On Tue, Dec 16, 2008 at 01:05:47PM +0100, Kasparek Tomas wrote:
> On Sun, Dec 14, 2008 at 02:50:01PM -0500, Trond Myklebust wrote:
> > On Thu, 2008-12-04 at 11:23 +0100, Kasparek Tomas wrote:
> > > On Tue, Dec 02, 2008 at 01:10:07PM -0500, Trond Myklebust wrote:
> > > > On Tue, 2008-12-02 at 17:26 +0100, Kasparek Tomas wrote:
> > > >
> > > > > Did tried. The number should be seconds and defaults to 60, These
> > > > > connections are still there after several hours. Changing it to 10 (sec)
> > > > > and same behaviour. (BTW The server did not changed in last several months)
> > > >
> > > > Are you seeing the same behaviour with 'netstat -t'?
> > >
> > > yes:
> > >
> > > root@pckasparek: ~# ssh root@pcnlp1 'netstat -pan | grep WAIT' | cut -c-85
> > > tcp 0 0 147.229.12.146:989 147.229.176.14:2049 FIN_WAIT2
> > > root@pckasparek: ~# ssh root@pcnlp1 'netstat -t | grep WAIT' | cut -c-85
> > > tcp 0 0 pcnlp1.fit.vutbr.:ftps-data eva.fit.vutbr.cz:nfs FIN_WAIT2
> > >
> > > but it should be the same, did't it? -t just selects TCP connections and
> > > this is TCP connection so it shows the same
> >
> > Right, but the point is that the client is in the state FIN_WAIT2, which
> > means that it has closed the socket on its end, and is waiting for the
> > server to close on its end. The fact that the server is failing to do
> > this is a server bug.
> >
> > That said, we can't wait forever for buggy servers. I see now why the
> > linger2 stuff isn't working. I believe that the appended patch should
> > help...
>
> Hm, not happy to say that but it still does not work after some time. Now
> the problem is opposite there are no connections to the server according to
> netstat on client, just time to time there is
>
> pcnlp1.fit.vutbr.cz.15234 > kazi.fit.vutbr.cz.nfs: 40 null
> kazi.fit.vutbr.cz.nfs > pcnlp1.fit.vutbr.cz.15234: reply ok 24 null
>
> (kazi is server). Will try to investigate more details.
>
> (just to remember the same kernel with reversed
> e06799f958bf7f9f8fae15f0c6f519953fb0257c works fine - exact patch is
> included - it was slightly modified to fit 2.6.27.x kernels)
>
> Thank you very much for your help so far.
just the forgoten patch promised.
--
Tomas Kasparek, PhD student E-mail: kasparek@xxxxxxxxxxxx
CVT FIT VUT Brno, L127 Web: http://www.fit.vutbr.cz/~kasparek
Bozetechova 1, 612 66 Fax: +420 54114-1270
Brno, Czech Republic Phone: +420 54114-1220
jabber: tomas.kasparek@xxxxxxxxx
GPG: 2F1E 1AAF FD3B CFA3 1537 63BD DCBE 18FF A035 53BC
diff -ruN linux-2.6.27.4/net/sunrpc/xprtsock.c linux-2.6.27.4-64/net/sunrpc/xprtsock.c
--- linux-2.6.27.4/net/sunrpc/xprtsock.c 2008-11-04 14:30:26.000000000 +0100
+++ linux-2.6.27.4-64/net/sunrpc/xprtsock.c 2008-11-25 19:11:34.000000000 +0100
@@ -615,22 +615,6 @@
return status;
}
-/**
- * xs_tcp_shutdown - gracefully shut down a TCP socket
- * @xprt: transport
- *
- * Initiates a graceful shutdown of the TCP socket by calling the
- * equivalent of shutdown(SHUT_WR);
- */
-static void xs_tcp_shutdown(struct rpc_xprt *xprt)
-{
- struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
- struct socket *sock = transport->sock;
-
- if (sock != NULL)
- kernel_sock_shutdown(sock, SHUT_WR);
-}
-
static inline void xs_encode_tcp_record_marker(struct xdr_buf *buf)
{
u32 reclen = buf->len - sizeof(rpc_fraghdr);
@@ -709,7 +693,8 @@
dprintk("RPC: sendmsg returned unrecognized error %d\n",
-status);
clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);
- xs_tcp_shutdown(xprt);
+ xprt_disconnect_done(xprt);
+ break;
}
return status;
@@ -1670,7 +1655,8 @@
break;
default:
/* get rid of existing socket, and retry */
- xs_tcp_shutdown(xprt);
+ xs_close(xprt);
+ break;
}
}
out:
@@ -1729,7 +1715,8 @@
break;
default:
/* get rid of existing socket, and retry */
- xs_tcp_shutdown(xprt);
+ xs_close(xprt);
+ break;
}
}
out:
@@ -1776,19 +1763,6 @@
}
}
-static void xs_tcp_connect(struct rpc_task *task)
-{
- struct rpc_xprt *xprt = task->tk_xprt;
-
- /* Initiate graceful shutdown of the socket if not already done */
- if (test_bit(XPRT_CONNECTED, &xprt->state))
- xs_tcp_shutdown(xprt);
- /* Exit if we need to wait for socket shutdown to complete */
- if (test_bit(XPRT_CLOSING, &xprt->state))
- return;
- xs_connect(task);
-}
-
/**
* xs_udp_print_stats - display UDP socket-specifc stats
* @xprt: rpc_xprt struct containing statistics
@@ -1859,12 +1833,12 @@
.release_xprt = xs_tcp_release_xprt,
.rpcbind = rpcb_getport_async,
.set_port = xs_set_port,
- .connect = xs_tcp_connect,
+ .connect = xs_connect,
.buf_alloc = rpc_malloc,
.buf_free = rpc_free,
.send_request = xs_tcp_send_request,
.set_retrans_timeout = xprt_set_retrans_timeout_def,
- .close = xs_tcp_shutdown,
+ .close = xs_close,
.destroy = xs_destroy,
.print_stats = xs_tcp_print_stats,
};
