thermograph/infra/deploy/db/init/20-tuning.sh

#!/bin/bash
# Postgres memory / performance tuning, scaled to the container's DB_MEMORY budget so
# the same init works for any host with no hardcoding. There is ONE shared TimescaleDB
# instance now (prod and beta are separate databases/roles on it, not separate
# containers), sized from prod's vault values (16g on the 48 GB box) -- beta no longer
# gets a second database or a second tuning pass. Dev keeps its own, separate container
# (8g). Runs once on a fresh data volume from /docker-entrypoint-initdb.d, after
# 10-timescaledb.sql enables timescaledb. Settings are written via ALTER SYSTEM
# (persisted to postgresql.auto.conf, which the timescaledb image's own
# timescaledb-tune postgresql.conf defers to); the container's post-init restart brings
# restart-only settings (shared_buffers, …) into effect. NB: never ALTER SYSTEM SET
# shared_preload_libraries here — that would land in auto.conf and override the image's
# `timescaledb` preload. 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, 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)
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"

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;
SQL