2003-05-12 14:39:27

by Olof Johansson

Subject: [PATCH] TCP nfsd connection hangs when partial record header is received

Below patch resolves a hang where a TCP nfsd connection will hang even
though new data is received on the socket. We've seen this a few times in
our lab, but it usually happened every few weeks.

If a short record header is received, the SK_BUSY flag is never cleared,
and even though new data arrives, it will not be handled. This in turn
leads to hangs of particular clients (while others will continue to work
without problem).

I also changed the return code for that condition to be the same as for a
(regular) short read.

Patch is against 2.4.20.


Thanks,

Olof


--- net/sunrpc/svcsock.c.orig 2002-11-28 17:53:16.000000000 -0600
+++ net/sunrpc/svcsock.c 2003-05-12 09:33:42.000000000 -0500
@@ -819,8 +819,12 @@ svc_tcp_recvfrom(struct svc_rqst *rqstp)
if ((len = svc_recvfrom(rqstp, &iov, 1, want)) < 0)
goto error;
svsk->sk_tcplen += len;
- if (len < want)
- return 0;
+ if (len < want) {
+ dprintk("svc: short recvfrom while reading record length (%d of %d)\n",
+ len, want);
+ svc_sock_received(svsk);
+ return -EAGAIN; /* record header not complete */
+ }

svsk->sk_reclen = ntohl(svsk->sk_reclen);
if (!(svsk->sk_reclen & 0x80000000)) {


---
Olof Johansson Office: 4E002/905
pSeries Linux Development IBM Systems Group
Email: [email protected] Phone: 512-838-9858



-------------------------------------------------------
Enterprise Linux Forum Conference & Expo, June 4-6, 2003, Santa Clara
The only event dedicated to issues related to Linux enterprise solutions
http://www.enterpriselinuxforum.com

_______________________________________________
NFS maillist - [email protected]
https://lists.sourceforge.net/lists/listinfo/nfs

2003-05-13 05:17:43

by NeilBrown

Subject: Re: [PATCH] TCP nfsd connection hangs when partial record header is received

On Monday May 12, [email protected] wrote:
> Below patch resolves a hang where a TCP nfsd connection will hang even
> though new data is received on the socket. We've seen this a few times in
> our lab, but it usually happened every few weeks.
>
> If a short record header is received, the SK_BUSY flag is never cleared,
> and even though new data arrives, it will not be handled. This in turn
> leads to hangs of particular clients (while others will continue to work
> without problem).
>
> I also changed the return code for that condition to be the same as for a
> (regular) short read.
>
> Patch is against 2.4.20.

Thanks. It is needed for 2.5 as well.
I have added it to my patch collections for each and they should get
to Marcelo/Linus eventually.

NeilBrown


-------------------------------------------------------
Enterprise Linux Forum Conference & Expo, June 4-6, 2003, Santa Clara
The only event dedicated to issues related to Linux enterprise solutions
http://www.enterpriselinuxforum.com

_______________________________________________
NFS maillist - [email protected]
https://lists.sourceforge.net/lists/listinfo/nfs