1 |
On Friday 12 January 2007 03:41, Duncan <1i5t5.duncan@×××.net> wrote |
2 |
about '[gentoo-desktop] Re: CD player recommendations ??': |
3 |
> "Boyd Stephen Smith Jr." <bss03@××××××××××.net> posted |
4 |
> 200701111413.31743.bss03@××××××××××.net, excerpted below, on Thu, 11 |
5 |
> Jan |
6 |
> |
7 |
> 2007 14:13:19 -0600: |
8 |
> > [I'm a little fuzzy here as to weather a read-only |
9 |
> > page is ever written to actual swap space, the kernel may just |
10 |
> > remember where (on disk) the original is keep and release the real |
11 |
> > memory page.] |
12 |
> |
13 |
> That's for local disk, anyway. It's very possibly (and reasonably so) |
14 |
> different with NFS and other remote file systems, where local swap may |
15 |
> be rather faster and more dependable than access to the remote file |
16 |
> system. |
17 |
|
18 |
Or, on a system where (e.g.) /home is on RAID 6 across 5 disks, and swap is |
19 |
on RAID 0 across 5 disks (same disks possibly). In this case I/O to swap |
20 |
is nearly twice as fast, so it may be reasonable to sometimes swap out |
21 |
pages that are backed by files or even *filesystem cache*. This is, in |
22 |
fact, fairly similar to my current setup. |
23 |
|
24 |
You can invent even more esoteric system profiles where (e.g.) swap is many |
25 |
times faster than a particular filesystem, especially for small |
26 |
(page-size) random writes, even without introducing a network. |
27 |
|
28 |
-- |
29 |
"If there's one thing we've established over the years, |
30 |
it's that the vast majority of our users don't have the slightest |
31 |
clue what's best for them in terms of package stability." |
32 |
-- Gentoo Developer Ciaran McCreesh |