| To: | ralph+d@xxxxxxxxx, ralph@xxxxxxxxx |
|---|---|
| Subject: | Re: Route cache performance under stress |
| From: | "David S. Miller" <davem@xxxxxxxxxx> |
| Date: | Tue, 10 Jun 2003 10:32:34 -0700 (PDT) |
| Cc: | hadi@xxxxxxxxxxxxxxxx, xerox@xxxxxxxxxx, sim@xxxxxxxxxxxxx, fw@xxxxxxxxxxxxx, netdev@xxxxxxxxxxx, linux-net@xxxxxxxxxxxxxxx |
| In-reply-to: | <Pine.LNX.4.51.0306101332300.8755@xxxxxxxxxxxx> |
| References: | <Pine.LNX.4.51.0306092006420.12038@xxxxxxxxxxxx> <20030610.084940.74727904.davem@xxxxxxxxxx> <Pine.LNX.4.51.0306101332300.8755@xxxxxxxxxxxx> |
| Sender: | netdev-bounce@xxxxxxxxxxx |
From: Ralph Doncaster <ralph@xxxxxxxxx> Date: Tue, 10 Jun 2003 13:33:01 -0400 (EDT) On Tue, 10 Jun 2003, David S. Miller wrote: > When packet (more specifically, software interrupt) processing > reaches a certain level, we offload the work into process context. That sounds good. Adjust the nice value of the ksoftirqd tasks, that's the only thing available. But your problem has to do with all the PIO accesses, that absolutely kills the machine. |
| Previous by Date: | Re: 3c59x, David S. Miller |
|---|---|
| Next by Date: | Re: 3c59x, chas williams |
| Previous by Thread: | Re: Route cache performance under stress, Ralph Doncaster |
| Next by Thread: | Re: Route cache performance under stress, Robert Olsson |
| Indexes: | [Date] [Thread] [Top] [All Lists] |