Re: [squid-users] Squid requirements

2008-07-16 Thread Adrian Chadd
What we're really missing is a bunch of hardware x, config y, testing
z, results a, b, c. TMF used to have some stuff up for older hardware
but there's just nothing recent to use as a measuring stick..



Adrian


2008/7/16 Chris Robertson [EMAIL PROTECTED]:
 Luis Daniel Lucio Quiroz wrote:

 HI folks

 I already know that there is not a recipe for squid.  But I wonder if
 anyone knows an official document that lists squid requirements.

 Regards,

 LD


 That's a bit like asking What kind of a car should I get?.  You need to
 give some details of the expected workload.

 In general, get a higher clocked CPU, as much RAM and as many drives as you
 can afford, and use regex based ACLs sparingly.

 Chris




Re: [squid-users] Squid requirements

2008-07-16 Thread Philipp Rusch - New Vision

Adrian Chadd schrieb:

What we're really missing is a bunch of hardware x, config y, testing
z, results a, b, c. TMF used to have some stuff up for older hardware
but there's just nothing recent to use as a measuring stick..



Adrian


2008/7/16 Chris Robertson [EMAIL PROTECTED]:
  

Luis Daniel Lucio Quiroz wrote:


HI folks

I already know that there is not a recipe for squid.  But I wonder if
anyone knows an official document that lists squid requirements.

Regards,

LD

  

That's a bit like asking What kind of a car should I get?.  You need to
give some details of the expected workload.

In general, get a higher clocked CPU, as much RAM and as many drives as you
can afford, and use regex based ACLs sparingly.

Chris

OK - then let's start collecting some numbers with more recent hardware:

we have a Squid 3 stable 5 on a opensuse 10.3 running on following 
system for about 100 users

with adequate response times:
IBM xSeries 3250 M2
1x Intel Core 2 Duo E4600 2.4 Ghz/800 MHz (2 MB L2 cache)
3 GB PC2-5300 CL5 ECC DDR2 SDRAM DIMM
2x 250 GB SATA hard drive as a mirror configuration

This system is doing virus-scanning with ICAP-enabled Squid through KAV 5.5
Kaspersky AntiVirus for Internet Gateways
AND it is doing web-content filtering with SquidGuard 1.3
AND it is doing NTLM AUTH against the internal W2k3-ADS-domain

Best regards,
--

Mit freundlichen Grüßen,
Philipp Rusch




Re: [squid-users] Squid requirements

2008-07-16 Thread Richard Hubbell
 I already know that there is not a recipe for squid.  But I
 wonder if anyone 
 knows an official document that lists squid requirements.
 
 Regards,
 
 LD

In addition to the other poster's recommendations. You might want to consider 
having two servers for redundancy.  

But really without detail it's hard to know what to recommend.


  


Re: [squid-users] Squid requirements

2008-07-16 Thread Richard Hubbell
--- On Wed, 7/16/08, Adrian Chadd [EMAIL PROTECTED] wrote:

 From: Adrian Chadd [EMAIL PROTECTED]
 Subject: Re: [squid-users] Squid requirements
 To: Chris Robertson [EMAIL PROTECTED]
 Cc: Squid Users squid-users@squid-cache.org
 Date: Wednesday, July 16, 2008, 9:28 AM
 What we're really missing is a bunch of hardware
 x, config y, testing
 z, results a, b, c. TMF used to have some stuff up
 for older hardware
 but there's just nothing recent to use as a measuring
 stick..
 

The problem is that there's so much disparate technology out there.
multi-core cpus, all kinds of different memory, all kinds of different disk 
technologies,  different filesystems,  different OS, different kernels, and on 
and on.  It's hard to get useful measuring sticks.

I still think it's a useful pursuit.  But I think that the reasons above make 
people less inclined to do it.

spec.org tries to level the field, if someone concocted a level field and made 
it easy for people to do, then we'd see more results.


  


Re: [squid-users] Squid requirements

2008-07-16 Thread Josh Haft
My most recent setup was on an old Compaq desktop server 1100mhz, 1gb
RAM (not sure of speed) with ~30gb cache on 10k rpm SCSI disks.

Squid was auth-ing against Samba using the winbind helper. No AV, but
dansguardian was used for content filtering. Performance was adequate
for ~100 users.


Josh


On Wed, Jul 16, 2008 at 5:49 PM, Richard Hubbell
[EMAIL PROTECTED] wrote:
 --- On Wed, 7/16/08, Adrian Chadd [EMAIL PROTECTED] wrote:

 From: Adrian Chadd [EMAIL PROTECTED]
 Subject: Re: [squid-users] Squid requirements
 To: Chris Robertson [EMAIL PROTECTED]
 Cc: Squid Users squid-users@squid-cache.org
 Date: Wednesday, July 16, 2008, 9:28 AM
 What we're really missing is a bunch of hardware
 x, config y, testing
 z, results a, b, c. TMF used to have some stuff up
 for older hardware
 but there's just nothing recent to use as a measuring
 stick..


 The problem is that there's so much disparate technology out there.
 multi-core cpus, all kinds of different memory, all kinds of different disk 
 technologies,  different filesystems,  different OS, different kernels, and 
 on and on.  It's hard to get useful measuring sticks.

 I still think it's a useful pursuit.  But I think that the reasons above make 
 people less inclined to do it.

 spec.org tries to level the field, if someone concocted a level field and 
 made it easy for people to do, then we'd see more results.






Re: [squid-users] Squid requirements

2008-07-16 Thread Michel

 --- On Wed, 7/16/08, Adrian Chadd [EMAIL PROTECTED] wrote:

 From: Adrian Chadd [EMAIL PROTECTED]
 Subject: Re: [squid-users] Squid requirements
 To: Chris Robertson [EMAIL PROTECTED]
 Cc: Squid Users squid-users@squid-cache.org
 Date: Wednesday, July 16, 2008, 9:28 AM
 What we're really missing is a bunch of hardware
 x, config y, testing
 z, results a, b, c. TMF used to have some stuff up
 for older hardware
 but there's just nothing recent to use as a measuring
 stick..


 The problem is that there's so much disparate technology out there.
 multi-core cpus, all kinds of different memory, all kinds of different disk
 technologies,  different filesystems,  different OS, different kernels, and 
 on and
 on.  It's hard to get useful measuring sticks.


shoot me, but as ever faster is more expensive, so if you can't afford a
Lamborghini but like what it does then buy something else what comes close and 
fits
your budget, hammer-speed and cheap does not exist, reasonable speed at 
reasonable
cost does exist, hammer-speed at low-cost does not exist unless you jump the 
cliff
what might result in sudden-death ... that is free and is fufufast (sudden=now)

 I still think it's a useful pursuit.  But I think that the reasons above make
 people less inclined to do it.ree and


to do what? caching? or proxying? or nothing?
while(my_input=0); (do='nothing');


 spec.org tries to level the field, if someone concocted a level field and 
 made it
 easy for people to do, then we'd see more results.


problem is most people look for easy=lazy and lazy=cheap but unfortunatly that
equation does not work either

as also do not exist any valuable hardware comparism since you need to do it
yourself, means you need to look (clients, uplink, machine, bandwidth_for_each,
disired_performance, budget) and finally look at your cache and at the end it is
what_you_get_is_what_you_get_(for_your_money) ... so my friend, at the end it 
does
not matter what they say to buy what you _CAN_ buy and get lucky with it :)


michel





Tecnologia Internet Matik http://info.matik.com.br
Sistemas Wireless para o Provedor Banda Larga
Hospedagem e Email personalizado - e claro, no Brasil.




Re: [squid-users] Squid requirements

2008-07-16 Thread Amos Jeffries
 What we're really missing is a bunch of hardware x, config y, testing
 z, results a, b, c. TMF used to have some stuff up for older hardware
 but there's just nothing recent to use as a measuring stick..


Right. Well. I've left this far too long. But there is now a wiki page for
initial benchmarking info.

Until TMF have the standardized testing ready for public use its only
going to contain very rough information as submitted.
Still, it's better than posts spread randomly through the mailing lists...

Current info listed is very simple:
  OS, CPU model + GHz rating, RAM, HDD, Req/Sec

http://wiki.squid-cache.org/KnowledgeBase/Benchmarks

If you are running any release of squid and can provide the same details
with a better requests-per-second rate than one listed. Or a different H/W
configuration we would like to know about it.

Thanks.

Amos



 Adrian


 2008/7/16 Chris Robertson [EMAIL PROTECTED]:
 Luis Daniel Lucio Quiroz wrote:

 HI folks

 I already know that there is not a recipe for squid.  But I wonder if
 anyone knows an official document that lists squid requirements.

 Regards,

 LD


 That's a bit like asking What kind of a car should I get?.  You need
 to
 give some details of the expected workload.

 In general, get a higher clocked CPU, as much RAM and as many drives as
 you
 can afford, and use regex based ACLs sparingly.

 Chris







Re: [squid-users] Squid requirements

2008-07-16 Thread Amos Jeffries
 Adrian Chadd schrieb:
 What we're really missing is a bunch of hardware x, config y, testing
 z, results a, b, c. TMF used to have some stuff up for older hardware
 but there's just nothing recent to use as a measuring stick..



 Adrian


 2008/7/16 Chris Robertson [EMAIL PROTECTED]:

 Luis Daniel Lucio Quiroz wrote:

 HI folks

 I already know that there is not a recipe for squid.  But I wonder if
 anyone knows an official document that lists squid requirements.

 Regards,

 LD


 That's a bit like asking What kind of a car should I get?.  You need
 to
 give some details of the expected workload.

 In general, get a higher clocked CPU, as much RAM and as many drives as
 you
 can afford, and use regex based ACLs sparingly.

 Chris
 OK - then let's start collecting some numbers with more recent hardware:

 we have a Squid 3 stable 5 on a opensuse 10.3 running on following
 system for about 100 users
 with adequate response times:
 IBM xSeries 3250 M2
 1x Intel Core 2 Duo E4600 2.4 Ghz/800 MHz (2 MB L2 cache)
 3 GB PC2-5300 CL5 ECC DDR2 SDRAM DIMM
 2x 250 GB SATA hard drive as a mirror configuration

 This system is doing virus-scanning with ICAP-enabled Squid through KAV
 5.5
 Kaspersky AntiVirus for Internet Gateways
 AND it is doing web-content filtering with SquidGuard 1.3
 AND it is doing NTLM AUTH against the internal W2k3-ADS-domain

Thank you.
Are you able to indicate the average req/sec your machine is reaching?

Amos




Re: [squid-users] Squid requirements

2008-07-16 Thread Amos Jeffries
 --- On Wed, 7/16/08, Adrian Chadd [EMAIL PROTECTED] wrote:

 From: Adrian Chadd [EMAIL PROTECTED]
 Subject: Re: [squid-users] Squid requirements
 To: Chris Robertson [EMAIL PROTECTED]
 Cc: Squid Users squid-users@squid-cache.org
 Date: Wednesday, July 16, 2008, 9:28 AM
 What we're really missing is a bunch of hardware
 x, config y, testing
 z, results a, b, c. TMF used to have some stuff up
 for older hardware
 but there's just nothing recent to use as a measuring
 stick..


 The problem is that there's so much disparate technology out there.
 multi-core cpus, all kinds of different memory, all kinds of different
 disk technologies,  different filesystems,  different OS, different
 kernels, and on and on.  It's hard to get useful measuring sticks.

 I still think it's a useful pursuit.  But I think that the reasons above
 make people less inclined to do it.

 spec.org tries to level the field, if someone concocted a level field and
 made it easy for people to do, then we'd see more results.


TMF when last seen were working on a standard set of tests for Squid such
that we could run them on any given OS and CPU/RAM/HDD config and
benchmark the interesting stats. Hopefully it (a) wont take too much
longer (b) will be public so anyone can run the tests and report data to
us.

Meanwhile I've added a wiki page to cover the worst part of the
information gap. http://wiki.squid-cache.org/KnowledgeBase/Benchmarks

Amos



Re: [squid-users] Squid requirements

2008-07-16 Thread Amos Jeffries

 --- On Wed, 7/16/08, Adrian Chadd [EMAIL PROTECTED] wrote:

 From: Adrian Chadd [EMAIL PROTECTED]
 Subject: Re: [squid-users] Squid requirements
 To: Chris Robertson [EMAIL PROTECTED]
 Cc: Squid Users squid-users@squid-cache.org
 Date: Wednesday, July 16, 2008, 9:28 AM
 What we're really missing is a bunch of hardware
 x, config y, testing
 z, results a, b, c. TMF used to have some stuff up
 for older hardware
 but there's just nothing recent to use as a measuring
 stick..


 The problem is that there's so much disparate technology out there.
 multi-core cpus, all kinds of different memory, all kinds of different
 disk
 technologies,  different filesystems,  different OS, different kernels,
 and on and
 on.  It's hard to get useful measuring sticks.


 shoot me, but as ever faster is more expensive, so if you can't afford a
 Lamborghini but like what it does then buy something else what comes close
 and fits
 your budget, hammer-speed and cheap does not exist, reasonable speed at
 reasonable
 cost does exist, hammer-speed at low-cost does not exist unless you jump
 the cliff
 what might result in sudden-death ... that is free and is fufufast
 (sudden=now)

 I still think it's a useful pursuit.  But I think that the reasons above
 make
 people less inclined to do it.ree and


 to do what? caching? or proxying? or nothing?
 while(my_input=0); (do='nothing');


 spec.org tries to level the field, if someone concocted a level field
 and made it
 easy for people to do, then we'd see more results.


 problem is most people look for easy=lazy and lazy=cheap but
 unfortunatly that
 equation does not work either

Wrong. It works. Just not very fast. :-)

I've had squid running on a 800MHz machine with 10GB HDD. 25% savings on
the web bandwidth costs paid for the upgrade machine in short order. Now
the savings are even better.


 as also do not exist any valuable hardware comparism since you need to do
 it
 yourself, means you need to look (clients, uplink, machine,
 bandwidth_for_each,
 disired_performance, budget) and finally look at your cache and at the end
 it is
 what_you_get_is_what_you_get_(for_your_money) ... so my friend, at the end
 it does
 not matter what they say to buy what you _CAN_ buy and get lucky with it
 :)

The measure of interest to an admin spec'ing up a Squid box are IMO:
 - highest req/sec vs cost.
H/W config provides the cost scale.
But whats missing is: what req/sec matches what H/W config for Squid?

Amos



[squid-users] Squid requirements

2008-07-15 Thread Luis Daniel Lucio Quiroz
HI folks

I already know that there is not a recipe for squid.  But I wonder if anyone 
knows an official document that lists squid requirements.

Regards,

LD


Re: [squid-users] Squid requirements

2008-07-15 Thread Chris Robertson

Luis Daniel Lucio Quiroz wrote:

HI folks

I already know that there is not a recipe for squid.  But I wonder if anyone 
knows an official document that lists squid requirements.


Regards,

LD
  


That's a bit like asking What kind of a car should I get?.  You need 
to give some details of the expected workload.


In general, get a higher clocked CPU, as much RAM and as many drives as 
you can afford, and use regex based ACLs sparingly.


Chris