Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Fri, 1 Jul 2022 07:43:30 +0900
From:   Dominique MARTINET <dominique.martinet@atmark-techno.com>
To:     Theodore Ts'o <tytso@mit.edu>
Cc:     "Matthew Wilcox (Oracle)" <willy@infradead.org>,
        linux-btrfs@vger.kernel.org, linux-mm@kvack.org,
        linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
        Yu Kuai <yukuai3@huawei.com>,
        Kent Overstreet <kent.overstreet@gmail.com>
Subject: Re: Major btrfs fiemap slowdown on file with many extents once in
 cache (RCU stalls?) (Was: [PATCH 1/3] filemap: Correct the conditions for
 marking a folio as accessed)
Message-ID: <Yr4nEoNLkXPKcOBi@atmark-techno.com>
References: <20220619151143.1054746-1-willy@infradead.org>
 <20220619151143.1054746-2-willy@infradead.org>
 <Yr1QwVW+sHWlAqKj@atmark-techno.com>
 <Yr21RoL+ztf1W5Od@mit.edu>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
In-Reply-To: <Yr21RoL+ztf1W5Od@mit.edu>
Precedence: bulk

Theodore Ts'o wrote on Thu, Jun 30, 2022 at 10:37:58AM -0400:
> On Thu, Jun 30, 2022 at 04:29:05PM +0900, Dominique MARTINET wrote:
> > Hi Willy, linux-btrfs@vger,
> > 
> > Matthew Wilcox (Oracle) wrote on Sun, Jun 19, 2022 at 04:11:41PM +0100:
> > > We had an off-by-one error which meant that we never marked the first page
> > > in a read as accessed.  This was visible as a slowdown when re-reading
> > > a file as pages were being evicted from cache too soon.  In reviewing
> > > this code, we noticed a second bug where a multi-page folio would be
> > > marked as accessed multiple times when doing reads that were less than
> > > the size of the folio.
> > 
> > when debugging an unrelated issue (short reads on btrfs with io_uring
> > and O_DIRECT[1]), I noticed that my horrible big file copy speeds fell
> > down from ~2GB/s (there's compression and lots of zeroes) to ~100MB/s
> > the second time I was copying it with cp.
> > 
> > I've taken a moment to bisect this and came down to this patch.
> 
> I think you may have forgotten to include the commit-id that was the
> results of your bisect.... ?

Sorry, this is the patch I replied to and it was recent enough that I
assumed it'd still be in mailboxes, but you're right it's better with a
commit id. This is was merged as 5ccc944dce3d ("filemap: Correct the
conditions for marking a folio as accessed")


Thanks,
-- 
Dominique