Re: [PATCH Round 2 0/2][RFC] Network Event Notifier Mechanism

2006-06-27 Thread David Miller
From: Steve Wise <[EMAIL PROTECTED]> Date: Tue, 27 Jun 2006 15:33:19 -0500 > From my experimentation with netlink, RTM_NEWROUTE and RTM_DELROUTE > messages do not get sent up for redirect events. I have, in fact, added > this with the new patch I'll send out soon. So either way I need to > chang

Re: [PATCH Round 2 0/2][RFC] Network Event Notifier Mechanism

2006-06-27 Thread Steve Wise
On Tue, 2006-06-27 at 13:21 -0700, David Miller wrote: > From: Steve Wise <[EMAIL PROTECTED]> > Date: Tue, 27 Jun 2006 15:19:08 -0500 > > > For an RDMA NIC, all this logic is in HW, which is why we need the event > > notification; to tell the HW to change its next hop information. > > Back to the

RE: [PATCH Round 2 0/2][RFC] Network Event Notifier Mechanism

2006-06-27 Thread Caitlin Bestler
[EMAIL PROTECTED] wrote: > From: Steve Wise <[EMAIL PROTECTED]> > Date: Tue, 27 Jun 2006 10:02:19 -0500 > >> For the RDMA kernel subsystem, however, we still need a specific >> event. We need both the old and new dst_entry struct ptrs to figure >> out which active connections were using the old ds

Re: [PATCH Round 2 0/2][RFC] Network Event Notifier Mechanism

2006-06-27 Thread David Miller
From: Steve Wise <[EMAIL PROTECTED]> Date: Tue, 27 Jun 2006 10:02:19 -0500 > For the RDMA kernel subsystem, however, we still need a specific event. > We need both the old and new dst_entry struct ptrs to figure out which > active connections were using the old dst_entry and should be updated to >

Re: [PATCH Round 2 0/2][RFC] Network Event Notifier Mechanism

2006-06-27 Thread Steve Wise
On Tue, 2006-06-27 at 13:14 -0700, David Miller wrote: > This change isn't truly atomic from a kernel standpoint either. > > The new dst won't be selected by the socket until later, > when the socket tries to send something, notices the old dst > is obsolete, and looks up a new one. > > Your code

Re: [PATCH Round 2 0/2][RFC] Network Event Notifier Mechanism

2006-06-27 Thread David Miller
From: Steve Wise <[EMAIL PROTECTED]> Date: Tue, 27 Jun 2006 15:19:08 -0500 > For an RDMA NIC, all this logic is in HW, which is why we need the event > notification; to tell the HW to change its next hop information. Back to the route change notification, I still think you can get what you need b

Re: [PATCH Round 2 0/2][RFC] Network Event Notifier Mechanism

2006-06-27 Thread Steve Wise
On Tue, 2006-06-27 at 03:09 -0700, David Miller wrote: > From: Steve Wise <[EMAIL PROTECTED]> > Date: Mon, 26 Jun 2006 15:36:38 -0500 > > > Round 2 Changes: > > > > - cleaned up event structures per review feedback. > > - began integration with netlink (see neighbour changes in patch 2). > > - ad

Re: [PATCH Round 2 0/2][RFC] Network Event Notifier Mechanism

2006-06-27 Thread David Miller
From: Steve Wise <[EMAIL PROTECTED]> Date: Mon, 26 Jun 2006 15:36:38 -0500 > Round 2 Changes: > > - cleaned up event structures per review feedback. > - began integration with netlink (see neighbour changes in patch 2). > - added IPv6 support. Yes, ipv6 support is the main think I saw lacking. E

[PATCH Round 2 0/2][RFC] Network Event Notifier Mechanism

2006-06-26 Thread Steve Wise
Round 2 Changes: - cleaned up event structures per review feedback. - began integration with netlink (see neighbour changes in patch 2). - added IPv6 support. STILL TODO: - PMTU events/netlink - Redirect netlink (need to define a new netlink message for this). Questions: - this patch is enabl