Search squid archive

Re: Rock Store max object size 3.5.14

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Hey,

Some of the emails was probably off-list from some reason so responding here.

Since you are having some issues with the current way that the proxy works since it gets to 100% CPU and probably your clients\users suffering from an issue I would suggest to try another approach to get couple clear things into our\yout sight.

Stop using disk cache as a starter and make sure that the current basic CPU+RAM handles the traffic properly. Only after you somehow made sure that the proxy handles something right try to see what can be done with any form of cache_dir.

Since you have plenty of RAM and CORES see if *without* any cache_dir you are having any CPU issues.
If you still have then I would suggest to do two things simultaneously:
- disable access logs
- upper the workers number from the default 1 to more

If when the access logs are disabled and the cores number was bumped-up to the maximum you are probably having the wrong machine for the task. If in some state that the access logs disabled and the number of cores was higher then 1 and not up to the maximum of the machine you hare having a somehow balanced CPU percentages you still have a chance to match the hardware to the task. Then the next step would be to enabled the access logs and see how the machine holds only this.

The above method is the basic way to make sure you are on the right track.
If you need more advice just respond to email.

All The Bests,
Eliezer

On 23/02/2016 21:11, Heiler Bemerguy wrote:

Thanks Alex.

We have a simple cache_dir config like this, with no "workers" defined:
cache_dir rock /cache2 80000 min-size=0 max-size=32767
cache_dir aufs /cache 320000 96 256 min-size=32768

And we are suffering from a 100% CPU use by a single squid thread. We
have lots of ram, cores and disk space.. but also too many users:
Number of clients accessing cache:      1634
Number of HTTP requests received:       3276691
Average HTTP requests per minute since start:   12807.1
Select loop called: 60353401 times, 22.017 ms avg

Getting rid of this big aufs and spreading to many rock stores will
improve things here? I've already shrunk the acls and patterns/regexes etc

Best Regards,


_______________________________________________
squid-users mailing list
squid-users@xxxxxxxxxxxxxxxxxxxxx
http://lists.squid-cache.org/listinfo/squid-users




[Index of Archives]     [Linux Audio Users]     [Samba]     [Big List of Linux Books]     [Linux USB]     [Yosemite News]

  Powered by Linux