dev.ix.0.queueX.interrupt_rate

[Slawa Olhovchenkov]

On Wed, Aug 26, 2015 at 08:31:14AM +0200, Gerrit K"uhn wrote:

> On Tue, 25 Aug 2015 19:45:08 +0300 Slawa Olhovchenkov <slw at zxy.spb.ru>
> wrote about Re: dev.ix.0.queueX.interrupt_rate:
> 
> SO> For discover poor network performance you need:
> 
> [...]
> 
> I am already through this, see
> <https://lists.freebsd.org/pipermail/freebsd-net/2015-June/042536.html>

I am don't subscribe to freebsd-net.
I am quick look into thread and don't see this information.
For you case collet also `top -PHS` and may be you need capture nfs
seession by tcpdump and analize this by wireshark (may be solaris
servered synchronus write).

> I just wanted to let /you/ know that my interrupt rates look similar (you
> asked for that).

My case is very special -- I am realy have 3Mpps syn-flood and try to
mitigate this by netmap filtering.

> I think there are a couple of people on the mailing lists reporting
> performance issues with ix interfaces and (especially?) NFS lately. Would
> be great if we could find and fix the root cause(s)...

Nobody do instrumental analysis. I see only guesting.

My experience talk: before solve software problem make sure no
hardware problem. For this need to collect `show interface`, netstat
and etc.

My experience talk: before tuning make sure what tuning need and so.
For this need capturing nfs session and analise by wireshark.
May be just solaris on every write do sync.