There is a problem with nfs hang on my machine, Steps to reproduce:
1.
echo "options sunrpc tcp_slot_table_entries=2" >> /etc/modprobe.d/sunrpc.conf
echo "options sunrpc tcp_max_slot_table_entries=2" >> /etc/modprobe.d/sunrpc.conf
and remount nfsv3: sudo mount -t nfs -o vers=3,nolock,proto=tcp 127.0.0.1:/root/nfs_server/ /root/nfs_client/
2.Run case
# cat case.sh
while true
do
ls &
done &
while true
do
killall ls
done &
[root@cuibixuan nfs_client]# cd /root/nfs_client/; sh case.sh
3. Run 'killall sh' to kill case after waiting 10 seconds
4. The nfs hang and xprt->state is 0x212(XPRT_CONGESTED):
[root@cuibixuan sunrpc]# cat /sys/kernel/debug/sunrpc/rpc_xprt/4/info
netid: tcp
addr: 127.0.0.1
port: 2049
state: 0x212
[root@cuibixuan sunrpc]# cat /sys/kernel/debug/sunrpc/rpc_clnt/4/tasks
155 0080 -11 0x4 0x0 0 rpc_default_ops [sunrpc] nfsv3 GETATTR a:call_reserveresult [sunrpc] q:xprt_backlog
15418 0080 -11 0x4 0x0 0 rpc_default_ops [sunrpc] nfsv3 GETATTR a:call_reserveresult [sunrpc] q:xprt_backlog
5. Enable ftrace
# echo 1 > /sys/kernel/debug/tracing/events/sunrpc/enable
# cat /sys/kernel/debug/tracing/trace
...
ls-18792 [001] .... 668.541062: rpc_task_run_action: task:28885@4 flags=0080 state=0005 status=0 action=call_start [sunrpc]
ls-18792 [001] .... 668.541063: rpc_request: task:28885@4 nfsv3 GETATTR (sync)
ls-18792 [001] .... 668.541063: rpc_task_run_action: task:28885@4 flags=0080 state=0005 status=0 action=call_reserve [sunrpc]
ls-18792 [001] .... 668.541065: rpc_task_sleep: task:28885@4 flags=0080 state=0005 status=-11 timeout=0 queue=xprt_backlog
ls-18792 [000] .... 670.815066: rpc_task_wakeup: task:28885@4 flags=0180 state=0006 status=-512 timeout=0 queue=xprt_backlog
ls-18792 [000] .... 670.815069: rpc_task_run_action: task:28885@4 flags=0180 state=0005 status=-512 action=rpc_exit_task [sunrpc]
ls-18846 [001] .... 682.302970: rpc_task_begin: task:28886@4 flags=0080 state=0004 status=0 action= (null)
ls-18846 [001] .... 682.302972: rpc_task_run_action: task:28886@4 flags=0080 state=0005 status=0 action=call_start [sunrpc]
ls-18846 [001] .... 682.302973: rpc_request: task:28886@4 nfsv3 GETATTR (sync)
ls-18846 [001] .... 682.302973: rpc_task_run_action: task:28886@4 flags=0080 state=0005 status=0 action=call_reserve [sunrpc]
ls-18846 [001] .... 682.302974: rpc_task_sleep: task:28886@4 flags=0080 state=0005 status=-11 timeout=0 queue=xprt_backlog
ls-18846 [000] .... 684.690924: rpc_task_wakeup: task:28886@4 flags=0180 state=0006 status=-512 timeout=0 queue=xprt_backlog
ls-18846 [000] .... 684.690928: rpc_task_run_action: task:28886@4 flags=0180 state=0005 status=-512 action=rpc_exit_task [sunrpc]
The kernel version of my machine is 4.19.91, and it can be fixed with
the following patch (in v4.19):
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 793f595..2656048 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -1358,6 +1358,7 @@ void xprt_release(struct rpc_task *task)
if (req == NULL) {
if (task->tk_client) {
xprt = task->tk_xprt;
+ xprt_wake_up_backlog(xprt);
if (xprt->snd_task == task)
xprt_release_write(xprt, task);
}
I checked the -next code, there should be the same problem.
Bixuan Cui (1):
SUNRPC: Clean XPRT_CONGESTED of xprt->state when rpc task is killed
net/sunrpc/xprt.c | 1 +
1 file changed, 1 insertion(+)
--
1.8.3.1
