On Mon, Dec 8, 2008 at 3:38 PM, J. Bruce Fields <bfields@xxxxxxxxxxxx> wrote: > So the "server" in the first paragraph is an NFS client, and its NFS > server is the FreeBSD machine? Yes > And what are the first symptoms? Any threads accessing the NFS > filesystem just hang? A sysrq-T trace on the client showing where > they're hanging might be helpful. Honestly, these are production, and I looked in every place I could think for any hints, and I get nothing. I can't really be using this to test either. What is odd is identically configured machines (down to the same files in /etc, same packages from dpkg -l etc) have no issue. For a last result, I tried different kernel versions (from Ubuntu): linux-image-2.6.27-10-server - broken linux-image-2.6.27-7-server - broken linux-image-2.6.28-2-server - i think i used this too quick and it was broken (I might be wrong and wound up deciding to go back instead of forward) linux-image-2.6.24-16-server - working for 2 days now, so sticking with it Note that all the other nodes (5 of the 6 identical nodes are fine, this was the one bad one) are running the default kernel in Intrepid at the moment: linux-image-2.6.27-10-server and don't seem to be suffering from any issues. So it seems to be a combination of those kernels + that machine. Problem is, that machine's configuration is identical - same nfs-utils, portmap, etc, etc. and from my rsync scan, even the majority of files (and anything that should be relevant) in /etc are identical too. This might be an Ubuntu bug or something flaky with 2.6.27 (maybe 2.6.28 too) and NFS in general but I don't know how I can produce any worthwhile debugging, especially considering this is in production. When I wrote this I saw no fix in place; the kernel downgrade appears to be the workaround for now. Sorry I can't be more help. At the point of this email I had the luxury of a broken setup to debug, but now that I've stabilized it I have to keep it this way :) ------------------------------------------------------------------------------ SF.Net email is Sponsored by MIX09, March 18-20, 2009 in Las Vegas, Nevada. The future of the web can't happen without you. Join us at MIX09 to help pave the way to the Next Web now. Learn more and register at http://ad.doubleclick.net/clk;208669438;13503038;i?http://2009.visitmix.com/ _______________________________________________ NFS maillist - NFS@xxxxxxxxxxxxxxxxxxxxx https://lists.sourceforge.net/lists/listinfo/nfs _______________________________________________ Please note that nfs@xxxxxxxxxxxxxxxxxxxxx is being discontinued. Please subscribe to linux-nfs@xxxxxxxxxxxxxxx instead. http://vger.kernel.org/vger-lists.html#linux-nfs -- To unsubscribe from this list: send the line "unsubscribe linux-nfs" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html