linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Vivek Goyal <vgoyal@redhat.com>
To: Tejun Heo <tj@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>, lkml <linux-kernel@vger.kernel.org>,
	Li Zefan <lizefan@huawei.com>,
	containers@lists.linux-foundation.org,
	Cgroups <cgroups@vger.kernel.org>
Subject: Re: [PATCHSET] blk-throttle: implement proper hierarchy support
Date: Fri, 3 May 2013 17:05:13 -0400	[thread overview]
Message-ID: <20130503210513.GE6062@redhat.com> (raw)
In-Reply-To: <20130503191418.GC22860@mtj.dyndns.org>

On Fri, May 03, 2013 at 12:14:18PM -0700, Tejun Heo wrote:
> On Fri, May 03, 2013 at 03:08:23PM -0400, Vivek Goyal wrote:
> > 		T1	T2	T3	T4	T5	T6	T7
> > parent:			b1	b2	b3		b4 	b5
> > child: 		b1	b2	b3		b4	b5	
> > 
> > 
> > So continuity breaks down because application is waiting for previous
> > IO to finish. This forces expiry of existing time slices and new time
> > slice start both in child and parent and penalty keep on increasing.
> 
> It's a problem even in flat mode as the "child" above can easily be
> just a process which is throttling itself and it won't be able to get
> the configured bandwidth due to the scheduling bubbles introduced
> whenever new slice is started.  Shouldn't be too difficult to get rid
> of, right?

Hi Tejun,

Following inline patch implements transferring child's start time to 
parent, if parent slice had expired at the time of bio migration.

I does seem to help a lot on my machine. Can you please give it a try.

I think even this approach is flawed. If there are multiple children,
it might happen that one child pushes up the bio early (as it is smaller
size bio or group rate is high). And later other child pushes up the bio
(bio was big or group limit was slow). We still lost time and effective
rate will still be lower than anticipated.

Thanks
Vivek


---
 block/blk-throttle.c |   40 ++++++++++++++++++++++++++++++++++++++--
 1 file changed, 38 insertions(+), 2 deletions(-)

Index: linux-2.6/block/blk-throttle.c
===================================================================
--- linux-2.6.orig/block/blk-throttle.c	2013-05-03 16:03:10.279016400 -0400
+++ linux-2.6/block/blk-throttle.c	2013-05-03 16:46:11.398936631 -0400
@@ -547,6 +547,30 @@ static bool throtl_schedule_next_dispatc
 	return false;
 }
 
+static inline void throtl_start_new_slice_with_credit(struct throtl_grp *tg,
+		bool rw, unsigned long start)
+{
+	tg->bytes_disp[rw] = 0;
+	tg->io_disp[rw] = 0;
+
+	/*
+	 * Previous slice has expired. We must have trimmed it after last
+	 * bio dispatch. That means since start of last slice, we never used
+	 * that bandwidth. Do try to make use of that bandwidth while giving
+	 * credit
+	 */
+	if (time_after_eq(start, tg->slice_start[rw])) {
+		tg->slice_start[rw] = start;
+	} else
+		tg->slice_start[rw] = tg->slice_start[rw];
+
+	tg->slice_end[rw] = jiffies + throtl_slice;
+	throtl_log(&tg->service_queue,
+		   "[%c] new slice with credit start=%lu end=%lu jiffies=%lu",
+		   rw == READ ? 'R' : 'W', tg->slice_start[rw],
+		   tg->slice_end[rw], jiffies);
+}
+
 static inline void throtl_start_new_slice(struct throtl_grp *tg, bool rw)
 {
 	tg->bytes_disp[rw] = 0;
@@ -888,6 +912,16 @@ static void tg_update_disptime(struct th
 	tg->flags &= ~THROTL_TG_WAS_EMPTY;
 }
 
+static void start_parent_slice_with_credit(struct throtl_grp *child_tg,
+					struct throtl_grp *parent_tg, bool rw)
+{
+	if (throtl_slice_used(parent_tg, rw)) {
+		throtl_start_new_slice_with_credit(parent_tg, rw,
+				child_tg->slice_start[rw]);
+	}
+
+}
+
 static void tg_dispatch_one_bio(struct throtl_grp *tg, bool rw)
 {
 	struct throtl_service_queue *sq = &tg->service_queue;
@@ -908,7 +942,9 @@ static void tg_dispatch_one_bio(struct t
 	 * responsible for issuing these bios.
 	 */
 	if (parent_tg) {
+		throtl_log(parent_sq, "add bio sz=%u", bio->bi_size);
 		throtl_add_bio_tg(bio, parent_tg);
+		start_parent_slice_with_credit(tg, parent_tg, rw);
 	} else {
 		bio_list_add(&parent_sq->bio_lists[rw], bio);
 		BUG_ON(tg->td->nr_queued[rw] <= 0);
@@ -1369,11 +1405,11 @@ bool blk_throtl_bio(struct request_queue
 	}
 
 	/* out-of-limit, queue to @tg */
-	throtl_log(sq, "[%c] bio. bdisp=%llu sz=%u bps=%llu iodisp=%u iops=%u queued=%d/%d",
+	throtl_log(sq, "[%c] bio. bdisp=%llu sz=%u bps=%llu iodisp=%u iops=%u queued=%d/%d sz=%u",
 		   rw == READ ? 'R' : 'W',
 		   tg->bytes_disp[rw], bio->bi_size, tg->bps[rw],
 		   tg->io_disp[rw], tg->iops[rw],
-		   sq->nr_queued[READ], sq->nr_queued[WRITE]);
+		   sq->nr_queued[READ], sq->nr_queued[WRITE], bio->bi_size);
 
 	bio_associate_current(bio);
 	tg->td->nr_queued[rw]++;

  parent reply	other threads:[~2013-05-03 21:05 UTC|newest]

Thread overview: 68+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-05-02  0:39 [PATCHSET] blk-throttle: implement proper hierarchy support Tejun Heo
2013-05-02  0:39 ` [PATCH 01/31] blkcg: fix error return path in blkg_create() Tejun Heo
2013-05-02  0:39 ` [PATCH 02/31] blkcg: move blkg_for_each_descendant_pre() to block/blk-cgroup.h Tejun Heo
2013-05-02  0:39 ` [PATCH 03/31] blkcg: implement blkg_for_each_descendant_post() Tejun Heo
2013-05-02  0:39 ` [PATCH 04/31] blkcg: invoke blkcg_policy->pd_init() after parent is linked Tejun Heo
2013-05-02  0:39 ` [PATCH 05/31] blkcg: move bulk of blkcg_gq release operations to the RCU callback Tejun Heo
2013-05-02  0:39 ` [PATCH 06/31] blk-throttle: remove spurious throtl_enqueue_tg() call from throtl_select_dispatch() Tejun Heo
2013-05-02  0:39 ` [PATCH 07/31] blk-throttle: removed deferred config application mechanism Tejun Heo
2013-05-02 14:49   ` Vivek Goyal
2013-05-02 17:27     ` Tejun Heo
2013-05-02  0:39 ` [PATCH 08/31] blk-throttle: collapse throtl_dispatch() into the work function Tejun Heo
2013-05-02  0:39 ` [PATCH 09/31] blk-throttle: relocate throtl_schedule_delayed_work() Tejun Heo
2013-05-02  0:39 ` [PATCH 10/31] blk-throttle: remove pointless throtl_nr_queued() optimizations Tejun Heo
2013-05-02  0:39 ` [PATCH 11/31] blk-throttle: rename throtl_rb_root to throtl_service_queue Tejun Heo
2013-05-02  0:39 ` [PATCH 12/31] blk-throttle: simplify throtl_grp flag handling Tejun Heo
2013-05-02  0:39 ` [PATCH 13/31] blk-throttle: add backlink pointer from throtl_grp to throtl_data Tejun Heo
2013-05-02  0:39 ` [PATCH 14/31] blk-throttle: pass around throtl_service_queue instead of throtl_data Tejun Heo
2013-05-02  0:39 ` [PATCH 15/31] blk-throttle: reorganize throtl_service_queue passed around as argument Tejun Heo
2013-05-02 15:21   ` Vivek Goyal
2013-05-02 17:29     ` Tejun Heo
2013-05-02  0:39 ` [PATCH 16/31] blk-throttle: add throtl_grp->service_queue Tejun Heo
2013-05-02  0:39 ` [PATCH 17/31] blk-throttle: move bio_lists[] and friends to throtl_service_queue Tejun Heo
2013-05-02  0:39 ` [PATCH 18/31] blk-throttle: dispatch to throtl_data->service_queue.bio_lists[] Tejun Heo
2013-05-02  0:39 ` [PATCH 19/31] blk-throttle: generalize update_disptime optimization in blk_throtl_bio() Tejun Heo
2013-05-02  0:39 ` [PATCH 20/31] blk-throttle: add throtl_service_queue->parent_sq Tejun Heo
2013-05-02  0:39 ` [PATCH 21/31] blk-throttle: implement sq_to_tg(), sq_to_td() and throtl_log() Tejun Heo
2013-05-06 17:36   ` Vivek Goyal
2013-05-06 18:38     ` Tejun Heo
2013-05-06 20:38     ` Tejun Heo
2013-05-06 20:39       ` Tejun Heo
2013-05-06 20:41       ` Vivek Goyal
2013-05-06 20:43         ` Tejun Heo
2013-05-02  0:39 ` [PATCH 22/31] blk-throttle: set REQ_THROTTLED from throtl_charge_bio() and gate stats update with it Tejun Heo
2013-05-02  0:39 ` [PATCH 23/31] blk-throttle: separate out throtl_service_queue->pending_timer from throtl_data->dispatch_work Tejun Heo
2013-05-02  0:39 ` [PATCH 24/31] blk-throttle: implement dispatch looping Tejun Heo
2013-05-02  0:39 ` [PATCH 25/31] blk-throttle: dispatch from throtl_pending_timer_fn() Tejun Heo
2013-05-02  0:39 ` [PATCH 26/31] blk-throttle: make blk_throtl_drain() ready for hierarchy Tejun Heo
2013-05-02  0:39 ` [PATCH 27/31] blk-throttle: make blk_throtl_bio() " Tejun Heo
2013-05-02  0:39 ` [PATCH 28/31] blk-throttle: make tg_dispatch_one_bio() " Tejun Heo
2013-05-02  0:39 ` [PATCH 29/31] blk-throttle: make throtl_pending_timer_fn() " Tejun Heo
2013-05-02  0:39 ` [PATCH 30/31] blk-throttle: implement throtl_grp->has_rules[] Tejun Heo
2013-05-02  0:39 ` [PATCH 31/31] blk-throttle: implement proper hierarchy support Tejun Heo
2013-05-02 17:34 ` [PATCHSET] " Vivek Goyal
2013-05-02 17:57   ` Tejun Heo
2013-05-02 18:17     ` Vivek Goyal
2013-05-02 18:29       ` Tejun Heo
2013-05-02 18:45         ` Vivek Goyal
2013-05-02 18:49           ` Tejun Heo
2013-05-02 19:07             ` Vivek Goyal
2013-05-02 19:11               ` Tejun Heo
2013-05-02 19:31                 ` Vivek Goyal
2013-05-02 23:13                   ` Tejun Heo
2013-05-03 17:56                     ` Vivek Goyal
2013-05-03 18:57                       ` Tejun Heo
2013-05-03 18:58                         ` Tejun Heo
2013-05-03 19:08                         ` Vivek Goyal
2013-05-03 19:14                           ` Tejun Heo
2013-05-03 19:26                             ` Vivek Goyal
2013-05-03 21:05                             ` Vivek Goyal [this message]
2013-05-03 23:54                               ` Tejun Heo
2013-05-06 17:33                                 ` Vivek Goyal
2013-05-02 18:08   ` Vivek Goyal
2013-05-02 18:44     ` Tejun Heo
2013-05-02 18:59       ` Vivek Goyal
2013-05-04  0:50 ` [PATCH 29.5/32] blk-throttle: add throtl_qnode for dispatch fairness Tejun Heo
2013-05-04  0:53   ` Tejun Heo
2013-05-06 16:00   ` Vivek Goyal
2013-05-06 18:35     ` Tejun Heo

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=20130503210513.GE6062@redhat.com \
    --to=vgoyal@redhat.com \
    --cc=axboe@kernel.dk \
    --cc=cgroups@vger.kernel.org \
    --cc=containers@lists.linux-foundation.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=lizefan@huawei.com \
    --cc=tj@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;
as well as URLs for NNTP newsgroup(s).