From mboxrd@z Thu Jan 1 00:00:00 1970 From: Stefan Priebe - Profihost AG Subject: Re: bcache: Fix a writeback performance regression Date: Tue, 20 Aug 2013 10:01:07 +0200 Message-ID: <52132243.8050803@profihost.ag> References: <20130814225904.GA6427@kmo-pixel> <520C788A.1060208@profihost.ag> <520DFAB4.1050402@profihost.ag> <52114614.4070509@profihost.ag> <20130819222718.GA32104@kmo-pixel> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <20130819222718.GA32104@kmo-pixel> Sender: linux-bcache-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org To: Kent Overstreet Cc: Jens Axboe , linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-bcache-u79uwXL29TY76Z2rM5mHXA@public.gmane.org List-Id: linux-bcache@vger.kernel.org Am 20.08.2013 00:27, schrieb Kent Overstreet: > On Mon, Aug 19, 2013 at 12:09:24AM +0200, Stefan Priebe wrote: >> >> Vanilla 3.10.7 + bcache: Fix a writeback performance regression >> >> http://pastebin.com/raw.php?i=LXZk4cMH > > Whoops, at first I thought this was the same bug as one I'd already been > chasing down that had been a harmless bug - turns out I didn't look > closely enough at the backtrace. > > What happened is background writeback is deadlocking, because for some > reason the workqueue it's running out of is a singlethreaded workqueue, > so as soon as it decides to queue enough writeback bios that it has to > sleep on that semaphore (which often won't happen due to the PD > controller based ratelimiting) - boom, deadlock. > > Here's the fixup patch I just tested and am applying: thanks, this works fine. The only issue i still have, is that the dirty_date value starts at 0 and goes to a negative value after reboot. Greets, Stefan