As solid-state drives are becoming very popular with enthusiasts and a common choice for those interested in high-performance data storage, at Phoronix we have reviewed many SSDs from OCZ Technology including the Agility, Agility EX, Vertex, and Solid 2. Today we are reviewing the next-generation Vertex SSD, which is the Vertex 2, and it promises to offer much faster reads and writes, is rated to last an extra 500,000 hours beyond the 1.5 million hour MTBF of the original Vertex, and is available in capacities up to 480GB.
A review of the RevoDrive would be very interesting (if you can get your hands on one)
The OCZ website does not list linux compat. for that product, but the Sil3124 used should work out of the box and I wonder if you can have the two "drives" show up as two drives and use linux software raid on it.
Also comparing linux software raid with the raid from the Sil (which also should be in software) would be interesting.
Please publish benchmarks comparing the Vertex 2 to the Intel MLC G2 SSD. I think a lot of people own the latter (as it's cheap and was said to have the best ssd controller for some time) and are considering an upgrade now.
Different filesystems would be interesting, too :-)
I have the drive and two problems emerged:
Running it on a Samsung NC20 doesnt work with fc13 and ext4, doesnt matter if LVM or not. Netboot install fails. Installation on a different computer - booting on NC20 fails. It works perfect with ext3, booting is not as fast as i expected it.
And GUI disk utility (Gnome) reported nasty values for a block-reliability related SMART-interface, but this seems to be a firmware bug (no problems or data-loss happened).
I recommend a modern SSD for Laptops. No noises, no vibrations, cool, very good speed. On a well-equiped desktop with a lot of RAM and running Linux, i had no massive speedup (but still noteable), due to cashing and Linux not being Windows.
It's not clear from the article if all the drives were brand new or not. Especially for older drives without TRIM support (or ones that require an explicit tool to TRIM, if said tool hasn't been used), comparing a brand new out of the box drive with drives that have been used heavily during previous benchmarks will completely skew the results.