14:43:40 *swh-scheduler@db1:5432=> with maven_lister_ids as (
swh-scheduler(>     select id from listers where name='maven'
swh-scheduler(> ) delete from
swh-scheduler->     listed_origins lo1
swh-scheduler->   where
swh-scheduler->     lister_id in (select id from maven_lister_ids)
swh-scheduler->     and visit_type = 'git'
swh-scheduler->     and url like '%github.com%'
swh-scheduler->     and not exists (
swh-scheduler(>       select 1 from listed_origins lo2
swh-scheduler(>       where
swh-scheduler(>         lo1.visit_type = lo2.visit_type
swh-scheduler(>         and lo1.url = lo2.url
swh-scheduler(>         and lo2.lister_id not in (select id from maven_lister_ids)
swh-scheduler(>     );

DELETE 28067
Time: 61233.213 ms (01:01.233)
14:44:42 *swh-scheduler@db1:5432=>
14:44:42 *swh-scheduler@db1:5432=> commit;
COMMIT
Time: 258.813 ms

15:04:45 swh-scheduler@db1:5432=>  update task set status='next_run_not_scheduled', next_run=now() where id=31171944;
UPDATE 1
Time: 215.620 ms
15:05:01 swh-scheduler@db1:5432=> select * from task where id=31171944;
+-[ RECORD 1 ]-----+-----------------------------------------------------------------------------------------------------------------------------------------------------------------+
| id               | 31171944                                                                                                                                                        |
| type             | list-maven-full                                                                                                                                                 |
| arguments        | {"args": [], "kwargs": {"url": "https://repo1.maven.org/maven2/", "index_url": "https://maven-exporter.internal.staging.swh.network/export-maven-central.fld"}} |
| next_run         | 2022-06-01 13:05:01.466561+00                                                                                                                                   |
| current_interval | 90 days                                                                                                                                                         |
| status           | next_run_scheduled                                                                                                                                              |
| policy           | recurring                                                                                                                                                       |
| retries_left     | 0                                                                                                                                                               |
| priority         | (null)                                                                                                                                                          |
+------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------+

Time: 5.767 ms

root@pergamon:~# clush -b -w @staging-workers 'systemctl status swh-worker@lister' | grep maven | grep succeeded
Jun 03 09:08:00 worker0 python3[4170026]: [2022-06-03 09:08:00,712: INFO/ForkPoolWorker-4] Task swh.lister.maven.tasks.FullMavenLister[8d1d52b4-f0d0-4f3d-817b-3d02ad48eb0a] succeeded in 1171.5895328279585s: {'pages': 9941, 'origins': 9935}
Jun 03 08:08:43 worker3 python3[3724078]: [2022-06-03 08:08:43,751: INFO/ForkPoolWorker-4] Task swh.lister.maven.tasks.FullMavenLister[c9a18b0b-fcdd-492b-ab5a-5eca07896b2f] succeeded in 2246.291659256909s: {'pages': 30853, 'origins': 30840}

13:52:37 swh-scheduler@db1:5432=> with maven_lister_ids as (
    select id from listers where name='maven'
) select now(), visit_type, url
  from
    listed_origins lo1
  where
    lister_id in (select id from maven_lister_ids)
    and visit_type = 'git'
    and url like '%github.com%'
    and not exists (
      select 1 from listed_origins lo2
      where
        lo1.visit_type = lo2.visit_type
        and lo1.url = lo2.url
        and lo2.lister_id not in (select id from maven_lister_ids)
    )
;
+-----+------------+-----+
| now | visit_type | url |
+-----+------------+-----+
+-----+------------+-----+
(0 rows)

Time: 16936.595 ms (00:16.937)

16:43:29 swh-scheduler@db1:5432=> select now(), count(*) from listed_origins where visit_type='git' and url like '%github.com%';
+-------------------------------+---------+
|              now              |  count  |
+-------------------------------+---------+
| 2022-06-03 14:43:31.116227+00 | 2213849 |
+-------------------------------+---------+
(1 row)

Time: 4361.559 ms (00:04.362)

16:02:46 swh-scheduler@db1:5432=> with maven_lister_ids as (
    select id from listers where name='maven'
) select now(), visit_type, count(*)
  from
    listed_origins lo1
  where
    lister_id in (select id from maven_lister_ids)
    and visit_type != 'maven'
    and not exists (
      select 1 from listed_origins lo2
      where
        lo1.visit_type = lo2.visit_type
        and lo1.url = lo2.url
        and lo2.lister_id not in (select id from maven_lister_ids)
    )
  group by visit_type;
+-------------------------------+------------+-------+
|              now              | visit_type | count |
+-------------------------------+------------+-------+
| 2022-06-03 14:02:57.631052+00 | svn        | 14015 |
| 2022-06-03 14:02:57.631052+00 | hg         |   255 |
| 2022-06-03 14:02:57.631052+00 | cvs        |    64 |
| 2022-06-03 14:02:57.631052+00 | git        |  1887 |
+-------------------------------+------------+-------+
(4 rows)

Time: 59889.690 ms (00:59.890)