All times are UTC-06:00




Post new topic  Reply to topic  [ 3 posts ] 
Author Message
PostPosted: Sat Jun 04, 2011 2:00 pm 
Offline

Joined: Sun May 01, 2011 6:12 pm
Posts: 42
Location: Denmark
Hello all

I'm wondering if I could get someone to benchmark the internal SSD of the Smartbook - and also the Smarttop, just to see how they compare. iozone works quite well for this. This command tests 4k, 64k and 512k sequential and random read/write operations.
Code:
iozone -I -a -s 256M -r 4k -r 64k -r 512k -i 0 -i 1 -i 2
I'm especially interested in the random read rate. After switching to an SSD in my stationary computer I've realized how much of a difference this can make, how much of a bottleneck a conventional HDD is. So I'm curious to see how capable the internal SSD in the Smartbook is.

Just for comparison: my 80GB Intel Postville X25-M SSD can get a ~22MB/s random read throughput with a record size of 4KB, while my Western Digital WD20EARS HDD gets ~500KB/s.

Thanks!


Top
   
 Post subject: result..
PostPosted: Wed Jun 15, 2011 10:37 am 
Offline

Joined: Tue Feb 03, 2009 7:32 am
Posts: 19
Location: Toronto, Canada
Well, not sure helpful this is...

I ran iozone (with the specific parameters) on an Efika MX smartbook on the internal "disk"...

# uname -a
Linux kicsi 2.6.31.14.20-efikamx #1 PREEMPT Fri Feb 25 13:24:56 CST 2011 armv7l GNU/Linux

# runlevel
N 2

# iozone -I -a -s 256M -r 4k -r 64k -r 512k -i 0 -i 1 -i 2
Iozone: Performance Test of File I/O
Version $Revision: 3.308 $
Compiled for 32 bit mode.
Build: linux

Contributors:William Norcott, Don Capps, Isom Crawford, Kirby Collins
Al Slater, Scott Rhine, Mike Wisner, Ken Goss
Steve Landherr, Brad Smith, Mark Kelly, Dr. Alain CYR,
Randy Dunlap, Mark Montague, Dan Million, Gavin Brebner,
Jean-Marc Zucconi, Jeff Blomberg, Benny Halevy,
Erik Habbinga, Kris Strecker, Walter Wong, Joshua Root.

Run began: Tue Jun 14 17:29:38 2011

O_DIRECT feature enabled
Auto Mode
File size set to 262144 KB
Record Size 4 KB
Record Size 64 KB
Record Size 512 KB
Command line used: iozone -I -a -s 256M -r 4k -r 64k -r 512k -i 0 -i 1 -i 2
Output is in Kbytes/sec
Time Resolution = 0.000001 seconds.
Processor cache size set to 1024 Kbytes.
Processor cache line size set to 32 bytes.
File stride size set to 17 * record size.
random random bkwd record stride
KB reclen write rewrite read reread read write read rewrite read fwrite frewrite fread freread
262144 4 1419 1499 4513 4448 3802 24
262144 64 5954 6818 18530 18580 18516 379
262144 512 7242 7781 15782 15826 16293 2160

iozone test complete.


Top
   
 Post subject:
PostPosted: Sun Jun 19, 2011 4:54 am 
Offline

Joined: Sun May 01, 2011 6:12 pm
Posts: 42
Location: Denmark
Thank you! These results are very helpful.

Here are the results formatted a bit nicer:
Code:
Command line used: iozone -I -a -s 256M -r 4k -r 64k -r 512k -i 0 -i 1 -i 2
Output is in Kbytes/sec

[...]
random random
KB reclen write rewrite read reread read write
262144 4 1419 1499 4513 4448 3802 24
262144 64 5954 6818 18530 18580 18516 379
262144 512 7242 7781 15782 15826 16293 2160
These results show that when reading 4 KB blocks in random positions from the SSD, we get a throughput of 3800 KB/s (first row with a "reclen" of 4, in the "random read" column).

This is actually better than what I expected. With reference to my original post, it's about 8 times faster than a conventional hard drive (500 KB/s), but still about 6 times slower than an Intel SSD (22 MB/s). But the Intel SSD is probably around 10 times more expensive, so I definitely think these results are impressive.
3800 KB/s with a block size of 4 KB/s is around 1000 IOPS per second, that's definitely a step up from both a conventional hard drive and the earliest SSDs that made it into netbooks.

The random write speed, however, really falls throgh the floor: 24 KB/s, or 6 IOPS per second (that's a latency of ~170 milliseconds when doing small random writes to the disk!). But it seems we can't have everything, ie. the SSD in the Efika is probably optimized to do fast random 4 KB reads - and wisely so!

I probably should have asked you to perform the test like this though:
Code:
iozone -I -a -s 32M -r 4k -r 64k -r 512k -i 0 -i 1 -i 2
ie. writing a temporary 32 MB file to the disk instead of a 256 MB file (the test much have taken ages to complete at 24 KB/s random writes!). Thanks for enduring :).

By the way - does anyone know if it's a Sandisk iSSD that is in the Efikas?


Top
   
Display posts from previous:  Sort by  
Post new topic  Reply to topic  [ 3 posts ] 

All times are UTC-06:00


Who is online

Users browsing this forum: No registered users and 2 guests


You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum

Search for:
Jump to:  
PowerDeveloper.org: Copyright © 2004-2012, Genesi USA, Inc. The Power Architecture and Power.org wordmarks and the Power and Power.org logos and related marks are trademarks and service marks licensed by Power.org.
All other names and trademarks used are property of their respective owners. Privacy Policy
Powered by phpBB® Forum Software © phpBB Group