We run a couple of NFS servers (RedHat 3.0, 2.4.21-15.0.3, nfs-utils
1.0.6) that have access to the same underlying file system (GPFS).
Sometimes the servers stop responding to mount requests. Clients give up
with 'RPC: Timed out messages'. A second later all is green again and
mount requests go through without a hitch.
I have included a server side tcpdump trace of a client trying to mount
an export which gives up with a 'RPC: Timed out' response. What could be
the reason for the momentary failure? The servers handle 5 to 10 mounts
and unmounts per minute. /var/lib/nfs/rmtab has some 1000 - 1300
entries. Is there something to look for? Can you help? Thanks.
[root@f01-010-103 root]# tcpdump host l01-001-118
tcpdump: listening on eth0
23:35:26.742161 l01-001-118.784 > f01-010-103.sunrpc: S
682592854:682592854(0) win 5840 <mss 1460,sackOK,timestamp 36812367
0,nop,wscale 0> (DF)
23:35:26.742186 f01-010-103.sunrpc > l01-001-118.784: S
3720816568:3720816568(0) ack 682592855 win 5792 <mss
1460,sackOK,timestamp 2711116 36812367,nop,wscale 0> (DF)
23:35:26.742270 l01-001-118.784 > f01-010-103.sunrpc: . ack 1 win 5840
<nop,nop,timestamp 36812367 2711116> (DF)
23:35:26.742323 l01-001-118.784 > f01-010-103.sunrpc: P 1:45(44) ack 1
win 5840 <nop,nop,timestamp 36812367 2711116> (DF)
23:35:26.742330 f01-010-103.sunrpc > l01-001-118.784: . ack 45 win 5792
<nop,nop,timestamp 2711116 36812367> (DF)
23:35:26.742466 f01-010-103.sunrpc > l01-001-118.784: P 1:401(400) ack
45 win 5792 <nop,nop,timestamp 2711116 36812367> (DF)
23:35:26.742554 l01-001-118.784 > f01-010-103.sunrpc: . ack 401 win 6432
<nop,nop,timestamp 36812367 2711116> (DF)
23:35:26.742561 f01-010-103.sunrpc > l01-001-118.784: P 401:597(196) ack
45 win 5792 <nop,nop,timestamp 2711116 36812367> (DF)
23:35:26.742638 l01-001-118.784 > f01-010-103.sunrpc: . ack 597 win 7504
<nop,nop,timestamp 36812367 2711116> (DF)
23:35:26.742660 l01-001-118.784 > f01-010-103.sunrpc: F 45:45(0) ack 597
win 7504 <nop,nop,timestamp 36812367 2711116> (DF)
23:35:26.742681 f01-010-103.sunrpc > l01-001-118.784: F 597:597(0) ack
46 win 5792 <nop,nop,timestamp 2711116 36812367> (DF)
23:35:26.742756 l01-001-118.784 > f01-010-103.sunrpc: . ack 598 win 7504
<nop,nop,timestamp 36812367 2711116> (DF)
23:35:26.742779 l01-001-118.785 > f01-010-103.859: udp 124 (DF)
23:35:29.743481 l01-001-118.785 > f01-010-103.859: udp 124 (DF)
23:35:32.753998 l01-001-118.785 > f01-010-103.859: udp 124 (DF)
23:35:35.764540 l01-001-118.785 > f01-010-103.859: udp 124 (DF)
23:35:38.775053 l01-001-118.785 > f01-010-103.859: udp 124 (DF)
23:35:41.785575 l01-001-118.785 > f01-010-103.859: udp 124 (DF)
23:35:44.796101 l01-001-118.785 > f01-010-103.859: udp 124 (DF)
19 packets received by filter
0 packets dropped by kernel
[root@f01-010-103 root]#
-------------------------------------------------------
The SF.Net email is sponsored by: Beat the post-holiday blues
Get a FREE limited edition SourceForge.net t-shirt from ThinkGeek.
It's fun and FREE -- well, almost....http://www.thinkgeek.com/sfshirt
_______________________________________________
NFS maillist - [email protected]
https://lists.sourceforge.net/lists/listinfo/nfs
On Thu, Jan 06, 2005 at 12:03:56AM +0100, Jos van Wezel wrote:
> We run a couple of NFS servers (RedHat 3.0, 2.4.21-15.0.3, nfs-utils
> 1.0.6) that have access to the same underlying file system (GPFS).
> Sometimes the servers stop responding to mount requests. Clients give up
> with 'RPC: Timed out messages'. A second later all is green again and
> mount requests go through without a hitch.
Can your reproduce the issues without propritary (GFPS) or know
totally buggy (it's clue code) modules loaded?
-------------------------------------------------------
The SF.Net email is sponsored by: Beat the post-holiday blues
Get a FREE limited edition SourceForge.net t-shirt from ThinkGeek.
It's fun and FREE -- well, almost....http://www.thinkgeek.com/sfshirt
_______________________________________________
NFS maillist - [email protected]
https://lists.sourceforge.net/lists/listinfo/nfs