sr k8s 部署出现 CN 节点链接不上FE 节点

guojk · 2025年04月2日 14:55

为了更快的定位您的问题，请提供以下信息，谢谢
【详述】部署sr出现异常
【背景】做过哪些操作？
【业务影响】
【是否存算分离】是
【StarRocks版本】例如：3.3 版本
【集群规模】例如：1fe（1 follower）+ 3CN
【机器信息】CPU虚拟核/内存/网卡，例如：48C/64G/万兆
【联系方式】guoqi76327@163.com
【附件】
[Wed Apr 2 14:53:46 UTC 2025] Process conf file cn.conf …

[Wed Apr 2 14:53:46 UTC 2025] Add myself (starrockscluster-cn-0.starrockscluster-cn-search.starrocks.svc.cluster.local:9050) into FE …

ERROR 2003 (HY000): Can’t connect to MySQL server on ‘starrockscluster-fe-service:9030’ (110)

[Wed Apr 2 14:53:52 UTC 2025] Add myself (starrockscluster-cn-0.starrockscluster-cn-search.starrocks.svc.cluster.local:9050) into FE …

ERROR 2003 (HY000): Can’t connect to MySQL server on ‘starrockscluster-fe-service:9030’ (110)

[Wed Apr 2 14:53:58 UTC 2025] Add myself (starrockscluster-cn-0.starrockscluster-cn-search.starrocks.svc.cluster.local:9050) into FE …

ERROR 2003 (HY000): Can’t connect to MySQL server on ‘starrockscluster-fe-service:9030’ (110)

[Wed Apr 2 14:54:04 UTC 2025] Add myself (starrockscluster-cn-0.starrockscluster-cn-search.starrocks.svc.cluster.local:9050) into FE …

ERROR 2003 (HY000): Can’t connect to MySQL server on ‘starrockscluster-fe-service:9030’ (110)

[Wed Apr 2 14:54:10 UTC 2025] Add myself (starrockscluster-cn-0.starrockscluster-cn-search.starrocks.svc.cluster.local:9050) into FE …

ERROR 2003 (HY000): Can’t connect to MySQL server on ‘starrockscluster-fe-service:9030’ (110)

[Wed Apr 2 14:54:16 UTC 2025] Add myself (starrockscluster-cn-0.starrockscluster-cn-search.starrocks.svc.cluster.local:9050) into FE …

ERROR 2003 (HY000): Can’t connect to MySQL server on ‘starrockscluster-fe-service:9030’ (110)

guojk · 2025年04月2日 14:56

apiVersion: starrocks.com/v1
kind: StarRocksCluster
metadata:
name: starrockscluster
namespace: starrocks
spec:
starRocksFeSpec:
image: starrocks/fe-ubuntu:latest
replicas: 1
runAsNonRoot: false
limits:
cpu: 2
memory: 4Gi
requests:
cpu: 2
memory: 4Gi
storageVolumes:
- name: fe-storage-meta
storageClassName: “nfs-storage” # you can remove this line if you want to use the default storage class
storageSize: 10Gi # the size of storage volume for metadata
mountPath: /opt/starrocks/fe/meta # the path of metadata
- name: fe-storage-log
storageClassName: “nfs-storage” # you can remove this line if you want to use the default storage class
storageSize: 1Gi # the size of storage volume for log
mountPath: /opt/starrocks/fe/log # the path of log
configMapInfo:
configMapName: starrockscluster-fe-cm
resolveKey: fe.conf
starRocksCnSpec:
image: starrocks/cn-ubuntu:latest
replicas: 1
runAsNonRoot: false
limits:
cpu: 2
memory: 8Gi
requests:
cpu: 2
memory: 8Gi
configMapInfo:
configMapName: starrockscluster-cn-cm
resolveKey: cn.conf

storageVolumes:
  - name: cn-storage-data
    storageClassName: "nfs-storage"  # you can remove this line if you want to use the default storage class
    storageSize: 15Gi   # the size of storage volume for data
    mountPath: /opt/starrocks/cn/storage  # the path of data
  - name: cn-storage-log
    storageClassName: "nfs-storage"  # you can remove this line if you want to use the default storage class
    storageSize: 10Gi  # the size of storage volume for log
    mountPath: /opt/starrocks/cn/log  # the path of log

starRocksFeProxySpec:
replicas: 1
limits:
cpu: 1
memory: 4Gi
requests:
cpu: 1
memory: 4Gi
service:
type: NodePort # export fe proxy service
ports:
- name: http-port # fill the name from the fe proxy service ports
containerPort: 8080
nodePort: 30180 # The range of valid ports is 30000-32767
port: 8080
- name:
# resolver: “coredns.kube-system.svc.cluster.local” # this is the default dns server.

fe config

apiVersion: v1
kind: ConfigMap
metadata:
name: starrockscluster-fe-cm
namespace: starrocks
labels:
cluster: starrockscluster
data:
fe.conf: |
LOG_DIR = ${STARROCKS_HOME}/log
DATE = “$(date +%Y%m%d-%H%M%S)”
JAVA_OPTS="-Dlog4j2.formatMsgNoLookups=true -Xmx8192m -XX:+UseMembar -XX:SurvivorRatio=8 -XX:MaxTenuringThreshold=7 -XX:+PrintGCDateStamps -XX:+PrintGCDetails -XX:+UseConcMarkSweepGC -XX:+UseParNewGC -XX:+CMSClassUnloadingEnabled -XX:-CMSParallelRemarkEnabled -XX:CMSInitiatingOccupancyFraction=80 -XX:SoftRefLRUPolicyMSPerMB=0 -Xloggc:${LOG_DIR}/fe.gc.log.$DATE"
JAVA_OPTS_FOR_JDK_9="-Dlog4j2.formatMsgNoLookups=true -Xmx8192m -XX:SurvivorRatio=8 -XX:MaxTenuringThreshold=7 -XX:+CMSClassUnloadingEnabled -XX:-CMSParallelRemarkEnabled -XX:CMSInitiatingOccupancyFraction=80 -XX:SoftRefLRUPolicyMSPerMB=0 -Xlog:gc:${LOG_DIR}/fe.gc.log.$DATE:time"
JAVA_OPTS_FOR_JDK_11="-Dlog4j2.formatMsgNoLookups=true -Xmx8192m -XX:+UseG1GC -Xlog:gc:${LOG_DIR}/fe.gc.log.$DATE:time"
http_port = 8030
rpc_port = 9020
query_port = 9030
edit_log_port = 9010
mysql_service_nio_enabled = true
sys_log_level = INFO
run_mode = shared_data
cloud_native_meta_port = 6090
enable_load_volume_from_conf = true
cloud_native_storage_type = S3
aws_s3_path = starrocks
aws_s3_endpoint = http://mi-nio-service.aegis.svc.cluster.local:9090
aws_s3_access_key = AKIAIOSFODNN7EXAMPLE
aws_s3_secret_key = wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY
aws_s3_use_instance_profile = false
metadata_failure_recovery = true

cn config

apiVersion: v1
kind: ConfigMap
metadata:
name: starrockscluster-cn-cm
namespace: starrocks
labels:
cluster: starrockscluster
data:
cn.conf: |
sys_log_level = INFO
# ports for admin, web, heartbeat service
thrift_port = 9060
starlet_port = 9070
webserver_port = 8040
heartbeat_service_port = 9050
brpc_port = 8060