netdev
[Top] [All Lists]

Re: RFC: NAPI packet weighting patch

To: Robert Olsson <Robert.Olsson@xxxxxxxxxxx>, netdev@xxxxxxxxxxx
Subject: Re: RFC: NAPI packet weighting patch
From: Rick Jones <rick.jones2@xxxxxx>
Date: Tue, 07 Jun 2005 16:19:46 -0700
Cc: Martin Josefsson <gandalf@xxxxxxxxxxxxxx>, jamal <hadi@xxxxxxxxxx>, Stephen Hemminger <shemminger@xxxxxxxx>, Mitch Williams <mitch.a.williams@xxxxxxxxx>, "Ronciak, John" <john.ronciak@xxxxxxxxx>, "David S. Miller" <davem@xxxxxxxxxxxxx>, mchan@xxxxxxxxxxxx, buytenh@xxxxxxxxxxxxxx, jdmason@xxxxxxxxxx, "Venkatesan, Ganesh" <ganesh.venkatesan@xxxxxxxxx>, "Brandeburg, Jesse" <jesse.brandeburg@xxxxxxxxx>
In-reply-to: <17061.52365.336303.369135@xxxxxxxxxxxx>
References: <468F3FDA28AA87429AD807992E22D07E0450C00B@orsmsx408> <Pine.CYG.4.58.0506061647340.128@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx> <42A5284C.3060808@xxxxxxxx> <1118147904.6320.108.camel@xxxxxxxxxxxxxxxxxxxxx> <Pine.LNX.4.58.0506071351080.16594@xxxxxxxxxxxxxx> <1118150948.6320.152.camel@xxxxxxxxxxxxxxxxxxxxx> <Pine.LNX.4.58.0506071432570.16594@xxxxxxxxxxxxxx> <17061.52365.336303.369135@xxxxxxxxxxxx>
Sender: netdev-bounce@xxxxxxxxxxx
User-agent: Mozilla/5.0 (X11; U; HP-UX 9000/785; en-US; rv:1.6) Gecko/20040304


 BTW, Can netperf be used for tests like this? (Rick?)

Assuming I'm translating "test like this" to the right sort of stuff :)

If one wants to see the effect of different buffer replenishment strategies, I suppose that some netperf tests could indeed be used. It would be desirable to look at service demand moreso than throughput (assuming the throughput is link-bound). TCP_STREAM and/or TCP_MAERTS. I'm not sure the extent to which it would be visible to a TCP_RR test.

Differences in service demand could also be used to measure effects of irq migration, pinning IRQs and/or processes to specific CPUs and the like. The linux processor affinity stuff in netperf could use a little help though - it is easily confused as to when to use a two argument vs three argument sched_setaffinity call. I suspect one may also see differences in TCP_RR transaction rates.

I suspect some high number of confidence interval iterations might be required.

rick jones

i'd trim individual names from the dist list, but am not 100% sure who is on netdev...

<Prev in Thread] Current Thread [Next in Thread>