Gentoo Archives: gentoo-user

From: Michael Mol <mikemol@×××××.com>
To: gentoo-user@l.g.o
Subject: Re: [gentoo-user] [OT] Curious hdparm results
Date: Sun, 13 May 2012 21:03:14
Message-Id: CA+czFiDAjGygDNPnbkyUj5vhVRZ0yO+YwTL0OOXdJN8E4eEUBg@mail.gmail.com
In Reply to: [gentoo-user] [OT] Curious hdparm results by walt
1 On Sun, May 13, 2012 at 4:28 PM, walt <w41ter@×××××.com> wrote:
2 > I have a usb3 docking station which is showing some behavior I don't
3 > understand:
4 >
5 >  #hdparm -t /dev/sdc
6 >
7 > /dev/sdc:
8 >  Timing buffered disk reads: 266 MB in  3.00 seconds =  88.59 MB/sec
9 >  Timing buffered disk reads: 268 MB in  3.01 seconds =  89.05 MB/sec
10 >  Timing buffered disk reads: 266 MB in  3.01 seconds =  88.43 MB/sec
11 >  Timing buffered disk reads: 266 MB in  3.02 seconds =  88.10 MB/sec
12 >  Timing buffered disk reads: 306 MB in  3.01 seconds = 101.72 MB/sec
13 >  Timing buffered disk reads: 266 MB in  3.00 seconds =  88.59 MB/sec
14 >  Timing buffered disk reads: 306 MB in  3.00 seconds = 101.84 MB/sec
15 >  Timing buffered disk reads: 306 MB in  3.00 seconds = 101.86 MB/sec
16 >
17 > That's all the same disk, repeating hdparm as fast as I could.  The
18 > disk was not even mounted at the time, and no other disks were active.
19 >
20 > Two very different but reproducible numbers, changing values at random
21 > times.  The only thing I can think of is that the disk may be doing
22 > a SMART self-test, but for some reason the USB connection prevents
23 > me from accessing the data so I can't test my theory.
24 >
25 > Any other ideas?
26
27 bonnie++?
28
29 My first guess is that something on the same USB bus might be
30 periodically active, changing how the kernel manages talking to USB
31 devices. Try ensuring no other USB devices are connected (or active),
32 and running something like "hdparm -t /dev/sdc; hdparm -t /dev/sdc;
33 hdparm -t /dev/sdc; hdparm -t /dev/sdc; hdparm -t /dev/sdc; hdparm -t
34 /dev/sdc" ...letting the shell automate it for you.
35
36 My second guess would be something relating to the kernel's page
37 cache...but I'm unsure if a filesystem needs to be mounted first.
38
39 My third guess would be some internal buffering behavior inside the
40 USB disk, and hdparm's behavior happens to straddle an edge condition.
41
42
43
44
45 --
46 :wq

Replies

Subject Author
[gentoo-user] Re: [OT] Curious hdparm results walt <w41ter@×××××.com>