Hacker News Reader

Comment by igrigorik | Hacker News Reader

Huh, interesting. Any resources where I can learn more about these firmware optimizations? Intuitively, that doesn't make much sense: it would seem that dropping a lot of the software overhead associated with concurrency, etc, would yield a significant improvement.

Having said that, it's also possible that the actual 'software overhead' is pretty much negligible when compared to disk access times.

Would love to learn more on this.

View on HN

I'm not familiar with RethinkDB, but I have read the H-Store paper and I think some of its optimizations are applicable to RAM but not SSD. SSDs are much faster than disk, but I don't think they're fast enough that you can afford to eliminate caching or locking. In particular, good SSDs are internally parallel and require multiple concurrent I/Os for good performance, so you'll probably have to execute multiple transactions concurrently.

Well, if an average random access to disk is ~5ms, and an X25 Intel SSD is ~500 microseconds, then we're already talking a 10x difference and that's for a 'consumer grade' SSD. I'm sure the latency will come down over time as well. If you look at some of the PCI-E SSD solutions, then we're dipping below 100 microseconds, which means we're into 50-60x difference.

Indeed. Even with ram, concurrency is optimal on many server architectures. See NUMA, http://en.wikipedia.org/wiki/Non-Uniform_Memory_Access

Reply on news.ycombinator.com