30 likes | 141 Views
This report covers various issues and updates related to Tier0/Central services, such as problems at Tier1 sites, EOS migration progress, and GGUS ticket management. Stay informed about system upgrades, bug fixes, and operational challenges faced by different data centers.
E N D
AMOD Report5 – 11 Sept AMOD Report5 – 11 Sept Guido Negri
Tier0/Central Services • Castor@CERN • garbage collector acting on stale information and removing very young files (not yet processed); SFO-Tier0 handshake mechanism prevented loss of sensible data; problem could happen again (developers are not sure about the cause) • EOS@CERN • migration proceeding smoothly, a few minor bugs detected and promptly fixed, hardware upgraded transparently, EOS alarm tickets in GGUS tested to be correctly tracked
Tier1s/Tier2s • a few problems with some Tier1 • CNAF LFC: file allocation limit reached, limit raised • CNAF SRM: storm daemon stuck, relaunched • SARA-MATRIX SRM: problems with 8 pool nodes that crashed, all with the same hardware, but not yet understood why; workaround should be in place • TAIWAN-LCG2 SRM: CRL expired, cron job for upfdating was stopped; relaunched • Several T1s MCTAPE: high load was responsible for some error beginning of last week • RAL: network problems on monday early morning, fixed by late morning on the same day • minor problems with a few Tier2s • GGUS tickets promtly submitted by ADCoS shifters and always managed by the sites in a timely way