1 |
On Wednesday, September 17, 2014 09:05:09 PM James wrote: |
2 |
> J. Roeleveld <joost <at> antarean.org> writes: |
3 |
> > AFS has caching and can survive temporary disappearance of the |
4 |
server. |
5 |
> |
6 |
> Excellent for low bandwidth connections. Most DFS have mechanisms to |
7 |
> deal with transient failures, but not as generaous on the time-scale |
8 |
> as AFS. I believe, if I recall correctly, these hi-latency, low bandwith |
9 |
> recovery mechanism keen design paramters, at least bake in the |
10 |
> CMU develop cycples, for AFS? |
11 |
> |
12 |
> While attractive for your situation, these features might actually |
13 |
> be detrimental to a hi_performance distributed cluster's needs for |
14 |
> a DFS? |
15 |
|
16 |
I tend to agree. I'm not sure how up-to-date AFS is, but from re-reading the |
17 |
wikipedia pages, it sounds like what I need. Provided I can get it to work |
18 |
together with Samba. I need to allow MS Windows laptops access to the |
19 |
files on the remote location. |
20 |
|
21 |
> > For me, I need to be able to provide Samba filesharing on top of that |
22 |
> > layer on 2 different locations as I don't see the network bandwidth to |
23 |
> > be sufficient for normal operations. (ADSL uplinks tend to be dead |
24 |
slow) |
25 |
> |
26 |
> Yea, I'm not going to be testing OpenAFS for my needs, unless I read |
27 |
> some compelling publish data on it's applicability to high end |
28 |
> clusters best choice as a DFS..... |
29 |
|
30 |
I wouldn't either. |
31 |
|
32 |
> It's probably great for SETI etc etc. |
33 |
|
34 |
Doubtful :) |
35 |
|
36 |
Did you see the following wikipedia page: |
37 |
http://en.wikipedia.org/wiki/List_of_file_systems |
38 |
|
39 |
It contains a nice long list of various distributed, clustered,.... filesystems. |
40 |
I just miss an indication on how well these are still supported and on which |
41 |
OSs these (can) work. |
42 |
|
43 |
-- |
44 |
Joost |