[HBASE-1892] [performance] make hbase splits run faster - ASF JIRA

XML

Word

Printable

JSON

Hadoop Flags:

Reviewed
Release Note:

Hide
On region close, this change makes it so we don't wait on compaction to complete with the close-region flag in place -- i.e. region is offline while we wait on the compaction close -- and secondly, if the region memstores are over a configurable limit, before closing, we'll run a "pre-flush" to get the bulk of the memory flushed before we put the close flag up.

Show
On region close, this change makes it so we don't wait on compaction to complete with the close-region flag in place -- i.e. region is offline while we wait on the compaction close -- and secondly, if the region memstores are over a configurable limit, before closing, we'll run a "pre-flush" to get the bulk of the memory flushed before we put the close flag up.

hbase-1506 tried and failed making splits faster in 0.20 context. This issue is about doing it in 0.21 where we'll have to tools to do.

blocks

HBASE-354 [hbase] Make region splits faster

HBASE-1506 [performance] Make splits faster

incorporates

HBASE-2375 Revisit compaction configuration parameters

is related to

HBASE-1506 [performance] Make splits faster

relates to

HBASE-2510 [performance] make hbase splits run even faster still