[ https://issues.apache.org/jira/browse/HBASE-12912?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Andrew Purtell updated HBASE-12912: ----------------------------------- Assignee: (was: Andrew Purtell) > Cache Configuration used during scanner creation > ------------------------------------------------ > > Key: HBASE-12912 > URL: https://issues.apache.org/jira/browse/HBASE-12912 > Project: HBase > Issue Type: Sub-task > Reporter: John Leach > Attachments: StoreScannerStall.tiff > > Original Estimate: 1h > Remaining Estimate: 1h > > There is a clear CPU drain and iterator creation when creating store scanners > under high load. Splice was running a TPCC test of our database and we are > seeing object creation and CPU waste on the boolean check.... > Code Snippet... > if (store != null && ((HStore)store).getHRegion() != null > && store.getStorefilesCount() > 1) { > RegionServerServices rsService = > ((HStore)store).getHRegion().getRegionServerServices(); > if (rsService == null || !rsService.getConfiguration().getBoolean( > STORESCANNER_PARALLEL_SEEK_ENABLE, false)) return; > isParallelSeekEnabled = true; > executor = rsService.getExecutorService(); > } > Will attach profile... -- This message was sent by Atlassian JIRA (v6.3.4#6332)