I’ve been playing with my new work laptop, a Dell E4200 (which I chose as I wanted something light) and thought I’d run Bonnie++ on my XFS /home partition on the SSD (a “SAMSUNG SSD Thin uSATA 128GB M” according to dmesg) to see how it compares to spinning disk. Here’s the results with Ubuntu Intrepid (8.10):
Version 1.03c ------Sequential Output------ --Sequential Input- --Random-
-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
sys26 2G 68551 27 38896 23 90404 30 1356 6
------Sequential Create------ --------Random Create--------
-Create-- --Read--- -Delete-- -Create-- --Read--- -Delete--
files /sec %CP /sec %CP /sec %CP /sec %CP /sec %CP /sec %CP
16 556 8 +++++ +++ 679 7 605 8 +++++ +++ 442 5
sys26,2G,,,68551,27,38896,23,,,90404,30,1355.6,6,16,556,8,+++++,+++,679,7,605,8,+++++,+++,442,5
real 3m56.775s
user 0m0.580s
sys 0m36.930s
So comparing with some old results on my home desktop system seems to show that the block I/O numbers are better, but the file manipulation stuff is much worse! Once I can get btrfs on here I’ll have to try again. π