[squid-users] Slowly rising CPU load (eventually hits 100)

squid at peralex.com squid at peralex.com
Fri Apr 1 05:47:00 UTC 2016


On 2016-03-31 18:44, Alex Rousskov wrote:
> 
> My working theory is that the longer you let your Squid run, the bigger
> objects it might store in RAM, increasing the severity of the linear
> search delays mentioned below. A similar pattern may also be caused by
> larger objects becoming more popular during certain days of the week.
> 

Thanks.  The current maximum_object_size_in_memory is 19 MB.

> 
> In summary, dealing with in-RAM objects significantly larger than 1MB
> bigger the object, the longer Squid takes to scan its nodes.
> 
> Short term, try limiting the size of in-RAM objects using
> maximum_object_size_in_memory first. If that solves the problem, then,
> most likely, only cached objects are affected.

I'll try this next, after I've given Yuri's suggestion a while to yield
results (or not).

> Also, forcing shared memory cache (even if you are not using SMP Squid)
> shared memory code itself does not have the above linear search, SMP
> Squid still uses local memory code and might hit the same linear search.

I'll look at that too.

> guess less. Please point to or copy to this email exchange to your bug
> report.

I've added bug http://bugs.squid-cache.org/show_bug.cgi?id=4477, and
included a reference to this thread at the end of the bug report.

Thanks for the assistance.
Mark






More information about the squid-users mailing list