Date:   Thu, 31 Mar 2022 16:24:09 +0100
From:   Mel Gorman <mgorman@...e.de>
To:     Nicolas Saenz Julienne <nsaenzju@...hat.com>
Cc:     akpm@...ux-foundation.org, linux-kernel@...r.kernel.org,
        linux-mm@...ck.org, frederic@...nel.org, tglx@...utronix.de,
        mtosatti@...hat.com, linux-rt-users@...r.kernel.org,
        vbabka@...e.cz, cl@...ux.com, paulmck@...nel.org,
        willy@...radead.org
Subject: Re: [PATCH 0/2] mm/page_alloc: Remote per-cpu lists drain support

On Wed, Mar 30, 2022 at 01:29:04PM +0200, Nicolas Saenz Julienne wrote:
> Hi Mel,
> 
> On Thu, 2022-03-03 at 11:45 +0000, Mel Gorman wrote:
> > On Tue, Feb 08, 2022 at 11:07:48AM +0100, Nicolas Saenz Julienne wrote:
> > > This series replaces mm/page_alloc's per-cpu page lists drain mechanism with
> > > one that allows accessing the lists remotely. Currently, only a local CPU is
> > > permitted to change its per-cpu lists, and it's expected to do so, on-demand,
> > > whenever a process demands it by means of queueing a drain task on the local
> > > CPU. This causes problems for NOHZ_FULL CPUs and real-time systems that can't
> > > take any sort of interruption and to some lesser extent inconveniences idle and
> > > virtualised systems.
> > > 
> > 
> > I know this has been sitting here for a long while. Last few weeks have
> > not been fun.
> > 
> > > Note that this is not the first attempt at fixing this per-cpu page lists:
> > >  - The first attempt[1] tried to conditionally change the pagesets locking
> > >    scheme based the NOHZ_FULL config. It was deemed hard to maintain as the
> > >    NOHZ_FULL code path would be rarely tested. Also, this only solves the issue
> > >    for NOHZ_FULL setups, which isn't ideal.
> > >  - The second[2] unanimously switched the local_locks to per-cpu spinlocks. The
> > >    performance degradation was too big.
> > > 
> > 
> > For unrelated reasons I looked at using llist to avoid locks entirely. It
> > turns out it's not possible and needs a lock. We know "local_locks to
> > per-cpu spinlocks" took a large penalty so I considered alternatives on
> > how a lock could be used.  I found it's possible to both remote drain
> > the lists and avoid the disable/enable of IRQs entirely as long as a
> > preempting IRQ is willing to take the zone lock instead (should be very
> > rare). The IRQ part is a bit hairy though as softirqs are also a problem
> > and preempt-rt needs different rules and the llist has to sort PCP
> > refills which might be a loss in total. However, the remote draining may
> > still be interesting. The full series is at
> > https://git.kernel.org/pub/scm/linux/kernel/git/mel/linux.git/ mm-pcpllist-v1r2
> > 
> > It's still waiting on tests to complete and not all the changelogs are
> > complete which is why it's not posted.
> > 
> > This is a comparison of vanilla vs "local_locks to per-cpu spinlocks"
> > versus the git series up to "mm/page_alloc: Remotely drain per-cpu lists"
> > for the page faulting microbench I originally complained about.  The test
> > machine is a 2-socket CascadeLake machine.
> > 
> > pft timings
> >                                  5.17.0-rc5             5.17.0-rc5             5.17.0-rc5
> >                                     vanilla    mm-remotedrain-v2r1       mm-pcpdrain-v1r1
> > Amean     elapsed-1        32.54 (   0.00%)       33.08 *  -1.66%*       32.82 *  -0.86%*
> > Amean     elapsed-4         8.66 (   0.00%)        9.24 *  -6.72%*        8.69 *  -0.38%*
> > Amean     elapsed-7         5.02 (   0.00%)        5.43 *  -8.16%*        5.05 *  -0.55%*
> > Amean     elapsed-12        3.07 (   0.00%)        3.38 * -10.00%*        3.09 *  -0.72%*
> > Amean     elapsed-21        2.36 (   0.00%)        2.38 *  -0.89%*        2.19 *   7.39%*
> > Amean     elapsed-30        1.75 (   0.00%)        1.87 *  -6.50%*        1.62 *   7.59%*
> > Amean     elapsed-48        1.71 (   0.00%)        2.00 * -17.32%*        1.71 (  -0.08%)
> > Amean     elapsed-79        1.56 (   0.00%)        1.62 *  -3.84%*        1.56 (  -0.02%)
> > Amean     elapsed-80        1.57 (   0.00%)        1.65 *  -5.31%*        1.57 (  -0.04%)
> > 
> > Note the local_lock conversion took 1 1-17% penalty while the git tree
> > takes a negligile penalty while still allowing remote drains. It might
> > have some potential while being less complex than the RCU approach.
> 
> I've been made aware of a problem with the spin_trylock() approach. It doesn't
> work for UP since in that context spin_lock() is a NOOP (well, it only disables
> preemption). So nothing prevents a race with an IRQ.
> 

I didn't think of UP being a problem. I'm offline shortly until early next
week but superficially the spin_[try]lock for PCP would need a pcp_lock
and pcp_trylock helpers. On SMP, it would be the equivalent lock. On UP,
pcp_lock would map to spin_lock but pcp_trylock would likely need to map
to spin_lock_irqsave. It means that UP would always disable IRQs but that
would be no worse than the current allocator.

-- 
Mel Gorman
SUSE Labs

Powered by blists - more mailing lists