[ 
https://issues.apache.org/jira/browse/HBASE-23634?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17161078#comment-17161078
 ] 

Guanghao Zhang commented on HBASE-23634:
----------------------------------------

{quote}before compaction, large number of small hfiles affect read and write 
performance of region.
{quote}
Only read performance. And "bad performance read" is better than "cannot read"?
{quote}hfile needs 3 NN RPCs to bulkload during 
openRegion(validate态rename态createReader)
{quote}
For this, I thought the "validate" step may not need? For bulkload, it need to 
check the hfile meet the region start/end key. But for this, failover is a 
internal system operation, it doesn't need the validate step.

And for the RPCs, wal replay need same number "createReader" rpcs for the 
recovered edits.

> Enable "Split WAL to HFile" by default
> --------------------------------------
>
>                 Key: HBASE-23634
>                 URL: https://issues.apache.org/jira/browse/HBASE-23634
>             Project: HBase
>          Issue Type: Task
>    Affects Versions: 3.0.0-alpha-1, 2.3.0
>            Reporter: Guanghao Zhang
>            Priority: Blocker
>             Fix For: 3.0.0-alpha-1, 2.4.0
>
>




--
This message was sent by Atlassian Jira
(v8.3.4#803005)

Reply via email to