From: Tejun Heo <tj@kernel.org>
To: axboe@kernel.dk
Cc: linux-block@vger.kernel.org, linux-kernel@vger.kernel.org,
kernel-team@vger.kernel.org, cgroups@vger.kernel.org,
newella@fb.com, josef@toxicpanda.com
Subject: [PATCHSET block/for-5.8] iocost: improve use_delay and latency target handling
Date: Wed, 8 Apr 2020 16:14:45 -0400 [thread overview]
Message-ID: <20200408201450.3959560-1-tj@kernel.org> (raw)
Hello, Jens.
This patchset improves the following two iocost control behaviors.
* iocost was failing to punish heavy shared IO generators (file metadata, memory
reclaim) through use_delay mechanism - use_delay automatically decays which
works well for iolatency but doesn't match how iocost behaves. This led to
e.g. memory bombs which generate a lot of swap IOs to use over their allotted
amount. This is fixed by adding non-decaying use_delay mechanism.
* The same latency targets were being applied regardless of the IO sizes. While
this works fine for loose targets, it gets in the way when trying to tigthen
them - a latency target adequate for a 4k IO is too short for a 1 meg IO.
iocost now discounts the size portion of cost when testing whether a given IO
met or missed its latency target.
While at it, it also makes minor changse to iocost_monitor.py.
This patchset contains the following five patches.
0001-blk-iocost-switch-to-fixed-non-auto-decaying-use_del.patch
0002-block-add-request-io_data_len.patch
0003-blk-iocost-account-for-IO-size-when-testing-latencie.patch
0004-iocost_monitor-exit-successfully-if-interval-is-zero.patch
0005-iocost_monitor-drop-string-wrap-around-numbers-when-.patch
and is also available in the following git branch.
git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup.git iocost-delay-latency
diffstat follows. Thanks.
block/Kconfig | 4 +++
block/blk-cgroup.c | 6 ++++
block/blk-iocost.c | 54 ++++++++++++++++++++++++++++-------------
block/blk-mq.c | 6 ++++
include/linux/blk-cgroup.h | 43 +++++++++++++++++++++++++-------
include/linux/blkdev.h | 8 ++++++
tools/cgroup/iocost_monitor.py | 48 +++++++++++++++++++-----------------
7 files changed, 121 insertions(+), 48 deletions(-)
--
tejun
next reply other threads:[~2020-04-08 20:14 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-04-08 20:14 Tejun Heo [this message]
2020-04-08 20:14 ` [PATCH 1/5] blk-iocost: switch to fixed non-auto-decaying use_delay Tejun Heo
2020-04-08 20:14 ` [PATCH 2/5] block: add request->io_data_len Tejun Heo
2020-04-09 1:44 ` Ming Lei
2020-04-09 2:11 ` Tejun Heo
2020-04-09 2:38 ` Ming Lei
2020-04-09 5:08 ` Pavel Begunkov
2020-04-13 14:02 ` Tejun Heo
2020-04-13 13:56 ` Tejun Heo
2020-04-09 3:44 ` Bart Van Assche
2020-04-13 13:52 ` Tejun Heo
2020-04-08 20:14 ` [PATCH 3/5] blk-iocost: account for IO size when testing latencies Tejun Heo
2020-04-08 20:14 ` [PATCH 4/5] iocost_monitor: exit successfully if interval is zero Tejun Heo
2020-04-08 20:14 ` [PATCH 5/5] iocost_monitor: drop string wrap around numbers when outputting json 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=20200408201450.3959560-1-tj@kernel.org \
--to=tj@kernel.org \
--cc=axboe@kernel.dk \
--cc=cgroups@vger.kernel.org \
--cc=josef@toxicpanda.com \
--cc=kernel-team@vger.kernel.org \
--cc=linux-block@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=newella@fb.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