Latest Server Stats (Tue Mar 20 10:00:00 PST 2012) "
Code: Select all
# Server IP Name Who Client Status Connect CPU Net Fin DL Diff WUs WUs WUs
Load Load Wait Time Avail To Go Wait
31 171.64.65.10 vspg3v2 densign GPU full Accepting 1.54 13 0 109 0 277 168 9443
% Ass % Ass % Ass % Ass WUs WU E S CS NMJ 80 OS_Weight_Program_Port
80 G PS Rcv
401 16 10 1 3325 1 W_2_I_8080G;
W_1_B_8080G;
W_1_A_8080G;
W_1_F_8080G401: % Assigned G - could this represent an extremely large number of unsuccessful hits on the WS based on assignments?
3325: NMJ, or No More Jobs flag. I've seen this before as either zero or one. What's 3325??
GreyWhiskers wrote:My guess is that it is still/again an issue with the Work Server "171.64.65.103 vspg3v2".
I posted Sunday nightthat I had been having similar issues with getting that work server to a) accept uploads of finished ATI GPU WUs; and b) download new WUs after being assigned by the Assignment server. Note that as far as I can tell (see end of this post), this is NOT and was not one of the servers announced by yslin on Saturday as being down.
Here's what is currently happening with my "Old Style" ATI GPU client.
I finally got an assignment for a new work unit on 2012-03-20 @ 02:56 GMT. project:4724 run:4 clone:466 gen:69. This completed in about 7.5 hours at 10:31 GMT. It is currently 17:01 GMT.
Initially, I got the following failure upon attempt to get a new WU - this happened repeatedly:Then, it seems the Assignment Server quit banging 171.64.65.103, and has stopped handing out assignments.10:31:28:WU00:FS01:Connecting to assign-GPU.stanford.edu:80
10:31:28:WU00:FS01:News: Welcome to Folding@Home
10:31:28:WU00:FS01:Assigned to work server 171.64.65.103
10:31:28:WU00:FS01:Requesting new work unit for slot 01: RUNNING gpu:0:"RV730 Pro AGP [Radeon HD 4600 Series]" from 171.64.65.103
10:31:28:WU00:FS01:Connecting to 171.64.65.103:8080
10:31:28:ERROR:WU00:FS01:Exception: 10002: Received short response, expected 512 bytes, got 0[EDIT] After almost two hours, I goosed the V7 client to retry a download (pause/fold the GPU slot). It's back to the assignment server assigning to work server 171.64.65.103 - but the work server seems to be sending a corrupt response (zero bytes).13:58:22:WU01:FS01:Connecting to assign-GPU.stanford.edu:80
13:58:22:WU01:FS01:News: Welcome to Folding@Home
13:58:22:WARNING:WU01:FS01:Failed to get assignment from 'assign-GPU.stanford.edu:80': Empty work server assignment
13:58:22:WU01:FS01:Connecting to assign-GPU.stanford.edu:8080
13:58:22:WU01:FS01:News: Welcome to Folding@Home
13:58:22:WARNING:WU01:FS01:Failed to get assignment from 'assign-GPU.stanford.edu:8080': Empty work server assignment
13:58:22:ERROR:WU01:FS01:Exception: Could not get an assignment
16:01:22:WU01:FS01:Connecting to assign-GPU.stanford.edu:80
16:01:22:WU01:FS01:News: Welcome to Folding@Home
==================================================17:57:24:WU01:FS01:Connecting to assign-GPU.stanford.edu:80
17:57:24:WU01:FS01:News: Welcome to Folding@Home
17:57:24:WU01:FS01:Assigned to work server 171.64.65.103
17:57:24:WU01:FS01:Requesting new work unit for slot 01: READY gpu:0:"RV730 Pro AGP [Radeon HD 4600 Series]" from 171.64.65.103
17:57:24:WU01:FS01:Connecting to 171.64.65.103:8080
17:57:24:ERROR:WU01:FS01:Exception: 10002: Received short response, expected 512 bytes, got 0
Server Stats Report initiated on Tue Mar 20 08:20:01 PST 2012.
31 171.64.65.103 vspg3v2 densign GPU full Accepting 1.28 14 0 109 0 173 64 9363 260 48 0 1 0 1 W_2_I_8080G; W_1_B_8080G; W_1_A_8080G; W_1_F_8080G
Translation of some of the status columns:
full/Accepting: Ostensibly completely normal mode
260: % Assigned G (??? how can a percentage be over 100?)
173: WUs Available.
vspg3v2: Server name. So far as I can tell, this was not one of those involved in the last "server offline" post by yslin on Saturday (which announcement has not been updated). BTW, I've listed the current status for the vsp11v and vsp05s servers. Interesting that the vsp05d seems "full/accepting" while the others are in reject.
40 171.67.108.20 vsp11v lin5 GPU full Reject 0.00 0 0 999 0 0 0 0 0 0 1 0 0 W_1000_B_8080Gvsp05's and vsp11v offline
by yslin » Sat Mar 17, 2012 10:04 am
Two drives failed on the vsp05 machine and we are working on getting it back online and restoring the data. Sorry and thanks!
41 171.67.108.31 vsp05a lin5 GPU full Reject 0.00 0 0 999 0 0 0 0 0 0 1 0 0 W_500_F_8080G
42 171.67.108.32 vsp05b lin5 GPU full Reject 0.00 0 0 999 0 0 0 0 0 0 1 0 0 W_1_F_8080G
44 171.67.108.44 vsp05d lin5 GPU full Accepting 0.00 0 0 999 0 14662 14662 14662 37 17 0 1 0 1 W_100_F_8080G; W_100_A_8080G