| To: | Ben Greear <greearb@xxxxxxxxxxxxxxx> |
|---|---|
| Subject: | Re: Ethernet bridge performance |
| From: | "David S. Miller" <davem@xxxxxxxxxx> |
| Date: | Thu, 7 Aug 2003 12:35:47 -0700 |
| Cc: | felix@xxxxxxxxx, netdev@xxxxxxxxxxx |
| In-reply-to: | <3F3284EA.5050406@xxxxxxxxxxxxxxx> |
| References: | <3F3217E7.2080903@xxxxxxxxx> <3F3284EA.5050406@xxxxxxxxxxxxxxx> |
| Sender: | netdev-bounce@xxxxxxxxxxx |
On Thu, 07 Aug 2003 09:57:14 -0700 Ben Greear <greearb@xxxxxxxxxxxxxxx> wrote: > Btw, I've considered saving, say, 10k skbs on a list in my module, > allocated by GFP_KERNEL at module load time, and using them when > GFP_ATOMIC skb_alloc fails in the IRQ handling portion of the code.... > > Anyone think that's a good idea? :) Not really. GFP_ATOMIC should not fail regularly under normal (even heavy load) operation. If it does, it means the amount of reserved pages the kernel keeps around is not set correctly for your system. In 2.6.x, play with /proc/sys/vm/min_free_kbytes |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: Ethernet bridge performance, jamal |
|---|---|
| Next by Date: | Re: Ethernet bridge performance, Ben Greear |
| Previous by Thread: | Re: Ethernet bridge performance, Robert Olsson |
| Next by Thread: | Re: Ethernet bridge performance, Ben Greear |
| Indexes: | [Date] [Thread] [Top] [All Lists] |