| To: | Nivedita Singhvi <niv@xxxxxxxxxx>, Andi Kleen <ak@xxxxxxx> |
|---|---|
| Subject: | Re: Early SPECWeb99 results on 2.5.33 with TSO on e1000 |
| From: | "Martin J. Bligh" <Martin.Bligh@xxxxxxxxxx> |
| Date: | Fri, 06 Sep 2002 12:45:39 -0700 |
| Cc: | linux-kernel@xxxxxxxxxxxxxxx, netdev@xxxxxxxxxxx |
| In-reply-to: | <1031339954.3d78ffb257d22@imap.linux.ibm.com> |
| References: | <1031339954.3d78ffb257d22@imap.linux.ibm.com> |
| Reply-to: | "Martin J. Bligh" <Martin.Bligh@xxxxxxxxxx> |
| Sender: | netdev-bounce@xxxxxxxxxxx |
> Tthere is some cacheline thrashing hurting the NUMA > more than other systems here too.. There is no NUMA here ... the clients are 4 single node SMP systems. We're using the old quads to make them, but they're all split up, not linked together into one system. Sorry if we didn't make that clear. M. |
| Previous by Date: | Re: Early SPECWeb99 results on 2.5.33 with TSO on e1000, Nivedita Singhvi |
|---|---|
| Next by Date: | Re: Early SPECWeb99 results on 2.5.33 with TSO on e1000, Gerrit Huizenga |
| Previous by Thread: | Re: Early SPECWeb99 results on 2.5.33 with TSO on e1000, Nivedita Singhvi |
| Next by Thread: | Re: Early SPECWeb99 results on 2.5.33 with TSO on e1000, Gerrit Huizenga |
| Indexes: | [Date] [Thread] [Top] [All Lists] |