| 1 |
Peter Humphrey <peter@××××××××××××.uk> schrieb: |
| 2 |
|
| 3 |
> On Friday 20 June 2014 19:48:14 Kai Krakow wrote: |
| 4 |
>> microcai <microcai@×××××××××××××.org> schrieb: |
| 5 |
>> > rsync is doing bunch of 4k ramdon IO when updateing portage tree, |
| 6 |
>> > that will kill SSDs with much higher Write Amplification Factror. |
| 7 |
>> > |
| 8 |
>> > I have a 2year old SSDs that have reported Write Amplification Factor |
| 9 |
>> > of 26. I think the only reason is that I put portage tree on this SSD |
| 10 |
>> > to speed it up. |
| 11 |
>> |
| 12 |
>> Use a file system that turns random writes into sequential writes, like |
| 13 |
>> the pretty newcomer f2fs. You could try using it for your rootfs but |
| 14 |
>> currently I suggest just creating a separate partition for it and either |
| 15 |
>> mount it as /usr/portage or symlink that dir into this directory (that |
| 16 |
>> way you could use it for other purposes, too, that generate random short |
| 17 |
>> writes, like log files). |
| 18 |
> |
| 19 |
> Well, there's a surprise! Thanks for mentioning f2fs. I've just converted |
| 20 |
> my Atom box's seven partitions to it, recompiled the kernel to include it, |
| 21 |
> changed the fstab entries and rebooted. It just worked. |
| 22 |
|
| 23 |
It's said to be twice as fast with some workloads (especially write |
| 24 |
workloads). Can you confirm that? I didn't try it that much yet - usually I |
| 25 |
use it for pendrives only. I have no experience using it for rootfs. |
| 26 |
|
| 27 |
And while we are at it, I'd also like to mention bcache. Tho, conversion is |
| 28 |
not straight forward. However, I'm going to try that soon for my spinning |
| 29 |
rust btrfs. |
| 30 |
|
| 31 |
-- |
| 32 |
Replies to list only preferred. |
Archives