Hi, I'm experiencing serious temporary kernel hangs on a Supermicro X8SIE machine with an aacraid controller. I'm suspecting the latter one since the issue looks similar to: ========================================================================= commit cf16123c9c8e346ed1dd171295a678d77648d7f8 Author: Vasily Averin <vvs@xxxxxxxxxxxxx> Date: Fri Nov 11 13:42:16 2011 +0400 [SCSI] aacraid: controller hangs if kernel uses non-default ASPM policy ========================================================================= The problem is triggered by regular nightly backup rsyncs and is reproducible: The below kernel traces happen _once_ around the first nightly rsync after booting. During following days, no further traces are written, but the machine feels generally slow. I/O during the rsync runs leading to load values >30. Both the AAC RAID and the Supermicro board have already been replaced (with same models) but the problem is still there. ========================================================================= [29040.293627] INFO: task flush-8:0:1074 blocked for more than 120 seconds. [29040.293676] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [29040.293727] flush-8:0 D ffff880131ffcfc0 0 1074 2 0x00000000 [29040.293730] ffff880131ffcfc0 0000000000000046 ffff880100000000 ffff880134f480c0 [29040.293733] 0000000000013440 ffff8801319f9fd8 ffff8801319f9fd8 0000000000013440 [29040.293735] ffff880131ffcfc0 ffff8801319f8010 ffff8801319f9810 00000001319f9810 [29040.293738] Call Trace: [29040.293746] [<ffffffff8134b6dc>] ? io_schedule+0x84/0xc3 [29040.293750] [<ffffffff811a16f1>] ? get_request_wait+0x104/0x199 [29040.293753] [<ffffffff81061b25>] ? wake_up_bit+0x20/0x20 [29040.293756] [<ffffffff811a1bc8>] ? blk_queue_bio+0x17a/0x2ce [29040.293759] [<ffffffff81129076>] ? T.1020+0x17/0x17 [29040.293761] [<ffffffff811a106e>] ? generic_make_request+0x8e/0xcd [29040.293763] [<ffffffff811a1186>] ? submit_bio+0xd9/0xf7 [29040.293765] [<ffffffff81129076>] ? T.1020+0x17/0x17 [29040.293767] [<ffffffff8112be2d>] ? bio_alloc_bioset+0x44/0xb3 [29040.293770] [<ffffffff81127cd1>] ? submit_bh+0xe5/0x105 [29040.293772] [<ffffffff8112a360>] ? __block_write_full_page+0x1dd/0x2b5 [29040.293774] [<ffffffff8112c354>] ? I_BDEV+0x8/0x8 [29040.293778] [<ffffffff810c31e2>] ? __writepage+0xa/0x21 [29040.293781] [<ffffffff810c42d5>] ? write_cache_pages+0x226/0x31e [29040.293783] [<ffffffff810c31d8>] ? set_page_dirty+0x61/0x61 [29040.293785] [<ffffffff810c440b>] ? generic_writepages+0x3e/0x55 [29040.293790] [<ffffffff81122b15>] ? writeback_single_inode+0x178/0x35e [29040.293792] [<ffffffff81123015>] ? writeback_sb_inodes+0x169/0x1ff [29040.293794] [<ffffffff81123118>] ? __writeback_inodes_wb+0x6d/0xab [29040.293796] [<ffffffff8112333f>] ? wb_writeback+0x128/0x222 [29040.293798] [<ffffffff8134b36d>] ? __schedule+0x5a0/0x5cd [29040.293800] [<ffffffff811235b2>] ? wb_do_writeback+0x179/0x1de [29040.293805] [<ffffffff81053dcb>] ? del_timer_sync+0x34/0x3e [29040.293807] [<ffffffff811236da>] ? bdi_writeback_thread+0xc3/0x1fe [29040.293809] [<ffffffff81123617>] ? wb_do_writeback+0x1de/0x1de [29040.293811] [<ffffffff81123617>] ? wb_do_writeback+0x1de/0x1de [29040.293813] [<ffffffff810616e9>] ? kthread+0x7a/0x82 [29040.293816] [<ffffffff81354eb4>] ? kernel_thread_helper+0x4/0x10 [29040.293818] [<ffffffff8106166f>] ? kthread_worker_fn+0x147/0x147 [29040.293820] [<ffffffff81354eb0>] ? gs_change+0x13/0x13 ========================================================================= See also full kernel log at http://antcom.de/linux-aacraid-supermicro-X8SIE.dmesg Please redirect me if you suspect the problem elsewhere. Thanks in advance, Roland -- To unsubscribe from this list: send the line "unsubscribe linux-scsi" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html