Re: [PATCH 1/1] mm: introduce process_reap system call

From: Suren Baghdasaryan <surenb@google.com>
To: Andy Lutomirski <luto@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	Michal Hocko <mhocko@kernel.org>, Michal Hocko <mhocko@suse.com>,
	David Rientjes <rientjes@google.com>,
	Matthew Wilcox <willy@infradead.org>,
	Johannes Weiner <hannes@cmpxchg.org>,
	Roman Gushchin <guro@fb.com>, Rik van Riel <riel@surriel.com>,
	Minchan Kim <minchan@kernel.org>,
	Christian Brauner <christian@brauner.io>,
	Christoph Hellwig <hch@infradead.org>,
	Oleg Nesterov <oleg@redhat.com>,
	David Hildenbrand <david@redhat.com>,
	Jann Horn <jannh@google.com>, Shakeel Butt <shakeelb@google.com>,
	Tim Murray <timmurray@google.com>,
	Linux API <linux-api@vger.kernel.org>,
	Linux-MM <linux-mm@kvack.org>,
	LKML <linux-kernel@vger.kernel.org>,
	Android Kernel Team <kernel-team@android.com>
Subject: Re: [PATCH 1/1] mm: introduce process_reap system call
Date: Wed, 30 Jun 2021 11:51:36 -0700	[thread overview]
Message-ID: <CAJuCfpFMTP-g9CFELMqNawX0FhF4vBNtRDP_R=WAi_RiuGW8-Q@mail.gmail.com> (raw)
In-Reply-To: <CALCETrU577MD59P-+9sMYtS3t2sZYx-zi=VirhQpZLnhEck1vg@mail.gmail.com>

On Wed, Jun 30, 2021 at 11:26 AM Andy Lutomirski <luto@kernel.org> wrote:
>
> On Wed, Jun 23, 2021 at 12:28 PM Suren Baghdasaryan <surenb@google.com> wrote:
> >
> > In modern systems it's not unusual to have a system component monitoring
> > memory conditions of the system and tasked with keeping system memory
> > pressure under control. One way to accomplish that is to kill
> > non-essential processes to free up memory for more important ones.
> > Examples of this are Facebook's OOM killer daemon called oomd and
> > Android's low memory killer daemon called lmkd.
> > For such system component it's important to be able to free memory
> > quickly and efficiently. Unfortunately the time process takes to free
> > up its memory after receiving a SIGKILL might vary based on the state
> > of the process (uninterruptible sleep), size and OPP level of the core
> > the process is running. A mechanism to free resources of the target
> > process in a more predictable way would improve system's ability to
> > control its memory pressure.
> > Introduce process_reap system call that reclaims memory of a dying process
> > from the context of the caller. This way the memory in freed in a more
> > controllable way with CPU affinity and priority of the caller. The workload
> > of freeing the memory will also be charged to the caller.
> > The operation is allowed only on a dying process.
>
> At the risk of asking a potentially silly question, should this just
> be a file in procfs?

Hmm. I guess it's doable if procfs will not disappear too soon before
memory is released... syscall also supports parameters, in this case
flags can be used in the future to support PIDs in addition to PIDFDs
for example.
Before looking more in that direction, a silly question from my side:
why procfs interface would be preferable to a syscall?

>
> Also, please consider removing all mention of the word "reap" from the
> user API.  For better or for worse, "reap" in UNIX refers to what
> happens when a dead task gets wait()ed.  I sincerely wish I could go
> back in time and gently encourage whomever invented that particular
> abomination to change their mind, but my time machine doesn't work.

I see. Thanks for the note. How about process_mem_release() and
replacing reap with release everywhere?

>
> --Andy