Chris Mellinger - 2019-10-29

I'm trying to run a fairly substantial model in a parallelized way. I'm
getting an error on the step where results are read back in to R after the
chains finish running. According to the output, all chains finish
successfully, but then it doesn't look like the results files get written.
Output is copied below. Any ideas on how to approach debugging this?

Thanks for any help you can provide!

Loading required package: coda

[1] "nchains: 10"

[1] "nsamples: 80000"

[1] "nadapt: 1000"

[1] "nburnin: 1000"

prime object rt

1 blue gun 0.3484571

2 red gun 0.3483569

3 blue nogun 0.3731412

4 red nogun 0.3742160

prime object condition shoot == "yes"

1 blue gun blue 0.8107618

2 red gun blue 0.6344477

3 blue nogun blue 0.3896072

4 red nogun blue 0.2314544

5 blue gun red 0.6486331

6 red gun red 0.8266590

7 blue nogun red 0.2088229

8 red nogun red 0.3713923

[1] "Starting run.jags: 2019-10-29 00:25:42"

Calling 10 simulations using the parallel method...

Following the progress of chain 1 (the program will wait for all chains

to finish before continuing):

Welcome to JAGS 4.3.0 on Tue Oct 29 00:25:54 2019

JAGS is free software and comes with ABSOLUTELY NO WARRANTY

Loading module: basemod: ok

Loading module: bugs: ok

. Loading module: wiener: ok

. Loading module: lecuyer: ok

. Loading module: dic: ok

. . Reading data file data.txt

. Compiling model graph

Resolving undeclared variables

Allocating nodes

Graph information:

Observed stochastic nodes: 133541

Unobserved stochastic nodes: 9171

Total graph size: 629924

. Reading parameter file inits1.txt

. Initializing model

. Adapting 1000

-------------------------------------------------| 1000

++++++++++++++++++++++++++++++++++++++++++++++++++ 100%

Adaptation successful

. Updating 1000

-------------------------------------------------| 1000

******** 100%

. . . . . . . . . . . . . . Updating 16000

-------------------------------------------------| 16000

******** 100%

. . . . Updating 0

. Deleting model

Following the progress of chain 3 (the program will wait for all chains

to finish before continuing):

Welcome to JAGS 4.3.0 on Tue Oct 29 00:25:54 2019

JAGS is free software and comes with ABSOLUTELY NO WARRANTY

Loading module: basemod: ok

Loading module: bugs: ok

. Loading module: wiener: ok

. Loading module: lecuyer: ok

. Loading module: dic: ok

. . Reading data file data.txt

. Compiling model graph

Resolving undeclared variables

Allocating nodes

Graph information:

Observed stochastic nodes: 133541

Unobserved stochastic nodes: 9171

Total graph size: 629924

. Reading parameter file inits3.txt

. Initializing model

. Adapting 1000

-------------------------------------------------| 1000

++++++++++++++++++++++++++++++++++++++++++++++++++ 100%

Adaptation successful

. Updating 1000

-------------------------------------------------| 1000

******** 100%

. . . . . . . . . . . . . . Updating 16000

-------------------------------------------------| 16000

******** 100%

. . . . Updating 0

. Deleting model

All chains have finished

Waiting for the CODA files to be completed...

Error in runjags.readin(directory = startinfo$directory, silent.jags =
silent.jags, :

Timed out waiting for the CODA files to be completed. You can wait for
the files to be written, and then run
results.jags("/tmp/RtmpeajGll/runjagsfilesb74435c5187e")

The file size and modification times at 2019-10-29 02:26:48 were:
sim.1/CODAchain1.txt : 0 : 2019-10-29 02:25:07, sim.2/CODAchain1.txt :
184131584 : 2019-10-29 02:24:51, sim.3/CODAchain1.txt : 0 : 2019-10-29
02:26:17, sim.4/CODAchain1.txt : 372187136 : 2019-10-29 02:24:50,
sim.5/CODAchain1.txt : 0 : 2019-10-29 02:24:54, sim.6/CODAchain1.txt : 0 :
2019-10-29 02:25:22, sim.7/CODAchain1.txt : 0 : 2019-10-29 02:25:04,
sim.8/CODAchain1.txt : 73748480 : 2019-10-29 02:24:51, sim.9/CODAchain1.txt
221855744 : 2019-10-29 02:24:50, sim.10/CODAchain1.txt : 209637376 :
2019-10-29 02:24:50. Please file a bug report (including this message) to
the runjags package author.

Calls: tryCatch ... tryCatchList -> run.jags -> extend.jags ->
runjags.readin

JAGS files were saved to the 'runjagsfiles' folder in your current

working directory

Note: Either one or more simulation(s) failed, or there was an error in

processing the results. You may be able to retrieve any successful

simulations using:

results.jags("runjagsfiles", recover.chains=TRUE)

See the help file for that function for possible options.

[1] "run.jags call ended at: 2019-10-29 02:26:50"

   user      system     elapsed

0.7529333 0.1682333 121.1302167

Execution halted

--
Chris Mellinger

 
alternate