[jira] [Updated] (HBASE-17747) Support both weak and soft object pool
[ https://issues.apache.org/jira/browse/HBASE-17747?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Duo Zhang updated HBASE-17747: -- Affects Version/s: (was: 2.0) 2.0.0 Fix Version/s: (was: 2.0) 2.0.0 > Support both weak and soft object pool > -- > > Key: HBASE-17747 > URL: https://issues.apache.org/jira/browse/HBASE-17747 > Project: HBase > Issue Type: Improvement >Affects Versions: 2.0.0 >Reporter: Yu Li >Assignee: Yu Li > Fix For: 2.0.0 > > Attachments: HBASE-17747.patch, HBASE-17747.v2.patch, > HBASE-17747.v3.patch > > > During YCSB testing on embedded mode after HBASE-17744, we found that under > high read load GC is quite severe even with offheap L2 cache. After some > investigation, we found it's caused by using weak reference in > {{IdReadWriteLock}}. In embedded mode the read is so quick that the lock > might already get promoted to the old generation when the weak reference is > cleared, which causes dirty card table (old reference get removed and new > lock object set into {{referenceCache}}, see {{WeakObjectPool#get}}) thus > slowing YGC. In distributed mode there'll also be more lock object created > with weak reference than soft reference that slowing down the processing. > So we proposed to use soft reference for this {{IdReadWriteLock}} used in > cache, which won't get cleared until JVM memory is not enough, and could > resolve the issue mentioned above. What's more, we propose to extend the > {{WeakObjectPool}} to be more generate to support both weak and soft > reference. > Note that the GC issue only emerges under embedded mode with DirectOperator, > in which case all costs on the wire is removed thus produces extremely high > concurrency. -- This message was sent by Atlassian JIRA (v6.3.15#6346)
[jira] [Updated] (HBASE-17747) Support both weak and soft object pool
[ https://issues.apache.org/jira/browse/HBASE-17747?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Yu Li updated HBASE-17747: -- Resolution: Fixed Status: Resolved (was: Patch Available) Closing JIRA and move to HBASE-17782 for further discussion. Thanks all for review. > Support both weak and soft object pool > -- > > Key: HBASE-17747 > URL: https://issues.apache.org/jira/browse/HBASE-17747 > Project: HBase > Issue Type: Improvement >Affects Versions: 2.0 >Reporter: Yu Li >Assignee: Yu Li > Fix For: 2.0 > > Attachments: HBASE-17747.patch, HBASE-17747.v2.patch, > HBASE-17747.v3.patch > > > During YCSB testing on embedded mode after HBASE-17744, we found that under > high read load GC is quite severe even with offheap L2 cache. After some > investigation, we found it's caused by using weak reference in > {{IdReadWriteLock}}. In embedded mode the read is so quick that the lock > might already get promoted to the old generation when the weak reference is > cleared, which causes dirty card table (old reference get removed and new > lock object set into {{referenceCache}}, see {{WeakObjectPool#get}}) thus > slowing YGC. In distributed mode there'll also be more lock object created > with weak reference than soft reference that slowing down the processing. > So we proposed to use soft reference for this {{IdReadWriteLock}} used in > cache, which won't get cleared until JVM memory is not enough, and could > resolve the issue mentioned above. What's more, we propose to extend the > {{WeakObjectPool}} to be more generate to support both weak and soft > reference. > Note that the GC issue only emerges under embedded mode with DirectOperator, > in which case all costs on the wire is removed thus produces extremely high > concurrency. -- This message was sent by Atlassian JIRA (v6.3.15#6346)
[jira] [Updated] (HBASE-17747) Support both weak and soft object pool
[ https://issues.apache.org/jira/browse/HBASE-17747?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Yu Li updated HBASE-17747: -- Affects Version/s: 2.0 Hadoop Flags: Reviewed Fix Version/s: 2.0 Pushed into master branch, thanks all for review [~tedyu] [~Apache9] [~anoop.hbase]. Leave this JIRA open for the ongoing discussion. > Support both weak and soft object pool > -- > > Key: HBASE-17747 > URL: https://issues.apache.org/jira/browse/HBASE-17747 > Project: HBase > Issue Type: Improvement >Affects Versions: 2.0 >Reporter: Yu Li >Assignee: Yu Li > Fix For: 2.0 > > Attachments: HBASE-17747.patch, HBASE-17747.v2.patch, > HBASE-17747.v3.patch > > > During YCSB testing on embedded mode after HBASE-17744, we found that under > high read load GC is quite severe even with offheap L2 cache. After some > investigation, we found it's caused by using weak reference in > {{IdReadWriteLock}}. In embedded mode the read is so quick that the lock > might already get promoted to the old generation when the weak reference is > cleared, which causes dirty card table (old reference get removed and new > lock object set into {{referenceCache}}, see {{WeakObjectPool#get}}) thus > slowing YGC. In distributed mode there'll also be more lock object created > with weak reference than soft reference that slowing down the processing. > So we proposed to use soft reference for this {{IdReadWriteLock}} used in > cache, which won't get cleared until JVM memory is not enough, and could > resolve the issue mentioned above. What's more, we propose to extend the > {{WeakObjectPool}} to be more generate to support both weak and soft > reference. > Note that the GC issue only emerges under embedded mode with DirectOperator, > in which case all costs on the wire is removed thus produces extremely high > concurrency. -- This message was sent by Atlassian JIRA (v6.3.15#6346)
[jira] [Updated] (HBASE-17747) Support both weak and soft object pool
[ https://issues.apache.org/jira/browse/HBASE-17747?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Yu Li updated HBASE-17747: -- Description: During YCSB testing on embedded mode after HBASE-17744, we found that under high read load GC is quite severe even with offheap L2 cache. After some investigation, we found it's caused by using weak reference in {{IdReadWriteLock}}. In embedded mode the read is so quick that the lock might already get promoted to the old generation when the weak reference is cleared, which causes dirty card table (old reference get removed and new lock object set into {{referenceCache}}, see {{WeakObjectPool#get}}) thus slowing YGC. In distributed mode there'll also be more lock object created with weak reference than soft reference that slowing down the processing. So we proposed to use soft reference for this {{IdReadWriteLock}} used in cache, which won't get cleared until JVM memory is not enough, and could resolve the issue mentioned above. What's more, we propose to extend the {{WeakObjectPool}} to be more generate to support both weak and soft reference. Note that the GC issue only emerges under embedded mode with DirectOperator, in which case all costs on the wire is removed thus produces extremely high concurrency. was: During YCSB testing on embedded mode after HBASE-17744, we found that under high read load GC is quite severe even with offheap L2 cache. After some investigation, we found it's caused by using weak reference for IdReadWriteLock. In embedded mode the read is so quick that the lock might already get promoted to the old generation when the weak reference is cleared, which causes dirty card table thus slowing YGC. So we proposed to use soft reference for this IdReadWriteLock used in cache, which won't get cleared until JVM memory is not enough, and could resolve the issue mentioned above. What's more, we propose to extend the WeakObjectPool to be more generate to support both weak and soft reference. Note that this issue only emerges under embedded mode with DirectOperator, in which case all costs on the wire is removed thus produces extremely high workloads. > Support both weak and soft object pool > -- > > Key: HBASE-17747 > URL: https://issues.apache.org/jira/browse/HBASE-17747 > Project: HBase > Issue Type: Improvement >Reporter: Yu Li >Assignee: Yu Li > Attachments: HBASE-17747.patch, HBASE-17747.v2.patch, > HBASE-17747.v3.patch > > > During YCSB testing on embedded mode after HBASE-17744, we found that under > high read load GC is quite severe even with offheap L2 cache. After some > investigation, we found it's caused by using weak reference in > {{IdReadWriteLock}}. In embedded mode the read is so quick that the lock > might already get promoted to the old generation when the weak reference is > cleared, which causes dirty card table (old reference get removed and new > lock object set into {{referenceCache}}, see {{WeakObjectPool#get}}) thus > slowing YGC. In distributed mode there'll also be more lock object created > with weak reference than soft reference that slowing down the processing. > So we proposed to use soft reference for this {{IdReadWriteLock}} used in > cache, which won't get cleared until JVM memory is not enough, and could > resolve the issue mentioned above. What's more, we propose to extend the > {{WeakObjectPool}} to be more generate to support both weak and soft > reference. > Note that the GC issue only emerges under embedded mode with DirectOperator, > in which case all costs on the wire is removed thus produces extremely high > concurrency. -- This message was sent by Atlassian JIRA (v6.3.15#6346)
[jira] [Updated] (HBASE-17747) Support both weak and soft object pool
[ https://issues.apache.org/jira/browse/HBASE-17747?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Yu Li updated HBASE-17747: -- Attachment: HBASE-17747.v3.patch Rebase on latest code base and fix javadoc issue. > Support both weak and soft object pool > -- > > Key: HBASE-17747 > URL: https://issues.apache.org/jira/browse/HBASE-17747 > Project: HBase > Issue Type: Improvement >Reporter: Yu Li >Assignee: Yu Li > Attachments: HBASE-17747.patch, HBASE-17747.v2.patch, > HBASE-17747.v3.patch > > > During YCSB testing on embedded mode after HBASE-17744, we found that under > high read load GC is quite severe even with offheap L2 cache. After some > investigation, we found it's caused by using weak reference for > IdReadWriteLock. In embedded mode the read is so quick that the lock might > already get promoted to the old generation when the weak reference is > cleared, which causes dirty card table thus slowing YGC. > So we proposed to use soft reference for this IdReadWriteLock used in cache, > which won't get cleared until JVM memory is not enough, and could resolve the > issue mentioned above. What's more, we propose to extend the WeakObjectPool > to be more generate to support both weak and soft reference. > Note that this issue only emerges under embedded mode with DirectOperator, in > which case all costs on the wire is removed thus produces extremely high > workloads. -- This message was sent by Atlassian JIRA (v6.3.15#6346)
[jira] [Updated] (HBASE-17747) Support both weak and soft object pool
[ https://issues.apache.org/jira/browse/HBASE-17747?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Yu Li updated HBASE-17747: -- Attachment: HBASE-17747.v2.patch The v2 patch fixes the javadoc issue > Support both weak and soft object pool > -- > > Key: HBASE-17747 > URL: https://issues.apache.org/jira/browse/HBASE-17747 > Project: HBase > Issue Type: Improvement >Reporter: Yu Li >Assignee: Yu Li > Attachments: HBASE-17747.patch, HBASE-17747.v2.patch > > > During YCSB testing on embedded mode after HBASE-17744, we found that under > high read load GC is quite severe even with offheap L2 cache. After some > investigation, we found it's caused by using weak reference for > IdReadWriteLock. In embedded mode the read is so quick that the lock might > already get promoted to the old generation when the weak reference is > cleared, which causes dirty card table thus slowing YGC. > So we proposed to use soft reference for this IdReadWriteLock used in cache, > which won't get cleared until JVM memory is not enough, and could resolve the > issue mentioned above. What's more, we propose to extend the WeakObjectPool > to be more generate to support both weak and soft reference. > Note that this issue only emerges under embedded mode with DirectOperator, in > which case all costs on the wire is removed thus produces extremely high > workloads. -- This message was sent by Atlassian JIRA (v6.3.15#6346)
[jira] [Updated] (HBASE-17747) Support both weak and soft object pool
[ https://issues.apache.org/jira/browse/HBASE-17747?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Yu Li updated HBASE-17747: -- Status: Patch Available (was: Open) Submit patch for HadoopQA > Support both weak and soft object pool > -- > > Key: HBASE-17747 > URL: https://issues.apache.org/jira/browse/HBASE-17747 > Project: HBase > Issue Type: Improvement >Reporter: Yu Li >Assignee: Yu Li > Attachments: HBASE-17747.patch > > > During YCSB testing on embedded mode after HBASE-17744, we found that under > high read load GC is quite severe even with offheap L2 cache. After some > investigation, we found it's caused by using weak reference for > IdReadWriteLock. In embedded mode the read is so quick that the lock might > already get promoted to the old generation when the weak reference is > cleared, which causes dirty card table thus slowing YGC. > So we proposed to use soft reference for this IdReadWriteLock used in cache, > which won't get cleared until JVM memory is not enough, and could resolve the > issue mentioned above. What's more, we propose to extend the WeakObjectPool > to be more generate to support both weak and soft reference. > Note that this issue only emerges under embedded mode with DirectOperator, in > which case all costs on the wire is removed thus produces extremely high > workloads. -- This message was sent by Atlassian JIRA (v6.3.15#6346)
[jira] [Updated] (HBASE-17747) Support both weak and soft object pool
[ https://issues.apache.org/jira/browse/HBASE-17747?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Yu Li updated HBASE-17747: -- Attachment: HBASE-17747.patch Uploading the initial patch > Support both weak and soft object pool > -- > > Key: HBASE-17747 > URL: https://issues.apache.org/jira/browse/HBASE-17747 > Project: HBase > Issue Type: Improvement >Reporter: Yu Li >Assignee: Yu Li > Attachments: HBASE-17747.patch > > > During YCSB testing on embedded mode after HBASE-17744, we found that under > high read load GC is quite severe even with offheap L2 cache. After some > investigation, we found it's caused by using weak reference for > IdReadWriteLock. In embedded mode the read is so quick that the lock might > already get promoted to the old generation when the weak reference is > cleared, which causes dirty card table thus slowing YGC. > So we proposed to use soft reference for this IdReadWriteLock used in cache, > which won't get cleared until JVM memory is not enough, and could resolve the > issue mentioned above. What's more, we propose to extend the WeakObjectPool > to be more generate to support both weak and soft reference. > Note that this issue only emerges under embedded mode with DirectOperator, in > which case all costs on the wire is removed thus produces extremely high > workloads. -- This message was sent by Atlassian JIRA (v6.3.15#6346)