From: Alexei Starovoitov <ast@fb.com>
To: Tejun Heo <tj@kernel.org>, Quentin Monnet <quentin.monnet@netronome.com>
Cc: "axboe@kernel.dk" <axboe@kernel.dk>, Andy Newell <newella@fb.com>,
"Chris Mason" <clm@fb.com>,
"josef@toxicpanda.com" <josef@toxicpanda.com>,
"Dennis Zhou" <dennisz@fb.com>,
"lizefan@huawei.com" <lizefan@huawei.com>,
"hannes@cmpxchg.org" <hannes@cmpxchg.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"linux-block@vger.kernel.org" <linux-block@vger.kernel.org>,
Kernel Team <Kernel-team@fb.com>,
"cgroups@vger.kernel.org" <cgroups@vger.kernel.org>,
"ast@kernel.org" <ast@kernel.org>,
"daniel@iogearbox.net" <daniel@iogearbox.net>,
Martin Lau <kafai@fb.com>, Song Liu <songliubraving@fb.com>,
Yonghong Song <yhs@fb.com>,
"bpf@vger.kernel.org" <bpf@vger.kernel.org>
Subject: Re: [PATCH 10/10] blkcg: implement BPF_PROG_TYPE_IO_COST
Date: Fri, 14 Jun 2019 16:35:35 +0000 [thread overview]
Message-ID: <bed0a66a-7aa6-ac36-9182-31a4937257e5@fb.com> (raw)
In-Reply-To: <20190614145239.GA538958@devbig004.ftw2.facebook.com>
On 6/14/19 7:52 AM, Tejun Heo wrote:
> Hello, Quentin.
>
> On Fri, Jun 14, 2019 at 12:32:09PM +0100, Quentin Monnet wrote:
>> Please make sure to update the documentation and bash
>> completion when adding the new type to bpftool. You
>> probably want something like the diff below.
>
> Thank you so much. Will incorporate them. Just in case, while it's
> noted in the head message, I lost the RFC marker while prepping this
> patch. It isn't yet clear whether we'd really need custom cost
> functions and this patch is included more as a proof of concept.
the example bpf prog looks flexible enough to allow some degree
of experiments. The question is what kind of new algorithms you envision
it will do? what other inputs it would need to make a decision?
I think it's ok to start with what it does now and extend further
when need arises.
> If
> it turns out that this is beneficial enough, the followings need to be
> answered.
>
> * Is block ioctl the right mechanism to attach these programs?
imo ioctl is a bit weird, but since its only one program per block
device it's probably ok? Unless you see it being cgroup scoped in
the future? Then cgroup-bpf style hooks will be more suitable
and allow a chain of programs.
> * Are there more parameters that need to be exposed to the programs?
>
> * It'd be great to have efficient access to per-blockdev and
> per-blockdev-cgroup-pair storages available to these programs so
> that they can keep track of history. What'd be the best of way of
> doing that considering the fact that these programs will be called
> per each IO and the overhead can add up quickly?
Martin's socket local storage solved that issue for sockets.
Something very similar can work for per-blockdev-per-cgroup.
next prev parent reply other threads:[~2019-06-14 16:37 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-06-14 1:56 [PATCHSET block/for-next] IO cost model based work-conserving porportional controller Tejun Heo
2019-06-14 1:56 ` [PATCH 01/10] blkcg: pass @q and @blkcg into blkcg_pol_alloc_pd_fn() Tejun Heo
2019-06-14 1:56 ` [PATCH 02/10] blkcg: make ->cpd_init_fn() optional Tejun Heo
2019-06-14 1:56 ` [PATCH 03/10] blkcg: separate blkcg_conf_get_disk() out of blkg_conf_prep() Tejun Heo
2019-06-14 1:56 ` [PATCH 04/10] block/rq_qos: add rq_qos_merge() Tejun Heo
2019-06-14 1:56 ` [PATCH 05/10] block/rq_qos: implement rq_qos_ops->queue_depth_changed() Tejun Heo
2019-06-14 1:56 ` [PATCH 06/10] blkcg: s/RQ_QOS_CGROUP/RQ_QOS_LATENCY/ Tejun Heo
2019-06-14 1:56 ` [PATCH 07/10] blk-mq: add optional request->pre_start_time_ns Tejun Heo
2019-06-14 1:56 ` [PATCH 08/10] blkcg: implement blk-ioweight Tejun Heo
2019-06-14 12:17 ` Toke Høiland-Jørgensen
2019-06-14 15:09 ` Tejun Heo
2019-06-14 20:50 ` Toke Høiland-Jørgensen
2019-06-15 15:57 ` Tejun Heo
2019-06-14 1:56 ` [PATCH 09/10] blkcg: add tools/cgroup/monitor_ioweight.py Tejun Heo
2019-06-14 1:56 ` [PATCH 10/10] blkcg: implement BPF_PROG_TYPE_IO_COST Tejun Heo
2019-06-14 11:32 ` Quentin Monnet
2019-06-14 14:52 ` Tejun Heo
2019-06-14 16:35 ` Alexei Starovoitov [this message]
2019-06-14 17:09 ` Tejun Heo
2019-06-14 17:56 ` [PATCHSET block/for-next] IO cost model based work-conserving porportional controller Tejun Heo
2019-08-20 10:48 ` Paolo Valente
2019-08-20 15:04 ` Paolo Valente
2019-08-20 15:19 ` Tejun Heo
2019-08-22 8:58 ` Paolo Valente
2019-08-31 6:53 ` Tejun Heo
2019-08-31 7:10 ` Paolo Valente
2019-08-31 11:20 ` Tejun Heo
2019-09-02 15:45 ` Paolo Valente
2019-09-02 15:56 ` Tejun Heo
2019-09-02 19:43 ` Paolo Valente
2019-09-05 16:55 ` Tejun Heo
2019-09-06 9:07 ` Paolo Valente
2019-09-06 14:58 ` Tejun Heo
2020-02-19 18:34 ` Paolo Valente
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=bed0a66a-7aa6-ac36-9182-31a4937257e5@fb.com \
--to=ast@fb.com \
--cc=Kernel-team@fb.com \
--cc=ast@kernel.org \
--cc=axboe@kernel.dk \
--cc=bpf@vger.kernel.org \
--cc=cgroups@vger.kernel.org \
--cc=clm@fb.com \
--cc=daniel@iogearbox.net \
--cc=dennisz@fb.com \
--cc=hannes@cmpxchg.org \
--cc=josef@toxicpanda.com \
--cc=kafai@fb.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=lizefan@huawei.com \
--cc=newella@fb.com \
--cc=quentin.monnet@netronome.com \
--cc=songliubraving@fb.com \
--cc=tj@kernel.org \
--cc=yhs@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;
as well as URLs for NNTP newsgroup(s).