Date: Sat, 06 Jul 2002 14:54:48 -0700 (PDT) From: John Polstra <jdp@polstra.com> To: stable@freebsd.org Subject: NFS errors at high hz values with TCP mounts Message-ID: <XFMail.20020706145448.jdp@polstra.com>
next in thread | raw e-mail | index | archive | help
I am seeing some strange NFS client behavior on a 4.6-stable system
running at hz=10000. The system is plenty fast enough for this hz
value, and everything else has been working great for months in this
configuration.
I set the hz value in /boot/loader.conf like this:
kern.hz="10000"
Here's what happens when I try to copy a 512 kbyte file from the
hz=10000 client to a server that is NFS-mounted:
thin$ dd if=/dev/zero of=/mnt/foo count=1000
dd: /mnt/foo: Resource temporarily unavailable
61+0 records in
60+0 records out
30720 bytes transferred in 0.000996 secs (30843571 bytes/sec)
This is completely repeatable. It only happens when hz is set high
and a TCP mount is used. If hz is reduced to the default of 100, the
problem does not occur. Likewise, if a UDP mount is used the problem
does not occur. With TCP mounts, it happens whether NFS version 2
or version 3 is used. The "soft" and "intr" options don't make any
difference.
Copying a file in the other direction, from server to client, works
fine.
Any ideas?
John
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-stable" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?XFMail.20020706145448.jdp>