Phoenix Pro Testing on a really slow Linux box

longblock454

2[H]4U
Joined
Nov 28, 2004
Messages
2,908
Phoenix Pro: FM-25S2S-60GBP2, firmware 3.1 on a solar powered Atom 330, Fedora 14 with default OS partitioning/OS installation.

Code:
[root@garage ~]# dd if=/dev/zero of=test.file bs=1M count=1K; sync; date
1024+0 records in
1024+0 records out
1073741824 bytes (1.1 GB) copied, 9.23717 s, 116 MB/s
Fri Nov 26 21:21:53 EST 2010
[root@garage ~]#

Code:
Version  1.96       ------Sequential Output------ --Sequential Input- --Random-
Concurrency   1     -Per Chr- --Block-- -Rewrite- -Per Chr- --Block-- --Seeks--
Machine        Size K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP  /sec %CP
garage        5000M    55  99 110876  92 72984  61   605  99 218262  60  5351 345
Latency               161ms   33246us     218ms   15936us    7091us    9442us
Version  1.96       ------Sequential Create------ --------Random Create--------
garage              -Create-- --Read--- -Delete-- -Create-- --Read--- -Delete--
              files  /sec %CP  /sec %CP  /sec %CP  /sec %CP  /sec %CP  /sec %CP
                 16  3659  97 +++++ +++ 11618  97  1751  46 +++++ +++ 11422  97
Latency             12248us    2379us    2496us     705us     869us     215us
1.96,1.96,garage,1,1290821703,5000M,,55,99,110876,92,72984,61,605,99,218262,60,5351,345,16,,,,,3659,97,+++++,+++,11618,97,1751,46,+++++,+++,11422,97,161ms,33246us,218ms,15936us,7091us,9442us,12248us,2379us,2496us,705us,869us,215us
[root@garage ~]#

Performance improvement was extremely noticeable, this is my first SSD, very satisfied...
 
For comparison, try:

# dd if=/dev/urandom of=test.file bs=1M count=10K

That will probably be very slow, since /dev/urandom is slow. If you have another way to generate a random 10GB test file that is faster, you can use that. It is important that the file be much bigger than the buffer cache (which will use most of your available RAM) for the next tests.

Then try:

# dd if=test.file of=/dev/null bs=1M count=10K

to see what the read speed is for a random file. Then, try:

# dd if=test.file of=test2.file bs=1M count=10K

to check the copy and write speed. If you have a fast HDD or RAID array, you could also copy the random file there and then write it back to the SSD.
 
WOW, that took forever!

Code:
[root@garage ~]# dd if=/dev/urandom of=test.file bs=1M count=10K
10240+0 records in
10240+0 records out
10737418240 bytes (11 GB) copied, 6077.34 s, 1.8 MB/s
[root@garage ~]#


Code:
[root@garage ~]# dd if=test.file of=/dev/null bs=1M count=10K
10240+0 records in
10240+0 records out
10737418240 bytes (11 GB) copied, 75.3075 s, 143 MB/s
[root@garage ~]#

Code:
[root@garage ~]# dd if=test.file of=test2.file bs=1M count=10K
10240+0 records in
10240+0 records out
10737418240 bytes (11 GB) copied, 251.775 s, 42.6 MB/s
[root@garage ~]#

I'm sure the drive has way more in it, Atom just can't hold up it's end of the bargain...
 
Interesting results, thanks for posting. Not bad for a solar powered computer, I guess!
 
Back
Top