[PATCH v5] btrfs: Handle delalloc error correctly to avoid ordered extent hang

[BUG] Reports about btrfs hang running btrfs/124 with default mount option and btrfs/125 with nospace_cache or space_cache=v2 mount options, with following backtrace. Call Trace: __schedule+0x2d4/0xae0 schedule+0x3d/0x90 btrfs_start_ordered_extent+0x160/0x200 [btrfs] ?

[PATCH v5] btrfs: Handle delalloc error correctly to avoid ordered extent hang

[BUG] Reports about btrfs hang running btrfs/124 with default mount option and btrfs/125 with nospace_cache or space_cache=v2 mount options, with following backtrace. Call Trace: __schedule+0x2d4/0xae0 schedule+0x3d/0x90 btrfs_start_ordered_extent+0x160/0x200 [btrfs] ?

Re: "parent transid verify failed" out of blue sky

At 02/28/2017 02:51 AM, Andrei Borzenkov wrote: This is VM under QEMU/KVM running openSUSE Tumbleweed. I boot it infrequently for short time to test something. Last time it installed quite a lot of updates including kernel (I think 4.9.11 was the last version); I do not remember whether I

Re: [PATCH v4] btrfs: Handle delalloc error correctly to avoid ordered extent deadlock

At 02/28/2017 12:14 AM, Filipe Manana wrote: On Fri, Feb 24, 2017 at 2:06 AM, Qu Wenruo wrote: If run btrfs/125 with nospace_cache or space_cache=v2 mount option, btrfs will block with the following backtrace: Happens with btrfs/124 without any mount options too.

Re: Low IOOP Performance

[ ... ] > I have a 6-device test setup at home and I tried various setups > and I think I got rather better than that. * 'raid1' profile: soft# btrfs fi df /mnt/sdb5 Data, RAID1:

Re: Low IOOP Performance

>>> On Mon, 27 Feb 2017 22:11:29 +, p...@btrfs.list.sabi.co.uk (Peter >>> Grandi) said: > [ ... ] >> I have a 6-device test setup at home and I tried various setups >> and I think I got rather better than that. [ ... ] > That's a range of 700-1300 4KiB random mixed-rw IOPS, Rerun with 1M

Re: Low IOOP Performance

On 2017-02-27 14:15, John Marrett wrote: Liubo correctly identified direct IO as a solution for my test performance issues, with it in use I achieved 908 read and 305 write, not quite as fast as ZFS but more than adequate for my needs. I then applied Peter's recommendation of switching to raid10

Re: BTRFS hybrid system setup issues

Hi, On further testing I found that many of the functionality works fine (most of the core functionality). One function I could not get to work with this x86_64 kernel and i386 userland is btrfs subvolme functionality works; btrfsck works; scrub works fine. BUT --- $ sudo btrfs send aa >

Re: Low IOOP Performance

Liubo correctly identified direct IO as a solution for my test performance issues, with it in use I achieved 908 read and 305 write, not quite as fast as ZFS but more than adequate for my needs. I then applied Peter's recommendation of switching to raid10 and tripled performance again up to 3000

"parent transid verify failed" out of blue sky

This is VM under QEMU/KVM running openSUSE Tumbleweed. I boot it infrequently for short time to test something. Last time it installed quite a lot of updates including kernel (I think 4.9.11 was the last version); I do not remember whether I rebooted it after that. Today I booted it to check

Re: [PATCH v4] btrfs: Handle delalloc error correctly to avoid ordered extent deadlock

On Mon, Feb 27, 2017 at 4:14 PM, Filipe Manana wrote: Also, forgot to mention before, looking at the subject, the term deadlock is not correct, as it's a hang. A deadlock is when a task is trying to acquire a resource (typically a lock) that is already held by some other

Re: assertion failed: last_size == new_size, file: fs/btrfs/inode.c

On Sun, Feb 26, 2017 at 07:18:42PM -0500, Dave Jones wrote: > Hitting this fairly frequently.. I'm not sure if this is the same bug I've > been hitting occasionally since 4.9. The assertion looks new to me at least. > It was recently introduced by my commit and used to catch data loss at

Re: assertion failed: last_size == new_size, file: fs/btrfs/inode.c

On Mon, Feb 27, 2017 at 07:53:48AM -0800, Liu Bo wrote: > On Sun, Feb 26, 2017 at 07:18:42PM -0500, Dave Jones wrote: > > Hitting this fairly frequently.. I'm not sure if this is the same bug I've > > been hitting occasionally since 4.9. The assertion looks new to me at > > least. > > > >

Re: Low IOOP Performance

[ ... ] > a ten disk raid1 using 7.2k 3 TB SAS drives Those are really low IOPS-per-TB devices, but good choice for SAS, as they will have SCT/ERC. > and used aio to test IOOP rates. I was surprised to measure > 215 read and 72 write IOOPs on the clean new filesystem. For that you really want

Re: [PATCH v4] btrfs: Handle delalloc error correctly to avoid ordered extent deadlock

On Fri, Feb 24, 2017 at 2:06 AM, Qu Wenruo wrote: > If run btrfs/125 with nospace_cache or space_cache=v2 mount option, > btrfs will block with the following backtrace: Happens with btrfs/124 without any mount options too. > > Call Trace: > __schedule+0x2d4/0xae0 >

Re: Low IOOP Performance

On Mon, Feb 27, 2017 at 08:20:49AM -0500, John Marrett wrote: > In preparation for a system and storage upgrade I performed some btrfs > performance tests. I created a ten disk raid1 using 7.2k 3 TB SAS > drives and used aio to test IOOP rates. I was surprised to measure 215 > read and 72 write

Re: [PATCH 0/3] introduce type based delalloc metadata reserve to fix some false enospc issues

Hi, can please anybody comment on that one? Josef? Chris? I still need those patches to be able to let btrfs run for more than 24hours without ENOSPC issues. Greets, Stefan Am 27.02.2017 um 08:22 schrieb Qu Wenruo: > > > At 02/25/2017 04:23 PM, Stefan Priebe - Profihost AG wrote: >> Dear Qu,

Low IOOP Performance

In preparation for a system and storage upgrade I performed some btrfs performance tests. I created a ten disk raid1 using 7.2k 3 TB SAS drives and used aio to test IOOP rates. I was surprised to measure 215 read and 72 write IOOPs on the clean new filesystem. Sequential writes ran as expected at

Re: List of corruption cases for scrub

On Mon, Feb 27, 2017 at 11:40:31AM +0800, Qu Wenruo wrote: > > > At 02/24/2017 10:32 AM, Lakshmipathi.G wrote: > >Hi. > > > >I tried to a create list of corruption test scenarios for scrubbing process > >with RAID5. > >Here's the list: >