[jira] [Updated] (HBASE-20710) extra cloneFamily() in Mutation.add(Cell)
[ https://issues.apache.org/jira/browse/HBASE-20710?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Guanghao Zhang updated HBASE-20710: --- Fix Version/s: (was: 2.2.0) > extra cloneFamily() in Mutation.add(Cell) > - > > Key: HBASE-20710 > URL: https://issues.apache.org/jira/browse/HBASE-20710 > Project: HBase > Issue Type: Sub-task > Components: regionserver >Affects Versions: 2.0.1 >Reporter: huaxiang sun >Assignee: huaxiang sun >Priority: Minor > Fix For: 3.0.0, 2.1.0, 2.0.2 > > Attachments: 2.0621.2.12782.alloc.svg, 2.0623.111354.alloc.svg, > HBASE-20710-master-v001.patch, HBASE-20710-master-v002.patch, > HBASE-20710-master-v002.patch, HBASE-20710.master.001.patch, > alloc-put-fix.svg, alloc-put-orig.svg > > > The cpu profiling shows that during PE randomWrite testing, about 1 percent > of time is spent in cloneFamily. Reviewing code found that when a cell is DBB > backed ByteBuffKeyValueCell (which is default with Netty Rpc), > cell.getFamilyArray() will call cloneFamily() and there is again a > cloneFamily() in the following line of the code. since this is the critical > write path processing, this needs to be optimized. > https://github.com/apache/hbase/blob/master/hbase-client/src/main/java/org/apache/hadoop/hbase/client/Mutation.java#L791 > https://github.com/apache/hbase/blob/master/hbase-client/src/main/java/org/apache/hadoop/hbase/client/Mutation.java#L795 -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Updated] (HBASE-20710) extra cloneFamily() in Mutation.add(Cell)
[ https://issues.apache.org/jira/browse/HBASE-20710?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Guanghao Zhang updated HBASE-20710: --- Fix Version/s: 2.2.0 > extra cloneFamily() in Mutation.add(Cell) > - > > Key: HBASE-20710 > URL: https://issues.apache.org/jira/browse/HBASE-20710 > Project: HBase > Issue Type: Sub-task > Components: regionserver >Affects Versions: 2.0.1 >Reporter: huaxiang sun >Assignee: huaxiang sun >Priority: Minor > Fix For: 3.0.0, 2.1.0, 2.2.0, 2.0.2 > > Attachments: 2.0621.2.12782.alloc.svg, 2.0623.111354.alloc.svg, > HBASE-20710-master-v001.patch, HBASE-20710-master-v002.patch, > HBASE-20710-master-v002.patch, HBASE-20710.master.001.patch, > alloc-put-fix.svg, alloc-put-orig.svg > > > The cpu profiling shows that during PE randomWrite testing, about 1 percent > of time is spent in cloneFamily. Reviewing code found that when a cell is DBB > backed ByteBuffKeyValueCell (which is default with Netty Rpc), > cell.getFamilyArray() will call cloneFamily() and there is again a > cloneFamily() in the following line of the code. since this is the critical > write path processing, this needs to be optimized. > https://github.com/apache/hbase/blob/master/hbase-client/src/main/java/org/apache/hadoop/hbase/client/Mutation.java#L791 > https://github.com/apache/hbase/blob/master/hbase-client/src/main/java/org/apache/hadoop/hbase/client/Mutation.java#L795 -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Updated] (HBASE-20710) extra cloneFamily() in Mutation.add(Cell)
[ https://issues.apache.org/jira/browse/HBASE-20710?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] stack updated HBASE-20710: -- Resolution: Fixed Hadoop Flags: Reviewed Fix Version/s: 2.1.0 3.0.0 Status: Resolved (was: Patch Available) Pushed to branch-2.0, 2.1, and master. Thanks [~huaxiang] I pushed it because want it in my profiling runs. Hope you don't mind. > extra cloneFamily() in Mutation.add(Cell) > - > > Key: HBASE-20710 > URL: https://issues.apache.org/jira/browse/HBASE-20710 > Project: HBase > Issue Type: Sub-task > Components: regionserver >Affects Versions: 2.0.1 >Reporter: huaxiang sun >Assignee: huaxiang sun >Priority: Minor > Fix For: 3.0.0, 2.1.0, 2.0.2 > > Attachments: 2.0621.2.12782.alloc.svg, 2.0623.111354.alloc.svg, > HBASE-20710-master-v001.patch, HBASE-20710-master-v002.patch, > HBASE-20710-master-v002.patch, HBASE-20710.master.001.patch, > alloc-put-fix.svg, alloc-put-orig.svg > > > The cpu profiling shows that during PE randomWrite testing, about 1 percent > of time is spent in cloneFamily. Reviewing code found that when a cell is DBB > backed ByteBuffKeyValueCell (which is default with Netty Rpc), > cell.getFamilyArray() will call cloneFamily() and there is again a > cloneFamily() in the following line of the code. since this is the critical > write path processing, this needs to be optimized. > https://github.com/apache/hbase/blob/master/hbase-client/src/main/java/org/apache/hadoop/hbase/client/Mutation.java#L791 > https://github.com/apache/hbase/blob/master/hbase-client/src/main/java/org/apache/hadoop/hbase/client/Mutation.java#L795 -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Updated] (HBASE-20710) extra cloneFamily() in Mutation.add(Cell)
[ https://issues.apache.org/jira/browse/HBASE-20710?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] stack updated HBASE-20710: -- Attachment: 2.0621.2.12782.alloc.svg > extra cloneFamily() in Mutation.add(Cell) > - > > Key: HBASE-20710 > URL: https://issues.apache.org/jira/browse/HBASE-20710 > Project: HBase > Issue Type: Sub-task > Components: regionserver >Affects Versions: 2.0.1 >Reporter: huaxiang sun >Assignee: huaxiang sun >Priority: Minor > Fix For: 2.0.2 > > Attachments: 2.0621.2.12782.alloc.svg, 2.0623.111354.alloc.svg, > HBASE-20710-master-v001.patch, HBASE-20710-master-v002.patch, > HBASE-20710-master-v002.patch, HBASE-20710.master.001.patch, > alloc-put-fix.svg, alloc-put-orig.svg > > > The cpu profiling shows that during PE randomWrite testing, about 1 percent > of time is spent in cloneFamily. Reviewing code found that when a cell is DBB > backed ByteBuffKeyValueCell (which is default with Netty Rpc), > cell.getFamilyArray() will call cloneFamily() and there is again a > cloneFamily() in the following line of the code. since this is the critical > write path processing, this needs to be optimized. > https://github.com/apache/hbase/blob/master/hbase-client/src/main/java/org/apache/hadoop/hbase/client/Mutation.java#L791 > https://github.com/apache/hbase/blob/master/hbase-client/src/main/java/org/apache/hadoop/hbase/client/Mutation.java#L795 -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Updated] (HBASE-20710) extra cloneFamily() in Mutation.add(Cell)
[ https://issues.apache.org/jira/browse/HBASE-20710?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] stack updated HBASE-20710: -- Attachment: 2.0623.111354.alloc.svg > extra cloneFamily() in Mutation.add(Cell) > - > > Key: HBASE-20710 > URL: https://issues.apache.org/jira/browse/HBASE-20710 > Project: HBase > Issue Type: Sub-task > Components: regionserver >Affects Versions: 2.0.1 >Reporter: huaxiang sun >Assignee: huaxiang sun >Priority: Minor > Fix For: 2.0.2 > > Attachments: 2.0623.111354.alloc.svg, HBASE-20710-master-v001.patch, > HBASE-20710-master-v002.patch, HBASE-20710-master-v002.patch, > HBASE-20710.master.001.patch, alloc-put-fix.svg, alloc-put-orig.svg > > > The cpu profiling shows that during PE randomWrite testing, about 1 percent > of time is spent in cloneFamily. Reviewing code found that when a cell is DBB > backed ByteBuffKeyValueCell (which is default with Netty Rpc), > cell.getFamilyArray() will call cloneFamily() and there is again a > cloneFamily() in the following line of the code. since this is the critical > write path processing, this needs to be optimized. > https://github.com/apache/hbase/blob/master/hbase-client/src/main/java/org/apache/hadoop/hbase/client/Mutation.java#L791 > https://github.com/apache/hbase/blob/master/hbase-client/src/main/java/org/apache/hadoop/hbase/client/Mutation.java#L795 -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Updated] (HBASE-20710) extra cloneFamily() in Mutation.add(Cell)
[ https://issues.apache.org/jira/browse/HBASE-20710?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] stack updated HBASE-20710: -- Attachment: HBASE-20710.master.001.patch > extra cloneFamily() in Mutation.add(Cell) > - > > Key: HBASE-20710 > URL: https://issues.apache.org/jira/browse/HBASE-20710 > Project: HBase > Issue Type: Sub-task > Components: regionserver >Affects Versions: 2.0.1 >Reporter: huaxiang sun >Assignee: huaxiang sun >Priority: Minor > Fix For: 2.0.2 > > Attachments: HBASE-20710-master-v001.patch, > HBASE-20710-master-v002.patch, HBASE-20710-master-v002.patch, > HBASE-20710.master.001.patch, alloc-put-fix.svg, alloc-put-orig.svg > > > The cpu profiling shows that during PE randomWrite testing, about 1 percent > of time is spent in cloneFamily. Reviewing code found that when a cell is DBB > backed ByteBuffKeyValueCell (which is default with Netty Rpc), > cell.getFamilyArray() will call cloneFamily() and there is again a > cloneFamily() in the following line of the code. since this is the critical > write path processing, this needs to be optimized. > https://github.com/apache/hbase/blob/master/hbase-client/src/main/java/org/apache/hadoop/hbase/client/Mutation.java#L791 > https://github.com/apache/hbase/blob/master/hbase-client/src/main/java/org/apache/hadoop/hbase/client/Mutation.java#L795 -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Updated] (HBASE-20710) extra cloneFamily() in Mutation.add(Cell)
[ https://issues.apache.org/jira/browse/HBASE-20710?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] huaxiang sun updated HBASE-20710: - Attachment: HBASE-20710-master-v002.patch > extra cloneFamily() in Mutation.add(Cell) > - > > Key: HBASE-20710 > URL: https://issues.apache.org/jira/browse/HBASE-20710 > Project: HBase > Issue Type: Sub-task > Components: regionserver >Affects Versions: 2.0.1 >Reporter: huaxiang sun >Assignee: huaxiang sun >Priority: Minor > Fix For: 2.0.2 > > Attachments: HBASE-20710-master-v001.patch, > HBASE-20710-master-v002.patch, HBASE-20710-master-v002.patch, > alloc-put-fix.svg, alloc-put-orig.svg > > > The cpu profiling shows that during PE randomWrite testing, about 1 percent > of time is spent in cloneFamily. Reviewing code found that when a cell is DBB > backed ByteBuffKeyValueCell (which is default with Netty Rpc), > cell.getFamilyArray() will call cloneFamily() and there is again a > cloneFamily() in the following line of the code. since this is the critical > write path processing, this needs to be optimized. > https://github.com/apache/hbase/blob/master/hbase-client/src/main/java/org/apache/hadoop/hbase/client/Mutation.java#L791 > https://github.com/apache/hbase/blob/master/hbase-client/src/main/java/org/apache/hadoop/hbase/client/Mutation.java#L795 -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Updated] (HBASE-20710) extra cloneFamily() in Mutation.add(Cell)
[ https://issues.apache.org/jira/browse/HBASE-20710?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] stack updated HBASE-20710: -- Fix Version/s: (was: 2.0.1) 2.0.2 > extra cloneFamily() in Mutation.add(Cell) > - > > Key: HBASE-20710 > URL: https://issues.apache.org/jira/browse/HBASE-20710 > Project: HBase > Issue Type: Sub-task > Components: regionserver >Affects Versions: 2.0.1 >Reporter: huaxiang sun >Assignee: huaxiang sun >Priority: Minor > Fix For: 2.0.2 > > Attachments: HBASE-20710-master-v001.patch, > HBASE-20710-master-v002.patch, alloc-put-fix.svg, alloc-put-orig.svg > > > The cpu profiling shows that during PE randomWrite testing, about 1 percent > of time is spent in cloneFamily. Reviewing code found that when a cell is DBB > backed ByteBuffKeyValueCell (which is default with Netty Rpc), > cell.getFamilyArray() will call cloneFamily() and there is again a > cloneFamily() in the following line of the code. since this is the critical > write path processing, this needs to be optimized. > https://github.com/apache/hbase/blob/master/hbase-client/src/main/java/org/apache/hadoop/hbase/client/Mutation.java#L791 > https://github.com/apache/hbase/blob/master/hbase-client/src/main/java/org/apache/hadoop/hbase/client/Mutation.java#L795 -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Updated] (HBASE-20710) extra cloneFamily() in Mutation.add(Cell)
[ https://issues.apache.org/jira/browse/HBASE-20710?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] huaxiang sun updated HBASE-20710: - Attachment: alloc-put-orig.svg alloc-put-fix.svg > extra cloneFamily() in Mutation.add(Cell) > - > > Key: HBASE-20710 > URL: https://issues.apache.org/jira/browse/HBASE-20710 > Project: HBase > Issue Type: Sub-task > Components: regionserver >Affects Versions: 2.0.1 >Reporter: huaxiang sun >Assignee: huaxiang sun >Priority: Minor > Fix For: 2.0.1 > > Attachments: HBASE-20710-master-v001.patch, > HBASE-20710-master-v002.patch, alloc-put-fix.svg, alloc-put-orig.svg > > > The cpu profiling shows that during PE randomWrite testing, about 1 percent > of time is spent in cloneFamily. Reviewing code found that when a cell is DBB > backed ByteBuffKeyValueCell (which is default with Netty Rpc), > cell.getFamilyArray() will call cloneFamily() and there is again a > cloneFamily() in the following line of the code. since this is the critical > write path processing, this needs to be optimized. > https://github.com/apache/hbase/blob/master/hbase-client/src/main/java/org/apache/hadoop/hbase/client/Mutation.java#L791 > https://github.com/apache/hbase/blob/master/hbase-client/src/main/java/org/apache/hadoop/hbase/client/Mutation.java#L795 -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Updated] (HBASE-20710) extra cloneFamily() in Mutation.add(Cell)
[ https://issues.apache.org/jira/browse/HBASE-20710?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] huaxiang sun updated HBASE-20710: - Attachment: HBASE-20710-master-v002.patch > extra cloneFamily() in Mutation.add(Cell) > - > > Key: HBASE-20710 > URL: https://issues.apache.org/jira/browse/HBASE-20710 > Project: HBase > Issue Type: Sub-task > Components: regionserver >Affects Versions: 2.0.1 >Reporter: huaxiang sun >Assignee: huaxiang sun >Priority: Minor > Fix For: 2.0.1 > > Attachments: HBASE-20710-master-v001.patch, > HBASE-20710-master-v002.patch > > > The cpu profiling shows that during PE randomWrite testing, about 1 percent > of time is spent in cloneFamily. Reviewing code found that when a cell is DBB > backed ByteBuffKeyValueCell (which is default with Netty Rpc), > cell.getFamilyArray() will call cloneFamily() and there is again a > cloneFamily() in the following line of the code. since this is the critical > write path processing, this needs to be optimized. > https://github.com/apache/hbase/blob/master/hbase-client/src/main/java/org/apache/hadoop/hbase/client/Mutation.java#L791 > https://github.com/apache/hbase/blob/master/hbase-client/src/main/java/org/apache/hadoop/hbase/client/Mutation.java#L795 -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Updated] (HBASE-20710) extra cloneFamily() in Mutation.add(Cell)
[ https://issues.apache.org/jira/browse/HBASE-20710?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] huaxiang sun updated HBASE-20710: - Status: Patch Available (was: Open) I tried to avoid calling cloneFamily() and getFamilyArray() in Muation.add(). The family byte array allocation is limited to 2 allocations even there are more than 2 cells in that family. Run some unittests, it seems ok. Put it to see if it breaks anything. > extra cloneFamily() in Mutation.add(Cell) > - > > Key: HBASE-20710 > URL: https://issues.apache.org/jira/browse/HBASE-20710 > Project: HBase > Issue Type: Sub-task > Components: regionserver >Affects Versions: 2.0.1 >Reporter: huaxiang sun >Assignee: huaxiang sun >Priority: Minor > Fix For: 2.0.1 > > Attachments: HBASE-20710-master-v001.patch > > > The cpu profiling shows that during PE randomWrite testing, about 1 percent > of time is spent in cloneFamily. Reviewing code found that when a cell is DBB > backed ByteBuffKeyValueCell (which is default with Netty Rpc), > cell.getFamilyArray() will call cloneFamily() and there is again a > cloneFamily() in the following line of the code. since this is the critical > write path processing, this needs to be optimized. > https://github.com/apache/hbase/blob/master/hbase-client/src/main/java/org/apache/hadoop/hbase/client/Mutation.java#L791 > https://github.com/apache/hbase/blob/master/hbase-client/src/main/java/org/apache/hadoop/hbase/client/Mutation.java#L795 -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Updated] (HBASE-20710) extra cloneFamily() in Mutation.add(Cell)
[ https://issues.apache.org/jira/browse/HBASE-20710?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] huaxiang sun updated HBASE-20710: - Attachment: HBASE-20710-master-v001.patch > extra cloneFamily() in Mutation.add(Cell) > - > > Key: HBASE-20710 > URL: https://issues.apache.org/jira/browse/HBASE-20710 > Project: HBase > Issue Type: Sub-task > Components: regionserver >Affects Versions: 2.0.1 >Reporter: huaxiang sun >Assignee: huaxiang sun >Priority: Minor > Fix For: 2.0.1 > > Attachments: HBASE-20710-master-v001.patch > > > The cpu profiling shows that during PE randomWrite testing, about 1 percent > of time is spent in cloneFamily. Reviewing code found that when a cell is DBB > backed ByteBuffKeyValueCell (which is default with Netty Rpc), > cell.getFamilyArray() will call cloneFamily() and there is again a > cloneFamily() in the following line of the code. since this is the critical > write path processing, this needs to be optimized. > https://github.com/apache/hbase/blob/master/hbase-client/src/main/java/org/apache/hadoop/hbase/client/Mutation.java#L791 > https://github.com/apache/hbase/blob/master/hbase-client/src/main/java/org/apache/hadoop/hbase/client/Mutation.java#L795 -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Updated] (HBASE-20710) extra cloneFamily() in Mutation.add(Cell)
[ https://issues.apache.org/jira/browse/HBASE-20710?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] stack updated HBASE-20710: -- Fix Version/s: 2.0.1 > extra cloneFamily() in Mutation.add(Cell) > - > > Key: HBASE-20710 > URL: https://issues.apache.org/jira/browse/HBASE-20710 > Project: HBase > Issue Type: Sub-task > Components: regionserver >Affects Versions: 2.0.1 >Reporter: huaxiang sun >Assignee: huaxiang sun >Priority: Minor > Fix For: 2.0.1 > > > The cpu profiling shows that during PE randomWrite testing, about 1 percent > of time is spent in cloneFamily. Reviewing code found that when a cell is DBB > backed ByteBuffKeyValueCell (which is default with Netty Rpc), > cell.getFamilyArray() will call cloneFamily() and there is again a > cloneFamily() in the following line of the code. since this is the critical > write path processing, this needs to be optimized. > https://github.com/apache/hbase/blob/master/hbase-client/src/main/java/org/apache/hadoop/hbase/client/Mutation.java#L791 > https://github.com/apache/hbase/blob/master/hbase-client/src/main/java/org/apache/hadoop/hbase/client/Mutation.java#L795 -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Updated] (HBASE-20710) extra cloneFamily() in Mutation.add(Cell)
[ https://issues.apache.org/jira/browse/HBASE-20710?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] stack updated HBASE-20710: -- Issue Type: Sub-task (was: Improvement) Parent: HBASE-20188 > extra cloneFamily() in Mutation.add(Cell) > - > > Key: HBASE-20710 > URL: https://issues.apache.org/jira/browse/HBASE-20710 > Project: HBase > Issue Type: Sub-task > Components: regionserver >Affects Versions: 2.0.1 >Reporter: huaxiang sun >Assignee: huaxiang sun >Priority: Minor > > The cpu profiling shows that during PE randomWrite testing, about 1 percent > of time is spent in cloneFamily. Reviewing code found that when a cell is DBB > backed ByteBuffKeyValueCell (which is default with Netty Rpc), > cell.getFamilyArray() will call cloneFamily() and there is again a > cloneFamily() in the following line of the code. since this is the critical > write path processing, this needs to be optimized. > https://github.com/apache/hbase/blob/master/hbase-client/src/main/java/org/apache/hadoop/hbase/client/Mutation.java#L791 > https://github.com/apache/hbase/blob/master/hbase-client/src/main/java/org/apache/hadoop/hbase/client/Mutation.java#L795 -- This message was sent by Atlassian JIRA (v7.6.3#76005)
