Re: [RFC] wrr (weighted round-robin) bonding

2006-10-20 Thread Dawid Ciezarkiewicz
On Thursday, 19 October 2006 21:04, Andy Gospodarek wrote: It would seem to me that extending an existing mode would be more desirable than adding yet another mode to worry about. I don't even like the fact that there are as many as there are, but I understand why they are there. Ack. I

Re: [RFC] wrr (weighted round-robin) bonding

2006-10-20 Thread Jay Vosburgh
Dawid Ciezarkiewicz [EMAIL PROTECTED] wrote: On Thursday, 19 October 2006 21:04, Andy Gospodarek wrote: It would seem to me that extending an existing mode would be more desirable than adding yet another mode to worry about. I don't even like the fact that there are as many as there are, but

Re: [RFC] wrr (weighted round-robin) bonding

2006-10-20 Thread Dawid Ciezarkiewicz
On Friday, 20 October 2006 21:53, Jay Vosburgh wrote: Dawid Ciezarkiewicz [EMAIL PROTECTED] wrote: On Thursday, 19 October 2006 21:04, Andy Gospodarek wrote: It would seem to me that extending an existing mode would be more desirable than adding yet another mode to worry about. I don't

Re: [RFC] wrr (weighted round-robin) bonding

2006-10-20 Thread Andy Gospodarek
On Fri, Oct 20, 2006 at 10:52:00PM +0200, Dawid Ciezarkiewicz wrote: Oh. I'm quite puzzled here. What is current policy? I'd like sysfs interfaces better than ioctl - they are much cleaner etc. - but I thought ioctl will be better here because current bonding control uses ioctl and

Re: [RFC] wrr (weighted round-robin) bonding

2006-10-19 Thread Andy Gospodarek
On Tue, Oct 17, 2006 at 10:16:21AM +0200, Dawid Ciezarkiewicz wrote: In fact - as default weight is being set to 1, without changing it wrr bonding mode works like plain round-robin one. But it have little more overhead (recharging tokens), and code is a bit more complicated. I was not

Re: [RFC] wrr (weighted round-robin) bonding

2006-10-17 Thread Dawid Ciezarkiewicz
On Monday, 16 October 2006 23:30, Andy Gospodarek wrote: On Mon, Oct 16, 2006 at 09:07:57PM +0200, Dawid Ciezarkiewicz wrote: Before getting into the technical bits of the patch, what's the reason for wanting to do this, and why is this rather complex manual weight assignment

[RFC] wrr (weighted round-robin) bonding

2006-10-16 Thread Dawid Ciezarkiewicz
This patch is little thinner then the previous one. - To unsubscribe from this list: send the line unsubscribe netdev in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html

Re: [RFC] wrr (weighted round-robin) bonding

2006-10-16 Thread Dawid Ciezarkiewicz
On Monday, 16 October 2006 20:21, Dawid Ciezarkiewicz wrote: This patch is little thinner then the previous one. I'm sorry for that. I've just ... nevermind. Here goes the patch. Should I post patch for ifenslave here, too? diff -Nur linux-2.6.17.orig/Documentation/networking/bonding.txt

Re: [RFC] wrr (weighted round-robin) bonding

2006-10-16 Thread Jay Vosburgh
Dawid Ciezarkiewicz [EMAIL PROTECTED] wrote: [...] + weighted-rr or 7 + + Weighted round-robin bonding. In this mode bonding + interface will use weights assigned to it's slaves. + + Each slave can have weight assigned via ioctl (ifenslave). +

Re: [RFC] wrr (weighted round-robin) bonding

2006-10-16 Thread Dawid Ciezarkiewicz
On Monday, 16 October 2006 20:50, you wrote: Dawid Ciezarkiewicz [EMAIL PROTECTED] wrote: [...] +weighted-rr or 7 + +Weighted round-robin bonding. In this mode bonding +interface will use weights assigned to it's slaves. + +Each slave can have

Re: [RFC] wrr (weighted round-robin) bonding

2006-10-16 Thread Andy Gospodarek
On Mon, Oct 16, 2006 at 09:07:57PM +0200, Dawid Ciezarkiewicz wrote: Before getting into the technical bits of the patch, what's the reason for wanting to do this, and why is this rather complex manual weight assignment better than an automatic system based on, e.g., link speed of