 |
 |
Thanks Chuck, we will sort this our later. Wain012-16 are up running xrootd. We are not using wain011 yet. So I think I can bring back the cluster. Regards, -- Wei Yang | [log in to unmask] | 650-926-3338(O) > -----Original Message----- > From: Boeheim, Charles T. > Sent: Sunday, July 13, 2008 11:38 AM > To: Yang, Wei > Cc: core-unix; core-hpsc; atlas-sccs-planning-l > Subject: Re: power outage for ATLAS xrootd servers > > Things seem in bit disarray. The power lights are blinking > on wain010, wain012, and steady on the others. > > console to wain012 gets you the login prompt for wain011. > > console to wain011 gets an unconfigured system. I tried > booting it and it goes into the system configuration menu. > At this point I don't know what state things were left in. > > On Jul 12, 2008, at 10:32 PM, Wei Yang wrote: > > > I am bring most them up except wain012. The SP on wai012 isn't > > pingable. .. It is part of the ATLAS xrootd cluster. > > > > Wei Yang | [log in to unmask] | 650-926-3338(O) > > > > > > Chuck Boeheim wrote: > >> That sounds like the time at which glastlnx12 lost power also. I > >> brought that up using the SP, so it wasn't a breaker trip. > Try the > >> same on the wains. > >> On Jul 12, 2008, at 10:13 PM, Wei Yang wrote: > >>> I just found wain011-16 were power off. The SPs on all > but wain012 > >>> are pingable. So I guess there is a power outage rather than a > >>> scheduled power down. Gangla monitoring lost heartbeat of > them from > >>> ~ 4:10pm. > >>> > >>> Wain011-16 are ATLAS xrootd servers (so do wain003-5, > which are OK). > >>> Other wains are OK. Do we know what happened ? > >>> > >>> -- > >>> Wei Yang | [log in to unmask] | 650-926-3338(O) > >