From: Vivek Goyal <vgoyal@redhat.com>
To: Shaohua Li <shaohua.li@intel.com>
Cc: lkml <linux-kernel@vger.kernel.org>,
jaxboe@fusionio.com, czoccolo@gmail.com
Subject: Re: [patch]cfq-iosched: schedule dispatch for noidle queue
Date: Mon, 20 Sep 2010 10:02:42 -0400 [thread overview]
Message-ID: <20100920140242.GD6138@redhat.com> (raw)
In-Reply-To: <1284972817.6598.19.camel@sli10-conroe.sh.intel.com>
On Mon, Sep 20, 2010 at 04:53:37PM +0800, Shaohua Li wrote:
> A queue is idle at cfq_dispatch_requests(), but it gets noidle later for
> different reasons. Unless other task explictly does unplug or all requests
> are drained, we will not deliever requests to the disk even cfq_arm_slice_timer
> doesn't make the queue idle. For example, cfq_should_idle() returns true
> because of service_tree->count == 1, and then other queues are added.
> Note, I didn't see obvious performance impacts so far with the patch, but
> just thought this could be a problem.
>
Shaohua Li,
What are those reasons when an idling queue becomes a non idle one
(without getting a new request in the queue)?
Vivek
> Signed-off-by: Shaohua Li <shaohua.li@intel.com>
>
> ---
> block/cfq-iosched.c | 23 ++++++++++++++++++++++-
> 1 file changed, 22 insertions(+), 1 deletion(-)
>
> Index: linux-2.6/block/cfq-iosched.c
> ===================================================================
> --- linux-2.6.orig/block/cfq-iosched.c 2010-09-21 00:20:46.000000000 +0800
> +++ linux-2.6/block/cfq-iosched.c 2010-09-21 00:22:58.000000000 +0800
> @@ -3256,6 +3256,10 @@
> if (cfq_class_rt(new_cfqq) && !cfq_class_rt(cfqq))
> return true;
>
> + /* An idle queue should not be idle now for different reasons */
> + if (RB_EMPTY_ROOT(&cfqq->sort_list) && !cfq_should_idle(cfqd, cfqq))
> + return true;
> +
> if (!cfqd->active_cic || !cfq_cfqq_wait_request(cfqq))
> return false;
>
> @@ -3509,8 +3513,25 @@
> }
> }
>
> - if (!cfqd->rq_in_driver)
> + if (!cfqd->rq_in_driver) {
> + cfq_schedule_dispatch(cfqd);
> + return;
> + }
> + /*
> + * A queue is idle at cfq_dispatch_requests(), but it gets noidle later
> + * for different reasons. We schedule a dispatch if the queue has no
> + * requests, otherwise the disk is actually in idle till all requests
> + * are finished even cfq_arm_slice_timer doesn't make the queue idle
> + * */
> + cfqq = cfqd->active_queue;
> + if (!cfqq)
> + return;
> +
> + if (RB_EMPTY_ROOT(&cfqq->sort_list) && !cfq_should_idle(cfqd, cfqq) &&
> + (!cfqd->cfq_group_idle || cfqq->cfqg->nr_cfqq > 1)) {
> + cfq_del_timer(cfqd, cfqq);
> cfq_schedule_dispatch(cfqd);
> + }
> }
>
> /*
>
next prev parent reply other threads:[~2010-09-20 14:02 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-09-20 8:53 Shaohua Li
2010-09-20 14:02 ` Vivek Goyal [this message]
2010-09-20 23:29 ` Shaohua Li
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=20100920140242.GD6138@redhat.com \
--to=vgoyal@redhat.com \
--cc=czoccolo@gmail.com \
--cc=jaxboe@fusionio.com \
--cc=linux-kernel@vger.kernel.org \
--cc=shaohua.li@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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
Powered by JetHome