1 |
On Tue, Aug 14, 2012 at 3:55 PM, Alecks Gates <alecks.g@×××××.com> wrote: |
2 |
|
3 |
> On Tue, Aug 14, 2012 at 12:50 PM, Michael Hampicke <gentoo-user@××××.biz> |
4 |
> wrote: |
5 |
> > Am 14.08.2012 19:42, schrieb Volker Armin Hemmann: |
6 |
> >> Am Dienstag, 14. August 2012, 13:21:35 schrieb Jason Weisberger: |
7 |
> >>> Sure, but wouldn't compression make write operations slower? And |
8 |
> isn't he |
9 |
> >>> looking for performance? |
10 |
> >> |
11 |
> >> not really. As long as the CPU can compress faster than the disk can |
12 |
> write |
13 |
> >> stuff. |
14 |
> >> |
15 |
> >> More interessting: is btrfs trying to be smart - only compressing |
16 |
> compressible |
17 |
> >> stuff? |
18 |
> >> |
19 |
> > |
20 |
> > It does do that, but letting btrfs check if the files are already |
21 |
> > compressed, if you know, that they are compressed, is a waste of cpu |
22 |
> > cycles :) |
23 |
> > |
24 |
> |
25 |
> Also look into the difference between compress and compress-force[0]. |
26 |
> I wonder how much overhead checking whether or not to compress a file |
27 |
> costs. I use mount options similar to Helmut and get great results: |
28 |
> defaults,autodefrag,space_cache,compress=lzo,subvol=@,relatime |
29 |
> |
30 |
> But most of my data is compressible. Compression makes such a huge |
31 |
> difference, it surprises me. Apparently on this Ubuntu system it |
32 |
> automatically makes use of all files on / as a subvolume in "@". |
33 |
> Interesting. |
34 |
> |
35 |
|
36 |
Huge difference, how? |
37 |
|
38 |
Could we see some bonnie++ comparisons between the various configurations |
39 |
we've discussed for ext4 and btrfs? Depending on the results, it might be |
40 |
getting time for me to take the plunge myself. |
41 |
|
42 |
-- |
43 |
:wq |