[ https://issues.apache.org/jira/browse/HBASE-13876?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Abhilash updated HBASE-13876: ----------------------------- Description: I am trying to improve the performance of DefaultHeapMemoryTuner by introducing some more checks. The current checks under which the DefaultHeapMemoryTuner works are very rare so I am trying to weaken these checks to improve its performance. Check current memstore size and current block cache size. If we are using less than 50% of currently available block cache size we say block cache is sufficient and same for memstore. This check will be very effective when server is either load heavy or write heavy. Earlier version just waited to for number of evictions / number of flushes to be zero which is very rare to happen. Otherwise based on percent change in number of cache misses and number of flushes we increase / decrease memory provided for caching / memstore. After doing so, on next call of HeapMemoryTuner we verify that last change has indeed decreased number of evictions / flush ( combined). I am doing this analysis by comparing percent change (which is basically nothing but normalized of the derivative) of number of evictions and number of flushes in last two periods. The main motive for doing this was that if we have random reads then even after increasing block cache we wont be able to decrease number of cache misses and eventually we will not waste memory on block caches. was: I am trying to improve the performance of DefaultHeapMemoryTuner by introducing some more checks. The current checks under which the DefaultHeapMemoryTuner works are very rare so I am trying to weaken these checks to improve its performance. Check current memstore size and current block cache size. If we are using less than 50% of currently available block cache size we say block cache is sufficient and same for memstore. This check will be very effective when cluster is load heavy or write heavy. Earlier version just waited to for number of evictions / number of flushes to be zero which is very rare to happen. Otherwise based on percent change in number of cache misses and number of flushes we increase / decrease memory provided for caching / memstore. After doing so, on next call of HeapMemoryTuner we verify that last change has indeed decreased number of evictions / flush ( combined). I am doing this analysis by comparing percent change (which is basically nothing but normalized of the derivative) of number of evictions and number of flushes in last two periods. The main motive for doing this was that if we have random reads then even after increasing block cache we wont be able to decrease number of cache misses and eventually we will not waste memory on block caches. > Improving performance of HeapMemoryManager > ------------------------------------------ > > Key: HBASE-13876 > URL: https://issues.apache.org/jira/browse/HBASE-13876 > Project: HBase > Issue Type: Improvement > Components: hbase, regionserver > Affects Versions: 2.0.0, 1.0.1, 1.1.0, 1.1.1 > Reporter: Abhilash > Assignee: Abhilash > Priority: Minor > Attachments: HBASE-13876.patch > > > I am trying to improve the performance of DefaultHeapMemoryTuner by > introducing some more checks. The current checks under which the > DefaultHeapMemoryTuner works are very rare so I am trying to weaken these > checks to improve its performance. > Check current memstore size and current block cache size. If we are using > less than 50% of currently available block cache size we say block cache is > sufficient and same for memstore. This check will be very effective when > server is either load heavy or write heavy. Earlier version just waited to > for number of evictions / number of flushes to be zero which is very rare to > happen. > Otherwise based on percent change in number of cache misses and number of > flushes we increase / decrease memory provided for caching / memstore. After > doing so, on next call of HeapMemoryTuner we verify that last change has > indeed decreased number of evictions / flush ( combined). I am doing this > analysis by comparing percent change (which is basically nothing but > normalized of the derivative) of number of evictions and number of flushes in > last two periods. The main motive for doing this was that if we have random > reads then even after increasing block cache we wont be able to decrease > number of cache misses and eventually we will not waste memory on block > caches. > -- This message was sent by Atlassian JIRA (v6.3.4#6332)