|To:||"David S. Miller" <davem@xxxxxxxxxxxxx>|
|Subject:||Re: bad TSO performance in 2.6.9-rc2-BK|
|From:||Nivedita Singhvi <niv@xxxxxxxxxx>|
|Date:||Wed, 22 Sep 2004 13:56:17 -0700|
|Cc:||ak@xxxxxxx, anton@xxxxxxxxx, netdev@xxxxxxxxxxx|
|References:||<20040920063012.GL2825@krispykreme> <20040920203021.GD4242@xxxxxxxxxxxxx> <20040921155835.18aee381.davem@xxxxxxxxxxxxx> <20040922140000.GD27432@xxxxxxxxxxxxx> <20040922111209.7887df53.davem@xxxxxxxxxxxxx> <20040922195515.GA2619@xxxxxxxxxxxxx> <4151DB6C.8050906@xxxxxxxxxx> <20040922133011.5885640b.davem@xxxxxxxxxxxxx>|
|User-agent:||Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.4.1) Gecko/20031030|
David S. Miller wrote:
The former rarely goes faster with TSO enabled simply because there is sufficient cpu and bus bandwidth to keep the card full.
At about 700MHz (ok, old, I know) or thereabouts, it usually took > 1 CPU to drive a gigabit card, iirc, about 1.5 CPUs or so.
Whereas with something like SpecWEB the extra cpu and bus cycles are needed by other resources of the benchmark and thus performance goes up.
I have no idea why people think TSO will make some single stream TCP test go faster, it doesn't buy you more bytes on the wire :-)
True, if the card was already doing line speed, no, as you say, it won't help making the stack go faster :). If not, though, the gain in doing only one pass down the stack, one route look up, etc in place of multiple handoffs should help, correct? thanks, Nivedita
|<Prev in Thread]||Current Thread||[Next in Thread>|
|Previous by Date:||Re: bad TSO performance in 2.6.9-rc2-BK, David S. Miller|
|Next by Date:||Re: [Bug 3440] New: eth0 freezes: "NETDEV WATCHDOG: eth0: transmit timed out ", Perolo Silantico|
|Previous by Thread:||Re: bad TSO performance in 2.6.9-rc2-BK, David S. Miller|
|Next by Thread:||Re: bad TSO performance in 2.6.9-rc2-BK, Andi Kleen|
|Indexes:||[Date] [Thread] [Top] [All Lists]|