| To: | Greg Banks <gnb@xxxxxxx> |
|---|---|
| Subject: | Re: [PATCH] fix BUG in tg3_tx |
| From: | "David S. Miller" <davem@xxxxxxxxxx> |
| Date: | Wed, 26 May 2004 11:01:21 -0700 |
| Cc: | mchan@xxxxxxxxxxxx, netdev@xxxxxxxxxxx |
| In-reply-to: | <20040526160443.GD4557@sgi.com> |
| References: | <B1508D50A0692F42B217C22C02D849727FEDB8@NT-IRVA-0741.brcm.ad.broadcom.com> <20040526160443.GD4557@sgi.com> |
| Sender: | netdev-bounce@xxxxxxxxxxx |
On Thu, 27 May 2004 02:04:43 +1000 Greg Banks <gnb@xxxxxxx> wrote: > On a related note, is there a good reason why the tg3 driver uses > the on-chip SRAM send ring by default instead of the host send ring? > This seems like it would dramatically increase the PIO load on the > chipset for some of the workloads I'm interested in. Good question. It actually results in better performance to use PIOs to the chip to write the TXD descriptors. You may be skeptical about this but it cannot be denied that it does result in lower latency as we don't have to wait for the chip to do it's next prefetch and _furthermore_ this means that no CPU cache lines will bounce from cpu-->device in order to get the descriptors to the chip. |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | RE: [PATCH] fix BUG in tg3_tx, Michael Chan |
|---|---|
| Next by Date: | Re: [PATCH] fix BUG in tg3_tx, David S. Miller |
| Previous by Thread: | Re: [PATCH] fix BUG in tg3_tx, Greg Banks |
| Next by Thread: | Re: [PATCH] fix BUG in tg3_tx, Greg Banks |
| Indexes: | [Date] [Thread] [Top] [All Lists] |