Hey again,
It took me some time...
The number of clients is sometimes irrelevant compared to other factors.
For example a network with 30k Clients\Users which only access basic
email service. So it might be possible that in some period of time your
service will have this kind of load AVG.
Y
On 02/25/2016 01:19 PM, Heiler Bemerguy wrote:
>>> /2016/02/25 13:42:19 kid1| WARNING: swapfile header inconsistent with
>>> available data
>> I do not know what causes these in your environment. Do you see them
>> when _not_ using any optional options on the cache_dir lines and not
>> sending an
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA256
Eh. Looks like bug.
26.02.16 2:19, Heiler Bemerguy пишет:
>
>
> Em 25/02/2016 16:29, Alex Rousskov escreveu:
>>> Then:
>>> /2016/02/25 13:42:19 kid1| WARNING: swapfile header inconsistent with
>>> available data
>> I do not know what causes these
Em 25/02/2016 16:29, Alex Rousskov escreveu:
Then:
/2016/02/25 13:42:19 kid1| WARNING: swapfile header inconsistent with
available data
I do not know what causes these in your environment. Do you see them
when _not_ using any optional options on the cache_dir lines and not
sending any HTTP req
On 02/25/2016 12:32 PM, Heiler Bemerguy wrote:
> BTW, I just wiped out the caches again, put only one cache_dir and
> started it again.. (killed everything, squid -z, then ./squid.rc start)
In addition to previous suggestions, please make sure that your
./squid.rc does not [incorrectly] run "squi
Hi guys.
Sorry, Yuri, I didn't understand your question...
BTW, I just wiped out the caches again, put only one cache_dir and
started it again.. (killed everything, squid -z, then ./squid.rc start)
*cache_dir rock /cache2/rock1 2 min-size=0 max-size=4096 slot-size=2048*
/2016/02/25 16:2
On 02/25/2016 09:58 AM, Heiler Bemerguy wrote:
> So, to start from the start, after seeing squid was totally stable and
> fast, running with NO cache_dirs, I tried to add only 2 rockstore
> cache_dirs to test.
> cache_dir rock /cache2/rock1 2 min-size=0 max-size=4096 slot-size=2048
> cache_di
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA256
Hm. What array does itself this time?
26.02.16 0:44, Heiler Bemerguy пишет:
>
> Since it started with both cache_dirs...
>
>
> Em 25/02/2016 15:32, Yuri Voinov escreveu:
>>
> Don't think so.
>
> This messages floods all time?
>
> 26.02.16 0:17, He
Since it started with both cache_dirs...
Em 25/02/2016 15:32, Yuri Voinov escreveu:
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA256
Don't think so.
This messages floods all time?
26.02.16 0:17, Heiler Bemerguy пишет:
> > I waited squid -z to finish.. did a "ps auxw |grep squid" a dozen
ti
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA256
Don't think so.
This messages floods all time?
26.02.16 0:17, Heiler Bemerguy пишет:
>
> I waited squid -z to finish.. did a "ps auxw |grep squid" a dozen
times to check.. THEN I started it.
> It may have tried to serve something, as lots of user
I waited squid -z to finish.. did a "ps auxw |grep squid" a dozen times
to check.. THEN I started it.
It may have tried to serve something, as lots of users we're already
conecting to it right after it started, but I'm still seeing a flood of
warnings on error.log:
/2016/02/25 15:06:38 kid1
On 26/02/2016 5:58 a.m., Heiler Bemerguy wrote:
>
> Hi Alex, Eliezer, Yuri, Amos..
>
> So, to start from the start, after seeing squid was totally stable and
> fast, running with NO cache_dirs, I tried to add only 2 rockstore
> cache_dirs to test.
>
> conf:
> /cache_dir rock /cache2/rock1 2
Hi Alex, Eliezer, Yuri, Amos..
So, to start from the start, after seeing squid was totally stable and
fast, running with NO cache_dirs, I tried to add only 2 rockstore
cache_dirs to test.
conf:
/cache_dir rock /cache2/rock1 2 min-size=0 max-size=4096
slot-size=2048//
//cache_dir rock /c
On 02/24/2016 12:44 PM, Heiler Bemerguy wrote:
> I don't think I had a bottleneck on I/O itself,
In general, I/O bottlenecks with rock or ufs cache_dirs do not result in
sustained 100% CPU utilization. I do not know enough about aufs to say
whether that cache_dir type can have those symptoms dur
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA256
But you can continue to think that the problem is in the Squid. :) And
keep looking for a magical setting configuration. :)
25.02.16 2:40, Heiler Bemerguy пишет:
>
> Not to mention only 10GB of cache is almost useless for us... lol
>
> But I still
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA256
It's simple. It is strange that you do not understand. Do you have a
thread on the CPU, the pending IO. Then comes another one. Third. Do you
think that makes the OS? It unloads it in a swap? Ha ha, with several
tens of gigabytes of RAM you have no
Not to mention only 10GB of cache is almost useless for us... lol
But I still think cpu is cpu and i/o is i/o. "WAIT" fields on both TOP
and VMSTAT shows almost always a ZERO
Why would it show a process using cpu while actually it's waiting for a
I/O.. ?
Best Regards
--
Heiler Bemerguy -
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA256
AFAIK, if you solve issue with cache_mem 10 GB and completely disabled
disk cache, then you had disk IO bottleneck exactly. You completely
disable disk caches. So, all obvious now.
But - what you will do after squid restart? :) A deadl
Hi Eliezer, thanks for your reply.
As you've suggested, I removed all cache_dirs to verify if the rest was
stable/fast and raised cache_mem to 10GB. I didn't disable access logs
because we really need it..
And it is super fast, I can't even notice it using only ONE core.. (and
it isn't runn
19 matches
Mail list logo
