From: Wido den Hollander <wido@widodh.nl>
To: "Jens Kristian Søgaard" <jens@mermaidconsulting.dk>
Cc: Sage Weil <sage@inktank.com>,
Stefan Priebe <s.priebe@profihost.ag>,
"ceph-devel@vger.kernel.org" <ceph-devel@vger.kernel.org>
Subject: Re: Hit suicide timeout after adding new osd
Date: Wed, 23 Jan 2013 13:26:33 +0100 [thread overview]
Message-ID: <50FFD6F9.1010705@widodh.nl> (raw)
In-Reply-To: <50FFD420.7000604@mermaidconsulting.dk>
On 01/23/2013 01:14 PM, Jens Kristian Søgaard wrote:
> Hi Sage,
>
>> I think the problem now is just that 'osd target transaction size' is
>> too big (default is 300). Recommended 50.. let's see how that goes.
>> Even smaller (20 or 25) would probably be fine.
>
Going through the code and reading that this solved it for Jens, could
this issue be traced back to less powerful CPUs?
I've seen this on Atom and Fusion platforms which both don't excel in
their computing power.
From what I read is that the OSD by default does 300 transactions and
then commits them? If the CPU is to slow to handle all the work timeouts
can occur because it can't do all the transactions inside the set window?
By lowering the number of transactions it sends out a heartbeat more
often thus keeping itself alive.
Correct?
Wido
> I set it to 50, and that seems to have solved all my problems.
>
> After a day or so my cluster got to a HEALTH_OK state again. It has been
> running for a few days now without any crashes!
>
> Thanks for all your help!
>
--
To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
next prev parent reply other threads:[~2013-01-23 12:26 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-01-17 14:35 Hit suicide timeout after adding new osd Jens Kristian Søgaard
2013-01-17 14:47 ` Wido den Hollander
2013-01-17 14:50 ` Stefan Priebe
2013-01-17 15:33 ` Wido den Hollander
2013-01-17 15:37 ` Stefan Priebe
2013-01-17 17:17 ` Sage Weil
2013-01-17 20:32 ` Jens Kristian Søgaard
2013-01-17 22:03 ` Sage Weil
2013-01-18 11:24 ` Jens Kristian Søgaard
2013-01-18 21:28 ` Sage Weil
2013-01-18 21:36 ` Jens Kristian Søgaard
2013-01-18 21:44 ` Sage Weil
2013-01-19 9:25 ` Jens Kristian Søgaard
2013-01-19 16:44 ` Sage Weil
2013-01-19 17:56 ` Jens Kristian Søgaard
2013-01-19 18:19 ` Sage Weil
2013-01-19 18:40 ` Jens Kristian Søgaard
2013-01-19 20:08 ` Sage Weil
2013-01-19 20:29 ` Jens Kristian Søgaard
2013-01-19 22:04 ` Sage Weil
2013-01-21 0:14 ` Sage Weil
2013-01-21 6:59 ` Jens Kristian Søgaard
2013-01-21 7:11 ` Sage Weil
2013-01-23 12:14 ` Jens Kristian Søgaard
2013-01-23 12:26 ` Wido den Hollander [this message]
2013-01-23 12:29 ` Jens Kristian Søgaard
2013-01-23 13:13 ` Sage Weil
2013-01-23 20:59 ` Jens Kristian Søgaard
2013-01-23 22:56 ` Andrey Korolyov
2013-01-24 4:39 ` Sage Weil
2013-01-24 7:44 ` Andrey Korolyov
2013-01-24 18:01 ` Sage Weil
2013-02-17 11:21 ` Andrey Korolyov
2013-02-17 17:52 ` Sage Weil
2013-01-24 4:28 ` Sage Weil
2013-01-24 10:08 ` Jens Kristian Søgaard
2013-01-24 18:06 ` Sage Weil
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=50FFD6F9.1010705@widodh.nl \
--to=wido@widodh.nl \
--cc=ceph-devel@vger.kernel.org \
--cc=jens@mermaidconsulting.dk \
--cc=s.priebe@profihost.ag \
--cc=sage@inktank.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.