Newbe - hardware recommendations
Eric Chang
scrazy77 at gmail.com
Wed Jan 4 16:18:41 UTC 2006
My experience:
2 perlbal -> 2 trackers -> 2 apache/mod_php -> 2 mysql (1 master, 1
replication slave)
2 storage node ( 8 sata 300g disks total)
now store 2139276 files (include html, jpg ,xml...all files in my blog
service)
Checking devices...
host device size(G) used(G) free(G) use%
---- --------------- ---------- ---------- ---------- ------
[ 1] dev1 267.556 25.126 242.430 9.39%
[ 1] dev2 275.073 25.821 249.252 9.39%
[ 1] dev3 275.073 25.467 249.606 9.26%
[ 1] dev4 275.073 25.885 249.188 9.41%
[ 2] dev11 264.183 4.712 259.471 1.78%
[ 2] dev12 279.450 4.941 274.509 1.77%
[ 2] dev7 275.073 39.244 235.829 14.27%
[ 2] dev8 275.073 39.258 235.816 14.27%
---- --------------- ---------- ---------- ---------- ------
total: 2186.555 190.453 1996.102 8.71%
Works fine, and you can find that dev11 dev12 is replaced 2 disks failed
last month.
Since min devcount=2 so, we didn't lose any files.
And the dev weight setting , let us balanced the files write to all disks.
But I've found the write speed is not fast enough for my service.
So I'm redesigning my storage node.
Must lower power, lower price, and get more and more spindles as we can.
The reference is Petabox using in http://www.archive.org (
http://www.archive.org/web/petabox.php).
I think the mysql will not the bottlenack, but single point failure maybe
the problem.
I've not found good opensource solution to do auto fail-over with mysql
node.
And I must thank livejournal provide us a good storage solution!
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://lists.danga.com/pipermail/mogilefs/attachments/20060105/3e2fcaef/attachment.htm
More information about the mogilefs
mailing list