Merge pull request #4 from SESYNC-ci/extensions

Now on CRAN.

.Rbuildignore

@@ -1,4 +1,5 @@
 ^.*\.Rproj$
 ^\.Rproj\.user$
 ^\.travis\.yml$
-cran-comments.md
+^cran-comments\.md
+^release\.R

.gitignore

@@ -1,4 +1,3 @@
 .Rproj.user
 .Rhistory
 .RData
-inst/doc

.travis.yml

@@ -1,6 +1,8 @@
 language: r
 warnings_are_errors: true
 sudo: required
+r_build_args: "--no-build-vignettes"
+r_check_args: "--no-vignettes --as-cran"
 
 env:
  global:

DESCRIPTION

@@ -1,10 +1,10 @@
 Package: rslurm
 Type: Package
 Title: Submit R Calculations to a 'SLURM' Cluster
-Description: Functions that simplify the R interface the 'SLURM' cluster workload 
-    manager, and automate the process of dividing a parallel calculation across 
-    cluster nodes.
-Version: 0.3.2
+Description: Functions that simplify submitting R scripts to a 'SLURM' cluster
+    workload manager, in part by automating the division of embarrassingly parallel
+    calculations across cluster nodes.
+Version: 0.3.3
 License: GPL-3
 URL: https://github.com/SESYNC-ci/rslurm
 BugReports: https://github.com/SESYNC-ci/rslurm/issues
@@ -18,7 +18,8 @@ Imports:
     parallel,
     whisker (>= 0.3)
 RoxygenNote: 6.0.1
-Suggests: testthat,
+Suggests:
+    testthat,
     knitr,
     rmarkdown
 VignetteBuilder: knitr

R/get_slurm_out.R

@@ -27,7 +27,9 @@
 get_slurm_out <- function(slr_job, outtype = "raw", wait = TRUE) {
 
     # Check arguments
-    if (!(class(slr_job) == "slurm_job")) stop("slr_job must be a slurm_job")
+    if (!(class(slr_job) == "slurm_job")) {
+        stop("slr_job must be a slurm_job")
+    }
     outtypes <- c("table", "raw")
     if (!(outtype %in% outtypes)) {
         stop(paste("outtype should be one of:", paste(outtypes, collapse = ', ')))
@@ -37,9 +39,11 @@ get_slurm_out <- function(slr_job, outtype = "raw", wait = TRUE) {
     }
 
     # Wait for slr_job using SLURM dependency
-    if (wait) wait_for_job(slr_job)
+    if (wait) {
+        wait_for_job(slr_job)
+    }
 
-    res_files <- paste0("results_", 0:(slr_job$nodes - 1), ".RData")
+    res_files <- paste0("results_", 0:(slr_job$nodes - 1), ".RDS")
     tmpdir <- paste0("_rslurm_", slr_job$jobname)
     missing_files <- setdiff(res_files, dir(path = tmpdir))
     if (length(missing_files) > 0) {

R/rslurm.R

@@ -1,8 +1,3 @@
-#' rslurm: Submit R calculations to a SLURM cluster
-#'
-#' This package automates the process of sending simple function calls or 
-#' parallel calculations to a cluster using the SLURM workload manager.
-#' 
 #' @section Overview:
 #' This package includes two core functions used to send computations to a 
 #' SLURM cluster. While \code{\link{slurm_call}} executes a function using a
@@ -19,7 +14,7 @@
 #' \code{\link{get_slurm_out}} and \code{\link{cleanup_files}}.
 #' 
 #' For bug reports or questions about this package, contact 
-#' Philippe Marchand (pmarchand@@sesync.org).
+#' Ian Carroll(icarroll@sesync.org).
 #' 
 #' @section Function Specification:
 #' To be compatible with \code{\link{slurm_apply}}, a function may accept
@@ -65,9 +60,10 @@
 #' cleanup_files(sjob1)
 #' }
 #' 
-#' @docType package
-#' @name rslurm-package
-#' @aliases rslurm
+#' @section Acknowledgement:
+#' Development of this R package was supported by the National
+#' Socio-Environmental Synthesis Center (SESYNC) under funding received
+#' from the National Science Foundation DBI-1052875.
 #' 
 #' @importFrom utils capture.output
-NULL
+"_PACKAGE"

R/slurm_apply.R

@@ -4,8 +4,8 @@
 #' parameters in parallel, spread across multiple nodes of a SLURM cluster. 
 #' 
 #' This function creates a temporary folder ("_rslurm_[jobname]") in the current
-#' directory, holding the .RData files, the R script and the Bash submission 
-#' script generated for the SLURM job. 
+#' directory, holding .RData and .RDS data files, the R script to run and the Bash
+#' submission script generated for the SLURM job. 
 #' 
 #' The set of input parameters is divided in equal chunks sent to each node, and 
 #' \code{f} is evaluated in parallel within each node using functions from the
@@ -23,7 +23,7 @@
 #' 
 #' When processing the computation job, the SLURM cluster will output two types
 #' of files in the temporary folder: those containing the return values of the
-#' function for each subset of parameters ("results_[node_id].RData") and those
+#' function for each subset of parameters ("results_[node_id].RDS") and those
 #' containing any console or error output produced by R on each node
 #' ("slurm_[node_id].out").
 #' 
@@ -100,9 +100,9 @@ slurm_apply <- function(f, params, jobname = NA, nodes = 2, cpus_per_node = 2,
 
     # Create temp folder
     tmpdir <- paste0("_rslurm_", jobname)
-    dir.create(tmpdir)
+    dir.create(tmpdir, showWarnings = FALSE)
 
-    saveRDS(params, file = file.path(tmpdir, "params.RData"))
+    saveRDS(params, file = file.path(tmpdir, "params.RDS"))
     if (!is.null(add_objects)) {
         save(list = add_objects, file = file.path(tmpdir, "add_objects.RData"))
     }    
@@ -142,6 +142,10 @@ slurm_apply <- function(f, params, jobname = NA, nodes = 2, cpus_per_node = 2,
     writeLines(script_sh, file.path(tmpdir, "submit.sh"))
 
     # Submit job to SLURM if applicable
+    if (submit && system('squeue', ignore.stdout = TRUE)) {
+        submit <- FALSE
+        cat("Cannot submit; no SLURM workload manager on path\n")
+    }
     if (submit) {
         jobid <- submit_slurm_job(tmpdir)
     } else {

R/slurm_call.R

@@ -4,8 +4,8 @@
 #' cluster. 
 #' 
 #' This function creates a temporary folder ("_rslurm_[jobname]") in the current
-#' directory, holding the .RData files, the R script and the Bash submission 
-#' script generated for the SLURM job. 
+#' directory, holding .RData and .RDS data files, the R script to run and the Bash
+#' submission script generated for the SLURM job. 
 #' 
 #' The names of any other R objects (besides \code{params}) that \code{f} needs 
 #' to access should be listed in the \code{add_objects} argument.
@@ -20,7 +20,7 @@
 #' 
 #' When processing the computation job, the SLURM cluster will output two files 
 #' in the temporary folder: one with the return value of the function 
-#' ("results_0.RData") and one containing any console or error output produced 
+#' ("results_0.RDS") and one containing any console or error output produced 
 #' by R ("slurm_[node_id].out").
 #' 
 #' If \code{submit = TRUE}, the job is sent to the cluster and a confirmation
@@ -74,9 +74,9 @@ slurm_call <- function(f, params, jobname = NA, add_objects = NULL,
 
     # Create temp folder
     tmpdir <- paste0("_rslurm_", jobname)
-    dir.create(tmpdir)
+    dir.create(tmpdir, showWarnings = FALSE)
 
-    saveRDS(params, file = file.path(tmpdir, "params.RData"))
+    saveRDS(params, file = file.path(tmpdir, "params.RDS"))
     if (!is.null(add_objects)) {
         save(list = add_objects, file = file.path(tmpdir, "add_objects.RData"))
     }    
@@ -103,6 +103,10 @@ slurm_call <- function(f, params, jobname = NA, add_objects = NULL,
     writeLines(script_sh, file.path(tmpdir, "submit.sh"))
 
     # Submit job to SLURM if applicable
+    if (system('squeue', ignore.stdout = TRUE)) {
+        submit <- FALSE
+        cat("Cannot submit; no SLURM workload manager on path\n")
+    }
     if (submit) {
         jobid <- submit_slurm_job(tmpdir)
     } else {

R/slurm_job.R

@@ -16,10 +16,7 @@
 #' @return A \code{slurm_job} object.
 #' @export
 slurm_job <- function(jobname, nodes, jobid) {
-    slr_job <- list(jobname = jobname, nodes = nodes)
-    if (!missing(jobid)) {
-        slr_job$jobid <- as.integer(jobid)
-    }
+    slr_job <- list(jobname = jobname, nodes = nodes, jobid = jobid)
     class(slr_job) <- "slurm_job"
     slr_job
 }

R/slurm_utils.R

@@ -7,7 +7,8 @@ func_to_str <- function(f) {
 }
 
 
-# Make jobname by cleaning user-provided name or (if NA) generate one from clock
+# Make jobname by cleaning user-provided name or (if NA) generate one
+# from base::tempfile
 make_jobname <- function(name) {
     if (is.na(name)) {
         tmpfile <- tempfile("_rslurm_", tmpdir=".")
@@ -47,7 +48,9 @@ local_slurm_array <- function(slr_job) {
                      "Sys.setenv(SLURM_ARRAY_TASK_ID = i)",
                      "source('slurm_run.R')", "}"), "local_run.R")
         system(paste(rscript_path, "--vanilla local_run.R"))
+        slr_job$jobid = 0L
     }, finally = setwd(olddir))
+    return(slr_job)
 }
 
 # Submit job capturing jobid