checkpoint: pipeline + 27k/h baseline before sitemap discovery

This commit is contained in:
qananasikq
2026-04-18 16:34:09 +03:00
parent a8c5f8aa41
commit 5999c2e42d
30 changed files with 4993 additions and 61 deletions

26
_dispatch_check.sh Normal file
View File

@@ -0,0 +1,26 @@
#!/usr/bin/env bash
set -euo pipefail
cd /root/iaai_scraper_project
echo "== dispatch =="
TID=$(docker compose exec -T worker python -c "from iaai_scraper.worker.tasks import sync_listing_task; print(sync_listing_task.delay().id)")
echo "dispatched: $TID"
echo "== wait 120s =="
sleep 120
echo
echo "== DB =="
docker compose exec -T postgres psql -U iaai -d iaai_scraper -c "SELECT count(*) AS total, count(*) FILTER (WHERE last_seen_at > now() - interval '5 minutes') AS last_5min, max(last_seen_at) AS max FROM cars;"
echo
echo "== upsert / batch / segment-done events (last 40) =="
docker compose logs --tail=800 worker 2>&1 | grep -E 'HTTP-mode batch|upserted=|HTTP-mode listing done|Segment .* done|HTTP fast-path using proxy|Sync run .* finished' | tail -n 40
echo
echo "== page-progress tail =="
docker compose logs --tail=400 worker 2>&1 | grep -E 'HTTP-mode page' | tail -n 15
echo
echo "== errors if any =="
docker compose logs --tail=400 worker 2>&1 | grep -Ei 'error|exception|403|500|incapsula|pardon' | tail -n 15 || true