At the last few conferences I've presented at, there have been questions about using SSDs (Solid-State Drives) for enterprise storage and whether that will change some of the database maintenance practices. My answer to that is "I don't know" (ha – bet you thought I was going to say "It depends!") because adoption of SSDs is very low. I haven't been able to find much info about using them, but the Microsoft Research group in Cambridge just published a research paper Migrating Sever Storage to SSDs: Analysis of Tradeoffs, which does a nice job of walking through the issues involved and concludes that for the majority of workloads, it makes more economic sense to host them on HDDs. The exception is for top-end OLTP databases. I'll warn you that this isn't a whitepaper – it's a research paper, and gets a bit deep into algorithms and mathematical analyses, but if you're up to the challenge it's a great read.
You can download the paper from http://research.microsoft.com/en-us/um/people/antr/ms/ssd.pdf. Enjoy!
PS I found it on James Hamilton's blog.
3 thoughts on “New research paper: Migrating Server Storage to SSDs: Analysis of Tradeoffs”
Prediction: Within 2 years, you will have 2-4TB PCI-X SSD cards that will beat the shit out a rack full of EMC(insert SAN vendor here) drives. The problem is the system BUS will need to catch up. The new intel xeon procs are a step in the right direction though.
2 years? try 3 months. Fusion-io is gearing up to double the size of their iodrive duo every 6 months. So, right now their top is 640GB 1.28TB is due out in Q3 then 6 months for each size doubling after than for as long as they can. At 1.5GB sec reads and 200k IO’s they are already at the top of the food chain as far as SAN or any IO performance measurement for that matter.
Interesting article, but its a pity they didn’t measure a SQL Server load specifically as there are very big wins to be made from using SSDs under tempdb, with minimal risk given temporary nature of tempdb workload.