sbatch
job_single(
name = "my_shell_script", memory = "10G", cores = 2, create_shell = FALSE
)
-#> 2023-10-10 16:14:48.792008 creating the logs directory at: logs
+#> 2023-10-10 17:29:56.073699 creating the logs directory at: logs
#> #!/bin/bash
#> #SBATCH -p shared
#> #SBATCH --mem-per-cpu=10G
@@ -249,7 +249,7 @@ Creating Shell Scripts to sbatch
name = "my_array_job", memory = "5G", cores = 1, create_shell = FALSE,
task_num = 10
)
-#> 2023-10-10 16:14:48.876895 creating the logs directory at: logs
+#> 2023-10-10 17:29:56.172312 creating the logs directory at: logs
#> #!/bin/bash
#> #SBATCH -p shared
#> #SBATCH --mem-per-cpu=5G
@@ -388,8 +388,8 @@ Submitting and Resubmitting Jobs name = "my_array_job", memory = "5G", cores = 1, create_shell = TRUE,
task_num = 10
)
-#> 2023-10-10 16:14:49.664747 creating the logs directory at: logs
-#> 2023-10-10 16:14:49.6662 creating the shell file my_array_job.sh
+#> 2023-10-10 17:29:57.081484 creating the logs directory at: logs
+#> 2023-10-10 17:29:57.083036 creating the shell file my_array_job.sh
#> To submit the job use: sbatch my_array_job.sh
# Suppose that tasks 3, 6, 7, and 8 failed
@@ -460,6 +460,56 @@ Monitoring Running Jobs#> 1 60 2
+Monitoring Partitions
+
+Sometimes, it’s useful to know about the partitions as a whole rather
+than about specific jobs. partition_info() serves this
+purpose, and parses sinfo output into a
+tibble. We’ll load an example of the output from
+partition_info(partition = NULL, all_nodes = FALSE).
+
+print(partition_df)
+#> # A tibble: 5 × 7
+#> partition free_cpus total_cpus prop_free_cpus free_mem_gb total_mem_gb
+#> <chr> <int> <int> <dbl> <dbl> <dbl>
+#> 1 partition_1 48 48 1 126. 128.
+#> 2 partition_2 324 384 0.844 1050. 1643.
+#> 3 partition_3 48 48 1 127. 128.
+#> 4 partition_4 412 1024 0.402 2806. 4126.
+#> 5 partition_5 76 128 0.594 519. 1000.
+#> # ℹ 1 more variable: prop_free_mem_gb <dbl>
+Since all_nodes was FALSE, there’s one row
+per partition, summarizing information across all nodes that compose
+each partition. Alternatively, set all_nodes to
+TRUE to yield one row per node.
+With partition_df, let’s summarize how busy the cluster
+is as a whole, then rank partitions by amount of free memory.
+
+# Print the proportion of CPUs and memory available for the whole cluster
+partition_df |>
+ summarize(
+ prop_free_cpus = sum(free_cpus) / sum(total_cpus),
+ prop_free_mem_gb = sum(free_mem_gb) / sum(total_mem_gb)
+ ) |>
+ print()
+#> # A tibble: 1 × 2
+#> prop_free_cpus prop_free_mem_gb
+#> <dbl> <dbl>
+#> 1 0.556 0.659
+
+# Now let's take the top 3 partitions by memory currently available
+partition_df |>
+ arrange(desc(free_mem_gb)) |>
+ select(partition, free_mem_gb) |>
+ slice_head(n = 3)
+#> # A tibble: 3 × 2
+#> partition free_mem_gb
+#> <chr> <dbl>
+#> 1 partition_4 2806.
+#> 2 partition_2 1050.
+#> 3 partition_5 519.
+
+
Analyzing Finished Jobs
The job_report() function returns in-depth information
@@ -480,7 +530,7 @@
Analyzing Finished Jobsjob_report as available in the slurmjobs
package.
-
+
job_df <- readRDS(
system.file("extdata", "job_report_df.rds", package = "slurmjobs")
)
@@ -500,7 +550,7 @@ Analyzing Finished Jobs#> 10 297331 user1 broken_… shared 2 5 1.16 1.16
#> # ℹ 3 more variables: array_task_id <int>, exit_code <dbl>, status <fct>
Now let’s choose a better memory request:
-
+
stat_df <- job_df |>
# This example includes tasks that fail. We're only interested in memory
# for successfully completed tasks
@@ -556,7 +606,7 @@ Reproducibility
This package was developed using biocthis.
Code for creating the vignette
-
+
## Create the vignette
library("rmarkdown")
system.time(render("slurmjobs.Rmd", "BiocStyle::html_document"))
@@ -565,9 +615,9 @@ Reproducibilitylibrary("knitr")
knit("slurmjobs.Rmd", tangle = TRUE)
Date the vignette was generated.
-#> [1] "2023-10-10 16:14:50 UTC"
+#> [1] "2023-10-10 17:29:58 UTC"
Wallclock time spent generating the vignette.
-#> Time difference of 2.77 secs
+#> Time difference of 3.398 secs
R session information.
#> ─ Session info ───────────────────────────────────────────────────────────────────────────────────────────────────────
#> setting value
@@ -637,6 +687,7 @@ Reproducibility#> timechange 0.2.0 2023-01-11 [1] RSPM (R 4.3.0)
#> utf8 1.2.3 2023-01-31 [2] RSPM (R 4.3.0)
#> vctrs 0.6.3 2023-06-14 [2] RSPM (R 4.3.0)
+#> withr 2.5.1 2023-09-26 [2] RSPM (R 4.3.0)
#> xfun 0.40 2023-08-09 [2] RSPM (R 4.3.0)
#> xml2 1.3.5 2023-07-06 [2] RSPM (R 4.3.0)
#> yaml 2.3.7 2023-01-23 [2] RSPM (R 4.3.0)
diff --git a/pkgdown.yml b/pkgdown.yml
index 1a4f9c7..b4b670d 100644
--- a/pkgdown.yml
+++ b/pkgdown.yml
@@ -3,5 +3,5 @@ pkgdown: 2.0.7
pkgdown_sha: ~
articles:
slurmjobs: slurmjobs.html
-last_built: 2023-10-10T16:14Z
+last_built: 2023-10-10T17:29Z
diff --git a/reference/array_submit.html b/reference/array_submit.html
index 4ad1962..38e8651 100644
--- a/reference/array_submit.html
+++ b/reference/array_submit.html
@@ -141,8 +141,8 @@ Examples
submit = FALSE
)
})
-#> 2023-10-10 16:14:44.960887 creating the logs directory at: logs
-#> 2023-10-10 16:14:44.962572 creating the shell file array_submit_example_2023-10-10.sh
+#> 2023-10-10 17:29:51.568844 creating the logs directory at: logs
+#> 2023-10-10 17:29:51.570559 creating the shell file array_submit_example_2023-10-10.sh
#> To submit the job use: sbatch array_submit_example_2023-10-10.sh
#> [1] "array_submit_example_2023-10-10.sh"
diff --git a/reference/index.html b/reference/index.html
index 1c6f12c..3a78654 100644
--- a/reference/index.html
+++ b/reference/index.html
@@ -79,6 +79,10 @@ All functions job_single()
Build a SLURM job bash script
+
+
+ Example output from partition_info(partition = NULL, all_nodes = FALSE)
diff --git a/reference/partition_df.html b/reference/partition_df.html
new file mode 100644
index 0000000..5f0f86a
--- /dev/null
+++ b/reference/partition_df.html
@@ -0,0 +1,92 @@
+
+Example output from partition_info(partition = NULL, all_nodes = FALSE) — partition_df • slurmjobs
+
+
+
+
+
+
+
+
+
+
+ Example output from partition_info(partition = NULL, all_nodes = FALSE)
+ Source: R/data.R
+ partition_df.Rd
+
+
+
+ A tibble with 5 rows and 7 columns giving information about memory and CPUs
+as available at the time of creation)
+
+
+
+ partition_df
+
+
+
+ Format
+ An object of class tbl_df (inherits from tbl, data.frame) with 5 rows and 7 columns.
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
diff --git a/sitemap.xml b/sitemap.xml
index 59b7cf0..0ab055b 100644
--- a/sitemap.xml
+++ b/sitemap.xml
@@ -48,6 +48,9 @@
/reference/job_single.html
+
+ /reference/partition_df.html
+
/reference/partition_info.html