From: Christoph Hellwig <hch@infradead.org>
To: Milosz Tanski <milosz@adfin.com>
Cc: Dong Yuan <yuandong1222@gmail.com>,
Haomai Wang <haomaiwang@gmail.com>, Sage Weil <sweil@redhat.com>,
"ceph-devel@vger.kernel.org" <ceph-devel@vger.kernel.org>,
Somnath Roy <Somnath.Roy@sandisk.com>,
Allen Samuels <Allen.Samuels@sandisk.com>,
Kasper Dieter <dieter.kasper@ts.fujitsu.com>,
PVonStamwitz@us.fujitsu.com, "Shu, Xinxin" <xinxin.shu@intel.com>,
Stefan Priebe - Profihost AG <s.priebe@profihost.ag>,
xiaoxi.chen@intel.com, "Wang, Zhiqiang" <zhiqiang.wang@intel.com>,
jianpeng.ma@intel.com, gdror@mellanox.com, vuhuong@mellanox.com,
Mark Nelson <mark.nelson@inktank.com>
Subject: Re: Weekly performance meeting
Date: Fri, 26 Sep 2014 06:02:39 -0700 [thread overview]
Message-ID: <20140926130239.GA4577@infradead.org> (raw)
In-Reply-To: <CANP1eJGTx6vwBgnKZjHmwwwDbYOTs-Q6sUjYAt7ei1YqsDdeaQ@mail.gmail.com>
On Fri, Sep 26, 2014 at 08:58:56AM -0400, Milosz Tanski wrote:
> First, I have recently submitted a series of patches to kernel to add
> a new preadv2 syscall that lets you do a "fast read" out of the page
> cache the point being that you can skip the whole disk IO queue in
> user space in the cases it's already cached (thus reducing the
> latency). Obviously this doesn't do much for writes (yet, Christoph
> Heldwig is working on that). Samba expressed an interest using these
> new syscalls as well.
We could also implement it for writes, but if would be a bit more
complicated. If there is a compelling use case it might be worth
exploring.
next prev parent reply other threads:[~2014-09-26 13:02 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-09-25 18:27 Weekly performance meeting Sage Weil
2014-09-25 19:03 ` Matt W. Benjamin
2014-09-25 21:15 ` Vu Pham
2014-09-26 6:42 ` Dror Goldenberg
2014-09-26 1:50 ` Paul Von-Stamwitz
2014-09-26 2:27 ` Haomai Wang
2014-09-26 2:45 ` Haomai Wang
2014-09-26 6:30 ` Dong Yuan
2014-09-26 6:40 ` Somnath Roy
2014-09-26 7:20 ` Dong Yuan
2014-09-26 12:58 ` Milosz Tanski
2014-09-26 13:02 ` Christoph Hellwig [this message]
2014-09-26 15:37 ` Sage Weil
2014-09-26 15:57 ` Mark Nelson
2014-09-26 2:47 ` Guang Yang
2014-09-26 13:12 ` Mark Nelson
2014-09-27 3:05 ` Guang Yang
2014-09-26 6:40 ` Zhang, Jian
2014-09-26 7:25 ` Loic Dachary
2014-09-26 8:37 ` Zhang, Jian
2014-09-26 8:56 ` Loic Dachary
[not found] ` <20140925192728.GA22139@oder.mch.fsc.net>
2014-09-25 19:30 ` Mark Nelson
2014-09-25 19:31 ` Mark Nelson
2014-09-25 19:41 ` Sage Weil
2014-09-25 20:20 ` Somnath Roy
2014-10-01 9:30 ` Andreas Bluemle
[not found] <549524118.380.1411702754627.JavaMail.root@thunderbeast.private.linuxbox.com>
2014-09-26 3:39 ` Matt W. Benjamin
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=20140926130239.GA4577@infradead.org \
--to=hch@infradead.org \
--cc=Allen.Samuels@sandisk.com \
--cc=PVonStamwitz@us.fujitsu.com \
--cc=Somnath.Roy@sandisk.com \
--cc=ceph-devel@vger.kernel.org \
--cc=dieter.kasper@ts.fujitsu.com \
--cc=gdror@mellanox.com \
--cc=haomaiwang@gmail.com \
--cc=jianpeng.ma@intel.com \
--cc=mark.nelson@inktank.com \
--cc=milosz@adfin.com \
--cc=s.priebe@profihost.ag \
--cc=sweil@redhat.com \
--cc=vuhuong@mellanox.com \
--cc=xiaoxi.chen@intel.com \
--cc=xinxin.shu@intel.com \
--cc=yuandong1222@gmail.com \
--cc=zhiqiang.wang@intel.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.