Ilker ManapandClaude Opus 5.5
748f777a56
CI / test (push) Successful in 10m57s
Since 23.11 Slurm runs badly without accounting storage: the main scheduler passes every job by as InvalidAccount. slurmdbd takes MySQL or MariaDB only, so the controller's agent installs MariaDB beside it, answering that machine alone, makes the database and its user (the password made from the munge key, never on a command line), runs slurmdbd and adds the cluster, all before slurmctld. A MariaDB that was on the machine before keeps its settings. slurm.conf accounts the jobs there, with what each used from its cgroup and the cards, and the priority is multifactor again. Port 6819 joins Slurm's in the firewall. ctl slurm status and the console say whether slurmdbd runs; the install screen, server init --slurm and the guide say what is put where. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
85 lines
2.7 KiB
Go
85 lines
2.7 KiB
Go
package agent
|
|
|
|
import (
|
|
"context"
|
|
"errors"
|
|
"log/slog"
|
|
"strings"
|
|
"testing"
|
|
"time"
|
|
|
|
llmgwv1 "gitea.mynodes.xyz/ilker/llmgw/api/gen/llmgw/v1"
|
|
"gitea.mynodes.xyz/ilker/llmgw/internal/agent/slurmnode"
|
|
)
|
|
|
|
// fakeShell answers the firewall package's scripts and records what was
|
|
// installed or removed.
|
|
type fakeShell struct {
|
|
present bool
|
|
installed string
|
|
deleted bool
|
|
}
|
|
|
|
func (f *fakeShell) Run(_ context.Context, script string, stdin []byte) ([]byte, error) {
|
|
switch {
|
|
case strings.HasPrefix(script, "ip -o route get 10.0.0.140"):
|
|
return []byte("10.0.0.140 dev eth0 src 10.0.0.141 uid 0\n2: eth0 inet 10.0.0.141/24 brd 10.0.0.255 scope global eth0\n"), nil
|
|
case strings.HasPrefix(script, "sudo -n /usr/sbin/nft list table"):
|
|
if f.present {
|
|
return nil, nil
|
|
}
|
|
return nil, errors.New("no table")
|
|
case strings.Contains(script, "nft delete table") && !strings.Contains(script, "cat > "):
|
|
f.deleted, f.present = true, false
|
|
return nil, nil
|
|
case strings.HasPrefix(script, "sudo cat "):
|
|
return nil, nil
|
|
default:
|
|
f.installed, f.present = string(stdin), true
|
|
return []byte("changed\n"), nil
|
|
}
|
|
}
|
|
|
|
func TestANodeKeepsOrDropsItsFirewallAsTheClusterSays(t *testing.T) {
|
|
sh := &fakeShell{}
|
|
a := &Agent{log: slog.New(slog.DiscardHandler), fwRunner: sh, serverList: []string{"https://10.0.0.140:7443"}}
|
|
|
|
a.applyFirewall(&llmgwv1.Firewall{Enabled: true, Networks: []string{"192.168.5.0/24", "10.9.9.9"},
|
|
EnginePortsFrom: 20000, EnginePortsTo: 20999})
|
|
for _, want := range []string{"10.0.0.0/24", "192.168.5.0/24", "10.9.9.9/32", "20000-20999", "9100"} {
|
|
if !strings.Contains(sh.installed, want) {
|
|
t.Errorf("the rules lack %s:\n%s", want, sh.installed)
|
|
}
|
|
}
|
|
|
|
a.applyFirewall(&llmgwv1.Firewall{Enabled: false})
|
|
if !sh.deleted {
|
|
t.Error("turned off, the table stayed")
|
|
}
|
|
}
|
|
|
|
func TestANodeGivenAPartInSlurmLetsSlurmInFromTheClusterOnly(t *testing.T) {
|
|
sh := &fakeShell{}
|
|
a := &Agent{log: slog.New(slog.DiscardHandler), fwRunner: sh, serverList: []string{"https://10.0.0.140:7443"},
|
|
slurm: slurmnode.New(nil, nil, "", slog.New(slog.DiscardHandler))}
|
|
a.applyFirewall(&llmgwv1.Firewall{Enabled: true, EnginePortsFrom: 20000, EnginePortsTo: 20999})
|
|
if strings.Contains(sh.installed, "6817") {
|
|
t.Fatalf("Slurm's ports before the node has a part in it:\n%s", sh.installed)
|
|
}
|
|
|
|
a.slurmMessage(&llmgwv1.Slurm{Name: "node05", Node: true, ConfServer: "10.0.0.148:6817"})
|
|
deadline := time.Now().Add(5 * time.Second)
|
|
for {
|
|
a.fwMu.Lock()
|
|
got := sh.installed
|
|
a.fwMu.Unlock()
|
|
if strings.Contains(got, "6817-6819") && strings.Contains(got, "60001-63000") {
|
|
break
|
|
}
|
|
if time.Now().After(deadline) {
|
|
t.Fatalf("given a part in Slurm, the rules still lack its ports:\n%s", got)
|
|
}
|
|
time.Sleep(10 * time.Millisecond)
|
|
}
|
|
}
|