feat(server): retention GenServer prunes samples older than 48h hourly

server/lib/server/application.ex

@@ -15,6 +15,7 @@ defmodule Server.Application do
         skip: skip_migrations?()},
       {DNSCluster, query: Application.get_env(:server, :dns_cluster_query) || :ignore},
       {Phoenix.PubSub, name: Server.PubSub},
+      Server.Retention,
       # Start a worker by calling: Server.Worker.start_link(arg)
       # {Server.Worker, arg},
       # Start to serve requests, typically the last entry

server/lib/server/retention.ex

@@ -0,0 +1,36 @@
+defmodule Server.Retention do
+  @moduledoc "Deletes metric samples older than the retention window. Runs hourly."
+
+  use GenServer
+  require Logger
+
+  @default_retention_seconds 48 * 60 * 60
+  @default_interval_ms 60 * 60 * 1_000
+
+  def start_link(opts) do
+    GenServer.start_link(__MODULE__, opts, name: __MODULE__)
+  end
+
+  @doc "Synchronous prune used by tests and manual ops."
+  def prune_now(retention_seconds \\ @default_retention_seconds) do
+    cutoff = DateTime.add(DateTime.utc_now(), -retention_seconds, :second)
+    Server.Metrics.delete_older_than(cutoff)
+  end
+
+  @impl true
+  def init(opts) do
+    retention_seconds = Keyword.get(opts, :retention_seconds, @default_retention_seconds)
+    interval_ms = Keyword.get(opts, :interval_ms, @default_interval_ms)
+    state = %{retention_seconds: retention_seconds, interval_ms: interval_ms}
+    Process.send_after(self(), :prune, interval_ms)
+    {:ok, state}
+  end
+
+  @impl true
+  def handle_info(:prune, state) do
+    {count, _} = prune_now(state.retention_seconds)
+    if count > 0, do: Logger.info("retention: pruned #{count} stale samples")
+    Process.send_after(self(), :prune, state.interval_ms)
+    {:noreply, state}
+  end
+end

server/test/server/retention_test.exs

@@ -0,0 +1,21 @@
+defmodule Server.RetentionTest do
+  use Server.DataCase, async: false
+
+  alias Server.{Hosts, Metrics, Retention}
+
+  test "prune_now/1 deletes samples older than the retention window" do
+    {:ok, {host, _}} = Hosts.create_host("pve-01")
+    stale_at = DateTime.add(DateTime.utc_now(), -49 * 3600, :second)
+    fresh_at = DateTime.add(DateTime.utc_now(), -60, :second)
+
+    {:ok, _} = Metrics.record_sample(host.id, "fast", stale_at, %{"x" => 1})
+    {:ok, fresh} = Metrics.record_sample(host.id, "fast", fresh_at, %{"x" => 2})
+
+    {deleted, _} = Retention.prune_now(48 * 3600)
+
+    assert deleted == 1
+    remaining = Server.Repo.all(Server.Schema.Metric)
+    assert length(remaining) == 1
+    assert hd(remaining).id == fresh.id
+  end
+end