[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16860356#comment-16860356 ] Josh Elser commented on HBASE-22346: Not sure if you still need/want it, but I removed this branch and pushed a tag (feature-HBASE-22346-tag) instead. If this is just one commit, I reckon that precommit should give you the necessary testing capabilities? Trying to clean up space on Jenkins. Shout if you want this back :) > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16859735#comment-16859735 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #38 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/38/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- For more information [see general report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/38//General_Nightly_Build_Report/] (x) {color:red}-1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/38//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- For more information [see jdk8 (hadoop3) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/38//JDK8_Nightly_Build_Report_(Hadoop3)/] (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16859557#comment-16859557 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #37 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/37/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- For more information [see general report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/37//General_Nightly_Build_Report/] (x) {color:red}-1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/37//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- For more information [see jdk8 (hadoop3) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/37//JDK8_Nightly_Build_Report_(Hadoop3)/] (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16859386#comment-16859386 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #36 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/36/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- For more information [see general report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/36//General_Nightly_Build_Report/] (x) {color:red}-1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/36//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- For more information [see jdk8 (hadoop3) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/36//JDK8_Nightly_Build_Report_(Hadoop3)/] (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16859136#comment-16859136 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #35 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/35/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- For more information [see general report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/35//General_Nightly_Build_Report/] (x) {color:red}-1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/35//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- For more information [see jdk8 (hadoop3) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/35//JDK8_Nightly_Build_Report_(Hadoop3)/] (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16858327#comment-16858327 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #34 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/34/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- For more information [see general report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/34//General_Nightly_Build_Report/] (x) {color:red}-1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/34//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- For more information [see jdk8 (hadoop3) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/34//JDK8_Nightly_Build_Report_(Hadoop3)/] (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16857415#comment-16857415 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #33 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/33/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- For more information [see general report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/33//General_Nightly_Build_Report/] (/) {color:green}+1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/33//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- For more information [see jdk8 (hadoop3) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/33//JDK8_Nightly_Build_Report_(Hadoop3)/] (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16856429#comment-16856429 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #32 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/32/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- For more information [see general report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/32//General_Nightly_Build_Report/] (/) {color:green}+1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/32//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- For more information [see jdk8 (hadoop3) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/32//JDK8_Nightly_Build_Report_(Hadoop3)/] (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16855426#comment-16855426 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #31 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/31/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- For more information [see general report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/31//General_Nightly_Build_Report/] (/) {color:green}+1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/31//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- For more information [see jdk8 (hadoop3) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/31//JDK8_Nightly_Build_Report_(Hadoop3)/] (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16854358#comment-16854358 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #29 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/29/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- For more information [see general report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/29//General_Nightly_Build_Report/] (/) {color:green}+1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/29//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- For more information [see jdk8 (hadoop3) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/29//JDK8_Nightly_Build_Report_(Hadoop3)/] (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16854305#comment-16854305 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #30 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/30/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- For more information [see general report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/30//General_Nightly_Build_Report/] (x) {color:red}-1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/30//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- For more information [see jdk8 (hadoop3) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/30//JDK8_Nightly_Build_Report_(Hadoop3)/] (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16853868#comment-16853868 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #28 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/28/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- For more information [see general report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/28//General_Nightly_Build_Report/] (x) {color:red}-1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/28//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- For more information [see jdk8 (hadoop3) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/28//JDK8_Nightly_Build_Report_(Hadoop3)/] (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16853583#comment-16853583 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #27 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/27/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- For more information [see general report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/27//General_Nightly_Build_Report/] (x) {color:red}-1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/27//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- For more information [see jdk8 (hadoop3) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/27//JDK8_Nightly_Build_Report_(Hadoop3)/] (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16852708#comment-16852708 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #26 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/26/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- For more information [see general report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/26//General_Nightly_Build_Report/] (x) {color:red}-1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/26//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- For more information [see jdk8 (hadoop3) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/26//JDK8_Nightly_Build_Report_(Hadoop3)/] (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16851633#comment-16851633 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #25 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/25/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- For more information [see general report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/25//General_Nightly_Build_Report/] (/) {color:green}+1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/25//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- For more information [see jdk8 (hadoop3) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/25//JDK8_Nightly_Build_Report_(Hadoop3)/] (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16850553#comment-16850553 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #24 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/24/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- For more information [see general report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/24//General_Nightly_Build_Report/] (/) {color:green}+1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/24//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- For more information [see jdk8 (hadoop3) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/24//JDK8_Nightly_Build_Report_(Hadoop3)/] (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16849373#comment-16849373 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #23 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/23/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- For more information [see general report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/23//General_Nightly_Build_Report/] (x) {color:red}-1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/23//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- For more information [see jdk8 (hadoop3) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/23//JDK8_Nightly_Build_Report_(Hadoop3)/] (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16848727#comment-16848727 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #22 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/22/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- For more information [see general report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/22//General_Nightly_Build_Report/] (x) {color:red}-1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/22//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- For more information [see jdk8 (hadoop3) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/22//JDK8_Nightly_Build_Report_(Hadoop3)/] (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16848349#comment-16848349 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #21 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/21/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- For more information [see general report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/21//General_Nightly_Build_Report/] (x) {color:red}-1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/21//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- For more information [see jdk8 (hadoop3) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/21//JDK8_Nightly_Build_Report_(Hadoop3)/] (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16848074#comment-16848074 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #20 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/20/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- For more information [see general report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/20//General_Nightly_Build_Report/] (x) {color:red}-1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/20//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- For more information [see jdk8 (hadoop3) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/20//JDK8_Nightly_Build_Report_(Hadoop3)/] (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16847269#comment-16847269 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #19 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/19/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- For more information [see general report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/19//General_Nightly_Build_Report/] (x) {color:red}-1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/19//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- For more information [see jdk8 (hadoop3) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/19//JDK8_Nightly_Build_Report_(Hadoop3)/] (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16846480#comment-16846480 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #18 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/18/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- For more information [see general report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/18//General_Nightly_Build_Report/] (x) {color:red}-1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/18//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- For more information [see jdk8 (hadoop3) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/18//JDK8_Nightly_Build_Report_(Hadoop3)/] (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16845623#comment-16845623 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #17 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/17/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- For more information [see general report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/17//General_Nightly_Build_Report/] (/) {color:green}+1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/17//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- For more information [see jdk8 (hadoop3) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/17//JDK8_Nightly_Build_Report_(Hadoop3)/] (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16845476#comment-16845476 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #16 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/16/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- For more information [see general report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/16//General_Nightly_Build_Report/] (x) {color:red}-1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/16//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- For more information [see jdk8 (hadoop3) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/16//JDK8_Nightly_Build_Report_(Hadoop3)/] (/) {color:green}+1 source release artifact{color} -- See build output for details. (x) {color:red}-1 client integration test{color} --Failed when running client tests on top of Hadoop 2. [see log for details|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/16//artifact/output-integration/hadoop-2.log]. (note that this means we didn't run on Hadoop 3) > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16844458#comment-16844458 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #15 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/15/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- Something went wrong running this stage, please [check relevant console output|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/15//console]. (x) {color:red}-1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/15//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- For more information [see jdk8 (hadoop3) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/15//JDK8_Nightly_Build_Report_(Hadoop3)/] (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16843616#comment-16843616 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #14 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/14/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- For more information [see general report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/14//General_Nightly_Build_Report/] (x) {color:red}-1 jdk8 hadoop2 checks{color} -- Something went wrong running this stage, please [check relevant console output|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/14//console]. (x) {color:red}-1 jdk8 hadoop3 checks{color} -- For more information [see jdk8 (hadoop3) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/14//JDK8_Nightly_Build_Report_(Hadoop3)/] (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16843105#comment-16843105 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #12 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/12/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- For more information [see general report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/12//General_Nightly_Build_Report/] (x) {color:red}-1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/12//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- Something went wrong running this stage, please [check relevant console output|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/12//console]. (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16841873#comment-16841873 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #11 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/11/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- For more information [see general report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/11//General_Nightly_Build_Report/] (x) {color:red}-1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/11//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- Something went wrong running this stage, please [check relevant console output|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/11//console]. (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16840965#comment-16840965 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #10 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/10/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- For more information [see general report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/10//General_Nightly_Build_Report/] (x) {color:red}-1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/10//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- For more information [see jdk8 (hadoop3) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/10//JDK8_Nightly_Build_Report_(Hadoop3)/] (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16840117#comment-16840117 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #9 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/9/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- For more information [see general report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/9//General_Nightly_Build_Report/] (x) {color:red}-1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/9//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- For more information [see jdk8 (hadoop3) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/9//JDK8_Nightly_Build_Report_(Hadoop3)/] (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16839205#comment-16839205 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #8 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/8/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- For more information [see general report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/8//General_Nightly_Build_Report/] (x) {color:red}-1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/8//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- For more information [see jdk8 (hadoop3) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/8//JDK8_Nightly_Build_Report_(Hadoop3)/] (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16838313#comment-16838313 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #7 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/7/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- Something went wrong running this stage, please [check relevant console output|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/7//console]. (x) {color:red}-1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/7//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- Something went wrong running this stage, please [check relevant console output|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/7//console]. (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16838002#comment-16838002 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #6 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/6/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- For more information [see general report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/6//General_Nightly_Build_Report/] (x) {color:red}-1 jdk8 hadoop2 checks{color} -- Something went wrong running this stage, please [check relevant console output|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/6//console]. (x) {color:red}-1 jdk8 hadoop3 checks{color} -- For more information [see jdk8 (hadoop3) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/6//JDK8_Nightly_Build_Report_(Hadoop3)/] (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16837794#comment-16837794 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #5 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/5/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- For more information [see general report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/5//General_Nightly_Build_Report/] (x) {color:red}-1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/5//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- For more information [see jdk8 (hadoop3) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/5//JDK8_Nightly_Build_Report_(Hadoop3)/] (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16837004#comment-16837004 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #4 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/4/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- For more information [see general report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/4//General_Nightly_Build_Report/] (x) {color:red}-1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/4//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- For more information [see jdk8 (hadoop3) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/4//JDK8_Nightly_Build_Report_(Hadoop3)/] (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16836221#comment-16836221 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #3 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/3/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- Something went wrong running this stage, please [check relevant console output|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/3//console]. (x) {color:red}-1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/3//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- For more information [see jdk8 (hadoop3) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/3//JDK8_Nightly_Build_Report_(Hadoop3)/] (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16835334#comment-16835334 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #2 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/2/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- For more information [see general report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/2//General_Nightly_Build_Report/] (x) {color:red}-1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/2//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- For more information [see jdk8 (hadoop3) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/2//JDK8_Nightly_Build_Report_(Hadoop3)/] (/) {color:green}+1 source release artifact{color} -- See build output for details. (/) {color:green}+1 client integration test{color} > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16834689#comment-16834689 ] Hudson commented on HBASE-22346: Results for branch HBASE-22346 [build #1 on builds.a.o|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/1/]: (x) *{color:red}-1 overall{color}* details (if available): (x) {color:red}-1 general checks{color} -- For more information [see general report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/1//General_Nightly_Build_Report/] (x) {color:red}-1 jdk8 hadoop2 checks{color} -- For more information [see jdk8 (hadoop2) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/1//JDK8_Nightly_Build_Report_(Hadoop2)/] (x) {color:red}-1 jdk8 hadoop3 checks{color} -- For more information [see jdk8 (hadoop3) report|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/1//JDK8_Nightly_Build_Report_(Hadoop3)/] (/) {color:green}+1 source release artifact{color} -- See build output for details. (x) {color:red}-1 client integration test{color} --Failed when running client tests on top of Hadoop 2. [see log for details|https://builds.apache.org/job/HBase%20Nightly/job/HBASE-22346/1//artifact/output-integration/hadoop-2.log]. (note that this means we didn't run on Hadoop 3) > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > Attachments: HBASE-22346.01.patch, HBASE-22346.patch > > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16834330#comment-16834330 ] HBase QA commented on HBASE-22346: -- | (x) *{color:red}-1 overall{color}* | \\ \\ || Vote || Subsystem || Runtime || Comment || | {color:blue}0{color} | {color:blue} reexec {color} | {color:blue} 0m 56s{color} | {color:blue} Docker mode activated. {color} | || || || || {color:brown} Prechecks {color} || | {color:green}+1{color} | {color:green} hbaseanti {color} | {color:green} 0m 0s{color} | {color:green} Patch does not have any anti-patterns. {color} | | {color:green}+1{color} | {color:green} @author {color} | {color:green} 0m 0s{color} | {color:green} The patch does not contain any @author tags. {color} | | {color:green}+1{color} | {color:green} test4tests {color} | {color:green} 0m 0s{color} | {color:green} The patch appears to include 1 new or modified test files. {color} | || || || || {color:brown} master Compile Tests {color} || | {color:green}+1{color} | {color:green} mvninstall {color} | {color:green} 7m 8s{color} | {color:green} master passed {color} | | {color:green}+1{color} | {color:green} compile {color} | {color:green} 2m 1s{color} | {color:green} master passed {color} | | {color:green}+1{color} | {color:green} checkstyle {color} | {color:green} 2m 10s{color} | {color:green} master passed {color} | | {color:green}+1{color} | {color:green} shadedjars {color} | {color:green} 5m 48s{color} | {color:green} branch has no errors when building our shaded downstream artifacts. {color} | | {color:green}+1{color} | {color:green} findbugs {color} | {color:green} 3m 53s{color} | {color:green} master passed {color} | | {color:green}+1{color} | {color:green} javadoc {color} | {color:green} 0m 31s{color} | {color:green} master passed {color} | || || || || {color:brown} Patch Compile Tests {color} || | {color:green}+1{color} | {color:green} mvninstall {color} | {color:green} 4m 33s{color} | {color:green} the patch passed {color} | | {color:green}+1{color} | {color:green} compile {color} | {color:green} 1m 8s{color} | {color:green} the patch passed {color} | | {color:green}+1{color} | {color:green} javac {color} | {color:green} 1m 8s{color} | {color:green} the patch passed {color} | | {color:red}-1{color} | {color:red} checkstyle {color} | {color:red} 1m 27s{color} | {color:red} hbase-server: The patch generated 5 new + 94 unchanged - 1 fixed = 99 total (was 95) {color} | | {color:green}+1{color} | {color:green} whitespace {color} | {color:green} 0m 0s{color} | {color:green} The patch has no whitespace issues. {color} | | {color:green}+1{color} | {color:green} shadedjars {color} | {color:green} 6m 32s{color} | {color:green} patch has no errors when building our shaded downstream artifacts. {color} | | {color:green}+1{color} | {color:green} hadoopcheck {color} | {color:green} 13m 53s{color} | {color:green} Patch does not cause any errors with Hadoop 2.7.4 or 3.0.0. {color} | | {color:green}+1{color} | {color:green} findbugs {color} | {color:green} 6m 6s{color} | {color:green} the patch passed {color} | | {color:green}+1{color} | {color:green} javadoc {color} | {color:green} 1m 2s{color} | {color:green} the patch passed {color} | || || || || {color:brown} Other Tests {color} || | {color:red}-1{color} | {color:red} unit {color} | {color:red}160m 7s{color} | {color:red} hbase-server in the patch failed. {color} | | {color:green}+1{color} | {color:green} asflicense {color} | {color:green} 0m 24s{color} | {color:green} The patch does not generate ASF License warnings. {color} | | {color:black}{color} | {color:black} {color} | {color:black}218m 28s{color} | {color:black} {color} | \\ \\ || Reason || Tests || | Failed junit tests | hadoop.hbase.client.TestAsyncTableGetMultiThreaded | \\ \\ || Subsystem || Report/Notes || | Docker | Client=17.05.0-ce Server=17.05.0-ce base: https://builds.apache.org/job/PreCommit-HBASE-Build/253/artifact/patchprocess/Dockerfile | | JIRA Issue | HBASE-22346 | | JIRA Patch URL | https://issues.apache.org/jira/secure/attachment/12967980/HBASE-22346.01.patch | | Optional Tests | dupname asflicense javac javadoc unit findbugs shadedjars hadoopcheck hbaseanti checkstyle compile | | uname | Linux f3493376e302 4.4.0-143-generic #169~14.04.2-Ubuntu SMP Wed Feb 13 15:00:41 UTC 2019 x86_64 GNU/Linux | | Build tool | maven | | Personality | dev-support/hbase-personality.sh | | git revision | master / 67c937fa92 | | maven | version: Apache Maven 3.5.4 (1edded0938998edf8bf061f1ceb3cfdeccf443fe; 2018-06-17T18:33:14Z) | | Default Java | 1.8.0_181 | | findbugs | v3.1.11 | | checkstyle | https://builds.apache.org/job/PreCommit-HBASE-Build/253/artifact/patchprocess/diff-checkstyle-hbase-server.txt | | unit | https://builds.apache.org/job/PreCommit-HBASE-Build/253/artifact/patchprocess/patch-unit-hbase-server.txt | | Test Results |
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16831243#comment-16831243 ] HBase QA commented on HBASE-22346: -- | (x) *{color:red}-1 overall{color}* | \\ \\ || Vote || Subsystem || Runtime || Comment || | {color:blue}0{color} | {color:blue} reexec {color} | {color:blue} 0m 17s{color} | {color:blue} Docker mode activated. {color} | || || || || {color:brown} Prechecks {color} || | {color:green}+1{color} | {color:green} hbaseanti {color} | {color:green} 0m 0s{color} | {color:green} Patch does not have any anti-patterns. {color} | | {color:green}+1{color} | {color:green} @author {color} | {color:green} 0m 0s{color} | {color:green} The patch does not contain any @author tags. {color} | | {color:green}+1{color} | {color:green} test4tests {color} | {color:green} 0m 0s{color} | {color:green} The patch appears to include 1 new or modified test files. {color} | || || || || {color:brown} master Compile Tests {color} || | {color:green}+1{color} | {color:green} mvninstall {color} | {color:green} 4m 24s{color} | {color:green} master passed {color} | | {color:green}+1{color} | {color:green} compile {color} | {color:green} 0m 51s{color} | {color:green} master passed {color} | | {color:green}+1{color} | {color:green} checkstyle {color} | {color:green} 1m 17s{color} | {color:green} master passed {color} | | {color:green}+1{color} | {color:green} shadedjars {color} | {color:green} 4m 31s{color} | {color:green} branch has no errors when building our shaded downstream artifacts. {color} | | {color:green}+1{color} | {color:green} findbugs {color} | {color:green} 3m 50s{color} | {color:green} master passed {color} | | {color:green}+1{color} | {color:green} javadoc {color} | {color:green} 0m 31s{color} | {color:green} master passed {color} | || || || || {color:brown} Patch Compile Tests {color} || | {color:green}+1{color} | {color:green} mvninstall {color} | {color:green} 4m 8s{color} | {color:green} the patch passed {color} | | {color:green}+1{color} | {color:green} compile {color} | {color:green} 0m 52s{color} | {color:green} the patch passed {color} | | {color:green}+1{color} | {color:green} javac {color} | {color:green} 0m 52s{color} | {color:green} the patch passed {color} | | {color:red}-1{color} | {color:red} checkstyle {color} | {color:red} 1m 17s{color} | {color:red} hbase-server: The patch generated 6 new + 94 unchanged - 1 fixed = 100 total (was 95) {color} | | {color:green}+1{color} | {color:green} whitespace {color} | {color:green} 0m 0s{color} | {color:green} The patch has no whitespace issues. {color} | | {color:green}+1{color} | {color:green} shadedjars {color} | {color:green} 4m 31s{color} | {color:green} patch has no errors when building our shaded downstream artifacts. {color} | | {color:green}+1{color} | {color:green} hadoopcheck {color} | {color:green} 8m 38s{color} | {color:green} Patch does not cause any errors with Hadoop 2.7.4 or 3.0.0. {color} | | {color:green}+1{color} | {color:green} findbugs {color} | {color:green} 4m 18s{color} | {color:green} the patch passed {color} | | {color:green}+1{color} | {color:green} javadoc {color} | {color:green} 0m 31s{color} | {color:green} the patch passed {color} | || || || || {color:brown} Other Tests {color} || | {color:green}+1{color} | {color:green} unit {color} | {color:green}137m 33s{color} | {color:green} hbase-server in the patch passed. {color} | | {color:green}+1{color} | {color:green} asflicense {color} | {color:green} 0m 21s{color} | {color:green} The patch does not generate ASF License warnings. {color} | | {color:black}{color} | {color:black} {color} | {color:black}178m 23s{color} | {color:black} {color} | \\ \\ || Subsystem || Report/Notes || | Docker | Client=17.05.0-ce Server=17.05.0-ce base: https://builds.apache.org/job/PreCommit-HBASE-Build/226/artifact/patchprocess/Dockerfile | | JIRA Issue | HBASE-22346 | | JIRA Patch URL | https://issues.apache.org/jira/secure/attachment/12967572/HBASE-22346.patch | | Optional Tests | dupname asflicense javac javadoc unit findbugs shadedjars hadoopcheck hbaseanti checkstyle compile | | uname | Linux 3bcbdd583a67 4.4.0-143-generic #169~14.04.2-Ubuntu SMP Wed Feb 13 15:00:41 UTC 2019 x86_64 GNU/Linux | | Build tool | maven | | Personality | dev-support/hbase-personality.sh | | git revision | master / 4379fe4ad3 | | maven | version: Apache Maven 3.5.4 (1edded0938998edf8bf061f1ceb3cfdeccf443fe; 2018-06-17T18:33:14Z) | | Default Java | 1.8.0_181 | | findbugs | v3.1.11 | | checkstyle | https://builds.apache.org/job/PreCommit-HBASE-Build/226/artifact/patchprocess/diff-checkstyle-hbase-server.txt | | Test Results | https://builds.apache.org/job/PreCommit-HBASE-Build/226/testReport/ | | Max. process+thread count | 4915 (vs. ulimit of 1) | | modules | C: hbase-server U: hbase-server | | Console output |
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16830826#comment-16830826 ] Sergey Shelukhin commented on HBASE-22346: -- [~stack] [~mbertozzi] does this make sense to you? preserves the old behavior with low/no overhead when unset. We will probably run this for meta only on our cluster and see how it goes. > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Assignee: Sergey Shelukhin >Priority: Major > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (HBASE-22346) scanner priorities/deadline units are invalid for non-huge scanners
[ https://issues.apache.org/jira/browse/HBASE-22346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16830647#comment-16830647 ] Sergey Shelukhin commented on HBASE-22346: -- cc [~mbertozzi] was adding the number to received time intentional? > scanner priorities/deadline units are invalid for non-huge scanners > --- > > Key: HBASE-22346 > URL: https://issues.apache.org/jira/browse/HBASE-22346 > Project: HBase > Issue Type: Bug >Reporter: Sergey Shelukhin >Priority: Major > > I was looking at using the priority (deadline) queue for scanner requests; > what I see is that AnnotationReadingPriorityFunction, the only impl of the > deadline function available, implements getDeadline as sqrt of the number of > next() calls, from HBASE-10993. > However, CallPriorityComparator.compare, its only caller, adds that > "deadline" value to the callA.getReceiveTime() in milliseconds... > That results in some sort of a meaningless value that I assume only make > sense "by coincidence" for telling apart broad and specific classes of > scanners... in practice next calls must be in the 1000s before it becomes > meaningful vs small differences in ReceivedTime > When there's contention from many scanners, e.g. small scanners for meta, or > just users creating tons of scanners to the point where requests queue up, > the actual deadline is not accounted for and the priority function itself is > meaningless... In fact as queueing increases, it becomes worse because > receivedtime differences grow. -- This message was sent by Atlassian JIRA (v7.6.3#76005)