Mar 202013
 

As you’ll no doubt know, I’ve recently bought two new computer, and built them up. I’ve settled on the Toshiba 3TB DT01ACA300 HDD as my drive of choice for these systems. I ran a few tests recently and found some interesting results. I haven’t published them here yet. My main test is a database load. I just take an 8GB text file and create a PostgreSQL database from it. The file in question is a dump of the FreshPorts database. Once loaded, it’s about 33GB on disk. I reckon this is a good decent test. It writes, it reads, it writes some more. It’s easily reproducible.

These tests took about 14.5 minutes to run.

Then I moved those HDD to another server. I planned to run the same tests there.

On this different server, the tests take 21 minutes. That’s a 50% performance hit.

WHY?

In both cases, the HDD are attached to the M/B, as opposed to a SATA card.

The motherboards in question are:

fast one

not so fast one

Conclusions?

I guess we can clearly state that the Intel Xeon is blazingly faster than the AMD Opteron. I just didn’t expect such a big difference.

Did I buy the wrong CPU for the other M/B?

Website Pin Facebook Twitter Myspace Friendfeed Technorati del.icio.us Digg Google StumbleUpon Premium Responsive

  6 Responses to “same HDD, different server, +50% performance hit”

  1. May be different SATA mode? AHCI vs IDE or another ?

  2. On the slower server, all the HDD are connected to a SATA card… Hopefully that’s running in SATA III mode. But that is something to investigate. Thank you.

    See also the latest post which shows bonnie++.