Skip to content

Commit

Permalink
feat: Support SLURM multiple daemons
Browse files Browse the repository at this point in the history
* This commit adds support to handle multiple cgroup directories that multiple SLURM daemons can create on the same physical host when it is compiled with `--enable-multiple-daemons` flag. The hostname in the cgroup directory is exposed as `cgrouphostname` label in the metrics.

* Refactor the way cgroupCollector metrics are gathered from main collectors.

* Update e2e test fixtures and outputs

Signed-off-by: Mahendra Paipuri <[email protected]>
  • Loading branch information
mahendrapaipuri committed Feb 10, 2025
1 parent 2925b75 commit dff6282
Show file tree
Hide file tree
Showing 26 changed files with 39,858 additions and 4,875 deletions.
48 changes: 48 additions & 0 deletions pkg/collector/alloy_targets_test.go
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,34 @@ import (

var (
expectedTargetsV2 = []Target{
{Targets: []string{"2009248"}, Labels: map[string]string{"__process_pid__": "56231", "service_name": "2009248"}},
{Targets: []string{"2009248"}, Labels: map[string]string{"__process_pid__": "56281", "service_name": "2009248"}},
{Targets: []string{"2009248"}, Labels: map[string]string{"__process_pid__": "3346567", "service_name": "2009248"}},
{Targets: []string{"2009248"}, Labels: map[string]string{"__process_pid__": "3346596", "service_name": "2009248"}},
{Targets: []string{"2009248"}, Labels: map[string]string{"__process_pid__": "3346674", "service_name": "2009248"}},
{Targets: []string{"2009249"}, Labels: map[string]string{"__process_pid__": "56235", "service_name": "2009249"}},
{Targets: []string{"2009249"}, Labels: map[string]string{"__process_pid__": "56236", "service_name": "2009249"}},
{Targets: []string{"2009249"}, Labels: map[string]string{"__process_pid__": "3346567", "service_name": "2009249"}},
{Targets: []string{"2009249"}, Labels: map[string]string{"__process_pid__": "46233", "service_name": "2009249"}},
{Targets: []string{"2009250"}, Labels: map[string]string{"__process_pid__": "36242", "service_name": "2009250"}},
{Targets: []string{"2009250"}, Labels: map[string]string{"__process_pid__": "56233", "service_name": "2009250"}},
{Targets: []string{"2009250"}, Labels: map[string]string{"__process_pid__": "3346567", "service_name": "2009250"}},
{Targets: []string{"2009250"}, Labels: map[string]string{"__process_pid__": "3346596", "service_name": "2009250"}},
{Targets: []string{"2009250"}, Labels: map[string]string{"__process_pid__": "3346674", "service_name": "2009250"}},
{Targets: []string{"3009248"}, Labels: map[string]string{"__process_pid__": "66231", "service_name": "3009248"}},
{Targets: []string{"3009248"}, Labels: map[string]string{"__process_pid__": "66281", "service_name": "3009248"}},
{Targets: []string{"3009248"}, Labels: map[string]string{"__process_pid__": "3346567", "service_name": "3009248"}},
{Targets: []string{"3009248"}, Labels: map[string]string{"__process_pid__": "3346596", "service_name": "3009248"}},
{Targets: []string{"3009248"}, Labels: map[string]string{"__process_pid__": "3346674", "service_name": "3009248"}},
{Targets: []string{"3009249"}, Labels: map[string]string{"__process_pid__": "66235", "service_name": "3009249"}},
{Targets: []string{"3009249"}, Labels: map[string]string{"__process_pid__": "66236", "service_name": "3009249"}},
{Targets: []string{"3009249"}, Labels: map[string]string{"__process_pid__": "3346567", "service_name": "3009249"}},
{Targets: []string{"3009249"}, Labels: map[string]string{"__process_pid__": "46233", "service_name": "3009249"}},
{Targets: []string{"3009250"}, Labels: map[string]string{"__process_pid__": "46242", "service_name": "3009250"}},
{Targets: []string{"3009250"}, Labels: map[string]string{"__process_pid__": "66233", "service_name": "3009250"}},
{Targets: []string{"3009250"}, Labels: map[string]string{"__process_pid__": "3346567", "service_name": "3009250"}},
{Targets: []string{"3009250"}, Labels: map[string]string{"__process_pid__": "3346596", "service_name": "3009250"}},
{Targets: []string{"3009250"}, Labels: map[string]string{"__process_pid__": "3346674", "service_name": "3009250"}},
{Targets: []string{"1009248"}, Labels: map[string]string{"__process_pid__": "46231", "service_name": "1009248"}},
{Targets: []string{"1009248"}, Labels: map[string]string{"__process_pid__": "46281", "service_name": "1009248"}},
{Targets: []string{"1009248"}, Labels: map[string]string{"__process_pid__": "3346567", "service_name": "1009248"}},
Expand All @@ -33,6 +61,14 @@ var (
{Targets: []string{"1009248"}, Labels: map[string]string{"__process_pid__": "46281", "service_name": "1009248"}},
{Targets: []string{"1009249"}, Labels: map[string]string{"__process_pid__": "46235", "service_name": "1009249"}},
{Targets: []string{"1009249"}, Labels: map[string]string{"__process_pid__": "46236", "service_name": "1009249"}},
{Targets: []string{"2009248"}, Labels: map[string]string{"__process_pid__": "56231", "service_name": "2009248"}},
{Targets: []string{"2009248"}, Labels: map[string]string{"__process_pid__": "56281", "service_name": "2009248"}},
{Targets: []string{"2009249"}, Labels: map[string]string{"__process_pid__": "56235", "service_name": "2009249"}},
{Targets: []string{"2009249"}, Labels: map[string]string{"__process_pid__": "56236", "service_name": "2009249"}},
{Targets: []string{"3009248"}, Labels: map[string]string{"__process_pid__": "66231", "service_name": "3009248"}},
{Targets: []string{"3009248"}, Labels: map[string]string{"__process_pid__": "66281", "service_name": "3009248"}},
{Targets: []string{"3009249"}, Labels: map[string]string{"__process_pid__": "66235", "service_name": "3009249"}},
{Targets: []string{"3009249"}, Labels: map[string]string{"__process_pid__": "66236", "service_name": "3009249"}},
}
expectedTargetsV1 = []Target{
{Targets: []string{"1009248"}, Labels: map[string]string{"__process_pid__": "46231", "service_name": "1009248"}},
Expand All @@ -41,6 +77,18 @@ var (
{Targets: []string{"1009249"}, Labels: map[string]string{"__process_pid__": "46236", "service_name": "1009249"}},
{Targets: []string{"1009250"}, Labels: map[string]string{"__process_pid__": "26242", "service_name": "1009250"}},
{Targets: []string{"1009250"}, Labels: map[string]string{"__process_pid__": "46233", "service_name": "1009250"}},
{Targets: []string{"2009248"}, Labels: map[string]string{"__process_pid__": "56231", "service_name": "2009248"}},
{Targets: []string{"2009248"}, Labels: map[string]string{"__process_pid__": "56281", "service_name": "2009248"}},
{Targets: []string{"2009249"}, Labels: map[string]string{"__process_pid__": "56235", "service_name": "2009249"}},
{Targets: []string{"2009249"}, Labels: map[string]string{"__process_pid__": "56236", "service_name": "2009249"}},
{Targets: []string{"2009250"}, Labels: map[string]string{"__process_pid__": "36242", "service_name": "2009250"}},
{Targets: []string{"2009250"}, Labels: map[string]string{"__process_pid__": "56233", "service_name": "2009250"}},
{Targets: []string{"3009248"}, Labels: map[string]string{"__process_pid__": "66231", "service_name": "3009248"}},
{Targets: []string{"3009248"}, Labels: map[string]string{"__process_pid__": "66281", "service_name": "3009248"}},
{Targets: []string{"3009249"}, Labels: map[string]string{"__process_pid__": "66235", "service_name": "3009249"}},
{Targets: []string{"3009249"}, Labels: map[string]string{"__process_pid__": "66236", "service_name": "3009249"}},
{Targets: []string{"3009250"}, Labels: map[string]string{"__process_pid__": "46242", "service_name": "3009250"}},
{Targets: []string{"3009250"}, Labels: map[string]string{"__process_pid__": "66233", "service_name": "3009250"}},
}
)

Expand Down
Loading

0 comments on commit dff6282

Please sign in to comment.