Top all-time · #1190
Small Datum
Personal blog · smalldatum.blogspot.comdatasystems
Small Datum is a personal blog at smalldatum.blogspot.com about data and systems. Since 2014, 61 different Hacker News readers have linked it 133 times, most often “Review: The Design of the Postgres Storage System”. It is still writing: the last post was on 2026-06-20, and you can follow it by feed.
Most-linked posts?
- Review: The Design of the Postgres Storage System3 people · 7 mentions · first linked 2020-07-15
- Using MMAP with RocksDB2 people · 11 mentions · first linked 2022-05-10
- Garbage Collection for MVCC – MyRocks, InnoDB and Postgres2 people · 4 mentions · first linked 2023-04-13
- Stalls from TRIM after deleting a lot of data2 people · 2 mentions · first linked 2024-06-19
- /2 people · 2 mentions · first linked 2014-04-03
- How efficient is RocksDB for IO-bound, point-query workloads?2 people · 2 mentions · first linked 2025-10-26
- Trying out a dedicated server from Hetzner2 people · 2 mentions · first linked 2024-09-04
- Common prefix skipping, adaptive sort2 people · 2 mentions · first linked 2026-01-03
- /2026/01/common-prefix-skipping-adaptive-sort.html2 people · 2 mentions · first linked 2026-07-06
What Hacker News says?
A number of features stood out to me in this release: 1. Chipping away more at vacuum. Fundamentally Postgres doesn't have undo log and therefore has to have vacuum. It's a trade-off of fast recovery vs well.. having to vacuum. The unfortunate part about vacuum is that it adds load to the system exactly when the system needs all the resources. I hope one day people stop knowing that vacuum exists, we are one step cl…
Comment linking /
on “PostgreSQL 17”Submitted The original LSM paper as a story · 92 points
HN discussionI would say that that's pretty dubious claim with modern versions of Postgres and MySQL/InnoDB, running on modern hardware. See for example this recent comparative Benchmark from Mark Callaghan, a well known member of the MySQL community: https://smalldatum.blogspot.com/2021/01/sysbench-postgres-vs... I'm not claiming that this benchmark justifies the claim that Postgres broadly performs better than MySQL/InnoDB the…
Comment linking /2021/01/sysbench-postgres-vs-mysql-and-impact.html
on “An early look at Postgres 14: Performance and monitoring Improvements”Submitted Sysbench for MySQL 5.0, 5.1, 5.5, 5.6, 5.7 and 8 as a story · 66 points
HN discussionCheck this "web scale" out: http://smalldatum.blogspot.com (via http://dom.as/2014/03/31/mongo-io/ )
Comment linking /
on “ Subtly Bad Things Linux May Be Doing To PostgreSQL ”Submitted Magma, a new storage engine for Couchbase as a story · 51 points
HN discussionTbf, either can be made to be fast, or slow. MySQL used to have a huge advantage for range queries due to its clustering index (assuming you have designed a schema to exploit that capability), but as time has gone on that gap has narrowed [0] (despite the title, it's not just about inserts). My own benchmarks for strictly read-only queries have also borne that out. The biggest difference, IMO, is if you _aren't_ awa…
Comment linking /2024/09/mysql-and-postgres-vs-insert-benchmark.html
on “Upgrading Uber's MySQL Fleet”Submitted Durability vs. Availability as a story · 51 points
HN discussionI am a big fan of their focus on manageability for sharded databases. I am less of a fan of their db internals that might require you to use many more shards than a more performant engine. More details at http://smalldatum.blogspot.com
Comment linking /
on “MongoDB 2.6 Released”Submitted On Storage Engines as a story · 32 points
HN discussionjemalloc and tcmalloc have been much better than glibc for me, especially when it comes to avoiding fragmentation with some server workloads http://smalldatum.blogspot.com/2017/11/concurrent-large-allo... http://smalldatum.blogspot.com/2018/04/myrocks-malloc-and-fr... http://smalldatum.blogspot.com/2015/10/myrocks-versus-alloca...
Comment linking /2015/10/myrocks-versus-allocators-glibc.html
on “Testing Memory Allocators: ptmalloc2 vs. tcmalloc vs. hoard vs. jemalloc”Submitted Battle of the Mallocators as a story · 27 points
HN discussionThere are many options but most don't have to be set. We need to improve the tuning experience. See http://smalldatum.blogspot.com/2018/09/5-things-to-set-when-...
Comment linking /2018/09/5-things-to-set-when-configuring.html
on “MariaDB acquires Clustrix”Submitted Blind-writes and an LSM as a story · 20 points
HN discussionMyRocks isn't 5.6 only. It is in Percona 5.7 and MariaDB 10.3 I agree that tuning is too complex and we should do much better there. This explains where to ask for advice - http://smalldatum.blogspot.com/2018/05/where-to-ask-question...
Comment linking /2018/05/where-to-ask-questions-about-myrocks.html
on “MariaDB acquires Clustrix”Submitted Too many performance regressions for InnoDB in MySQL 8.0.29 and 8.0.30 as a story · 4 points
HN discussionyou might want to check out the tests conducted by Mark in his blog - https://smalldatum.blogspot.com/2017/12/io-bound-linkbench-a... . There's a lot more there.
Comment linking /2017/12/io-bound-linkbench-and-fast-server.html
on “MyRocks – A RocksDB storage engine with MySQL”Submitted Postgres 17rc1 looks great with sysbench on a small and large server as a story · 4 points
HN discussionI think the author is specifically evaluating low-concurrency in-memory workloads here. The previous post describes why regressions for those workloads might be "not a surprise": https://smalldatum.blogspot.com/2017/05/the-history-of-low-c...
Comment linking /2017/05/the-history-of-low-concurrency.html
on “Sysbench for MySQL 5.0, 5.1, 5.5, 5.6, 5.7 and 8”Submitted Vector indexes, large server: MariaDB, Qdrant and pgvector as a story · 3 points
HN discussionThere’s a good reference in a comment to the original post about read, write, and space amplification by choosing the wrong index structure for the data set: http://smalldatum.blogspot.com/2019/05/crum-conjecture-read-...
Comment linking /2019/05/crum-conjecture-read-write-space-and.html
on “Frugal Computing”Submitted Trying out a dedicated server from Hetzner as a story · 3 points
HN discussionRight, PG calls the REDO log the WAL (for most purposes they are the same thing). I did not know that 9.4 can do partial page writes to the WAL now. Guess I will have more reading to do, thanks for pointing it out! A nice blog post by a colleague recently showing how large writes to redo logs matter is (not about PG, but why it is significant in the context of size of entries): http://smalldatum.blogspot.com/2014/03…
Comment linking /2014/03/redo-logs-in-mongodb-and-innodb.html
on “Google and Facebook Team Up to Modernize Old-School Databases”Submitted RocksDB Internals: LRU as a story · 3 points
HN discussionFirst, this article is mostly (AI?) regurgitation. This is much better: https://smalldatum.blogspot.com/2026/01/common-prefix-skippi... . Second, I have independently invented this (quicksort on string prefixes) at my time at CWI, although I didn't end up publishing it, because... Third, this was already published in the original 1961 Quicksort paper by Hoare: https://www.cs.ox.ac.uk/files/6226/H2006%20-%20Historic%…
Comment linking /2026/01/common-prefix-skipping-adaptive-sort.html
on “Orasort: 5x faster column-sorting with an expired patent from Oracle”Submitted Compatible with MySQL or Postgres? as a story · 3 points
HN discussionthat article sucks and doesnt describes real algorithm I think this is inventors blog https://smalldatum.blogspot.com/2026/01/common-prefix-skippi...
Comment linking /2026/01/common-prefix-skipping-adaptive-sort.html
on “Orasort: 5x faster column-sorting with an expired patent from Oracle”Submitted Postgres, Vacuum and the Insert Benchmark as a story · 3 points
HN discussionThis is from 2022. Seems the RocksDB issue linked in the article has been fixed[1] and an updated blog post was made[2] showing decent results, though buffered IO still wins in some cases from what I can tell. [1]: https://github.com/facebook/rocksdb/issues/9931 [2]: http://smalldatum.blogspot.com/2022/06/fixing-mmap-performan...
Comment linking /2022/06/fixing-mmap-performance-for-rocksdb.html
on “Using MMAP with RocksDB”Submitted Review: The Design of the Postgres Storage System as a story · 3 points
HN discussion
