From: Alexei Starovoitov <alexei.starovoitov@gmail.com>
To: Kenny Ho <y2kenny@gmail.com>
Cc: Kenny Ho <Kenny.Ho@amd.com>,
Alexander Viro <viro@zeniv.linux.org.uk>,
Alexei Starovoitov <ast@kernel.org>,
Daniel Borkmann <daniel@iogearbox.net>,
Martin KaFai Lau <kafai@fb.com>, Song Liu <songliubraving@fb.com>,
Yonghong Song <yhs@fb.com>, Andrii Nakryiko <andriin@fb.com>,
John Fastabend <john.fastabend@gmail.com>,
KP Singh <kpsingh@chromium.org>, bpf <bpf@vger.kernel.org>,
Network Development <netdev@vger.kernel.org>,
Linux-Fsdevel <linux-fsdevel@vger.kernel.org>,
"open list:CONTROL GROUP (CGROUP)" <cgroups@vger.kernel.org>,
Alex Deucher <alexander.deucher@amd.com>,
amd-gfx list <amd-gfx@lists.freedesktop.org>
Subject: Re: [RFC] Add BPF_PROG_TYPE_CGROUP_IOCTL
Date: Tue, 3 Nov 2020 13:04:18 -0800 [thread overview]
Message-ID: <20201103210418.q7hddyl7rvdplike@ast-mbp.dhcp.thefacebook.com> (raw)
In-Reply-To: <CAOWid-czZphRz6Y-H3OcObKCH=bLLC3=bOZaSB-6YBE56+Qzrg@mail.gmail.com>
On Tue, Nov 03, 2020 at 02:19:22PM -0500, Kenny Ho wrote:
> On Tue, Nov 3, 2020 at 12:43 AM Alexei Starovoitov
> <alexei.starovoitov@gmail.com> wrote:
> > On Mon, Nov 2, 2020 at 9:39 PM Kenny Ho <y2kenny@gmail.com> wrote:
> > pls don't top post.
> My apology.
>
> > > Cgroup awareness is desired because the intent
> > > is to use this for resource management as well (potentially along with
> > > other cgroup controlled resources.) I will dig into bpf_lsm and learn
> > > more about it.
> >
> > Also consider that bpf_lsm hooks have a way to get cgroup-id without
> > being explicitly scoped. So the bpf program can be made cgroup aware.
> > It's just not as convenient as attaching a prog to cgroup+hook at once.
> > For prototyping the existing bpf_lsm facility should be enough.
> > So please try to follow this route and please share more details about
> > the use case.
>
> Ok. I will take a look and see if that is sufficient. My
> understanding of bpf-cgroup is that it not only makes attaching prog
> to cgroup easier but it also facilitates hierarchical calling of
> attached progs which might be useful if users wants to manage gpu
> resources with bpf cgroup along with other cgroup resources (like
> cpu/mem/io, etc.)
Right. Hierarchical cgroup-bpf logic cannot be replicated inside
the program. If you're relying on cgv2 hierarchy to containerize
applications then what I suggested earlier won't work indeed.
> About the use case. The high level motivation here is to provide the
> ability to subdivide/share a GPU via cgroups/containers in a way that
> is similar to other resources like CPU and memory. Users have been
> requesting this type of functionality because GPU compute can get
> expensive and they want to maximize the utilization to get the most
> bang for their bucks. A traditional way to do this is via
> SRIOV/virtualization but that often means time sharing the GPU as a
> whole unit. That is useful for some applications but not others due
> to the flushing and added latency. We also have a study that
> identified various GPU compute application types. These types can
> benefit from more asymmetrical/granular sharing of the GPU (for
> example some applications are compute bound while others can be memory
> bound that can benefit from having more VRAM.)
>
> I have been trying to add a cgroup subsystem for the drm subsystem for
> this purpose but I ran into two challenges. First, the composition of
> a GPU and how some of the subcomponents (like VRAM or shader
> engines/compute units) can be shared are very much vendor specific so
> we are unable to arrive at a common interface across all vendors.
> Because of this and the variety of places a GPU can go into
> (smartphone, PC, server, HPC), there is also no agreement on how
> exactly a GPU should be shared. The best way forward appears to
> simply provide hooks for users to define how and what they want to
> share via a bpf program.
Thank you for sharing the details. It certainly helps.
> From what I can tell so far (I am still learning), there are multiple
> pieces that need to fall in place for bpf-cgroup to work for this use
> case. First there is resource limit enforcement, which is the
> motivation for this RFC (I will look into bpf_lsm as the path
> forward.) I have also been thinking about instrumenting the drm
> subsystem with a new BPF program type and have various attach types
> across the drm subsystem but I am not sure if this is allowed (this
> one is more for resource usage monitoring.) Another thing I have been
> considering is to have the gpu driver provide bpf helper functions for
> bpf programs to modify drm driver internals. That was the reason I
> asked about the potential of BTF support for kernel modules a couple
> of months ago (and Andrii Nakryiko mentioned that it is being worked
> on.)
Sounds like either bpf_lsm needs to be made aware of cgv2 (which would
be a great thing to have regardless) or cgroup-bpf needs a drm/gpu specific hook.
I think generic ioctl hook is too broad for this use case.
I suspect drm/gpu internal state would be easier to access inside
bpf program if the hook is next to gpu/drm. At ioctl level there is 'file'.
It's probably too abstract for the things you want to do.
Like how VRAM/shader/etc can be accessed through file?
Probably possible through a bunch of lookups and dereferences, but
if the hook is custom to GPU that info is likely readily available.
Then such cgroup-bpf check would be suitable in execution paths where
ioctl-based hook would be too slow.
next prev parent reply other threads:[~2020-11-03 21:23 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-10-07 15:23 [RFC] Add BPF_PROG_TYPE_CGROUP_IOCTL Kenny Ho
2020-11-02 19:23 ` Kenny Ho
2020-11-03 5:32 ` Alexei Starovoitov
2020-11-03 5:39 ` Kenny Ho
2020-11-03 5:42 ` Alexei Starovoitov
2020-11-03 19:19 ` Kenny Ho
2020-11-03 21:04 ` Alexei Starovoitov [this message]
2020-11-03 22:57 ` Kenny Ho
2020-11-03 23:28 ` Alexei Starovoitov
2021-02-01 14:49 ` Daniel Vetter
2021-02-01 16:51 ` Kenny Ho
2021-02-03 11:09 ` Daniel Vetter
2021-02-03 19:01 ` Kenny Ho
2021-02-05 13:49 ` Daniel Vetter
2021-05-07 2:06 ` Kenny Ho
2021-05-07 8:59 ` Daniel Vetter
2021-05-07 15:33 ` Kenny Ho
2021-05-07 16:13 ` Daniel Vetter
2021-05-07 16:19 ` Alex Deucher
2021-05-07 16:26 ` Daniel Vetter
2021-05-07 16:31 ` Alex Deucher
2021-05-07 16:50 ` Alex Deucher
2021-05-07 16:54 ` Daniel Vetter
2021-05-07 17:04 ` Kenny Ho
2021-05-07 19:33 ` Tejun Heo
2021-05-07 19:55 ` Alex Deucher
2021-05-07 20:59 ` Tejun Heo
2021-05-07 22:30 ` Alex Deucher
2021-05-07 23:45 ` Tejun Heo
2021-05-11 15:48 ` Alex Deucher
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=20201103210418.q7hddyl7rvdplike@ast-mbp.dhcp.thefacebook.com \
--to=alexei.starovoitov@gmail.com \
--cc=Kenny.Ho@amd.com \
--cc=alexander.deucher@amd.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=andriin@fb.com \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=cgroups@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=john.fastabend@gmail.com \
--cc=kafai@fb.com \
--cc=kpsingh@chromium.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=songliubraving@fb.com \
--cc=viro@zeniv.linux.org.uk \
--cc=y2kenny@gmail.com \
--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).