1 |
Christian Spoo wrote: |
2 |
|
3 |
> That's just the point. The server will be used to store bigger files |
4 |
> (lots of digital photos, videos, etc.) and publish them. Concerning |
5 |
> Ronan's last sentence I'd stick to speed and reliability as the most |
6 |
> important points. At least with the load of several users that'll access |
7 |
|
8 |
heh. I work for a video and photo sharing site and a good friend of mine |
9 |
works for an HD post production house. His I/O requirements are at least |
10 |
an order of magnitude higher than mine. Publishing vs editing, and it |
11 |
really depends on how one defines these things, are two very different |
12 |
workloads. I tend to have much more random reads than he does and have |
13 |
to partition data and disks to get around that. |
14 |
|
15 |
That said in the four disk range RAID 10 in a single box is a pretty |
16 |
good deal. The cost starts to get ugly as your arrays get bigger and |
17 |
start having to pay for the shelf or enclosure. |
18 |
|
19 |
1 shelf + (16 - 2 (hot spare & parity)) x 500GB x RAID 5 = 7TB usable |
20 |
1 shelf + (16/2) x 500GB x RAID10 = 4TB usable |
21 |
|
22 |
Assuming a total cost of $10k per, 28TB at RAID 5 you'd pay $40k and at |
23 |
RAID10 you'd pay $70k |
24 |
|
25 |
In a single box your only have to worry about drive costs. |
26 |
|
27 |
(3-1) x 250 = 500 GB |
28 |
(2/1) x 250 = 500 GB |
29 |
|
30 |
Assuming drives are $100 then it's the difference of $300 vs $400 which |
31 |
is a much better ratio than the shelf example. At this level going with |
32 |
better performance for that cost difference makes sense. |
33 |
|
34 |
This concludes today's lecture in system administration titled |
35 |
"Economics: Bane of Performance" :-) |
36 |
|
37 |
kashani |
38 |
-- |
39 |
gentoo-server@g.o mailing list |