jcreek/CosmicClash
1
0
Fork 0
mirror of https://github.com/jcreek/CosmicClash.git synced 2026-09-11 08:23:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(multiplayer): reclaim stalled allocations without penalising players

Browse Source 
Closes the last named item on task 8.28 (Health-reclaim): nothing
currently detects or cleans up a match stuck in
ALLOCATING/PROCESS_READY/ASSIGNMENT_READY forever because its server
crashed or was reclaimed by Agones as unhealthy before ever
registering -- players would wait indefinitely for a match that was
never coming.

The design question this was blocked on -- does an abandoned match
auto-requeue its players, or fail and make them re-queue -- isn't
actually open: task 8.50's own stated acceptance criterion already
answers it ("infrastructure-caused cases cannot penalise affected
players"). A server-side crash/reclaim is exactly that, not player
behaviour, so store.ExpireStalledAllocations fails the match but
requeues every participant's ticket to QUEUED with a fresh expiry
(matching the ordinary 30s queue window), releases their
match_participants row (participation_active = false, so they're
matchable again immediately), all inside one FOR UPDATE SKIP LOCKED
pass so a second maintenance replica continues past whatever a
concurrent one is already reclaiming.

Wired into cmd/maintenance alongside the existing season-rollover
sweep: --stalled-allocation-deadline (default 2m) and
--stalled-allocation-batch (default 100).

Covered by a SQL-fragment test and a real PostgreSQL integration test:
two matches (one genuinely stalled, one recent), confirming the
deadline boundary is respected (recent match untouched), both
stranded participants' tickets requeue with a refreshed expiry, the
match_participants row releases, and a second pass doesn't reprocess
an already-FAILED match. Verified clean across 5 runs, plus the full
integration and unit suites.
This commit is contained in:
Josh Creek
2026-09-01 13:54:54 +01:00
parent d8245047a9
commit fc2faf9723
4 changed files with 217 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
server/store/stalled_allocation_sql_test.go
+41
View File
@@ -0,0 +1,41 @@
package store
import (
"context"
"strings"
"testing"
"time"
)
func TestExpireStalledAllocationsSQLFencesAndRequeuesWithoutPenalty(t *testing.T) {
for _, fragment := range []string{
"ALLOCATING", "PROCESS_READY", "ASSIGNMENT_READY",
"FOR UPDATE SKIP LOCKED",
"SET state = 'FAILED'",
"SET participation_active = FALSE",
"SET state = 'QUEUED'",
} {
if !strings.Contains(ExpireStalledAllocationsSQL, fragment) {
t.Fatalf("ExpireStalledAllocationsSQL missing fragment %q:\n%s", fragment, ExpireStalledAllocationsSQL)
}
}
}
func TestExpireStalledAllocationsRejectsInvalidArgumentsWithoutDatabase(t *testing.T) {
now := time.Unix(1000, 0).UTC()
if _, err := ExpireStalledAllocations(context.Background(), nil, now, time.Minute, 10); err == nil {
t.Fatal("nil database accepted")
}
if _, err := ExpireStalledAllocations(context.Background(), nil, time.Time{}, time.Minute, 10); err == nil {
t.Fatal("zero time accepted")
}
if _, err := ExpireStalledAllocations(context.Background(), nil, now, 0, 10); err == nil {
t.Fatal("non-positive deadline accepted")
}
if _, err := ExpireStalledAllocations(context.Background(), nil, now, time.Minute, 0); err == nil {
t.Fatal("zero limit accepted")
}
if _, err := ExpireStalledAllocations(context.Background(), nil, now, time.Minute, 1001); err == nil {
t.Fatal("oversized limit accepted")
}
}