Gentoo Archives: gentoo-user

From: Joshua Murphy <poisonbl@×××××.com>
To: gentoo-user@l.g.o
Subject: Re: OT: Re: [gentoo-user] X Freezes With Firefox on Many Post 2.6.38 Kernels
Date: Sun, 31 Jul 2011 14:18:33
In Reply to: Re: OT: Re: [gentoo-user] X Freezes With Firefox on Many Post 2.6.38 Kernels by Peter Humphrey
1 On Sun, Jul 31, 2011 at 9:51 AM, Peter Humphrey
2 <peter@××××××××××××××.org> wrote:
3 > On Sunday 31 July 2011 14:15:20 Joshua Murphy wrote:
4 >
5 >> Well, GParted, if I recall, does a couple checks to guess 'best' block
6 >> size when cloning or moving a partition, but I'm really not sure how
7 >> it does things when shrinking and shifting it sideways to a spot that
8 >> overlaps with where it started... but based on the above, I would
9 >> guess it really does do a bs of 512, or ar best, the cluster size of
10 >> the file system it is moving (usually 4k), since it's moving the data
11 >> stored there, not the whole partition, block for block.
12 >
13 > In fact it did run those tests, and it settled on a value of, I think, 16MB
14 > blocks. It then ran a read-only test of the entire file system, and only then
15 > started copying it. As it was moving the partition upwards by about half its
16 > occupied size, there was considerable overlap. That must mean that it
17 > started with the highest-numbered block and worked steadily (very!)
18 > downwards.
19 >
20 > I don't know where in the partition it ran its speed tests, but on a
21 > partition that occupies almost all the physical disk, as it did, there must
22 > be a considerable speed difference between its two ends.
23 >
24 > --
25 > Rgds
26 > Peter           Linux Counter 5290, 1994-04-23
27 >
28 >
30 There probably is a fair chunk of difference in maximum speed the disk
31 can work at on each end (I've even seen around a 20MB/s difference on
32 several 160GB drives I've dealt with), but outside of some older
33 drives that've been heavily abused in their lives, I'm not sure I've
34 seen a sata drive that I've used my usual drive test (MHDD on a
35 Hiren's bootable USB) on register below around 60MB/s on the slow end,
36 and USB2's *theoretical* limit is 480Mb/s (60MB/s) ... real-world
37 implementations rarely reach, let alone top, around 40MB/s, so disk
38 speed variation across the disk is an unlikely source of the slowdown.
39 More likely, it's the fact that parted has to start from the end, and
40 work its way backwards, reading, writing, and verifying in separate
41 rotations of the disk with no benefit from the drive's ability to
42 stream a larger block into cache, since the whole process is backwards
43 compared to the streaming read most drives are optimized for. Of
44 course, this is all off the cuff conjecture on my part, including my
45 assumptions about how parted approaches the whole task... mixed with a
46 bit of anecdotal evidence on my end... but, makes for amusing
47 conversation and contemplation, if nothing more substantial. I will
48 point out that the newer advanced format WD 500GB blue's I've worked
49 recently with pulled a consistent 120-110MB/s speed from end to end...
50 when their older 320s usually peaked at around 85 or so.
52 --
53 Poison [BLX]
54 Joshua M. Murphy


Subject Author
Re: OT: Re: [gentoo-user] X Freezes With Firefox on Many Post 2.6.38 Kernels Peter Humphrey <peter@××××××××××××××.org>