prop/lib/microwaveprop/workers/propagation_prune_worker.ex
Graham McInitre 4ac606e682 fix: ensure all unused historical NFS data gets cleaned up
Close 6 cleanup gaps on the shared /data NFS mount:

- HRDPS .hrdps.prop score files: parse_valid_time regex now matches
  the .hrdps.prop extension, so these files are found and pruned
- HRDPS scalar dirs (weather_scalars/{iso}.hrdps/): strip .hrdps suffix
  before DateTime.from_iso8601 in list_valid_time_dirs
- ScalarFile: prune_older_than was defined but never called from
  Propagation.prune_old_scores - now called alongside Scores/Profiles
- Orphan .tmp.* files: sweep all three base dirs (scores/profiles/scalars)
  for .tmp.* files left by crashed atomic-write processes
- Building cache (/data/buildings/): add MsFootprints.prune_older_than
  with 30-day mtime cutoff
- Canopy cache (/data/canopy/ + staging/): add Canopy.prune_older_than
  with 30-day cutoff, cleanup empty staging dir

All cleanup is cutoff-based (older than X time) so if the prune worker
is missed for any period it catches up fully on the next run.

PropagationPruneWorker updated to call all new cleanup functions.
2026-07-20 09:27:36 -05:00

45 lines
1.5 KiB
Elixir

defmodule Microwaveprop.Workers.PropagationPruneWorker do
@moduledoc """
Standalone worker that prunes stale rows from `propagation_scores`.
Pruning used to be tacked on to the end of `PropagationGridWorker.perform/1`,
which meant it only ran after a successful grid compute. When the compute
worker was being killed mid-run (OOM / SIGTERM), prune never ran and the
table grew unbounded. Running prune on its own cron keeps the table healthy
regardless of the compute worker's state.
"""
use Oban.Pro.Worker,
queue: :propagation,
# Lower priority than PropagationGridWorker so the hourly chain
# never waits behind a pending prune on the shared :propagation
# queue (2 slots).
priority: 5,
max_attempts: 3,
unique: [period: 300, states: :incomplete]
alias Microwaveprop.Buildings.MsFootprints
alias Microwaveprop.Canopy
alias Microwaveprop.Propagation
require Logger
@impl Oban.Pro.Worker
def process(%Oban.Job{}) do
Propagation.prune_old_scores()
cutoff_30d = DateTime.add(DateTime.utc_now(), -30, :day)
buildings_deleted = MsFootprints.prune_older_than(cutoff_30d)
canopy_deleted = Canopy.prune_older_than(cutoff_30d)
if buildings_deleted > 0 do
Logger.info("MsFootprints: pruned #{buildings_deleted} cached tile files older than #{cutoff_30d}")
end
if canopy_deleted > 0 do
Logger.info("Canopy: pruned #{canopy_deleted} cached tile/staging files older than #{cutoff_30d}")
end
:ok
end
end