From c7e7472c5754f06defe63634e604476660327798 Mon Sep 17 00:00:00 2001
From: Graham McIntire <graham@mcintire.me>
Date: Tue, 21 Apr 2026 13:20:22 -0500
Subject: [PATCH] perf(db): add (valid_time, lat, lon) composite index on
 hrrr[_native]_profiles
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Weather.find_nearest_hrrr/3 and Weather.find_nearest_native_profile/3
run a three-range scan gated first by a ±1h valid_time window, then
by a ±0.07° lat/lon box. The existing unique `(lat, lon, valid_time)`
index is only usable on its `lat` prefix for these queries, forcing
Postgres to scan wide lat slices before applying the valid_time
filter — expensive on the Turing Pi 2 node.

Add a `(valid_time, lat, lon)` composite so valid_time leads,
collapsing the search to a narrow btree slice inside a single
partition before the lat/lon box filter kicks in.

`hrrr_profiles` is RANGE-partitioned by valid_time, so
CREATE INDEX CONCURRENTLY is applied per partition and the resulting
indexes are attached to a parent index created ON ONLY the partitioned
table. `hrrr_native_profiles` is a regular table, so the concurrent
build runs directly on it.
---
 ..._hrrr_profiles_valid_time_latlon_index.exs | 78 +++++++++++++++++++
 1 file changed, 78 insertions(+)
 create mode 100644 priv/repo/migrations/20260421181818_add_hrrr_profiles_valid_time_latlon_index.exs

diff --git a/priv/repo/migrations/20260421181818_add_hrrr_profiles_valid_time_latlon_index.exs b/priv/repo/migrations/20260421181818_add_hrrr_profiles_valid_time_latlon_index.exs
new file mode 100644
index 00000000..86ad570d
--- /dev/null
+++ b/priv/repo/migrations/20260421181818_add_hrrr_profiles_valid_time_latlon_index.exs
@@ -0,0 +1,78 @@
+defmodule Microwaveprop.Repo.Migrations.AddHrrrProfilesValidTimeLatlonIndex do
+  use Ecto.Migration
+
+  # Matches the hot range-scan access pattern in
+  # `Weather.find_nearest_hrrr/3` and `Weather.find_nearest_native_profile/3`:
+  #   WHERE valid_time BETWEEN ? AND ?
+  #     AND lat BETWEEN ? AND ?
+  #     AND lon BETWEEN ? AND ?
+  # `valid_time` leads because the ±1h window collapses the search to a
+  # single partition and a narrow btree slice; lat/lon then filter the
+  # ~9×9 tile grid within that bucket. The existing unique index
+  # `(lat, lon, valid_time)` services upsert dedup but its first column
+  # is lat — it can't serve a three-range scan that is selective only
+  # on valid_time.
+  #
+  # `hrrr_profiles` is partitioned by `valid_time`, so CREATE INDEX
+  # CONCURRENTLY cannot run directly on the partitioned parent. We use
+  # the PG 11+ pattern: create an invalid index on ONLY the parent,
+  # concurrently build a matching index on each partition, then ATTACH
+  # each partition index to the parent — Postgres validates the parent
+  # once every child is attached.
+  #
+  # `hrrr_native_profiles` is a regular table, so the standard
+  # `create index(..., concurrently: true)` form applies.
+
+  @disable_ddl_transaction true
+  @disable_migration_lock true
+
+  def up do
+    # Parent index (invalid until partitions attach).
+    execute """
+    CREATE INDEX IF NOT EXISTS hrrr_profiles_valid_time_lat_lon_index
+      ON ONLY hrrr_profiles (valid_time, lat, lon)
+    """
+
+    for partition <- hrrr_profile_partitions() do
+      child_idx = "#{partition}_valid_time_lat_lon_index"
+
+      execute """
+      CREATE INDEX CONCURRENTLY IF NOT EXISTS #{child_idx}
+        ON #{partition} (valid_time, lat, lon)
+      """
+
+      execute """
+      ALTER INDEX hrrr_profiles_valid_time_lat_lon_index
+        ATTACH PARTITION #{child_idx}
+      """
+    end
+
+    # Native profiles: not partitioned, so concurrently works directly.
+    execute """
+    CREATE INDEX CONCURRENTLY IF NOT EXISTS hrrr_native_profiles_valid_time_lat_lon_index
+      ON hrrr_native_profiles (valid_time, lat, lon)
+    """
+  end
+
+  def down do
+    execute "DROP INDEX IF EXISTS hrrr_native_profiles_valid_time_lat_lon_index"
+    execute "DROP INDEX IF EXISTS hrrr_profiles_valid_time_lat_lon_index"
+  end
+
+  defp hrrr_profile_partitions do
+    {:ok, %{rows: rows}} =
+      repo().query(
+        """
+        SELECT child.relname
+        FROM pg_inherits
+        JOIN pg_class parent ON pg_inherits.inhparent = parent.oid
+        JOIN pg_class child  ON pg_inherits.inhrelid  = child.oid
+        WHERE parent.relname = 'hrrr_profiles'
+        ORDER BY child.relname
+        """,
+        []
+      )
+
+    Enum.map(rows, fn [name] -> name end)
+  end
+end