| To: | Anton Blanchard <anton@xxxxxxxxx> |
|---|---|
| Subject: | Re: some TSO analysis |
| From: | "David S. Miller" <davem@xxxxxxxxxxxxx> |
| Date: | Thu, 11 Nov 2004 10:26:22 -0800 |
| Cc: | herbert@xxxxxxxxxxxxxxxxxxx, netdev@xxxxxxxxxxx |
| In-reply-to: | <20041111083647.GA20769@xxxxxxxxxxxxxxxxxxxxxxxxxx> |
| References: | <20041111050608.GG1922@xxxxxxxxxxxxxxxxxxxxxxxxxx> <E1CS9Fm-0004hC-00@xxxxxxxxxxxxxxxxxxxxxxxx> <20041111083647.GA20769@xxxxxxxxxxxxxxxxxxxxxxxxxx> |
| Sender: | netdev-bounce@xxxxxxxxxxx |
On Thu, 11 Nov 2004 19:36:47 +1100 Anton Blanchard <anton@xxxxxxxxx> wrote: > Im interested if the divisor of 8 was based on some testing, or if we > can tune the default a bit. It would be nice for TSO to kick in on > normal workloads (like web serving). It was the best compromise found between performance and burstyness. If you set it too small, you get large bursts of TSO created frames which is very undesirable. |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: node-local multicast issues, Mark Borst |
|---|---|
| Next by Date: | Re: 2.6.10-rc1-mm4 -1 EAGAIN after allocation failure was: Re: Kernel 2.6.9 Multiple Page Allocation Failures, jhigdon |
| Previous by Thread: | Re: some TSO analysis, Anton Blanchard |
| Next by Thread: | ack.lrcvtime initialization in Linux 2.6.9, Sami Farin |
| Indexes: | [Date] [Thread] [Top] [All Lists] |