Hi Kent, Could you please comment ? I want to know if I am doing something fundamentally wrong or there is a problem using bcache. Any pointer/help is of great help. Thanks Neo On Wed, Aug 14, 2013 at 5:50 PM, kernel neophyte <neophyte.hacker001@xxxxxxxxx> wrote: > Hi Kent, > > I am an independent researcher, researching on next generation memory. > Thanks a lot for Bcache this was badly needed in linux :-). In future > too I am willing to bet bcache is going to be an very important part > of linux. > > The problem I am facing right now: > > during random write, Bcache comes to a halt (Deadlock ?) and system > becomes flakey. (its impossible to kill the process and issue a > reboot). > > How it is set up > > Total Dram is : 192G > Free Ram available is 32G > > RamDisk of 150G acting as a cache > > Dram<->RamDisk<->HDD > > commands used: > make-bcache -B -w 4096 /dev/sda3 > make-bcache -C -w 4096 /dev/rxd1 (this is the ramdisk) > > echo /dev/sda3 > /sys/fs/bcache/register > echo /dev/rxd1 > /sys/fs/bcache/register > echo 1e26e5ca-5cb9-4c5a-ad7e-3c787524a9dc > /sys/block/bcache0/bcache/attach > > echo writeback > /sys/block/bcache0/bcache/cache_mode > echo 0 > /sys/block/bcache0/bcache/sequential_cutoff > echo 0 > /sys/fs/bcache/1e26e5ca-5cb9-4c5a-ad7e-3c787524a9dc/congested_read_threshold_us > echo 0 > /sys/fs/bcache/1e26e5ca-5cb9-4c5a-ad7e-3c787524a9dc/congested_write_threshold_us > > mkfs -b 4096 -t ext4 /dev/bcache0 > mount /dev/bcache0 /mnt/fastcache/ > > iozone -s 80g -i 0 -i 1 -i 2 -r 4k -I -b > /home/neo/bcache.80g.4k.ext4.csv -f /mnt/fastcache/test1 > > > The Kernel is 3.11.0-rc5 (custom. It includes all commits from > bcache-dev tree from bcache: Fix a dumb journal discard bug > (eeea65848d4305836b9c397169515b2ab0c2a034) till bcache: Zero less > memory (824e8155faa5afc2a4984378aeed37b343bd2876)) > > [ 3922.208949] bcache: register_bdev() registered backing device sda3 > [ 3932.517255] bcache: run_cache_set() invalidating existing data > [ 3932.535187] bcache: register_cache() registered cache device rxd1 > [ 3977.155432] bcache: bch_cached_dev_attach() Caching sda3 as bcache0 > on set 92a817d6-4283-4041-9c9c-2635e0fe9253 > [ 6962.658113] INFO: task kswapd0:51 blocked for more than 120 seconds. > [ 6962.658123] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" > disables this message. > [ 6962.658129] kswapd0 D ffffffff8180fbc0 0 51 2 0x00000000 > [ 6962.658137] ffff882fa49b5b28 0000000000000046 ffff882fa49b5b68 > ffffffff8108a4d9 > [ 6962.658143] ffff882f8a38c590 ffff882fa49b5fd8 ffff882fa49b5fd8 > ffff882fa49b5fd8 > [ 6962.658148] ffff882fa6aa8000 ffff882f8a38c590 ffff882fa49b5b18 > ffff882e4b5e0d98 > [ 6962.658153] Call Trace: > [ 6962.658167] [<ffffffff8108a4d9>] ? find_busiest_group+0x39/0x4a0 > [ 6962.658176] [<ffffffff816e2cd9>] schedule+0x29/0x70 > [ 6962.658182] [<ffffffff816e2fbe>] schedule_preempt_disabled+0xe/0x10 > [ 6962.658188] [<ffffffff816e1272>] __mutex_lock_slowpath+0x112/0x1b0 > [ 6962.658194] [<ffffffff816e076a>] mutex_lock+0x2a/0x41 > [ 6962.658202] [<ffffffff8152af05>] bch_mca_shrink+0x1b5/0x2f0 > [ 6962.658211] [<ffffffff8118c972>] ? prune_super+0x162/0x1b0 > [ 6962.658218] [<ffffffff8113b474>] shrink_slab+0x154/0x300 > [ 6962.658223] [<ffffffff8108b52b>] ? idle_balance+0xeb/0x150 > [ 6962.658230] [<ffffffff8113e934>] balance_pgdat+0x494/0x5d0 > [ 6962.658235] [<ffffffff816e0193>] ? schedule_timeout+0x133/0x250 > [ 6962.658240] [<ffffffff8113ebdf>] kswapd+0x16f/0x480 > [ 6962.658248] [<ffffffff81070cf0>] ? add_wait_queue+0x60/0x60 > [ 6962.658252] [<ffffffff8113ea70>] ? balance_pgdat+0x5d0/0x5d0 > [ 6962.658258] [<ffffffff810704f0>] kthread+0xc0/0xd0 > [ 6962.658263] [<ffffffff81070430>] ? flush_kthread_worker+0xb0/0xb0 > [ 6962.658271] [<ffffffff816ec89c>] ret_from_fork+0x7c/0xb0 > [ 6962.658276] [<ffffffff81070430>] ? flush_kthread_worker+0xb0/0xb0 > [ 6962.658286] INFO: task bcache_writebac:5046 blocked for more than > 120 seconds. > [ 6962.658290] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" > disables this message. > [ 6962.658295] bcache_writebac D ffffffff8180fbc0 0 5046 2 0x00000000 > [ 6962.658300] ffff881955e31cd8 0000000000000046 0000000000000001 > 0000000000000001 > [ 6962.658304] ffff882f8a740000 ffff881955e31fd8 ffff881955e31fd8 > ffff881955e31fd8 > [ 6962.658309] ffff882fa6aa9730 ffff882f8a740000 ffff882f8a740000 > ffff882f8a740000 > [ 6962.658314] Call Trace: > [ 6962.658320] [<ffffffff816e2cd9>] schedule+0x29/0x70 > [ 6962.658326] [<ffffffff816e3a15>] rwsem_down_write_failed+0xf5/0x1a0 > [ 6962.658335] [<ffffffff81343e43>] call_rwsem_down_write_failed+0x13/0x20 > [ 6962.658340] [<ffffffff816e16a1>] ? down_write+0x31/0x40 > [ 6962.658347] [<ffffffff81535362>] bch_writeback_thread+0x62/0x7f0 > [ 6962.658353] [<ffffffff8108b52b>] ? idle_balance+0xeb/0x150 > [ 6962.658359] [<ffffffff81535300>] ? write_dirty+0xc0/0xc0 > [ 6962.658363] [<ffffffff810704f0>] kthread+0xc0/0xd0 > [ 6962.658368] [<ffffffff81070430>] ? flush_kthread_worker+0xb0/0xb0 > [ 6962.658374] [<ffffffff816ec89c>] ret_from_fork+0x7c/0xb0 > [ 6962.658378] [<ffffffff81070430>] ? flush_kthread_worker+0xb0/0xb0 > [ 6962.658383] INFO: task iozone:7406 blocked for more than 120 seconds. > [ 6962.658387] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" > disables this message. > [ 6962.658391] iozone D 0000000000000000 0 7406 7246 0x00000000 > [ 6962.658395] ffff8809dcfbb978 0000000000000082 ffff8809dcfbb938 > ffffffff8131187a > [ 6962.658400] ffff882f8c8b4590 ffff8809dcfbbfd8 ffff8809dcfbbfd8 > ffff8809dcfbbfd8 > [ 6962.658405] ffff882f8c8b1730 ffff882f8c8b4590 ffff8809dcfbb978 > ffff882fbf293c28 > [ 6962.658409] Call Trace: > [ 6962.658417] [<ffffffff8131187a>] ? generic_make_request+0xca/0x100 > [ 6962.658422] [<ffffffff816e2cd9>] schedule+0x29/0x70 > [ 6962.658427] [<ffffffff816e2daf>] io_schedule+0x8f/0xd0 > [ 6962.658437] [<ffffffff811c49bc>] do_blockdev_direct_IO+0x1a7c/0x1fb0 > [ 6962.658448] [<ffffffffa022ea70>] ? ext2_get_blocks+0xa60/0xa60 [ext2] > [ 6962.658454] [<ffffffff811c4f45>] __blockdev_direct_IO+0x55/0x60 > [ 6962.658460] [<ffffffffa022ea70>] ? ext2_get_blocks+0xa60/0xa60 [ext2] > [ 6962.658466] [<ffffffffa022f339>] ext2_direct_IO+0x79/0xe0 [ext2] > [ 6962.658471] [<ffffffffa022ea70>] ? ext2_get_blocks+0xa60/0xa60 [ext2] > [ 6962.658480] [<ffffffff81051426>] ? current_fs_time+0x16/0x60 > [ 6962.658487] [<ffffffff8112b1f6>] generic_file_direct_write+0xc6/0x180 > [ 6962.658492] [<ffffffff8112b58d>] __generic_file_aio_write+0x2dd/0x3b0 > [ 6962.658497] [<ffffffff816e0674>] ? mutex_unlock+0x14/0x20 > [ 6962.658502] [<ffffffff8112b6c9>] generic_file_aio_write+0x69/0xd0 > [ 6962.658507] [<ffffffff8118866a>] do_sync_write+0x7a/0xb0 > [ 6962.658512] [<ffffffff8118949e>] vfs_write+0xce/0x200 > [ 6962.658518] [<ffffffff811a4d60>] ? fget_light+0x70/0xd0 > [ 6962.658523] [<ffffffff811899a2>] SyS_write+0x52/0xa0 > [ 6962.658529] [<ffffffff816ec942>] system_call_fastpath+0x16/0x1b > [ 6962.658533] INFO: task kworker/u64:1:7435 blocked for more than 120 seconds. > [ 6962.658538] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" > disables this message. > [ 6962.658542] kworker/u64:1 D ffffffff8180fbc0 0 7435 2 0x00000000 > [ 6962.658554] Workqueue: writeback bdi_writeback_workfn (flush-252:0) > [ 6962.658557] ffff8818427955a0 0000000000000046 ffff882f90c15cc0 > ffff881842795548 > [ 6962.658562] ffff882f90c15cc0 ffff881842795fd8 ffff881842795fd8 > ffff881842795fd8 > [ 6962.658566] ffff882fa6aaae60 ffff882f90c15cc0 ffffffff8112c705 > ffff882f90c15cc0 > [ 6962.658571] Call Trace: > [ 6962.658576] [<ffffffff8112c705>] ? mempool_alloc_slab+0x15/0x20 > [ 6962.658581] [<ffffffff816e2cd9>] schedule+0x29/0x70 > [ 6962.658587] [<ffffffff816e3b5d>] rwsem_down_read_failed+0x9d/0xf0 > [ 6962.658592] [<ffffffff81343e14>] call_rwsem_down_read_failed+0x14/0x30 > [ 6962.658598] [<ffffffff816e16d4>] ? down_read+0x24/0x2b > [ 6962.658602] [<ffffffff81539932>] cached_dev_make_request+0x752/0xf00 > [ 6962.658607] [<ffffffff813115f8>] ? generic_make_request_checks+0x1e8/0x3a0 > [ 6962.658612] [<ffffffff8131187a>] generic_make_request+0xca/0x100 > [ 6962.658617] [<ffffffff81311929>] submit_bio+0x79/0x160 > [ 6962.658622] [<ffffffff811be700>] ? bio_alloc_bioset+0xa0/0x1d0 > [ 6962.658627] [<ffffffff811b8ccf>] _submit_bh+0x13f/0x200 > [ 6962.658631] [<ffffffff811b8da0>] submit_bh+0x10/0x20 > [ 6962.658636] [<ffffffff811bc6c8>] __block_write_full_page+0x1d8/0x360 > [ 6962.658641] [<ffffffff811ba3c0>] ? end_buffer_async_read+0x130/0x130 > [ 6962.658645] [<ffffffff811bfc60>] ? I_BDEV+0x10/0x10 > [ 6962.658650] [<ffffffff811bfc60>] ? I_BDEV+0x10/0x10 > [ 6962.658655] [<ffffffff811bc91a>] block_write_full_page_endio+0xca/0x100 > [ 6962.658660] [<ffffffff811bc965>] block_write_full_page+0x15/0x20 > [ 6962.658665] [<ffffffff811c0648>] blkdev_writepage+0x18/0x20 > [ 6962.658673] [<ffffffff81133da7>] __writepage+0x17/0x40 > [ 6962.658678] [<ffffffff8113427e>] write_cache_pages+0x20e/0x460 > [ 6962.658686] [<ffffffff8122a636>] ? ext4_writepages+0x416/0xc70 > [ 6962.658691] [<ffffffff81133d90>] ? set_page_dirty_lock+0x60/0x60 > [ 6962.658697] [<ffffffff8113451a>] generic_writepages+0x4a/0x70 > [ 6962.658701] [<ffffffff81135d70>] do_writepages+0x20/0x40 > [ 6962.658707] [<ffffffff811b06d5>] __writeback_single_inode+0x45/0x290 > [ 6962.658712] [<ffffffff81089fb3>] ? update_sd_lb_stats+0x123/0x610 > [ 6962.658717] [<ffffffff811b195d>] writeback_sb_inodes+0x1ad/0x3d0 > [ 6962.658723] [<ffffffff811b1c1e>] __writeback_inodes_wb+0x9e/0xd0 > [ 6962.658728] [<ffffffff811b1ecb>] wb_writeback+0x27b/0x320 > [ 6962.658733] [<ffffffff811a3082>] ? get_nr_dirty_inodes+0x52/0x80 > [ 6962.658738] [<ffffffff811b200f>] wb_check_old_data_flush+0x9f/0xb0 > [ 6962.658744] [<ffffffff811b384c>] bdi_writeback_workfn+0x1bc/0x3e0 > [ 6962.658752] [<ffffffff810681e2>] ? __queue_delayed_work+0x92/0x1a0 > [ 6962.658772] [<ffffffffa008ff8d>] ? mlx4_sense_port+0x7d/0xc0 [mlx4_core] > [ 6962.658777] [<ffffffff81068724>] process_one_work+0x174/0x490 > [ 6962.658782] [<ffffffff810697eb>] worker_thread+0x11b/0x370 > [ 6962.658788] [<ffffffff810696d0>] ? manage_workers.isra.21+0x2d0/0x2d0 > [ 6962.658793] [<ffffffff810704f0>] kthread+0xc0/0xd0 > [ 6962.658798] [<ffffffff81070430>] ? flush_kthread_worker+0xb0/0xb0 > [ 6962.658803] [<ffffffff816ec89c>] ret_from_fork+0x7c/0xb0 > [ 6962.658808] [<ffffffff81070430>] ? flush_kthread_worker+0xb0/0xb0 > [ 6962.658812] INFO: task kworker/4:2:7469 blocked for more than 120 seconds. > [ 6962.658816] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" > disables this message. > [ 6962.658821] kworker/4:2 D ffffffff8180fea0 0 7469 2 0x00000000 > [ 6962.658829] Workqueue: bcache bch_data_insert_keys > [ 6962.658832] ffff88176c719658 0000000000000046 ffff88176c719678 > 0000000000000000 > [ 6962.658836] ffff882f8c8b1730 ffff88176c719fd8 ffff88176c719fd8 > ffff88176c719fd8 > [ 6962.658841] ffff882fa66e9730 ffff882f8c8b1730 ffff882f8c8b1730 > ffff882e4b5e0d98 > [ 6962.658845] Call Trace: > [ 6962.658851] [<ffffffff816e2cd9>] schedule+0x29/0x70 > [ 6962.658856] [<ffffffff816e2fbe>] schedule_preempt_disabled+0xe/0x10 > [ 6962.658862] [<ffffffff816e1272>] __mutex_lock_slowpath+0x112/0x1b0 > [ 6962.658867] [<ffffffff81147189>] ? zone_statistics+0x99/0xc0 > [ 6962.658872] [<ffffffff816e076a>] mutex_lock+0x2a/0x41 > [ 6962.658876] [<ffffffff8152af05>] bch_mca_shrink+0x1b5/0x2f0 > [ 6962.658881] [<ffffffff8118c972>] ? prune_super+0x162/0x1b0 > [ 6962.658886] [<ffffffff8113b474>] shrink_slab+0x154/0x300 > [ 6962.658892] [<ffffffff8107d258>] ? resched_task+0x68/0x70 > [ 6962.658898] [<ffffffff8107db85>] ? check_preempt_curr+0x75/0xa0 > [ 6962.658902] [<ffffffff811471c9>] ? fragmentation_index+0x19/0x70 > [ 6962.658908] [<ffffffff8113dfdf>] do_try_to_free_pages+0x1ef/0x440 > [ 6962.658913] [<ffffffff8113e3e4>] try_to_free_pages+0xe4/0x1a0 > [ 6962.658919] [<ffffffff81530c51>] ? __bch_bset_search+0x1d1/0x480 > [ 6962.658925] [<ffffffff81132f08>] __alloc_pages_nodemask+0x618/0x9a0 > [ 6962.658932] [<ffffffff8116e47a>] alloc_pages_current+0xba/0x170 > [ 6962.658937] [<ffffffff8112e50e>] __get_free_pages+0xe/0x40 > [ 6962.658942] [<ffffffff815287d3>] mca_data_alloc+0x73/0x1d0 > [ 6962.658946] [<ffffffff8152ab57>] mca_alloc+0x277/0x470 > [ 6962.658951] [<ffffffff81530e59>] ? __bch_bset_search+0x3d9/0x480 > [ 6962.658956] [<ffffffff8152b45e>] bch_btree_node_get+0x10e/0x280 > [ 6962.658961] [<ffffffff8152b822>] bch_btree_map_nodes_recurse+0xe2/0x170 > [ 6962.658966] [<ffffffff8152d3e0>] ? bch_btree_insert_node+0x2f0/0x2f0 > [ 6962.658971] [<ffffffff811c222a>] ? dio_bio_end_io+0x5a/0x90 > [ 6962.658977] [<ffffffff81086931>] ? update_curr+0x141/0x200 > [ 6962.658982] [<ffffffff8152e9ee>] __bch_btree_map_nodes+0x13e/0x1c0 > [ 6962.658987] [<ffffffff8152d3e0>] ? bch_btree_insert_node+0x2f0/0x2f0 > [ 6962.658992] [<ffffffff8153484f>] ? bch_journal+0x42f/0x4b0 > [ 6962.658997] [<ffffffff8152eb24>] bch_btree_insert+0xb4/0x120 > [ 6962.659003] [<ffffffff81537d9e>] bch_data_insert_keys+0x3e/0x160 > [ 6962.659008] [<ffffffff81068724>] process_one_work+0x174/0x490 > [ 6962.659013] [<ffffffff810697eb>] worker_thread+0x11b/0x370 > [ 6962.659018] [<ffffffff810696d0>] ? manage_workers.isra.21+0x2d0/0x2d0 > [ 6962.659023] [<ffffffff810704f0>] kthread+0xc0/0xd0 > [ 6962.659028] [<ffffffff81070430>] ? flush_kthread_worker+0xb0/0xb0 > [ 6962.659033] [<ffffffff816ec89c>] ret_from_fork+0x7c/0xb0 > [ 6962.659038] [<ffffffff81070430>] ? flush_kthread_worker+0xb0/0xb0 > [ 6962.659052] INFO: task kworker/0:32:7497 blocked for more than 120 seconds. > [ 6962.659056] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" > disables this message. > [ 6962.659061] kworker/0:32 D ffffffff8180fbc0 0 7497 2 0x00000000 > [ 6962.659067] Workqueue: events update_writeback_rate > [ 6962.659070] ffff882f80151cd0 0000000000000046 0000000000000000 > ffff882f80151d68 > [ 6962.659074] ffff88232d532e60 ffff882f80151fd8 ffff882f80151fd8 > ffff882f80151fd8 > [ 6962.659079] ffffffff81c10440 ffff88232d532e60 0000000000000002 > ffff88232d532e60 > [ 6962.659083] Call Trace: > [ 6962.659089] [<ffffffff816e2cd9>] schedule+0x29/0x70 > [ 6962.659094] [<ffffffff816e3b5d>] rwsem_down_read_failed+0x9d/0xf0 > [ 6962.659101] [<ffffffff8105a210>] ? internal_add_timer+0x20/0x50 > [ 6962.659107] [<ffffffff81343e14>] call_rwsem_down_read_failed+0x14/0x30 > [ 6962.659112] [<ffffffff816e16d4>] ? down_read+0x24/0x2b > [ 6962.659117] [<ffffffff81534bf0>] update_writeback_rate+0x30/0x230 > [ 6962.659123] [<ffffffff81068724>] process_one_work+0x174/0x490 > [ 6962.659128] [<ffffffff810697eb>] worker_thread+0x11b/0x370 > [ 6962.659133] [<ffffffff810696d0>] ? manage_workers.isra.21+0x2d0/0x2d0 > [ 6962.659137] [<ffffffff810704f0>] kthread+0xc0/0xd0 > [ 6962.659142] [<ffffffff81070430>] ? flush_kthread_worker+0xb0/0xb0 > [ 6962.659148] [<ffffffff816ec89c>] ret_from_fork+0x7c/0xb0 > [ 6962.659152] [<ffffffff81070430>] ? flush_kthread_worker+0xb0/0xb0 > [ 6962.659158] INFO: task kworker/u64:0:7535 blocked for more than 120 seconds. > [ 6962.659162] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" > disables this message. > [ 6962.659170] kworker/u64:0 D ffffffff8180fbc0 0 7535 2 0x00000000 > [ 6962.659176] Workqueue: bch_btree_io btree_node_write_work > [ 6962.659178] ffff8809d3e2f778 0000000000000046 00000000102985a0 > 0000000974b06800 > [ 6962.659183] ffff8806cc1bdcc0 ffff8809d3e2ffd8 ffff8809d3e2ffd8 > ffff8809d3e2ffd8 > [ 6962.659188] ffffffff81c10440 ffff8806cc1bdcc0 9000000000800000 > ffff882e4b5e0d98 > [ 6962.659192] Call Trace: > [ 6962.659198] [<ffffffff816e2cd9>] schedule+0x29/0x70 > [ 6962.659203] [<ffffffff816e2fbe>] schedule_preempt_disabled+0xe/0x10 > [ 6962.659208] [<ffffffff816e1272>] __mutex_lock_slowpath+0x112/0x1b0 > [ 6962.659213] [<ffffffff816e076a>] mutex_lock+0x2a/0x41 > [ 6962.659218] [<ffffffff8152af05>] bch_mca_shrink+0x1b5/0x2f0 > [ 6962.659223] [<ffffffff8118c972>] ? prune_super+0x162/0x1b0 > [ 6962.659228] [<ffffffff8113b474>] shrink_slab+0x154/0x300 > [ 6962.659233] [<ffffffff8107d258>] ? resched_task+0x68/0x70 > [ 6962.659239] [<ffffffff8107db85>] ? check_preempt_curr+0x75/0xa0 > [ 6962.659243] [<ffffffff811471c9>] ? fragmentation_index+0x19/0x70 > [ 6962.659248] [<ffffffff8113dfdf>] do_try_to_free_pages+0x1ef/0x440 > [ 6962.659253] [<ffffffff8113e3e4>] try_to_free_pages+0xe4/0x1a0 > [ 6962.659259] [<ffffffff81132f08>] __alloc_pages_nodemask+0x618/0x9a0 > [ 6962.659265] [<ffffffff8116e47a>] alloc_pages_current+0xba/0x170 > [ 6962.659270] [<ffffffff8112e50e>] __get_free_pages+0xe/0x40 > [ 6962.659275] [<ffffffff81531be8>] __btree_sort+0x48/0x230 > [ 6962.659280] [<ffffffff8153127c>] ? __bch_btree_iter_init+0x7c/0xc0 > [ 6962.659285] [<ffffffff81531f21>] bch_btree_sort_partial+0x101/0x120 > [ 6962.659290] [<ffffffff81528c20>] ? __btree_node_write_done+0x100/0x100 > [ 6962.659295] [<ffffffff81532088>] bch_btree_sort_lazy+0x68/0x90 > [ 6962.659300] [<ffffffff8152a5da>] bch_btree_node_write+0x36a/0x4a0 > [ 6962.659306] [<ffffffff8108b52b>] ? idle_balance+0xeb/0x150 > [ 6962.659311] [<ffffffff8106837c>] ? pwq_activate_delayed_work+0x4c/0xb0 > [ 6962.659316] [<ffffffff8152b097>] btree_node_write_work+0x57/0x80 > [ 6962.659320] [<ffffffff81068724>] process_one_work+0x174/0x490 > [ 6962.659326] [<ffffffff810697eb>] worker_thread+0x11b/0x370 > [ 6962.659331] [<ffffffff810696d0>] ? manage_workers.isra.21+0x2d0/0x2d0 > [ 6962.659335] [<ffffffff810704f0>] kthread+0xc0/0xd0 > [ 6962.659340] [<ffffffff81070430>] ? flush_kthread_worker+0xb0/0xb0 > [ 6962.659345] [<ffffffff816ec89c>] ret_from_fork+0x7c/0xb0 > [ 6962.659350] [<ffffffff81070430>] ? flush_kthread_worker+0xb0/0xb0 > > > [ 7082.658055] INFO: task kswapd0:51 blocked for more than 120 seconds. > [ 7082.658065] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" > disables this message. > [ 7082.658072] kswapd0 D ffffffff8180fbc0 0 51 2 0x00000000 > [ 7082.658078] ffff882fa49b5b28 0000000000000046 ffff882fa49b5b68 > ffffffff8108a4d9 > [ 7082.658083] ffff882f8a38c590 ffff882fa49b5fd8 ffff882fa49b5fd8 > ffff882fa49b5fd8 > [ 7082.658088] ffff882fa6aa8000 ffff882f8a38c590 ffff882fa49b5b18 > ffff882e4b5e0d98 > [ 7082.658093] Call Trace: > [ 7082.658103] [<ffffffff8108a4d9>] ? find_busiest_group+0x39/0x4a0 > [ 7082.658110] [<ffffffff816e2cd9>] schedule+0x29/0x70 > [ 7082.658116] [<ffffffff816e2fbe>] schedule_preempt_disabled+0xe/0x10 > [ 7082.658121] [<ffffffff816e1272>] __mutex_lock_slowpath+0x112/0x1b0 > [ 7082.658127] [<ffffffff816e076a>] mutex_lock+0x2a/0x41 > [ 7082.658132] [<ffffffff8152af05>] bch_mca_shrink+0x1b5/0x2f0 > [ 7082.658138] [<ffffffff8118c972>] ? prune_super+0x162/0x1b0 > [ 7082.658144] [<ffffffff8113b474>] shrink_slab+0x154/0x300 > [ 7082.658149] [<ffffffff8108b52b>] ? idle_balance+0xeb/0x150 > [ 7082.658155] [<ffffffff8113e934>] balance_pgdat+0x494/0x5d0 > [ 7082.658160] [<ffffffff816e0193>] ? schedule_timeout+0x133/0x250 > [ 7082.658165] [<ffffffff8113ebdf>] kswapd+0x16f/0x480 > [ 7082.658171] [<ffffffff81070cf0>] ? add_wait_queue+0x60/0x60 > [ 7082.658176] [<ffffffff8113ea70>] ? balance_pgdat+0x5d0/0x5d0 > [ 7082.658180] [<ffffffff810704f0>] kthread+0xc0/0xd0 > [ 7082.658185] [<ffffffff81070430>] ? flush_kthread_worker+0xb0/0xb0 > [ 7082.658191] [<ffffffff816ec89c>] ret_from_fork+0x7c/0xb0 > [ 7082.658196] [<ffffffff81070430>] ? flush_kthread_worker+0xb0/0xb0 > [ 7082.658207] INFO: task bcache_writebac:5046 blocked for more than > 120 seconds. > [ 7082.658213] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" > disables this message. > [ 7082.658219] bcache_writebac D ffffffff8180fbc0 0 5046 2 0x00000000 > [ 7082.658223] ffff881955e31cd8 0000000000000046 0000000000000001 > 0000000000000001 > [ 7082.658228] ffff882f8a740000 ffff881955e31fd8 ffff881955e31fd8 > ffff881955e31fd8 > [ 7082.658232] ffff882fa6aa9730 ffff882f8a740000 ffff882f8a740000 > ffff882f8a740000 > [ 7082.658237] Call Trace: > [ 7082.658243] [<ffffffff816e2cd9>] schedule+0x29/0x70 > [ 7082.658249] [<ffffffff816e3a15>] rwsem_down_write_failed+0xf5/0x1a0 > [ 7082.658255] [<ffffffff81343e43>] call_rwsem_down_write_failed+0x13/0x20 > [ 7082.658260] [<ffffffff816e16a1>] ? down_write+0x31/0x40 > [ 7082.658266] [<ffffffff81535362>] bch_writeback_thread+0x62/0x7f0 > [ 7082.658272] [<ffffffff8108b52b>] ? idle_balance+0xeb/0x150 > [ 7082.658278] [<ffffffff81535300>] ? write_dirty+0xc0/0xc0 > [ 7082.658282] [<ffffffff810704f0>] kthread+0xc0/0xd0 > [ 7082.658287] [<ffffffff81070430>] ? flush_kthread_worker+0xb0/0xb0 > [ 7082.658293] [<ffffffff816ec89c>] ret_from_fork+0x7c/0xb0 > [ 7082.658297] [<ffffffff81070430>] ? flush_kthread_worker+0xb0/0xb0 > [ 7082.658301] INFO: task iozone:7406 blocked for more than 120 seconds. > [ 7082.658306] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" > disables this message. > [ 7082.658312] iozone D 0000000000000000 0 7406 7246 0x00000000 > [ 7082.658316] ffff8809dcfbb978 0000000000000082 ffff8809dcfbb938 > ffffffff8131187a > [ 7082.658320] ffff882f8c8b4590 ffff8809dcfbbfd8 ffff8809dcfbbfd8 > ffff8809dcfbbfd8 > [ 7082.658325] ffff882f8c8b1730 ffff882f8c8b4590 ffff8809dcfbb978 > ffff882fbf293c28 > [ 7082.658329] Call Trace: > [ 7082.658335] [<ffffffff8131187a>] ? generic_make_request+0xca/0x100 > [ 7082.658341] [<ffffffff816e2cd9>] schedule+0x29/0x70 > [ 7082.658346] [<ffffffff816e2daf>] io_schedule+0x8f/0xd0 > [ 7082.658353] [<ffffffff811c49bc>] do_blockdev_direct_IO+0x1a7c/0x1fb0 > [ 7082.658362] [<ffffffffa022ea70>] ? ext2_get_blocks+0xa60/0xa60 [ext2] > [ 7082.658369] [<ffffffff811c4f45>] __blockdev_direct_IO+0x55/0x60 > [ 7082.658375] [<ffffffffa022ea70>] ? ext2_get_blocks+0xa60/0xa60 [ext2] > [ 7082.658381] [<ffffffffa022f339>] ext2_direct_IO+0x79/0xe0 [ext2] > [ 7082.658386] [<ffffffffa022ea70>] ? ext2_get_blocks+0xa60/0xa60 [ext2] > [ 7082.658392] [<ffffffff81051426>] ? current_fs_time+0x16/0x60 > [ 7082.658397] [<ffffffff8112b1f6>] generic_file_direct_write+0xc6/0x180 > [ 7082.658402] [<ffffffff8112b58d>] __generic_file_aio_write+0x2dd/0x3b0 > [ 7082.658407] [<ffffffff816e0674>] ? mutex_unlock+0x14/0x20 > [ 7082.658412] [<ffffffff8112b6c9>] generic_file_aio_write+0x69/0xd0 > [ 7082.658417] [<ffffffff8118866a>] do_sync_write+0x7a/0xb0 > [ 7082.658421] [<ffffffff8118949e>] vfs_write+0xce/0x200 > [ 7082.658426] [<ffffffff811a4d60>] ? fget_light+0x70/0xd0 > [ 7082.658431] [<ffffffff811899a2>] SyS_write+0x52/0xa0 > [ 7082.658437] [<ffffffff816ec942>] system_call_fastpath+0x16/0x1b > > > Another similar crash but with ext4: > > [ 2088.219467] bcache: register_bdev() registered backing device sda3 > [ 2094.581831] bcache: run_cache_set() invalidating existing data > [ 2094.599616] bcache: register_cache() registered cache device rxd1 > [ 2117.644140] bcache: bch_cached_dev_attach() Caching sda3 as bcache0 > on set 1e26e5ca-5cb9-4c5a-ad7e-3c787524a9dc > [ 2232.400911] EXT4-fs (bcache0): mounted filesystem with ordered data > mode. Opts: (null) > [ 3723.031832] INFO: task kswapd0:51 blocked for more than 120 seconds. > [ 3723.031842] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" > disables this message. > [ 3723.031848] kswapd0 D ffffffff8180fbc0 0 51 2 0x00000000 > [ 3723.031856] ffff882f8a39bb28 0000000000000046 00000000ffffffff > ffff882f8a39bb78 > [ 3723.031862] ffff882f8a38c590 ffff882f8a39bfd8 ffff882f8a39bfd8 > ffff882f8a39bfd8 > [ 3723.031867] ffff882fa6aa8000 ffff882f8a38c590 ffff882f8a39bb18 > ffff882ec9ea0d98 > [ 3723.031872] Call Trace: > [ 3723.031886] [<ffffffff816e2cd9>] schedule+0x29/0x70 > [ 3723.031893] [<ffffffff816e2fbe>] schedule_preempt_disabled+0xe/0x10 > [ 3723.031899] [<ffffffff816e1272>] __mutex_lock_slowpath+0x112/0x1b0 > [ 3723.031905] [<ffffffff816e076a>] mutex_lock+0x2a/0x41 > [ 3723.031913] [<ffffffff8152af05>] bch_mca_shrink+0x1b5/0x2f0 > [ 3723.031922] [<ffffffff8118c972>] ? prune_super+0x162/0x1b0 > [ 3723.031929] [<ffffffff8113b474>] shrink_slab+0x154/0x300 > [ 3723.031936] [<ffffffff8113e934>] balance_pgdat+0x494/0x5d0 > [ 3723.031941] [<ffffffff8113ebdf>] kswapd+0x16f/0x480 > [ 3723.031949] [<ffffffff81070cf0>] ? add_wait_queue+0x60/0x60 > [ 3723.031954] [<ffffffff8113ea70>] ? balance_pgdat+0x5d0/0x5d0 > [ 3723.031959] [<ffffffff810704f0>] kthread+0xc0/0xd0 > [ 3723.031964] [<ffffffff81070430>] ? flush_kthread_worker+0xb0/0xb0 > [ 3723.031971] [<ffffffff816ec89c>] ret_from_fork+0x7c/0xb0 > [ 3723.031976] [<ffffffff81070430>] ? flush_kthread_worker+0xb0/0xb0 > [ 3723.031987] INFO: task bcache_writebac:1706 blocked for more than > 120 seconds. > [ 3723.031992] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" > disables this message. > [ 3723.031997] bcache_writebac D ffffffff8180fbc0 0 1706 2 0x00000000 > [ 3723.032001] ffff882f90c2bcd8 0000000000000046 0000000000000001 > 0000000000000001 > [ 3723.032006] ffff882f8989dcc0 ffff882f90c2bfd8 ffff882f90c2bfd8 > ffff882f90c2bfd8 > [ 3723.032011] ffff882fa6aaae60 ffff882f8989dcc0 ffff882f8989dcc0 > ffff882f8989dcc0 > [ 3723.032015] Call Trace: > [ 3723.032021] [<ffffffff816e2cd9>] schedule+0x29/0x70 > [ 3723.032027] [<ffffffff816e3a15>] rwsem_down_write_failed+0xf5/0x1a0 > [ 3723.032036] [<ffffffff81343e43>] call_rwsem_down_write_failed+0x13/0x20 > [ 3723.032041] [<ffffffff816e16a1>] ? down_write+0x31/0x40 > [ 3723.032049] [<ffffffff81535362>] bch_writeback_thread+0x62/0x7f0 > [ 3723.032057] [<ffffffff8108b52b>] ? idle_balance+0xeb/0x150 > [ 3723.032063] [<ffffffff81535300>] ? write_dirty+0xc0/0xc0 > [ 3723.032068] [<ffffffff810704f0>] kthread+0xc0/0xd0 > [ 3723.032072] [<ffffffff81070430>] ? flush_kthread_worker+0xb0/0xb0 > [ 3723.032078] [<ffffffff816ec89c>] ret_from_fork+0x7c/0xb0 > [ 3723.032082] [<ffffffff81070430>] ? flush_kthread_worker+0xb0/0xb0 > [ 3723.032087] INFO: task jbd2/bcache0-8:1732 blocked for more than 120 seconds. > [ 3723.032091] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" > disables this message. > [ 3723.032096] jbd2/bcache0-8 D ffffffff8180fbc0 0 1732 2 0x00000000 > [ 3723.032100] ffff882fa4b81a00 0000000000000046 ffff882fa4b819d0 > 0000000000000000 > [ 3723.032104] ffff882f885e2e60 ffff882fa4b81fd8 ffff882fa4b81fd8 > ffff882fa4b81fd8 > [ 3723.032109] ffff882fa6aaae60 ffff882f885e2e60 ffff8822e655cf08 > ffff882f885e2e60 > [ 3723.032113] Call Trace: > [ 3723.032119] [<ffffffff816e2cd9>] schedule+0x29/0x70 > [ 3723.032125] [<ffffffff816e3b5d>] rwsem_down_read_failed+0x9d/0xf0 > [ 3723.032130] [<ffffffff81343e14>] call_rwsem_down_read_failed+0x14/0x30 > [ 3723.032135] [<ffffffff816e16d4>] ? down_read+0x24/0x2b > [ 3723.032140] [<ffffffff81539932>] cached_dev_make_request+0x752/0xf00 > [ 3723.032147] [<ffffffff813115f8>] ? generic_make_request_checks+0x1e8/0x3a0 > [ 3723.032152] [<ffffffff8131187a>] generic_make_request+0xca/0x100 > [ 3723.032157] [<ffffffff81311929>] submit_bio+0x79/0x160 > [ 3723.032164] [<ffffffff811be700>] ? bio_alloc_bioset+0xa0/0x1d0 > [ 3723.032169] [<ffffffff811b8ccf>] _submit_bh+0x13f/0x200 > [ 3723.032173] [<ffffffff811b8da0>] submit_bh+0x10/0x20 > [ 3723.032180] [<ffffffff81276521>] > jbd2_journal_commit_transaction+0x6c1/0x1990 > [ 3723.032187] [<ffffffff8105a48f>] ? try_to_del_timer_sync+0x4f/0x70 > [ 3723.032193] [<ffffffff8127b638>] kjournald2+0xb8/0x240 > [ 3723.032198] [<ffffffff81070cf0>] ? add_wait_queue+0x60/0x60 > [ 3723.032203] [<ffffffff8127b580>] ? commit_timeout+0x10/0x10 > [ 3723.032208] [<ffffffff810704f0>] kthread+0xc0/0xd0 > [ 3723.032212] [<ffffffff81070430>] ? flush_kthread_worker+0xb0/0xb0 > [ 3723.032218] [<ffffffff816ec89c>] ret_from_fork+0x7c/0xb0 > [ 3723.032223] [<ffffffff81070430>] ? flush_kthread_worker+0xb0/0xb0 > [ 3723.032226] INFO: task iozone:2060 blocked for more than 120 seconds. > [ 3723.032230] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" > disables this message. > [ 3723.032235] iozone D 0000000000000000 0 2060 1422 0x00000000 > [ 3723.032239] ffff88180409d8e8 0000000000000082 ffff88180409d8a8 > ffffffff8131187a > [ 3723.032243] ffff882f8a5d4590 ffff88180409dfd8 ffff88180409dfd8 > ffff88180409dfd8 > [ 3723.032248] ffff88149dbc9730 ffff882f8a5d4590 ffff88180409d8b8 > ffff882fbf213c28 > [ 3723.032252] Call Trace: > [ 3723.032257] [<ffffffff8131187a>] ? generic_make_request+0xca/0x100 > [ 3723.032263] [<ffffffff816e2cd9>] schedule+0x29/0x70 > [ 3723.032268] [<ffffffff816e2daf>] io_schedule+0x8f/0xd0 > [ 3723.032275] [<ffffffff811c49bc>] do_blockdev_direct_IO+0x1a7c/0x1fb0 > [ 3723.032280] [<ffffffff810709de>] ? wake_up_bit+0x2e/0x40 > [ 3723.032288] [<ffffffff81227600>] ? ext4_get_block_write_nolock+0x20/0x20 > [ 3723.032294] [<ffffffff811c4f45>] __blockdev_direct_IO+0x55/0x60 > [ 3723.032299] [<ffffffff81227600>] ? ext4_get_block_write_nolock+0x20/0x20 > [ 3723.032303] [<ffffffff81223410>] ? ext4_invalidatepage+0xe0/0xe0 > [ 3723.032309] [<ffffffff811a2381>] ? inode_dio_done+0x31/0x40 > [ 3723.032313] [<ffffffff812252f6>] ext4_direct_IO+0x2c6/0x4e0 > [ 3723.032317] [<ffffffff81227600>] ? ext4_get_block_write_nolock+0x20/0x20 > [ 3723.032321] [<ffffffff81223410>] ? ext4_invalidatepage+0xe0/0xe0 > [ 3723.032327] [<ffffffff811b1283>] ? __mark_inode_dirty+0x53/0x2d0 > [ 3723.032334] [<ffffffff8112b1f6>] generic_file_direct_write+0xc6/0x180 > [ 3723.032339] [<ffffffff8112b58d>] __generic_file_aio_write+0x2dd/0x3b0 > [ 3723.032344] [<ffffffff8121fe08>] ext4_file_write+0x258/0x400 > [ 3723.032349] [<ffffffff8118866a>] do_sync_write+0x7a/0xb0 > [ 3723.032354] [<ffffffff811c81f0>] ? fsnotify+0x2a0/0x2b0 > [ 3723.032359] [<ffffffff8118949e>] vfs_write+0xce/0x200 > [ 3723.032363] [<ffffffff811899a2>] SyS_write+0x52/0xa0 > [ 3723.032369] [<ffffffff816ec942>] system_call_fastpath+0x16/0x1b > [ 3723.032373] INFO: task kworker/u64:1:2070 blocked for more than 120 seconds. > [ 3723.032377] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" > disables this message. > [ 3723.032381] kworker/u64:1 D ffffffff8180fbc0 0 2070 2 0x00000000 > [ 3723.032389] Workqueue: bch_btree_io btree_node_write_work > [ 3723.032391] ffff880783d1f778 0000000000000046 0000000000000000 > 0000000000000001 > [ 3723.032395] ffff882f87d88000 ffff880783d1ffd8 ffff880783d1ffd8 > ffff880783d1ffd8 > [ 3723.032400] ffffffff81c10440 ffff882f87d88000 ffff880783d1f7b8 > ffff882ec9ea0d98 > [ 3723.032404] Call Trace: > [ 3723.032410] [<ffffffff816e2cd9>] schedule+0x29/0x70 > [ 3723.032415] [<ffffffff816e2fbe>] schedule_preempt_disabled+0xe/0x10 > [ 3723.032421] [<ffffffff816e1272>] __mutex_lock_slowpath+0x112/0x1b0 > [ 3723.032426] [<ffffffff816e076a>] mutex_lock+0x2a/0x41 > [ 3723.032430] [<ffffffff8152af05>] bch_mca_shrink+0x1b5/0x2f0 > [ 3723.032435] [<ffffffff8118c972>] ? prune_super+0x162/0x1b0 > [ 3723.032440] [<ffffffff8113b474>] shrink_slab+0x154/0x300 > [ 3723.032449] [<ffffffff8107d258>] ? resched_task+0x68/0x70 > [ 3723.032454] [<ffffffff811471c9>] ? fragmentation_index+0x19/0x70 > [ 3723.032460] [<ffffffff8113dfdf>] do_try_to_free_pages+0x1ef/0x440 > [ 3723.032465] [<ffffffff8113e3e4>] try_to_free_pages+0xe4/0x1a0 > [ 3723.032472] [<ffffffff81132f08>] __alloc_pages_nodemask+0x618/0x9a0 > [ 3723.032480] [<ffffffff8116e47a>] alloc_pages_current+0xba/0x170 > [ 3723.032486] [<ffffffff8112e50e>] __get_free_pages+0xe/0x40 > [ 3723.032491] [<ffffffff81531be8>] __btree_sort+0x48/0x230 > [ 3723.032497] [<ffffffff8153127c>] ? __bch_btree_iter_init+0x7c/0xc0 > [ 3723.032502] [<ffffffff81531f21>] bch_btree_sort_partial+0x101/0x120 > [ 3723.032507] [<ffffffff81528c20>] ? __btree_node_write_done+0x100/0x100 > [ 3723.032512] [<ffffffff81532088>] bch_btree_sort_lazy+0x68/0x90 > [ 3723.032516] [<ffffffff8152a5da>] bch_btree_node_write+0x36a/0x4a0 > [ 3723.032522] [<ffffffff8108b52b>] ? idle_balance+0xeb/0x150 > [ 3723.032529] [<ffffffff8106837c>] ? pwq_activate_delayed_work+0x4c/0xb0 > [ 3723.032534] [<ffffffff8152b097>] btree_node_write_work+0x57/0x80 > [ 3723.032539] [<ffffffff81068724>] process_one_work+0x174/0x490 > [ 3723.032544] [<ffffffff810697eb>] worker_thread+0x11b/0x370 > [ 3723.032550] [<ffffffff810696d0>] ? manage_workers.isra.21+0x2d0/0x2d0 > [ 3723.032554] [<ffffffff810704f0>] kthread+0xc0/0xd0 > [ 3723.032559] [<ffffffff81070430>] ? flush_kthread_worker+0xb0/0xb0 > [ 3723.032565] [<ffffffff816ec89c>] ret_from_fork+0x7c/0xb0 > [ 3723.032569] [<ffffffff81070430>] ? flush_kthread_worker+0xb0/0xb0 > [ 3723.032575] INFO: task kworker/0:10:2142 blocked for more than 120 seconds. > [ 3723.032579] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" > disables this message. > [ 3723.032584] kworker/0:10 D ffffffff8180fbc0 0 2142 2 0x00000000 > [ 3723.032591] Workqueue: events update_writeback_rate > [ 3723.032593] ffff8821cfb3fcd0 0000000000000046 0000000000000000 > ffff8821cfb3fd68 > [ 3723.032597] ffff882f8965dcc0 ffff8821cfb3ffd8 ffff8821cfb3ffd8 > ffff8821cfb3ffd8 > [ 3723.032602] ffffffff81c10440 ffff882f8965dcc0 0000000000000002 > ffff882f8965dcc0 > [ 3723.032606] Call Trace: > [ 3723.032612] [<ffffffff816e2cd9>] schedule+0x29/0x70 > [ 3723.032617] [<ffffffff816e3b5d>] rwsem_down_read_failed+0x9d/0xf0 > [ 3723.032623] [<ffffffff81343e14>] call_rwsem_down_read_failed+0x14/0x30 > [ 3723.032628] [<ffffffff816e16d4>] ? down_read+0x24/0x2b > [ 3723.032633] [<ffffffff81534bf0>] update_writeback_rate+0x30/0x230 > [ 3723.032638] [<ffffffff81068724>] process_one_work+0x174/0x490 > [ 3723.032643] [<ffffffff810697eb>] worker_thread+0x11b/0x370 > [ 3723.032649] [<ffffffff810696d0>] ? manage_workers.isra.21+0x2d0/0x2d0 > [ 3723.032653] [<ffffffff810704f0>] kthread+0xc0/0xd0 > [ 3723.032658] [<ffffffff81070430>] ? flush_kthread_worker+0xb0/0xb0 > [ 3723.032663] [<ffffffff816ec89c>] ret_from_fork+0x7c/0xb0 > [ 3723.032668] [<ffffffff81070430>] ? flush_kthread_worker+0xb0/0xb0 > [ 3723.032680] INFO: task kworker/0:63:2546 blocked for more than 120 seconds. > [ 3723.032684] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" > disables this message. > [ 3723.032691] kworker/0:63 D ffffffff8180fea0 0 2546 2 0x00000000 > [ 3723.032699] Workqueue: bcache bch_data_insert_keys > [ 3723.032701] ffff8821d4f99658 0000000000000046 ffff8821d4f99678 > ffff88307fff9d80 > [ 3723.032705] ffff88149dbc9730 ffff8821d4f99fd8 ffff8821d4f99fd8 > ffff8821d4f99fd8 > [ 3723.032710] ffff882fa6a9dcc0 ffff88149dbc9730 ffff88149dbc9730 > ffff882ec9ea0d98 > [ 3723.032714] Call Trace: > [ 3723.032720] [<ffffffff816e2cd9>] schedule+0x29/0x70 > [ 3723.032726] [<ffffffff816e2fbe>] schedule_preempt_disabled+0xe/0x10 > [ 3723.032732] [<ffffffff816e1272>] __mutex_lock_slowpath+0x112/0x1b0 > [ 3723.032737] [<ffffffff816e076a>] mutex_lock+0x2a/0x41 > [ 3723.032742] [<ffffffff8152af05>] bch_mca_shrink+0x1b5/0x2f0 > [ 3723.032747] [<ffffffff8118c972>] ? prune_super+0x162/0x1b0 > [ 3723.032752] [<ffffffff8113b474>] shrink_slab+0x154/0x300 > [ 3723.032757] [<ffffffff8107d258>] ? resched_task+0x68/0x70 > [ 3723.032763] [<ffffffff8107db85>] ? check_preempt_curr+0x75/0xa0 > [ 3723.032767] [<ffffffff811471c9>] ? fragmentation_index+0x19/0x70 > [ 3723.032772] [<ffffffff8113dfdf>] do_try_to_free_pages+0x1ef/0x440 > [ 3723.032777] [<ffffffff8113e3e4>] try_to_free_pages+0xe4/0x1a0 > [ 3723.032783] [<ffffffff81530c51>] ? __bch_bset_search+0x1d1/0x480 > [ 3723.032789] [<ffffffff81132f08>] __alloc_pages_nodemask+0x618/0x9a0 > [ 3723.032794] [<ffffffff8116e47a>] alloc_pages_current+0xba/0x170 > [ 3723.032799] [<ffffffff8112e50e>] __get_free_pages+0xe/0x40 > [ 3723.032804] [<ffffffff815287d3>] mca_data_alloc+0x73/0x1d0 > [ 3723.032808] [<ffffffff8152ab57>] mca_alloc+0x277/0x470 > [ 3723.032813] [<ffffffff81530c51>] ? __bch_bset_search+0x1d1/0x480 > [ 3723.032818] [<ffffffff8152b45e>] bch_btree_node_get+0x10e/0x280 > [ 3723.032823] [<ffffffff8152b822>] bch_btree_map_nodes_recurse+0xe2/0x170 > [ 3723.032828] [<ffffffff8152d3e0>] ? bch_btree_insert_node+0x2f0/0x2f0 > [ 3723.032834] [<ffffffff811c222a>] ? dio_bio_end_io+0x5a/0x90 > [ 3723.032840] [<ffffffff81086931>] ? update_curr+0x141/0x200 > [ 3723.032845] [<ffffffff81534dfe>] ? dirty_io_destructor+0xe/0x10 > [ 3723.032850] [<ffffffff8152e9ee>] __bch_btree_map_nodes+0x13e/0x1c0 > [ 3723.032855] [<ffffffff8152d3e0>] ? bch_btree_insert_node+0x2f0/0x2f0 > [ 3723.032860] [<ffffffff8153484f>] ? bch_journal+0x42f/0x4b0 > [ 3723.032865] [<ffffffff8152eb24>] bch_btree_insert+0xb4/0x120 > [ 3723.032871] [<ffffffff81537d9e>] bch_data_insert_keys+0x3e/0x160 > [ 3723.032876] [<ffffffff81068724>] process_one_work+0x174/0x490 > [ 3723.032881] [<ffffffff810697eb>] worker_thread+0x11b/0x370 > [ 3723.032887] [<ffffffff810696d0>] ? manage_workers.isra.21+0x2d0/0x2d0 > [ 3723.032891] [<ffffffff810704f0>] kthread+0xc0/0xd0 > [ 3723.032896] [<ffffffff81070430>] ? flush_kthread_worker+0xb0/0xb0 > [ 3723.032901] [<ffffffff816ec89c>] ret_from_fork+0x7c/0xb0 > [ 3723.032906] [<ffffffff81070430>] ? flush_kthread_worker+0xb0/0xb0 > [ 3843.031746] INFO: task kswapd0:51 blocked for more than 120 seconds. > [ 3843.031755] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" > disables this message. > [ 3843.031761] kswapd0 D ffffffff8180fbc0 0 51 2 0x00000000 > [ 3843.031768] ffff882f8a39bb28 0000000000000046 00000000ffffffff > ffff882f8a39bb78 > [ 3843.031774] ffff882f8a38c590 ffff882f8a39bfd8 ffff882f8a39bfd8 > ffff882f8a39bfd8 > [ 3843.031778] ffff882fa6aa8000 ffff882f8a38c590 ffff882f8a39bb18 > ffff882ec9ea0d98 > [ 3843.031783] Call Trace: > [ 3843.031794] [<ffffffff816e2cd9>] schedule+0x29/0x70 > [ 3843.031800] [<ffffffff816e2fbe>] schedule_preempt_disabled+0xe/0x10 > [ 3843.031806] [<ffffffff816e1272>] __mutex_lock_slowpath+0x112/0x1b0 > [ 3843.031812] [<ffffffff816e076a>] mutex_lock+0x2a/0x41 > [ 3843.031817] [<ffffffff8152af05>] bch_mca_shrink+0x1b5/0x2f0 > [ 3843.031823] [<ffffffff8118c972>] ? prune_super+0x162/0x1b0 > [ 3843.031829] [<ffffffff8113b474>] shrink_slab+0x154/0x300 > [ 3843.031835] [<ffffffff8113e934>] balance_pgdat+0x494/0x5d0 > [ 3843.031840] [<ffffffff8113ebdf>] kswapd+0x16f/0x480 > [ 3843.031846] [<ffffffff81070cf0>] ? add_wait_queue+0x60/0x60 > [ 3843.031851] [<ffffffff8113ea70>] ? balance_pgdat+0x5d0/0x5d0 > [ 3843.031856] [<ffffffff810704f0>] kthread+0xc0/0xd0 > [ 3843.031861] [<ffffffff81070430>] ? flush_kthread_worker+0xb0/0xb0 > [ 3843.031867] [<ffffffff816ec89c>] ret_from_fork+0x7c/0xb0 > [ 3843.031872] [<ffffffff81070430>] ? flush_kthread_worker+0xb0/0xb0 > [ 3843.031883] INFO: task bcache_writebac:1706 blocked for more than > 120 seconds. > [ 3843.031888] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" > disables this message. > [ 3843.031894] bcache_writebac D ffffffff8180fbc0 0 1706 2 0x00000000 > [ 3843.031899] ffff882f90c2bcd8 0000000000000046 0000000000000001 > 0000000000000001 > [ 3843.031904] ffff882f8989dcc0 ffff882f90c2bfd8 ffff882f90c2bfd8 > ffff882f90c2bfd8 > [ 3843.031908] ffff882fa6aaae60 ffff882f8989dcc0 ffff882f8989dcc0 > ffff882f8989dcc0 > [ 3843.031913] Call Trace: > [ 3843.031919] [<ffffffff816e2cd9>] schedule+0x29/0x70 > [ 3843.031925] [<ffffffff816e3a15>] rwsem_down_write_failed+0xf5/0x1a0 > [ 3843.031931] [<ffffffff81343e43>] call_rwsem_down_write_failed+0x13/0x20 > [ 3843.031936] [<ffffffff816e16a1>] ? down_write+0x31/0x40 > [ 3843.031942] [<ffffffff81535362>] bch_writeback_thread+0x62/0x7f0 > [ 3843.031949] [<ffffffff8108b52b>] ? idle_balance+0xeb/0x150 > [ 3843.031955] [<ffffffff81535300>] ? write_dirty+0xc0/0xc0 > [ 3843.031959] [<ffffffff810704f0>] kthread+0xc0/0xd0 > [ 3843.031964] [<ffffffff81070430>] ? flush_kthread_worker+0xb0/0xb0 > [ 3843.031969] [<ffffffff816ec89c>] ret_from_fork+0x7c/0xb0 > [ 3843.031974] [<ffffffff81070430>] ? flush_kthread_worker+0xb0/0xb0 > [ 3843.031978] INFO: task jbd2/bcache0-8:1732 blocked for more than 120 seconds. > [ 3843.031982] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" > disables this message. > [ 3843.031988] jbd2/bcache0-8 D ffffffff8180fbc0 0 1732 2 0x00000000 > [ 3843.031992] ffff882fa4b81a00 0000000000000046 ffff882fa4b819d0 > 0000000000000000 > [ 3843.031996] ffff882f885e2e60 ffff882fa4b81fd8 ffff882fa4b81fd8 > ffff882fa4b81fd8 > [ 3843.032001] ffff882fa6aaae60 ffff882f885e2e60 ffff8822e655cf08 > ffff882f885e2e60 > [ 3843.032005] Call Trace: > [ 3843.032011] [<ffffffff816e2cd9>] schedule+0x29/0x70 > [ 3843.032016] [<ffffffff816e3b5d>] rwsem_down_read_failed+0x9d/0xf0 > [ 3843.032022] [<ffffffff81343e14>] call_rwsem_down_read_failed+0x14/0x30 > [ 3843.032027] [<ffffffff816e16d4>] ? down_read+0x24/0x2b > [ 3843.032031] [<ffffffff81539932>] cached_dev_make_request+0x752/0xf00 > [ 3843.032037] [<ffffffff813115f8>] ? generic_make_request_checks+0x1e8/0x3a0 > [ 3843.032042] [<ffffffff8131187a>] generic_make_request+0xca/0x100 > [ 3843.032047] [<ffffffff81311929>] submit_bio+0x79/0x160 > [ 3843.032052] [<ffffffff811be700>] ? bio_alloc_bioset+0xa0/0x1d0 > [ 3843.032057] [<ffffffff811b8ccf>] _submit_bh+0x13f/0x200 > [ 3843.032061] [<ffffffff811b8da0>] submit_bh+0x10/0x20 > [ 3843.032067] [<ffffffff81276521>] > jbd2_journal_commit_transaction+0x6c1/0x1990 > [ 3843.032073] [<ffffffff8105a48f>] ? try_to_del_timer_sync+0x4f/0x70 > [ 3843.032079] [<ffffffff8127b638>] kjournald2+0xb8/0x240 > [ 3843.032084] [<ffffffff81070cf0>] ? add_wait_queue+0x60/0x60 > [ 3843.032089] [<ffffffff8127b580>] ? commit_timeout+0x10/0x10 > [ 3843.032093] [<ffffffff810704f0>] kthread+0xc0/0xd0 > [ 3843.032098] [<ffffffff81070430>] ? flush_kthread_worker+0xb0/0xb0 > [ 3843.032104] [<ffffffff816ec89c>] ret_from_fork+0x7c/0xb0 > [ 3843.032108] [<ffffffff81070430>] ? flush_kthread_worker+0xb0/0xb0 > > Could you please help me out to fix this ? Also please let me know if > I am missing anything here. I can recreate this scenario very easily > please let me know if you require any specific information. > > Thanks, > Neo -- To unsubscribe from this list: send the line "unsubscribe linux-bcache" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html