Home
| Calendar
| Mail Lists
| List Archives
| Desktop SIG
| Hardware Hacking SIG
Wiki | Flickr | PicasaWeb | Video | Maps & Directions | Installfests | Keysignings Linux Cafe | Meeting Notes | Linux Links | Bling | About BLU |
On 3/18/2012 11:20 PM, Tom Metro wrote: > That's great, but my point was that if the machine is going to be > deployed as a mail or web server, those are the types of loads you want > to benchmark with. True enough. But then, the typical mail or web server tends to see very spiky load patterns and it tends to be I/O-bound rather than CPU-bound. At that point you should look at seek times and IOPS and possibly I/O cache rather than CPU performance. You should also look at how your data is stored since that can have more of an impact on performance than the hardware. -- Rich P.
BLU is a member of BostonUserGroups | |
We also thank MIT for the use of their facilities. |