[squid-users] 3.5.27 to 4.4: a worker is dead

[Heiler Bemerguy]

Em 08/11/2018 00:32, Amos Jeffries escreveu:

> Your rock cache apparently contains at least several objects with the
> exact string "[unknown URI]" as their URL / store-ID key. These are
> attempting to be delivered to the client when it requested that OSCP URL.
>
> Squid has detected the problem and will fetch a new object from the
> network instead of the cache. It also begins the process of purging that
> corrupt object from the cache.
This always ocurred, even with 3.5.27.. and I think it's related to 
cache_peers asking for objects. Am I the only one seeing it?
>
>> 2018/11/07 07:17:03 kid4| FATAL: Dying from an exception handling
>> failure; exception: check failed: false
>>      exception location: mem/PageStack.cc(106) push
>>
> The SMP shared-memory space has been asked to allocate more memory than
> it has total capacity.

Why would it do that? 3.5.27 worked forever flawlessly with the same 
config. Should I decrease cache_mem?


-- 
Atenciosamente,

Heiler Bensimon Bemerguy - CINBESA
Analista de Redes, Wi-Fi,
Virtualização e Serviços Internet
(55) 91 98151-4894