hbase-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Dave Revell <d...@urbanairship.com>
Subject Re: Occasional regionserver crashes following socket errors writing to HDFS
Date Fri, 25 May 2012 19:52:08 GMT
Have you verified that your nodes are not swapping? This has caused serious
issues for many people, including me.

Swapping can occur even if you have lots of available memory, for
complicated reasons.


On Thu, May 24, 2012 at 4:39 PM, Stack <stack@duboce.net> wrote:

> On Thu, May 24, 2012 at 4:15 AM, Eran Kutner <eran@gigya.com> wrote:
> > Any idea why it would not respond in 20 seconds? Seems like quite a lot
> of
> > time.
> The only explaination I have is long GC.  If you are not having these,
> I'm not sure what it is.  Pastebin log and .out from around a zk
> timeout.  We might see something.
> St.Ack

  • Unnamed multipart/alternative (inline, None, 0 bytes)
View raw message