mirror of
https://git.postgresql.org/git/postgresql.git
synced 2026-03-02 02:06:59 +08:00
28e626bde0
This commit adds the infrastructure for more detailed IO statistics. The calls to actually count IOs, a system view to access the new statistics, documentation and tests will be added in subsequent commits, to make review easier. While we already had some IO statistics, e.g. in pg_stat_bgwriter and pg_stat_database, they did not provide sufficient detail to understand what the main sources of IO are, or whether configuration changes could avoid IO. E.g., pg_stat_bgwriter.buffers_backend does contain the number of buffers written out by a backend, but as that includes extending relations (always done by backends) and writes triggered by the use of buffer access strategies, it cannot easily be used to tune background writer or checkpointer. Similarly, pg_stat_database.blks_read cannot easily be used to tune shared_buffers / compute a cache hit ratio, as the use of buffer access strategies will often prevent a large fraction of the read blocks to end up in shared_buffers. The new IO statistics count IO operations (evict, extend, fsync, read, reuse, and write), and are aggregated for each combination of backend type (backend, autovacuum worker, bgwriter, etc), target object of the IO (relations, temp relations) and context of the IO (normal, vacuum, bulkread, bulkwrite). What is tracked in this series of patches, is sufficient to perform the aforementioned analyses. Further details, e.g. tracking the number of buffer hits, would make that even easier, but was left out for now, to keep the scope of the already large patchset manageable. Bumps PGSTAT_FILE_FORMAT_ID. Author: Melanie Plageman <melanieplageman@gmail.com> Reviewed-by: Andres Freund <andres@anarazel.de> Reviewed-by: Justin Pryzby <pryzby@telsasoft.com> Reviewed-by: Kyotaro Horiguchi <horikyota.ntt@gmail.com> Discussion: https://postgr.es/m/20200124195226.lth52iydq2n2uilq@alap3.anarazel.de
# Generating dummy probes If Postgres isn't configured with dtrace enabled, we need to generate dummy probes for the entries in probes.d, that do nothing. This is accomplished in Unix via the sed script `Gen_dummy_probes.sed`. We used to use this in MSVC builds using the perl utility `psed`, which mimicked sed. However, that utility disappeared from Windows perl distributions and so we converted the sed script to a perl script to be used in MSVC builds. We still keep the sed script as the authoritative source for generating these dummy probes because except on Windows perl is not a hard requirement when building from a tarball. So, if you need to change the way dummy probes are generated, first change the sed script, and when it's working generate the perl script. This can be accomplished by using the perl utility s2p. s2p is no longer part of the perl core, so it might not be on your system, but it is available on CPAN and also in many package systems. e.g. on Fedora it can be installed using `cpan App::s2p` or `dnf install perl-App-s2p`. The Makefile contains a recipe for regenerating Gen_dummy_probes.pl, so all you need to do is once you have s2p installed is `make Gen_dummy_probes.pl` Note that in a VPATH build this will generate the file in the vpath tree, not the source tree.