[
https://issues.apache.org/jira/browse/LUCENE-6779?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14743566#comment-14743566
]
Shalin Shekhar Mangar commented on LUCENE-6779:
-----------------------------------------------
In these results, testWriteString3 is the one which uses scratch bytes to
encode small strings:
{code}
java -server -Xmx2048M -Xms2048M -Dtests.seed=18262
-Dtests.datagen.path=./data.txt -Dtests.string.minlen=5
-Dtests.string.maxlen=64 -Dtests.string.num=10000 -jar target/benchmarks.jar
-wi 5 -i 50 -gc true -f 2 -prof gc ".*GrowableByteArrayDataOutputBenchmark.*"
# Run complete. Total time: 00:08:55
Benchmark
Mode Cnt Score Error Units
GrowableByteArrayDataOutputBenchmark.testWriteString1
thrpt 100 2915687.179 ± 4981.266 ops/s
GrowableByteArrayDataOutputBenchmark.testWriteString1:·gc.alloc.rate
thrpt 100 0.001 ± 0.001 MB/sec
GrowableByteArrayDataOutputBenchmark.testWriteString1:·gc.alloc.rate.norm
thrpt 100 ≈ 10⁻⁴ B/op
GrowableByteArrayDataOutputBenchmark.testWriteString1:·gc.count
thrpt 100 ≈ 0 counts
GrowableByteArrayDataOutputBenchmark.testWriteString2
thrpt 100 4216428.245 ± 7822.793 ops/s
GrowableByteArrayDataOutputBenchmark.testWriteString2:·gc.alloc.rate
thrpt 100 595.210 ± 1.103 MB/sec
GrowableByteArrayDataOutputBenchmark.testWriteString2:·gc.alloc.rate.norm
thrpt 100 148.060 ± 0.001 B/op
GrowableByteArrayDataOutputBenchmark.testWriteString2:·gc.count
thrpt 100 1.000 counts
GrowableByteArrayDataOutputBenchmark.testWriteString2:·gc.time
thrpt 100 2.000 ms
GrowableByteArrayDataOutputBenchmark.testWriteString3
thrpt 100 4581362.617 ± 11683.766 ops/s
GrowableByteArrayDataOutputBenchmark.testWriteString3:·gc.alloc.rate
thrpt 100 0.001 ± 0.001 MB/sec
GrowableByteArrayDataOutputBenchmark.testWriteString3:·gc.alloc.rate.norm
thrpt 100 ≈ 10⁻⁴ B/op
GrowableByteArrayDataOutputBenchmark.testWriteString3:·gc.count
thrpt 100 ≈ 0 counts
GrowableByteArrayDataOutputBenchmark.testWriteStringDefault
thrpt 100 4277669.423 ± 19742.963 ops/s
GrowableByteArrayDataOutputBenchmark.testWriteStringDefault:·gc.alloc.rate
thrpt 100 603.855 ± 2.787 MB/sec
GrowableByteArrayDataOutputBenchmark.testWriteStringDefault:·gc.alloc.rate.norm
thrpt 100 148.060 ± 0.001 B/op
GrowableByteArrayDataOutputBenchmark.testWriteStringDefault:·gc.churn.PS_Eden_Space
thrpt 100 5.947 ± 20.169 MB/sec
GrowableByteArrayDataOutputBenchmark.testWriteStringDefault:·gc.churn.PS_Eden_Space.norm
thrpt 100 1.462 ± 4.958 B/op
GrowableByteArrayDataOutputBenchmark.testWriteStringDefault:·gc.count
thrpt 100 2.000 counts
GrowableByteArrayDataOutputBenchmark.testWriteStringDefault:·gc.time
thrpt 100 3.000 ms
{code}
> Reduce memory allocated by CompressingStoredFieldsWriter to write large
> strings
> -------------------------------------------------------------------------------
>
> Key: LUCENE-6779
> URL: https://issues.apache.org/jira/browse/LUCENE-6779
> Project: Lucene - Core
> Issue Type: Improvement
> Components: core/codecs
> Reporter: Shalin Shekhar Mangar
> Attachments: LUCENE-6779.patch, LUCENE-6779.patch, LUCENE-6779.patch,
> LUCENE-6779_alt.patch
>
>
> In SOLR-7927, I am trying to reduce the memory required to index very large
> documents (between 10 to 100MB) and one of the places which allocate a lot of
> heap is the UTF8 encoding in CompressingStoredFieldsWriter. The same problem
> existed in JavaBinCodec and we reduced its memory allocation by falling back
> to a double pass approach in SOLR-7971 when the utf8 size of the string is
> greater than 64KB.
> I propose to make the same changes to CompressingStoredFieldsWriter as we
> made to JavaBinCodec in SOLR-7971.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
