| To: | Andrea Arcangeli <andrea@xxxxxxx> |
|---|---|
| Subject: | Re: route cache DoS testing and softirqs |
| From: | "David S. Miller" <davem@xxxxxxxxxx> |
| Date: | Tue, 30 Mar 2004 13:30:00 -0800 |
| Cc: | kuznet@xxxxxxxxxxxxx, dipankar@xxxxxxxxxx, linux-kernel@xxxxxxxxxxxxxxx, netdev@xxxxxxxxxxx, Robert.Olsson@xxxxxxxxxxx, paulmck@xxxxxxxxxx, akpm@xxxxxxxx |
| In-reply-to: | <20040330211450.GI3808@xxxxxxxxxxxxxxxxx> |
| References: | <20040329222926.GF3808@xxxxxxxxxxxxxxxxx> <200403302005.AAA00466@xxxxxxxxxxxxxxx> <20040330211450.GI3808@xxxxxxxxxxxxxxxxx> |
| Sender: | netdev-bounce@xxxxxxxxxxx |
On Tue, 30 Mar 2004 23:14:50 +0200 Andrea Arcangeli <andrea@xxxxxxx> wrote: > > There are no hardirqs in the case under investigation, remember? > > no hardirqs? there must be tons of hardirqs if ksoftirqd never runs. NAPI should be kicking in for this workload, and I know for a fact it is for Robert's case. There should only be a few thousand hard irqs per second. Until the RX ring is depleted the device's hardirqs will not be re- enabled. |
| Previous by Date: | Re: route cache DoS testing and softirqs, Robert Olsson |
|---|---|
| Next by Date: | Re: route cache DoS testing and softirqs, Andrea Arcangeli |
| Previous by Thread: | Re: route cache DoS testing and softirqs, Andrea Arcangeli |
| Next by Thread: | Re: route cache DoS testing and softirqs, Andrea Arcangeli |
| Indexes: | [Date] [Thread] [Top] [All Lists] |