Mark Callaghan
This has results for MariaDB versions 10.2 through 13.0 vs the Insert Benchmark on a 32-core server. The goal is to see how performance changes over time to find regressions or highlight improvements. My previous post has results from a 24-core server. Differences between these servers...
Mark Callaghan
This has results for sysbench vs MariaDB on a small server. I repeated tests using the same charset (latin1) for all versions as explained here. In previous results I used a multi-byte charset for modern MariaDB (probably 11.4+) by mistake and that adds a 5% CPU overhead for many...
Mark Callaghan
This post has results for CPU-bound sysbench vs Postgres, MySQL and MariaDB on a large server using older and newer releases. The goal is to measure:how performance changes over time from old versions to new versionsperformance between modern MySQL, MariaDB and PostgresThe context here is a...
Mark Callaghan
This has results for sysbench on a small server and compares performanc for Postgres, MySQL and MariaDB compiled using clang vs using gcc.tl;drThroughput with clang and gcc is similarBuilds, configuration and hardwareI compiled Postgres 18.3, MySQL 8.4.8 and MariaDB 11.8.6 from source. The server...
Mark Callaghan
MySQL and MariaDB have many character-set related options, perhaps too many:character_set_clientcharacter_set_connectioncharacter_set_databasecharacter_set_filesystemcharacter_set_resultscharacter_set_servercharacter_set_systemThis is a topic that I don't know much about and I am still far from an...
Mark Callaghan
MariaDB 12.3 has a new feature enabled by the option binlog_storage_engine. When enabled it uses InnoDB instead of raw files to store the binlog. A big benefit from this is reducing the number of fsync calls per commit from 2 to 1 because it reduces the number of resource managers from 2 (binlog,...
Mark Callaghan
MariaDB 12.3 has a new feature enabled by the option binlog_storage_engine. When enabled it uses InnoDB instead of raw files to store the binlog. A big benefit from this is reducing the number of fsync calls per commit from 2 to 1 because it reduces the number of resource managers from 2 (binlog,...
Mark Callaghan
I started to use TPROC-C from HammerDB to test MariaDB, MySQL and Postgres and published results for MySQL and Postgres on small and large servers. This post provides more detail on CPU overheads for MariaDB, MySQL and Postgres on a small server.tl;drPostgres get the most throughput and the...
Mark Callaghan
Last year I shared many posts documenting MariaDB performance for vector search using ann-benchmarks. Performance was great in MariaDB 11 and this blog post explains that it is even better in MariaDB 12. This work was done by Small Datum LLC and sponsored by the MariaDB Foundation. My previous...
Mark Callaghan
MariaDB 12.3 has a new feature enabled by the option binlog_storage_engine. When enabled it uses InnoDB instead of raw files to store the binlog. A big benefit from this is reducing the number of fsync calls per commit from 2 to 1 because it reduces the number of resource managers from 2 (binlog,...
Mark Callaghan
MariaDB 12.3 has a new feature enabled by the option binlog_storage_engine. When enabled it uses InnoDB instead of raw files to store the binlog. A big benefit from this is reducing the number of fsync calls per commit from 2 to 1 because it reduces the number of resource managers from 2 (binlog,...
Ivan
Undo log Undo log in MariaDB/InnoDB is divided into a set of rollback segments (128) which reside in dedicated tablespaces (data files) (undo0XXX) including historically the one number Zero (0) that resides in the system tablespace starting at page 6 (FSP_FIRST_RSEG_PAGE_NO / fsp0types.h) (at...
Ivan
Redo log structure The database log (aka redo log) is used to ensure data integrity in the case of a crash or unexpected shutdown. It records changes made to the database before they are actually written (?) so that they can be replayed during recovery. Redo log is stored in ib_logfileX files....