ANTs Software is in essence a “public venture capital” outfit, with over $100 million in market capitalization and negligible revenue. It also features some interesting ideas in OLTP data management, a new management team (as of last year), and a new strategy. ANTs’ new strategy, in my opinion, stands a better chance of success than its predecessor, which in essence was to tell large enterprises “Throw out Oracle and use ANTs DB instead for your most mission-critical OLTP apps, because it’s faster, cheaper, and compatible.”
There actually are two prongs to ANTs’ new strategy. One of them, however, is a Big Secret that the company adamantly insists I not write about, notwithstanding that it is pretty much spelled out in this press release. The other is high-performance OLTP for specialized apps, in defense, telecom, financial trading, etc. The best way to summarize what “high-performance” means is this: When I asked what the technical sweet spot for ANTs DB, Engineering VP Rao Yendluri said “Half a million updates per second.”
The secret to ANTs’ technology is in essence radical modularity. In the past the company bragged more about its lock-free approach, but now ANTs is talking more about another feature and patent, the batching of commutative updates. Here’s how I understand that idea. In essence, ANTs DB does all of an update in memory except for the commit part, then commits in one big batch as long as what’s being committed is “commutative” – i.e., as long as the updates are independent of each other and hence can safely be made in any order. Consequently, CPU processing of an update never has to wait for disk I/O, which is a cool memory-centric approach that mainstream DBMS might do well to emulate.
Come to think of it – as I understand things, that’s also the essence of the lockless approach to transaction consistency. I.e., it’s the essence of the whole ANTs DB architecture. Nice idea. As long as performance (including, when appropriate, redos) holds up in practice, I don’t immediately see any downside to it.