[ https://issues.apache.org/jira/browse/HBASE-9467?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Michael Stack updated HBASE-9467: --------------------------------- Comment: was deleted (was: *Mark L Latham* 0. [https://robertgladden.gitbook.io/robert-gladden-statement/] 1. [https://robertgladden.gitbook.io/personal-statement/] 2. [https://robertgladden.gitbook.io/my-statement/] 3. [https://robertgladden.gitbook.io/fashionable-black-platform-bed/] 4. [https://robertgladden.gitbook.io/casshina-platform-bed/] 5. [https://robertgladden.gitbook.io/nyx-bed-frame/] 6. [https://robertgladden.gitbook.io/poliform-bed-frame/] 7. [https://www.leetchi.com/c/living-and-platform-bed] 8. [https://www.leetchi.com/c/no-head-if-you-choose-a-bed] 9. [https://www.leetchi.com/c/disadvantages-of-headless-beds] 10. [https://www.leetchi.com/c/choose-a-bed-without-a-headboard] 11. [https://note.com/marklatham/n/n27c1074ab519] 12. [https://note.com/marklatham/n/n60e3bfbd4a6e] 13. [https://note.com/marklatham/n/n5786d7fa4da5] 14. [https://note.com/marklatham/n/n1fd28ac31cb7] 15. [https://note.com/marklatham/n/nb936c8ab5b56] 16. [https://note.com/marklatham/n/n81e0a513af2e] 17. [https://note.com/marklatham/n/n75366750e7b5]) > write can be totally blocked temporarily by a write-heavy region > ---------------------------------------------------------------- > > Key: HBASE-9467 > URL: https://issues.apache.org/jira/browse/HBASE-9467 > Project: HBase > Issue Type: Improvement > Reporter: Honghua Feng > Assignee: Honghua Feng > Priority: Major > Fix For: 0.98.0, 0.96.0 > > Attachments: HBASE-9467-trunk-v0.patch, HBASE-9467-trunk-v1.patch, > HBASE-9467-trunk-v1.patch, HBASE-9467-trunk-v1.patch > > > Write to a region can be blocked temporarily if the memstore of that region > reaches the threshold(hbase.hregion.memstore.block.multiplier * > hbase.hregion.flush.size) until the memstore of that region is flushed. > For a write-heavy region, if its write requests saturates all the handler > threads of that RS when write blocking for that region occurs, requests of > other regions/tables to that RS also can't be served due to no available > handler threads...until the pending writes of that write-heavy region are > served after the flush is done. Hence during this time period, from the RS > perspective it can't serve any request from any table/region just due to a > single write-heavy region. > This sounds not very reasonable, right? Maybe write requests from a region > can only be served by a sub-set of the handler threads, and then write > blocking of any single region can't lead to the scenario mentioned above? > Comment? -- This message was sent by Atlassian Jira (v8.3.4#803005)