On Monday 15 September 2014 19:47:18 Stefan Priebe - Profihost AG wrote: > Same to me. Hello Stefan. Is the 3.16.2 working better? Uhh and what happend to load bug? Even with 3.17-rc4 i have a constant load of 2.00 on an otherwise idle system. cheers t. > Stefan > > Excuse my typo sent from my mobile phone. > > > Am 15.09.2014 um 19:26 schrieb Thomas Stein <himbeere@xxxxxxxxxxxx>: > > > > Hello eveybody. > > > > Just played around with 3.17-rc4 and bcache. I've build bcache with a 120G > > SSD as caching device and a Raid1 device (md4) as backing device. Today > > under heavy i/o load (moving a 100G VM Image) the machine froze. Call > > trace is this: > > > > Sep 15 10:13:48 hn kernel: [82567.843075] Task dump for CPU 0: > > Sep 15 10:13:48 hn kernel: [82567.843078] bcache_gc R running task > > 12248 28611 2 0x00080808 > > Sep 15 10:13:48 hn kernel: [82567.843083] ffffffff81c411c0 > > ffff88083fa03d78 ffffffff81071492 0000000000000000 > > Sep 15 10:13:48 hn kernel: [82567.843087] ffffffff81c411c0 > > ffff88083fa03d98 ffffffff810740b8 ffff88083fa03dd8 > > Sep 15 10:13:48 hn kernel: [82567.843090] 0000000000000000 > > ffff88083fa03dc8 ffffffff8108f335 ffff88083fa0d280 > > Sep 15 10:13:48 hn kernel: [82567.843093] Call Trace: > > Sep 15 10:13:48 hn kernel: [82567.843096] <IRQ> [<ffffffff81071492>] > > sched_show_task+0xc2/0x130 > > Sep 15 10:13:48 hn kernel: [82567.843108] [<ffffffff810740b8>] > > dump_cpu_task+0x38/0x40 > > Sep 15 10:13:48 hn kernel: [82567.843119] [<ffffffff8108f335>] > > rcu_dump_cpu_stacks+0x85/0xc0 > > Sep 15 10:13:48 hn kernel: [82567.843131] [<ffffffff81092610>] > > rcu_check_callbacks+0x3c0/0x680 > > Sep 15 10:13:48 hn kernel: [82567.843135] [<ffffffff81096e13>] > > update_process_times+0x43/0x80 > > Sep 15 10:13:48 hn kernel: [82567.843139] [<ffffffff810a54f1>] > > tick_sched_handle.isra.13+0x31/0x40 > > Sep 15 10:13:48 hn kernel: [82567.843142] [<ffffffff810a5667>] > > tick_sched_timer+0x47/0x70 > > Sep 15 10:13:48 hn kernel: [82567.843146] [<ffffffff8109766b>] > > __run_hrtimer+0x7b/0x1c0 > > Sep 15 10:13:48 hn kernel: [82567.843149] [<ffffffff810a5620>] ? > > tick_sched_do_timer+0x30/0x30 > > Sep 15 10:13:48 hn kernel: [82567.843153] [<ffffffff81097e37>] > > hrtimer_interrupt+0xf7/0x230 > > Sep 15 10:13:48 hn kernel: [82567.843158] [<ffffffff81033196>] > > local_apic_timer_interrupt+0x36/0x60 > > Sep 15 10:13:48 hn kernel: [82567.843162] [<ffffffff810334de>] > > smp_apic_timer_interrupt+0x3e/0x60 > > Sep 15 10:13:48 hn kernel: [82567.843166] [<ffffffff8166994a>] > > apic_timer_interrupt+0x6a/0x70 > > Sep 15 10:13:48 hn kernel: [82567.843168] <EOI> [<ffffffff8148f848>] ? > > btree_gc_count_keys+0x28/0x60 > > Sep 15 10:13:48 hn kernel: [82567.843175] [<ffffffff8148f869>] ? > > btree_gc_count_keys+0x49/0x60 > > Sep 15 10:13:48 hn kernel: [82567.843178] [<ffffffff814950b5>] > > btree_gc_recurse+0x1b5/0x320 > > Sep 15 10:13:48 hn kernel: [82567.843182] [<ffffffff814904f3>] ? > > btree_gc_mark_node+0x63/0x240 > > Sep 15 10:13:48 hn kernel: [82567.843186] [<ffffffff81080b2e>] ? > > __wake_up+0x4e/0x70 > > Sep 15 10:13:48 hn kernel: [82567.843190] [<ffffffff81495635>] > > bch_btree_gc+0x415/0x5a0 > > Sep 15 10:13:48 hn kernel: [82567.843194] [<ffffffff81080780>] ? > > finish_wait+0x80/0x80 > > Sep 15 10:13:48 hn kernel: [82567.843197] [<ffffffff814957f8>] > > bch_gc_thread+0x38/0x120 > > Sep 15 10:13:48 hn kernel: [82567.843200] [<ffffffff814957c0>] ? > > bch_btree_gc+0x5a0/0x5a0 > > Sep 15 10:13:48 hn kernel: [82567.843204] [<ffffffff810672b4>] > > kthread+0xc4/0xe0 > > Sep 15 10:13:48 hn kernel: [82567.843207] [<ffffffff810671f0>] ? > > kthread_worker_fn+0x150/0x150 > > Sep 15 10:13:48 hn kernel: [82567.843211] [<ffffffff81668aac>] > > ret_from_fork+0x7c/0xb0 > > Sep 15 10:13:48 hn kernel: [82567.843214] [<ffffffff810671f0>] ? > > kthread_worker_fn+0x150/0x150 > > > > That's it. Should i be worried? It's a testing machine of course. > > > > thanks and best regards > > t. > > -- > > 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 -- 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
