On Sun, Feb 21, 2010 at 10:40:10PM +0100, Frank A. Stevenson wrote: > Such a setup should easily be capable of handling over 10k random reads > / second. But when I was googling after parts for this project, I came > across this beauty: > > http://www.tomshardware.com/news/RAIDDRive-Storage-Flash,7443.html > > http://www.supertalent.com/products/ssd_category_detail.php?type=RAIDDrive > > Access time is listed as 0.1 ms - which is a definite improvement to the > proposed Christmas tree of USB memory sticks, but probably slower than > the grid solution listed above. It doesn't appear to be on sale yet, > neither have I found a price quote.
The access time for 4 usb sticks is already 0.3ms. Their combined size is 64GB. Take 32 of these groups and you get down to 0.01ms (if it scales indeed). What i was able to test was that it scales up to 16 devices. I got 0.08ms access time with this configuration IIRC. Even if you need 2 or even 4 distinct USB host adaptors to connect 128 devices, you still end up faster and cheaper than with SSD. Besides that, those PCIe SSDs are still more expensive than 2.5inch SSDs. And we certainly do not need hundreds of megabytes per second bandwidth. The write performance is also of no concern. As for the optimization of the USB bus, that comes for free. If you start 4 CPU threads and manage to make each thread access the data blocks of a single device, then the access time improvements scale linearly with the number of devices. _______________________________________________ A51 mailing list [email protected] http://lists.lists.reflextor.com/cgi-bin/mailman/listinfo/a51
