Merge branch 'E21' of https://git.mesalab.cn/galaxy/online-config into E21

3 files changed, 124 insertions, 1 deletions

diff --git a/hbase/DC/docker-compose.yml b/hbase/DC/docker-compose.yml
index 9794510..523c310 100644
--- a/hbase/DC/docker-compose.yml
+++ b/hbase/DC/docker-compose.yml
@@ -30,7 +30,7 @@ services:
     deploy:
       resources:
         limits:
-          memory: 15G
+          memory: 25G
 networks:
   galaxy:
     external: true
diff --git a/olap_metrics b/olap_metrics
new file mode 100644
index 0000000..1c24c6a
--- /dev/null
+++ b/olap_metrics
@@ -0,0 +1,103 @@
+services通用:
+http_server_requests_seconds_count
+process_uptime_seconds
+http_server_requests_seconds_max
+jvm_memory_used_bytes
+http_server_requests_seconds_sum
+
+job:
+jobLogSuccessCount
+jobLogCount
+triggerCountRunningTotal
+triggerDayCountSucList
+triggerDayCountFailList
+system_cpu_usage
+logback_events_total
+triggerCountSucTotal
+triggerCountFailTotal
+
+report:
+system_cpu_usage
+report_success_count_total
+report_fail_count_total
+
+hos:
+process_cpu_usage
+dashInfo
+
+Flink:
+flink_taskmanager_job_task_backPressuredTimeMsPerSecond
+flink_taskmanager_job_task_numBytesInPerSecond
+flink_taskmanager_job_task_numBytesOutPerSecond
+flink_taskmanager_Status_JVM_CPU_Load
+flink_taskmanager_Status_JVM_Memory_Heap_Used
+flink_taskmanager_Status_JVM_Memory_Heap_Committed
+flink_jobmanager_job_numRestarts
+flink_jobmanager_taskSlotsTotal
+flink_jobmanager_numRunningJobsa
+同时过滤task.*和job_id标签。
+
+Nginx:
+nginx_vts_start_time_seconds
+nginx_vts_server_requests_total
+nginx_vts_upstream_requests_total
+nginx_vts_upstream_response_seconds_total
+
+Kafka:
+kafka_consumergroup_lag_sum
+kafka_server_BrokerTopicMetrics_OneMinuteRate
+kafka_server_BrokerTopicMetrics_OneMinuteRate
+kafka_server_socket_server_metrics_request_rate
+kafka_network_RequestMetrics_Errors_total
+
+Clickhouse:
+bad_requests_total
+clickhouse_inserted_bytes_total
+clickhouse_inserted_rows_total
+clickhouse_merge_total
+clickhouse_slow_read_total
+process_cpu_seconds_total
+process_virtual_memory_bytes
+request_sum_total
+
+Druid:
+coordinator_segment_count
+coordinator_segment_size
+sys_swap_page_in
+ingest_kafka_lag
+node_cpu_seconds_total
+sys_mem_used
+
+Hadoop:
+Hadoop_DataNode_HeartbeatsNumOps
+Hadoop_HBase_numMasterWALs
+Hadoop_HBase_numRegionServers
+Hadoop_NameNode_Total
+Hadoop_NameNode_PercentUsed
+Hadoop_NameNode_NumDeadDataNodes
+Hadoop_NameNode_NumberOfMissingBlocks
+
+HBase:
+java_lang_OperatingSystem_ProcessCpuLoad
+jvm_memory_bytes_used
+Hadoop_HBase_numDeadRegionServers
+Hadoop_HBase_regionCount
+Hadoop_HBase_ritCount
+Hadoop_HBase_slowGetCount
+Hadoop_HBase_slowPutCount
+Hadoop_HBase_slowAppendCount
+
+Nacos:
+http_server_requests_seconds_count
+jvm_memory_used_bytes
+system_cpu_usage
+
+Zookeeper:
+zookeeper_connections
+zookeeper_latency_avg_ms
+zookeeper_latency_max_ms
+zookeeper_leader
+zookeeper_outstanding_requests
+zookeeper_packets_received
+zookeeper_packets_sent
+zookeeper_znode_count
diff --git a/现场情况记录 b/现场情况记录
new file mode 100644
index 0000000..1fd9639
--- /dev/null
+++ b/现场情况记录
@@ -0,0 +1,20 @@
+2021-11-03
+1：界面无dos阈值配置时，dos-detection程序后台频繁抛出异常。（dos-detection程序已更新）
+2：更新generate-baselines程序。
+3：topN计算在数据量较少的情况下无法统计出结果。
+
+2021-11-04
+1：集群安装包：
+1.1：Flink set_flink_env.sh.j2脚本内chkconfig keepflinkjob 错误 应为：chkconfig keepflinkjob on
+1.2：iplearning启动脚本判断已启动命令错误。
+1.3：dos-baseline程序启动脚本配置文件打入jar位置异常。
+1.4：dos-baseline定时任务周期错误。
+1.5：HBase-region监控配置文件异常，缺少配置。
+
+2021-11-05
+昨天晚上对分中心主机名进行修改发现以下问题：
+1：修改主机名后，HBase容器重启/重建、删除data数据目录/zk内节点重建服务均异常；全部目录删除重装后正常。
+2：整机重启后Flink任务丢失。
+------------------------
+1：单机taskmanager重启后，从出现两个的情况；此时两个taskmanager服务状态不正常(无法在界面看到任何资源信息，均为-)，同时任务也无法恢复。
+2：schema原始日志和livecharts删除data_center解析。