You are viewing a plain text version of this content. The canonical link for it is here.

Posted to dev@hbase.apache.org by Andrew Purtell <ap...@apache.org> on 2010/06/25 22:17:19 UTC

Re: [jira] Resolved: (HBASE-2774) Spin in ReadWriteConsistencyControl eating CPU (load > 40) and no progress running YCSB on clean cluster startup

Thanks.
I may backport this anyway to have it waiting just in case.
  - Andy

--- On Thu, 6/24/10, Stack <st...@duboce.net> wrote:

From: Stack <st...@duboce.net>
Subject: Re: [jira] Resolved: (HBASE-2774) Spin in ReadWriteConsistencyControl  eating CPU (load > 40) and no progress running YCSB on clean cluster startup
To: dev@hbase.apache.org, apurtell@apache.org
Date: Thursday, June 24, 2010, 8:03 AM

On Wed, Jun 23, 2010 at 10:59 PM, Andrew Purtell <ap...@apache.org> wrote:
> RWCC is in 0.20 branch also.
>
> Something about the 0.20 code base make this not an issue there?
>

I tried to repro the RWCC issue I saw on TRUNK over on 0.20.5RC5 but
couldn't.  The multiput is missing from 0.20.  That might be helping
bring it on.  We could be burning CPU in 0.20 unnecessarily, but I
didn't see it.  I could apply the patch for 0.20.6 but would rather
have a citing of the "phenomenon" -- a spike in server load, java
process using thousands of percent of CPU -- before I do.

St.Ack