RE: [squid-users] Cache_dir size considerations

From: GIGO . <gigoz_at_msn.com>
Date: Fri, 19 Mar 2010 16:27:19 +0000

Yes you are right about asking of lot of questions at once. i be careful.
 
+
 
Thank you

----------------------------------------
> Date: Fri, 19 Mar 2010 16:44:18 +0100
> From: mromani_at_ottotecnica.com
> To: gigoz_at_msn.com
> CC: squid-users_at_squid-cache.org
> Subject: Re: [squid-users] Cache_dir size considerations
>
> GIGO . ha scritto:
>> Well i want to make sure that my settings are optimized and want to
>> learn more about the cache_dir settings.....let me come in details
>
> Gigo,
> you are asking a lot of questions all at once.
> This is a volounteer-based support list, so your chances of getting
> (good) responses are maximized if you ask specific questions, one or two
> per post (possibly related).
>
> That said, I'll try to answer with what I know...
>
>>
>>
>> I have installed squid3stable24 on Ubuntu 8.04 on IBM 3650 X series
>> server with two hard disks on which physical RAID1 is implemented. I
>> am to use the Squid Server for 1000 users out of which 250 are power
>> usrs rest of them are normal users for which there are many
>> restrictions(youtube,facebook,msnmessgenger,yahoomessenger,mp3mpg
>> etc...).
>
> OK
>
>>
>> I have done my settings specifically to ensure that windows updates
>> are cached and my maximum_object_size is 256 mb. Also i am looking
>> forward to cache Youtube content(for which i have no updated script
>> and settings so far the one on internet is with storeurl directive
>> which is depricated).......
>>
>>
>> Now my cache directory size is 50 gb with 16 L1 and 256 L2. I think
>> better would be
>>
>> Cache_dir_size aufs 50 GB 48(L1) 768(L2)
>>
>>
>> as far as L1 & L2 settings i am clear that there should be no more
>> than around 100 file in L2 directories so one's settings should be
>> adjusted accordingly. However i am confused that if setting your
>> cache (50gb) of too large a size will have anything to do with your
>> performance. Secondly at the moment the cache directory is
>> implemented on the same hard drive on which OS is installed. I know
>> that cache should be better moved to a spare hard drive. But what
>> about the highavailability? Failure of a disk cud result in the
>> failure of proxy?
>
> To maximize performance you want 1 disk for OS and logs, and one disk
> per cache_dir, without any RAID.
> With only two disks, obviously if either one dies you have an out of
> service.
> So to achieve ha squid you'd neeto to have two phisical squid boxes, I
> think. Haven't tried myself, so i cannot guide you on how to set that up...
>
>>
>> Another confusion which i have is that what about the
>> cahe_effective_user i hav set my user
>>
>> cache_effective_user proxy but i dont have much concepts about it. I
>> have read on SAN institute site a white paper published 2003 that
>> squid should not be run as nobody user but as a sandbox user with
>> noshell. However i am not sure what is it all about and whether this
>> informaiton is still valid after 7 years have been passed.
>
> Squid should not be run as root.
> You should have a dedicated user account for it.
> Squid cache dirs should be rw by that squid account, obviously.
> I belive most distros (at least server-oriented ones) take care of this
> setup when you install squid via package manager.
>
>>
>> Please also guide me that what are the risks involved with this
>> setting which i have done for windows update:
>>
>> range_offset_limit -1 maximum_object_size 256 MB quick_abort_min -1
>
> No risk, but if a user interrupts a huge download, squid will continue
> it until it finishes, possibly wasting a lot of bandwidth on the wan side.
>
>>
>>
>> Further after giving squid too many longs list of blocked site say
>> containg 100+ sites. I have noticed that its slowed down however i am
>> not sure that if it is the reason? please guide......
>>
>
> Well, blocking sites involves checking every request's url against all
> the sites in the blacklist. This might have a noticeable impact on the
> server load. Also, if you have many regexes in the blacklist(s) the load
> will be significantly higher.
> You might want to have a look at squidGuard or other external helper, to
> take advantage of the multiple CPU cores your server might have.
>
>>
>> Please guide in detail it will be really beneficial for me as concept
>> building...i would be really thankful..
>>
>> regards,
>>
>>
>
> HTH
>
>>
>>
>>
>>
>> ----------------------------------------
>>> Date: Wed, 17 Mar 2010 11:00:22 +0100 From: mromani_at_ottotecnica.com
>>> CC: squid-users_at_squid-cache.org Subject: Re: [squid-users]
>>> Cache_dir size considerations
>>>
>>> GIGO . ha scritto:
>>>> The total amount of Ram on the server is 4 GB with cache_mem
>>>> parameter set to 1 GB.
>>>>
>>> IMHO there's plenty of HW for squid to run smoothly. But it also
>>> depends on the amount of traffic.
>>>
>>> I'm sorry but I think I don't get your point... what is exactly the
>>> problem you're having ?
>>>
>>> -- Marcello Romani
>> _________________________________________________________________
>> Your E-mail and More On-the-Go. Get Windows Live Hotmail Free.
>> https://signup.live.com/signup.aspx?id=60969
>
>
> --
> Marcello Romani
_________________________________________________________________
Hotmail: Trusted email with powerful SPAM protection.
https://signup.live.com/signup.aspx?id=60969
Received on Fri Mar 19 2010 - 16:27:25 MDT

This archive was generated by hypermail 2.2.0 : Sat Mar 20 2010 - 12:00:05 MDT