Re: [Xen-devel] [PATCH v3 1/3][xen-netback] add a pseudo pps rate limit

[Sander Eikelenboom <linux@xxxxxxxxxxxxxx>]

Wednesday, July 10, 2013, 2:50:59 PM, you wrote:

> On Tue, 2013-07-09 at 16:01 +0200, William Dauchy wrote:
>> On Jul09 15:48, Sander Eikelenboom wrote:
>> > Just wondering, why should this be done in the drivers ?
>> > Couldn't this also be achieved with netfilter and the recent/limit modules 
>> > ?
>> > The limit module can already handle bursts.
>> 
>> We indeed forgot to talk about it since we already got the question from
>> Wei.
>> The first thing is that your comment is also true for bandwidth which is
>> already present. Moreover PPS is linked to bandwidth.
>> By using netfilter, PPS shaping is done on backend level, once packet
>> has left the VM; which means after using an additional memory transaction
>> to copy packet from frontend. IMHO, at scale, shaping in this way should
>> save some memory transactions comparing to netfilter.

> Have you tried the netfilter approach and found it to be insufficient in
> practice?

> I'm not sure how netfilter recent/limit is implemented but if it queues
> rather than drops you would naturally find that you end up with back
> pressure onto the netback device where the ring would fill with
> in-progress requests and therefore netback would have to stop processing
> more packets.

recent/limit don't queue it self, it's just for classifying,
you need to specify a target which implements what to do with the packet
when it hits the limit or if it is recent enough.

When i read the manpage from iptables, the most likely target candidates (drop, 
reject, queue (to userspace queue), tarpit),
all seem to consume the packet, so no back pressure will be built in ring.

Also when the packet is not consumed, the recent and limit will probably keep 
getting hit by the same packet over and over again.
So it's probably not possible at the moment, but informing on the 
netfilter-list is worth a shot i guess.

--
Sander

> Ian.




_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel