Page 1 of 1

VSP05 & associated servers DOWN

Posted: Thu Nov 04, 2010 1:11 pm
by bollix47

Code: Select all

171.64.122.72	classic	VSP05	-	accept	DOWN	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	1	171.64.122.76
	-	-	-	-	-	-	-	-	-	-	-	;	-	-	-	-	-	-	-	-	-	VSP05
171.67.108.33	classic	vsp05c	-	full	DOWN	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	1	-	-	-	-	WL; ;	500;	5;	5;	10000;	64;	-	-	;	F;	80;	-	-	-	-	-	-	-	vsp05c
171.67.108.20	GPU	vsp11v	-	full	DOWN	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	1	-	-	-	-	W; W;	1, 1	6.3, 6.119	-	49, 49	64, 64	-	-	; , 2, 3	F, F	8080G, 8080G	-	-	-	-	-	-	-	vsp11v
171.67.108.31	GPU	vsp05a	-	full	DOWN	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	1	-	-	-	-	W;	500	6.3	-	49	64	-	-	; , 2	F	8080G	-	-	-	-	-	-	-	vsp05a
SERVER IP	client	NAME	WHO	STATUS	CONNECT	CPU LOAD	NET LOAD	FIN WAIT	DL	GB TOT	GB AV	DIFF TIME	WU L	WUs AVAIL	WUs to go	WUs WAIT	% Ass	% Ass 80	% Ass G	% Ass PS	WUs RCV	WU E	T	st	S	CS	CSlisted	NMJ	80	OperatingSystem	WEIGHT	min ver	Min_packet	Max_packet	memory	smp cores	min smp	gp type	PROGRAM	AssignedPort	ver	C	T	G	RMEM	WHO	PBL	NAME
171.67.108.32	GPU	vsp05b	-	full	DOWN	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	1	-	-	-	-	W;	500	6.119	-	49	64	-	-	; , 3	F	8080G	-	-	-	-	-	-	-	vsp05b
171.67.108.44	GPU	vsp05d	-	full	DOWN	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	1	-	-	-	-	W;	10000	6.119	-	49	64	-	-	; , 1	-	8080G	-	-	-	-	-	-	-	vsp05d

Re: VSP05 & associated servers DOWN

Posted: Thu Nov 04, 2010 1:16 pm
by HaloJones
Looking at the server stats page there's loads down and I now have a 460GTX with no work :(

Re: VSP05 & associated servers DOWN

Posted: Thu Nov 04, 2010 1:56 pm
by jimerickson
got 2 gtx 480's with 11 attempts each. gpus are cold, i am sad.

Re: VSP05 & associated servers DOWN

Posted: Thu Nov 04, 2010 2:07 pm
by VijayPande
Yes, we are on it. And also looking into the root cause.

Re: VSP05 & associated servers DOWN

Posted: Thu Nov 04, 2010 2:18 pm
by HaloJones
Got work for the 460GTX and just brought a 450GTS on-line

Re: VSP05 & associated servers DOWN

Posted: Thu Nov 04, 2010 2:19 pm
by VijayPande
Yes, we should be back on line.

Dr Lin caught this one quickly, but I am a little worried that whatever crashed the machine will happen again. These machines shouldn't kernel panic, so here's something weird going on. Quite possibly bad RAM. We're looking into it.

Re: VSP05 & associated servers DOWN

Posted: Thu Nov 04, 2010 2:21 pm
by jimerickson
thank you Dr. Pande!