Skip site navigation (1)Skip section navigation (2)
Date:      Tue, 24 Jun 2014 10:14:06 -0400
From:      Mike Tancsa <mike@sentex.net>
To:        Rick Macklem <rmacklem@uoguelph.ca>
Cc:        FreeBSD-STABLE Mailing List <freebsd-stable@freebsd.org>
Subject:   Re: nfs slowdown (RELENG_8)
Message-ID:  <53A987AE.8060708@sentex.net>
In-Reply-To: <53A978D1.2000207@sentex.net>
References:  <2091718059.2982836.1403563319620.JavaMail.root@uoguelph.ca> <53A978D1.2000207@sentex.net>

next in thread | previous in thread | raw e-mail | index | archive | help
On 6/24/2014 9:10 AM, Mike Tancsa wrote:
> On 6/23/2014 6:41 PM, Rick Macklem wrote:
>>>
>> I suggest you try disabling TSO on the nics (or setting wsize=32786
>> on all mounts). Usually such slowdowns are related to the underlying
>> network fabric and there are known TSO issues for nics/drivers that
>> only handle 32 transmit buffers when 64K writes are being used.
>
> Thanks Rick,
>      I tried that. Both doing ifconfig em1 -tso and set net.inet.tcp.tso
> to 0.  No impact on these particular boxes.  Mount is done
>
>
> /sbin/mount_nfs -o tcp,rsize=32768,wsize=32768,async
>
> I looked at the tcpdump between the working and non working servers and
> they look identical.  Tried changing switch ports and the problem does
> not follow the port, only the server.

I also just tried with an igb nic and the same issue.  These are i386 
boxes. I wonder if its something to do with that. (non PAE kernel)

	---Mike


-- 
-------------------
Mike Tancsa, tel +1 519 651 3400
Sentex Communications, mike@sentex.net
Providing Internet services since 1994 www.sentex.net
Cambridge, Ontario Canada   http://www.tancsa.com/



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?53A987AE.8060708>