admin
eed23e7594
gates / gates (push) Successful in 32s
A count above 0 in a running container's current run fires the existing app_oom line (source cgroup/docker in the details), whatever Docker's OOMKilled says. Old agent: 404 back-off; no agent: Docker's flag only. Tests TestR528_* red first / red-proved. Commit only.
51 lines
1.5 KiB
Go
51 lines
1.5 KiB
Go
package main
|
|
|
|
import (
|
|
"context"
|
|
"errors"
|
|
"log"
|
|
"net/http"
|
|
"sync"
|
|
"time"
|
|
|
|
"gitea.dooplex.hu/admin/felhom-controller/internal/agentapi"
|
|
)
|
|
|
|
// hostOOMSource (R-528) is the 30-s dead-app scan's host-side OOM counter: one agent call per scan (5 s cap). An agent
|
|
// without the route (404) is not asked again for hostOOMRetryAfter, and said once; any other failure is a nil answer
|
|
// for this scan only (Docker's flag still works). Pinned by TestR528_HostOOMSource*.
|
|
const hostOOMRetryAfter = 10 * time.Minute
|
|
|
|
func hostOOMSource(ask func(context.Context) (agentapi.GuestOOMKillsState, error), logger *log.Logger, now func() time.Time) func() map[string]int64 {
|
|
var mu sync.Mutex
|
|
var until time.Time
|
|
said := false
|
|
return func() map[string]int64 {
|
|
mu.Lock()
|
|
defer mu.Unlock()
|
|
if now().Before(until) {
|
|
return nil
|
|
}
|
|
ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
|
|
defer cancel()
|
|
st, err := ask(ctx)
|
|
if err != nil {
|
|
var se *agentapi.StatusError
|
|
if errors.As(err, &se) && se.Code == http.StatusNotFound {
|
|
until = now().Add(hostOOMRetryAfter)
|
|
if !said {
|
|
logger.Printf("[INFO] [deadapp] the agent has no OOM counter route (R-528) — Docker's OOM flag only; asked again in %s", hostOOMRetryAfter)
|
|
said = true
|
|
}
|
|
return nil
|
|
}
|
|
logger.Printf("[WARN] [deadapp] the host OOM counter could not be read: %v — Docker's OOM flag only for this scan", err)
|
|
return nil
|
|
}
|
|
if !st.Available {
|
|
return nil
|
|
}
|
|
return st.Containers
|
|
}
|
|
}
|