Hi ming Sorry for delayed report this. On 01/17/2018 05:57 PM, Ming Lei wrote: > 2) hctx->next_cpu can become offline from online before __blk_mq_run_hw_queue > is run, there isn't warning, but once the IO is submitted to hardware, > after it is completed, how does the HBA/hw queue notify CPU since CPUs > assigned to this hw queue(irq vector) are offline? blk-mq's timeout > handler may cover that, but looks too tricky. In theory, the irq affinity will be migrated to other cpu. This is done by fixup_irqs() in the context of stop_machine. However, in my test, I found this log: [ 267.161043] do_IRQ: 7.33 No irq handler for vector The 33 is the vector used by nvme cq. The irq seems to be missed and sometimes IO hang occurred. It is not every time, I think maybe due to nvme_process_cq in nvme_queue_rq. I add dump stack behind the error log and get following: [ 267.161043] do_IRQ: 7.33 No irq handler for vector migration/7 [ 267.161045] CPU: 7 PID: 52 Comm: migration/7 Not tainted 4.15.0-rc7+ #27 [ 267.161045] Hardware name: LENOVO 10MLS0E339/3106, BIOS M1AKT22A 06/27/2017 [ 267.161046] Call Trace: [ 267.161047] <IRQ> [ 267.161052] dump_stack+0x7c/0xb5 [ 267.161054] do_IRQ+0xb9/0xf0 [ 267.161056] common_interrupt+0xa2/0xa2 [ 267.161057] </IRQ> [ 267.161059] RIP: 0010:multi_cpu_stop+0xb0/0x120 [ 267.161060] RSP: 0018:ffffbb6c81af7e70 EFLAGS: 00000202 ORIG_RAX: ffffffffffffffde [ 267.161061] RAX: 0000000000000001 RBX: 0000000000000004 RCX: 0000000000000000 [ 267.161062] RDX: 0000000000000006 RSI: ffffffff898c4591 RDI: 0000000000000202 [ 267.161063] RBP: ffffbb6c826e7c88 R08: ffff991abc1256bc R09: 0000000000000005 [ 267.161063] R10: ffffbb6c81af7db8 R11: ffffffff89c91d20 R12: 0000000000000001 [ 267.161064] R13: ffffbb6c826e7cac R14: 0000000000000003 R15: 0000000000000000 [ 267.161067] ? cpu_stop_queue_work+0x90/0x90 [ 267.161068] cpu_stopper_thread+0x83/0x100 [ 267.161070] smpboot_thread_fn+0x161/0x220 [ 267.161072] kthread+0xf5/0x130 [ 267.161073] ? sort_range+0x20/0x20 [ 267.161074] ? kthread_associate_blkcg+0xe0/0xe0 [ 267.161076] ret_from_fork+0x24/0x30 The irq just occurred after the irq is enabled in multi_cpu_stop. 0xffffffff8112d655 is in multi_cpu_stop (/home/will/u04/source_code/linux-block/kernel/stop_machine.c:223). 218 */ 219 touch_nmi_watchdog(); 220 } 221 } while (curstate != MULTI_STOP_EXIT); 222 223 local_irq_restore(flags); 224 return err; 225 } Thanks Jianchao
