drivers/raw_exec: enable setting cgroup override values (#20481)

* drivers/raw_exec: enable setting cgroup override values

This PR enables configuration of cgroup override values on the `raw_exec`
task driver. WARNING: setting cgroup override values eliminates any
gauruntee Nomad can make about resource availability for *any* task on
the client node.

For cgroup v2 systems, set a single unified cgroup path using `cgroup_v2_override`.
The path may be either absolute or relative to the cgroup root.

config {
  cgroup_v2_override = "custom.slice/app.scope"
}

or

config {
  cgroup_v2_override = "/sys/fs/cgroup/custom.slice/app.scope"
}

For cgroup v1 systems, set a per-controller path for each controller using
`cgroup_v1_override`. The path(s) may be either absolute or relative to
the controller root.

config {
  cgroup_v1_override = {
    "pids": "custom/app",
    "cpuset": "custom/app",
  }
}

or

config {
  cgroup_v1_override = {
    "pids": "/sys/fs/cgroup/pids/custom/app",
    "cpuset": "/sys/fs/cgroup/cpuset/custom/app",
  }
}

* drivers/rawexec: ensure only one of v1/v2 cgroup override is set

* drivers/raw_exec: executor should error if setting cgroup does not work

* drivers/raw_exec: create cgroups in raw_exec tests

* drivers/raw_exec: ensure we fail to start if custom cgroup set and non-root

* move custom cgroup func into shared file

---------

Co-authored-by: Michael Schurter <mschurter@hashicorp.com>
This commit is contained in:
Seth Hoenig
2024-05-07 19:46:27 -04:00
committed by GitHub
parent 5041460043
commit 14a022cbc0
16 changed files with 430 additions and 84 deletions

View File

@@ -27,6 +27,7 @@ import (
"github.com/hashicorp/nomad/client/config"
consulclient "github.com/hashicorp/nomad/client/consul"
"github.com/hashicorp/nomad/client/devicemanager"
"github.com/hashicorp/nomad/client/lib/cgroupslib"
"github.com/hashicorp/nomad/client/lib/proclib"
"github.com/hashicorp/nomad/client/pluginmanager/drivermanager"
regMock "github.com/hashicorp/nomad/client/serviceregistration/mock"
@@ -107,7 +108,15 @@ func testTaskRunnerConfig(t *testing.T, alloc *structs.Allocation, taskName stri
}
taskDir := allocDir.NewTaskDir(taskName)
// Create cgroup
f := cgroupslib.Factory(alloc.ID, taskName, false)
must.NoError(t, f.Setup())
trCleanup := func() {
// destroy and remove the cgroup
_ = f.Kill()
_ = f.Teardown()
// destroy the alloc dir
if err := allocDir.Destroy(); err != nil {
t.Logf("error destroying alloc dir: %v", err)
}
@@ -189,6 +198,7 @@ func runTestTaskRunner(t *testing.T, alloc *structs.Allocation, taskName string)
}
tr, err := NewTaskRunner(config)
require.NoError(t, err)
go tr.Run()