From: Jens Axboe <jens.axboe@oracle.com>
To: linux-kernel@vger.kernel.org
Cc: Jens Axboe <jens.axboe@oracle.com>
Subject: [PATCH 1/15] cfq-iosched: improve preemption for cooperating tasks
Date: Tue, 24 Apr 2007 10:15:29 +0200 [thread overview]
Message-ID: <11774025432284-git-send-email-jens.axboe@oracle.com> (raw)
In-Reply-To: <11774025432481-git-send-email-jens.axboe@oracle.com>
When testing the syslet async io approach, I discovered that CFQ
sometimes didn't perform as well as expected. cfq_should_preempt()
needs to better check for cooperating tasks, so fix that by allowing
preemption of an equal priority queue if the recently queued request
is as good a candidate for IO as the one we are currently waiting for.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
block/cfq-iosched.c | 26 ++++++++++++++++++++------
1 files changed, 20 insertions(+), 6 deletions(-)
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 9e37971..a683d00 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -861,15 +861,11 @@ static int cfq_arm_slice_timer(struct cfq_data *cfqd)
static void cfq_dispatch_insert(request_queue_t *q, struct request *rq)
{
- struct cfq_data *cfqd = q->elevator->elevator_data;
struct cfq_queue *cfqq = RQ_CFQQ(rq);
cfq_remove_request(rq);
cfqq->on_dispatch[rq_is_sync(rq)]++;
elv_dispatch_sort(q, rq);
-
- rq = list_entry(q->queue_head.prev, struct request, queuelist);
- cfqd->last_sector = rq->sector + rq->nr_sectors;
}
/*
@@ -1579,6 +1575,7 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
struct request *rq)
{
struct cfq_queue *cfqq = cfqd->active_queue;
+ sector_t dist;
if (cfq_class_idle(new_cfqq))
return 0;
@@ -1588,14 +1585,14 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
if (cfq_class_idle(cfqq))
return 1;
- if (!cfq_cfqq_wait_request(new_cfqq))
- return 0;
+
/*
* if the new request is sync, but the currently running queue is
* not, let the sync request have priority.
*/
if (rq_is_sync(rq) && !cfq_cfqq_sync(cfqq))
return 1;
+
/*
* So both queues are sync. Let the new request get disk time if
* it's a metadata request and the current queue is doing regular IO.
@@ -1603,6 +1600,21 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
if (rq_is_meta(rq) && !cfqq->meta_pending)
return 1;
+ if (!cfqd->active_cic || !cfq_cfqq_wait_request(cfqq))
+ return 0;
+
+ /*
+ * if this request is as-good as one we would expect from the
+ * current cfqq, let it preempt
+ */
+ if (rq->sector > cfqd->last_sector)
+ dist = rq->sector - cfqd->last_sector;
+ else
+ dist = cfqd->last_sector - rq->sector;
+
+ if (dist <= cfqd->active_cic->seek_mean)
+ return 1;
+
return 0;
}
@@ -1719,6 +1731,8 @@ static void cfq_completed_request(request_queue_t *q, struct request *rq)
cfqq->on_dispatch[sync]--;
cfqq->service_last = now;
+ cfqd->last_sector = rq->hard_sector + rq->hard_nr_sectors;
+
if (!cfq_class_idle(cfqq))
cfqd->last_end_request = now;
--
1.5.1.1.190.g74474
next prev parent reply other threads:[~2007-04-24 8:16 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-04-24 8:15 [PATCH 0/15] CFQ IO scheduler patch series Jens Axboe
2007-04-24 8:15 ` Jens Axboe [this message]
2007-04-24 8:15 ` [PATCH 2/15] cfq-iosched: development update Jens Axboe
2007-04-24 8:15 ` [PATCH 3/15] cfq-iosched: minor updates Jens Axboe
2007-04-24 8:15 ` [PATCH 4/15] cfq-iosched: rework the whole round-robin list concept Jens Axboe
2007-04-24 8:15 ` [PATCH 5/15] cfq-iosched: speed up rbtree handling Jens Axboe
2007-04-25 15:59 ` Alan D. Brunelle
2007-04-25 17:15 ` Jens Axboe
2007-04-25 17:50 ` Jens Axboe
2007-04-25 18:08 ` Jens Axboe
2007-04-26 14:28 ` Alan D. Brunelle
2007-04-26 15:46 ` Jens Axboe
2007-04-24 8:15 ` [PATCH 6/15] cfq-iosched: sort RT queues into the rbtree Jens Axboe
2007-04-24 8:15 ` [PATCH 7/15] cfq-iosched: sort IDLE " Jens Axboe
2007-04-24 8:15 ` [PATCH 8/15] cfq-iosched: style cleanups and comments Jens Axboe
2007-04-24 8:15 ` [PATCH 9/15] cfq-iosched: slice offset should take ioprio into account Jens Axboe
2007-04-24 8:15 ` [PATCH 10/15] cfq-iosched: get rid of ->cur_rr and ->cfq_list Jens Axboe
2007-04-24 8:15 ` [PATCH 11/15] cfq-iosched: don't pass unused preemption variable around Jens Axboe
2007-04-24 8:15 ` [PATCH 12/15] cfq-iosched: get rid of ->dispatch_slice Jens Axboe
2007-04-24 8:15 ` [PATCH 13/15] cfq-iosched: never allow an async queue idling Jens Axboe
2007-04-24 8:15 ` [PATCH 14/15] cfq-iosched: improve sync vs async workloads Jens Axboe
2007-04-24 8:15 ` [PATCH 15/15] cfq-iosched: tighten queue request overlap condition Jens Axboe
2007-04-25 14:42 ` [PATCH 0/15] CFQ IO scheduler patch series Alan D. Brunelle
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=11774025432284-git-send-email-jens.axboe@oracle.com \
--to=jens.axboe@oracle.com \
--cc=linux-kernel@vger.kernel.org \
/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®