RAID5 + ext4 on SSD crashes during mkfs.ext4

[Vadim Tkachenko]

Ubuntu 12.04.3

Kernel
3.8.0-31-generic #46~precise1-Ubuntu SMP

I have 3 SSD : Crucial M500 960GB, and I am trying to create mdadm RAID5 + ext4 fs on this.

mdadm:

mdadm --create /dev/md5 --level=5 --raid-devices=3 /dev/sdd /dev/sde /dev/sdg

next
mkfs.ext4 /dev/md5
and there system crashes :

Oct 2 12:06:10 cisco1 kernel: [ 214.583650] Process md5_raid5 (pid: 2190, threadinfo ffff885b5c540000, task ffff882b79e0ae80)
Oct 2 12:06:10 cisco1 kernel: [ 214.604457] Stack:
Oct 2 12:06:10 cisco1 kernel: [ 214.615179] ffff885b63384900 ffff885b628348d0 ffff885b5c541b08 ffffffff814af18d
Oct 2 12:06:10 cisco1 kernel: [ 214.635227] ffff885b628348d0 ffff885b628348d0 ffff882b767aa000 ffff885b628348d0
Oct 2 12:06:10 cisco1 kernel: [ 214.655206] ffff885b63384900 ffff882b767aa000 ffff885b62c70000 000000000007f000
Oct 2 12:06:10 cisco1 kernel: [ 214.675234] Call Trace:
Oct 2 12:06:10 cisco1 kernel: [ 214.684923] [<ffffffff814af18d>] scsi_init_io+0x3d/0x150
Oct 2 12:06:10 cisco1 kernel: [ 214.694646] [<ffffffff814af452>] scsi_setup_blk_pc_cmnd.part.33+0x42/0xe0
Oct 2 12:06:10 cisco1 kernel: [ 214.704457] [<ffffffff814af51f>] scsi_setup_blk_pc_cmnd+0x2f/0x40
Oct 2 12:06:10 cisco1 kernel: [ 214.714951] [<ffffffff814c041f>] sd_setup_discard_cmnd+0x13f/0x250
Oct 2 12:06:10 cisco1 kernel: [ 214.724654] [<ffffffff814c05c8>] sd_prep_fn+0x98/0xb00
Oct 2 12:06:10 cisco1 kernel: [ 214.733974] [<ffffffff8134a175>] ? deadline_remove_request.isra.3+0x55/0x90
Oct 2 12:06:10 cisco1 kernel: [ 214.743236] [<ffffffffa0256c60>] ? ops_run_io+0x2d0/0x6e0 [raid456]
Oct 2 12:06:10 cisco1 kernel: [ 214.752226] [<ffffffff813322fa>] blk_peek_request+0xba/0x220
Oct 2 12:06:10 cisco1 kernel: [ 214.761226] [<ffffffff814af5df>] scsi_request_fn+0x4f/0x450
Oct 2 12:06:10 cisco1 kernel: [ 214.769925] [<ffffffff8132b757>] __blk_run_queue+0x37/0x50
Oct 2 12:06:10 cisco1 kernel: [ 214.778795] [<ffffffff8132de31>] queue_unplugged+0x41/0xd0
Oct 2 12:06:10 cisco1 kernel: [ 214.787494] [<ffffffff8133278d>] blk_flush_plug_list+0x12d/0x220
Oct 2 12:06:10 cisco1 kernel: [ 214.796371] [<ffffffff81332898>] blk_finish_plug+0x18/0x50
Oct 2 12:06:10 cisco1 kernel: [ 214.805061] [<ffffffffa025b3a7>] raid5d+0x1f7/0x210 [raid456]
Oct 2 12:06:10 cisco1 kernel: [ 214.813972] [<ffffffff81568bdd>] md_thread+0x11d/0x170
Oct 2 12:06:10 cisco1 kernel: [ 214.822322] [<ffffffff8107fd90>] ? add_wait_queue+0x60/0x60
Oct 2 12:06:10 cisco1 kernel: [ 214.830519] [<ffffffff81568ac0>] ? md_rdev_init+0x140/0x140
Oct 2 12:06:10 cisco1 kernel: [ 214.838592] [<ffffffff8107f1d0>] kthread+0xc0/0xd0
Oct 2 12:06:10 cisco1 kernel: [ 214.846706] [<ffffffff8107f110>] ? flush_kthread_worker+0xb0/0xb0
Oct 2 12:06:10 cisco1 kernel: [ 214.854954] [<ffffffff816fcb2c>] ret_from_fork+0x7c/0xb0
Oct 2 12:06:10 cisco1 kernel: [ 214.863080] [<ffffffff8107f110>] ? flush_kthread_worker+0xb0/0xb0
Oct 2 12:06:10 cisco1 kernel: [ 214.870943] Code: 24 38 4c 89 e6 48 8b 13 e8 5f 7d e8 ff 3b 43 08 77 19 89 43 08 41 8b 44 24 54 89 43 10 31 c0 5b 41 5c 5d c3 b8 02 00 00 00 eb f4 <0f> 0b 66 66 66 66 66 66 2e 0f 1f 84 00 00 00 00 00 66 66 66 66
Oct 2 12:06:10 cisco1 kernel: [ 214.895823] RIP [<ffffffff814af13f>] scsi_init_sgtable+0x5f/0x70
Oct 2 12:06:10 cisco1 kernel: [ 214.903879] RSP <ffff885b5c541aa8>
Oct 2 12:06:10 cisco1 kernel: [ 214.911791] ---[ end trace 783387391a8e7729 ]---
Oct 2 12:06:42 cisco1 kernel: [ 241.599296] ------------[ cut here ]------------

[Ubuntu Foundations Team Bug Bot (crichton)]

Thank you for taking the time to report this bug and helping to make Ubuntu better. It seems that your bug report is not filed about a specific source package though, rather it is just filed against Ubuntu in general. It is important that bug reports be filed about source packages so that people interested in the package can find the bugs about it. You can find some hints about determining what package your bug might be about at https://wiki.ubuntu.com/Bugs/FindRightPackage. You might also ask for help in the #ubuntu-bugs irc channel on Freenode.

To change the source package that this bug is filed about visit https://bugs.launchpad.net/ubuntu/+bug/1234359/+editstatus and add the package name in the text box next to the word Package.

[This is an automated message. I apologize if it reached you inappropriately; please just reply to this message indicating so.]

[Vadim Tkachenko (vadim-tk)]

As stacktrace prompts I think this is ralated to TRIM operation.

When I use mkfs -t ext4 -E nodiscard /dev/md5 - there is no crash