dave.taht at gmail.com
Mon Oct 24 17:57:13 EDT 2022
On Mon, Oct 24, 2022 at 2:19 PM Herbert Wolverson via LibreQoS
<libreqos at lists.bufferbloat.net> wrote:
> Highly un-scientific (we need to let it run for a bit and do a proper before-after comparison that includes a decent timeframe), but I like the quick'n'dirty results of testing "ack-filter":
> We've been having a Bad Network Day (TM), with sudden flooding making us use some pretty constrained
I've been looking at various ddos mitigation schemes of late. Are you using any?
>- so our latencies were really suffering in one region. That region just happens to be the worst part of our network (we haven't finished digesting an acquisition; there's even Bullet M2 omnis up there!). Lots of relatively low-speed plans, all with big variance (10/3, 25/5, I found a 5/1 that someone forgot to upgrade!). They seem to have benefitted greatly. The parts of the network that were doing great - are still doing great, with very little change.
I made my previous comments in looking at the swing downwards being so
large, possibly not being a positive direction (my ever suspicious gut
was reacting, but I wasn't qualifying the numbers - been a long day
I also forgot to mention that ack-filtering uses up less txops on
older versions of wifi. Very useful. I'd meant
to put it into my mt76 stuff ages ago but got overwhelmed by bugs.
> Just a quick'n'dirty test. I'll try and put something more useful together tomorrow, when it's had a chance to see how peak time hits it.
> (Also, this digging revealed an issue with pping-cpumap in production. It wasn't tracking enough flows, so the reporting is heavily biased towards the top-consumers - who are likely to be monitored before the buffer fills up and it stops counting until stats are read. So I added a "maximums.h" file to make it easy to set user limits, and made flow-count derive from that.)
I think polling it more frequently would be closer to the typical
durations of flows. Most flows last for under 3 seconds.
What would be the harm in vastly expanding the number of flows it tracks?
> LibreQoS mailing list
> LibreQoS at lists.bufferbloat.net
This song goes out to all the folk that thought Stadia would work:
Dave Täht CEO, TekLibre, LLC
More information about the LibreQoS