[squid-users] reconfigure drops in memory caches for external_acl_type

[Alex Rousskov]

On 2023-11-29 09:38, Ziert, Norman wrote:

> in the very recent past I stumbled over that a "squid -k reconfigure" 
> drops in memory caches for external_acl_type helpers, wich in my case 
> leads to a massive query burst against local winbind 
> (ext_wbinfo_group_acl) and infact the active directory 
> domaincontrollers. This also leads to an massive impact in servicetime 
> to endusers, where after a reconfigure the time needed to fullfill takes 
> a recent time by group membership authorization within squid until the 
> external_acl cache is "rewarmed".
> 
> 
> I have veriefied that behavior back to v5.2.
> 
> 
> I want to ask if this is a wanted behavior to squid or should I file a 
> bug-report on this?


This behavior is usually unwanted, but there is no particular need for a 
bug report IMHO: We know that this and similar reconfiguration side 
effects are usually unwanted. We are actively working on avoiding 
various unwanted reconfiguration side effects -- the "smooth 
reconfiguration" project has merged about 25 pull requests in recent 
months (some of them were very complex/substantial -- we need to payoff 
a lot of very old technical debt first!), and more are coming. We will 
solve this problem in the foreseeable future.


> Maybe I discovered a topic wich is connected to this discussion: 
> https://wiki.squid-cache.org/Features/HotConf 

Yes, that old wiki page has some relevant pieces, but we have moved far 
ahead of those old discussions since then and have solved complex 
architectural problems with functional, deployment-tested code that 
supports smooth reconfiguration in some typical cases. We are actively 
working on polishing, merging, and enhancing those improvements.


HTH,

Alex.