If you have a GPFS support contract for this cluster, please open a PMR. Unanswered question This question has not been answered yet. Hello, I have configured NFS Server 1 IBM Web Server. User Name Remember Me?
Thanks for you help, I can see that I have a looong way to go. I don't think the error is that simple, otherwise the symptom would be a little more famous. Results 1 to 2 of 2 Thread: NFS & tcpdump error in CentOS Thread Tools Show Printable Version Email this Page… Subscribe to this Thread… Display Linear Mode Switch to Hybrid AndyGreen8th May 2005, 04:46 PMI am thinking about the cables and the hubs/switches inbetween then. https://groups.google.com/d/topic/vglug/6xNZ6a6yDfA
Wireshark/TShark should do a better job of this, for two reasons: 1) it does reassembly of ONC RPC requests and replies over TCP, as well as handling TCP segments with multiple The next step would be to collect a GPFS trace covering the event and send it to IBM Support. Vyas Reply With Quote 02-15-2010 #2 Rubberman View Profile View Forum Posts Private Message View Articles Linux Guru Join Date Apr 2009 Location I can be found either 40 miles west it will have a fragment offset of 0, and can be identified by looking at the IP header.
I will try the tcdump when I get home. This can cause packets to be mis-dissected; the apparent RPC errors you're seeing are probably examples of that. I have disconnected the cable modem from the router to see if that makes a difference and it doesn't. That part of the code has changed in tcpdump-3.9.7, which we installed, and now gives : 16:01:19.890794 IP nfs_server.nfs > client_46.1205729087: reply Unknown rpc response code=3128327487 1448 16:01:19.890831 IP nfs_server.nfs >
Now I wouldn't expect tcpdump to implement the whole (probably quite complicated) segmentation logic of wireshark, but retitling the very misleading "ERR" to, perhaps, "Unknown" would be appropriate: there is no I've tried other NSD servers in the cluster as well (using them to export the fs), with the same Stale file handle results. A switch or router is failing. 5. I also ran tcpdump on my workstation when trasferring a file via nfs from my server to my workstation and I found this rather odd line at the very end of
AndyGreen4th May 2005, 07:58 AMStill interested in...mii-tool eth0Scott. Full text and rfc822 format available. Message #5 received at [email protected] (full text, mbox, reply): From: Adrian von Bidder
I am sure that there is some log that provides a clue, unfortunately as I originally stated I am very new to this (about a month) and it seems that I Just remember, Semper Gumbi - always be flexible! Previous message View by thread View by date Next message [tcpdump-workers] RPC responde code question (print-nfs.c) Alex Still Re: [tcpdump-workers] RPC responde code question (print-nf... I use to think I was a reasonably intelligent person, and then I installed linux on a Dell server.
Quote Postby pschaff » 2010/02/16 14:45:21 Welcome to the CentOS fora.Have you checked to be sure nothing else on the network is using a duplicate network address? By Date By Thread Current thread: RPC responde code question (print-nfs.c) Alex Still (Sep 05) Re: RPC responde code question (print-nfs.c) Guy Harris (Sep 05) Re: RPC responde code question Google shows other ERR output from tcpdump can discuss problems with illegal flags. A cable is bad. 3.
Other than that it is pretty generic. Home Forum Today's Posts | FAQ | Calendar | Community Groups | Forum Actions Mark Forums Read | Quick Links View Site Leaders | Unanswered Posts | Forum Rules Articles Marketplace I don't understand what's happening here.
We're seeing a lot of these : [..] 16:01:19.890794 IP nfs_server.nfs > client_46.1205729087: reply ERR 1448 16:01:19.890831 IP nfs_server.nfs > client_46.3664003007: reply ERR 1448 [..] That seems to be an RPC I am running NFS, Samba, MySQL. I've played around with maxfilestocache, changing the value to 10000, this did not help. Drivers????
Not sure if that would matter but, the server is a solaris 10, linux fedora clients, NFSv3 over TCP. I'll see whether that could be done. - This is the tcpdump-workers list. Visit https://cod.sandelman.ca/ to unsubscribe. scottthepotter8th May 2005, 05:26 PMYes, I thought that it was a bit strange myself.
I redirected the output to a file, so rather than bore you with the 7 and a half minutes of out put I will just post a small sampling that was Now, today i was having slow response on IBM Web Server & by measuring the NFS, i found below error while running "tcpdump" command. Show: 10 25 50 100 items per page Previous Next Feed for this topic Skip to site navigation (Press enter) Re: [tcpdump-workers] RPC responde code question (print-nfs.c) Guy Harris Wed, 05 You may have to register before you can post: click the register link above to proceed.
Yes. Some hours later I discovered, when cross-checking tcpdump output with wireshark's output, that these supposed "Errors" are only segments of NFS requests/replies that get reassembled -- wireshark shows this nicely: the To start viewing messages, select the forum that you want to visit from the selection below. ** If you are logged in, most ads will not be displayed. ** Linuxforums now I have ran "tcpdump" command on NFS Server.
Now, Today i was having slow response on IBM Web Server & by measuring the NFS, i found below error while running "tcpdump" command on CentOS Server.tcpdump -n -i eth1 | A tcp dump reveals: 21:22:52.270974 storage-fe-2.nfs > compute-node-100.3212161118: reply ok 28 getattr ERROR: Stale NFS file handle (DF) 21:22:52.270999 compute-node-100.3228938334 > storage-fe-2.nfs: 140 getattr nfs (DF) 21:22:52.271246 storage-fe-2.nfs > compute-node-100.3228938334: reply Don't really understand what is going on. let it be and forget about it.
w5set4th May 2005, 06:28 AMTry an old 10/100 card in the server if possible. Log in to reply. I can copy a file to the server, and it happens as one would expect using 100T. Join our community today!
Thanks for the reply. Mijn accountZoekenMapsYouTubePlayNieuwsGmailDriveAgendaGoogle+VertalenFoto'sMeerShoppingDocumentenBoekenBloggerContactpersonenHangoutsNog meer van GoogleInloggenVerborgen veldenZoeken naar groepen of berichten Register Help Remember Me? Updated on 2006-03-02T16:07:50Z at 2006-03-02T16:07:50Z by SystemAdmin bevans 120000CAP9 36 Posts Re: GPFS over NFS 2006-03-02T08:45:41Z This is the accepted answer. Toggle useless messagesView this report as an mbox folder, status mbox, maintainer mbox Report forwarded to [email protected], Romain Francoise
This just seems to be a problem when the server is "sending' files. Anything nonzero in there on either side?