POSETTE 2024 is a wrap! 💯 Thanks for joining the fun! Missed it? Watch all 42 talks online 🍿
POSETTE 2024 is a wrap! 💯 Thanks for joining the fun! Missed it? Watch all 42 talks online 🍿
Written by Craig Kerstiens
June 19, 2018
It’s a common question we get at conferences, on calls, in meetings. “Citrus”, “Citius”, “Citus”, is that how you pronounce it? The quick and short of it is, we’re not named after a fruit. You pronounce it like “site-us”.
Most tend to leave it there, without wondering further. But a few do inquire as to the meaning. Citus’s name comes from the Olympic Motto “Citius, Altius, Fortius” which is Latin for “Faster, Higher, Stronger.” Our goal for the Citus extension is to be fast for both transactional and analytical workloads.
On the transactional side we do this by allowing you to horizontally scale out Postgres across nodes. We extend Postgres to no longer be constrained to a single machine. In fact Citus is the only cloud database service1 that has all the power of Postgres without being limited by how large you can vertically scale your instance. Even on the same total hardware by sharding your data under the covers we see customers achieve 3–5x performance boosts. More performance for the same cost tends to be a win.
On the analytical side, we seamlessly parallelize your queries across all the cores in your cluster. We do this without you having to write MapReduce jobs or heavily change your queries. Within Citus you can run a simple SELECT count(*)...
: we split up the query into smaller count (*)
queries, pre-aggregate, then aggregate and return the final result to you. This approach sees performance gains that are correlated to the number of cores in your cluster. In a hundred-core cluster it's not surprising to see 100x performance improvements.
How do you pronounce Citus? The answer is “Site-us”. But the more important question may be what does Citus stand for? And that's speed.
Footnotes