Ilker ManapandClaude Opus 5.5
a00c92648e
CI / test (push) Failing after 6m57s
Setup asks for webhooks, but one left empty was never mentioned again: a lost node or a judge down was told nobody. With no notify.webhooks in the cluster's settings, ctl status and the console's Overview say so, and how to set one. BACKLOG: the judge's refusal after a placement change, tried again on idle VMs, did not happen; a cold judge's first answer is 2-3x slower but inside its budget. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
103 lines
3.1 KiB
Go
103 lines
3.1 KiB
Go
package cli
|
|
|
|
import (
|
|
"bytes"
|
|
"io"
|
|
"net/http"
|
|
"net/http/httptest"
|
|
"os"
|
|
"strings"
|
|
"testing"
|
|
|
|
"gitea.mynodes.xyz/ilker/llmgw/internal/control/adminapi"
|
|
"github.com/spf13/cobra"
|
|
)
|
|
|
|
func TestAQueuedChangeIsNotReportedAsAnError(t *testing.T) {
|
|
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
|
|
w.WriteHeader(http.StatusAccepted)
|
|
_, _ = w.Write([]byte(`{"queued":["r1"]}`))
|
|
}))
|
|
defer srv.Close()
|
|
var out struct {
|
|
Queued []string `json:"queued"`
|
|
}
|
|
if err := newCtlClient(srv.URL).post(t.Context(), "/api/v1/restart", []byte(`{}`), &out); err != nil {
|
|
t.Fatalf("202 read as a failure: %v", err)
|
|
}
|
|
if len(out.Queued) != 1 {
|
|
t.Errorf("the body of a 202 was not read: %+v", out)
|
|
}
|
|
}
|
|
|
|
func TestStatusSaysWhoLeadsTheStoreAndWhetherTheRestKeepUp(t *testing.T) {
|
|
render := func(s adminapi.Summary) string {
|
|
cmd := &cobra.Command{}
|
|
var b bytes.Buffer
|
|
cmd.SetOut(&b)
|
|
printSummary(cmd, s)
|
|
return b.String()
|
|
}
|
|
out := render(adminapi.Summary{Store: []adminapi.StoreMember{
|
|
{Name: "llmgw-ctl02", Role: "replica", State: "streaming", Lag: 2048},
|
|
{Name: "llmgw-pg01", Role: "leader", State: "running"},
|
|
}})
|
|
if !strings.Contains(out, "STORE llmgw-ctl02 streaming (2 KB behind), llmgw-pg01 leads") {
|
|
t.Errorf("status:\n%s", out)
|
|
}
|
|
out = render(adminapi.Summary{Store: []adminapi.StoreMember{{Name: "llmgw-pg01", Role: "replica", State: "stopped"}}})
|
|
if !strings.Contains(out, "NO LEADER") {
|
|
t.Errorf("a store with no leader was not called out:\n%s", out)
|
|
}
|
|
if out := render(adminapi.Summary{}); strings.Contains(out, "STORE") {
|
|
t.Error("a single database got a store line")
|
|
}
|
|
}
|
|
|
|
func TestTheSummaryIsWrittenWhereItIsToldNotToTheTerminal(t *testing.T) {
|
|
// The console draws the summary into its panel. Its GPU table went to
|
|
// the terminal instead, through the full screen, every three seconds —
|
|
// on a cluster with a GPU, which the test cluster did not have.
|
|
r, w, err := os.Pipe()
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
stdout := os.Stdout
|
|
os.Stdout = w
|
|
var b bytes.Buffer
|
|
cmd := &cobra.Command{}
|
|
cmd.SetOut(&b)
|
|
printSummary(cmd, adminapi.Summary{
|
|
GPUs: []adminapi.ClassUse{{Class: "6000-24g", Total: 1, Used: 1}},
|
|
Fabrics: []adminapi.FabricUse{{Fabric: "ib-a", Nodes: 2}},
|
|
IdleReplicas: []adminapi.IdleReplica{{ID: "r1", Model: "m", IdleSec: 3600, GPUs: 1}},
|
|
})
|
|
os.Stdout = stdout
|
|
_ = w.Close()
|
|
leaked, _ := io.ReadAll(r)
|
|
if len(leaked) > 0 {
|
|
t.Errorf("written to the terminal: %q", leaked)
|
|
}
|
|
for _, want := range []string{"6000-24g", "ib-a", "r1"} {
|
|
if !strings.Contains(b.String(), want) {
|
|
t.Errorf("the summary lacks %q:\n%s", want, b.String())
|
|
}
|
|
}
|
|
}
|
|
|
|
func TestStatusSaysWhenAlertsGoNowhere(t *testing.T) {
|
|
render := func(s adminapi.Summary) string {
|
|
cmd := &cobra.Command{}
|
|
var b bytes.Buffer
|
|
cmd.SetOut(&b)
|
|
printSummary(cmd, s)
|
|
return b.String()
|
|
}
|
|
if out := render(adminapi.Summary{NoAlerts: true}); !strings.Contains(out, "ALERTS nowhere") {
|
|
t.Errorf("no webhook was not called out:\n%s", out)
|
|
}
|
|
if out := render(adminapi.Summary{}); strings.Contains(out, "ALERTS") {
|
|
t.Errorf("an alerts line with webhooks set:\n%s", out)
|
|
}
|
|
}
|