Langouste -- WU upload/download de-coupler (+upload capping)

This forum contains information about 3rd party applications which may be of use to those who run the FAH client and one place where you might be able to get help when using one of those apps.

Moderator: Site Moderators

Post Reply
tear
Posts: 254
Joined: Sun Dec 02, 2007 4:08 am
Hardware configuration: None
Location: Rocky Mountains

Re: Langouste -- WU upload/download de-coupler (+upload capping)

Post by tear »

Great, thanks.

Ok, langouste log appears to be consistent with the helper log (the one from temp directory)...

Code: Select all

[20:47:02] Connecting to http://171.67.108.25:8080/
[20:47:52] - Couldn't send HTTP request to server
At this time my only theory is that something funky is happening with the server (really!).
Serverstat page shows .56's network load of 200 -- not sure if that's high or not.

Can you please do the following:
1) Shut the client down (wait for FahCores to stop, etc.)
2) Create a copy of FAH directory (in case I need to see it later on)
3) Start the client; since the WU hasn't been successfully returned client should re-attempt to return it
4) Observe helper log (the one in temp directory); check for success (or lack thereof)
5) If WU return is not successful shut the client down (again) and
6) Turn the proxy off, restart the client, check for success


Let me know if you have any questions or concerns.


Thanks,
tear
One man's ceiling is another man's floor.
Image
weedacres
Posts: 138
Joined: Mon Dec 24, 2007 11:18 pm
Hardware configuration: UserNames: weedacres_gpu ...
Location: Eastern Washington

Re: Langouste -- WU upload/download de-coupler (+upload capping)

Post by weedacres »

I think 200 is pretty high.

I stopped and restarted the client and it uploaded just fine. :D
Thanks for the help.

I've set Langouste up on another machine that failed when I first tried it last week. It's due in about 30 minutes. I'll let you know what happens.
Image
weedacres
Posts: 138
Joined: Mon Dec 24, 2007 11:18 pm
Hardware configuration: UserNames: weedacres_gpu ...
Location: Eastern Washington

Re: Langouste -- WU upload/download de-coupler (+upload capping)

Post by weedacres »

I have it running on 5 smp's now and 2 just uploaded fine.
.56 appears to be the culprit, and I've certainly had more trouble with that server than the rest combined.

If the upload does fail, do you have a retry built in or will it wait for the autosend?

This is a slick program, I was able to fold 6% of a P2633 while it was uploading. Only 2% of a P6701 though...., but every bit helps.

Thanks again.
Image
tear
Posts: 254
Joined: Sun Dec 02, 2007 4:08 am
Hardware configuration: None
Location: Rocky Mountains

Re: Langouste -- WU upload/download de-coupler (+upload capping)

Post by tear »

There is no retry built in (you need to wait for the autosend to kick in). Though you might be right...

Client's logic, per my observations, is:
a) one attempt (+alternative port) during autosend -- that's consistent with current behaviour of Langouste's helper
b) five attempts (each with alternative port) between WUs -- that's _not_ consistent; Langouste "attempts" only once (+alternative port)

I'll give it some thoughts.

Thanks for the feedback!


tear
One man's ceiling is another man's floor.
Image
Blasphemous Cannibal
Posts: 27
Joined: Wed Oct 28, 2009 11:20 pm

Re: Langouste -- WU upload/download de-coupler (+upload capping)

Post by Blasphemous Cannibal »

I've been seeing some funky client behavior on two multi GPU + SMP Windows rigs when using Langouste. Is this even a supported configuration? Thought I'd try it anyway :oops: . It works until both GPU console clients complete/send simultaneously. I was somehow assigned the same project on both clients which had frozen chewing up the CPU also affecting SMP frames.

I've seen this occur a few times with both a Win 7 & XP rig although I don't think I had the issue with the same WU assigned to the two cards with the first instances. This may be dependent on the steps I took to recover? The clients had frozen in the same way though.

Should I just forget the GPU clients with Langouste or limit to one GPU client only? I could maybe make more of an effort to stagger the clients but is it even really worthwhile at all for a couple or maybe 5 minutes more simulation at most a in 24 hour period?
tear
Posts: 254
Joined: Sun Dec 02, 2007 4:08 am
Hardware configuration: None
Location: Rocky Mountains

Re: Langouste -- WU upload/download de-coupler (+upload capping)

Post by tear »

BC, thanks for the report.
Blasphemous Cannibal wrote:I've been seeing some funky client behavior on two multi GPU + SMP Windows rigs when using Langouste. Is this even a supported configuration?
Such configuration should not affect Langouste per se. If it does -- it's a bug.
Blasphemous Cannibal wrote:Thought I'd try it anyway :oops: . It works until both GPU console clients complete/send simultaneously. I was somehow assigned the same project on both clients (...)
That's not Langouste's fault; Windows client stores UserID in the registry, not in client's
working directory (Linux and Mac clients store it in machinedependent.dat). UserID is used to
~uniquely identify a client.

As registry location is common for _all_ Windows clients, WU assignment logic has no way
of distinguishing your two GPU clients.

I'd say you've just been lucky not to have run into this issue before.
I haven't run more than one client (of a given type) on Windows for reasons other than testing
so I don't know how to mitigate this issue. Though I'd expect it to have been discussed in the
forum in the past.

In other words -- I can easily reproduce this issue without Lanoguste.
Blasphemous Cannibal wrote:(...) which had frozen chewing up the CPU also affecting SMP frames.

I've seen this occur a few times with both a Win 7 & XP rig although I don't think I had the issue with the same WU assigned to the two cards with the first instances. This may be dependent on the steps I took to recover? The clients had frozen in the same way though.
Langouste doesn't really have the "power" to affect client/core to net what you're describing.
Stiil, feel free to send relevant logs (clients, Langouste, Langouste helper) and details for analysis.
Blasphemous Cannibal wrote:Should I just forget the GPU clients with Langouste or limit to one GPU client only? I could maybe make more of an effort to stagger the clients but is it even really worthwhile at all for a couple or maybe 5 minutes more simulation at most a in 24 hour period?
GPU WUs are small compared to SMP WUs -- at the end of the day it's your call.
If I were you I'd probably keep Langouste for SMP though.


Let know if you have any other questions or concerns.

Thanks,
tear
One man's ceiling is another man's floor.
Image
Flathead74
Posts: 266
Joined: Sun Dec 02, 2007 6:08 pm
Location: Central New York
Contact:

Re: Langouste -- WU upload/download de-coupler (+upload capping)

Post by Flathead74 »

Many people that run multiple GPU clients have received duplicate WUs concurrently.
There are many posts in the forum attesting to such.

This is not an issue caused by using Langouste.
Blasphemous Cannibal
Posts: 27
Joined: Wed Oct 28, 2009 11:20 pm

Re: Langouste -- WU upload/download de-coupler (+upload capping)

Post by Blasphemous Cannibal »

OK, the duplicate WU thing just occurred when I restarted the Clients &/or Langouste, (cant remember which order) after they had ground to a complete halt. I have seen duplicate WUs before just not coupled with this freezing issue is what I was trying to explain. I will see what logs I have & post them later.
bruce
Posts: 20824
Joined: Thu Nov 29, 2007 10:13 pm
Location: So. Cal.

Re: Langouste -- WU upload/download de-coupler (+upload capping)

Post by bruce »

The userID is stored in the registry, as you say, and is common to all clients. The MachineID is stored in the client.cfg and is unique to each client. The servers are designed to recognize individual clients based on (UserID+Machineid) and are supposed to treat each one as an independent node in the massive supercomputer.

Duplicate assignments are EXPECTED in Windows unless each client is represented by a unique MachineID. We have seen situations where the servers assign duplicates even when the MachineIDs are unique, but they are rare.

If Langouste does not process (UserID+MachineID) then that's the bug that's being reported. If it does, then it's a server bug. If two clients are running with the same value of MachineID, then it's a configuration error that must be fixed by the user.
tear
Posts: 254
Joined: Sun Dec 02, 2007 4:08 am
Hardware configuration: None
Location: Rocky Mountains

Re: Langouste -- WU upload/download de-coupler (+upload capping)

Post by tear »

bruce wrote:The servers are designed to recognize individual clients based on (UserID+Machineid)
Ah, yes. Now I remember you mentioning this before. I'll take a closer look next time I run Windows client.
I can't really attest to the behavior you speak of at this time -- I do remember seeing something odd and
dismissing it.

And for the record -- the only manipulation Langouste does (in original client's directory)
is removal of "work/wuresults_XX.dat" file. With "forked " copy it's just ./fah6 -send XX and nothing else.
In other words, the value of MachineID is retained; also please keep in mind that Langouste does
NOT affect WU downloads per se.

Too funny, for all those who even remotely consider Langouste to be the cause of .56
server issues --
1) There have been at most 30 (thirty) Langouste downloads since Windows port introduction
2) (If the same server's used for distribution and collection) one minute return delay* is enough
to avoid I/O overlap if downstream is 4 Mbps or more (for 30MB WU)

From experience, typical multiple-client server load bottlenecks are:
a) Packet processing delay (NIC chip/NIC driver/OS kernel), which translates to
b) Amount of absolute bandwidth**
c) Ineffective I/O multiplexing in the server application, i.e. use of select(2) or poll(2)
(better alternatives have been around for several years)


*) though do NOT attempt to change it; doing so _will_ break internal logic; if you'd like the
delay to be tunable -- let me know

**) (a) and (b) are related but they are _not_ the same thing

tear
One man's ceiling is another man's floor.
Image
7im
Posts: 10179
Joined: Thu Nov 29, 2007 4:30 pm
Hardware configuration: Intel i7-4770K @ 4.5 GHz, 16 GB DDR3-2133 Corsair Vengence (black/red), EVGA GTX 760 @ 1200 MHz, on an Asus Maximus VI Hero MB (black/red), in a blacked out Antec P280 Tower, with a Xigmatek Night Hawk (black) HSF, Seasonic 760w Platinum (black case, sleeves, wires), 4 SilenX 120mm Case fans with silicon fan gaskets and silicon mounts (all black), a 512GB Samsung SSD (black), and a 2TB Black Western Digital HD (silver/black).
Location: Arizona
Contact:

Re: Langouste -- WU upload/download de-coupler (+upload capping)

Post by 7im »

tear wrote:
Too funny, for all those who even remotely consider Langouste to be the cause of .56
server issues --
1) There have been at most 30 (thirty) Langouste downloads since Windows port introduction
2) (If the same server's used for distribution and collection) one minute return delay* is enough
to avoid I/O overlap if downstream is 4 Mbps or more (for 30MB WU)

tear

#2 might be a bad assumption, and so not as remote as you assume. 1 minute may not be long enough.

It would be better to wait for the download to finish, ADD 1 minute, and then upload. Downloading and uploading on a slow connection increases concurrent connection loads that the normal client does not. And when a server is capped at 200 connections, even a handful of Win Langouste users could be using double the number of connections, and chew up a significant percentage of the total active connections.

And who really knows how many people are using your new bandwidth usage limiting feature to slow down the uploads and downloads even more, potentially increasing the connection overlaps even more, even on a fast connection.



Don't get me wrong, I'm not accusing you or your program of causing any problems. However, GREAT care needs to be taken to avoid unintended consequences, and IMO, Langouste has done that. But there is room for improvement . ;)

And yes, there is room for improvement at Stanford as well. The obvious answer would be to add more SMP servers to increase the available connections, which is already in the works... http://folding.typepad.com/news/2010/08 ... -line.html 8-)

It would be great if someday both the tools and the servers would support uploading and downloading at the same time.
How to provide enough information to get helpful support
Tell me and I forget. Teach me and I remember. Involve me and I learn.
Blasphemous Cannibal
Posts: 27
Joined: Wed Oct 28, 2009 11:20 pm

Re: Langouste -- WU upload/download de-coupler (+upload capping)

Post by Blasphemous Cannibal »

Here is the first log for gpu1, the 'issue' on this client became apparent at 21:25-ish.

Code: Select all

--- Opening Log file [August 18 20:58:44 UTC] 


# Windows GPU Console Edition 

#################################################
####################################################################

###########

                       Folding@Home Client Version 6.30r1

                          http://folding.stanford.edu

####################################################################

###########
####################################################################

###########

Launch directory: C:\Documents and Settings\Phil\FAH
Executable: C:\Documents and Settings\Phil\FAH\fah6.exe
Arguments: -gpu 0 -verbosity 9 

[20:58:44] - Ask before connecting: No
[20:58:44] - Proxy: 127.0.0.1:8880
[20:58:44] - User name: ZombieKiller1 (Team 35947)
[20:58:44] - User ID: 595352301DBE1C12
[20:58:44] - Machine ID: 2
[20:58:44] 
[20:58:44] Gpu type=2 species=30.
[20:58:44] Loaded queue successfully.
[20:58:44] 
[20:58:44] + Processing work unit
[20:58:44] Core required: FahCore_11.exe
[20:58:44] - Autosending finished units... [August 18 20:58:44 UTC]
[20:58:44] Trying to send all finished work units
[20:58:44] + No unsent completed units remaining.
[20:58:44] - Autosend completed
[20:58:44] Core found.
[20:58:44] Working on queue slot 02 [August 18 20:58:44 UTC]
[20:58:44] + Working ...
[20:58:44] - Calling '.\FahCore_11.exe -dir work/ -suffix 02 -nice 

19 -priority 96 -nocpulock -checkpoint 15 -verbose -lifeline 2508 

-version 630'

[20:58:44] 
[20:58:44] *------------------------------*
[20:58:44] Folding@Home GPU Core
[20:58:44] Version 1.31 (Tue Sep 15 10:57:42 PDT 2009)
[20:58:44] 
[20:58:44] Compiler  : Microsoft (R) 32-bit C/C++ Optimizing 

Compiler Version 14.00.50727.762 for 80x86 
[20:58:44] Build host: amoeba
[20:58:44] Board Type: Nvidia
[20:58:44] Core      : 
[20:58:44] Preparing to commence simulation
[20:58:44] - Looking at optimizations...
[20:58:44] - Files status OK
[20:58:44] - Expanded 46780 -> 252912 (decompressed 540.6 percent)
[20:58:44] Called DecompressByteArray: compressed_data_size=46780 

data_size=252912, decompressed_data_size=252912 diff=0
[20:58:44] - Digital signature verified
[20:58:44] 
[20:58:44] Project: 5766 (Run 10, Clone 104, Gen 227)
[20:58:44] 
[20:58:44] Assembly optimizations on if available.
[20:58:44] Entering M.D.
[20:58:51] Will resume from checkpoint file
[20:58:51] Tpr hash work/wudata_02.tpr:  3095420931 1630390106 

2516796858 1713697518 2108928685
[20:58:51] 
[20:58:51] Calling fah_main args: 14 usage=100
[20:58:51] 
[20:58:51] Working on Protein
[20:58:51] Client config found, loading data.
[20:58:51] Starting GUI Server
[20:58:51] Resuming from checkpoint
[20:58:51] fcCheckPointResume: retreived and current tpr file hash:
[20:58:51]    0   3095420931   3095420931
[20:58:51]    1   1630390106   1630390106
[20:58:51]    2   2516796858   2516796858
[20:58:51]    3   1713697518   1713697518
[20:58:51]    4   2108928685   2108928685
[20:58:51] fcCheckPointResume: file hashes same.
[20:58:51] fcCheckPointResume: state restored.
[20:58:51] Verified work/wudata_02.log
[20:58:51] Verified work/wudata_02.edr
[20:58:51] Verified work/wudata_02.xtc
[20:58:51] Completed 53%
[20:59:26] Completed 54%
[20:59:59] Completed 55%
[21:00:33] Completed 56%
[21:01:06] Completed 57%
[21:01:40] Completed 58%
[21:02:13] Completed 59%
[21:02:46] Completed 60%
[21:03:21] Completed 61%
[21:03:56] Completed 62%
[21:04:31] Completed 63%
[21:05:05] Completed 64%
[21:05:39] Completed 65%
[21:06:13] Completed 66%
[21:06:50] Completed 67%
[21:07:23] Completed 68%
[21:07:57] Completed 69%
[21:08:30] Completed 70%
[21:09:03] Completed 71%
[21:09:37] Completed 72%
[21:10:10] Completed 73%
[21:10:46] Completed 74%
[21:11:20] Completed 75%
[21:11:53] Completed 76%
[21:12:27] Completed 77%
[21:13:00] Completed 78%
[21:13:33] Completed 79%
[21:14:10] Completed 80%
[21:14:43] Completed 81%
[21:15:16] Completed 82%
[21:15:49] Completed 83%
[21:16:22] Completed 84%
[21:16:55] Completed 85%
[21:17:28] Completed 86%
[21:18:01] Completed 87%
[21:18:33] Completed 88%
[21:19:06] Completed 89%
[21:19:39] Completed 90%
[21:20:12] Completed 91%
[21:20:45] Completed 92%
[21:21:18] Completed 93%
[21:21:51] Completed 94%
[21:22:24] Completed 95%
[21:22:57] Completed 96%
[21:23:30] Completed 97%
[21:24:03] Completed 98%
[21:24:36] Completed 99%
[21:25:09] Completed 100%
[21:25:09] Successful run
[21:25:09] DynamicWrapper: Finished Work Unit: sleep=10000
[21:25:19] Reserved 75796 bytes for xtc file; Cosm status=0
[21:25:19] Allocated 75796 bytes for xtc file
[21:25:19] - Reading up to 75796 from "work/wudata_02.xtc": Read 

75796
[21:25:19] Read 75796 bytes from xtc file; available packet 

space=786354668
[21:25:19] xtc file hash check passed.
[21:25:19] Reserved 15168 15168 786354668 bytes for arc 

file=<work/wudata_02.trr> Cosm status=0
[21:25:19] Allocated 15168 bytes for arc file
[21:25:19] - Reading up to 15168 from "work/wudata_02.trr": Read 

15168
[21:25:19] Read 15168 bytes from arc file; available packet 

space=786339500
[21:25:19] trr file hash check passed.
[21:25:19] Allocated 560 bytes for edr file
[21:25:19] Read bedfile
[21:25:19] edr file hash check passed.
[21:25:19] Allocated 33730 bytes for logfile
[21:25:19] Read logfile
[21:25:19] GuardedRun: success in DynamicWrapper
[21:25:19] GuardedRun: done
[21:25:19] Run: GuardedRun completed.
[21:25:21] + Opened results file
[21:25:21] - Writing 125766 bytes of core data to disk...
[21:25:21] Done: 125254 -> 99310 (compressed to 79.2 percent)
[21:25:21]   ... Done.
[21:25:21] DeleteFrameFiles: successfully deleted 

file=work/wudata_02.ckp
[21:25:21] Shutting down core 
[21:25:21] 
[21:25:21] Folding@home Core Shutdown: FINISHED_UNIT
[21:25:25] CoreStatus = 64 (100)
[21:25:25] Unit 2 finished with 96 percent of time to deadline 

remaining.
[21:25:25] Updated performance fraction: 0.981939
[21:25:25] Sending work to server
[21:25:25] Project: 5766 (Run 10, Clone 104, Gen 227)
[21:25:25] - Read packet limit of 540015616... Set to 524286976.


[21:25:25] + Attempting to send results [August 18 21:25:25 UTC]
[21:25:25] - Reading file work/wuresults_02.dat from core
[21:25:25]   (Read 99822 bytes from disk)
[21:25:25] Gpu type=2 species=30.
[21:25:25] Connecting to http://171.67.108.11:8080/
[21:32:16] Posted data.
[21:52:16] Initial: 00BA; + Could not connect to Work Server 

(results)
[22:12:16]     (171.67.108.11:8080)
[22:12:16] + Retrying using alternative port
[22:12:16] Connecting to http://171.67.108.11:80/
[22:19:07] Posted data.
[22:22:32] ***** Got a SIGTERM signal (2)
[22:22:32] Killing all core threads

Folding@Home Client Shutdown.


--- Opening Log file [August 18 22:22:49 UTC] 


# Windows GPU Console Edition 

#################################################
####################################################################

###########

                       Folding@Home Client Version 6.30r1

                          http://folding.stanford.edu

####################################################################

###########
####################################################################

###########

Launch directory: C:\Documents and Settings\Phil\FAH
Executable: C:\Documents and Settings\Phil\FAH\fah6.exe
Arguments: -gpu 0 -verbosity 9 

[22:22:49] - Ask before connecting: No
[22:22:49] - Proxy: 127.0.0.1:8880
[22:22:49] - User name: ZombieKiller1 (Team 35947)
[22:22:49] - User ID: 595352301DBE1C12
[22:22:49] - Machine ID: 2
[22:22:49] 
[22:22:49] Gpu type=2 species=30.
[22:22:49] Loaded queue successfully.
[22:22:49] - Preparing to get new work unit...
[22:22:49] Cleaning up work directory
[22:22:49] - Autosending finished units... [August 18 22:22:49 UTC]
[22:22:49] Trying to send all finished work units
[22:22:49] Project: 5766 (Run 10, Clone 104, Gen 227)
[22:22:49] - Read packet limit of 540015616... Set to 524286976.


[22:22:49] + Attempting to send results [August 18 22:22:49 UTC]
[22:22:49] - Reading file work/wuresults_02.dat from core
[22:22:49]   (Read 99822 bytes from disk)
[22:22:49] Gpu type=2 species=30.
[22:22:49] Connecting to http://171.67.108.11:8080/
[22:22:49] + Attempting to get work packet
[22:22:49] - Will indicate memory of 3071 MB
[22:22:49] Gpu type=2 species=30.
[22:22:49] - Detect CPU. Vendor: GenuineIntel, Family: 6, Model: 7, 

Stepping: 10
[22:22:49] - Connecting to assignment server
[22:22:49] Connecting to http://assign-GPU.stanford.edu:8080/
[22:24:49] Posted data.
[22:29:40] Posted data.
[22:30:51] Initial: 00BA; [22:30:51] Initial: 00BA; + Could not 

connect to Assignment Server
[22:30:51] Connecting to http://assign-GPU.stanford.edu:80/
+ Could not connect to Work Server (results)
[22:30:51]     (171.67.108.11:8080)
[22:30:51] + Retrying using alternative port
[22:30:51] Connecting to http://171.67.108.11:80/
[22:30:52] - Couldn't send HTTP request to server[22:30:52] - 

Couldn't send HTTP request to server

[22:30:52] + Could not connect to Work Server (results)
[22:30:52]     (171.67.108.11:80)
[22:30:52] + Could not connect to Assignment Server 2
[22:30:52] - Error: Could not transmit unit 02 (completed August 18) 

to work server.
[22:30:52] + Couldn't get work instructions.
[22:30:52] - 1 failed uploads of this unit.
[22:30:52] - Attempt #1  to get work failed, and no other work to 

do.
Waiting before retry.
[22:30:52]   Keeping unit 02 in queue.
[22:30:52] + Sent 0 of 1 completed units to the server
[22:30:52] - Autosend completed
[22:31:02] + Attempting to get work packet
[22:31:02] - Will indicate memory of 3071 MB
[22:31:02] Gpu type=2 species=30.
[22:31:02] - Connecting to assignment server
[22:31:02] Connecting to http://assign-GPU.stanford.edu:8080/
[22:31:03] Posted data.
[22:31:03] Initial: 40AB; - Successful: assigned to (171.64.65.61).
[22:31:03] + News From Folding@Home: Welcome to Folding@Home
[22:31:03] Loaded queue successfully.
[22:31:03] Gpu type=2 species=30.
[22:31:03] Empty passkey
[22:31:03] Connecting to http://171.64.65.61:8080/
[22:31:03] Posted data.
[22:31:03] Initial: 0000; - Receiving payload (expected size: 74246)
[22:31:05] - Downloaded at ~36 kB/s
[22:31:05] - Averaged speed for that direction ~35 kB/s
[22:31:05] + Received work.
[22:31:05] + Closed connections
[22:31:05] 
[22:31:05] + Processing work unit
[22:31:05] Core required: FahCore_11.exe
[22:31:05] Core found.
[22:31:05] Working on queue slot 03 [August 18 22:31:05 UTC]
[22:31:05] + Working ...
[22:31:05] - Calling '.\FahCore_11.exe -dir work/ -suffix 03 -nice 

19 -priority 96 -nocpulock -checkpoint 15 -verbose -lifeline 2320 

-version 630'

[22:31:05] 
[22:31:05] *------------------------------*
[22:31:05] Folding@Home GPU Core
[22:31:05] Version 1.31 (Tue Sep 15 10:57:42 PDT 2009)
[22:31:05] 
[22:31:05] Compiler  : Microsoft (R) 32-bit C/C++ Optimizing 

Compiler Version 14.00.50727.762 for 80x86 
[22:31:05] Build host: amoeba
[22:31:05] Board Type: Nvidia
[22:31:05] Core      : 
[22:31:05] Preparing to commence simulation
[22:31:05] - Looking at optimizations...
[22:31:05] DeleteFrameFiles: successfully deleted 

file=work/wudata_03.ckp
[22:31:05] - Created dyn
[22:31:05] - Files status OK
[22:31:05] - Expanded 73734 -> 383588 (decompressed 520.2 percent)
[22:31:05] Called DecompressByteArray: compressed_data_size=73734 

data_size=383588, decompressed_data_size=383588 diff=0
[22:31:05] - Digital signature verified
[22:31:05] 
[22:31:05] Project: 6600 (Run 7, Clone 865, Gen 53)
[22:31:05] 
[22:31:05] Assembly optimizations on if available.
[22:31:05] Entering M.D.
[22:31:11] Tpr hash work/wudata_03.tpr:  4264609972 2773602567 

1784608812 4263961791 2476999212
[22:31:11] 
[22:31:11] Calling fah_main args: 14 usage=100
[22:31:11] 
[22:31:12] Working on Protein
[22:31:13] Client config found, loading data.
[22:31:13] Starting GUI Server
[22:31:53] Completed 1%
[22:32:34] Completed 2%
[22:33:15] Completed 3%
[22:33:56] Completed 4%
[22:34:37] Completed 5%
[22:35:17] Completed 6%
[22:36:00] Completed 7%
[22:36:42] Completed 8%
[22:37:23] Completed 9%
[22:38:04] Completed 10%
[22:38:46] Completed 11%
[22:39:27] Completed 12%
[22:40:07] Completed 13%
[22:40:47] Completed 14%
[22:41:28] Completed 15%
[22:42:08] Completed 16%
[22:42:48] Completed 17%
[22:43:30] Completed 18%
[22:44:12] Completed 19%
[22:44:54] Completed 20%
[22:45:36] Completed 21%
[22:46:17] Completed 22%
[22:46:58] Completed 23%
[22:47:39] Completed 24%
[22:48:20] Completed 25%
[22:49:00] Completed 26%
[22:49:41] Completed 27%
[22:50:23] Completed 28%
[22:51:05] Completed 29%
[22:51:46] Completed 30%
[22:52:28] Completed 31%
[22:53:09] Completed 32%
[22:53:50] Completed 33%
[22:54:32] Completed 34%
[22:55:13] Completed 35%
[22:55:54] Completed 36%
[22:56:36] Completed 37%
[22:57:17] Completed 38%
[22:57:59] Completed 39%
[22:58:40] Completed 40%
[22:59:22] Completed 41%
[23:00:05] Completed 42%
[23:00:46] Completed 43%
[23:01:27] Completed 44%
[23:02:08] Completed 45%
[23:02:49] Completed 46%
[23:03:31] Completed 47%
[23:04:12] Completed 48%
[23:04:54] Completed 49%
[23:05:35] Completed 50%
[23:06:16] Completed 51%
[23:06:57] Completed 52%
[23:07:38] Completed 53%
[23:08:19] Completed 54%
[23:09:00] Completed 55%
[23:09:41] Completed 56%
[23:10:22] Completed 57%
[23:11:03] Completed 58%
[23:11:44] Completed 59%
[23:12:25] Completed 60%
[23:13:05] Completed 61%
[23:13:46] Completed 62%
[23:14:27] Completed 63%
[23:15:07] Completed 64%
[23:15:48] Completed 65%
[23:16:28] Completed 66%
[23:17:11] Completed 67%
[23:17:53] Completed 68%
[23:18:35] Completed 69%
[23:19:16] Completed 70%
[23:19:58] Completed 71%
[23:20:40] Completed 72%
[23:21:21] Completed 73%
[23:22:02] Completed 74%
[23:22:44] Completed 75%
[23:23:26] Completed 76%
[23:24:07] Completed 77%
[23:24:49] Completed 78%
[23:25:30] Completed 79%
[23:26:12] Completed 80%
[23:26:53] Completed 81%
[23:27:34] Completed 82%
[23:28:16] Completed 83%
[23:28:58] Completed 84%
[23:29:39] Completed 85%
[23:30:21] Completed 86%
[23:31:03] Completed 87%
[23:31:45] Completed 88%
[23:32:26] Completed 89%
[23:33:08] Completed 90%
[23:33:50] Completed 91%
[23:34:32] Completed 92%
[23:35:14] Completed 93%
[23:35:55] Completed 94%
[23:36:36] Completed 95%
[23:37:18] Completed 96%
[23:37:35] ***** Got a SIGTERM signal (2)
[23:37:35] Killing all core threads

Folding@Home Client Shutdown.
Here are the logs for gpu2, I now see that this is where the problem starts at 21:03-ish.

Code: Select all

--- Opening Log file [August 18 20:58:46 UTC] 


# Windows GPU Console Edition 

#################################################
####################################################################

###########

                       Folding@Home Client Version 6.30r1

                          http://folding.stanford.edu

####################################################################

###########
####################################################################

###########

Launch directory: C:\Documents and Settings\Phil\FAH2
Executable: C:\Documents and Settings\Phil\FAH\fah6.exe
Arguments: -gpu 1 -verbosity 9 

[20:58:46] - Ask before connecting: No
[20:58:46] - Proxy: 127.0.0.1:8880
[20:58:46] - User name: ZombieKiller1 (Team 35947)
[20:58:46] - User ID: 595352301DBE1C12
[20:58:46] - Machine ID: 3
[20:58:46] 
[20:58:46] Gpu type=2 species=30.
[20:58:47] Loaded queue successfully.
[20:58:47] 
[20:58:47] + Processing work unit
[20:58:47] - Autosending finished units... [August 18 20:58:47 UTC]
[20:58:47] Core required: FahCore_11.exe[20:58:47] Trying to send 

all finished work units

[20:58:47] + No unsent completed units remaining.
[20:58:47] - Autosend completed
[20:58:47] Core found.
[20:58:47] Working on queue slot 06 [August 18 20:58:47 UTC]
[20:58:47] + Working ...
[20:58:47] - Calling '.\FahCore_11.exe -dir work/ -suffix 06 -nice 

19 -priority 96 -nocpulock -checkpoint 15 -verbose -lifeline 3232 

-version 630'

[20:58:47] 
[20:58:47] *------------------------------*
[20:58:47] Folding@Home GPU Core
[20:58:47] Version 1.31 (Tue Sep 15 10:57:42 PDT 2009)
[20:58:47] 
[20:58:47] Compiler  : Microsoft (R) 32-bit C/C++ Optimizing 

Compiler Version 14.00.50727.762 for 80x86 
[20:58:47] Build host: amoeba
[20:58:47] Board Type: Nvidia
[20:58:47] Core      : 
[20:58:47] Preparing to commence simulation
[20:58:47] - Looking at optimizations...
[20:58:47] - Files status OK
[20:58:47] - Expanded 45416 -> 251112 (decompressed 552.9 percent)
[20:58:47] Called DecompressByteArray: compressed_data_size=45416 

data_size=251112, decompressed_data_size=251112 diff=0
[20:58:47] - Digital signature verified
[20:58:47] 
[20:58:47] Project: 5770 (Run 12, Clone 128, Gen 496)
[20:58:47] 
[20:58:47] Assembly optimizations on if available.
[20:58:47] Entering M.D.
[20:58:53] Will resume from checkpoint file
[20:58:53] Tpr hash work/wudata_06.tpr:  1788059252 994530361 

1302572463 3876813674 825351192
[20:58:53] 
[20:58:53] Calling fah_main args: 14 usage=100
[20:58:53] 
[20:58:53] Working on Protein
[20:58:54] Client config found, loading data.
[20:58:54] Resuming from checkpoint
[20:58:54] fcCheckPointResume: retreived and current tpr file hash:
[20:58:54]    0   1788059252   1788059252
[20:58:54]    1    994530361    994530361
[20:58:54]    2   1302572463   1302572463
[20:58:54]    3   3876813674   3876813674
[20:58:54]    4    825351192    825351192
[20:58:54] fcCheckPointResume: file hashes same.
[20:58:54] fcCheckPointResume: state restored.
[20:58:54] Verified work/wudata_06.log
[20:58:54] Verified work/wudata_06.edr
[20:58:54] Verified work/wudata_06.xtc
[20:58:54] Completed 93%
[20:58:54] Starting GUI Server
[20:59:28] Completed 94%
[21:00:02] Completed 95%
[21:00:37] Completed 96%
[21:01:11] Completed 97%
[21:01:45] Completed 98%
[21:02:19] Completed 99%
[21:02:53] Completed 100%
[21:02:53] Successful run
[21:02:53] DynamicWrapper: Finished Work Unit: sleep=10000
[21:03:03] Reserved 75872 bytes for xtc file; Cosm status=0
[21:03:03] Allocated 75872 bytes for xtc file
[21:03:03] - Reading up to 75872 from "work/wudata_06.xtc": Read 

75872
[21:03:03] Read 75872 bytes from xtc file; available packet 

space=786354592
[21:03:03] xtc file hash check passed.
[21:03:03] Reserved 15168 15168 786354592 bytes for arc 

file=<work/wudata_06.trr> Cosm status=0
[21:03:03] Allocated 15168 bytes for arc file
[21:03:03] - Reading up to 15168 from "work/wudata_06.trr": Read 

15168
[21:03:03] Read 15168 bytes from arc file; available packet 

space=786339424
[21:03:03] trr file hash check passed.
[21:03:03] Allocated 560 bytes for edr file
[21:03:03] Read bedfile
[21:03:03] edr file hash check passed.
[21:03:03] Allocated 33742 bytes for logfile
[21:03:03] Read logfile
[21:03:03] GuardedRun: success in DynamicWrapper
[21:03:03] GuardedRun: done
[21:03:03] Run: GuardedRun completed.
[21:03:07] + Opened results file
[21:03:07] - Writing 125854 bytes of core data to disk...
[21:03:07] Done: 125342 -> 99405 (compressed to 79.3 percent)
[21:03:07]   ... Done.
[21:03:07] DeleteFrameFiles: successfully deleted 

file=work/wudata_06.ckp
[21:03:07] Shutting down core 
[21:03:07] 
[21:03:07] Folding@home Core Shutdown: FINISHED_UNIT
[21:03:11] CoreStatus = 64 (100)
[21:03:11] Unit 6 finished with 96 percent of time to deadline 

remaining.
[21:03:11] Updated performance fraction: 0.981812
[21:03:11] Sending work to server
[21:03:11] Project: 5770 (Run 12, Clone 128, Gen 496)
[21:03:11] - Read packet limit of 540015616... Set to 524286976.


[21:03:11] + Attempting to send results [August 18 21:03:11 UTC]
[21:03:11] - Reading file work/wuresults_06.dat from core
[21:03:11]   (Read 99917 bytes from disk)
[21:03:11] Gpu type=2 species=30.
[21:03:11] Connecting to http://171.67.108.11:8080/
[21:10:05] Posted data.
[21:30:05] Initial: 00BA; + Could not connect to Work Server 

(results)
[21:50:05]     (171.67.108.11:8080)
[21:50:05] + Retrying using alternative port
[21:50:05] Connecting to http://171.67.108.11:80/
[21:56:59] Posted data.
[22:16:59] Initial: 00BA; ***** Got a SIGTERM signal (2)
[22:22:35] Killing all core threads

Folding@Home Client Shutdown.


--- Opening Log file [August 18 22:30:27 UTC] 


# Windows GPU Console Edition 

#################################################
####################################################################

###########

                       Folding@Home Client Version 6.30r1

                          http://folding.stanford.edu

####################################################################

###########
####################################################################

###########

Launch directory: C:\Documents and Settings\Phil\FAH2
Executable: C:\Documents and Settings\Phil\FAH\fah6.exe
Arguments: -gpu 1 -verbosity 9 

[22:30:27] - Ask before connecting: No
[22:30:27] - Proxy: 127.0.0.1:8880
[22:30:27] - User name: ZombieKiller1 (Team 35947)
[22:30:27] - User ID: 595352301DBE1C12
[22:30:27] - Machine ID: 3
[22:30:27] 
[22:30:27] Gpu type=2 species=30.
[22:30:27] Loaded queue successfully.
[22:30:27] - Preparing to get new work unit...
[22:30:27] Cleaning up work directory
[22:30:27] - Autosending finished units... [August 18 22:30:27 UTC]
[22:30:27] Trying to send all finished work units
[22:30:27] Project: 5770 (Run 12, Clone 128, Gen 496)
[22:30:27] - Read packet limit of 540015616... Set to 524286976.


[22:30:27] + Attempting to send results [August 18 22:30:27 UTC]
[22:30:27] - Reading file work/wuresults_06.dat from core
[22:30:27]   (Read 99917 bytes from disk)
[22:30:27] Gpu type=2 species=30.
[22:30:27] Connecting to http://171.67.108.11:8080/
[22:30:27] + Attempting to get work packet
[22:30:27] - Will indicate memory of 3071 MB
[22:30:27] Gpu type=2 species=30.
[22:30:27] - Detect CPU. Vendor: GenuineIntel, Family: 6, Model: 7, 

Stepping: 10
[22:30:27] - Connecting to assignment server
[22:30:27] Connecting to http://assign-GPU.stanford.edu:8080/
[22:30:51] - Couldn't send HTTP request to server
[22:30:51] - Couldn't send HTTP request to server
[22:30:51] + Could not connect to Assignment Server
[22:30:51] Connecting to http://assign-GPU.stanford.edu:80/
[22:30:51] + Could not connect to Work Server (results)
[22:30:51]     (171.67.108.11:8080)
[22:30:51] + Retrying using alternative port
[22:30:51] Connecting to http://171.67.108.11:80/
[22:30:52] - Couldn't send HTTP request to server
[22:30:52] - Couldn't send HTTP request to server
[22:30:52] + Could not connect to Assignment Server 2
[22:30:52] + Couldn't get work instructions.
[22:30:52] + Could not connect to Work Server (results)
[22:30:52] - Attempt #1  to get work failed, and no other work to 

do.
Waiting before retry.
[22:30:52]     (171.67.108.11:80)
[22:30:52] - Error: Could not transmit unit 06 (completed August 18) 

to work server.
[22:30:52] - 1 failed uploads of this unit.
[22:30:52]   Keeping unit 06 in queue.
[22:30:52] + Sent 0 of 1 completed units to the server
[22:30:52] - Autosend completed
[22:31:00] + Attempting to get work packet
[22:31:00] - Will indicate memory of 3071 MB
[22:31:00] Gpu type=2 species=30.
[22:31:00] - Connecting to assignment server
[22:31:00] Connecting to http://assign-GPU.stanford.edu:8080/
[22:31:01] Posted data.
[22:31:01] Initial: 40AB; - Successful: assigned to (171.64.65.61).
[22:31:01] + News From Folding@Home: Welcome to Folding@Home
[22:31:01] Loaded queue successfully.
[22:31:01] Gpu type=2 species=30.
[22:31:01] Empty passkey
[22:31:01] Connecting to http://171.64.65.61:8080/
[22:31:01] Posted data.
[22:31:01] Initial: 0000; - Receiving payload (expected size: 74246)
[22:31:03] - Downloaded at ~36 kB/s
[22:31:03] - Averaged speed for that direction ~39 kB/s
[22:31:03] + Received work.
[22:31:03] + Closed connections
[22:31:03] 
[22:31:03] + Processing work unit
[22:31:03] Core required: FahCore_11.exe
[22:31:03] Core found.
[22:31:03] Working on queue slot 07 [August 18 22:31:03 UTC]
[22:31:03] + Working ...
[22:31:03] - Calling '.\FahCore_11.exe -dir work/ -suffix 07 -nice 

19 -priority 96 -nocpulock -checkpoint 15 -verbose -lifeline 2104 

-version 630'

[22:31:03] 
[22:31:03] *------------------------------*
[22:31:03] Folding@Home GPU Core
[22:31:03] Version 1.31 (Tue Sep 15 10:57:42 PDT 2009)
[22:31:03] 
[22:31:03] Compiler  : Microsoft (R) 32-bit C/C++ Optimizing 

Compiler Version 14.00.50727.762 for 80x86 
[22:31:03] Build host: amoeba
[22:31:03] Board Type: Nvidia
[22:31:03] Core      : 
[22:31:03] Preparing to commence simulation
[22:31:03] - Looking at optimizations...
[22:31:03] DeleteFrameFiles: successfully deleted 

file=work/wudata_07.ckp
[22:31:03] - Created dyn
[22:31:03] - Files status OK
[22:31:03] - Expanded 73734 -> 383588 (decompressed 520.2 percent)
[22:31:03] Called DecompressByteArray: compressed_data_size=73734 

data_size=383588, decompressed_data_size=383588 diff=0
[22:31:03] - Digital signature verified
[22:31:03] 
[22:31:03] Project: 6600 (Run 7, Clone 865, Gen 53)
[22:31:03] 
[22:31:03] Assembly optimizations on if available.
[22:31:03] Entering M.D.
[22:31:09] Tpr hash work/wudata_07.tpr:  4264609972 2773602567 

1784608812 4263961791 2476999212
[22:31:09] 
[22:31:09] Calling fah_main args: 14 usage=100
[22:31:09] 
[22:31:09] Working on Protein
[22:31:10] Client config found, loading data.
[22:31:10] Starting GUI Server
[22:31:47] ***** Got a SIGTERM signal (2)
[22:31:47] Killing all core threads

Folding@Home Client Shutdown.


--- Opening Log file [August 18 22:35:09 UTC] 


# Windows GPU Console Edition 

#################################################
####################################################################

###########

                       Folding@Home Client Version 6.30r1

                          http://folding.stanford.edu

####################################################################

###########
####################################################################

###########

Launch directory: C:\Documents and Settings\Phil\FAH2
Executable: C:\Documents and Settings\Phil\FAH\fah6.exe
Arguments: -gpu 1 -verbosity 9 

[22:35:09] - Ask before connecting: No
[22:35:09] - Proxy: 127.0.0.1:8880
[22:35:09] - User name: ZombieKiller1 (Team 35947)
[22:35:09] - User ID: 595352301DBE1C12
[22:35:09] - Machine ID: 3
[22:35:09] 
[22:35:09] Gpu type=2 species=30.
[22:35:09] Loaded queue successfully.
[22:35:09] 
[22:35:09] + Processing work unit
[22:35:09] Core required: FahCore_11.exe
[22:35:09] - Autosending finished units... [August 18 22:35:09 UTC]
[22:35:09] Trying to send all finished work units
[22:35:09] Core found.
[22:35:09] Project: 5770 (Run 12, Clone 128, Gen 496)
[22:35:09] - Read packet limit of 540015616... Set to 524286976.


[22:35:09] + Attempting to send results [August 18 22:35:09 UTC]
[22:35:09] - Reading file work/wuresults_06.dat from core
[22:35:09]   (Read 99917 bytes from disk)
[22:35:09] Gpu type=2 species=30.
[22:35:09] Connecting to http://171.67.108.11:8080/
[22:35:09] Working on queue slot 07 [August 18 22:35:09 UTC]
[22:35:09] + Working ...
[22:35:09] - Calling '.\FahCore_11.exe -dir work/ -suffix 07 -nice 

19 -priority 96 -nocpulock -checkpoint 15 -verbose -lifeline 3844 

-version 630'

[22:35:09] 
[22:35:09] *------------------------------*
[22:35:09] Folding@Home GPU Core
[22:35:09] Version 1.31 (Tue Sep 15 10:57:42 PDT 2009)
[22:35:09] 
[22:35:09] Compiler  : Microsoft (R) 32-bit C/C++ Optimizing 

Compiler Version 14.00.50727.762 for 80x86 
[22:35:09] Build host: amoeba
[22:35:09] Board Type: Nvidia
[22:35:09] Core      : 
[22:35:09] Preparing to commence simulation
[22:35:09] - Looking at optimizations...
[22:35:09] - Files status OK
[22:35:09] - Expanded 73734 -> 383588 (decompressed 520.2 percent)
[22:35:09] Called DecompressByteArray: compressed_data_size=73734 

data_size=383588, decompressed_data_size=383588 diff=0
[22:35:09] - Digital signature verified
[22:35:09] 
[22:35:09] Project: 6600 (Run 7, Clone 865, Gen 53)
[22:35:09] 
[22:35:09] Assembly optimizations on if available.
[22:35:09] Entering M.D.
[22:35:15] Will resume from checkpoint file
[22:35:15] Tpr hash work/wudata_07.tpr:  4264609972 2773602567 

1784608812 4263961791 2476999212
[22:35:15] 
[22:35:15] Calling fah_main args: 14 usage=100
[22:35:15] 
[22:35:16] Working on Protein
[22:35:17] Client config found, loading data.
[22:35:17] Starting GUI Server
[22:35:17] Resuming from checkpoint
[22:35:17] fcCheckPointResume: retreived and current tpr file hash:
[22:35:17]    0   4264609972   4264609972
[22:35:17]    1   2773602567   2773602567
[22:35:17]    2   1784608812   1784608812
[22:35:17]    3   4263961791   4263961791
[22:35:17]    4   2476999212   2476999212
[22:35:17] fcCheckPointResume: file hashes same.
[22:35:17] fcCheckPointResume: state restored.
[22:35:17] Verified work/wudata_07.log
[22:35:17] Verified work/wudata_07.edr
[22:35:17] Verified work/wudata_07.xtc
[22:35:49] - Couldn't send HTTP request to server
[22:35:49] + Could not connect to Work Server (results)
[22:35:49]     (171.67.108.11:8080)
[22:35:49] + Retrying using alternative port
[22:35:49] Connecting to http://171.67.108.11:80/
[22:35:50] - Couldn't send HTTP request to server
[22:35:50] + Could not connect to Work Server (results)
[22:35:50]     (171.67.108.11:80)
[22:35:50] - Error: Could not transmit unit 06 (completed August 18) 

to work server.
[22:35:50] - 2 failed uploads of this unit.
[22:35:50] - Read packet limit of 540015616... Set to 524286976.


[22:35:50] + Attempting to send results [August 18 22:35:50 UTC]
[22:35:50] - Reading file work/wuresults_06.dat from core
[22:35:50]   (Read 99917 bytes from disk)
[22:35:50] Gpu type=2 species=30.
[22:35:50] Connecting to http://171.67.108.25:8080/
[22:35:51] - Couldn't send HTTP request to server
[22:35:51] + Could not connect to Work Server (results)
[22:35:51]     (171.67.108.25:8080)
[22:35:51] + Retrying using alternative port
[22:35:51] Connecting to http://171.67.108.25:80/
[22:36:06] ***** Got a SIGTERM signal (2)
[22:36:06] Killing all core threads

Folding@Home Client Shutdown.


--- Opening Log file [August 18 22:36:17 UTC] 


# Windows GPU Console Edition 

#################################################
####################################################################

###########

                       Folding@Home Client Version 6.30r1

                          http://folding.stanford.edu

####################################################################

###########
####################################################################

###########

Launch directory: C:\Documents and Settings\Phil\FAH2
Executable: C:\Documents and Settings\Phil\FAH\fah6.exe
Arguments: -gpu 1 -verbosity 9 

[22:36:17] - Ask before connecting: No
[22:36:17] - Proxy: 127.0.0.1:8880
[22:36:17] - User name: ZombieKiller1 (Team 35947)
[22:36:17] - User ID: 595352301DBE1C12
[22:36:17] - Machine ID: 3
[22:36:17] 
[22:36:17] Gpu type=2 species=30.
[22:36:17] Loaded queue successfully.
[22:36:17] 
[22:36:17] + Processing work unit
[22:36:17] Core required: FahCore_11.exe
[22:36:17] - Autosending finished units... [22:36:17]
[22:36:17] Trying to send all finished work units
[22:36:17] Project: 5770 (Run 12, Clone 128, Gen 496)
[22:36:17] Core found.
[22:36:17] - Read packet limit of 540015616... Set to 524286976.


[22:36:17] + Attempting to send results [August 18 22:36:17 UTC]
[22:36:17] - Reading file work/wuresults_06.dat from core
[22:36:17]   (Read 99917 bytes from disk)
[22:36:17] Gpu type=2 species=30.
[22:36:17] Connecting to http://171.67.108.11:8080/
[22:36:17] Working on queue slot 07 [August 18 22:36:17 UTC]
[22:36:17] + Working ...
[22:36:17] - Calling '.\FahCore_11.exe -dir work/ -suffix 07 -nice 

19 -priority 96 -nocpulock -checkpoint 15 -verbose -lifeline 2900 

-version 630'

[22:36:17] 
[22:36:17] *------------------------------*
[22:36:17] Folding@Home GPU Core
[22:36:17] Version 1.31 (Tue Sep 15 10:57:42 PDT 2009)
[22:36:17] 
[22:36:17] Compiler  : Microsoft (R) 32-bit C/C++ Optimizing 

Compiler Version 14.00.50727.762 for 80x86 
[22:36:17] Build host: amoeba
[22:36:17] Board Type: Nvidia
[22:36:17] Core      : 
[22:36:17] Preparing to commence simulation
[22:36:17] - Looking at optimizations...
[22:36:17] - Files status OK
[22:36:17] - Expanded 73734 -> 383588 (decompressed 520.2 percent)
[22:36:17] Called DecompressByteArray: compressed_data_size=73734 

data_size=383588, decompressed_data_size=383588 diff=0
[22:36:17] - Digital signature verified
[22:36:17] 
[22:36:17] Project: 6600 (Run 7, Clone 865, Gen 53)
[22:36:17] 
[22:36:17] Assembly optimizations on if available.
[22:36:17] Entering M.D.
[22:36:23] Will resume from checkpoint file
[22:36:23] Tpr hash work/wudata_07.tpr:  4264609972 2773602567 

1784608812 4263961791 2476999212
[22:36:23] 
[22:36:23] Calling fah_main args: 14 usage=100
[22:36:23] 
[22:36:23] Working on Protein
[22:36:24] Client config found, loading data.
[22:36:24] Starting GUI Server
[22:36:24] Resuming from checkpoint
[22:36:24] fcCheckPointResume: retreived and current tpr file hash:
[22:36:24]    0   4264609972   4264609972
[22:36:24]    1   2773602567   2773602567
[22:36:24]    2   1784608812   1784608812
[22:36:24]    3   4263961791   4263961791
[22:36:24]    4   2476999212   2476999212
[22:36:24] fcCheckPointResume: file hashes same.
[22:36:24] fcCheckPointResume: state restored.
[22:36:24] Verified work/wudata_07.log
[22:36:24] Verified work/wudata_07.edr
[22:36:24] Verified work/wudata_07.xtc
[22:37:14] Completed 1%
[22:37:22] - Couldn't send HTTP request to server
[22:37:22] + Could not connect to Work Server (results)
[22:37:22]     (171.67.108.11:8080)
[22:37:22] + Retrying using alternative port
[22:37:22] Connecting to http://171.67.108.11:80/
[22:37:23] - Couldn't send HTTP request to server
[22:37:23] + Could not connect to Work Server (results)
[22:37:23]     (171.67.108.11:80)
[22:37:23] - Error: Could not transmit unit 06 (completed August 18) 

to work server.
[22:37:23] - 2 failed uploads of this unit.
[22:37:23] - Read packet limit of 540015616... Set to 524286976.


[22:37:23] + Attempting to send results [August 18 22:37:23 UTC]
[22:37:23] - Reading file work/wuresults_06.dat from core
[22:37:23]   (Read 99917 bytes from disk)
[22:37:23] Gpu type=2 species=30.
[22:37:23] Connecting to http://171.67.108.25:8080/
[22:37:24] - Couldn't send HTTP request to server
[22:37:24] + Could not connect to Work Server (results)
[22:37:24]     (171.67.108.25:8080)
[22:37:24] + Retrying using alternative port
[22:37:24] Connecting to http://171.67.108.25:80/
[22:37:25] - Couldn't send HTTP request to server
[22:37:25] + Could not connect to Work Server (results)
[22:37:25]     (171.67.108.25:80)
[22:37:25]   Could not transmit unit 06 to Collection server; 

keeping in queue.
[22:37:25] + Sent 0 of 1 completed units to the server
[22:37:25] - Autosend completed
[22:37:30] ***** Got a SIGTERM signal (2)
[22:37:30] Killing all core threads

Folding@Home Client Shutdown.


--- Opening Log file [August 18 22:38:35 UTC] 


# Windows GPU Console Edition 

#################################################
####################################################################

###########

                       Folding@Home Client Version 6.30r1

                          http://folding.stanford.edu

####################################################################

###########
####################################################################

###########

Launch directory: C:\Documents and Settings\Phil\FAH2
Executable: C:\Documents and Settings\Phil\FAH\fah6.exe
Arguments: -gpu 1 -verbosity 9 

[22:38:35] - Ask before connecting: No
[22:38:35] - Proxy: 127.0.0.1:8880
[22:38:35] - User name: ZombieKiller1 (Team 35947)
[22:38:35] - User ID: 595352301DBE1C12
[22:38:35] - Machine ID: 3
[22:38:35] 
[22:38:35] Gpu type=2 species=30.
[22:38:35] Work directory not found. Creating...
[22:38:35] Could not open work queue, generating new queue...
[22:38:35] - Preparing to get new work unit...
[22:38:35] Cleaning up work directory
[22:38:35] - Autosending finished units... [August 18 22:38:35 UTC]
[22:38:35] Trying to send all finished work units
[22:38:35] + No unsent completed units remaining.
[22:38:35] - Autosend completed
[22:38:35] + Attempting to get work packet
[22:38:35] - Will indicate memory of 3071 MB
[22:38:35] Gpu type=2 species=30.
[22:38:35] - Detect CPU. Vendor: GenuineIntel, Family: 6, Model: 7, 

Stepping: 10
[22:38:35] - Connecting to assignment server
[22:38:35] Connecting to http://assign-GPU.stanford.edu:8080/
[22:38:36] Posted data.
[22:38:36] Initial: 43AB; - Successful: assigned to (171.67.108.11).
[22:38:36] + News From Folding@Home: Welcome to Folding@Home
[22:38:36] Loaded queue successfully.
[22:38:36] Gpu type=2 species=30.
[22:38:36] Empty passkey
[22:38:36] Connecting to http://171.67.108.11:8080/
[22:38:36] Posted data.
[22:38:36] Initial: 0000; - Receiving payload (expected size: 45928)
[22:38:38] - Downloaded at ~22 kB/s
[22:38:38] - Averaged speed for that direction ~22 kB/s
[22:38:38] + Received work.
[22:38:38] + Closed connections
[22:38:38] 
[22:38:38] + Processing work unit
[22:38:38] Core required: FahCore_11.exe
[22:38:38] Core found.
[22:38:38] Working on queue slot 01 [August 18 22:38:38 UTC]
[22:38:38] + Working ...
[22:38:38] - Calling '.\FahCore_11.exe -dir work/ -suffix 01 -nice 

19 -priority 96 -nocpulock -checkpoint 15 -verbose -lifeline 1976 

-version 630'

[22:38:38] 
[22:38:38] *------------------------------*
[22:38:38] Folding@Home GPU Core
[22:38:38] Version 1.31 (Tue Sep 15 10:57:42 PDT 2009)
[22:38:38] 
[22:38:38] Compiler  : Microsoft (R) 32-bit C/C++ Optimizing 

Compiler Version 14.00.50727.762 for 80x86 
[22:38:38] Build host: amoeba
[22:38:38] Board Type: Nvidia
[22:38:38] Core      : 
[22:38:38] Preparing to commence simulation
[22:38:38] - Looking at optimizations...
[22:38:38] DeleteFrameFiles: successfully deleted 

file=work/wudata_01.ckp
[22:38:38] - Created dyn
[22:38:38] - Files status OK
[22:38:38] - Expanded 45416 -> 251112 (decompressed 552.9 percent)
[22:38:38] Called DecompressByteArray: compressed_data_size=45416 

data_size=251112, decompressed_data_size=251112 diff=0
[22:38:38] - Digital signature verified
[22:38:38] 
[22:38:38] Project: 5770 (Run 12, Clone 128, Gen 496)
[22:38:38] 
[22:38:38] Assembly optimizations on if available.
[22:38:38] Entering M.D.
[22:38:44] Tpr hash work/wudata_01.tpr:  1788059252 994530361 

1302572463 3876813674 825351192
[22:38:44] 
[22:38:44] Calling fah_main args: 14 usage=100
[22:38:44] 
[22:38:44] Working on Protein
[22:38:45] Client config found, loading data.
[22:38:45] Starting GUI Server
[22:39:19] Completed 1%
[22:39:53] Completed 2%
[22:40:27] Completed 3%
[22:41:01] Completed 4%
[22:41:34] Completed 5%
[22:42:08] Completed 6%
[22:42:42] Completed 7%
[22:43:16] Completed 8%
[22:43:50] Completed 9%
[22:44:24] Completed 10%
[22:44:58] Completed 11%
[22:45:32] Completed 12%
[22:46:06] Completed 13%
[22:46:40] Completed 14%
[22:47:14] Completed 15%
[22:47:48] Completed 16%
[22:48:22] Completed 17%
[22:48:56] Completed 18%
[22:49:30] Completed 19%
[22:50:04] Completed 20%
[22:50:38] Completed 21%
[22:51:11] Completed 22%
[22:51:45] Completed 23%
[22:52:19] Completed 24%
[22:52:53] Completed 25%
[22:53:27] Completed 26%
[22:54:01] Completed 27%
[22:54:35] Completed 28%
[22:55:09] Completed 29%
[22:55:43] Completed 30%
[22:56:17] Completed 31%
[22:56:51] Completed 32%
[22:57:25] Completed 33%
[22:57:59] Completed 34%
[22:58:33] Completed 35%
[22:59:07] Completed 36%
[22:59:40] Completed 37%
[23:00:14] Completed 38%
[23:00:48] Completed 39%
[23:01:22] Completed 40%
[23:01:56] Completed 41%
[23:02:30] Completed 42%
[23:03:04] Completed 43%
[23:03:38] Completed 44%
[23:04:12] Completed 45%
[23:04:46] Completed 46%
[23:05:20] Completed 47%
[23:05:54] Completed 48%
[23:06:28] Completed 49%
[23:07:02] Completed 50%
[23:07:36] Completed 51%
[23:08:10] Completed 52%
[23:08:44] Completed 53%
[23:09:18] Completed 54%
[23:09:52] Completed 55%
[23:10:26] Completed 56%
[23:11:00] Completed 57%
[23:11:33] Completed 58%
[23:12:07] Completed 59%
[23:12:41] Completed 60%
[23:13:15] Completed 61%
[23:13:49] Completed 62%
[23:14:23] Completed 63%
[23:14:57] Completed 64%
[23:15:31] Completed 65%
[23:16:05] Completed 66%
[23:16:39] Completed 67%
[23:17:13] Completed 68%
[23:17:47] Completed 69%
[23:18:21] Completed 70%
[23:18:55] Completed 71%
[23:19:28] Completed 72%
[23:20:02] Completed 73%
[23:20:36] Completed 74%
[23:21:10] Completed 75%
[23:21:44] Completed 76%
[23:22:18] Completed 77%
[23:22:52] Completed 78%
[23:23:26] Completed 79%
[23:24:00] Completed 80%
[23:24:34] Completed 81%
[23:25:08] Completed 82%
[23:25:42] Completed 83%
[23:26:16] Completed 84%
[23:26:50] Completed 85%
[23:27:24] Completed 86%
[23:27:57] Completed 87%
[23:28:31] Completed 88%
[23:29:05] Completed 89%
[23:29:39] Completed 90%
[23:30:13] Completed 91%
[23:30:47] Completed 92%
[23:31:21] Completed 93%
[23:31:55] Completed 94%
[23:32:29] Completed 95%
[23:33:03] Completed 96%
[23:33:37] Completed 97%
[23:34:11] Completed 98%
[23:34:45] Completed 99%
[23:35:18] Completed 100%
[23:35:19] Successful run
[23:35:19] DynamicWrapper: Finished Work Unit: sleep=10000
[23:35:29] Reserved 75848 bytes for xtc file; Cosm status=0
[23:35:29] Allocated 75848 bytes for xtc file
[23:35:29] - Reading up to 75848 from "work/wudata_01.xtc": Read 

75848
[23:35:29] Read 75848 bytes from xtc file; available packet 

space=786354616
[23:35:29] xtc file hash check passed.
[23:35:29] Reserved 15168 15168 786354616 bytes for arc 

file=<work/wudata_01.trr> Cosm status=0
[23:35:29] Allocated 15168 bytes for arc file
[23:35:29] - Reading up to 15168 from "work/wudata_01.trr": Read 

15168
[23:35:29] Read 15168 bytes from arc file; available packet 

space=786339448
[23:35:29] trr file hash check passed.
[23:35:29] Allocated 560 bytes for edr file
[23:35:29] Read bedfile
[23:35:29] edr file hash check passed.
[23:35:29] Allocated 33315 bytes for logfile
[23:35:29] Read logfile
[23:35:29] GuardedRun: success in DynamicWrapper
[23:35:29] GuardedRun: done
[23:35:29] Run: GuardedRun completed.
[23:35:33] + Opened results file
[23:35:33] - Writing 125403 bytes of core data to disk...
[23:35:33] Done: 124891 -> 99391 (compressed to 79.5 percent)
[23:35:33]   ... Done.
[23:35:33] DeleteFrameFiles: successfully deleted 

file=work/wudata_01.ckp
[23:35:33] Shutting down core
[23:35:33] 
[23:35:33] Folding@home Core Shutdown: FINISHED_UNIT
[23:35:36] CoreStatus = 64 (100)
[23:35:36] Unit 1 finished with 99 percent of time to deadline 

remaining.
[23:35:36] Updated performance fraction: 0.986813
[23:35:36] Sending work to server
[23:35:36] Project: 5770 (Run 12, Clone 128, Gen 496)
[23:35:36] - Read packet limit of 540015616... Set to 524286976.


[23:35:36] + Attempting to send results [August 18 23:35:36 UTC]
[23:35:36] - Reading file work/wuresults_01.dat from core
[23:35:36]   (Read 99903 bytes from disk)
[23:35:36] Gpu type=2 species=30.
[23:35:36] Connecting to http://171.67.108.11:8080/
[23:37:11] - Couldn't send HTTP request to server
[23:37:11] + Could not connect to Work Server (results)
[23:37:11]     (171.67.108.11:8080)
[23:37:11] + Retrying using alternative port
[23:37:11] Connecting to http://171.67.108.11:80/
[23:37:12] - Couldn't send HTTP request to server
[23:37:12] + Could not connect to Work Server (results)
[23:37:12]     (171.67.108.11:80)
[23:37:12] - Error: Could not transmit unit 01 (completed August 18) 

to work server.
[23:37:12] - 1 failed uploads of this unit.
[23:37:12]   Keeping unit 01 in queue.
[23:37:12] Trying to send all finished work units
[23:37:12] Project: 5770 (Run 12, Clone 128, Gen 496)
[23:37:12] - Read packet limit of 540015616... Set to 524286976.


[23:37:12] + Attempting to send results [August 18 23:37:12 UTC]
[23:37:12] - Reading file work/wuresults_01.dat from core
[23:37:12]   (Read 99903 bytes from disk)
[23:37:12] Gpu type=2 species=30.
[23:37:12] Connecting to http://171.67.108.11:8080/
[23:37:24] ***** Got a SIGTERM signal (2)
[23:37:24] Killing all core threads

Folding@Home Client Shutdown.
For good measure I've thrown the SMP logs in as well, you can see the frames slow down whilst the GPUs are knackered.

Code: Select all

--- Opening Log file [August 18 20:58:20 UTC] 


# Windows SMP Console Edition 

#################################################
####################################################################

###########

                       Folding@Home Client Version 6.30

                          http://folding.stanford.edu

####################################################################

###########
####################################################################

###########

Launch directory: C:\Documents and Settings\Phil\FAH_SMP
Executable: C:\Documents and Settings\Phil\FAH_SMP\fah6.exe
Arguments: -smp 2 -verbosity 9 

[20:58:20] - Ask before connecting: No
[20:58:20] - Proxy: 127.0.0.1:8880
[20:58:20] - User name: ZombieKiller1 (Team 35947)
[20:58:20] - User ID: 595352301DBE1C12
[20:58:20] - Machine ID: 1
[20:58:20] 
[20:58:20] Loaded queue successfully.
[20:58:20] 
[20:58:20] + Processing work unit
[20:58:20] - Autosending finished units... [August 18 20:58:20 UTC]
[20:58:20] Core required: FahCore_a3.exe
[20:58:20] Trying to send all finished work units
[20:58:20] Project: 6702 (Run 7, Clone 96, Gen 26)
[20:58:20] Core found.


[20:58:20] + Attempting to send results [August 18 20:58:20 UTC]
[20:58:20] - Reading file work/wuresults_07.dat from core
[20:58:20] Working on queue slot 08 [August 18 20:58:20 UTC]
[20:58:21]   (Read 43619599 bytes from disk)
[20:58:21] + Working ...
[20:58:21] - Calling '.\FahCore_a3.exe -dir work/ -nice 19 -suffix 

08 -np 2 -checkpoint 15 -verbose -lifeline 3724 -version 630'

[20:58:21] Connecting to http://171.64.65.56:8080/
[20:58:21] 
[20:58:21] *------------------------------*
[20:58:21] Folding@Home Gromacs SMP Core
[20:58:21] Version 2.22 (Mar 12, 2010)
[20:58:21] 
[20:58:21] Preparing to commence simulation
[20:58:21] - Ensuring status. Please wait.
[20:58:22] - Couldn't send HTTP request to server
[20:58:22] + Could not connect to Work Server (results)
[20:58:22]     (171.64.65.56:8080)
[20:58:22] + Retrying using alternative port
[20:58:22] Connecting to http://171.64.65.56:80/
[20:58:23] - Couldn't send HTTP request to server
[20:58:23] + Could not connect to Work Server (results)
[20:58:23]     (171.64.65.56:80)
[20:58:23] - Error: Could not transmit unit 07 (completed August 18) 

to work server.
[20:58:23] - 5 failed uploads of this unit.


[20:58:23] + Attempting to send results [August 18 20:58:23 UTC]
[20:58:23] - Reading file work/wuresults_07.dat from core
[20:58:23]   (Read 43619599 bytes from disk)
[20:58:23] Connecting to http://171.67.108.25:8080/
[20:58:24] - Couldn't send HTTP request to server
[20:58:24] + Could not connect to Work Server (results)
[20:58:24]     (171.67.108.25:8080)
[20:58:24] + Retrying using alternative port
[20:58:24] Connecting to http://171.67.108.25:80/
[20:58:25] - Couldn't send HTTP request to server
[20:58:25] + Could not connect to Work Server (results)
[20:58:25]     (171.67.108.25:80)
[20:58:25]   Could not transmit unit 07 to Collection server; 

keeping in queue.
[20:58:25] + Sent 0 of 1 completed units to the server
[20:58:25] - Autosend completed
[20:58:31] - Looking at optimizations...
[20:58:31] - Working with standard loops on this execution.
[20:58:31] - Previous termination of core was improper.
[20:58:31] - Going to use standard loops.
[20:58:31] - Files status OK
[20:58:31] - Expanded 1765816 -> 2254597 (decompressed 127.6 

percent)
[20:58:31] Called DecompressByteArray: compressed_data_size=1765816 

data_size=2254597, decompressed_data_size=2254597 diff=0
[20:58:31] - Digital signature verified
[20:58:31] 
[20:58:31] Project: 6061 (Run 0, Clone 18, Gen 161)
[20:58:31] 
[20:58:31] Entering M.D.
[20:58:37] Using Gromacs checkpoints
[20:58:39] Resuming from checkpoint
[20:58:39] Verified work/wudata_08.log
[20:58:39] Verified work/wudata_08.trr
[20:58:39] Verified work/wudata_08.edr
[20:58:39] Completed 221722 out of 500000 steps  (44%)
[21:05:39] Completed 225000 out of 500000 steps  (45%)
[21:22:30] Completed 230000 out of 500000 steps  (46%)
[21:37:06] Completed 235000 out of 500000 steps  (47%)
[21:51:29] Completed 240000 out of 500000 steps  (48%)
[22:05:44] Completed 245000 out of 500000 steps  (49%)
[22:20:09] Completed 250000 out of 500000 steps  (50%)
[22:32:48] Completed 255000 out of 500000 steps  (51%)
[22:42:06] Completed 260000 out of 500000 steps  (52%)
[22:50:37] Completed 265000 out of 500000 steps  (53%)
[22:59:08] Completed 270000 out of 500000 steps  (54%)
[23:07:39] Completed 275000 out of 500000 steps  (55%)
[23:16:10] Completed 280000 out of 500000 steps  (56%)
[23:24:41] Completed 285000 out of 500000 steps  (57%)
[23:33:11] Completed 290000 out of 500000 steps  (58%)
[23:42:10] Completed 295000 out of 500000 steps  (59%)
[23:49:52] Completed 300000 out of 500000 steps  (60%)
[23:57:57] Completed 305000 out of 500000 steps  (61%)
[00:06:25] Completed 310000 out of 500000 steps  (62%)
[00:14:48] Completed 315000 out of 500000 steps  (63%)
[00:22:49] Completed 320000 out of 500000 steps  (64%)
[00:30:52] Completed 325000 out of 500000 steps  (65%)
[00:38:53] Completed 330000 out of 500000 steps  (66%)
[00:46:53] Completed 335000 out of 500000 steps  (67%)
[00:54:54] Completed 340000 out of 500000 steps  (68%)
[01:02:55] Completed 345000 out of 500000 steps  (69%)
[01:10:55] Completed 350000 out of 500000 steps  (70%)
[01:18:55] Completed 355000 out of 500000 steps  (71%)
[01:26:57] Completed 360000 out of 500000 steps  (72%)
[01:34:58] Completed 365000 out of 500000 steps  (73%)
[01:42:58] Completed 370000 out of 500000 steps  (74%)
[01:50:56] Completed 375000 out of 500000 steps  (75%)
[01:58:55] Completed 380000 out of 500000 steps  (76%)
[02:06:55] Completed 385000 out of 500000 steps  (77%)
[02:14:55] Completed 390000 out of 500000 steps  (78%)
[02:22:54] Completed 395000 out of 500000 steps  (79%)
[02:30:53] Completed 400000 out of 500000 steps  (80%)
[02:38:52] Completed 405000 out of 500000 steps  (81%)
[02:46:51] Completed 410000 out of 500000 steps  (82%)
[02:54:51] Completed 415000 out of 500000 steps  (83%)
[02:58:25] - Autosending finished units... [August 19 02:58:25 UTC]
[02:58:25] Trying to send all finished work units
[02:58:25] Project: 6702 (Run 7, Clone 96, Gen 26)


[02:58:25] + Attempting to send results [August 19 02:58:25 UTC]
[02:58:25] - Reading file work/wuresults_07.dat from core
[02:58:25]   (Read 43619599 bytes from disk)
[02:58:25] Connecting to http://171.64.65.56:8080/
[03:02:52] Completed 420000 out of 500000 steps  (84%)
[03:10:55] Completed 425000 out of 500000 steps  (85%)
[03:18:58] Completed 430000 out of 500000 steps  (86%)
[03:24:25] Posted data.
[03:24:26] Initial: 0000; - Uploaded at ~27 kB/s
[03:24:26] - Averaged speed for that direction ~30 kB/s
[03:24:26] + Results successfully sent
[03:24:26] Thank you for your contribution to Folding@Home.
[03:24:26] + Number of Units Completed: 12

[03:24:27] + Sent 1 of 1 completed units to the server
[03:24:27] - Autosend completed
[03:27:00] Completed 435000 out of 500000 steps  (87%)
[03:35:01] Completed 440000 out of 500000 steps  (88%)
[03:43:01] Completed 445000 out of 500000 steps  (89%)
[03:51:03] Completed 450000 out of 500000 steps  (90%)
[03:59:03] Completed 455000 out of 500000 steps  (91%)
[04:07:01] Completed 460000 out of 500000 steps  (92%)
[04:14:58] Completed 465000 out of 500000 steps  (93%)
[04:22:55] Completed 470000 out of 500000 steps  (94%)
[04:30:54] Completed 475000 out of 500000 steps  (95%)
[04:39:01] Completed 480000 out of 500000 steps  (96%)
[04:47:09] Completed 485000 out of 500000 steps  (97%)
[04:55:15] Completed 490000 out of 500000 steps  (98%)
[05:03:23] Completed 495000 out of 500000 steps  (99%)
[05:11:32] Completed 500000 out of 500000 steps  (100%)
[05:11:33] DynamicWrapper: Finished Work Unit: sleep=10000
[05:11:43] 
[05:11:43] Finished Work Unit:
[05:11:43] - Reading up to 3700368 from "work/wudata_08.trr": Read 

3700368
[05:11:43] trr file hash check passed.
[05:11:43] edr file hash check passed.
[05:11:43] logfile size: 59026
[05:11:43] Leaving Run
[05:11:47] - Writing 3794946 bytes of core data to disk...
[05:11:47]   ... Done.
[05:11:48] - Shutting down core
tear, can you tell me how to extract the Langouste logs please? btw I have no intention to stop using Langouste on my SMP clients but I've stopped using the proxy on the GPU's for now.

EDIT: tear, I've checked in the temp folder you directed weedacres to & the last helperfile was at 19:30 yesterday.

Cheers
Phil.
tear
Posts: 254
Joined: Sun Dec 02, 2007 4:08 am
Hardware configuration: None
Location: Rocky Mountains

Re: Langouste -- WU upload/download de-coupler (+upload capping)

Post by tear »

7im wrote:
tear wrote:
Too funny, for all those who even remotely consider Langouste to be the cause of .56
server issues --
1) There have been at most 30 (thirty) Langouste downloads since Windows port introduction
2) (If the same server's used for distribution and collection) one minute return delay* is enough
to avoid I/O overlap if downstream is 4 Mbps or more (for 30MB WU)

tear

#2 might be a bad assumption, and so not as remote as you assume. 1 minute may not be long enough.
For 4M+ downstream it is -- that's the message above.
7im wrote:It would be better to wait for the download to finish, ADD 1 minute, and then upload.
Nope, I'm not going to (implicitly) accept poor programming or insufficient hardware resources. You haven't met me yesterday, have you?
7im wrote:Downloading and uploading on a slow connection increases concurrent connection loads that the normal client does not. And when a server is capped at 200 connections, even a handful of Win Langouste users could be using double the number of connections, and chew up a significant percentage of the total active connections.
You seem not to understand the nature of the server issue. Users are not hitting soft limits.
It's not that "we have 5 extra users therefore 5 other users cannot send/receive data", it's the server/link/whatever that's just bogged down.
Just read the reports. Slow, incomplete uploads, dropped connections, et c. Classic symptoms.
7im wrote:And who really knows how many people are using your new bandwidth usage limiting feature to slow down the uploads and downloads even more, potentially increasing the connection overlaps even more, even on a fast connection.
Bandwidth usage limiting only affects uploads and technically it's no different than another bunch of slow-uplink users.
Also, there's no motivation for slowing uploads down more than necessary due to bonuses.

If backend doesn't have enough headroom or if soft limits aren't set (or estimated) correctly -- sorry, can't help that.
I'm always available for a consult tho. One just needs to ask.

FAH backend is not a rocket science. I'm not sure where you got the "200 connections" number but if that's
really the number when performance isn't acceptable any more then someone really needs to get back
to the drawing board (I'm being _very_ polite here).


tear
One man's ceiling is another man's floor.
Image
tear
Posts: 254
Joined: Sun Dec 02, 2007 4:08 am
Hardware configuration: None
Location: Rocky Mountains

Re: Langouste -- WU upload/download de-coupler (+upload capping)

Post by tear »

Hi Phil,
Blasphemous Cannibal wrote:Here is the first log for gpu1, the 'issue' on this client became apparent at 21:25-ish.

Code: Select all

--- Opening Log file [August 18 20:58:44 UTC] 


# Windows GPU Console Edition 

#################################################
####################################################################

###########

                       Folding@Home Client Version 6.30r1

                          http://folding.stanford.edu

####################################################################

###########
####################################################################

###########

Launch directory: C:\Documents and Settings\Phil\FAH
Executable: C:\Documents and Settings\Phil\FAH\fah6.exe
Arguments: -gpu 0 -verbosity 9 

[20:58:44] - Ask before connecting: No
[20:58:44] - Proxy: 127.0.0.1:8880
[20:58:44] - User name: ZombieKiller1 (Team 35947)
[20:58:44] - User ID: 595352301DBE1C12
[20:58:44] - Machine ID: 2
[20:58:44] 
[20:58:44] Gpu type=2 species=30.
[20:58:44] Loaded queue successfully.
[20:58:44] 
[20:58:44] + Processing work unit
[20:58:44] Core required: FahCore_11.exe
[20:58:44] - Autosending finished units... [August 18 20:58:44 UTC]
[20:58:44] Trying to send all finished work units
[20:58:44] + No unsent completed units remaining.
[20:58:44] - Autosend completed
[20:58:44] Core found.
[20:58:44] Working on queue slot 02 [August 18 20:58:44 UTC]
[20:58:44] + Working ...
[20:58:44] - Calling '.\FahCore_11.exe -dir work/ -suffix 02 -nice 

19 -priority 96 -nocpulock -checkpoint 15 -verbose -lifeline 2508 

-version 630'

[20:58:44] 
[20:58:44] *------------------------------*
[20:58:44] Folding@Home GPU Core
[20:58:44] Version 1.31 (Tue Sep 15 10:57:42 PDT 2009)
[20:58:44] 
[20:58:44] Compiler  : Microsoft (R) 32-bit C/C++ Optimizing 

Compiler Version 14.00.50727.762 for 80x86 
[20:58:44] Build host: amoeba
[20:58:44] Board Type: Nvidia
[20:58:44] Core      : 
[20:58:44] Preparing to commence simulation
[20:58:44] - Looking at optimizations...
[20:58:44] - Files status OK
[20:58:44] - Expanded 46780 -> 252912 (decompressed 540.6 percent)
[20:58:44] Called DecompressByteArray: compressed_data_size=46780 

data_size=252912, decompressed_data_size=252912 diff=0
[20:58:44] - Digital signature verified
[20:58:44] 
[20:58:44] Project: 5766 (Run 10, Clone 104, Gen 227)
[20:58:44] 
[20:58:44] Assembly optimizations on if available.
[20:58:44] Entering M.D.
[20:58:51] Will resume from checkpoint file
[20:58:51] Tpr hash work/wudata_02.tpr:  3095420931 1630390106 

2516796858 1713697518 2108928685
[20:58:51] 
[20:58:51] Calling fah_main args: 14 usage=100
[20:58:51] 
[20:58:51] Working on Protein
[20:58:51] Client config found, loading data.
[20:58:51] Starting GUI Server
[20:58:51] Resuming from checkpoint
[20:58:51] fcCheckPointResume: retreived and current tpr file hash:
[20:58:51]    0   3095420931   3095420931
[20:58:51]    1   1630390106   1630390106
[20:58:51]    2   2516796858   2516796858
[20:58:51]    3   1713697518   1713697518
[20:58:51]    4   2108928685   2108928685
[20:58:51] fcCheckPointResume: file hashes same.
[20:58:51] fcCheckPointResume: state restored.
[20:58:51] Verified work/wudata_02.log
[20:58:51] Verified work/wudata_02.edr
[20:58:51] Verified work/wudata_02.xtc
[20:58:51] Completed 53%
[20:59:26] Completed 54%
[20:59:59] Completed 55%
[21:00:33] Completed 56%
[21:01:06] Completed 57%
[21:01:40] Completed 58%
[21:02:13] Completed 59%
[21:02:46] Completed 60%
[21:03:21] Completed 61%
[21:03:56] Completed 62%
[21:04:31] Completed 63%
[21:05:05] Completed 64%
[21:05:39] Completed 65%
[21:06:13] Completed 66%
[21:06:50] Completed 67%
[21:07:23] Completed 68%
[21:07:57] Completed 69%
[21:08:30] Completed 70%
[21:09:03] Completed 71%
[21:09:37] Completed 72%
[21:10:10] Completed 73%
[21:10:46] Completed 74%
[21:11:20] Completed 75%
[21:11:53] Completed 76%
[21:12:27] Completed 77%
[21:13:00] Completed 78%
[21:13:33] Completed 79%
[21:14:10] Completed 80%
[21:14:43] Completed 81%
[21:15:16] Completed 82%
[21:15:49] Completed 83%
[21:16:22] Completed 84%
[21:16:55] Completed 85%
[21:17:28] Completed 86%
[21:18:01] Completed 87%
[21:18:33] Completed 88%
[21:19:06] Completed 89%
[21:19:39] Completed 90%
[21:20:12] Completed 91%
[21:20:45] Completed 92%
[21:21:18] Completed 93%
[21:21:51] Completed 94%
[21:22:24] Completed 95%
[21:22:57] Completed 96%
[21:23:30] Completed 97%
[21:24:03] Completed 98%
[21:24:36] Completed 99%
[21:25:09] Completed 100%
[21:25:09] Successful run
[21:25:09] DynamicWrapper: Finished Work Unit: sleep=10000
[21:25:19] Reserved 75796 bytes for xtc file; Cosm status=0
[21:25:19] Allocated 75796 bytes for xtc file
[21:25:19] - Reading up to 75796 from "work/wudata_02.xtc": Read 

75796
[21:25:19] Read 75796 bytes from xtc file; available packet 

space=786354668
[21:25:19] xtc file hash check passed.
[21:25:19] Reserved 15168 15168 786354668 bytes for arc 

file=<work/wudata_02.trr> Cosm status=0
[21:25:19] Allocated 15168 bytes for arc file
[21:25:19] - Reading up to 15168 from "work/wudata_02.trr": Read 

15168
[21:25:19] Read 15168 bytes from arc file; available packet 

space=786339500
[21:25:19] trr file hash check passed.
[21:25:19] Allocated 560 bytes for edr file
[21:25:19] Read bedfile
[21:25:19] edr file hash check passed.
[21:25:19] Allocated 33730 bytes for logfile
[21:25:19] Read logfile
[21:25:19] GuardedRun: success in DynamicWrapper
[21:25:19] GuardedRun: done
[21:25:19] Run: GuardedRun completed.
[21:25:21] + Opened results file
[21:25:21] - Writing 125766 bytes of core data to disk...
[21:25:21] Done: 125254 -> 99310 (compressed to 79.2 percent)
[21:25:21]   ... Done.
[21:25:21] DeleteFrameFiles: successfully deleted 

file=work/wudata_02.ckp
[21:25:21] Shutting down core 
[21:25:21] 
[21:25:21] Folding@home Core Shutdown: FINISHED_UNIT
[21:25:25] CoreStatus = 64 (100)
[21:25:25] Unit 2 finished with 96 percent of time to deadline 

remaining.
[21:25:25] Updated performance fraction: 0.981939
[21:25:25] Sending work to server
[21:25:25] Project: 5766 (Run 10, Clone 104, Gen 227)
[21:25:25] - Read packet limit of 540015616... Set to 524286976.


[21:25:25] + Attempting to send results [August 18 21:25:25 UTC]
[21:25:25] - Reading file work/wuresults_02.dat from core
[21:25:25]   (Read 99822 bytes from disk)
[21:25:25] Gpu type=2 species=30.
[21:25:25] Connecting to http://171.67.108.11:8080/
[21:32:16] Posted data.
[21:52:16] Initial: 00BA; + Could not connect to Work Server 

(results)
[22:12:16]     (171.67.108.11:8080)
[22:12:16] + Retrying using alternative port
[22:12:16] Connecting to http://171.67.108.11:80/
[22:19:07] Posted data.
[22:22:32] ***** Got a SIGTERM signal (2)
[22:22:32] Killing all core threads

Folding@Home Client Shutdown.


--- Opening Log file [August 18 22:22:49 UTC] 


# Windows GPU Console Edition 

#################################################
####################################################################

###########

                       Folding@Home Client Version 6.30r1

                          http://folding.stanford.edu

####################################################################

###########
####################################################################

###########

Launch directory: C:\Documents and Settings\Phil\FAH
Executable: C:\Documents and Settings\Phil\FAH\fah6.exe
Arguments: -gpu 0 -verbosity 9 

[22:22:49] - Ask before connecting: No
[22:22:49] - Proxy: 127.0.0.1:8880
[22:22:49] - User name: ZombieKiller1 (Team 35947)
[22:22:49] - User ID: 595352301DBE1C12
[22:22:49] - Machine ID: 2
[22:22:49] 
[22:22:49] Gpu type=2 species=30.
[22:22:49] Loaded queue successfully.
[22:22:49] - Preparing to get new work unit...
[22:22:49] Cleaning up work directory
[22:22:49] - Autosending finished units... [August 18 22:22:49 UTC]
[22:22:49] Trying to send all finished work units
[22:22:49] Project: 5766 (Run 10, Clone 104, Gen 227)
[22:22:49] - Read packet limit of 540015616... Set to 524286976.


[22:22:49] + Attempting to send results [August 18 22:22:49 UTC]
[22:22:49] - Reading file work/wuresults_02.dat from core
[22:22:49]   (Read 99822 bytes from disk)
[22:22:49] Gpu type=2 species=30.
[22:22:49] Connecting to http://171.67.108.11:8080/
[22:22:49] + Attempting to get work packet
[22:22:49] - Will indicate memory of 3071 MB
[22:22:49] Gpu type=2 species=30.
[22:22:49] - Detect CPU. Vendor: GenuineIntel, Family: 6, Model: 7, 

Stepping: 10
[22:22:49] - Connecting to assignment server
[22:22:49] Connecting to http://assign-GPU.stanford.edu:8080/
[22:24:49] Posted data.
[22:29:40] Posted data.
[22:30:51] Initial: 00BA; [22:30:51] Initial: 00BA; + Could not 

connect to Assignment Server
[22:30:51] Connecting to http://assign-GPU.stanford.edu:80/
+ Could not connect to Work Server (results)
[22:30:51]     (171.67.108.11:8080)
[22:30:51] + Retrying using alternative port
[22:30:51] Connecting to http://171.67.108.11:80/
[22:30:52] - Couldn't send HTTP request to server[22:30:52] - 

Couldn't send HTTP request to server

[22:30:52] + Could not connect to Work Server (results)
[22:30:52]     (171.67.108.11:80)
[22:30:52] + Could not connect to Assignment Server 2
[22:30:52] - Error: Could not transmit unit 02 (completed August 18) 

to work server.
[22:30:52] + Couldn't get work instructions.
[22:30:52] - 1 failed uploads of this unit.
[22:30:52] - Attempt #1  to get work failed, and no other work to 

do.
Waiting before retry.
[22:30:52]   Keeping unit 02 in queue.
[22:30:52] + Sent 0 of 1 completed units to the server
[22:30:52] - Autosend completed
[22:31:02] + Attempting to get work packet
[22:31:02] - Will indicate memory of 3071 MB
[22:31:02] Gpu type=2 species=30.
[22:31:02] - Connecting to assignment server
[22:31:02] Connecting to http://assign-GPU.stanford.edu:8080/
[22:31:03] Posted data.
[22:31:03] Initial: 40AB; - Successful: assigned to (171.64.65.61).
[22:31:03] + News From Folding@Home: Welcome to Folding@Home
[22:31:03] Loaded queue successfully.
[22:31:03] Gpu type=2 species=30.
[22:31:03] Empty passkey
[22:31:03] Connecting to http://171.64.65.61:8080/
[22:31:03] Posted data.
[22:31:03] Initial: 0000; - Receiving payload (expected size: 74246)
[22:31:05] - Downloaded at ~36 kB/s
[22:31:05] - Averaged speed for that direction ~35 kB/s
[22:31:05] + Received work.
[22:31:05] + Closed connections
[22:31:05] 
[22:31:05] + Processing work unit
[22:31:05] Core required: FahCore_11.exe
[22:31:05] Core found.
[22:31:05] Working on queue slot 03 [August 18 22:31:05 UTC]
[22:31:05] + Working ...
[22:31:05] - Calling '.\FahCore_11.exe -dir work/ -suffix 03 -nice 

19 -priority 96 -nocpulock -checkpoint 15 -verbose -lifeline 2320 

-version 630'

[22:31:05] 
[22:31:05] *------------------------------*
[22:31:05] Folding@Home GPU Core
[22:31:05] Version 1.31 (Tue Sep 15 10:57:42 PDT 2009)
[22:31:05] 
[22:31:05] Compiler  : Microsoft (R) 32-bit C/C++ Optimizing 

Compiler Version 14.00.50727.762 for 80x86 
[22:31:05] Build host: amoeba
[22:31:05] Board Type: Nvidia
[22:31:05] Core      : 
[22:31:05] Preparing to commence simulation
[22:31:05] - Looking at optimizations...
[22:31:05] DeleteFrameFiles: successfully deleted 

file=work/wudata_03.ckp
[22:31:05] - Created dyn
[22:31:05] - Files status OK
[22:31:05] - Expanded 73734 -> 383588 (decompressed 520.2 percent)
[22:31:05] Called DecompressByteArray: compressed_data_size=73734 

data_size=383588, decompressed_data_size=383588 diff=0
[22:31:05] - Digital signature verified
[22:31:05] 
[22:31:05] Project: 6600 (Run 7, Clone 865, Gen 53)
[22:31:05] 
[22:31:05] Assembly optimizations on if available.
[22:31:05] Entering M.D.
[22:31:11] Tpr hash work/wudata_03.tpr:  4264609972 2773602567 

1784608812 4263961791 2476999212
[22:31:11] 
[22:31:11] Calling fah_main args: 14 usage=100
[22:31:11] 
[22:31:12] Working on Protein
[22:31:13] Client config found, loading data.
[22:31:13] Starting GUI Server
[22:31:53] Completed 1%
[22:32:34] Completed 2%
[22:33:15] Completed 3%
[22:33:56] Completed 4%
[22:34:37] Completed 5%
[22:35:17] Completed 6%
[22:36:00] Completed 7%
[22:36:42] Completed 8%
[22:37:23] Completed 9%
[22:38:04] Completed 10%
[22:38:46] Completed 11%
[22:39:27] Completed 12%
[22:40:07] Completed 13%
[22:40:47] Completed 14%
[22:41:28] Completed 15%
[22:42:08] Completed 16%
[22:42:48] Completed 17%
[22:43:30] Completed 18%
[22:44:12] Completed 19%
[22:44:54] Completed 20%
[22:45:36] Completed 21%
[22:46:17] Completed 22%
[22:46:58] Completed 23%
[22:47:39] Completed 24%
[22:48:20] Completed 25%
[22:49:00] Completed 26%
[22:49:41] Completed 27%
[22:50:23] Completed 28%
[22:51:05] Completed 29%
[22:51:46] Completed 30%
[22:52:28] Completed 31%
[22:53:09] Completed 32%
[22:53:50] Completed 33%
[22:54:32] Completed 34%
[22:55:13] Completed 35%
[22:55:54] Completed 36%
[22:56:36] Completed 37%
[22:57:17] Completed 38%
[22:57:59] Completed 39%
[22:58:40] Completed 40%
[22:59:22] Completed 41%
[23:00:05] Completed 42%
[23:00:46] Completed 43%
[23:01:27] Completed 44%
[23:02:08] Completed 45%
[23:02:49] Completed 46%
[23:03:31] Completed 47%
[23:04:12] Completed 48%
[23:04:54] Completed 49%
[23:05:35] Completed 50%
[23:06:16] Completed 51%
[23:06:57] Completed 52%
[23:07:38] Completed 53%
[23:08:19] Completed 54%
[23:09:00] Completed 55%
[23:09:41] Completed 56%
[23:10:22] Completed 57%
[23:11:03] Completed 58%
[23:11:44] Completed 59%
[23:12:25] Completed 60%
[23:13:05] Completed 61%
[23:13:46] Completed 62%
[23:14:27] Completed 63%
[23:15:07] Completed 64%
[23:15:48] Completed 65%
[23:16:28] Completed 66%
[23:17:11] Completed 67%
[23:17:53] Completed 68%
[23:18:35] Completed 69%
[23:19:16] Completed 70%
[23:19:58] Completed 71%
[23:20:40] Completed 72%
[23:21:21] Completed 73%
[23:22:02] Completed 74%
[23:22:44] Completed 75%
[23:23:26] Completed 76%
[23:24:07] Completed 77%
[23:24:49] Completed 78%
[23:25:30] Completed 79%
[23:26:12] Completed 80%
[23:26:53] Completed 81%
[23:27:34] Completed 82%
[23:28:16] Completed 83%
[23:28:58] Completed 84%
[23:29:39] Completed 85%
[23:30:21] Completed 86%
[23:31:03] Completed 87%
[23:31:45] Completed 88%
[23:32:26] Completed 89%
[23:33:08] Completed 90%
[23:33:50] Completed 91%
[23:34:32] Completed 92%
[23:35:14] Completed 93%
[23:35:55] Completed 94%
[23:36:36] Completed 95%
[23:37:18] Completed 96%
[23:37:35] ***** Got a SIGTERM signal (2)
[23:37:35] Killing all core threads

Folding@Home Client Shutdown.
Here are the logs for gpu2, I now see that this is where the problem starts at 21:03-ish.

Code: Select all

--- Opening Log file [August 18 20:58:46 UTC] 


# Windows GPU Console Edition 

#################################################
####################################################################

###########

                       Folding@Home Client Version 6.30r1

                          http://folding.stanford.edu

####################################################################

###########
####################################################################

###########

Launch directory: C:\Documents and Settings\Phil\FAH2
Executable: C:\Documents and Settings\Phil\FAH\fah6.exe
Arguments: -gpu 1 -verbosity 9 

[20:58:46] - Ask before connecting: No
[20:58:46] - Proxy: 127.0.0.1:8880
[20:58:46] - User name: ZombieKiller1 (Team 35947)
[20:58:46] - User ID: 595352301DBE1C12
[20:58:46] - Machine ID: 3
[20:58:46] 
[20:58:46] Gpu type=2 species=30.
[20:58:47] Loaded queue successfully.
[20:58:47] 
[20:58:47] + Processing work unit
[20:58:47] - Autosending finished units... [August 18 20:58:47 UTC]
[20:58:47] Core required: FahCore_11.exe[20:58:47] Trying to send 

all finished work units

[20:58:47] + No unsent completed units remaining.
[20:58:47] - Autosend completed
[20:58:47] Core found.
[20:58:47] Working on queue slot 06 [August 18 20:58:47 UTC]
[20:58:47] + Working ...
[20:58:47] - Calling '.\FahCore_11.exe -dir work/ -suffix 06 -nice 

19 -priority 96 -nocpulock -checkpoint 15 -verbose -lifeline 3232 

-version 630'

[20:58:47] 
[20:58:47] *------------------------------*
[20:58:47] Folding@Home GPU Core
[20:58:47] Version 1.31 (Tue Sep 15 10:57:42 PDT 2009)
[20:58:47] 
[20:58:47] Compiler  : Microsoft (R) 32-bit C/C++ Optimizing 

Compiler Version 14.00.50727.762 for 80x86 
[20:58:47] Build host: amoeba
[20:58:47] Board Type: Nvidia
[20:58:47] Core      : 
[20:58:47] Preparing to commence simulation
[20:58:47] - Looking at optimizations...
[20:58:47] - Files status OK
[20:58:47] - Expanded 45416 -> 251112 (decompressed 552.9 percent)
[20:58:47] Called DecompressByteArray: compressed_data_size=45416 

data_size=251112, decompressed_data_size=251112 diff=0
[20:58:47] - Digital signature verified
[20:58:47] 
[20:58:47] Project: 5770 (Run 12, Clone 128, Gen 496)
[20:58:47] 
[20:58:47] Assembly optimizations on if available.
[20:58:47] Entering M.D.
[20:58:53] Will resume from checkpoint file
[20:58:53] Tpr hash work/wudata_06.tpr:  1788059252 994530361 

1302572463 3876813674 825351192
[20:58:53] 
[20:58:53] Calling fah_main args: 14 usage=100
[20:58:53] 
[20:58:53] Working on Protein
[20:58:54] Client config found, loading data.
[20:58:54] Resuming from checkpoint
[20:58:54] fcCheckPointResume: retreived and current tpr file hash:
[20:58:54]    0   1788059252   1788059252
[20:58:54]    1    994530361    994530361
[20:58:54]    2   1302572463   1302572463
[20:58:54]    3   3876813674   3876813674
[20:58:54]    4    825351192    825351192
[20:58:54] fcCheckPointResume: file hashes same.
[20:58:54] fcCheckPointResume: state restored.
[20:58:54] Verified work/wudata_06.log
[20:58:54] Verified work/wudata_06.edr
[20:58:54] Verified work/wudata_06.xtc
[20:58:54] Completed 93%
[20:58:54] Starting GUI Server
[20:59:28] Completed 94%
[21:00:02] Completed 95%
[21:00:37] Completed 96%
[21:01:11] Completed 97%
[21:01:45] Completed 98%
[21:02:19] Completed 99%
[21:02:53] Completed 100%
[21:02:53] Successful run
[21:02:53] DynamicWrapper: Finished Work Unit: sleep=10000
[21:03:03] Reserved 75872 bytes for xtc file; Cosm status=0
[21:03:03] Allocated 75872 bytes for xtc file
[21:03:03] - Reading up to 75872 from "work/wudata_06.xtc": Read 

75872
[21:03:03] Read 75872 bytes from xtc file; available packet 

space=786354592
[21:03:03] xtc file hash check passed.
[21:03:03] Reserved 15168 15168 786354592 bytes for arc 

file=<work/wudata_06.trr> Cosm status=0
[21:03:03] Allocated 15168 bytes for arc file
[21:03:03] - Reading up to 15168 from "work/wudata_06.trr": Read 

15168
[21:03:03] Read 15168 bytes from arc file; available packet 

space=786339424
[21:03:03] trr file hash check passed.
[21:03:03] Allocated 560 bytes for edr file
[21:03:03] Read bedfile
[21:03:03] edr file hash check passed.
[21:03:03] Allocated 33742 bytes for logfile
[21:03:03] Read logfile
[21:03:03] GuardedRun: success in DynamicWrapper
[21:03:03] GuardedRun: done
[21:03:03] Run: GuardedRun completed.
[21:03:07] + Opened results file
[21:03:07] - Writing 125854 bytes of core data to disk...
[21:03:07] Done: 125342 -> 99405 (compressed to 79.3 percent)
[21:03:07]   ... Done.
[21:03:07] DeleteFrameFiles: successfully deleted 

file=work/wudata_06.ckp
[21:03:07] Shutting down core 
[21:03:07] 
[21:03:07] Folding@home Core Shutdown: FINISHED_UNIT
[21:03:11] CoreStatus = 64 (100)
[21:03:11] Unit 6 finished with 96 percent of time to deadline 

remaining.
[21:03:11] Updated performance fraction: 0.981812
[21:03:11] Sending work to server
[21:03:11] Project: 5770 (Run 12, Clone 128, Gen 496)
[21:03:11] - Read packet limit of 540015616... Set to 524286976.


[21:03:11] + Attempting to send results [August 18 21:03:11 UTC]
[21:03:11] - Reading file work/wuresults_06.dat from core
[21:03:11]   (Read 99917 bytes from disk)
[21:03:11] Gpu type=2 species=30.
[21:03:11] Connecting to http://171.67.108.11:8080/
[21:10:05] Posted data.
[21:30:05] Initial: 00BA; + Could not connect to Work Server 

(results)
[21:50:05]     (171.67.108.11:8080)
[21:50:05] + Retrying using alternative port
[21:50:05] Connecting to http://171.67.108.11:80/
[21:56:59] Posted data.
[22:16:59] Initial: 00BA; ***** Got a SIGTERM signal (2)
[22:22:35] Killing all core threads

Folding@Home Client Shutdown.


--- Opening Log file [August 18 22:30:27 UTC] 


# Windows GPU Console Edition 

#################################################
####################################################################

###########

                       Folding@Home Client Version 6.30r1

                          http://folding.stanford.edu

####################################################################

###########
####################################################################

###########

Launch directory: C:\Documents and Settings\Phil\FAH2
Executable: C:\Documents and Settings\Phil\FAH\fah6.exe
Arguments: -gpu 1 -verbosity 9 

[22:30:27] - Ask before connecting: No
[22:30:27] - Proxy: 127.0.0.1:8880
[22:30:27] - User name: ZombieKiller1 (Team 35947)
[22:30:27] - User ID: 595352301DBE1C12
[22:30:27] - Machine ID: 3
[22:30:27] 
[22:30:27] Gpu type=2 species=30.
[22:30:27] Loaded queue successfully.
[22:30:27] - Preparing to get new work unit...
[22:30:27] Cleaning up work directory
[22:30:27] - Autosending finished units... [August 18 22:30:27 UTC]
[22:30:27] Trying to send all finished work units
[22:30:27] Project: 5770 (Run 12, Clone 128, Gen 496)
[22:30:27] - Read packet limit of 540015616... Set to 524286976.


[22:30:27] + Attempting to send results [August 18 22:30:27 UTC]
[22:30:27] - Reading file work/wuresults_06.dat from core
[22:30:27]   (Read 99917 bytes from disk)
[22:30:27] Gpu type=2 species=30.
[22:30:27] Connecting to http://171.67.108.11:8080/
[22:30:27] + Attempting to get work packet
[22:30:27] - Will indicate memory of 3071 MB
[22:30:27] Gpu type=2 species=30.
[22:30:27] - Detect CPU. Vendor: GenuineIntel, Family: 6, Model: 7, 

Stepping: 10
[22:30:27] - Connecting to assignment server
[22:30:27] Connecting to http://assign-GPU.stanford.edu:8080/
[22:30:51] - Couldn't send HTTP request to server
[22:30:51] - Couldn't send HTTP request to server
[22:30:51] + Could not connect to Assignment Server
[22:30:51] Connecting to http://assign-GPU.stanford.edu:80/
[22:30:51] + Could not connect to Work Server (results)
[22:30:51]     (171.67.108.11:8080)
[22:30:51] + Retrying using alternative port
[22:30:51] Connecting to http://171.67.108.11:80/
[22:30:52] - Couldn't send HTTP request to server
[22:30:52] - Couldn't send HTTP request to server
[22:30:52] + Could not connect to Assignment Server 2
[22:30:52] + Couldn't get work instructions.
[22:30:52] + Could not connect to Work Server (results)
[22:30:52] - Attempt #1  to get work failed, and no other work to 

do.
Waiting before retry.
[22:30:52]     (171.67.108.11:80)
[22:30:52] - Error: Could not transmit unit 06 (completed August 18) 

to work server.
[22:30:52] - 1 failed uploads of this unit.
[22:30:52]   Keeping unit 06 in queue.
[22:30:52] + Sent 0 of 1 completed units to the server
[22:30:52] - Autosend completed
[22:31:00] + Attempting to get work packet
[22:31:00] - Will indicate memory of 3071 MB
[22:31:00] Gpu type=2 species=30.
[22:31:00] - Connecting to assignment server
[22:31:00] Connecting to http://assign-GPU.stanford.edu:8080/
[22:31:01] Posted data.
[22:31:01] Initial: 40AB; - Successful: assigned to (171.64.65.61).
[22:31:01] + News From Folding@Home: Welcome to Folding@Home
[22:31:01] Loaded queue successfully.
[22:31:01] Gpu type=2 species=30.
[22:31:01] Empty passkey
[22:31:01] Connecting to http://171.64.65.61:8080/
[22:31:01] Posted data.
[22:31:01] Initial: 0000; - Receiving payload (expected size: 74246)
[22:31:03] - Downloaded at ~36 kB/s
[22:31:03] - Averaged speed for that direction ~39 kB/s
[22:31:03] + Received work.
[22:31:03] + Closed connections
[22:31:03] 
[22:31:03] + Processing work unit
[22:31:03] Core required: FahCore_11.exe
[22:31:03] Core found.
[22:31:03] Working on queue slot 07 [August 18 22:31:03 UTC]
[22:31:03] + Working ...
[22:31:03] - Calling '.\FahCore_11.exe -dir work/ -suffix 07 -nice 

19 -priority 96 -nocpulock -checkpoint 15 -verbose -lifeline 2104 

-version 630'

[22:31:03] 
[22:31:03] *------------------------------*
[22:31:03] Folding@Home GPU Core
[22:31:03] Version 1.31 (Tue Sep 15 10:57:42 PDT 2009)
[22:31:03] 
[22:31:03] Compiler  : Microsoft (R) 32-bit C/C++ Optimizing 

Compiler Version 14.00.50727.762 for 80x86 
[22:31:03] Build host: amoeba
[22:31:03] Board Type: Nvidia
[22:31:03] Core      : 
[22:31:03] Preparing to commence simulation
[22:31:03] - Looking at optimizations...
[22:31:03] DeleteFrameFiles: successfully deleted 

file=work/wudata_07.ckp
[22:31:03] - Created dyn
[22:31:03] - Files status OK
[22:31:03] - Expanded 73734 -> 383588 (decompressed 520.2 percent)
[22:31:03] Called DecompressByteArray: compressed_data_size=73734 

data_size=383588, decompressed_data_size=383588 diff=0
[22:31:03] - Digital signature verified
[22:31:03] 
[22:31:03] Project: 6600 (Run 7, Clone 865, Gen 53)
[22:31:03] 
[22:31:03] Assembly optimizations on if available.
[22:31:03] Entering M.D.
[22:31:09] Tpr hash work/wudata_07.tpr:  4264609972 2773602567 

1784608812 4263961791 2476999212
[22:31:09] 
[22:31:09] Calling fah_main args: 14 usage=100
[22:31:09] 
[22:31:09] Working on Protein
[22:31:10] Client config found, loading data.
[22:31:10] Starting GUI Server
[22:31:47] ***** Got a SIGTERM signal (2)
[22:31:47] Killing all core threads

Folding@Home Client Shutdown.


--- Opening Log file [August 18 22:35:09 UTC] 


# Windows GPU Console Edition 

#################################################
####################################################################

###########

                       Folding@Home Client Version 6.30r1

                          http://folding.stanford.edu

####################################################################

###########
####################################################################

###########

Launch directory: C:\Documents and Settings\Phil\FAH2
Executable: C:\Documents and Settings\Phil\FAH\fah6.exe
Arguments: -gpu 1 -verbosity 9 

[22:35:09] - Ask before connecting: No
[22:35:09] - Proxy: 127.0.0.1:8880
[22:35:09] - User name: ZombieKiller1 (Team 35947)
[22:35:09] - User ID: 595352301DBE1C12
[22:35:09] - Machine ID: 3
[22:35:09] 
[22:35:09] Gpu type=2 species=30.
[22:35:09] Loaded queue successfully.
[22:35:09] 
[22:35:09] + Processing work unit
[22:35:09] Core required: FahCore_11.exe
[22:35:09] - Autosending finished units... [August 18 22:35:09 UTC]
[22:35:09] Trying to send all finished work units
[22:35:09] Core found.
[22:35:09] Project: 5770 (Run 12, Clone 128, Gen 496)
[22:35:09] - Read packet limit of 540015616... Set to 524286976.


[22:35:09] + Attempting to send results [August 18 22:35:09 UTC]
[22:35:09] - Reading file work/wuresults_06.dat from core
[22:35:09]   (Read 99917 bytes from disk)
[22:35:09] Gpu type=2 species=30.
[22:35:09] Connecting to http://171.67.108.11:8080/
[22:35:09] Working on queue slot 07 [August 18 22:35:09 UTC]
[22:35:09] + Working ...
[22:35:09] - Calling '.\FahCore_11.exe -dir work/ -suffix 07 -nice 

19 -priority 96 -nocpulock -checkpoint 15 -verbose -lifeline 3844 

-version 630'

[22:35:09] 
[22:35:09] *------------------------------*
[22:35:09] Folding@Home GPU Core
[22:35:09] Version 1.31 (Tue Sep 15 10:57:42 PDT 2009)
[22:35:09] 
[22:35:09] Compiler  : Microsoft (R) 32-bit C/C++ Optimizing 

Compiler Version 14.00.50727.762 for 80x86 
[22:35:09] Build host: amoeba
[22:35:09] Board Type: Nvidia
[22:35:09] Core      : 
[22:35:09] Preparing to commence simulation
[22:35:09] - Looking at optimizations...
[22:35:09] - Files status OK
[22:35:09] - Expanded 73734 -> 383588 (decompressed 520.2 percent)
[22:35:09] Called DecompressByteArray: compressed_data_size=73734 

data_size=383588, decompressed_data_size=383588 diff=0
[22:35:09] - Digital signature verified
[22:35:09] 
[22:35:09] Project: 6600 (Run 7, Clone 865, Gen 53)
[22:35:09] 
[22:35:09] Assembly optimizations on if available.
[22:35:09] Entering M.D.
[22:35:15] Will resume from checkpoint file
[22:35:15] Tpr hash work/wudata_07.tpr:  4264609972 2773602567 

1784608812 4263961791 2476999212
[22:35:15] 
[22:35:15] Calling fah_main args: 14 usage=100
[22:35:15] 
[22:35:16] Working on Protein
[22:35:17] Client config found, loading data.
[22:35:17] Starting GUI Server
[22:35:17] Resuming from checkpoint
[22:35:17] fcCheckPointResume: retreived and current tpr file hash:
[22:35:17]    0   4264609972   4264609972
[22:35:17]    1   2773602567   2773602567
[22:35:17]    2   1784608812   1784608812
[22:35:17]    3   4263961791   4263961791
[22:35:17]    4   2476999212   2476999212
[22:35:17] fcCheckPointResume: file hashes same.
[22:35:17] fcCheckPointResume: state restored.
[22:35:17] Verified work/wudata_07.log
[22:35:17] Verified work/wudata_07.edr
[22:35:17] Verified work/wudata_07.xtc
[22:35:49] - Couldn't send HTTP request to server
[22:35:49] + Could not connect to Work Server (results)
[22:35:49]     (171.67.108.11:8080)
[22:35:49] + Retrying using alternative port
[22:35:49] Connecting to http://171.67.108.11:80/
[22:35:50] - Couldn't send HTTP request to server
[22:35:50] + Could not connect to Work Server (results)
[22:35:50]     (171.67.108.11:80)
[22:35:50] - Error: Could not transmit unit 06 (completed August 18) 

to work server.
[22:35:50] - 2 failed uploads of this unit.
[22:35:50] - Read packet limit of 540015616... Set to 524286976.


[22:35:50] + Attempting to send results [August 18 22:35:50 UTC]
[22:35:50] - Reading file work/wuresults_06.dat from core
[22:35:50]   (Read 99917 bytes from disk)
[22:35:50] Gpu type=2 species=30.
[22:35:50] Connecting to http://171.67.108.25:8080/
[22:35:51] - Couldn't send HTTP request to server
[22:35:51] + Could not connect to Work Server (results)
[22:35:51]     (171.67.108.25:8080)
[22:35:51] + Retrying using alternative port
[22:35:51] Connecting to http://171.67.108.25:80/
[22:36:06] ***** Got a SIGTERM signal (2)
[22:36:06] Killing all core threads

Folding@Home Client Shutdown.


--- Opening Log file [August 18 22:36:17 UTC] 


# Windows GPU Console Edition 

#################################################
####################################################################

###########

                       Folding@Home Client Version 6.30r1

                          http://folding.stanford.edu

####################################################################

###########
####################################################################

###########

Launch directory: C:\Documents and Settings\Phil\FAH2
Executable: C:\Documents and Settings\Phil\FAH\fah6.exe
Arguments: -gpu 1 -verbosity 9 

[22:36:17] - Ask before connecting: No
[22:36:17] - Proxy: 127.0.0.1:8880
[22:36:17] - User name: ZombieKiller1 (Team 35947)
[22:36:17] - User ID: 595352301DBE1C12
[22:36:17] - Machine ID: 3
[22:36:17] 
[22:36:17] Gpu type=2 species=30.
[22:36:17] Loaded queue successfully.
[22:36:17] 
[22:36:17] + Processing work unit
[22:36:17] Core required: FahCore_11.exe
[22:36:17] - Autosending finished units... [22:36:17]
[22:36:17] Trying to send all finished work units
[22:36:17] Project: 5770 (Run 12, Clone 128, Gen 496)
[22:36:17] Core found.
[22:36:17] - Read packet limit of 540015616... Set to 524286976.


[22:36:17] + Attempting to send results [August 18 22:36:17 UTC]
[22:36:17] - Reading file work/wuresults_06.dat from core
[22:36:17]   (Read 99917 bytes from disk)
[22:36:17] Gpu type=2 species=30.
[22:36:17] Connecting to http://171.67.108.11:8080/
[22:36:17] Working on queue slot 07 [August 18 22:36:17 UTC]
[22:36:17] + Working ...
[22:36:17] - Calling '.\FahCore_11.exe -dir work/ -suffix 07 -nice 

19 -priority 96 -nocpulock -checkpoint 15 -verbose -lifeline 2900 

-version 630'

[22:36:17] 
[22:36:17] *------------------------------*
[22:36:17] Folding@Home GPU Core
[22:36:17] Version 1.31 (Tue Sep 15 10:57:42 PDT 2009)
[22:36:17] 
[22:36:17] Compiler  : Microsoft (R) 32-bit C/C++ Optimizing 

Compiler Version 14.00.50727.762 for 80x86 
[22:36:17] Build host: amoeba
[22:36:17] Board Type: Nvidia
[22:36:17] Core      : 
[22:36:17] Preparing to commence simulation
[22:36:17] - Looking at optimizations...
[22:36:17] - Files status OK
[22:36:17] - Expanded 73734 -> 383588 (decompressed 520.2 percent)
[22:36:17] Called DecompressByteArray: compressed_data_size=73734 

data_size=383588, decompressed_data_size=383588 diff=0
[22:36:17] - Digital signature verified
[22:36:17] 
[22:36:17] Project: 6600 (Run 7, Clone 865, Gen 53)
[22:36:17] 
[22:36:17] Assembly optimizations on if available.
[22:36:17] Entering M.D.
[22:36:23] Will resume from checkpoint file
[22:36:23] Tpr hash work/wudata_07.tpr:  4264609972 2773602567 

1784608812 4263961791 2476999212
[22:36:23] 
[22:36:23] Calling fah_main args: 14 usage=100
[22:36:23] 
[22:36:23] Working on Protein
[22:36:24] Client config found, loading data.
[22:36:24] Starting GUI Server
[22:36:24] Resuming from checkpoint
[22:36:24] fcCheckPointResume: retreived and current tpr file hash:
[22:36:24]    0   4264609972   4264609972
[22:36:24]    1   2773602567   2773602567
[22:36:24]    2   1784608812   1784608812
[22:36:24]    3   4263961791   4263961791
[22:36:24]    4   2476999212   2476999212
[22:36:24] fcCheckPointResume: file hashes same.
[22:36:24] fcCheckPointResume: state restored.
[22:36:24] Verified work/wudata_07.log
[22:36:24] Verified work/wudata_07.edr
[22:36:24] Verified work/wudata_07.xtc
[22:37:14] Completed 1%
[22:37:22] - Couldn't send HTTP request to server
[22:37:22] + Could not connect to Work Server (results)
[22:37:22]     (171.67.108.11:8080)
[22:37:22] + Retrying using alternative port
[22:37:22] Connecting to http://171.67.108.11:80/
[22:37:23] - Couldn't send HTTP request to server
[22:37:23] + Could not connect to Work Server (results)
[22:37:23]     (171.67.108.11:80)
[22:37:23] - Error: Could not transmit unit 06 (completed August 18) 

to work server.
[22:37:23] - 2 failed uploads of this unit.
[22:37:23] - Read packet limit of 540015616... Set to 524286976.


[22:37:23] + Attempting to send results [August 18 22:37:23 UTC]
[22:37:23] - Reading file work/wuresults_06.dat from core
[22:37:23]   (Read 99917 bytes from disk)
[22:37:23] Gpu type=2 species=30.
[22:37:23] Connecting to http://171.67.108.25:8080/
[22:37:24] - Couldn't send HTTP request to server
[22:37:24] + Could not connect to Work Server (results)
[22:37:24]     (171.67.108.25:8080)
[22:37:24] + Retrying using alternative port
[22:37:24] Connecting to http://171.67.108.25:80/
[22:37:25] - Couldn't send HTTP request to server
[22:37:25] + Could not connect to Work Server (results)
[22:37:25]     (171.67.108.25:80)
[22:37:25]   Could not transmit unit 06 to Collection server; 

keeping in queue.
[22:37:25] + Sent 0 of 1 completed units to the server
[22:37:25] - Autosend completed
[22:37:30] ***** Got a SIGTERM signal (2)
[22:37:30] Killing all core threads

Folding@Home Client Shutdown.


--- Opening Log file [August 18 22:38:35 UTC] 


# Windows GPU Console Edition 

#################################################
####################################################################

###########

                       Folding@Home Client Version 6.30r1

                          http://folding.stanford.edu

####################################################################

###########
####################################################################

###########

Launch directory: C:\Documents and Settings\Phil\FAH2
Executable: C:\Documents and Settings\Phil\FAH\fah6.exe
Arguments: -gpu 1 -verbosity 9 

[22:38:35] - Ask before connecting: No
[22:38:35] - Proxy: 127.0.0.1:8880
[22:38:35] - User name: ZombieKiller1 (Team 35947)
[22:38:35] - User ID: 595352301DBE1C12
[22:38:35] - Machine ID: 3
[22:38:35] 
[22:38:35] Gpu type=2 species=30.
[22:38:35] Work directory not found. Creating...
[22:38:35] Could not open work queue, generating new queue...
[22:38:35] - Preparing to get new work unit...
[22:38:35] Cleaning up work directory
[22:38:35] - Autosending finished units... [August 18 22:38:35 UTC]
[22:38:35] Trying to send all finished work units
[22:38:35] + No unsent completed units remaining.
[22:38:35] - Autosend completed
[22:38:35] + Attempting to get work packet
[22:38:35] - Will indicate memory of 3071 MB
[22:38:35] Gpu type=2 species=30.
[22:38:35] - Detect CPU. Vendor: GenuineIntel, Family: 6, Model: 7, 

Stepping: 10
[22:38:35] - Connecting to assignment server
[22:38:35] Connecting to http://assign-GPU.stanford.edu:8080/
[22:38:36] Posted data.
[22:38:36] Initial: 43AB; - Successful: assigned to (171.67.108.11).
[22:38:36] + News From Folding@Home: Welcome to Folding@Home
[22:38:36] Loaded queue successfully.
[22:38:36] Gpu type=2 species=30.
[22:38:36] Empty passkey
[22:38:36] Connecting to http://171.67.108.11:8080/
[22:38:36] Posted data.
[22:38:36] Initial: 0000; - Receiving payload (expected size: 45928)
[22:38:38] - Downloaded at ~22 kB/s
[22:38:38] - Averaged speed for that direction ~22 kB/s
[22:38:38] + Received work.
[22:38:38] + Closed connections
[22:38:38] 
[22:38:38] + Processing work unit
[22:38:38] Core required: FahCore_11.exe
[22:38:38] Core found.
[22:38:38] Working on queue slot 01 [August 18 22:38:38 UTC]
[22:38:38] + Working ...
[22:38:38] - Calling '.\FahCore_11.exe -dir work/ -suffix 01 -nice 

19 -priority 96 -nocpulock -checkpoint 15 -verbose -lifeline 1976 

-version 630'

[22:38:38] 
[22:38:38] *------------------------------*
[22:38:38] Folding@Home GPU Core
[22:38:38] Version 1.31 (Tue Sep 15 10:57:42 PDT 2009)
[22:38:38] 
[22:38:38] Compiler  : Microsoft (R) 32-bit C/C++ Optimizing 

Compiler Version 14.00.50727.762 for 80x86 
[22:38:38] Build host: amoeba
[22:38:38] Board Type: Nvidia
[22:38:38] Core      : 
[22:38:38] Preparing to commence simulation
[22:38:38] - Looking at optimizations...
[22:38:38] DeleteFrameFiles: successfully deleted 

file=work/wudata_01.ckp
[22:38:38] - Created dyn
[22:38:38] - Files status OK
[22:38:38] - Expanded 45416 -> 251112 (decompressed 552.9 percent)
[22:38:38] Called DecompressByteArray: compressed_data_size=45416 

data_size=251112, decompressed_data_size=251112 diff=0
[22:38:38] - Digital signature verified
[22:38:38] 
[22:38:38] Project: 5770 (Run 12, Clone 128, Gen 496)
[22:38:38] 
[22:38:38] Assembly optimizations on if available.
[22:38:38] Entering M.D.
[22:38:44] Tpr hash work/wudata_01.tpr:  1788059252 994530361 

1302572463 3876813674 825351192
[22:38:44] 
[22:38:44] Calling fah_main args: 14 usage=100
[22:38:44] 
[22:38:44] Working on Protein
[22:38:45] Client config found, loading data.
[22:38:45] Starting GUI Server
[22:39:19] Completed 1%
[22:39:53] Completed 2%
[22:40:27] Completed 3%
[22:41:01] Completed 4%
[22:41:34] Completed 5%
[22:42:08] Completed 6%
[22:42:42] Completed 7%
[22:43:16] Completed 8%
[22:43:50] Completed 9%
[22:44:24] Completed 10%
[22:44:58] Completed 11%
[22:45:32] Completed 12%
[22:46:06] Completed 13%
[22:46:40] Completed 14%
[22:47:14] Completed 15%
[22:47:48] Completed 16%
[22:48:22] Completed 17%
[22:48:56] Completed 18%
[22:49:30] Completed 19%
[22:50:04] Completed 20%
[22:50:38] Completed 21%
[22:51:11] Completed 22%
[22:51:45] Completed 23%
[22:52:19] Completed 24%
[22:52:53] Completed 25%
[22:53:27] Completed 26%
[22:54:01] Completed 27%
[22:54:35] Completed 28%
[22:55:09] Completed 29%
[22:55:43] Completed 30%
[22:56:17] Completed 31%
[22:56:51] Completed 32%
[22:57:25] Completed 33%
[22:57:59] Completed 34%
[22:58:33] Completed 35%
[22:59:07] Completed 36%
[22:59:40] Completed 37%
[23:00:14] Completed 38%
[23:00:48] Completed 39%
[23:01:22] Completed 40%
[23:01:56] Completed 41%
[23:02:30] Completed 42%
[23:03:04] Completed 43%
[23:03:38] Completed 44%
[23:04:12] Completed 45%
[23:04:46] Completed 46%
[23:05:20] Completed 47%
[23:05:54] Completed 48%
[23:06:28] Completed 49%
[23:07:02] Completed 50%
[23:07:36] Completed 51%
[23:08:10] Completed 52%
[23:08:44] Completed 53%
[23:09:18] Completed 54%
[23:09:52] Completed 55%
[23:10:26] Completed 56%
[23:11:00] Completed 57%
[23:11:33] Completed 58%
[23:12:07] Completed 59%
[23:12:41] Completed 60%
[23:13:15] Completed 61%
[23:13:49] Completed 62%
[23:14:23] Completed 63%
[23:14:57] Completed 64%
[23:15:31] Completed 65%
[23:16:05] Completed 66%
[23:16:39] Completed 67%
[23:17:13] Completed 68%
[23:17:47] Completed 69%
[23:18:21] Completed 70%
[23:18:55] Completed 71%
[23:19:28] Completed 72%
[23:20:02] Completed 73%
[23:20:36] Completed 74%
[23:21:10] Completed 75%
[23:21:44] Completed 76%
[23:22:18] Completed 77%
[23:22:52] Completed 78%
[23:23:26] Completed 79%
[23:24:00] Completed 80%
[23:24:34] Completed 81%
[23:25:08] Completed 82%
[23:25:42] Completed 83%
[23:26:16] Completed 84%
[23:26:50] Completed 85%
[23:27:24] Completed 86%
[23:27:57] Completed 87%
[23:28:31] Completed 88%
[23:29:05] Completed 89%
[23:29:39] Completed 90%
[23:30:13] Completed 91%
[23:30:47] Completed 92%
[23:31:21] Completed 93%
[23:31:55] Completed 94%
[23:32:29] Completed 95%
[23:33:03] Completed 96%
[23:33:37] Completed 97%
[23:34:11] Completed 98%
[23:34:45] Completed 99%
[23:35:18] Completed 100%
[23:35:19] Successful run
[23:35:19] DynamicWrapper: Finished Work Unit: sleep=10000
[23:35:29] Reserved 75848 bytes for xtc file; Cosm status=0
[23:35:29] Allocated 75848 bytes for xtc file
[23:35:29] - Reading up to 75848 from "work/wudata_01.xtc": Read 

75848
[23:35:29] Read 75848 bytes from xtc file; available packet 

space=786354616
[23:35:29] xtc file hash check passed.
[23:35:29] Reserved 15168 15168 786354616 bytes for arc 

file=<work/wudata_01.trr> Cosm status=0
[23:35:29] Allocated 15168 bytes for arc file
[23:35:29] - Reading up to 15168 from "work/wudata_01.trr": Read 

15168
[23:35:29] Read 15168 bytes from arc file; available packet 

space=786339448
[23:35:29] trr file hash check passed.
[23:35:29] Allocated 560 bytes for edr file
[23:35:29] Read bedfile
[23:35:29] edr file hash check passed.
[23:35:29] Allocated 33315 bytes for logfile
[23:35:29] Read logfile
[23:35:29] GuardedRun: success in DynamicWrapper
[23:35:29] GuardedRun: done
[23:35:29] Run: GuardedRun completed.
[23:35:33] + Opened results file
[23:35:33] - Writing 125403 bytes of core data to disk...
[23:35:33] Done: 124891 -> 99391 (compressed to 79.5 percent)
[23:35:33]   ... Done.
[23:35:33] DeleteFrameFiles: successfully deleted 

file=work/wudata_01.ckp
[23:35:33] Shutting down core
[23:35:33] 
[23:35:33] Folding@home Core Shutdown: FINISHED_UNIT
[23:35:36] CoreStatus = 64 (100)
[23:35:36] Unit 1 finished with 99 percent of time to deadline 

remaining.
[23:35:36] Updated performance fraction: 0.986813
[23:35:36] Sending work to server
[23:35:36] Project: 5770 (Run 12, Clone 128, Gen 496)
[23:35:36] - Read packet limit of 540015616... Set to 524286976.


[23:35:36] + Attempting to send results [August 18 23:35:36 UTC]
[23:35:36] - Reading file work/wuresults_01.dat from core
[23:35:36]   (Read 99903 bytes from disk)
[23:35:36] Gpu type=2 species=30.
[23:35:36] Connecting to http://171.67.108.11:8080/
[23:37:11] - Couldn't send HTTP request to server
[23:37:11] + Could not connect to Work Server (results)
[23:37:11]     (171.67.108.11:8080)
[23:37:11] + Retrying using alternative port
[23:37:11] Connecting to http://171.67.108.11:80/
[23:37:12] - Couldn't send HTTP request to server
[23:37:12] + Could not connect to Work Server (results)
[23:37:12]     (171.67.108.11:80)
[23:37:12] - Error: Could not transmit unit 01 (completed August 18) 

to work server.
[23:37:12] - 1 failed uploads of this unit.
[23:37:12]   Keeping unit 01 in queue.
[23:37:12] Trying to send all finished work units
[23:37:12] Project: 5770 (Run 12, Clone 128, Gen 496)
[23:37:12] - Read packet limit of 540015616... Set to 524286976.


[23:37:12] + Attempting to send results [August 18 23:37:12 UTC]
[23:37:12] - Reading file work/wuresults_01.dat from core
[23:37:12]   (Read 99903 bytes from disk)
[23:37:12] Gpu type=2 species=30.
[23:37:12] Connecting to http://171.67.108.11:8080/
[23:37:24] ***** Got a SIGTERM signal (2)
[23:37:24] Killing all core threads

Folding@Home Client Shutdown.
For good measure I've thrown the SMP logs in as well, you can see the frames slow down whilst the GPUs are knackered.

Code: Select all

--- Opening Log file [August 18 20:58:20 UTC] 


# Windows SMP Console Edition 

#################################################
####################################################################

###########

                       Folding@Home Client Version 6.30

                          http://folding.stanford.edu

####################################################################

###########
####################################################################

###########

Launch directory: C:\Documents and Settings\Phil\FAH_SMP
Executable: C:\Documents and Settings\Phil\FAH_SMP\fah6.exe
Arguments: -smp 2 -verbosity 9 

[20:58:20] - Ask before connecting: No
[20:58:20] - Proxy: 127.0.0.1:8880
[20:58:20] - User name: ZombieKiller1 (Team 35947)
[20:58:20] - User ID: 595352301DBE1C12
[20:58:20] - Machine ID: 1
[20:58:20] 
[20:58:20] Loaded queue successfully.
[20:58:20] 
[20:58:20] + Processing work unit
[20:58:20] - Autosending finished units... [August 18 20:58:20 UTC]
[20:58:20] Core required: FahCore_a3.exe
[20:58:20] Trying to send all finished work units
[20:58:20] Project: 6702 (Run 7, Clone 96, Gen 26)
[20:58:20] Core found.


[20:58:20] + Attempting to send results [August 18 20:58:20 UTC]
[20:58:20] - Reading file work/wuresults_07.dat from core
[20:58:20] Working on queue slot 08 [August 18 20:58:20 UTC]
[20:58:21]   (Read 43619599 bytes from disk)
[20:58:21] + Working ...
[20:58:21] - Calling '.\FahCore_a3.exe -dir work/ -nice 19 -suffix 

08 -np 2 -checkpoint 15 -verbose -lifeline 3724 -version 630'

[20:58:21] Connecting to http://171.64.65.56:8080/
[20:58:21] 
[20:58:21] *------------------------------*
[20:58:21] Folding@Home Gromacs SMP Core
[20:58:21] Version 2.22 (Mar 12, 2010)
[20:58:21] 
[20:58:21] Preparing to commence simulation
[20:58:21] - Ensuring status. Please wait.
[20:58:22] - Couldn't send HTTP request to server
[20:58:22] + Could not connect to Work Server (results)
[20:58:22]     (171.64.65.56:8080)
[20:58:22] + Retrying using alternative port
[20:58:22] Connecting to http://171.64.65.56:80/
[20:58:23] - Couldn't send HTTP request to server
[20:58:23] + Could not connect to Work Server (results)
[20:58:23]     (171.64.65.56:80)
[20:58:23] - Error: Could not transmit unit 07 (completed August 18) 

to work server.
[20:58:23] - 5 failed uploads of this unit.


[20:58:23] + Attempting to send results [August 18 20:58:23 UTC]
[20:58:23] - Reading file work/wuresults_07.dat from core
[20:58:23]   (Read 43619599 bytes from disk)
[20:58:23] Connecting to http://171.67.108.25:8080/
[20:58:24] - Couldn't send HTTP request to server
[20:58:24] + Could not connect to Work Server (results)
[20:58:24]     (171.67.108.25:8080)
[20:58:24] + Retrying using alternative port
[20:58:24] Connecting to http://171.67.108.25:80/
[20:58:25] - Couldn't send HTTP request to server
[20:58:25] + Could not connect to Work Server (results)
[20:58:25]     (171.67.108.25:80)
[20:58:25]   Could not transmit unit 07 to Collection server; 

keeping in queue.
[20:58:25] + Sent 0 of 1 completed units to the server
[20:58:25] - Autosend completed
[20:58:31] - Looking at optimizations...
[20:58:31] - Working with standard loops on this execution.
[20:58:31] - Previous termination of core was improper.
[20:58:31] - Going to use standard loops.
[20:58:31] - Files status OK
[20:58:31] - Expanded 1765816 -> 2254597 (decompressed 127.6 

percent)
[20:58:31] Called DecompressByteArray: compressed_data_size=1765816 

data_size=2254597, decompressed_data_size=2254597 diff=0
[20:58:31] - Digital signature verified
[20:58:31] 
[20:58:31] Project: 6061 (Run 0, Clone 18, Gen 161)
[20:58:31] 
[20:58:31] Entering M.D.
[20:58:37] Using Gromacs checkpoints
[20:58:39] Resuming from checkpoint
[20:58:39] Verified work/wudata_08.log
[20:58:39] Verified work/wudata_08.trr
[20:58:39] Verified work/wudata_08.edr
[20:58:39] Completed 221722 out of 500000 steps  (44%)
[21:05:39] Completed 225000 out of 500000 steps  (45%)
[21:22:30] Completed 230000 out of 500000 steps  (46%)
[21:37:06] Completed 235000 out of 500000 steps  (47%)
[21:51:29] Completed 240000 out of 500000 steps  (48%)
[22:05:44] Completed 245000 out of 500000 steps  (49%)
[22:20:09] Completed 250000 out of 500000 steps  (50%)
[22:32:48] Completed 255000 out of 500000 steps  (51%)
[22:42:06] Completed 260000 out of 500000 steps  (52%)
[22:50:37] Completed 265000 out of 500000 steps  (53%)
[22:59:08] Completed 270000 out of 500000 steps  (54%)
[23:07:39] Completed 275000 out of 500000 steps  (55%)
[23:16:10] Completed 280000 out of 500000 steps  (56%)
[23:24:41] Completed 285000 out of 500000 steps  (57%)
[23:33:11] Completed 290000 out of 500000 steps  (58%)
[23:42:10] Completed 295000 out of 500000 steps  (59%)
[23:49:52] Completed 300000 out of 500000 steps  (60%)
[23:57:57] Completed 305000 out of 500000 steps  (61%)
[00:06:25] Completed 310000 out of 500000 steps  (62%)
[00:14:48] Completed 315000 out of 500000 steps  (63%)
[00:22:49] Completed 320000 out of 500000 steps  (64%)
[00:30:52] Completed 325000 out of 500000 steps  (65%)
[00:38:53] Completed 330000 out of 500000 steps  (66%)
[00:46:53] Completed 335000 out of 500000 steps  (67%)
[00:54:54] Completed 340000 out of 500000 steps  (68%)
[01:02:55] Completed 345000 out of 500000 steps  (69%)
[01:10:55] Completed 350000 out of 500000 steps  (70%)
[01:18:55] Completed 355000 out of 500000 steps  (71%)
[01:26:57] Completed 360000 out of 500000 steps  (72%)
[01:34:58] Completed 365000 out of 500000 steps  (73%)
[01:42:58] Completed 370000 out of 500000 steps  (74%)
[01:50:56] Completed 375000 out of 500000 steps  (75%)
[01:58:55] Completed 380000 out of 500000 steps  (76%)
[02:06:55] Completed 385000 out of 500000 steps  (77%)
[02:14:55] Completed 390000 out of 500000 steps  (78%)
[02:22:54] Completed 395000 out of 500000 steps  (79%)
[02:30:53] Completed 400000 out of 500000 steps  (80%)
[02:38:52] Completed 405000 out of 500000 steps  (81%)
[02:46:51] Completed 410000 out of 500000 steps  (82%)
[02:54:51] Completed 415000 out of 500000 steps  (83%)
[02:58:25] - Autosending finished units... [August 19 02:58:25 UTC]
[02:58:25] Trying to send all finished work units
[02:58:25] Project: 6702 (Run 7, Clone 96, Gen 26)


[02:58:25] + Attempting to send results [August 19 02:58:25 UTC]
[02:58:25] - Reading file work/wuresults_07.dat from core
[02:58:25]   (Read 43619599 bytes from disk)
[02:58:25] Connecting to http://171.64.65.56:8080/
[03:02:52] Completed 420000 out of 500000 steps  (84%)
[03:10:55] Completed 425000 out of 500000 steps  (85%)
[03:18:58] Completed 430000 out of 500000 steps  (86%)
[03:24:25] Posted data.
[03:24:26] Initial: 0000; - Uploaded at ~27 kB/s
[03:24:26] - Averaged speed for that direction ~30 kB/s
[03:24:26] + Results successfully sent
[03:24:26] Thank you for your contribution to Folding@Home.
[03:24:26] + Number of Units Completed: 12

[03:24:27] + Sent 1 of 1 completed units to the server
[03:24:27] - Autosend completed
[03:27:00] Completed 435000 out of 500000 steps  (87%)
[03:35:01] Completed 440000 out of 500000 steps  (88%)
[03:43:01] Completed 445000 out of 500000 steps  (89%)
[03:51:03] Completed 450000 out of 500000 steps  (90%)
[03:59:03] Completed 455000 out of 500000 steps  (91%)
[04:07:01] Completed 460000 out of 500000 steps  (92%)
[04:14:58] Completed 465000 out of 500000 steps  (93%)
[04:22:55] Completed 470000 out of 500000 steps  (94%)
[04:30:54] Completed 475000 out of 500000 steps  (95%)
[04:39:01] Completed 480000 out of 500000 steps  (96%)
[04:47:09] Completed 485000 out of 500000 steps  (97%)
[04:55:15] Completed 490000 out of 500000 steps  (98%)
[05:03:23] Completed 495000 out of 500000 steps  (99%)
[05:11:32] Completed 500000 out of 500000 steps  (100%)
[05:11:33] DynamicWrapper: Finished Work Unit: sleep=10000
[05:11:43] 
[05:11:43] Finished Work Unit:
[05:11:43] - Reading up to 3700368 from "work/wudata_08.trr": Read 

3700368
[05:11:43] trr file hash check passed.
[05:11:43] edr file hash check passed.
[05:11:43] logfile size: 59026
[05:11:43] Leaving Run
[05:11:47] - Writing 3794946 bytes of core data to disk...
[05:11:47]   ... Done.
[05:11:48] - Shutting down core
Veeery interesting. Seems that Langouste got confused and thought
your GPU clients were folding while, in fact, they were not.
Still, that doesn't explain the busy loop which should not have
happened and probably is a client bug...

Couple questions from me:
1) What Langouste version are you using?
2) Are you using upload capping? (-r parameter)
3) Can you please confirm it's the client (not FahCore) that's consuming CPU cycles?
4) What Windows flavor are you using? (is it Vista/7?)
5) Did you configure GPU clients to use proxy at 127.0.0.1 or was it "localhost"?
Blasphemous Cannibal wrote:tear, can you tell me how to extract the Langouste logs please? btw I have no intention to stop using Langouste on my SMP clients but I've stopped using the proxy on the GPU's for now.
Fair enough.

Re log extraction -- there are two techniques:
1) Copying the log off Langouste's console window -- left-click the icon on window's title bar, then "Edit" -> "Mark"; to mark press left mouse button and drag, then press enter -- doing so will copy the text to clipboard
2) Using Langouste with "-L logfile.txt" parameter (Langouste's own logging), you'd need to reproduce the issue and capture fresh log(s) though...
Blasphemous Cannibal wrote: EDIT: tear, I've checked in the temp folder you directed weedacres to & the last helperfile was at 19:30 yesterday.
Ok, I don't think I need to look at any of them at this time.


There are two possible paths we can venture:
1) You decide that determining source of the issue is not worth potential benefit
2) You decide you want to find out what the problem is

Let me know and we'll proceed accordingly :-)



Thanks,
Kris
One man's ceiling is another man's floor.
Image
7im
Posts: 10179
Joined: Thu Nov 29, 2007 4:30 pm
Hardware configuration: Intel i7-4770K @ 4.5 GHz, 16 GB DDR3-2133 Corsair Vengence (black/red), EVGA GTX 760 @ 1200 MHz, on an Asus Maximus VI Hero MB (black/red), in a blacked out Antec P280 Tower, with a Xigmatek Night Hawk (black) HSF, Seasonic 760w Platinum (black case, sleeves, wires), 4 SilenX 120mm Case fans with silicon fan gaskets and silicon mounts (all black), a 512GB Samsung SSD (black), and a 2TB Black Western Digital HD (silver/black).
Location: Arizona
Contact:

Re: Langouste -- WU upload/download de-coupler (+upload capping)

Post by 7im »

tear wrote:
7im wrote:It would be better to wait for the download to finish, ADD 1 minute, and then upload.
Nope, I'm not going to (implicitly) accept poor programming or insufficient hardware resources. You haven't met me yesterday, have you?

tear
Well, if that's the approach you are going to take, why wait 1 minute at all? That's 10 points off my bonus! :roll:
How to provide enough information to get helpful support
Tell me and I forget. Teach me and I remember. Involve me and I learn.
Post Reply