1 |
I would like to use openmosix for my class network.. |
2 |
16 gentoo's, now running the latest gentoo-sources.. |
3 |
Is overall performance improved when you use openmosix? |
4 |
Like for desktops and such (i noticed preempt isn't in it..) |
5 |
And if so, any good tutorials out there? |
6 |
|
7 |
Thanks! |
8 |
|
9 |
On Thursday 19 September 2002 15:43, Vitaly Kushneriuk wrote: |
10 |
|| On Fri, 2002-09-20 at 01:02, Tantive wrote: |
11 |
|| > Hi! |
12 |
|| > |
13 |
|| > |
14 |
|| > as I'm the OpenMosix (www.openmosix.org) guy for gentoo I would inform |
15 |
|| > you about the benefits you could have using openmosix and would ask you |
16 |
|| > to test the openmosix-ebuilds. |
17 |
|| > |
18 |
|| > In the portage tree we have at the moment: |
19 |
|| > |
20 |
|| > - openmosix-sources (2.4.18-r5 and 2.4.19-r5 are the latest, but masked) |
21 |
|| > The patched vanilla-sources including openmosix and evms. |
22 |
|| > |
23 |
|| > - openmosix-user (latest is 0.2.4, masked, too) |
24 |
|| > The userland tools needed to manage your cluster. |
25 |
|| > |
26 |
|| > - openmosixview (1.2, guess what... masked) |
27 |
|| > A nice gui which shows you the current load in you cluster. |
28 |
|| > |
29 |
|| > |
30 |
|| > |
31 |
|| > OpenMosix will allow you to share your CPU-power across several machines |
32 |
|| > (x86-only at the moment) building a cluster containing several nodes. |
33 |
|| > |
34 |
|| > So let's make an example: You have a slow machine and a fast one. If you |
35 |
|| > want to compile a new kernel on the slow one OpenMosix will "migrate" |
36 |
|| > these processes to the fast one. This means you could compile your |
37 |
|| > kernel at approx. the same speed you would on your good machine. |
38 |
|| > Having many nodes in your cluster the speed increases with every node. |
39 |
|| > BUT this happens completely transparent. You will have to do nothing. |
40 |
|| > Nodes can even join and leave a running cluster with no bad effects. |
41 |
|| |
42 |
|| Correct me if I'm wrong, but IIRC, the original mosix was useless for |
43 |
|| the compilation speed improvements due to the fact that a typical |
44 |
|| compilation process doesn't last long enough to even be considered |
45 |
|| for migration. And even if the migration would be forced, the migration |
46 |
|| overhead compared to the process execution time, would kill all the time |
47 |
|| savings. |
48 |
|| |
49 |
|| Vitaly |
50 |
|| |
51 |
|| _______________________________________________ |
52 |
|| gentoo-dev mailing list |
53 |
|| gentoo-dev@g.o |
54 |
|| http://lists.gentoo.org/mailman/listinfo/gentoo-dev |
55 |
|
56 |
-- |
57 |
Bart Verwilst |
58 |
Gentoo Linux Developer |
59 |
Gent, Belgium |