From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from cuda.sgi.com (cuda1.sgi.com [192.48.157.11]) by oss.sgi.com (8.14.3/8.14.3/SuSE Linux 0.8) with ESMTP id p9FC0AgS103560 for ; Sat, 15 Oct 2011 07:00:15 -0500 Received: from lo.gmane.org (localhost [127.0.0.1]) by cuda.sgi.com (Spam Firewall) with ESMTP id AA4401475DA1 for ; Sat, 15 Oct 2011 05:07:46 -0700 (PDT) Received: from lo.gmane.org (lo.gmane.org [80.91.229.12]) by cuda.sgi.com with ESMTP id BxuzHjCoLgwObHAa for ; Sat, 15 Oct 2011 05:07:46 -0700 (PDT) Received: from list by lo.gmane.org with local (Exim 4.69) (envelope-from ) id 1RF2uN-0004J5-GI for linux-xfs@oss.sgi.com; Sat, 15 Oct 2011 14:00:07 +0200 Received: from r1.spray.net.pl ([83.143.40.194]) by main.gmane.org with esmtp (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Sat, 15 Oct 2011 14:00:07 +0200 Received: from gmane by r1.spray.net.pl with local (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Sat, 15 Oct 2011 14:00:07 +0200 From: Marcin M Subject: tasks hangs in D state while writing to xfs Date: Sat, 15 Oct 2011 13:54:15 +0200 Message-ID: Mime-Version: 1.0 List-Id: XFS Filesystem from SGI List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: text/plain; charset="iso-8859-2" Content-Transfer-Encoding: quoted-printable Sender: xfs-bounces@oss.sgi.com Errors-To: xfs-bounces@oss.sgi.com To: linux-xfs@oss.sgi.com Hello! I've noticed strange problem with xfs. I've created filesystem with blocksize=3D1024 and log as small as it possible. Next i'm copying files using rsync, after sometime rsync hangs in D state. So i can't kill it, i've got to reboot hosts. In dmesg i'm getting such messages: [ 1320.535833] INFO: task flush-8:0:1173 blocked for more than 120 seconds. [ 1320.535834] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 1320.535836] flush-8:0 D 0000000000000000 0 1173 2 0x00000000 [ 1320.535838] ffff88001e1a0000 0000000000000046 ffff880000000000 0000000000000000 [ 1320.535841] ffff88001ed14a40 000000000000cd80 ffff88001e1a03f0 ffffffff81030fa0 [ 1320.535843] 000000000000cd80 ffff88001e1a03f0 ffff88001e1a03f0 000000000000cd80 [ 1320.535845] Call Trace: [ 1320.535847] [] ? check_preempt_wakeup+0x140/0x140 [ 1320.535854] [] ? xfs_bmap_search_multi_extents+0xab/0x120 [xfs] [ 1320.535860] [] ? xfs_bmap_search_extents+0x68/0x100 [xfs] [ 1320.535868] [] ? xlog_grant_log_space+0x16b/0x340 [xfs] [ 1320.535874] [] ? kmem_zone_zalloc+0x32/0x50 [xfs] [ 1320.535876] [] ? try_to_wake_up+0x280/0x280 [ 1320.535884] [] ? xfs_trans_reserve+0x9b/0x200 [xfs] [ 1320.535891] [] ? xfs_trans_alloc+0x97/0xb0 [xfs] [ 1320.535898] [] ? xfs_iomap_write_allocate+0x20b/0x320 [xfs] [ 1320.535907] [] ? xfs_map_blocks+0x18f/0x1c0 [xfs] [ 1320.535914] [] ? xfs_vm_writepage+0x1ae/0x4a0 [xfs] [ 1320.535916] [] ? __writepage+0x17/0x40 [ 1320.535918] [] ? write_cache_pages+0x1ca/0x400 [ 1320.535920] [] ? set_page_dirty+0x80/0x80 [ 1320.535922] [] ? generic_writepages+0x48/0x80 [ 1320.535926] [] ? writeback_single_inode+0x102/0x260 [ 1320.535928] [] ? writeback_sb_inodes+0xf6/0x1a0 [ 1320.535930] [] ? writeback_inodes_wb+0x8b/0x140 [ 1320.535932] [] ? wb_writeback+0x283/0x2f0 [ 1320.535935] [] ? wb_do_writeback+0x94/0x1e0 [ 1320.535938] [] ? run_timer_softirq+0x240/0x240 [ 1320.535940] [] ? bdi_writeback_thread+0x82/0x150 [ 1320.535942] [] ? wb_do_writeback+0x1e0/0x1e0 [ 1320.535944] [] ? wb_do_writeback+0x1e0/0x1e0 [ 1320.535946] [] ? kthread+0xa2/0xb0 [ 1320.535948] [] ? kernel_thread_helper+0x9/0x20 [ 1320.535950] [] ? retint_restore_args+0x6/0xd [ 1320.535952] [] ? kthread_worker_fn+0x140/0x140 [ 1320.535954] [] ? gs_change+0x1b/0x1b It looks it's reproducible problem on my host. Now i'm using kernel 3.0.4-hardened-r5 but this happens with older kernels too. I did echo "t" >/proc/sysrq and i got: [...] [ 3038.290721] xfsbufd/sda11 S ffff88001ecf6180 0 3892 2 0x00000000 [ 3038.290721] ffff880019562880 0000000000000046 0000000003b4ceaf ffff880000000001 [ 3038.290721] ffff88001e33af40 000000000000cd80 ffff880019562c70 ffffffff81030fa0 [ 3038.290721] 000000000000cd80 ffff880019562c70 ffff880019562c70 000000000000cd80 [ 3038.290721] Call Trace: [ 3038.290721] [] ? check_preempt_wakeup+0x140/0x140 [ 3038.290721] [] ? sd_prep_fn+0x15c/0xac0 [ 3038.290721] [] ? blk_peek_request+0xb4/0x1f0 [ 3038.290721] [] ? schedule_timeout+0x152/0x230 [ 3038.290721] [] ? run_timer_softirq+0x240/0x240 [ 3038.290721] [] ? xfsbufd+0x8f/0x120 [xfs] [ 3038.290721] [] ? xfs_bdstrat_cb+0x60/0x60 [xfs] [ 3038.290721] [] ? xfs_bdstrat_cb+0x60/0x60 [xfs] [ 3038.290721] [] ? kthread+0xa2/0xb0 [ 3038.290721] [] ? kernel_thread_helper+0x9/0x20 [ 3038.290721] [] ? retint_restore_args+0x6/0xd [ 3038.290721] [] ? kthread_worker_fn+0x140/0x140 [ 3038.290721] [] ? gs_change+0x1b/0x1b [ 3038.290721] rsync D 0000000000000000 0 3957 1 0x00000004 [ 3038.290721] ffff880019559440 0000000000000086 0000000000000400 0000000000000000 [ 3038.290721] ffff88001820b600 000000000000cd80 ffff880019559830 ffffffff81030fa0 [ 3038.290721] 000000000000cd80 ffff880019559830 ffff880019559830 000000000000cd80 [ 3038.290721] Call Trace: [ 3038.290721] [] ? check_preempt_wakeup+0x140/0x140 [ 3038.290721] [] ? account_page_dirtied+0x74/0xa0 [ 3038.290721] [] ? __block_commit_write.clone.17+0xa9/0xf0 [ 3038.290721] [] ? xlog_grant_log_space+0x236/0x340 [xfs] [ 3038.290721] [] ? try_to_wake_up+0x280/0x280 [ 3038.290721] [] ? xfs_trans_reserve+0x9b/0x200 [xfs] [ 3038.290721] [] ? xfs_trans_alloc+0x97/0xb0 [xfs] [ 3038.290721] [] ? xfs_rename+0x156/0x710 [xfs] [ 3038.290721] [] ? complete_walk+0x71/0x120 [ 3038.290721] [] ? xfs_vn_rename+0x60/0x70 [xfs] [ 3038.290721] [] ? vfs_rename+0x3c6/0x410 [ 3038.290721] [] ? d_lookup+0x2e/0x60 [ 3038.290721] [] ? __lookup_hash+0xab/0x1c0 [ 3038.290721] [] ? sys_renameat+0x286/0x2e0 [ 3038.290721] [] ? xfs_iunlock+0x4b/0xa0 [xfs] [ 3038.290721] [] ? xfs_setattr+0x3d9/0x7c0 [xfs] [ 3038.290721] [] ? notify_change+0x27c/0x3a0 [ 3038.290721] [] ? dput+0x3b/0x190 [ 3038.290721] [] ? system_call_fastpath+0x16/0x1b [ 3038.290721] [] ? system_call_after_swapgs+0x17/0x63 [ 3038.290721] [] ? system_call_after_swapgs+0x17/0x63 3038.290721] [] ? system_call_after_swapgs+0x17/0x63 If i can do some more debug pleas let me know, i'll prepare it. Thanks for help. Marcin Miros=B3aw _______________________________________________ xfs mailing list xfs@oss.sgi.com http://oss.sgi.com/mailman/listinfo/xfs