From: Hubert Kempkensteffen Subject: Re: [PATCH] bcache: Possible flush fix Date: Wed, 18 Sep 2013 17:05:41 +0000 (UTC) Message-ID: References: <20130917020316.GC10907@kmo-pixel> <20130917203741.GA32037@kmo-pixel> <20130917214043.GF32037@kmo-pixel> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Return-path: Sender: linux-bcache-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org To: linux-bcache-u79uwXL29TY76Z2rM5mHXA@public.gmane.org List-Id: linux-bcache@vger.kernel.org Kent Overstreet writes: > > Jens suggested that cloning the bio to issue a bare flush might be > copying some flags we don't want, and at least allocating a new bio > would be more correct. Worth a shot... > > Signed-off-by: Kent Overstreet > --- > > On Tue, Sep 17, 2013 at 08:54:57PM +0000, Hubert Kempkensteffen wrote: > > Kent Overstreet ...> writes: > > Sorry, my english. > > I have no raid and no LVM. There are both ordinary machines. > > And I just want to speed up the data disk! > > > > > > > > I think this bug requires something else in the stack to trigger, I'm > > > trying to figure out what the common factor is. > > Can you give this patch a try? > Now he stands. For about an hour, no more file has been copied. Otherwise, the computer is running normally. root@server:/mnt# bcache-super-show /dev/sda4 sb.magic ok sb.first_sector 8 [match] sb.csum 35DD4574872CBCCF [match] sb.version 3 [cache device] dev.uuid 3bbe60ea-6c90-464f-a443-7f18d7951431 dev.sectors_per_block 1 dev.sectors_per_bucket 1024 dev.cache.first_sector 1024 dev.cache.cache_sectors 66003968 dev.cache.total_sectors 66004992 dev.cache.discard no dev.cache.pos 0 cset.uuid 0e8ea8ea-9d8d-4f0e-b01c-b3f437fe3114 root@server:/mnt# bcache-super-show /dev/sdb1 sb.magic ok sb.first_sector 8 [match] sb.csum C39910AE9C093EBE [match] sb.version 1 [backing device] dev.uuid dff5307a-3994-4396-90d8-410a207f7426 dev.sectors_per_block 1 dev.sectors_per_bucket 1024 dev.data.first_sector 16 dev.data.cache_mode 0 [writethrough] dev.data.cache_state 1 [clean] cset.uuid 0e8ea8ea-9d8d-4f0e-b01c-b3f437fe3114 root@server:/mnt# dmesg [ 7923.176147] INFO: task sync:5536 blocked for more than 120 seconds. [ 7923.176159] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 7923.176164] sync D ffff8800d2a97760 0 5536 8091 0x00000000 [ 7923.176174] ffff8800d2a97760 0000000000000082 ffff88011fbf4760 ffff8800d7a09b80 [ 7923.176183] 0000000000012dc0 ffff8800aa977fd8 ffff8800aa977fd8 ffff8800d2a97760 [ 7923.176190] ffff88011b29d8a8 ffff88011fc12dc0 ffff8800d2a97760 ffff8800aa977da0 [ 7923.176197] Call Trace: [ 7923.176215] [] ? __lock_page+0x66/0x66 [ 7923.176228] [] ? io_schedule+0x56/0x6c [ 7923.176236] [] ? sleep_on_page+0x7/0xb [ 7923.176244] [] ? __wait_on_bit+0x3e/0x75 [ 7923.176252] [] ? find_get_pages_tag+0xe7/0x121 [ 7923.176260] [] ? wait_on_page_bit+0x6e/0x73 [ 7923.176269] [] ? autoremove_wake_function+0x2a/0x2a [ 7923.176277] [] ? filemap_fdatawait_range+0x66/0xfe [ 7923.176287] [] ? should_resched+0x5/0x23 [ 7923.176294] [] ? __wait_for_common+0x108/0x11b [ 7923.176301] [] ? try_to_wake_up+0x199/0x199 [ 7923.176311] [] ? sync_inodes_sb+0x140/0x18c [ 7923.176320] [] ? fdatawrite_one_bdev+0xd/0xd [ 7923.176330] [] ? iterate_supers+0x63/0xb5 [ 7923.176337] [] ? sys_sync+0x2e/0x81 [ 7923.176347] [] ? system_call_fastpath+0x16/0x1b