[jira] [Updated] (HBASE-4714) Don't ship w/ icms enabled by default
[ https://issues.apache.org/jira/browse/HBASE-4714?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] stack updated HBASE-4714: - Fix Version/s: 0.92.0 Assignee: stack Don't ship w/ icms enabled by default - Key: HBASE-4714 URL: https://issues.apache.org/jira/browse/HBASE-4714 Project: HBase Issue Type: Task Reporter: stack Assignee: stack Fix For: 0.92.0 Attachments: icms-v2.txt, icms.txt Incremental CMS (iCMS) was written for a specific use case - 1 or 2 hardware threads where concurrent activity by CMS would look like a STW (if only 1 hardware thread) or a high tax on the cpu cycles (2 hardware threads). It has a higher overhead and also is less efficient in terms of identifying garbage. The latter is because iCMS spreads out the concurrent work so that objects that it has identified as live earlier may actually be dead when the dead objects are swept up. It's worth testing with regular CMS instead of iCMS. From recent hotspot mailing list message. Rare is the case where we run on systems of 1 or 2 hardware threads (other than fellows laptops and there the above likely doesn't matter). -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (HBASE-4714) Don't ship w/ icms enabled by default
[ https://issues.apache.org/jira/browse/HBASE-4714?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] stack updated HBASE-4714: - Attachment: icms-v2.txt Don't ship w/ icms enabled by default - Key: HBASE-4714 URL: https://issues.apache.org/jira/browse/HBASE-4714 Project: HBase Issue Type: Task Reporter: stack Assignee: stack Fix For: 0.92.0 Attachments: icms-v2.txt, icms.txt Incremental CMS (iCMS) was written for a specific use case - 1 or 2 hardware threads where concurrent activity by CMS would look like a STW (if only 1 hardware thread) or a high tax on the cpu cycles (2 hardware threads). It has a higher overhead and also is less efficient in terms of identifying garbage. The latter is because iCMS spreads out the concurrent work so that objects that it has identified as live earlier may actually be dead when the dead objects are swept up. It's worth testing with regular CMS instead of iCMS. From recent hotspot mailing list message. Rare is the case where we run on systems of 1 or 2 hardware threads (other than fellows laptops and there the above likely doesn't matter). -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (HBASE-4714) Don't ship w/ icms enabled by default
[ https://issues.apache.org/jira/browse/HBASE-4714?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] stack updated HBASE-4714: - Status: Patch Available (was: Open) Don't ship w/ icms enabled by default - Key: HBASE-4714 URL: https://issues.apache.org/jira/browse/HBASE-4714 Project: HBase Issue Type: Task Reporter: stack Assignee: stack Fix For: 0.92.0 Attachments: icms-v2.txt, icms.txt Incremental CMS (iCMS) was written for a specific use case - 1 or 2 hardware threads where concurrent activity by CMS would look like a STW (if only 1 hardware thread) or a high tax on the cpu cycles (2 hardware threads). It has a higher overhead and also is less efficient in terms of identifying garbage. The latter is because iCMS spreads out the concurrent work so that objects that it has identified as live earlier may actually be dead when the dead objects are swept up. It's worth testing with regular CMS instead of iCMS. From recent hotspot mailing list message. Rare is the case where we run on systems of 1 or 2 hardware threads (other than fellows laptops and there the above likely doesn't matter). -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (HBASE-4714) Don't ship w/ icms enabled by default
[ https://issues.apache.org/jira/browse/HBASE-4714?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] stack updated HBASE-4714: - Attachment: icms.txt Disable icms and add a bit of doc that newer jvms are a bit better around avoiding fragmentation. Don't ship w/ icms enabled by default - Key: HBASE-4714 URL: https://issues.apache.org/jira/browse/HBASE-4714 Project: HBase Issue Type: Task Reporter: stack Fix For: 0.92.0 Attachments: icms-v2.txt, icms.txt Incremental CMS (iCMS) was written for a specific use case - 1 or 2 hardware threads where concurrent activity by CMS would look like a STW (if only 1 hardware thread) or a high tax on the cpu cycles (2 hardware threads). It has a higher overhead and also is less efficient in terms of identifying garbage. The latter is because iCMS spreads out the concurrent work so that objects that it has identified as live earlier may actually be dead when the dead objects are swept up. It's worth testing with regular CMS instead of iCMS. From recent hotspot mailing list message. Rare is the case where we run on systems of 1 or 2 hardware threads (other than fellows laptops and there the above likely doesn't matter). -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (HBASE-4714) Don't ship w/ icms enabled by default
[ https://issues.apache.org/jira/browse/HBASE-4714?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] stack updated HBASE-4714: - Resolution: Fixed Hadoop Flags: Reviewed Status: Resolved (was: Patch Available) Committed trunk and 0.92 branch. Commit on trunk took two attempts because I committed more than just patch so backed it all out. Thanks for review J-D Don't ship w/ icms enabled by default - Key: HBASE-4714 URL: https://issues.apache.org/jira/browse/HBASE-4714 Project: HBase Issue Type: Task Reporter: stack Assignee: stack Fix For: 0.92.0 Attachments: icms-v2.txt, icms.txt Incremental CMS (iCMS) was written for a specific use case - 1 or 2 hardware threads where concurrent activity by CMS would look like a STW (if only 1 hardware thread) or a high tax on the cpu cycles (2 hardware threads). It has a higher overhead and also is less efficient in terms of identifying garbage. The latter is because iCMS spreads out the concurrent work so that objects that it has identified as live earlier may actually be dead when the dead objects are swept up. It's worth testing with regular CMS instead of iCMS. From recent hotspot mailing list message. Rare is the case where we run on systems of 1 or 2 hardware threads (other than fellows laptops and there the above likely doesn't matter). -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira
