| To: | Benjamin LaHaise <bcrl@xxxxxxxxxx> |
|---|---|
| Subject: | Re: Poor gige performance with 2.4.20-pre* |
| From: | Richard Gooch <rgooch@xxxxxxxxxxxxxxx> |
| Date: | Sun, 29 Sep 2002 18:53:18 -0600 |
| Cc: | "Xiaoliang (David) Wei" <weixl@xxxxxxxxxxx>, netdev@xxxxxxxxxxx |
| In-reply-to: | <20020929204510.A26826@xxxxxxxxxx> |
| References: | <200209282257.g8SMvta32527@xxxxxxxxxxxxxxxxxxxxxxxx> <002f01c2675d$b642b640$f5f2010a@weixl> <200209290634.g8T6Y2o08439@xxxxxxxxxxxxxxxxxxxxxxxx> <20020929204510.A26826@xxxxxxxxxx> |
| Sender: | netdev-bounce@xxxxxxxxxxx |
Benjamin LaHaise writes:
> On Sun, Sep 29, 2002 at 12:34:02AM -0600, Richard Gooch wrote:
> > This is all on a LAN (of course; expecting good performance from a WAN
> > is pretty futile). I use a buffer size of 256 KiB.
>
> From my experience tuning on a 550MHz P3 Xeon, you're better off
> using a buffer size of 8-16KB that stays in the L1 cache. Of
> course, that was without actually doing anything useful with the
> data being transferred. Gige really does need a faster cpu in the
> ghz+ range. As for ns83820, it's a work in progress. Some of the
> recent bugfixes may have reduced performance, so it may need to be
> retuned.
Using 8 KiB buffer reduces performance, 16 KiB is almost the same as
using 256 KiB.
Regards,
Richard....
Permanent: rgooch@xxxxxxxxxxxxx
Current: rgooch@xxxxxxxxxxxxxxx
|
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: Poor gige performance with 2.4.20-pre*, Benjamin LaHaise |
|---|---|
| Next by Date: | Re: [BK PATCH] Make eth.c independent of dev->hard_header_len, David S. Miller |
| Previous by Thread: | Re: Poor gige performance with 2.4.20-pre*, Benjamin LaHaise |
| Next by Thread: | Re: Poor gige performance with 2.4.20-pre*, Ben Greear |
| Indexes: | [Date] [Thread] [Top] [All Lists] |