[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <CAKEwX=PDsYdyAq8s+A0-YQ7nQWVvJA9Tw5dNP6S1w6Rh==dQCw@mail.gmail.com>
Date: Thu, 17 Aug 2023 15:53:24 -0700
From: Nhat Pham <nphamcs@...il.com>
To: Yosry Ahmed <yosryahmed@...gle.com>
Cc: Andrew Morton <akpm@...ux-foundation.org>,
Konrad Rzeszutek Wilk <konrad.wilk@...cle.com>,
Seth Jennings <sjenning@...hat.com>,
Dan Streetman <ddstreet@...e.org>,
Vitaly Wool <vitaly.wool@...sulko.com>,
Johannes Weiner <hannes@...xchg.org>,
Domenico Cerasuolo <cerasuolodomenico@...il.com>,
Yu Zhao <yuzhao@...gle.com>, linux-mm@...ck.org,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH v3] mm: zswap: multiple zpools support
On Fri, Aug 11, 2023 at 4:21 PM Yosry Ahmed <yosryahmed@...gle.com> wrote:
>
> On Fri, Aug 11, 2023 at 2:19 PM Andrew Morton <akpm@...ux-foundation.org> wrote:
> >
> > On Thu, 13 Jul 2023 03:35:25 -0700 Yosry Ahmed <yosryahmed@...gle.com> wrote:
> >
> > > >
> > > > I'm experimenting with some other zswap changes - if I have
> > > > extra cycles and resources I'll try to apply this patch and see how the
> > > > numbers play out.
> > >
> > > That would be amazing. Looking forward to any numbers you can dig :)
> >
> > So this patch seems stuck. I can keep it in mm.git until the fog
> > clears, but would prefer not to. Can we please revisit and decide on a
> > way forward?
>
> Johannes did not like a config option so I proposed it here as a
> constant (like SWAP_CLUSTER_MAX and others we have). This is a value
> that we have been using in our data centers for almost a decade, so it
> has seen a ton of testing. I was hoping Johannes would get time to
> take a look, or Nhat would get time to test it out, but neither of
> these things happen.
Apologies - finally have some time + freed experiment machine cycles
to put in your patch :P And gotta wait a couple of days to obtain sufficient
data.
Result is quite unexciting - no tremendous gains or significant regression
in a bunch of internal metrics I was observing.
Of course, it's just one particular workload that I tested on - there could
be regression/gains in other workloads (or other metrics). But we can
always revisit this when it happens :)
With all that said, the code itself looks solid. And while I'm still not in
love with the change, I don't have any further objections, as of now.
I'll let you (and Johannes) continue from here.
Reviewed-by: Nhat Pham <nphamcs@...il.com>
Tested-by: Nhat Pham <nphamcs@...il.com>
>
> I obviously want it to be merged, but hopefully someone will chime in here :)
Powered by blists - more mailing lists