| To: | Ravinandan Arakali <ravinandan.arakali@xxxxxxxxxxxx> |
|---|---|
| Subject: | Re: High CPU utilization with Bonding driver ? |
| From: | Arthur Kepner <akepner@xxxxxxx> |
| Date: | Tue, 29 Mar 2005 10:29:07 -0800 (PST) |
| Cc: | netdev@xxxxxxxxxxx, bonding-devel@xxxxxxxxxxxxxxxxxxxxx, "Leonid. Grossman (E-mail)" <leonid.grossman@xxxxxxxxxxxx>, "Raghavendra. Koushik (E-mail)" <raghavendra.koushik@xxxxxxxxxxxx> |
| In-reply-to: | <001601c5348c$3f417f50$3a10100a@pc.s2io.com> |
| References: | <001601c5348c$3f417f50$3a10100a@pc.s2io.com> |
| Sender: | netdev-bounce@xxxxxxxxxxx |
On Tue, 29 Mar 2005, Ravinandan Arakali wrote: > .... > Results(8 nttcp/chariot streams): > --------------------------------- > 1. Combined throughputs(but no bonding): > 3.1 + 6.2 = 9.3 Gbps with 58% CPU idle. > > 2. eth0 and eth1 bonded together in LACP mode: > 8.2 Gbps with 1% CPU idle. > > From the above results, when Bonding driver is used(#2), the CPUs are > completely maxed out compared to the case when traffic is run > simultaneously on both the cards(#1). > Can anybody suggest some reasons for the above behavior ? > Ravi; Have you tried this patch? http://marc.theaimsgroup.com/?l=linux-netdev&m=111091146828779&w=2 If not, it will likely go a long way to solving your problem. -- Arthur |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | High CPU utilization with Bonding driver ?, Ravinandan Arakali |
|---|---|
| Next by Date: | Re: [RFC] TCP congestion schedulers, Rick Jones |
| Previous by Thread: | High CPU utilization with Bonding driver ?, Ravinandan Arakali |
| Next by Thread: | RE: High CPU utilization with Bonding driver ?, Ravinandan Arakali |
| Indexes: | [Date] [Thread] [Top] [All Lists] |