Related to the latency question, I just watched the Jane Street video (very nice!) and he mentioned that they use operator-initiated failover and he didn't know of anyone using a consensus based approach because it adds…
What kind of latency does the consensus add? We are looking at adding fault tolerance to our matching engine but can only afford 10-15 micros.
A way to get around Twitter's 800 tweet home timeline limit. Or maybe this exists already? That would be great.
You would think from reading this that PySpark does not exist.
Related to the latency question, I just watched the Jane Street video (very nice!) and he mentioned that they use operator-initiated failover and he didn't know of anyone using a consensus based approach because it adds…
What kind of latency does the consensus add? We are looking at adding fault tolerance to our matching engine but can only afford 10-15 micros.
A way to get around Twitter's 800 tweet home timeline limit. Or maybe this exists already? That would be great.
You would think from reading this that PySpark does not exist.