| To: | hadi@xxxxxxxxxxxxxxxx |
|---|---|
| Subject: | Re: Route cache performance under stress |
| From: | "David S. Miller" <davem@xxxxxxxxxx> |
| Date: | Tue, 10 Jun 2003 08:53:42 -0700 (PDT) |
| Cc: | ralph+d@xxxxxxxxx, xerox@xxxxxxxxxx, sim@xxxxxxxxxxxxx, fw@xxxxxxxxxxxxx, netdev@xxxxxxxxxxx, linux-net@xxxxxxxxxxxxxxx |
| In-reply-to: | <20030609204257.L35799@xxxxxxxxxxxxxxxx> |
| References: | <20030609195652.E35696@xxxxxxxxxxxxxxxx> <Pine.LNX.4.51.0306092006420.12038@xxxxxxxxxxxx> <20030609204257.L35799@xxxxxxxxxxxxxxxx> |
| Sender: | netdev-bounce@xxxxxxxxxxx |
From: Jamal Hadi <hadi@xxxxxxxxxxxxxxxx> Date: Mon, 9 Jun 2003 21:15:18 -0400 (EDT) Have you tried a different NIC? Not sure how well the 3com is maintained for example. Acutally, the main issue with 3c59x is that it still uses PIO accesses. This basically makes it useless for routing or anything wanting serious latency. Andrew Morton knows this, but he is such a good maintainer that he doesn't want to change over the MEM I/O accesses for fear of breaking something. It's actually a simple change to make if someone wants to spend a few cycles on it, then you can see what kind of performance you'll get with that. |
| Previous by Date: | [RFC] suggest changes cleanup to atm svc/pvc family, chas williams |
|---|---|
| Next by Date: | Re: Route cache performance under stress, David S. Miller |
| Previous by Thread: | Re: Real World Routers 8-), Florian Weimer |
| Next by Thread: | Re: 3c59x (was Route cache performance under stress), Bogdan Costescu |
| Indexes: | [Date] [Thread] [Top] [All Lists] |