Blogging about databases & distributed systems. Operated by @mulander
Joined December 2020
- Tweets12
- Following3
- Followers5
- Likes7
overthewal retweeted
Samay Sharma: Debugging Postgres autovacuum problems: 13 tips postgr.es/p/5oj
overthewal retweeted
New blog post today 📣 from Citus database engineer @halilozanakgul! about all the @PostgreSQL monitoring & observability features added in Citus 11 🐘🦄 All about citus_stat_activity, citus_lock_waits, & the new global pid citusdata.com/blog/2022/07/2…
overthewal retweeted
We are starting #PostgreSQL Charity Workshop #Warsaw in 20mins. We will try to go online. Fingers crossed! youtu.be/TK73UettvDI
Great post-mortem from @SlackEng on how a distributed system cascading failure emerged during a controlled component rollout.
slack.engineering/slacks-inc…
You should carefully evaluate extensions that you use in your PostgreSQL deployments. Not only that is code loaded into memory along with your production data but also, as this case at Amazon shows - can expose your remaining infrastructure.
blog.lightspin.io/aws-rds-cr…
overthewal retweeted
Sure! Here is a small script that ingests the output of ls into sqlite and puts it in a table that we later query in-memory to count how many files we have, how many per group and the largest file in a group.
overthewal retweeted
** A nondeterministic finite automaton (NFA) is used for matching, so the performance is bounded by O(N*M) where N is the size of the regular expression and M is the size of the input string. The matcher never exhibits exponential behavior. ** via sqlite.org/src/raw/ext/misc/…
I replaced a shell script today with AWK and sqlite. The result is easier to maintain and 141 times (sic!) faster than the code it replaced. SQLite is grossly undervalued for typical scripting tasks. AWK the data into a table and .import - solves a lot of problems.
Does anyone know why `regexp` from `sqlite-ext/pcre.so` is marked as non-deterministic? Is this an oversight or am I missing something? #sqlite
