| 1 |
Florian Philipp <lists@×××××××××××.net> wrote: |
| 2 |
|
| 3 |
> > Even if the i-nodes are sequential on-disk, there's no reason to think |
| 4 |
> > that the data blocks associated with the inodes are in any particular |
| 5 |
> > order with respect to the i-nodes themselves. |
| 6 |
> |
| 7 |
> You could probably find the intended order by using debugfs (at least |
| 8 |
> for ext*). The following command should output the first physical block |
| 9 |
> of every file: |
| 10 |
> find /var/db/portage/ -type f -printf 'bmap <%i> 0\n' | sudo debugfs |
| 11 |
> /dev/mapper/vg-portage |
| 12 |
|
| 13 |
This kind of order is not important for copy speed. |
| 14 |
|
| 15 |
Copy speed is dominated by write speed and write speed is dominated by seeks |
| 16 |
that are a result of keeping meta data up to date. |
| 17 |
|
| 18 |
Jörg |
| 19 |
|
| 20 |
-- |
| 21 |
EMail:joerg@××××××××××××××××××××××××.de (home) Jörg Schilling D-13353 Berlin |
| 22 |
js@××××××××××××.de (uni) |
| 23 |
joerg.schilling@××××××××××××××××.de (work) Blog: http://schily.blogspot.com/ |
| 24 |
URL: http://cdrecord.berlios.de/private/ ftp://ftp.berlios.de/pub/schily |
Archives