diff options
author | Bryan Newbold <bnewbold@archive.org> | 2020-10-17 17:10:51 -0700 |
---|---|---|
committer | Bryan Newbold <bnewbold@archive.org> | 2020-10-17 17:10:51 -0700 |
commit | e1698ffa62f0292ad9f8d0e53207dfa3aa23818d (patch) | |
tree | 5e9aab198a5a4b1f91865f72a8a03b2955c7ad83 /sql | |
parent | 4f5c66fd33263a146609efbfcbfde4a344f0ac2d (diff) | |
download | sandcrawler-e1698ffa62f0292ad9f8d0e53207dfa3aa23818d.tar.gz sandcrawler-e1698ffa62f0292ad9f8d0e53207dfa3aa23818d.zip |
update SQL ingest monitoring commands to be past-month by default
Diffstat (limited to 'sql')
-rw-r--r-- | sql/monitoring_queries.md | 10 |
1 files changed, 5 insertions, 5 deletions
diff --git a/sql/monitoring_queries.md b/sql/monitoring_queries.md index fd0ce51..1738731 100644 --- a/sql/monitoring_queries.md +++ b/sql/monitoring_queries.md @@ -1,21 +1,21 @@ ## fatcat-changelog pipeline -Overall ingest status, past 3 days: +Overall ingest status, past 30 days: SELECT ingest_file_result.ingest_type, ingest_file_result.status, COUNT(*) FROM ingest_file_result LEFT JOIN ingest_request ON ingest_file_result.ingest_type = ingest_request.ingest_type AND ingest_file_result.base_url = ingest_request.base_url - WHERE ingest_request.created >= NOW() - '3 day'::INTERVAL + WHERE ingest_request.created >= NOW() - '30 day'::INTERVAL AND ingest_request.ingest_type = 'pdf' AND ingest_request.ingest_request_source = 'fatcat-changelog' GROUP BY ingest_file_result.ingest_type, ingest_file_result.status ORDER BY COUNT DESC LIMIT 20; -Broken domains, past 3 days: +Broken domains, past 30 days: SELECT domain, status, COUNT((domain, status)) FROM ( @@ -29,7 +29,7 @@ Broken domains, past 3 days: AND ingest_file_result.base_url = ingest_request.base_url WHERE -- ingest_request.created >= NOW() - '3 day'::INTERVAL - ingest_file_result.updated >= NOW() - '3 day'::INTERVAL + ingest_file_result.updated >= NOW() - '30 day'::INTERVAL AND ingest_request.ingest_type = 'pdf' AND ingest_request.ingest_request_source = 'fatcat-changelog' ) t1 @@ -39,7 +39,7 @@ Broken domains, past 3 days: ORDER BY COUNT DESC LIMIT 25; -Throughput per day, and success, for past month: +Throughput per day, and success, for past 30 days: SELECT ingest_request.ingest_type, date(ingest_request.created), |