From abf9fbf6eacbf2da7a1d0e0ae6a35ea500a95b72 Mon Sep 17 00:00:00 2001 From: "Lei, HUANG" <6406592+v0y4g3r@users.noreply.github.com> Date: Fri, 24 Jul 2026 18:40:03 +0800 Subject: [PATCH] chore: enlarge fuzz failover test timeout waiting for datanodes online (#8633) * chore: enlarge fuzz test timeout while waiting Kafka cluster Signed-off-by: Lei, HUANG * ci: extend Kafka readiness timeout Signed-off-by: Lei, HUANG --------- Signed-off-by: Lei, HUANG --- .github/scripts/wait-kafka-ready.sh | 2 +- .github/workflows/develop.yml | 4 ++-- tests-fuzz/targets/failover/fuzz_failover_metric_regions.rs | 2 +- tests-fuzz/targets/failover/fuzz_failover_mito_regions.rs | 2 +- 4 files changed, 5 insertions(+), 5 deletions(-) diff --git a/.github/scripts/wait-kafka-ready.sh b/.github/scripts/wait-kafka-ready.sh index 7617bdfa1f..1306044891 100755 --- a/.github/scripts/wait-kafka-ready.sh +++ b/.github/scripts/wait-kafka-ready.sh @@ -6,7 +6,7 @@ GT_KAFKA_NAMESPACE="${GT_KAFKA_NAMESPACE:-kafka-cluster}" GT_KAFKA_CLIENT_NAMESPACE="${GT_KAFKA_CLIENT_NAMESPACE:-my-greptimedb}" GT_KAFKA_BOOTSTRAP_SERVERS="${GT_KAFKA_BOOTSTRAP_SERVERS:-kafka.kafka-cluster.svc.cluster.local:9092}" GT_KAFKA_IMAGE="${GT_KAFKA_IMAGE:-docker.io/greptime/kafka:3.9.0-debian-12-r1}" -GT_KAFKA_READY_TIMEOUT_SECS="${GT_KAFKA_READY_TIMEOUT_SECS:-120}" +GT_KAFKA_READY_TIMEOUT_SECS="${GT_KAFKA_READY_TIMEOUT_SECS:-180}" GT_KAFKA_READY_INTERVAL_SECS="${GT_KAFKA_READY_INTERVAL_SECS:-5}" GT_KAFKA_POD_LABEL="${GT_KAFKA_POD_LABEL:-app.kubernetes.io/instance=kafka}" diff --git a/.github/workflows/develop.yml b/.github/workflows/develop.yml index 7956e8dfde..a161a0d496 100644 --- a/.github/workflows/develop.yml +++ b/.github/workflows/develop.yml @@ -443,7 +443,7 @@ jobs: kubectl wait \ --for=condition=Ready \ pod -l app.kubernetes.io/instance=kafka \ - --timeout=120s \ + --timeout=180s \ -n kafka-cluster - if: matrix.mode.kafkaWalHelper name: Setup Kafka WAL helper @@ -653,7 +653,7 @@ jobs: kubectl wait \ --for=condition=Ready \ pod -l app.kubernetes.io/instance=kafka \ - --timeout=120s \ + --timeout=180s \ -n kafka-cluster - name: Print etcd info shell: bash diff --git a/tests-fuzz/targets/failover/fuzz_failover_metric_regions.rs b/tests-fuzz/targets/failover/fuzz_failover_metric_regions.rs index 8502103adb..06623c4235 100644 --- a/tests-fuzz/targets/failover/fuzz_failover_metric_regions.rs +++ b/tests-fuzz/targets/failover/fuzz_failover_metric_regions.rs @@ -252,7 +252,7 @@ async fn execute_failover(ctx: FuzzContext, input: FuzzInput) -> Result<()> { // Recovers pod failures recover_pod_failure(ctx.kube.clone(), &ctx.namespace, &chaos_name).await?; - wait_for_all_datanode_online(ctx.greptime.clone(), Duration::from_secs(60)).await; + wait_for_all_datanode_online(ctx.greptime.clone(), Duration::from_secs(180)).await; tokio::time::sleep(default_distributed_time_constants().region_lease).await; // Validates value rows diff --git a/tests-fuzz/targets/failover/fuzz_failover_mito_regions.rs b/tests-fuzz/targets/failover/fuzz_failover_mito_regions.rs index 77d51dc09d..da3b7dbcf3 100644 --- a/tests-fuzz/targets/failover/fuzz_failover_mito_regions.rs +++ b/tests-fuzz/targets/failover/fuzz_failover_mito_regions.rs @@ -320,7 +320,7 @@ async fn execute_failover(ctx: FuzzContext, input: FuzzInput) -> Result<()> { // Recovers pod failures recover_pod_failure(ctx.kube.clone(), &ctx.namespace, &chaos_name).await?; - wait_for_all_datanode_online(ctx.greptime.clone(), Duration::from_secs(60)).await; + wait_for_all_datanode_online(ctx.greptime.clone(), Duration::from_secs(180)).await; tokio::time::sleep(default_distributed_time_constants().region_lease).await; // Validates value rows