1 |
Michael Mol <mikemol <at> gmail.com> writes: |
2 |
|
3 |
|
4 |
> Let's start with that dual-xeon box I was using to benchmark "emerge |
5 |
> -e @world", figure I'm looking for how better to tune my MAKEOPTS and |
6 |
> EMERGE_DEFAULT_OPTS variables, and assume I'd like to get more |
7 |
> information about the following factors: |
8 |
|
9 |
Complex and never finished, imho..... |
10 |
|
11 |
|
12 |
> * What was the 1m, 5m 15m load averages? |
13 |
> * What were the similar averages for CPU spent in user time, system |
14 |
> time and I/O wait? |
15 |
|
16 |
sys-process/iotop |
17 |
|
18 |
> * What was network usage like? (I have a caching proxy server on the |
19 |
> network |
20 |
|
21 |
Lots of different tools to look at network performance: |
22 |
|
23 |
wireshark, (look around /usr/portage/net-analyzer) |
24 |
|
25 |
|
26 |
> so even if distfiles are lost on-system, well, a cache hit |
27 |
> transfers at up to around 50MB/s. It'd be better, except for read |
28 |
> performance limitations on the router box, and write performance |
29 |
> limitations on the local machine) |
30 |
|
31 |
|
32 |
bonnie++ (or bonnie) |
33 |
|
34 |
|
35 |
> * What was the temperature of each CPU core, RAM module and hard |
36 |
> drive? (Not so relevant for improving system performance, but still of |
37 |
> interest.) |
38 |
|
39 |
app-admin/hddtemp (for drives) |
40 |
|
41 |
dunno on individual cpu cores... |
42 |
|
43 |
> I'd like to have a web interface I could navigate to which would show |
44 |
> graphs of these counters. |
45 |
|
46 |
|
47 |
Now all of that in one gui tool? Do post back when you get it working, |
48 |
as I'd like to use it too!!!!! |
49 |
|
50 |
hth, |
51 |
James |