RAL in HC test overnight:
- Stage out failures (svc02) and Rack power off triggered HC test failures. One of the HC tests stopped running, so RAL not put back online.
- Have forced site online, and following up; experts now have reinjected tests.
BNL -> RAL (and CNAF) transfers over the OPN have been very slow for ~ 1 week. Problem appears to be on the BNL side however.
Accounting differences observered between the VO monitoring and WLCG accounting figures, starting ~ September. See attached plot.
DNS issues reappeared on Sunday morning. Due (?) to TTL changes to webdav alias, observed fewer transfer failures during this period.