1 |
i don't have any official numbers, as i don't run any of the master mirrors, and never bothered to |
2 |
test it out. i manage 2 here in canada though, and friend manages a 3rd, all 3 are running from |
3 |
ramdisk, you're welcome to try them out for yourself if you wish. rsync4, rsync5, & |
4 |
rsync9.ca.gentoo.org. |
5 |
|
6 |
i noticed an instant jump in the speed when i moved my mirror from u160 scsi to ramdisk, it does |
7 |
make sense if you think about it. you're serving roughly 100k tiny files to a bunch of people all at |
8 |
once. that's a lot of seek time on any hard disk. i also sync the ramdisk every 30 mins directly to |
9 |
ram. basically, it's a lot less disk thrashing. ;) |
10 |
|
11 |
rob |
12 |
|
13 |
Georgi Georgiev wrote: |
14 |
> maillog: 01/12/2004-16:30:40(-0700): Rob Baxter types |
15 |
> |
16 |
>>i think the point is that the data that gets cached can and does change |
17 |
>>every 30 minutes, so caching doesn't really help. |
18 |
> |
19 |
> |
20 |
> It does help. If data changes, it is first updated in the cache. New |
21 |
> data is served directly out of the cache, while the hard disk is synced |
22 |
> in the background. That's unless I am majorly mistaken about how caching |
23 |
> works. |
24 |
> |
25 |
> |
26 |
>>all 5 servers in the rsync.gentoo.org rotation are currently running |
27 |
>>rsync out of ram. i think i can safely say they wouldn't be nearly as |
28 |
>>fast as they are, running off a hard disk. |
29 |
> |
30 |
> |
31 |
> Do you have some real numbers? I am not trying to doubt you too much. I |
32 |
> am genuinely curious how big the speedup is and if it is worth the |
33 |
> effort. All I wanted to point in my post is that the speedup is probably |
34 |
> not that great, but I'd really like to see benchmark numbers if someone |
35 |
> went to the trouble of doing it. |
36 |
> |
37 |
> |
38 |
>>besides, ram is cheap |
39 |
> |
40 |
> |
41 |
> That's pretty relative. $70 for 512MB is not cheap for me. One reason |
42 |
> why my poor "server" is still running with 2x512MB *PC133*. |
43 |
> |
44 |
> |
45 |
>>and has a small footprint (smaller blocks) using |
46 |
>>ramdrive, why not use it. |
47 |
> |
48 |
> |
49 |
> Well, you may be right. I guess I could try serving two trees and do |
50 |
> some tests myself. |
51 |
> |
52 |
|
53 |
|
54 |
-- |
55 |
gentoo-mirrors@g.o mailing list |