 @@ import org.apache.hadoop.io.Text; import org.apache.hadoop.mapred.Reporter; import org.junit.Test; -import java.io.DataInputStream; -import java.io.File; - -import static org.junit.Assert.assertEquals; -import static org.junit.Assert.assertNull; - public class TestOrcRecordUpdater { @Test @@ -180,6 +183,49 @@ public class TestOrcRecordUpdater { } @Test + public void testWriterTblProperties() throws Exception { +Path root = new Path(workDir, "testWriterTblProperties"); +Configuration conf = new Configuration(); +// Must use raw local because the checksummer doesn't honor flushes. +FileSystem fs = FileSystem.getLocal(conf).getRaw(); +ObjectInspector inspector; +synchronized (TestOrcFile.class) { + inspector = ObjectInspectorFactory.getReflectionObjectInspector + (MyRow.class, ObjectInspectorFactory.ObjectInspectorOptions.JAVA); +} +Properties tblProps = new Properties(); +tblProps.setProperty("orc.compress", "SNAPPY"); +AcidOutputFormat.Options options = new AcidOutputFormat.Options(conf) +.filesystem(fs) +.bucket(10) +.writingBase(false) +.minimumTransactionId(10) +.maximumTransactionId(19) +.inspector(inspector) +.reporter(Reporter.NULL) +.finalDestination(root) +.tableProperties(tblProps); +RecordUpdater updater = new OrcRecordUpdater(root, options); +updater.insert(11, new MyRow("first")); +updater.insert(11, new MyRow("second")); +updater.insert(11, new MyRow("third")); +updater.flush(); +updater.insert(12, new MyRow("fourth")); +updater.insert(12, new MyRow("fifth")); +updater.flush(); + +PrintStream origOut = System.out; +ByteArrayOutputStream myOut = new ByteArrayOutputStream(); +System.setOut(new PrintStream(myOut)); +FileDump.main(new String[]{root.toUri().toString()}); +System.out.flush(); +String outDump = new String(myOut.toByteArray()); +
[74/91] [abbrv] hive git commit: HIVE-12520 : Fix schema_evol* tests on master (Ashutosh Chauhan via Prasanth J)
HIVE-12520 : Fix schema_evol* tests on master (Ashutosh Chauhan via Prasanth J) Signed-off-by: Ashutosh ChauhanProject: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/4201179c Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/4201179c Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/4201179c Branch: refs/heads/spark Commit: 4201179cfafbcc71acc6c057087957d6cffd1021 Parents: 5a5e249 Author: Ashutosh Chauhan Authored: Wed Nov 25 09:40:38 2015 -0800 Committer: Ashutosh Chauhan Committed: Wed Nov 25 10:04:15 2015 -0800 -- hbase-handler/src/test/results/positive/hbase_queries.q.out | 1 + ql/src/test/queries/clientpositive/insert_values_nonascii.q | 2 +- .../clientpositive/schema_evol_orc_acid_mapwork_part.q| 2 +- .../clientpositive/schema_evol_orc_acid_mapwork_table.q | 2 +- .../clientpositive/schema_evol_orc_acidvec_mapwork_part.q | 2 +- .../clientpositive/schema_evol_orc_acidvec_mapwork_table.q| 2 +- .../clientpositive/schema_evol_orc_nonvec_fetchwork_table.q | 3 +-- .../clientpositive/schema_evol_orc_nonvec_mapwork_table.q | 2 +- .../clientpositive/schema_evol_orc_vec_mapwork_table.q| 2 +- .../queries/clientpositive/schema_evol_text_fetchwork_table.q | 2 +- .../queries/clientpositive/schema_evol_text_mapwork_table.q | 2 +- ql/src/test/results/clientpositive/limit_join_transpose.q.out | 7 +++ .../results/clientpositive/tez/tez_dynpart_hashjoin_3.q.out | 2 ++ 13 files changed, 20 insertions(+), 11 deletions(-) -- http://git-wip-us.apache.org/repos/asf/hive/blob/4201179c/hbase-handler/src/test/results/positive/hbase_queries.q.out -- diff --git a/hbase-handler/src/test/results/positive/hbase_queries.q.out b/hbase-handler/src/test/results/positive/hbase_queries.q.out index fa348e3..1ab9877 100644 --- a/hbase-handler/src/test/results/positive/hbase_queries.q.out +++ b/hbase-handler/src/test/results/positive/hbase_queries.q.out @@ -176,6 +176,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) http://git-wip-us.apache.org/repos/asf/hive/blob/4201179c/ql/src/test/queries/clientpositive/insert_values_nonascii.q -- diff --git a/ql/src/test/queries/clientpositive/insert_values_nonascii.q b/ql/src/test/queries/clientpositive/insert_values_nonascii.q index 2e4ef41..52b34e9 100644 --- a/ql/src/test/queries/clientpositive/insert_values_nonascii.q +++ b/ql/src/test/queries/clientpositive/insert_values_nonascii.q @@ -1,6 +1,6 @@ set hive.support.concurrency=true; set hive.txn.manager=org.apache.hadoop.hive.ql.lockmgr.DbTxnManager; -set hive.enforce.bucketing=true; + create table insert_values_nonascii(t1 char(32), t2 string); http://git-wip-us.apache.org/repos/asf/hive/blob/4201179c/ql/src/test/queries/clientpositive/schema_evol_orc_acid_mapwork_part.q -- diff --git a/ql/src/test/queries/clientpositive/schema_evol_orc_acid_mapwork_part.q b/ql/src/test/queries/clientpositive/schema_evol_orc_acid_mapwork_part.q index 681a4ac..d6919c1 100644 --- a/ql/src/test/queries/clientpositive/schema_evol_orc_acid_mapwork_part.q +++ b/ql/src/test/queries/clientpositive/schema_evol_orc_acid_mapwork_part.q @@ -1,7 +1,7 @@ set hive.cli.print.header=true; set hive.support.concurrency=true; set hive.txn.manager=org.apache.hadoop.hive.ql.lockmgr.DbTxnManager; -set hive.enforce.bucketing=true; + SET hive.vectorized.execution.enabled=false; set hive.fetch.task.conversion=none; set hive.exec.dynamic.partition.mode=nonstrict; http://git-wip-us.apache.org/repos/asf/hive/blob/4201179c/ql/src/test/queries/clientpositive/schema_evol_orc_acid_mapwork_table.q -- diff --git a/ql/src/test/queries/clientpositive/schema_evol_orc_acid_mapwork_table.q b/ql/src/test/queries/clientpositive/schema_evol_orc_acid_mapwork_table.q index bde5d50..8c933e1 100644 --- a/ql/src/test/queries/clientpositive/schema_evol_orc_acid_mapwork_table.q +++ b/ql/src/test/queries/clientpositive/schema_evol_orc_acid_mapwork_table.q @@ -1,7 +1,7 @@ set hive.cli.print.header=true; set hive.support.concurrency=true; set hive.txn.manager=org.apache.hadoop.hive.ql.lockmgr.DbTxnManager; -set
[28/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning_2.q.out -- diff --git a/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning_2.q.out b/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning_2.q.out index cec4219..bf59bfe 100644 --- a/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning_2.q.out +++ b/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning_2.q.out @@ -166,67 +166,72 @@ STAGE PLANS: alias: agg filterExpr: dim_shops_id is not null (type: boolean) Statistics: Num rows: 9 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Map Join Operator -condition map: - Inner Join 0 to 1 -keys: - 0 dim_shops_id (type: int) - 1 id (type: int) -outputColumnNames: _col0, _col1, _col5, _col6 -input vertices: - 1 Map 4 -Statistics: Num rows: 9 Data size: 29 Basic stats: COMPLETE Column stats: NONE -HybridGraceHashJoin: true -Filter Operator - predicate: (_col1 = _col5) (type: boolean) - Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Select Operator +expressions: amount (type: decimal(10,0)), dim_shops_id (type: int) +outputColumnNames: _col0, _col1 +Statistics: Num rows: 9 Data size: 27 Basic stats: COMPLETE Column stats: NONE +Map Join Operator + condition map: + Inner Join 0 to 1 + keys: +0 _col1 (type: int) +1 _col0 (type: int) + outputColumnNames: _col0, _col3 + input vertices: +1 Map 4 + Statistics: Num rows: 9 Data size: 29 Basic stats: COMPLETE Column stats: NONE + HybridGraceHashJoin: true Select Operator -expressions: _col6 (type: string), _col0 (type: decimal(10,0)) -outputColumnNames: _col6, _col0 -Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE +expressions: _col3 (type: string), _col0 (type: decimal(10,0)) +outputColumnNames: _col3, _col0 +Statistics: Num rows: 9 Data size: 29 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(), sum(_col0) - keys: _col6 (type: string) + keys: _col3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 29 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) -Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE +Statistics: Num rows: 9 Data size: 29 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint), _col2 (type: decimal(20,0)) Execution mode: llap Map 4 Map Operator Tree: TableScan alias: d1 - filterExpr: (id is not null and (label) IN ('foo', 'bar')) (type: boolean) + filterExpr: ((label) IN ('foo', 'bar') and id is not null) (type: boolean) Statistics: Num rows: 3 Data size: 15 Basic stats: COMPLETE Column stats: NONE Filter Operator -predicate: (id is not null and (label) IN ('foo', 'bar')) (type: boolean) +predicate: ((label) IN ('foo', 'bar') and id is not null) (type: boolean) Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE -Reduce Output Operator - key expressions: id (type: int) - sort order: + - Map-reduce partition columns: id (type: int) - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column
[21/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/multiMapJoin1.q.out -- diff --git a/ql/src/test/results/clientpositive/multiMapJoin1.q.out b/ql/src/test/results/clientpositive/multiMapJoin1.q.out index 8548fc7..f0d86f2 100644 --- a/ql/src/test/results/clientpositive/multiMapJoin1.q.out +++ b/ql/src/test/results/clientpositive/multiMapJoin1.q.out @@ -189,35 +189,43 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: -firstjoin:smalltbl1 +$hdt$_0:$hdt$_1:smalltbl1 Fetch Operator limit: -1 -smalltbl2 +$hdt$_1:smalltbl2 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: -firstjoin:smalltbl1 +$hdt$_0:$hdt$_1:smalltbl1 TableScan alias: smalltbl1 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator -keys: - 0 key (type: string) - 1 key (type: string) -smalltbl2 + Select Operator +expressions: key (type: string) +outputColumnNames: _col0 +Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE +HashTable Sink Operator + keys: +0 _col0 (type: string) +1 _col0 (type: string) +$hdt$_1:smalltbl2 TableScan alias: smalltbl2 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: value is not null (type: boolean) Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator -keys: - 0 _col1 (type: string) - 1 value (type: string) + Select Operator +expressions: value (type: string) +outputColumnNames: _col0 +Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE +HashTable Sink Operator + keys: +0 _col0 (type: string) +1 _col0 (type: string) Stage: Stage-3 Map Reduce @@ -228,30 +236,38 @@ STAGE PLANS: Filter Operator predicate: (key is not null and value is not null) (type: boolean) Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE - Map Join Operator -condition map: - Inner Join 0 to 1 -keys: - 0 key (type: string) - 1 key (type: string) -outputColumnNames: _col1 -Statistics: Num rows: 1375 Data size: 14608 Basic stats: COMPLETE Column stats: NONE + Select Operator +expressions: key (type: string), value (type: string) +outputColumnNames: _col0, _col1 +Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: -0 _col1 (type: string) -1 value (type: string) - Statistics: Num rows: 1512 Data size: 16068 Basic stats: COMPLETE Column stats: NONE - Group By Operator -aggregations: count() -mode: hash +0 _col0 (type: string) +1 _col0 (type: string) + outputColumnNames: _col1 + Statistics: Num rows: 1375 Data size: 14608 Basic stats: COMPLETE Column stats: NONE + Select Operator +expressions: _col1 (type: string) outputColumnNames: _col0 -Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE -Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) +Statistics: Num rows: 1375 Data size: 14608 Basic stats: COMPLETE Column stats: NONE +Map Join Operator + condition map: + Inner Join 0 to 1 + keys: +0 _col0 (type: string) +
[71/91] [abbrv] hive git commit: HIVE-12399: Filter out NULLs in the Native Vector MapJoin operators. (Matt McCline via Gopal V)
HIVE-12399: Filter out NULLs in the Native Vector MapJoin operators. (Matt McCline via Gopal V) Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/63251225 Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/63251225 Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/63251225 Branch: refs/heads/spark Commit: 63251225cec37cd567b395e7576054df9186363d Parents: daf46aa Author: Gopal VAuthored: Wed Nov 25 00:51:39 2015 -0800 Committer: Gopal V Committed: Wed Nov 25 00:51:39 2015 -0800 -- .../VectorMapJoinInnerBigOnlyLongOperator.java | 63 +--- ...ctorMapJoinInnerBigOnlyMultiKeyOperator.java | 61 ++- ...VectorMapJoinInnerBigOnlyStringOperator.java | 57 +++--- .../mapjoin/VectorMapJoinInnerLongOperator.java | 63 +--- .../VectorMapJoinInnerMultiKeyOperator.java | 61 ++- .../VectorMapJoinInnerStringOperator.java | 58 ++ .../VectorMapJoinLeftSemiLongOperator.java | 63 +--- .../VectorMapJoinLeftSemiMultiKeyOperator.java | 63 ++-- .../VectorMapJoinLeftSemiStringOperator.java| 57 +++--- .../fast/VectorMapJoinFastLongHashTable.java| 7 +-- .../fast/VectorMapJoinFastStringCommon.java | 11 ++-- 11 files changed, 325 insertions(+), 239 deletions(-) -- http://git-wip-us.apache.org/repos/asf/hive/blob/63251225/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/mapjoin/VectorMapJoinInnerBigOnlyLongOperator.java -- diff --git a/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/mapjoin/VectorMapJoinInnerBigOnlyLongOperator.java b/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/mapjoin/VectorMapJoinInnerBigOnlyLongOperator.java index e8b722e..9e77d22 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/mapjoin/VectorMapJoinInnerBigOnlyLongOperator.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/mapjoin/VectorMapJoinInnerBigOnlyLongOperator.java @@ -179,13 +179,17 @@ public class VectorMapJoinInnerBigOnlyLongOperator extends VectorMapJoinInnerBig * Single-Column Long specific repeated lookup. */ -long key = vector[0]; JoinUtil.JoinResult joinResult; -if (useMinMax && (key < min || key > max)) { - // Out of range for whole batch. +if (!joinColVector.noNulls && joinColVector.isNull[0]) { joinResult = JoinUtil.JoinResult.NOMATCH; } else { - joinResult = hashMultiSet.contains(key, hashMultiSetResults[0]); + long key = vector[0]; + if (useMinMax && (key < min || key > max)) { +// Out of range for whole batch. +joinResult = JoinUtil.JoinResult.NOMATCH; + } else { +joinResult = hashMultiSet.contains(key, hashMultiSetResults[0]); + } } /* @@ -235,13 +239,21 @@ public class VectorMapJoinInnerBigOnlyLongOperator extends VectorMapJoinInnerBig * Single-Column Long get key. */ - long currentKey = vector[batchIndex]; + long currentKey; + boolean isNull; + if (!joinColVector.noNulls && joinColVector.isNull[batchIndex]) { +currentKey = 0; +isNull = true; + } else { +currentKey = vector[batchIndex]; +isNull = false; + } /* * Equal key series checking. */ - if (!haveSaveKey || currentKey != saveKey) { + if (isNull || !haveSaveKey || currentKey != saveKey) { // New key. @@ -261,25 +273,30 @@ public class VectorMapJoinInnerBigOnlyLongOperator extends VectorMapJoinInnerBig } } -// Regardless of our matching result, we keep that information to make multiple use -// of it for a possible series of equal keys. -haveSaveKey = true; - -/* - * Single-Column Long specific save key. - */ - -saveKey = currentKey; - -/* - * Single-Column Long specific lookup key. - */ - -if (useMinMax && (currentKey < min || currentKey > max)) { - // Key out of range for whole hash table. +if (isNull) { saveJoinResult = JoinUtil.JoinResult.NOMATCH; + haveSaveKey = false; } else { - saveJoinResult = hashMultiSet.contains(currentKey, hashMultiSetResults[hashMultiSetResultCount]); + // Regardless of our matching result, we keep that information to make multiple use + // of it for a possible series of equal
[53/91] [abbrv] hive git commit: HIVE-12472: Add test case for HIVE-10592 (Prasanth Jayachandran reviewed by Ashutosh Chauhan)
HIVE-12472: Add test case for HIVE-10592 (Prasanth Jayachandran reviewed by Ashutosh Chauhan) Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/8e9bae21 Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/8e9bae21 Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/8e9bae21 Branch: refs/heads/spark Commit: 8e9bae21af939fa5f264261662fd229f0e72fa70 Parents: 7f4379a Author: Prasanth JayachandranAuthored: Fri Nov 20 17:38:09 2015 -0600 Committer: Prasanth Jayachandran Committed: Fri Nov 20 17:38:09 2015 -0600 -- .../queries/clientpositive/orc_ppd_is_null.q| 20 +++ .../clientpositive/orc_ppd_is_null.q.out| 56 2 files changed, 76 insertions(+) -- http://git-wip-us.apache.org/repos/asf/hive/blob/8e9bae21/ql/src/test/queries/clientpositive/orc_ppd_is_null.q -- diff --git a/ql/src/test/queries/clientpositive/orc_ppd_is_null.q b/ql/src/test/queries/clientpositive/orc_ppd_is_null.q new file mode 100644 index 000..862a961 --- /dev/null +++ b/ql/src/test/queries/clientpositive/orc_ppd_is_null.q @@ -0,0 +1,20 @@ +SET hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat; +SET mapred.min.split.size=1000; +SET mapred.max.split.size=5000; + +create table newtypesorc(c char(10), v varchar(10), d date, ts timestamp) stored as orc tblproperties("orc.stripe.size"="16777216"); + +insert overwrite table newtypesorc select * from (select cast("apple" as char(10)), cast("bee" as varchar(10)), null, null from src src1 union all select cast("hello" as char(10)), cast("world" as varchar(10)), null, null from src src2) uniontbl; + +set hive.optimize.index.filter=false; +select sum(hash(*)) from newtypesorc where ts is null; + +set hive.optimize.index.filter=true; +select sum(hash(*)) from newtypesorc where ts is null; + +set hive.optimize.index.filter=false; +select sum(hash(*)) from newtypesorc where d is null; + +set hive.optimize.index.filter=true; +select sum(hash(*)) from newtypesorc where d is null; + http://git-wip-us.apache.org/repos/asf/hive/blob/8e9bae21/ql/src/test/results/clientpositive/orc_ppd_is_null.q.out -- diff --git a/ql/src/test/results/clientpositive/orc_ppd_is_null.q.out b/ql/src/test/results/clientpositive/orc_ppd_is_null.q.out new file mode 100644 index 000..954e175 --- /dev/null +++ b/ql/src/test/results/clientpositive/orc_ppd_is_null.q.out @@ -0,0 +1,56 @@ +PREHOOK: query: create table newtypesorc(c char(10), v varchar(10), d date, ts timestamp) stored as orc tblproperties("orc.stripe.size"="16777216") +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@newtypesorc +POSTHOOK: query: create table newtypesorc(c char(10), v varchar(10), d date, ts timestamp) stored as orc tblproperties("orc.stripe.size"="16777216") +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@newtypesorc +PREHOOK: query: insert overwrite table newtypesorc select * from (select cast("apple" as char(10)), cast("bee" as varchar(10)), null, null from src src1 union all select cast("hello" as char(10)), cast("world" as varchar(10)), null, null from src src2) uniontbl +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@newtypesorc +POSTHOOK: query: insert overwrite table newtypesorc select * from (select cast("apple" as char(10)), cast("bee" as varchar(10)), null, null from src src1 union all select cast("hello" as char(10)), cast("world" as varchar(10)), null, null from src src2) uniontbl +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@newtypesorc +POSTHOOK: Lineage: newtypesorc.c EXPRESSION [] +POSTHOOK: Lineage: newtypesorc.d EXPRESSION [] +POSTHOOK: Lineage: newtypesorc.ts EXPRESSION [] +POSTHOOK: Lineage: newtypesorc.v EXPRESSION [] +PREHOOK: query: select sum(hash(*)) from newtypesorc where ts is null +PREHOOK: type: QUERY +PREHOOK: Input: default@newtypesorc + A masked pattern was here +POSTHOOK: query: select sum(hash(*)) from newtypesorc where ts is null +POSTHOOK: type: QUERY +POSTHOOK: Input: default@newtypesorc + A masked pattern was here +80926068000 +PREHOOK: query: select sum(hash(*)) from newtypesorc where ts is null +PREHOOK: type: QUERY +PREHOOK: Input: default@newtypesorc + A masked pattern was here +POSTHOOK: query: select sum(hash(*)) from newtypesorc where ts is null +POSTHOOK: type: QUERY +POSTHOOK: Input: default@newtypesorc + A masked pattern was here +80926068000 +PREHOOK: query: select sum(hash(*)) from newtypesorc where d is null +PREHOOK: type: QUERY +PREHOOK: Input:
[36/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable CBO by default when number of joins in a query is equal or less than 1 (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/innerjoin.q.out -- diff --git a/ql/src/test/results/clientpositive/innerjoin.q.out b/ql/src/test/results/clientpositive/innerjoin.q.out index 91bb7b3..092065d 100644 --- a/ql/src/test/results/clientpositive/innerjoin.q.out +++ b/ql/src/test/results/clientpositive/innerjoin.q.out @@ -34,15 +34,14 @@ STAGE PLANS: predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator -expressions: key (type: string), value (type: string) -outputColumnNames: _col0, _col1 +expressions: key (type: string) +outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) TableScan alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -50,14 +49,15 @@ STAGE PLANS: predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator -expressions: key (type: string) -outputColumnNames: _col0 +expressions: key (type: string), value (type: string) +outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: @@ -65,10 +65,10 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col1, _col2 + outputColumnNames: _col0, _col2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator -expressions: UDFToInteger(_col2) (type: int), _col1 (type: string) +expressions: UDFToInteger(_col0) (type: int), _col2 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/join1.q.out -- diff --git a/ql/src/test/results/clientpositive/join1.q.out b/ql/src/test/results/clientpositive/join1.q.out index 9ce2646..761c85e 100644 --- a/ql/src/test/results/clientpositive/join1.q.out +++ b/ql/src/test/results/clientpositive/join1.q.out @@ -34,15 +34,14 @@ STAGE PLANS: predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator -expressions: key (type: string), value (type: string) -outputColumnNames: _col0, _col1 +expressions: key (type: string) +outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) TableScan alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -50,14 +49,15 @@ STAGE PLANS: predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator -expressions: key (type: string) -outputColumnNames: _col0 +expressions: key (type: string), value (type: string) +outputColumnNames: