| To: | Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx> |
|---|---|
| Subject: | Re: [TCP] Fixed mss in tcp_init_cwnd |
| From: | "David S. Miller" <davem@xxxxxxxxxxxxx> |
| Date: | Mon, 27 Sep 2004 12:00:31 -0700 |
| Cc: | netdev@xxxxxxxxxxx |
| In-reply-to: | <20040927080828.GA12056@gondor.apana.org.au> |
| References: | <20040927080828.GA12056@gondor.apana.org.au> |
| Sender: | netdev-bounce@xxxxxxxxxxx |
On Mon, 27 Sep 2004 18:08:28 +1000 Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx> wrote: > The MSS in tcp_init_cwnd should be the real one instead of the TSO value. This happens too early in the connections lifetime to make a difference for anything. It happens on the first move to ESTABLISHED state, and therefore by definition before we try to send any data on the connection. You're barking up the wrong tree in the search for these TSO problems. Instead, I'd recommend looking seriously at the tcp_clean_rtx_queue() partial ack'ing stuff I spoke about yesterday. |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: [6/6]: jenkins hash for neigh, David S. Miller |
|---|---|
| Next by Date: | Re: bad TSO performance in 2.6.9-rc2-BK, David S. Miller |
| Previous by Thread: | Re: [TCP] Fixed mss in tcp_init_cwnd, Nivedita Singhvi |
| Next by Thread: | Re: [TCP] Fixed mss in tcp_init_cwnd, Herbert Xu |
| Indexes: | [Date] [Thread] [Top] [All Lists] |