| To: | Nivedita Singhvi <niv@xxxxxxxxxx> |
|---|---|
| Subject: | Re: 2.6.9-rc1+bk: assertion tcp_get_pcount failed at net/ipv4/tcp_input.c |
| From: | "David S. Miller" <davem@xxxxxxxxxxxxx> |
| Date: | Fri, 10 Sep 2004 14:08:52 -0700 |
| Cc: | herbert@xxxxxxxxxxxxxxxxxxx, fork0@xxxxxxxxxxxxxxxxxxxxx, netdev@xxxxxxxxxxx |
| In-reply-to: | <41414C3D.2090606@us.ibm.com> |
| References: | <20040909111233.GA3987@steel.home> <20040910033055.GA26790@gondor.apana.org.au> <20040909222542.7a30c0e4.davem@davemloft.net> <41414C3D.2090606@us.ibm.com> |
| Sender: | netdev-bounce@xxxxxxxxxxx |
On Thu, 09 Sep 2004 23:39:57 -0700 Nivedita Singhvi <niv@xxxxxxxxxx> wrote: > David S. Miller wrote: > > > Herbert did you see my division fix I made today for > > tso_factor calculation? I was dividing by the TSO mss > > instead of the normal one :-) > > Dave, I'm just catching up with the most recent > kernel (from 2.6.8.1 and a hiatus), and I believe > the fixes you refer to as well as the change in > tcp_init_cwnd (tso_factor etc) make TSO consistent > with the standard now. > > That correct? (And thanks, much appreciated, I was > about to fiddle with the same stuff :)). That's absolutely correct and this was the purpose of these changes. |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | [PATCH 2.6-bk] typhoon: PCI cleanups and ethtool_ops conversion, David Dillow |
|---|---|
| Next by Date: | Re: iproute2 patch introducing mtu/txqlen/weight via rtnetlink, David S. Miller |
| Previous by Thread: | Re: 2.6.9-rc1+bk: assertion tcp_get_pcount failed at net/ipv4/tcp_input.c, Nivedita Singhvi |
| Next by Thread: | [IPSEC] Find larval SAs by sequence number, Herbert Xu |
| Indexes: | [Date] [Thread] [Top] [All Lists] |