zabbix 监控 es 集群

[root@elk-node1 elasticsearch_monitor]# curl -u elastic:qZXo7EkxoxmKvDqQIwn5 -s http://192.168.99.185:9200/_cat/health?v
epoch      timestamp cluster     status node.total node.data shards pri relo init unassign pending_tasks max_task_wait_time active_shards_percent
1578208577 07:16:17  elk-cluster green           2         2    998 499    0    0        0             0                  -                100.0%

cluster ，集群名称
status，集群状态 green代表健康；yellow代表分配了所有主分片，但至少缺少一个副本，此时集群数据仍旧完整；
red代表部分主分片不可用，可能已经丢失数据。
node.total，代表在线的节点总数量
node.data，代表在线的数据节点的数量
shards， active_shards 存活的分片数量
pri，active_primary_shards 存活的主分片数量 正常情况下 shards的数量是pri的两倍。
relo， relocating_shards 迁移中的分片数量，正常情况为 0
init， initializing_shards 初始化中的分片数量 正常情况为 0
unassign， unassigned_shards 未分配的分片 正常情况为 0
pending_tasks，准备中的任务，任务指迁移分片等 正常情况为 0
max_task_wait_time，任务最长等待时间
active_shards_percent，正常分片百分比 正常情况为 100%

[root@elk-node1 /]# curl -u elastic:qZXo7EkxoxmKvDqQIwn5 -XGET "http://192.168.99.185:9200/_cat/health?h=node.total"
2
[root@elk-node1 /]# curl -u elastic:qZXo7EkxoxmKvDqQIwn5 -XGET "http://192.168.99.185:9200/_cat/health?h=cluster"
elk-cluster
[root@elk-node1 /]# curl -u elastic:qZXo7EkxoxmKvDqQIwn5 -XGET "http://192.168.99.185:9200/_cat/health?h=active_shards_percent"
100.0%

[root@elk-node1 elasticsearch_monitor]# cat es_env.sh
# es监控环境变量配置文件
# es节点ip和端口
ESADDR="192.168.99.185:9200, 192.168.99.186:9200"

[root@elk-node1 elasticsearch_monitor]# cat  es_cluster_health.sh 
#!/bin/bash

PATH=/bin:/sbin:/usr/bin:/usr/sbin

#echo $0
cd $(dirname $0)
HOMEPATH=$(pwd)

source es_env.sh
[ $? -ne 0 ] && echo "ERROR: es_env.sh not not found." >&2 && exit 1

[ X$1 = X ] && echo "ERROR: type empty." >&2 && exit 1

for addr in $(echo ${ESADDR} |sed -e 's/,/ /g')
do
  curl -u elastic:qZXo7EkxoxmKvDqQIwn5 -XGET "http://$addr/_cat/health?h=$1" 2>/dev/null
  [ $? -eq 0 ] && break
done

[root@elk-node1 elasticsearch_monitor]# cat es_nodes_discovery.sh
#!/bin/bash

PATH=/bin:/sbin:/usr/bin:/usr/sbin

#echo $0
cd $(dirname $0)
HOMEPATH=$(pwd)

source es_env.sh
[ $? -ne 0 ] && echo "ERROR: es_env.sh not not found." >&2 && exit 1

# 连接es节点，获取索引，自动发现监控项
for addr in $(echo ${ESADDR} |sed -e 's/,/ /g')
do
  curl  -u elastic:qZXo7EkxoxmKvDqQIwn5 -XGET "http://$addr/" &>/dev/null
  [ $? -ne 0 ] && echo "WARN: connect to $addr failed." >&2 && continue

  # 获取索引列表
  # 日索引
  list=( $(curl  -u elastic:qZXo7EkxoxmKvDqQIwn5 -XGET "http://$addr/_cat/nodes?h=name" 2>/dev/null) )
  #echo -e "${list[*]}\n\n"

  #[ x$list = x ] && echo "ERROR: no discovery data list found." >&2 && exit 1
  # 将列表list，转换为发送给zabbx的json数据。length=${#list[@]}
  #printf "{\n"
  printf '{\"data\":[ '
  for ((i=0;i<$length;i++))
  do
    printf "{\"{#NAME}\":\"${list[$i]}\"}"

    if [ $i -lt $[ $length-1 ] ];then
      printf ','
    fi
  done
  #printf  "\n\t]\n"
  #printf "}\n"
  printf  " ]}"
  
  break
done

[root@elk-node1 elasticsearch_monitor]# cat es_node_monitor.sh
#!/bin/bash

PATH=/bin:/sbin:/usr/bin:/usr/sbin

#echo $0
cd $(dirname $0)
HOMEPATH=$(pwd)

source es_env.sh
[ $? -ne 0 ] && echo "ERROR: es_env.sh not not found." >&2 && exit 1

[ X$1 = X ] && echo "ERROR: node name empty." >&2 && exit 1
[ X$2 = X ] && echo "ERROR: type empty." >&2 && exit 1

for addr in $(echo ${ESADDR} |sed -e 's/,/ /g')
do
  curl  -u elastic:qZXo7EkxoxmKvDqQIwn5 -XGET "http://$addr/_cat/nodes?bytes=b&size=b&h=name,$2" 2>/dev/null |grep "^$1" |awk '{print $2}' 
  [ $? -eq 0 ] && break
done

[root@elk-node1 elasticsearch_monitor]# cat es_index_monitor.sh
#!/bin/bash

PATH=/bin:/sbin:/usr/bin:/usr/sbin

#echo $0
cd $(dirname $0)
HOMEPATH=$(pwd)

source es_env.sh
[ $? -ne 0 ] && echo "ERROR: es_env.sh not not found." >&2 && exit 1

# index count
indices_count() {
  local indexfilter=$1
  for addr in $(echo ${ESADDR} |sed -e 's/,/ /g')
  do
    curl -u elastic:qZXo7EkxoxmKvDqQIwn5 -XGET "http://$addr/_cat/count/$indexfilter*?h=count" 2>/dev/null
    [ $? -eq 0 ] && break
  done
}


# 检查类型
case $1 in
  count)
    indices_count $2
  ;;
  *)
    echo "ERROR: monitor type $1 error." >&2
esac

[root@elk-node1 elasticsearch_monitor]# cat  /etc/zabbix/zabbix_agentd.d/userparameter_elasticsearch.conf 
UserParameter=es_cluster_health[*],/usr/local/zabbix/scripts/elasticsearch_monitor/es_cluster_health.sh $1
UserParameter=es_nodes_discovery,/usr/local/zabbix/scripts/elasticsearch_monitor/es_nodes_discovery.sh
UserParameter=es_node_monitor[*],/usr/local/zabbix/scripts/elasticsearch_monitor/es_node_monitor.sh $1 $2
UserParameter=es_index_monitor[*],/usr/local/zabbix/scripts/elasticsearch_monitor/es_index_monitor.sh $1 $2