linux-kernel - Re: [PATCH RFC 1/4] fs/locks: Fix file lock cache accounting, again

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CALvZod7T=gops1B6gU3M7rOJ8D2mOrSwQ2hfpLaE-tNWZynAug@mail.gmail.com>
Date: Thu, 18 Jan 2024 23:47:51 -0800
From: Shakeel Butt <shakeelb@...gle.com>
To: Roman Gushchin <roman.gushchin@...ux.dev>
Cc: Linus Torvalds <torvalds@...ux-foundation.org>, Josh Poimboeuf <jpoimboe@...nel.org>, 
	Vlastimil Babka <vbabka@...e.cz>, Jeff Layton <jlayton@...nel.org>, 
	Chuck Lever <chuck.lever@...cle.com>, Johannes Weiner <hannes@...xchg.org>, 
	Michal Hocko <mhocko@...nel.org>, linux-kernel@...r.kernel.org, 
	Jens Axboe <axboe@...nel.dk>, Tejun Heo <tj@...nel.org>, Vasily Averin <vasily.averin@...ux.dev>, 
	Michal Koutny <mkoutny@...e.com>, Waiman Long <longman@...hat.com>, 
	Muchun Song <muchun.song@...ux.dev>, Jiri Kosina <jikos@...nel.org>, cgroups@...r.kernel.org, 
	linux-mm@...ck.org
Subject: Re: [PATCH RFC 1/4] fs/locks: Fix file lock cache accounting, again

On Wed, Jan 17, 2024 at 2:20 PM Roman Gushchin <roman.gushchin@...ux.dev> wrote:
>
> On Wed, Jan 17, 2024 at 01:02:19PM -0800, Shakeel Butt wrote:
> > On Wed, Jan 17, 2024 at 12:21 PM Linus Torvalds
> > <torvalds@...ux-foundation.org> wrote:
> > >
> > > On Wed, 17 Jan 2024 at 11:39, Josh Poimboeuf <jpoimboe@...nel.org> wrote:
> > > >
> > > > That's a good point.  If the microbenchmark isn't likely to be even
> > > > remotely realistic, maybe we should just revert the revert until if/when
> > > > somebody shows a real world impact.
> > > >
> > > > Linus, any objections to that?
> > >
> > > We use SLAB_ACCOUNT for much more common allocations like queued
> > > signals, so I would tend to agree with Jeff that it's probably just
> > > some not very interesting microbenchmark that shows any file locking
> > > effects from SLAB_ALLOC, not any real use.
> > >
> > > That said, those benchmarks do matter. It's very easy to say "not
> > > relevant in the big picture" and then the end result is that
> > > everything is a bit of a pig.
> > >
> > > And the regression was absolutely *ENORMOUS*. We're not talking "a few
> > > percent". We're talking a 33% regression that caused the revert:
> > >
> > >    https://lore.kernel.org/lkml/20210907150757.GE17617@xsang-OptiPlex-9020/
> > >
> > > I wish our SLAB_ACCOUNT wasn't such a pig. Rather than account every
> > > single allocation, it would be much nicer to account at a bigger
> > > granularity, possibly by having per-thread counters first before
> > > falling back to the obj_cgroup_charge. Whatever.
> > >
> > > It's kind of stupid to have a benchmark that just allocates and
> > > deallocates a file lock in quick succession spend lots of time
> > > incrementing and decrementing cgroup charges for that repeated
> > > alloc/free.
> > >
> > > However, that problem with SLAB_ACCOUNT is not the fault of file
> > > locking, but more of a slab issue.
> > >
> > > End result: I think we should bring in Vlastimil and whoever else is
> > > doing SLAB_ACCOUNT things, and have them look at that side.
> > >
> > > And then just enable SLAB_ACCOUNT for file locks. But very much look
> > > at silly costs in SLAB_ACCOUNT first, at least for trivial
> > > "alloc/free" patterns..
> > >
> > > Vlastimil? Who would be the best person to look at that SLAB_ACCOUNT
> > > thing? See commit 3754707bcc3e (Revert "memcg: enable accounting for
> > > file lock caches") for the history here.
> > >
> >
> > Roman last looked into optimizing this code path. I suspect
> > mod_objcg_state() to be more costly than obj_cgroup_charge(). I will
> > try to measure this path and see if I can improve it.
>
> It's roughly an equal split between mod_objcg_state() and obj_cgroup_charge().
> And each is comparable (by order of magnitude) to the slab allocation cost
> itself. On the free() path a significant cost comes simple from reading
> the objcg pointer (it's usually a cache miss).
>
> So I don't see how we can make it really cheap (say, less than 5% overhead)
> without caching pre-accounted objects.
>
> I thought about merging of charge and stats handling paths, which _maybe_ can
> shave off another 20-30%, but there still will be a double-digit% accounting
> overhead.
>
> I'm curious to hear other ideas and suggestions.
>
> Thanks!

I profiled (perf record -a) the same benchmark i.e. lock1_processes on
an icelake machine with 72 cores and got the following results:

  12.72%  lock1_processes  [kernel.kallsyms]   [k] mod_objcg_state
  10.89%  lock1_processes  [kernel.kallsyms]   [k] kmem_cache_free
   8.40%  lock1_processes  [kernel.kallsyms]   [k] slab_post_alloc_hook
   8.36%  lock1_processes  [kernel.kallsyms]   [k] kmem_cache_alloc
   5.18%  lock1_processes  [kernel.kallsyms]   [k] refill_obj_stock
   5.18%  lock1_processes  [kernel.kallsyms]   [k] _copy_from_user

On annotating mod_objcg_state(), the following irq disabling
instructions are taking 30% of its time.

  6.64 │       pushfq
 10.26│       popq   -0x38(%rbp)
  6.05 │       mov    -0x38(%rbp),%rcx
  7.60 │       cli

For kmem_cache_free() & kmem_cache_alloc(), the following instruction
was expensive, which corresponds to __update_cpu_freelist_fast().

 16.33 │      cmpxchg16b %gs:(%rsi)

For slab_post_alloc_hook(), it's all over the place and
refill_obj_stock() is very similar to mod_objcg_state().

I will dig more in the next couple of days.