Re: [squid-users] Urgent Help Needed: Any suggestion on CPU utiliztion increased from 73% to 97.5 after cache_mem increased from 4 GB to 8 GB

Henrik,

I used the memory cache only configuration without disk store
So :
 cache_dir null /tmp

On start up :
Using 8192 Store buckets ..

Is there any other information needed in order to analyze such problem ?

Thanks ,
-Arkin

On Sun, Jun 15, 2008 at 11:05 AM, Henrik Nordstrom
<henrik_at_henriknordstrom.net> wrote:
> On sön, 2008-06-15 at 10:57 +0800, Arkin Y wrote:
>
>> Acctually , I tried to use Linux OS default malloc, gnu malloc , dlmalloc,
>> dlmalloc could help me get the best performance among the three different
>> malloc .
>
> Interesting.
>
> For me dlmalloc fails completely when the process size goes above 2GB.
>
>> I checked all my mgr:info log , when I set the cache_mem to different size ,
>> the stroe entries are different too .
>> When the cache memory is 4GB , the Store Entries are ~519396
>> When the cache memory is 6 GB , the StoreEntries are ~776836
>> When the cache memory is 8 GB , the StoreEntries are ~1026097
>
> Are you running without an on-disk store? (cache_dir)
>
>> The average size of the stored objects almost ~8KB, so I am not sure
>> whether such problem was caused by large objects .
>
> Ok.
>
>
>> I checked a hash_lookup method , If in the worst cases in 8G scenario,it
>> looks like almost 2 times of hash keys will be traversed to get the
>> storeEntry than in 4 G scenario.
>
> The size of the hash table is dependent on the store size.
>
> But I guess this calculation screws up if there is no on-disk cache of
> reasonable size.
>
> On startup, what is reported NN for "Using NN Store buckets" in
> cache.log?
>
> Regards
> Henrik
>
Received on Mon Jun 16 2008 - 05:14:43 MDT