* NFS problem in 5.16 merge content
@ 2021-11-23 22:19 Dennis Dalessandro
2021-11-23 23:40 ` Chuck Lever III
0 siblings, 1 reply; 2+ messages in thread
From: Dennis Dalessandro @ 2021-11-23 22:19 UTC (permalink / raw)
To: linux-rdma; +Cc: Chuck Lever
Seeing NFS RDMA failures after pulling 5.16 content. Does this thing any bells?
[30847.409411] INFO: task kworker/u129:4:797744 blocked for more than 122 seconds.
[30847.417999] Tainted: G S 5.16.0-rc1+ #1
[30847.424735] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this
message.
[30847.433914] task:kworker/u129:4 state:D stack: 0 pid:797744 ppid: 2
flags:0x00004000
[30847.443870] Workqueue: rpciod rpc_async_schedule [sunrpc]
[30847.450418] Call Trace:
[30847.453625] <TASK>
[30847.456388] __schedule+0x3e3/0x9a0
[30847.460769] ? _raw_spin_lock_irqsave+0x17/0x40
[30847.466219] schedule+0x44/0xc0
[30847.470093] xprt_request_dequeue_xprt+0xd1/0x140 [sunrpc]
[30847.476719] ? init_wait_var_entry+0x50/0x50
[30847.481904] ? rpc_destroy_wait_queue+0x10/0x10 [sunrpc]
[30847.488238] xprt_release+0x26/0x140 [sunrpc]
[30847.493575] ? rpc_destroy_wait_queue+0x10/0x10 [sunrpc]
[30847.499920] rpc_release_resources_task+0xe/0x50 [sunrpc]
[30847.506352] __rpc_execute+0x25d/0x460 [sunrpc]
[30847.511825] rpc_async_schedule+0x29/0x40 [sunrpc]
[30847.517627] process_one_work+0x1cb/0x3a0
[30847.522472] worker_thread+0x30/0x380
[30847.526895] ? process_one_work+0x3a0/0x3a0
[30847.531896] kthread+0x167/0x190
[30847.535845] ? set_kthread_struct+0x40/0x40
[30847.540850] ret_from_fork+0x22/0x30
[30847.545164] </TASK>
-Denny
^ permalink raw reply [flat|nested] 2+ messages in thread
* Re: NFS problem in 5.16 merge content
2021-11-23 22:19 NFS problem in 5.16 merge content Dennis Dalessandro
@ 2021-11-23 23:40 ` Chuck Lever III
0 siblings, 0 replies; 2+ messages in thread
From: Chuck Lever III @ 2021-11-23 23:40 UTC (permalink / raw)
To: Dennis Dalessandro; +Cc: linux-rdma, Linux NFS Mailing List
Hi Dennis-
> On Nov 23, 2021, at 5:19 PM, Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com> wrote:
>
> Seeing NFS RDMA failures after pulling 5.16 content. Does this thing any bells?
No bells here.... but I don't see anything RDMA-related below.
If you can reproduce the issue:
1. # trace-cmd record -e sunrpc -e rpcrdma -e rdma_core -e rdma_cma
2. ... reproduce ...
3. ^C trace-cmd
4. Compress and e-mail the trace.dat file to me.
> [30847.409411] INFO: task kworker/u129:4:797744 blocked for more than 122 seconds.
> [30847.417999] Tainted: G S 5.16.0-rc1+ #1
> [30847.424735] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this
> message.
> [30847.433914] task:kworker/u129:4 state:D stack: 0 pid:797744 ppid: 2
> flags:0x00004000
> [30847.443870] Workqueue: rpciod rpc_async_schedule [sunrpc]
> [30847.450418] Call Trace:
> [30847.453625] <TASK>
> [30847.456388] __schedule+0x3e3/0x9a0
> [30847.460769] ? _raw_spin_lock_irqsave+0x17/0x40
> [30847.466219] schedule+0x44/0xc0
> [30847.470093] xprt_request_dequeue_xprt+0xd1/0x140 [sunrpc]
> [30847.476719] ? init_wait_var_entry+0x50/0x50
> [30847.481904] ? rpc_destroy_wait_queue+0x10/0x10 [sunrpc]
> [30847.488238] xprt_release+0x26/0x140 [sunrpc]
> [30847.493575] ? rpc_destroy_wait_queue+0x10/0x10 [sunrpc]
> [30847.499920] rpc_release_resources_task+0xe/0x50 [sunrpc]
> [30847.506352] __rpc_execute+0x25d/0x460 [sunrpc]
> [30847.511825] rpc_async_schedule+0x29/0x40 [sunrpc]
> [30847.517627] process_one_work+0x1cb/0x3a0
> [30847.522472] worker_thread+0x30/0x380
> [30847.526895] ? process_one_work+0x3a0/0x3a0
> [30847.531896] kthread+0x167/0x190
> [30847.535845] ? set_kthread_struct+0x40/0x40
> [30847.540850] ret_from_fork+0x22/0x30
> [30847.545164] </TASK>
>
> -Denny
--
Chuck Lever
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2021-11-23 23:40 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-11-23 22:19 NFS problem in 5.16 merge content Dennis Dalessandro
2021-11-23 23:40 ` Chuck Lever III
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.