From: Stefan Priebe - Profihost AG <s.priebe@profihost.ag>
To: Dietmar Maurer <dietmar@proxmox.com>
Cc: Alexandre DERUMIER <aderumier@odiso.com>,
Marcus Sorensen <shadowsor@gmail.com>,
Sage Weil <sage@inktank.com>,
ceph-devel <ceph-devel@vger.kernel.org>
Subject: Re: slow fio random read benchmark, need help
Date: Thu, 01 Nov 2012 09:08:03 +0100 [thread overview]
Message-ID: <50922DE3.9000903@profihost.ag> (raw)
In-Reply-To: <24E144B8C0207547AD09C467A8259F7557707A07@lisa.maurer-it.com>
Am 01.11.2012 08:38, schrieb Dietmar Maurer:
> I do not really understand that network latency argument.
> If one can get 40K iops with iSCSI, why can't I get the same with rados/ceph?
> Note: network latency is the same in both cases
> What do I miss?
Good question. Also i've seen 20k iops on ceph with 10GBE but i'm able
to get 100.000 iops via iSCSI.
Stefan
next prev parent reply other threads:[~2012-11-01 8:08 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-10-31 1:41 [PATCH 0/6] rbd: version 2 parent probing Alex Elder
2012-10-31 1:49 ` [PATCH 1/6] rbd: skip getting image id if known Alex Elder
2012-10-31 21:05 ` Josh Durgin
2012-10-31 1:49 ` [PATCH 2/6] rbd: allow null image name Alex Elder
2012-10-31 21:07 ` Josh Durgin
2012-10-31 1:49 ` [PATCH 3/6] rbd: get parent spec for version 2 images Alex Elder
2012-11-01 1:33 ` Josh Durgin
2012-10-31 1:49 ` [PATCH 4/6] libceph: define ceph_pg_pool_name_by_id() Alex Elder
2012-11-01 1:34 ` Josh Durgin
2012-10-31 1:49 ` [PATCH 5/6] rbd: get additional info in parent spec Alex Elder
2012-10-31 14:11 ` Alex Elder
2012-11-01 1:49 ` Josh Durgin
2012-11-01 12:18 ` Alex Elder
2012-10-31 1:50 ` [PATCH 6/6] rbd: probe the parent of an image if present Alex Elder
2012-10-31 11:59 ` slow fio random read benchmark, need help Alexandre DERUMIER
2012-10-31 15:57 ` Sage Weil
2012-10-31 16:29 ` Alexandre DERUMIER
2012-10-31 16:50 ` Alexandre DERUMIER
2012-10-31 17:08 ` Marcus Sorensen
2012-10-31 17:27 ` Alexandre DERUMIER
2012-10-31 17:38 ` Marcus Sorensen
2012-10-31 18:56 ` Alexandre DERUMIER
2012-10-31 19:50 ` Marcus Sorensen
2012-11-01 5:11 ` Alexandre DERUMIER
2012-11-01 5:41 ` Stefan Priebe - Profihost AG
2012-10-31 20:22 ` Josh Durgin
2012-11-01 7:38 ` Dietmar Maurer
2012-11-01 8:08 ` Stefan Priebe - Profihost AG [this message]
2012-11-01 10:40 ` Gregory Farnum
2012-11-01 10:54 ` Stefan Priebe - Profihost AG
2012-11-02 9:38 ` Alexandre DERUMIER
2012-11-03 10:01 ` slow fio random read benchmark: last librbd git : 20000iops ! Alexandre DERUMIER
2012-11-03 12:09 ` Alexandre DERUMIER
2012-11-01 15:46 ` slow fio random read benchmark, need help Marcus Sorensen
2012-11-01 16:28 ` Marcus Sorensen
2012-11-01 17:00 ` Dietmar Maurer
2012-11-03 17:09 ` Gregory Farnum
2012-11-04 14:54 ` Alexandre DERUMIER
2012-11-01 2:07 ` [PATCH 6/6] rbd: probe the parent of an image if present Josh Durgin
2012-11-01 12:26 ` Alex Elder
[not found] <CAMiztYLY364EXVQu6d6+He-FXd_AsDOqxkTO_DzKk24iJjwTcQ@mail.gmail.com>
2012-10-31 17:22 ` slow fio random read benchmark, need help Alexandre DERUMIER
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=50922DE3.9000903@profihost.ag \
--to=s.priebe@profihost.ag \
--cc=aderumier@odiso.com \
--cc=ceph-devel@vger.kernel.org \
--cc=dietmar@proxmox.com \
--cc=sage@inktank.com \
--cc=shadowsor@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.