perf(actions): debounce runner heartbeat writes and throttle task picks (#38281)

3 reductions in the DB load generated by many runners polling
`FetchTask`:

**1. Debounce runner heartbeat writes**
Every poll wrote `last_online`, and every `UpdateTask`/`UpdateLog` wrote
`last_active` — while a runner streams logs that is many writes per
second per runner. These are now persisted only when stale enough to
actually affect the active/offline status (`ShouldPersistLastOnline` /
`ShouldPersistLastActive`), using the existing columns.

**2. Throttle concurrent task picks**
A new in-process semaphore (`MAX_CONCURRENT_TASK_PICKS`) bounds how many
runners run the task-assignment transaction at once, so a fleet polling
together cannot stampede the query. Throttled polls retry on their next
poll without advancing the runner's tasks version.

**3. Paginate the task-pick query**
`CreateTaskForRunner` previously loaded every waiting job in the
runner's scope into memory on each poll (no `LIMIT`). Now it pages
through the waiting backlog oldest-first with `LIMIT`, claiming the
first label-matching job.

---------

Co-authored-by: Zettat123 <zettat123@gmail.com>
This commit is contained in:
bircni
2026-07-07 21:16:20 +02:00
committed by GitHub
parent 97078b96cf
commit 308a6f12ae
10 changed files with 317 additions and 30 deletions
+72
View File
@@ -6,14 +6,86 @@ package actions
import (
"fmt"
"testing"
"time"
"gitea.dev/models/db"
"gitea.dev/models/unittest"
"gitea.dev/modules/timeutil"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
func TestShouldPersistLastOnline(t *testing.T) {
now := time.Now()
tests := []struct {
name string
last timeutil.TimeStamp
want bool
}{
{
name: "fresh, skip write",
last: timeutil.TimeStamp(now.Add(-5 * time.Second).Unix()),
want: false,
},
{
name: "exactly at interval, write",
last: timeutil.TimeStamp(now.Add(-RunnerHeartbeatInterval).Unix()),
want: true,
},
{
name: "stale, write",
last: timeutil.TimeStamp(now.Add(-2 * RunnerHeartbeatInterval).Unix()),
want: true,
},
{
name: "zero (never seen), write",
last: 0,
want: true,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
assert.Equal(t, tt.want, ShouldPersistLastOnline(tt.last, now))
})
}
}
func TestShouldPersistLastActive(t *testing.T) {
now := time.Now()
tests := []struct {
name string
last timeutil.TimeStamp
want bool
}{
{
name: "fresh, skip write",
last: timeutil.TimeStamp(now.Add(-1 * time.Second).Unix()),
want: false,
},
{
name: "exactly at interval, write",
last: timeutil.TimeStamp(now.Add(-RunnerActiveInterval).Unix()),
want: true,
},
{
name: "stale, write",
last: timeutil.TimeStamp(now.Add(-2 * RunnerActiveInterval).Unix()),
want: true,
},
{
name: "zero (never seen), write",
last: 0,
want: true,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
assert.Equal(t, tt.want, ShouldPersistLastActive(tt.last, now))
})
}
}
func TestFindRunnerOptions_ToOrders_StableTiebreaker(t *testing.T) {
// Sorts on a non-unique column must end with the unique id tiebreaker so
// pagination is deterministic; without it, runners sharing the same