Re: UDP buffer drops / statistics collector

> On 19 Apr 2017, at 20:36, Tim Kane <tim(dot)kane(at)gmail(dot)com> wrote:
>
> Well, this is frustrating..
> The buffer drops are still occurring - so I thought it worth trying use a ramdisk and set stats_temp_directory accordingly.
>
> I've reloaded the instance, and can see that the stats directory is now being populated in the new location. Except - there is one last file (pgss_query_texts.stat) that continues to be updated in the old pg_stat_tmp path.. Is that supposed to happen?
>
>
> Fairly similar to this guy (but not quite the same).
> https://www.postgresql.org/message-id/D6E71BEFAD7BEB4FBCD8AE74FADB1265011BB40FC749@win-8-eml-ex1.eml.local
>
> I can see the packets arriving and being consumed by the collector.. and, the collector is indeed updating in the new stats_temp_directory.. just not for that one file.
>
>
> It also failed to resolve the buffer drops.. At this point, I'm not sure I expected it to. They tend to occur semi-regularly (every 8-13 minutes) but I can't correlate them with any kind of activity (and if I'm honest, it's possibly starting to drive me a little bit mad).

This rings a bell for me. I recently had a similar issue in an MMO (Windows) where every 15 minutes I would get a number of consecutive freezes in-game. You could set your alarm by it, so regular.

That suddenly went away after I rearranged my home-network (for unrelated reasons), which incidentally moved several connections from the switch the game-system was connected to to another switch. I never pinpointed it to UDP, but then again, TCP would correct for the lost transfers (probably at the cost of UDP traffic).

Perhaps you have a switch somewhere that's overburdened?

Alban Hertroys
--
If you can't see the forest for the trees,
cut the trees and you'll find there is no forest.