1 |
It is my opinion that benchmarks should be done with a real benchmark tool. |
2 |
|
3 |
Try with bonnie++ |
4 |
This will really show you the strengths and weaknesses of your setup. |
5 |
|
6 |
Good luck, |
7 |
Simon |
8 |
|
9 |
On Thu, Aug 11, 2011 at 1:49 PM, Volker Armin Hemmann < |
10 |
volkerarmin@××××××××××.com> wrote: |
11 |
|
12 |
> Am Donnerstag 11 August 2011, 10:30:04 schrieb Mark Knecht: |
13 |
> > On Thu, Aug 11, 2011 at 10:12 AM, Grant <emailgrant@×××××.com> wrote: |
14 |
> > > I'm testing this USB 3.0 bus-powered hard drive: |
15 |
> > > |
16 |
> > > http://www.amazon.com/gp/product/B0041OSQ9S |
17 |
> > > |
18 |
> > > and I get: |
19 |
> > > |
20 |
> > > # hdparm -tT /dev/sdb |
21 |
> > > /dev/sdb: |
22 |
> > > Timing cached reads: 8006 MB in 2.00 seconds = 4004.33 MB/sec |
23 |
> > > Timing buffered disk reads: 252 MB in 3.01 seconds = 83.63 MB/sec |
24 |
> > > |
25 |
> > > # hdparm -tT /dev/sdb |
26 |
> > > /dev/sdb: |
27 |
> > > Timing cached reads: 8230 MB in 2.00 seconds = 4116.54 MB/sec |
28 |
> > > Timing buffered disk reads: 252 MB in 3.02 seconds = 83.55 MB/sec |
29 |
> > > |
30 |
> > > # hdparm -tT /dev/sdb |
31 |
> > > /dev/sdb: |
32 |
> > > Timing cached reads: 8446 MB in 2.00 seconds = 4224.36 MB/sec |
33 |
> > > Timing buffered disk reads: 230 MB in 3.02 seconds = 76.28 MB/sec |
34 |
> > > |
35 |
> > > Wikipedia says USB 3.0 has transmission speeds of up to 5 Gbit/s. |
36 |
> > > Doesn't MB/sec denote mega*bytes* per second? |
37 |
> > > |
38 |
> > > - Grant |
39 |
> > |
40 |
> > 4000MB/s = 4Gb/s |
41 |
> |
42 |
> |
43 |
> please read man hdparm |
44 |
> |
45 |
> -T Perform timings of cache reads for benchmark and comparison |
46 |
> purposes. |
47 |
> For meaningful results, this operation |
48 |
> should be repeated 2-3 times on an otherwise inactive system |
49 |
> (no |
50 |
> other active processes) with at least a couple |
51 |
> of megabytes of free memory. This displays the speed of |
52 |
> reading |
53 |
> directly from the Linux buffer cache without |
54 |
> disk access. This measurement is essentially an indication of |
55 |
> the throughput of the processor, cache, and mem- |
56 |
> ory of the system under test. |
57 |
> |
58 |
> |
59 |
> as you can see, those numbers have nothing to do with the transport. |
60 |
> |
61 |
> And 80mb/sec for a harddisk is really, really good. |
62 |
> |
63 |
> -- |
64 |
> #163933 |
65 |
> |
66 |
> |