dc4ee9a8db
Two prod-readiness hardening changes: DB tuning scales with the container budget. Replace the fixed 8 GB 20-tuning.sql with 20-tuning.sh, which derives shared_buffers (25%), effective_cache_size (75%), work_mem, maintenance_work_mem and duckdb.max_memory (50%) from the DB_MEMORY the compose db service now passes in. The ratios reproduce the historical 8 GB tuning exactly and scale linearly, so the 48 GB prod box (db_memory 16g) gets shared_buffers 4 GB / duckdb 8 GB with no separate edit. Beta/local (8g default) are unchanged. Docs that told operators to raise the tuning by hand are updated. Boot ordering for the self-hosted archive. On an openmeteo host, install a docker.service drop-in (Wants/After rclone-om.service) so Docker starts after the object-storage mount is ready on every boot — the restart-policy containers never bind an empty mount point. rclone-om is Type=notify, so After waits for the mount to actually be ready. Cleaned up when openmeteo is toggled off.
64 lines
3.1 KiB
Bash
Executable file
64 lines
3.1 KiB
Bash
Executable file
#!/bin/bash
|
|
# Postgres memory / performance tuning, scaled to the container's DB_MEMORY budget so
|
|
# the same init serves every host (beta 8g; prod 16g on the 48 GB box) with no
|
|
# hardcoding. Runs once on a fresh data volume from /docker-entrypoint-initdb.d, after
|
|
# 10-parquet.sql enables pg_duckdb. Settings are written via ALTER SYSTEM (persisted to
|
|
# postgresql.auto.conf); the container's post-init restart brings restart-only settings
|
|
# (shared_buffers, …) into effect. Init scripts do NOT re-run on an existing volume — to
|
|
# re-tune later, set DB_MEMORY and run this by hand, then restart:
|
|
# docker compose exec -e DB_MEMORY=16g db bash /docker-entrypoint-initdb.d/20-tuning.sh
|
|
# docker compose restart db
|
|
set -euo pipefail
|
|
|
|
# Parse DB_MEMORY ("16g" / "8192m" / plain MB) into whole MB; default + floor at 8 GB.
|
|
budget="${DB_MEMORY:-8g}"
|
|
num="${budget//[!0-9]/}"
|
|
num="${num:-8}"
|
|
unit="$(printf '%s' "$budget" | tr -dc '[:alpha:]' | tr '[:upper:]' '[:lower:]')"
|
|
case "$unit" in
|
|
g | gb) mb=$((num * 1024)) ;;
|
|
m | mb | "") mb="$num" ;;
|
|
*) mb=8192 ;;
|
|
esac
|
|
if [ "$mb" -lt 1024 ]; then mb=8192; fi
|
|
|
|
# Derive settings from the budget. The ratios reproduce the historical 8 GB tuning
|
|
# (shared_buffers 2 GB, effective_cache_size 6 GB, duckdb 4 GB, work_mem 64 MB,
|
|
# maintenance_work_mem 512 MB) and scale linearly on a bigger box.
|
|
shared_buffers=$((mb / 4)) # 25% — the shared page cache
|
|
effective_cache=$((mb * 3 / 4)) # 75% — planner's view of total cache (PG + OS)
|
|
duckdb_mem=$((mb / 2)) # 50% — pg_duckdb ceiling for parquet processing
|
|
work_mem=$((mb / 128)) # ~64 MB at 8 GB (per-operation; kept modest)
|
|
if [ "$work_mem" -lt 16 ]; then work_mem=16; fi
|
|
maint_mem=$((mb / 16)) # 512 MB at 8 GB — index builds / VACUUM
|
|
|
|
echo "[tuning] DB_MEMORY=${budget} -> ${mb}MB: shared_buffers=${shared_buffers}MB" \
|
|
"effective_cache_size=${effective_cache}MB work_mem=${work_mem}MB" \
|
|
"maintenance_work_mem=${maint_mem}MB duckdb.max_memory=${duckdb_mem}MB"
|
|
|
|
psql -v ON_ERROR_STOP=1 --username "$POSTGRES_USER" --dbname "$POSTGRES_DB" <<SQL
|
|
-- Caching: the shared page cache, and the planner's view of total cache (PG + OS).
|
|
ALTER SYSTEM SET shared_buffers = '${shared_buffers}MB';
|
|
ALTER SYSTEM SET effective_cache_size = '${effective_cache}MB';
|
|
|
|
-- Processing: per-operation sort/hash memory, and maintenance (index builds, VACUUM).
|
|
ALTER SYSTEM SET work_mem = '${work_mem}MB';
|
|
ALTER SYSTEM SET maintenance_work_mem = '${maint_mem}MB';
|
|
|
|
-- Write throughput: fewer, larger checkpoints.
|
|
ALTER SYSTEM SET wal_buffers = '16MB';
|
|
ALTER SYSTEM SET min_wal_size = '1GB';
|
|
ALTER SYSTEM SET max_wal_size = '4GB';
|
|
ALTER SYSTEM SET checkpoint_completion_target = 0.9;
|
|
|
|
-- SSD-friendly planner + IO concurrency.
|
|
ALTER SYSTEM SET random_page_cost = 1.1;
|
|
ALTER SYSTEM SET effective_io_concurrency = 200;
|
|
|
|
-- Room for parallel scans/aggregates on the bigger analytic queries.
|
|
ALTER SYSTEM SET max_parallel_workers_per_gather = 2;
|
|
|
|
-- DuckDB (pg_duckdb) memory ceiling for parquet processing. pg_duckdb is preloaded
|
|
-- (shared_preload_libraries), so this GUC exists at ALTER SYSTEM time.
|
|
ALTER SYSTEM SET duckdb.max_memory = '${duckdb_mem}MB';
|
|
SQL
|