1 |
>> > I'm testing this USB 3.0 bus-powered hard drive: |
2 |
>> > |
3 |
>> > http://www.amazon.com/gp/product/B0041OSQ9S |
4 |
>> > |
5 |
>> > and I get: |
6 |
>> > |
7 |
>> > # hdparm -tT /dev/sdb |
8 |
>> > /dev/sdb: |
9 |
>> > Timing cached reads: 8006 MB in 2.00 seconds = 4004.33 MB/sec |
10 |
>> > Timing buffered disk reads: 252 MB in 3.01 seconds = 83.63 MB/sec |
11 |
>> > |
12 |
>> > # hdparm -tT /dev/sdb |
13 |
>> > /dev/sdb: |
14 |
>> > Timing cached reads: 8230 MB in 2.00 seconds = 4116.54 MB/sec |
15 |
>> > Timing buffered disk reads: 252 MB in 3.02 seconds = 83.55 MB/sec |
16 |
>> > |
17 |
>> > # hdparm -tT /dev/sdb |
18 |
>> > /dev/sdb: |
19 |
>> > Timing cached reads: 8446 MB in 2.00 seconds = 4224.36 MB/sec |
20 |
>> > Timing buffered disk reads: 230 MB in 3.02 seconds = 76.28 MB/sec |
21 |
>> > |
22 |
>> > Wikipedia says USB 3.0 has transmission speeds of up to 5 Gbit/s. |
23 |
>> > Doesn't MB/sec denote mega*bytes* per second? |
24 |
>> > |
25 |
>> > - Grant |
26 |
>> |
27 |
>> 4000MB/s = 4Gb/s |
28 |
> |
29 |
> |
30 |
> please read man hdparm |
31 |
> |
32 |
> -T Perform timings of cache reads for benchmark and comparison purposes. |
33 |
> For meaningful results, this operation |
34 |
> should be repeated 2-3 times on an otherwise inactive system (no |
35 |
> other active processes) with at least a couple |
36 |
> of megabytes of free memory. This displays the speed of reading |
37 |
> directly from the Linux buffer cache without |
38 |
> disk access. This measurement is essentially an indication of |
39 |
> the throughput of the processor, cache, and mem- |
40 |
> ory of the system under test. |
41 |
> |
42 |
> |
43 |
> as you can see, those numbers have nothing to do with the transport. |
44 |
> |
45 |
> And 80mb/sec for a harddisk is really, really good. |
46 |
|
47 |
Here's what I get from the same hard drive plugged into a USB 2.0 port: |
48 |
|
49 |
# hdparm -t /dev/sdb |
50 |
/dev/sdb: |
51 |
Timing buffered disk reads: 102 MB in 3.01 seconds = 33.90 MB/sec |
52 |
|
53 |
# hdparm -t /dev/sdb |
54 |
/dev/sdb: |
55 |
Timing buffered disk reads: 92 MB in 3.00 seconds = 30.66 MB/sec |
56 |
|
57 |
# hdparm -t /dev/sdb |
58 |
/dev/sdb: |
59 |
Timing buffered disk reads: 102 MB in 3.03 seconds = 33.63 MB/sec |
60 |
|
61 |
So USB 2.0 throughput is obviously creating a bottleneck. USB 2.0 |
62 |
throughput is said to be 60 MB/s so I'm surprised I'm not doing much |
63 |
better than 30 MB/s there. |
64 |
|
65 |
USB 3.0 throughput is said to be 625 MB/s so I must be running up |
66 |
against the speed of the disk itself in USB 3.0 mode, correct? Here's |
67 |
what I get from my internal SATA hard drive, but it is surely a much |
68 |
faster disk: |
69 |
|
70 |
# hdparm -t /dev/sda |
71 |
/dev/sda: |
72 |
Timing buffered disk reads: 412 MB in 3.01 seconds = 136.99 MB/sec |
73 |
|
74 |
# hdparm -t /dev/sda |
75 |
/dev/sda: |
76 |
Timing buffered disk reads: 412 MB in 3.01 seconds = 136.75 MB/sec |
77 |
|
78 |
# hdparm -t /dev/sda |
79 |
/dev/sda: |
80 |
Timing buffered disk reads: 414 MB in 3.01 seconds = 137.55 MB/sec |
81 |
|
82 |
- Grant |