2) As the exchange has grown, latency has too.
Which sucks. Latency is higher than it was 6 months ago.
So, a few weeks ago, we started working on reducing it.
3) We've successfully gotten it down by around 30% from where it was, though still slightly higher than in the summer.
There's more work to go.
We could probably get a factor of ~1.5 improvement over the next month.
4) Instead, we're going to do something a big more ambitious: re-writing the bulk of the matching engine.
The downside is this won't pay dividends until it's done, probably in two months or so.
The upside is that it should, hopefully, give us 2x or better improvements.
