Opened pseudo zap interface, measuring accuracy...

99.987793% 100.000000% 100.000000% 100.000000% 100.000000% 100.000000% 100.000000%

100.000000% 100.000000% 99.987793% 100.000000% 100.000000% 100.000000% 100.000000% 100.000000%

100.000000% 100.000000% 100.000000% 100.000000% 100.000000% 100.000000% 100.000000% 100.000000%

100.000000% 99.987793% 100.000000% 100.000000% 100.000000% 100.000000% 99.987793% 100.000000%

100.000000% 100.000000% 100.000000% 100.000000% 100.000000% 99.987793% 100.000000% 100.000000%

100.000000% 100.000000% 100.000000% 100.000000% 100.000000% 100.000000% 99.987793% 100.000000%

100.000000% 100.000000% 100.000000% 100.000000% 100.000000% 100.000000% 100.000000% 100.000000%

100.000000% 100.000000% 100.000000% 100.000000% 100.000000% 100.000000% 100.000000% 100.000000%

100.000000% 100.000000% 100.000000% 100.000000% 100.000000% 100.000000% 100.000000% 100.000000%

100.000000% 100.000000% 100.000000% 100.000000% 100.000000% 100.000000% 100.000000% 100.000000%

100.000000% 100.000000% 100.000000% 100.000000% 99.987793% 100.000000% 100.000000% 100.000000%

100.000000% 100.000000% 100.000000% 100.000000% 100.000000% 100.000000% 100.000000% 100.000000%

100.000000% 100.000000% 100.000000% 100.000000% 99.987793% 100.000000% 100.000000% 100.000000%

100.000000% 100.000000% 100.000000% 99.987793% 100.000000% 100.000000% 100.000000% 100.000000%

--- Results after 111 passes ---

Best: 100.000000 -- Worst: 99.987793 -- Average: 99.999015

 

Server Specs:

 

Asus P5WD2 Premium

Pentium D 830 (Dual Core)

Corsair DDR2-6400 2GB RAM (4 pices)

2xSATA2 RAID (linux software mirroring)

TE406P (not TE411P as I stated before)

 

Running debian with non-debian kernel (stock standard 2.6.15.4, email if you want .config )

 

Some anomalies have been observed during the testing of the server before implementing it into production.

1 – The server performed MUCH better with software RAID one then hardware, not so mention it was easier to setup.

2 – DDR2-6400 improved some of the benchmarks over DDR2-5200. My understanding that all samples that come in and out if

Digium card are copied to user space so faster ram should be of benefit to the system.

 

 

The system has not been restarted from December. Only asterisk was upgraded 3-4 times since December.

Before unloading zaptel drivers we checked for IRQ misses with zttool (before each unload/load of drivers) and since December we had none.

 

The system is now running realtime (mysql on the same machine), iaxmodem+hylafax combo for receiving faxes.

I must say, spending just a little extra to get good hardware pays off in the long run.

 

If you have any questions, email.

 

Boris

 

> -----Original Message-----

> From: [EMAIL PROTECTED] [mailto:asterisk-users-

> [EMAIL PROTECTED] On Behalf Of Anton Krall

> Sent: Friday, 21 April 2006 14:27

> To: 'Asterisk Users Mailing List - Non-Commercial Discussion'

> Subject: RE: [Asterisk-Users] Digium cards, so disappointing !

>

> Can you send the output of zttest ? Whats your average and what kind of

> hardware are you using?

>

> That will give people pointers of what to use/expect.

>

>

 

_______________________________________________
--Bandwidth and Colocation provided by Easynews.com --

Asterisk-Users mailing list
To UNSUBSCRIBE or update options visit:
   http://lists.digium.com/mailman/listinfo/asterisk-users

Reply via email to