lkml.org 
[lkml]   [1998]   [Aug]   [16]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
SubjectRe: [PATCH]: Push tcp rpc handling into task context
Date
> to be fine, but large writes still fail and hang the whole nfs filesystem
> code.

Ok. That means we are half way there. I'll now chase through all the write
side logic for naughties. Im doing this all loopback, and that may have
hidden the problems on write

> apparently random amount of data (139264 bytes in one case, but it's not
> constant). The kernel spits out the message "rpciod_down: waiting for pid
> xxx to exit", where pid xxx is an rpciod kernel thread.

Uggh. That isnt good

> - if a mount hangs, it will hang for ever; on solaris however a SIGINT
> solves the problem very quickly.

Thats actually a generic rpc layer problem. Its not one of the big hard
ones to fix

> - if _anything_ hangs in the NFS client code, if a server goes down... etc
> etc, there is no way to back out without a reboot. Again, a SIGINT or a
> SIGKILL on solaris solves the problem in a matter of seconds.

If the rpc io daemon logic crashes you are screwed. The other cases I've
not seen. Also note that sigint/sigkill kill a process in soft or hard,intr
mount styles in Linux as well. "hard" mounts try forever as per the man
pages.

Also if you have a umount that uses the new umount call then a forced
umount gets you out of a hard nfs hang.

It wont get you out of a stuck mount - the situation there is that
the superblock semaphore is held by the mount process and the synchronous
rpc code has signal catching commented out for some reason I don't yet
follow and its original author forgot to comment.


>
> - when the above happens, NFS access it completely screwed, any NFS access
> to any server will hang as well.
>
>
> Ion
>
> --
> It is better to keep your mouth shut and be thought a fool,
> than to open it and remove all doubt.
>
>


-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.altern.org/andrebalsa/doc/lkml-faq.html

\
 
 \ /
  Last update: 2005-03-22 13:44    [W:0.032 / U:1.984 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site