On Jan 9, 2013, at 8:02 PM, Ellis H. Wilson III wrote: > > Yea, it's computer science, and I'd love to see you try to toss 16 > crappy SSDs in a box with a crappy RAID controller and get this easy > 2.7GB/s random accesses you are touting. Not going to happen. >
If you had done effort reading what i wrote - i had said that the random latency is under 70 us (achieved) at SSD's, so doubting that is kind of nonsense. it's what you ACHIEVE. And i wrote that if the workload needs a tad of bandwidth, that you can easily achieve 2GB/s, in fact that the raid controllers can achieve easily 2.7GB/s bandwidth. You mix that up now as that you can get with random reads a speed of 2.7 GB/s, which is a very naive way of looking at it. Writes really isn't the problem at hardware that has lots of parallel channels. Maybe you should do some effort to read better. You would also have noticed then that i started a new subject here. Namely not being busy with 500GB. 500GB is total peanuts. Cheapskate oldie 4 socket AMD box with 500GB and done. No need to discuss even, as intel is too expensive simply at that range, not to mention IBM. More interesting is the discussion in the many Terabyte range what to do there, as there will be many alternatives where intel and IBM and others want to have to say something about i bet. Thanks, Vincent _______________________________________________ Beowulf mailing list, Beowulf@beowulf.org sponsored by Penguin Computing To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf
