Re: IPv6/KAME book

2006-09-21 Thread Jeffrey Hsu
> We recently published a book on the KAME implementation Sounds great! I'll be sure to check it out at the bookstore. > We would like to thank the FreeBSD community for helping > making this book possible. In particular (and in no particular > order), we'd like to thank the developers S

IPv6/KAME book

2006-09-21 Thread Qing Li
Hi, We recently published a book on the KAME implementation and on IPv6 in general. We hope this book could help developers gain better understanding of the KAME code on FreeBSD. The book is titled "IPv6 Core Protocols Implementation" and it is published by Morgan

Netboot issues with an HP BL35p blade system

2006-09-21 Thread Tim Spencer
Hey there! I am having some problems with an HP BL35p blade system. I'm trying to netboot it so that / is NFS mounted from a NetApp that I have, and it seems to hang as soon as it NFS mounts /. At the same time, bge0 flaps it's link for some unknown reason: Trying to mount root from nf

Re: Much improved sendfile(2) kernel implementation

2006-09-21 Thread Andre Oppermann
Andre Oppermann wrote: Gleb Smirnoff wrote: Is there RELENG_6 version of your patch. If there is one, we can test it quite extensively. This patch does not fully apply to RELENG_6 as there are some small changes and a bit locking differences. It shouldn't be too hard to adapt it. You won't g

Re: Much improved sendfile(2) kernel implementation

2006-09-21 Thread Robert Watson
On Thu, 21 Sep 2006, Peter Jeremy wrote: On Wed, 2006-Sep-20 23:59:13 +0200, Andre Oppermann wrote: I have rewritten kern_sendfile() to work in two loops, the inner which turns as many pages into mbufs as it can up to the free send socket buffer space. The 64K blocks sounds good but how doe

Re: Rapid link state changes on bge(4) interface

2006-09-21 Thread Slawek Zak
On 9/21/06, Gleb Smirnoff <[EMAIL PROTECTED]> wrote: On Thu, Sep 21, 2006 at 12:32:56PM +0200, Slawek Zak wrote: S> >Please try to add hw.bge.fake_autoneg=1 to /boot/loader.conf. May be S> >this will help. S> S> I did it, but sysctl doesn't show the value. S> S> w3-6# sysctl hw.bge S> sysctl: unk

Re: Much improved sendfile(2) kernel implementation

2006-09-21 Thread Robert Watson
On Thu, 21 Sep 2006, Andre Oppermann wrote: There should be unconditional M_NOWAIT. Oops, the M_DONTWAIT in the current code is incorrect. It is present since rev. 1.171. If the m_uiotombuf() fails the current code returns from syscall without error! Before rev. 1.171, there wasn't m_uiotombu

Re: Much improved sendfile(2) kernel implementation

2006-09-21 Thread Andre Oppermann
Peter Jeremy wrote: On Wed, 2006-Sep-20 23:59:13 +0200, Andre Oppermann wrote: I have rewritten kern_sendfile() to work in two loops, the inner which turns as many pages into mbufs as it can up to the free send socket buffer space. The 64K blocks sounds good but how does this interact with TCP

Re: Much improved sendfile(2) kernel implementation

2006-09-21 Thread Andre Oppermann
Gleb Smirnoff wrote: Andre, On Wed, Sep 20, 2006 at 11:59:13PM +0200, Andre Oppermann wrote: A> I have rewritten kern_sendfile() to work in two loops, the inner which turns A> as many pages into mbufs as it can up to the free send socket buffer space. A> The outer loop then drops the whole mbu

Re: Rapid link state changes on bge(4) interface

2006-09-21 Thread Gleb Smirnoff
On Thu, Sep 21, 2006 at 12:32:56PM +0200, Slawek Zak wrote: S> >Please try to add hw.bge.fake_autoneg=1 to /boot/loader.conf. May be S> >this will help. S> S> I did it, but sysctl doesn't show the value. S> S> w3-6# sysctl hw.bge S> sysctl: unknown oid 'hw.bge' S> S> This sysctl seems to be defi

Re: Much improved sendfile(2) kernel implementation

2006-09-21 Thread Gleb Smirnoff
Andre, On Wed, Sep 20, 2006 at 11:59:13PM +0200, Andre Oppermann wrote: A> I have rewritten kern_sendfile() to work in two loops, the inner which turns A> as many pages into mbufs as it can up to the free send socket buffer space. A> The outer loop then drops the whole mbuf chain into the send s

Re: Rapid link state changes on bge(4) interface

2006-09-21 Thread Slawek Zak
On 9/15/06, Gleb Smirnoff <[EMAIL PROTECTED]> wrote: On Wed, Sep 13, 2006 at 03:09:56PM +0200, Slawek Zak wrote: S> I'm testing network failover on IBM BladeCenter running FreeBSD 6.1 S> STABLE for Sep 6th. S> S> I suspect a problem with link state change detection in bge code. When S> I disable

Re: Much improved sendfile(2) kernel implementation

2006-09-21 Thread Claudio Jeker
On Thu, Sep 21, 2006 at 05:59:03PM +1000, Peter Jeremy wrote: > On Wed, 2006-Sep-20 23:59:13 +0200, Andre Oppermann wrote: > >I have rewritten kern_sendfile() to work in two loops, the inner which turns > >as many pages into mbufs as it can up to the free send socket buffer space. > > The 64K bloc

Re: Much improved sendfile(2) kernel implementation

2006-09-21 Thread Peter Jeremy
On Wed, 2006-Sep-20 23:59:13 +0200, Andre Oppermann wrote: >I have rewritten kern_sendfile() to work in two loops, the inner which turns >as many pages into mbufs as it can up to the free send socket buffer space. The 64K blocks sounds good but how does this interact with TCP slow start? Is there