From: Divyesh Shah <dpshah@google.com>
To: Vivek Goyal <vgoyal@redhat.com>
Cc: Jeff Moyer <jmoyer@redhat.com>,
linux-kernel@vger.kernel.org, axboe@kernel.dk, nauman@google.com,
guijianfeng@cn.fujitsu.com, czoccolo@gmail.com
Subject: Re: [PATCH 1/3] cfq-iosched: Improve time slice charging logic
Date: Mon, 19 Jul 2010 13:32:24 -0700 [thread overview]
Message-ID: <AANLkTikqd3VzLSkJfGoN0s29NzhkqJSYSPEEOS2s0TOn@mail.gmail.com> (raw)
In-Reply-To: <20100719185828.GB32503@redhat.com>
On Mon, Jul 19, 2010 at 11:58 AM, Vivek Goyal <vgoyal@redhat.com> wrote:
> Yes it is mixed now for default CFQ case. Whereever we don't have the
> capability to determine the slice_used, we charge IOPS.
>
> For slice_idle=0 case, we should charge IOPS almost all the time. Though
> if there is a workload where single cfqq can keep the request queue
> saturated, then current code will charge in terms of time.
>
> I agree that this is little confusing. May be in case of slice_idle=0
> we can always charge in terms of IOPS.
I agree with Jeff that this is very confusing. Also there are
absolutely no bets that one job may end up getting charged in IOPs for
this behavior while other jobs continue getting charged in timefor
their IOs. Depending on the speed of the disk, this could be a huge
advantage or disadvantage for the cgroup being charged in IOPs.
It should be black or white, time or IOPs and also very clearly called
out not just in code comments but in the Documentation too.
next prev parent reply other threads:[~2010-07-19 20:32 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-07-19 17:20 [RFC PATCH] cfq-iosched: Implement group idle V2 Vivek Goyal
2010-07-19 17:20 ` [PATCH 1/3] cfq-iosched: Improve time slice charging logic Vivek Goyal
2010-07-19 18:47 ` Jeff Moyer
2010-07-19 18:58 ` Vivek Goyal
2010-07-19 20:32 ` Divyesh Shah [this message]
2010-07-19 20:44 ` Vivek Goyal
2010-07-19 21:19 ` Corrado Zoccolo
2010-07-19 22:05 ` Vivek Goyal
2010-07-19 17:20 ` [PATCH 2/3] cfq-iosched: Implement a new tunable group_idle Vivek Goyal
2010-07-19 18:58 ` Jeff Moyer
2010-07-19 20:20 ` Vivek Goyal
2010-07-19 17:20 ` [PATCH 3/3] cfq-iosched: Print per slice sectors dispatched in blktrace Vivek Goyal
2010-07-19 18:59 ` Jeff Moyer
2010-07-19 22:16 ` Divyesh Shah
-- strict thread matches above, loose matches on Subject: below --
2010-07-19 17:14 [RFC PATCH] cfq-iosched: Implement group idle V2 Vivek Goyal
2010-07-19 17:14 ` [PATCH 1/3] cfq-iosched: Improve time slice charging logic Vivek Goyal
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=AANLkTikqd3VzLSkJfGoN0s29NzhkqJSYSPEEOS2s0TOn@mail.gmail.com \
--to=dpshah@google.com \
--cc=axboe@kernel.dk \
--cc=czoccolo@gmail.com \
--cc=guijianfeng@cn.fujitsu.com \
--cc=jmoyer@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=nauman@google.com \
--cc=vgoyal@redhat.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®