From: Blair Bethwaite <blair.bethwaite@gmail.com>
To: Wade Holler <wade.holler@gmail.com>
Cc: Ceph Development <ceph-devel@vger.kernel.org>,
"ceph-users@lists.ceph.com" <ceph-users@lists.ceph.com>
Subject: Re: Dramatic performance drop at certain number of objects in pool
Date: Thu, 16 Jun 2016 22:48:05 +1000 [thread overview]
Message-ID: <CA+z5Dsz=e1N9RxRoF5Wao8Dogf_S1UstNZaCJ=oj-efj83HBig@mail.gmail.com> (raw)
In-Reply-To: <CA+e22ScW-YrDE0mPABSuiDbDpKL=gYZXv6t2hK8RJxYuMaVLHg@mail.gmail.com>
Hi Wade,
What IO are you seeing on the OSD devices when this happens (see e.g.
iostat), are there short periods of high read IOPS where (almost) no
writes occur? What does your memory usage look like (including slab)?
Cheers,
On 16 June 2016 at 22:14, Wade Holler <wade.holler@gmail.com> wrote:
> Hi All,
>
> I have a repeatable condition when the object count in a pool gets to
> 320-330 million the object write time dramatically and almost
> instantly increases as much as 10X, exhibited by fs_apply_latency
> going from 10ms to 100s of ms.
>
> Can someone point me in a direction / have an explanation ?
>
> I can add a new pool and it performs normally.
>
> Config is generally
> 3 Nodes 24 physical core each, 768GB Ram each, 16 OSD / node , all SSD
> with NVME for journals. Centos 7.2, XFS
>
> Jewell is the release; inserting objects with librados via some Python
> test code.
>
> Best Regards
> Wade
> --
> 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
--
Cheers,
~Blairo
next prev parent reply other threads:[~2016-06-16 12:48 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-06-16 12:14 Dramatic performance drop at certain number of objects in pool Wade Holler
2016-06-16 12:48 ` Blair Bethwaite [this message]
[not found] ` <CA+z5Dsz=e1N9RxRoF5Wao8Dogf_S1UstNZaCJ=oj-efj83HBig-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2016-06-16 14:20 ` Dramatic performance drop at certain number ofobjects " Mykola
2016-06-16 14:30 ` Dramatic performance drop at certain number of objects " Wade Holler
2016-06-16 14:32 ` Wade Holler
2016-06-16 13:38 ` Wido den Hollander
2016-06-16 14:47 ` Wade Holler
2016-06-16 16:08 ` Wade Holler
2016-06-17 8:49 ` Wido den Hollander
2016-06-19 23:21 ` Blair Bethwaite
[not found] ` <CA+z5DszqHuevkAF3W01R=7AAeqVcyuHZTX0+bAvThgihvOjwuA-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2016-06-20 0:52 ` Christian Balzer
2016-06-20 6:32 ` Blair Bethwaite
[not found] ` <CA+z5Dsy4tbyiL71C8CQCTQ66tY1=9thSWdNA4BSn6=tNfGUE6w-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2016-06-20 18:48 ` Wade Holler
[not found] ` <CA+e22Sc3iY5Lvp4oGwJ_wwpJsOJsWdB1thaHWEAuYP=bbGHAeg-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2016-06-20 20:47 ` Warren Wang - ISD
[not found] ` <D38DCB57.131AE%warren.wang-dFwxUrggiyBBDgjK7y7TUQ@public.gmane.org>
2016-06-20 22:58 ` Christian Balzer
2016-06-23 1:26 ` [ceph-users] " Wade Holler
[not found] ` <CA+e22SdrwRHmAD=67MpVtUXVyCOmidcoUXrANZVeDJc2tcJfnQ-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2016-06-23 1:33 ` Blair Bethwaite
2016-06-23 1:41 ` [ceph-users] " Wade Holler
2016-06-23 2:01 ` Blair Bethwaite
2016-06-23 2:28 ` Christian Balzer
2016-06-23 2:36 ` Blair Bethwaite
2016-06-23 2:31 ` Wade Holler
[not found] ` <CA+e22SfaiBUQ9Wanay6_oji9t7131o67B2oDtaEW_zXwqCJfbQ-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2016-06-23 22:09 ` Warren Wang - ISD
[not found] ` <D391D1A4.145D6%warren.wang-dFwxUrggiyBBDgjK7y7TUQ@public.gmane.org>
2016-06-23 22:24 ` Somnath Roy
[not found] ` <BL2PR02MB2115BD5C173011A0CB92F964F42D0-TNqo25UYn65rzea/mugEKanrV9Ap65cLvxpqHgZTriW3zl9H0oFU5g@public.gmane.org>
2016-06-24 0:08 ` Christian Balzer
[not found] ` <20160624090806.1246b1ff-9yhXNL7Kh0lSCLKNlHTxZM8NsWr+9BEh@public.gmane.org>
2016-06-24 0:09 ` Somnath Roy
2016-06-24 14:23 ` [ceph-users] " Wade Holler
[not found] ` <CA+e22SdmGJVzJX9+63T41UGsfFcxs9R=xZqniQyTgu-yG=h0cA-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2016-06-24 16:24 ` Warren Wang - ISD
[not found] ` <D392D6EB.146C6%warren.wang-dFwxUrggiyBBDgjK7y7TUQ@public.gmane.org>
2016-06-24 19:45 ` Wade Holler
2016-06-25 3:07 ` [ceph-users] " Christian Balzer
[not found] ` <CAFMfnwoqbr+_c913oyxpvzHNS+NPdXX17dMdXoC1ZiuZM1GzPw@mail.gmail.com>
[not found] ` <CAFMfnwoqbr+_c913oyxpvzHNS+NPdXX17dMdXoC1ZiuZM1GzPw-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2016-06-27 8:12 ` Blair Bethwaite
2016-06-23 2:37 ` [ceph-users] " Christian Balzer
[not found] ` <20160623113717.446a1f9d-9yhXNL7Kh0lSCLKNlHTxZM8NsWr+9BEh@public.gmane.org>
2016-06-23 2:55 ` Blair Bethwaite
[not found] ` <CA+z5DszcLqV32NnWeuu+WsRZoZwM493Jfy7WcSpVtaDyArwFAQ-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2016-06-23 3:38 ` Christian Balzer
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='CA+z5Dsz=e1N9RxRoF5Wao8Dogf_S1UstNZaCJ=oj-efj83HBig@mail.gmail.com' \
--to=blair.bethwaite@gmail.com \
--cc=ceph-devel@vger.kernel.org \
--cc=ceph-users@lists.ceph.com \
--cc=wade.holler@gmail.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.