Hi all,
I was rudely awakened this morning to find that my 8.2 box NFS server crashed bringing down my vmware cluster. I'm running ZFS, and it was running well for a couple of months, did a restart over the weekend.
I logged into my FreeBSD box, I fired up top, and I saw nfsd was in some sort of buf_ha state. I have nfsd running with 16 threads, and I have 10 nodes connected to it.
I couldn't restart using the rc script, or kill. Since this is a production setup, I didn't have time to debug so I was forced to do a reboot -n.
In desperation this morning I upped my threads to 100, not sure if it will solve anything. I am about to take off on holidays this weekend, don't want to lose sleep over NFS stability. Anyone have any ideas to improve nfsd stability, or steps I can do to next time to provide useful debugging information?
Thanks,
Chris
I was rudely awakened this morning to find that my 8.2 box NFS server crashed bringing down my vmware cluster. I'm running ZFS, and it was running well for a couple of months, did a restart over the weekend.
I logged into my FreeBSD box, I fired up top, and I saw nfsd was in some sort of buf_ha state. I have nfsd running with 16 threads, and I have 10 nodes connected to it.
I couldn't restart using the rc script, or kill. Since this is a production setup, I didn't have time to debug so I was forced to do a reboot -n.
In desperation this morning I upped my threads to 100, not sure if it will solve anything. I am about to take off on holidays this weekend, don't want to lose sleep over NFS stability. Anyone have any ideas to improve nfsd stability, or steps I can do to next time to provide useful debugging information?
Thanks,
Chris