NFS on ZFS pure SSD pool

[Rick Macklem]

Sam Fourman Jr. wrote:
> 
> > 
> 
> 
> 
> 
> You could try this patch:
> http://people.freebsd.org/~rmacklem/drc4-stable9.patch
> - After applying the patch and booting a kernel built from the
> patched
> sources, you need to increase the value of vfs.nfsd.tcphighwater.
> (Try something like 5000 for it as a starting point.)
> 
> Although this patch is somewhat different code, it should be
> semantically
> the same as r254337 in head, that is scheduled to be MFC'd to
> stable/9 in
> a couple of weeks.
> 
> 
> 
> 
> Does anyone know why the server would get these errors?
> 
> 
> $ cat /var/log/messages | grep failed
> Aug 30 10:22:20 students nfsd[1978]: accept failed: Software caused
> connection abort
> Aug 30 10:27:16 students nfsd[1978]: accept failed: Software caused
> connection abort
> Aug 30 11:46:30 students nfsd[1978]: accept failed: Software caused
> connection abort
> Aug 30 11:47:10 students nfsd[1978]: accept failed: Software caused
> connection abort
> 
Since the master socket that is accepting connections isn't being closed,
I believe this error (ECONNABORTED returned by accept()) occurs when the
client closes the new TCP connection before it has been accepted. Why
would an NFS client do this? I have no idea.

You might want to post on freebsd-net at freebsd.org with a subject line
like "When does accept(2) fail with ECONNABORTED?" to try and confirm the
above.

rick

> 
> 
> --
> 
> Sam Fourman Jr.
>