Patches based on the latest version:
---
tools/vgchange.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/vgchange.c b/tools/vgchange.c
index f07b245bd..f35ff4c0e 100644
--- a/tools/vgchange.c
+++ b/tools/vgchange.c
@@ -1003,7 +1003,7 @@ int vgchange(struct cmd_context *cmd, int argc, char **argv)
init_external_device_info_source(DEV_EXT_NONE);
}
- if (update)
+ if (update || arg_is_set(cmd, refresh_ARG))
flags |= READ_FOR_UPDATE;
else if (arg_is_set(cmd, activate_ARG))
flags |= READ_FOR_ACTIVATE;
--
2.33.0
在 2023/8/29 11:53, wangzhiqiang (Q) 写道:
> I've got an issue while execute vgchange --refresh concurrently, process vgchange and systemd-udevd
> enters the D state.
> root 2933 0.0 1.0 54216 31344 pts/1 D<L 11:21 0:00 vgchange --refresh
> root 2934 0.0 1.1 54216 32788 pts/1 D<L 11:21 0:00 vgchange --refresh
> root 2935 0.0 1.0 54216 31496 pts/1 D<L 11:21 0:00 vgchange --refresh
> root 2937 0.0 1.0 54216 31500 pts/1 S<L 11:21 0:00 vgchange --refresh
> root 2951 0.0 0.0 0 0 ? D 11:21 0:00 [systemd-udevd]
> root 2952 0.0 0.0 0 0 ? D 11:21 0:00 [systemd-udevd]
>
> process stack as follows
> [root@localhost ~]# cat /proc/2937/stack
> [<0>] dm_wait_for_bios_completion+0x298/0x340 [dm_mod]
> [<0>] dm_wait_for_completion+0xfe/0x110 [dm_mod]
> [<0>] __dm_suspend+0xd0/0x310 [dm_mod]
> [<0>] dm_suspend+0x133/0x180 [dm_mod]
> [<0>] dev_suspend+0x115/0x150 [dm_mod]
> [<0>] ctl_ioctl+0x320/0x4c0 [dm_mod]
> [<0>] dm_ctl_ioctl+0x26/0x40 [dm_mod]
> [<0>] __se_sys_ioctl+0xeb/0x120
> [<0>] do_syscall_64+0x30/0x40
> [<0>] entry_SYSCALL_64_after_hwframe+0x61/0xc6
> [root@localhost ~]# cat /proc/2935/stack
> [<0>] dm_suspend+0x2b/0x180 [dm_mod]
> [<0>] dev_suspend+0x115/0x150 [dm_mod]
> [<0>] ctl_ioctl+0x320/0x4c0 [dm_mod]
> [<0>] dm_ctl_ioctl+0x26/0x40 [dm_mod]
> [<0>] __se_sys_ioctl+0xeb/0x120
> [<0>] do_syscall_64+0x30/0x40
> [<0>] entry_SYSCALL_64_after_hwframe+0x61/0xc6
> [root@localhost ~]# cat /proc/2951/stack
> [<0>] __lock_page+0x25a/0x7a0
> [<0>] truncate_inode_pages_range+0xc52/0x1370
> [<0>] __blkdev_put+0x15b/0x3f0
> [<0>] blkdev_close+0x49/0x60
> [<0>] __fput+0x1b9/0x480
> [<0>] task_work_run+0xad/0xf0
> [<0>] do_exit+0x47f/0x810
> [<0>] do_group_exit+0x77/0x150
> [<0>] get_signal+0x2a2/0xa60
> [<0>] arch_do_signal_or_restart+0x1c6/0x310
> [<0>] exit_to_user_mode_loop+0xdb/0x100
> [<0>] exit_to_user_mode_prepare+0x7e/0x90
> [<0>] syscall_exit_to_user_mode+0x12/0x40
> [<0>] entry_SYSCALL_64_after_hwframe+0x61/0xc6
>
> I recommend get an exclusive lock when vgchange --refresh.
>
>>From 7ddadf2bbbe0383893ab8f5b7cb8d51ebf7a5ed4 Mon Sep 17 00:00:00 2001
> From: wangzhiqiang <wangzhiqiang95@xxxxxxxxxx>
> Date: Tue, 29 Aug 2023 10:28:15 +0800
> Subject: [PATCH] vgchange acquire an exclusive VG lock for refresh.
>
> Let's run the following test cases, we've got hungtask.
> P2 or P3 can't suspend snap and udevd also can't read
> device info because real or cow has been suspend.
>
> P1(vgchange) P2(vgchange) P3(vgchange)
> --------------------------------------------------------
> suspend real
> suspend cow
> suspend snap
> suspend snap
> suspend snap
>
> function query()
> {
> while true
> do
> vgchange --refresh
> done
> }
>
> query 1 &> /dev/null &
> query 2 &> /dev/null &
> query 3 &> /dev/null &
>
> [ 247.250669] INFO: task vgchange:2934 blocked for more than 122 seconds.
> [ 247.251935] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
> [ 247.252619] task:vgchange state:D stack: 0 pid: 2934 ppid: 2930 flags:0x00000080
> [ 247.252626] Call Trace:
> [ 247.252633] __schedule+0x547/0xe80
> [ 247.252640] ? io_schedule_timeout+0xb0/0xb0
> [ 247.252647] ? _raw_spin_lock+0x7a/0xd0
> [ 247.252652] schedule+0x6f/0x130
> [ 247.252658] schedule_preempt_disabled+0xa/0x10
> [ 247.252664] __mutex_lock.constprop.0+0x311/0x700
> [ 247.252673] ? kernel_text_address.part.0+0xb9/0xc0
> [ 247.252678] ? ww_mutex_unlock+0x50/0x50
> [ 247.252685] ? unwind_get_return_address+0x33/0x50
> [ 247.252692] ? cred_has_capability.isra.0+0x14b/0x220
> [ 247.252698] ? check_nnp_nosuid.isra.0+0x170/0x170
> [ 247.252704] mutex_lock+0x114/0x130
> [ 247.252710] ? __mutex_lock_slowpath+0x10/0x10
> [ 247.252716] ? rwsem_down_write_slowpath+0x830/0x830
> [ 247.252733] ? dm_get+0x40/0x70 [dm_mod]
> [ 247.252752] ? dm_get_md+0xb3/0x120 [dm_mod]
> [ 247.252770] dm_suspend+0x2b/0x180 [dm_mod]
> [ 247.252788] dev_suspend+0x115/0x150 [dm_mod]
> [ 247.252805] ctl_ioctl+0x320/0x4c0 [dm_mod]
> [ 247.252823] ? dev_set_geometry+0x290/0x290 [dm_mod]
> [ 247.252841] ? copy_params+0x2e0/0x2e0 [dm_mod]
> [ 247.252846] ? locks_dispose_list+0xa0/0xd0
> [ 247.252851] ? locks_remove_posix+0x24f/0x340
> [ 247.252856] ? locks_remove_flock+0x1e6/0x250
> [ 247.252865] ? ioctl_fiemap.isra.0+0x110/0x1e0
> [ 247.252872] ? vfs_write+0x2a5/0x440
> [ 247.252877] ? selinux_file_ioctl+0x89/0x1c0
> [ 247.252895] ? ctl_ioctl+0x4c0/0x4c0 [dm_mod]
> [ 247.252912] dm_ctl_ioctl+0x26/0x40 [dm_mod]
> [ 247.252918] __se_sys_ioctl+0xeb/0x120
> [ 247.252923] do_syscall_64+0x30/0x40
> [ 247.252929] entry_SYSCALL_64_after_hwframe+0x61/0xc6
>
> [ 247.252967] INFO: task vgchange:2935 blocked for more than 122 seconds.
> [ 247.254242] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
> [ 247.254909] task:vgchange state:D stack: 0 pid: 2935 ppid: 2931 flags:0x00000080
> [ 247.254922] Call Trace:
> [ 247.254929] __schedule+0x547/0xe80
> [ 247.254935] ? io_schedule_timeout+0xb0/0xb0
> [ 247.254942] ? _raw_spin_lock+0x7a/0xd0
> [ 247.254947] schedule+0x6f/0x130
> [ 247.254953] schedule_preempt_disabled+0xa/0x10
> [ 247.254959] __mutex_lock.constprop.0+0x311/0x700
> [ 247.254965] ? kernel_text_address.part.0+0xb9/0xc0
> [ 247.254976] ? ww_mutex_unlock+0x50/0x50
> [ 247.254981] ? unwind_get_return_address+0x33/0x50
> [ 247.254988] ? cred_has_capability.isra.0+0x14b/0x220
> [ 247.254995] ? check_nnp_nosuid.isra.0+0x170/0x170
> [ 247.255000] mutex_lock+0x114/0x130
> [ 247.255006] ? __mutex_lock_slowpath+0x10/0x10
> [ 247.255012] ? rwsem_down_write_slowpath+0x830/0x830
> [ 247.255029] ? dm_get+0x40/0x70 [dm_mod]
> [ 247.255052] ? dm_get_md+0xb3/0x120 [dm_mod]
> [ 247.255069] dm_suspend+0x2b/0x180 [dm_mod]
> [ 247.255088] dev_suspend+0x115/0x150 [dm_mod]
> [ 247.255113] ctl_ioctl+0x320/0x4c0 [dm_mod]
> [ 247.255142] ? dev_set_geometry+0x290/0x290 [dm_mod]
> [ 247.255160] ? copy_params+0x2e0/0x2e0 [dm_mod]
> [ 247.255175] ? nohz_balance_exit_idle+0x2b/0x160
> [ 247.255187] ? rb_insert_color+0x2a/0x280
> [ 247.255196] ? ioctl_fiemap.isra.0+0x110/0x1e0
> [ 247.255202] ? selinux_file_ioctl+0x89/0x1c0
> [ 247.255219] ? ctl_ioctl+0x4c0/0x4c0 [dm_mod]
> [ 247.255238] dm_ctl_ioctl+0x26/0x40 [dm_mod]
> [ 247.255250] __se_sys_ioctl+0xeb/0x120
> [ 247.255255] do_syscall_64+0x30/0x40
> [ 247.255262] entry_SYSCALL_64_after_hwframe+0x61/0xc6
>
> [ 493.015195] INFO: task systemd-udevd:2951 blocked for more than 122 seconds.
> [ 493.016461] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
> [ 493.017131] task:systemd-udevd state:D stack: 0 pid: 2951 ppid: 719 flags:0x000043a6
> [ 493.017138] Call Trace:
> [ 493.017145] __schedule+0x547/0xe80
> [ 493.017152] ? io_schedule_timeout+0xb0/0xb0
> [ 493.017157] ? orc_find.part.0+0x240/0x240
> [ 493.017163] ? get_stack_info_noinstr+0x16/0x140
> [ 493.017171] ? bpf_ksym_find+0xc0/0x110
> [ 493.017189] schedule+0x6f/0x130
> [ 493.017195] io_schedule+0x6d/0xa0
> [ 493.017202] __lock_page+0x25a/0x7a0
> [ 493.017209] ? wait_on_page_bit_killable+0x6c0/0x6c0
> [ 493.017216] ? __lock_page_or_retry+0x3e0/0x3e0
> [ 493.017222] ? add_to_page_cache_lru+0x370/0x370
> [ 493.017231] truncate_inode_pages_range+0xc52/0x1370
> [ 493.017242] ? generic_error_remove_page+0x90/0x90
> [ 493.017248] ? __filemap_fdatawait_range+0x179/0x270
> [ 493.017256] ? filemap_range_has_page+0x170/0x170
> [ 493.017264] ? __bitmap_or_equal+0x89/0x120
> [ 493.017271] ? _find_next_bit.constprop.0+0xde/0x120
> [ 493.017279] ? cpumask_next+0x2c/0x40
> [ 493.017287] ? smp_call_function_many_cond+0x430/0x5f0
> [ 493.017295] ? touch_buffer+0xa0/0xa0
> [ 493.017305] ? __find_get_block+0x110/0x110
> [ 493.017311] ? __find_get_block+0x110/0x110
> [ 493.017316] ? touch_buffer+0xa0/0xa0
> [ 493.017322] __blkdev_put+0x15b/0x3f0
> [ 493.017328] ? blkdev_put+0x1c0/0x1c0
> [ 493.017333] blkdev_close+0x49/0x60
> [ 493.017339] __fput+0x1b9/0x480
> [ 493.017346] task_work_run+0xad/0xf0
> [ 493.017354] do_exit+0x47f/0x810
> [ 493.017361] ? exit_mm+0x450/0x450
> [ 493.017371] ? _raw_spin_lock_irq+0x7b/0xd0
> [ 493.017377] do_group_exit+0x77/0x150
> [ 493.017384] get_signal+0x2a2/0xa60
> [ 493.017393] arch_do_signal_or_restart+0x1c6/0x310
> [ 493.017399] ? get_sigframe_size+0x20/0x20
> [ 493.017405] ? vfs_read+0x1f6/0x2d0
> [ 493.017411] ? unroll_tree_refs+0x18a/0x1e0
> [ 493.017424] exit_to_user_mode_loop+0xdb/0x100
> [ 493.017430] exit_to_user_mode_prepare+0x7e/0x90
> [ 493.017438] syscall_exit_to_user_mode+0x12/0x40
> [ 493.017445] entry_SYSCALL_64_after_hwframe+0x61/0xc6
>
> cat /proc/2937/stack
> [<0>] dm_wait_for_bios_completion+0x298/0x340 [dm_mod]
> [<0>] dm_wait_for_completion+0xfe/0x110 [dm_mod]
> [<0>] __dm_suspend+0xd0/0x310 [dm_mod]
> [<0>] dm_suspend+0x133/0x180 [dm_mod]
> [<0>] dev_suspend+0x115/0x150 [dm_mod]
> [<0>] ctl_ioctl+0x320/0x4c0 [dm_mod]
> [<0>] dm_ctl_ioctl+0x26/0x40 [dm_mod]
> [<0>] __se_sys_ioctl+0xeb/0x120
> [<0>] do_syscall_64+0x30/0x40
> [<0>] entry_SYSCALL_64_after_hwframe+0x61/0xc6
>
> Signed-off-by: wangzhiqiang <wangzhiqiang95@xxxxxxxxxx>
> ---
> tools/vgchange.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/tools/vgchange.c b/tools/vgchange.c
> index e4b57db..eb3096d 100644
> --- a/tools/vgchange.c
> +++ b/tools/vgchange.c
> @@ -837,7 +837,7 @@ int vgchange(struct cmd_context *cmd, int argc, char **argv)
> cmd->lockd_vg_enforce_sh = 1;
> }
>
> - if (update)
> + if (update || arg_is_set(cmd, refresh_ARG))
> flags |= READ_FOR_UPDATE;
> else if (arg_is_set(cmd, activate_ARG))
> flags |= READ_FOR_ACTIVATE;
> --
> 2.33.0
>
_______________________________________________
linux-lvm mailing list
linux-lvm@xxxxxxxxxx
https://listman.redhat.com/mailman/listinfo/linux-lvm
read the LVM HOW-TO at http://tldp.org/HOWTO/LVM-HOWTO/
