Skip to content

Commit

Permalink
Merge pull request #5 from mahendrapaipuri/use_uid_gid_in_labels
Browse files Browse the repository at this point in the history 
Use UID and GID to job labels
  • Loading branch information
@mahendrapaipuri
mahendrapaipuri authored Nov 20, 2023
2 parents a71fd5f + 9b154d2 commit 4135ca2
Show file tree
Hide file tree
Showing 7 changed files with 110 additions and 83 deletions.
24 changes: 12 additions & 12 deletions collector/fixtures/e2e-test-cgroupsv1-output.txt
View file
Original file line number Diff line number Diff line change
@@ -1,44 +1,44 @@
# HELP batchjob_cpu_system_seconds Cumulative CPU system seconds
# TYPE batchjob_cpu_system_seconds gauge
batchjob_cpu_system_seconds{batch="slurm",jobid="1009248",step="",task="",ujobid="557d568b88bfc87489dbea91de6da689"} 0.45
batchjob_cpu_system_seconds{batch="slurm",jobgid="1000",jobid="1009248",jobuid="1000",jobuuid="8d4fad6d-c5e3-775b-8a8c-707e319114ec",step="",task=""} 0.45
# HELP batchjob_cpu_total_seconds Cumulative CPU total seconds
# TYPE batchjob_cpu_total_seconds gauge
batchjob_cpu_total_seconds{batch="slurm",jobid="1009248",step="",task="",ujobid="557d568b88bfc87489dbea91de6da689"} 1.012410966
batchjob_cpu_total_seconds{batch="slurm",jobgid="1000",jobid="1009248",jobuid="1000",jobuuid="8d4fad6d-c5e3-775b-8a8c-707e319114ec",step="",task=""} 1.012410966
# HELP batchjob_cpu_user_seconds Cumulative CPU user seconds
# TYPE batchjob_cpu_user_seconds gauge
batchjob_cpu_user_seconds{batch="slurm",jobid="1009248",step="",task="",ujobid="557d568b88bfc87489dbea91de6da689"} 0.39
batchjob_cpu_user_seconds{batch="slurm",jobgid="1000",jobid="1009248",jobuid="1000",jobuuid="8d4fad6d-c5e3-775b-8a8c-707e319114ec",step="",task=""} 0.39
# HELP batchjob_cpus Number of CPUs
# TYPE batchjob_cpus gauge
batchjob_cpus{batch="slurm",jobid="1009248",step="",task="",ujobid="557d568b88bfc87489dbea91de6da689"} 0
batchjob_cpus{batch="slurm",jobgid="1000",jobid="1009248",jobuid="1000",jobuuid="8d4fad6d-c5e3-775b-8a8c-707e319114ec",step="",task=""} 0
# HELP batchjob_exporter_build_info A metric with a constant '1' value labeled by version, revision, branch, goversion from which batchjob_exporter was built, and the goos and goarch for the build.
# TYPE batchjob_exporter_build_info gauge
# HELP batchjob_ipmi_dcmi_watts_total Current Power consumption in watts
# TYPE batchjob_ipmi_dcmi_watts_total counter
batchjob_ipmi_dcmi_watts_total 332
# HELP batchjob_memory_cache_bytes Memory cache used in bytes
# TYPE batchjob_memory_cache_bytes gauge
batchjob_memory_cache_bytes{batch="slurm",jobid="1009248",step="",task="",ujobid="557d568b88bfc87489dbea91de6da689"} 2.1086208e+07
batchjob_memory_cache_bytes{batch="slurm",jobgid="1000",jobid="1009248",jobuid="1000",jobuuid="8d4fad6d-c5e3-775b-8a8c-707e319114ec",step="",task=""} 2.1086208e+07
# HELP batchjob_memory_fail_count Memory fail count
# TYPE batchjob_memory_fail_count gauge
batchjob_memory_fail_count{batch="slurm",jobid="1009248",step="",task="",ujobid="557d568b88bfc87489dbea91de6da689"} 0
batchjob_memory_fail_count{batch="slurm",jobgid="1000",jobid="1009248",jobuid="1000",jobuuid="8d4fad6d-c5e3-775b-8a8c-707e319114ec",step="",task=""} 0
# HELP batchjob_memory_rss_bytes Memory RSS used in bytes
# TYPE batchjob_memory_rss_bytes gauge
batchjob_memory_rss_bytes{batch="slurm",jobid="1009248",step="",task="",ujobid="557d568b88bfc87489dbea91de6da689"} 1.0407936e+07
batchjob_memory_rss_bytes{batch="slurm",jobgid="1000",jobid="1009248",jobuid="1000",jobuuid="8d4fad6d-c5e3-775b-8a8c-707e319114ec",step="",task=""} 1.0407936e+07
# HELP batchjob_memory_total_bytes Memory total in bytes
# TYPE batchjob_memory_total_bytes gauge
batchjob_memory_total_bytes{batch="slurm",jobid="1009248",step="",task="",ujobid="557d568b88bfc87489dbea91de6da689"} 2.01362030592e+11
batchjob_memory_total_bytes{batch="slurm",jobgid="1000",jobid="1009248",jobuid="1000",jobuuid="8d4fad6d-c5e3-775b-8a8c-707e319114ec",step="",task=""} 2.01362030592e+11
# HELP batchjob_memory_used_bytes Memory used in bytes
# TYPE batchjob_memory_used_bytes gauge
batchjob_memory_used_bytes{batch="slurm",jobid="1009248",step="",task="",ujobid="557d568b88bfc87489dbea91de6da689"} 4.0194048e+07
batchjob_memory_used_bytes{batch="slurm",jobgid="1000",jobid="1009248",jobuid="1000",jobuuid="8d4fad6d-c5e3-775b-8a8c-707e319114ec",step="",task=""} 4.0194048e+07
# HELP batchjob_memsw_fail_count Swap fail count
# TYPE batchjob_memsw_fail_count gauge
batchjob_memsw_fail_count{batch="slurm",jobid="1009248",step="",task="",ujobid="557d568b88bfc87489dbea91de6da689"} 0
batchjob_memsw_fail_count{batch="slurm",jobgid="1000",jobid="1009248",jobuid="1000",jobuuid="8d4fad6d-c5e3-775b-8a8c-707e319114ec",step="",task=""} 0
# HELP batchjob_memsw_total_bytes Swap total in bytes
# TYPE batchjob_memsw_total_bytes gauge
batchjob_memsw_total_bytes{batch="slurm",jobid="1009248",step="",task="",ujobid="557d568b88bfc87489dbea91de6da689"} 9.223372036854772e+18
batchjob_memsw_total_bytes{batch="slurm",jobgid="1000",jobid="1009248",jobuid="1000",jobuuid="8d4fad6d-c5e3-775b-8a8c-707e319114ec",step="",task=""} 9.223372036854772e+18
# HELP batchjob_memsw_used_bytes Swap used in bytes
# TYPE batchjob_memsw_used_bytes gauge
batchjob_memsw_used_bytes{batch="slurm",jobid="1009248",step="",task="",ujobid="557d568b88bfc87489dbea91de6da689"} 4.032512e+07
batchjob_memsw_used_bytes{batch="slurm",jobgid="1000",jobid="1009248",jobuid="1000",jobuuid="8d4fad6d-c5e3-775b-8a8c-707e319114ec",step="",task=""} 4.032512e+07
# HELP batchjob_nvidia_gpu_jobid Batch Job ID of current nVIDIA GPU
# TYPE batchjob_nvidia_gpu_jobid gauge
batchjob_nvidia_gpu_jobid{uuid="GPU-61a65011-6571-a6d2-5ab8-66cbb6f7f9c3"} 11000
Expand Down
24 changes: 12 additions & 12 deletions collector/fixtures/e2e-test-cgroupsv2-output.txt
View file
Original file line number Diff line number Diff line change
@@ -1,44 +1,44 @@
# HELP batchjob_cpu_system_seconds Cumulative CPU system seconds
# TYPE batchjob_cpu_system_seconds gauge
batchjob_cpu_system_seconds{batch="slurm",jobid="1009248",step="",task="",ujobid="557d568b88bfc87489dbea91de6da689"} 115.777502
batchjob_cpu_system_seconds{batch="slurm",jobgid="1000",jobid="1009248",jobuid="1000",jobuuid="8d4fad6d-c5e3-775b-8a8c-707e319114ec",step="",task=""} 115.777502
# HELP batchjob_cpu_total_seconds Cumulative CPU total seconds
# TYPE batchjob_cpu_total_seconds gauge
batchjob_cpu_total_seconds{batch="slurm",jobid="1009248",step="",task="",ujobid="557d568b88bfc87489dbea91de6da689"} 60491.070351
batchjob_cpu_total_seconds{batch="slurm",jobgid="1000",jobid="1009248",jobuid="1000",jobuuid="8d4fad6d-c5e3-775b-8a8c-707e319114ec",step="",task=""} 60491.070351
# HELP batchjob_cpu_user_seconds Cumulative CPU user seconds
# TYPE batchjob_cpu_user_seconds gauge
batchjob_cpu_user_seconds{batch="slurm",jobid="1009248",step="",task="",ujobid="557d568b88bfc87489dbea91de6da689"} 60375.292848
batchjob_cpu_user_seconds{batch="slurm",jobgid="1000",jobid="1009248",jobuid="1000",jobuuid="8d4fad6d-c5e3-775b-8a8c-707e319114ec",step="",task=""} 60375.292848
# HELP batchjob_cpus Number of CPUs
# TYPE batchjob_cpus gauge
batchjob_cpus{batch="slurm",jobid="1009248",step="",task="",ujobid="557d568b88bfc87489dbea91de6da689"} 2
batchjob_cpus{batch="slurm",jobgid="1000",jobid="1009248",jobuid="1000",jobuuid="8d4fad6d-c5e3-775b-8a8c-707e319114ec",step="",task=""} 2
# HELP batchjob_exporter_build_info A metric with a constant '1' value labeled by version, revision, branch, goversion from which batchjob_exporter was built, and the goos and goarch for the build.
# TYPE batchjob_exporter_build_info gauge
# HELP batchjob_ipmi_dcmi_watts_total Current Power consumption in watts
# TYPE batchjob_ipmi_dcmi_watts_total counter
batchjob_ipmi_dcmi_watts_total 332
# HELP batchjob_memory_cache_bytes Memory cache used in bytes
# TYPE batchjob_memory_cache_bytes gauge
batchjob_memory_cache_bytes{batch="slurm",jobid="1009248",step="",task="",ujobid="557d568b88bfc87489dbea91de6da689"} 0
batchjob_memory_cache_bytes{batch="slurm",jobgid="1000",jobid="1009248",jobuid="1000",jobuuid="8d4fad6d-c5e3-775b-8a8c-707e319114ec",step="",task=""} 0
# HELP batchjob_memory_fail_count Memory fail count
# TYPE batchjob_memory_fail_count gauge
batchjob_memory_fail_count{batch="slurm",jobid="1009248",step="",task="",ujobid="557d568b88bfc87489dbea91de6da689"} 0
batchjob_memory_fail_count{batch="slurm",jobgid="1000",jobid="1009248",jobuid="1000",jobuuid="8d4fad6d-c5e3-775b-8a8c-707e319114ec",step="",task=""} 0
# HELP batchjob_memory_rss_bytes Memory RSS used in bytes
# TYPE batchjob_memory_rss_bytes gauge
batchjob_memory_rss_bytes{batch="slurm",jobid="1009248",step="",task="",ujobid="557d568b88bfc87489dbea91de6da689"} 4.098592768e+09
batchjob_memory_rss_bytes{batch="slurm",jobgid="1000",jobid="1009248",jobuid="1000",jobuuid="8d4fad6d-c5e3-775b-8a8c-707e319114ec",step="",task=""} 4.098592768e+09
# HELP batchjob_memory_total_bytes Memory total in bytes
# TYPE batchjob_memory_total_bytes gauge
batchjob_memory_total_bytes{batch="slurm",jobid="1009248",step="",task="",ujobid="557d568b88bfc87489dbea91de6da689"} 4.294967296e+09
batchjob_memory_total_bytes{batch="slurm",jobgid="1000",jobid="1009248",jobuid="1000",jobuuid="8d4fad6d-c5e3-775b-8a8c-707e319114ec",step="",task=""} 4.294967296e+09
# HELP batchjob_memory_used_bytes Memory used in bytes
# TYPE batchjob_memory_used_bytes gauge
batchjob_memory_used_bytes{batch="slurm",jobid="1009248",step="",task="",ujobid="557d568b88bfc87489dbea91de6da689"} 4.111491072e+09
batchjob_memory_used_bytes{batch="slurm",jobgid="1000",jobid="1009248",jobuid="1000",jobuuid="8d4fad6d-c5e3-775b-8a8c-707e319114ec",step="",task=""} 4.111491072e+09
# HELP batchjob_memsw_fail_count Swap fail count
# TYPE batchjob_memsw_fail_count gauge
batchjob_memsw_fail_count{batch="slurm",jobid="1009248",step="",task="",ujobid="557d568b88bfc87489dbea91de6da689"} 0
batchjob_memsw_fail_count{batch="slurm",jobgid="1000",jobid="1009248",jobuid="1000",jobuuid="8d4fad6d-c5e3-775b-8a8c-707e319114ec",step="",task=""} 0
# HELP batchjob_memsw_total_bytes Swap total in bytes
# TYPE batchjob_memsw_total_bytes gauge
batchjob_memsw_total_bytes{batch="slurm",jobid="1009248",step="",task="",ujobid="557d568b88bfc87489dbea91de6da689"} 0
batchjob_memsw_total_bytes{batch="slurm",jobgid="1000",jobid="1009248",jobuid="1000",jobuuid="8d4fad6d-c5e3-775b-8a8c-707e319114ec",step="",task=""} 0
# HELP batchjob_memsw_used_bytes Swap used in bytes
# TYPE batchjob_memsw_used_bytes gauge
batchjob_memsw_used_bytes{batch="slurm",jobid="1009248",step="",task="",ujobid="557d568b88bfc87489dbea91de6da689"} 0
batchjob_memsw_used_bytes{batch="slurm",jobgid="1000",jobid="1009248",jobuid="1000",jobuuid="8d4fad6d-c5e3-775b-8a8c-707e319114ec",step="",task=""} 0
# HELP batchjob_nvidia_gpu_jobid Batch Job ID of current nVIDIA GPU
# TYPE batchjob_nvidia_gpu_jobid gauge
batchjob_nvidia_gpu_jobid{uuid="GPU-61a65011-6571-a6d2-5ab8-66cbb6f7f9c3"} 11000
Expand Down
Loading

0 comments on commit 4135ca2

Please sign in to comment.