Files
nomad/client/allocrunner/taskrunner/wrangler_hook.go
Seth Hoenig 2e1974a574 client: refactor cpuset partitioning (#18371)
* client: refactor cpuset partitioning

This PR updates the way Nomad client manages the split between tasks
that make use of resources.cpus vs. resources.cores.

Previously, each task was explicitly assigned which CPU cores they were
able to run on. Every time a task was started or destroyed, all other
tasks' cpusets would need to be updated. This was inefficient and would
crush the Linux kernel when a client would try to run ~400 or so tasks.

Now, we make use of cgroup heirarchy and cpuset inheritence to efficiently
manage cpusets.

* cr: tweaks for feedback
2023-09-12 09:11:11 -05:00

59 lines
1.5 KiB
Go

// Copyright (c) HashiCorp, Inc.
// SPDX-License-Identifier: BUSL-1.1
package taskrunner
import (
"context"
"github.com/hashicorp/go-hclog"
ifs "github.com/hashicorp/nomad/client/allocrunner/interfaces"
cifs "github.com/hashicorp/nomad/client/interfaces"
"github.com/hashicorp/nomad/client/lib/proclib"
)
const (
wranglerHookName = "procisolation"
)
// A wranglerHook provides a mechanism through which the Client can be sure any
// processes spawned by a task forcefully get killed when the task is stopped.
//
// Currently only does anything on Linux with cgroups.
type wranglerHook struct {
wranglers cifs.ProcessWranglers
task proclib.Task
log hclog.Logger
}
func newWranglerHook(
wranglers cifs.ProcessWranglers,
task, allocID string,
cores bool,
log hclog.Logger,
) *wranglerHook {
return &wranglerHook{
log: log.Named(wranglerHookName),
wranglers: wranglers,
task: proclib.Task{
AllocID: allocID,
Task: task,
Cores: cores,
},
}
}
func (*wranglerHook) Name() string {
return wranglerHookName
}
func (wh *wranglerHook) Prestart(_ context.Context, request *ifs.TaskPrestartRequest, _ *ifs.TaskPrestartResponse) error {
wh.log.Trace("setting up client process management", "task", wh.task)
return wh.wranglers.Setup(wh.task)
}
func (wh *wranglerHook) Stop(_ context.Context, request *ifs.TaskStopRequest, _ *ifs.TaskStopResponse) error {
wh.log.Trace("stopping client process mangagement", "task", wh.task)
return wh.wranglers.Destroy(wh.task)
}