Ilker ManapandClaude Opus 5.5
35de47444c
A Slurm message says whether the node runs slurmctld on the leader's files, slurmd configless, both or neither, and whether it is lent. The agent installs munge and Slurm from the machine's sources (22.05 or newer, for cgroup v2), writes the munge key, starts slurmd through a drop-in with --conf-server, resumes a lent node that llmgw drained and drains one that is not, never touching a drain a Slurm administrator made, and reports its version, slurmd -C, state and jobs in SlurmStatus. Told it has no part, it stops what it started. New nodes enter slurm.conf drained. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
39 lines
1012 B
Go
39 lines
1012 B
Go
package agent
|
|
|
|
import (
|
|
llmgwv1 "gitea.mynodes.xyz/ilker/llmgw/api/gen/llmgw/v1"
|
|
)
|
|
|
|
// FeatureSlurm is the agent keeping its node's part in Slurm (BACKLOG P).
|
|
const FeatureSlurm = "slurm"
|
|
|
|
// slurmMarker says llmgw started Slurm's daemons on this machine.
|
|
var slurmMarker = "/var/lib/llmgw-agent/slurm"
|
|
|
|
// setSlurmOut is where Slurm's status goes now: this session's queue, or
|
|
// nowhere between sessions.
|
|
func (a *Agent) setSlurmOut(out chan<- *llmgwv1.AgentMessage) {
|
|
a.mu.Lock()
|
|
a.slurmOut = out
|
|
a.mu.Unlock()
|
|
if out != nil {
|
|
a.slurm.Resend()
|
|
}
|
|
}
|
|
|
|
// sendSlurm queues a status without waiting: a full queue or no session
|
|
// drops it, and the next session is sent it again.
|
|
func (a *Agent) sendSlurm(st *llmgwv1.SlurmStatus) {
|
|
a.mu.Lock()
|
|
out := a.slurmOut
|
|
a.mu.Unlock()
|
|
if out == nil {
|
|
return
|
|
}
|
|
select {
|
|
case out <- &llmgwv1.AgentMessage{Msg: &llmgwv1.AgentMessage_SlurmStatus{SlurmStatus: st}}:
|
|
default:
|
|
a.log.Warn("Slurm's status not sent: the queue to the control plane is full")
|
|
}
|
|
}
|