grafana已经启动了，web页面ip:3000已经可以看到监控数据了，但是services port status中仍然显示grafana的状态为down
请大佬帮忙看下
可以看下进程是否启动成功，另外辛苦提供下版本，另外，可以根据日志排查下问题
我发现我的grafana collector进程没有启动
grafana的日志貌似也没有看到什么报错的地方
状态一直没有更新吗，看上面讲的 grafana collector 进程没有启动，能否用日志方面排查下是什么问题吗？
t=2019-09-19T21:49:49+0800 lvl=eror msg="failed to look up user based on cookie" logger=context error="user token not found"
t=2019-09-19T21:49:52+0800 lvl=eror msg="Dashboard not found" logger=context userId=1 orgId=1 uname=admin error="Dashboard not found"
t=2019-09-19T21:50:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T21:50:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T21:51:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T21:51:10+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T21:52:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T21:52:19+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T21:53:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T21:53:05+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T21:53:23+0800 lvl=eror msg="Alert Rule Result Error" logger=alerting.evalContext ruleId=10 name="TiKV raft store CPU alert" error="tsdb.HandleRequest() error Get http://10.0.66.228:9090/api/v1/query_range?end=2019-09-19T21%3A53%3A23.196918121%2B08%3A00&query=sum%28rate%28tikv_thread_cpu_seconds_total%7Binstance%3D~%22%24instance%22%2C+name%3D~%22raftstore_.%2A%22%7D%5B1m%5D%29%29+by+%28instance%29&start=2019-09-19T21%3A52%3A23.196918121%2B08%3A00&step=30.000: dial tcp 10.0.66.228:9090: connect: connection refused" changing state to=alerting
t=2019-09-19T21:53:24+0800 lvl=eror msg="Alert Rule Result Error" logger=alerting.evalContext ruleId=7 name="server report failures alert" error="tsdb.HandleRequest() error Get http://10.0.66.228:9090/api/v1/query_range?end=2019-09-19T21%3A53%3A24.196592684%2B08%3A00&query=sum%28rate%28tikv_server_report_failure_msg_total%7Binstance%3D~%22%24instance%22%7D%5B1m%5D%29%29+by+%28type%2Cinstance%2Cstore_id%29&start=2019-09-19T21%3A53%3A14.196592684%2B08%3A00&step=30.000: dial tcp 10.0.66.228:9090: connect: connection refused" changing state to=alerting
t=2019-09-19T21:53:24+0800 lvl=eror msg="Alert Rule Result Error" logger=alerting.evalContext ruleId=9 name="approximate region size alert" error="tsdb.HandleRequest() error Get http://10.0.66.228:9090/api/v1/query_range?end=2019-09-19T21%3A53%3A24.196582431%2B08%3A00&query=histogram_quantile%280.99%2C+sum%28rate%28tikv_raftstore_region_size_bucket%7Binstance%3D~%22%24instance%22%7D%5B1m%5D%29%29+by+%28le%29%29&start=2019-09-19T21%3A52%3A24.196582431%2B08%3A00&step=30.000: dial tcp 10.0.66.228:9090: connect: connection refused" changing state to=alerting
t=2019-09-19T21:53:25+0800 lvl=eror msg="Alert Rule Result Error" logger=alerting.evalContext ruleId=8 name="TiKV channel full alert" error="tsdb.HandleRequest() error Get http://10.0.66.228:9090/api/v1/query_range?end=2019-09-19T21%3A53%3A25.196570793%2B08%3A00&query=sum%28rate%28tikv_channel_full_total%7Binstance%3D~%22%24instance%22%7D%5B1m%5D%29%29+by+%28instance%2C+type%29&start=2019-09-19T21%3A53%3A15.196570793%2B08%3A00&step=30.000: dial tcp 10.0.66.228:9090: connect: connection refused" changing state to=alerting
t=2019-09-19T21:53:28+0800 lvl=eror msg="Alert Rule Result Error" logger=alerting.evalContext ruleId=11 name="scheduler pending commands alert" error="tsdb.HandleRequest() error Get http://10.0.66.228:9090/api/v1/query_range?end=2019-09-19T21%3A53%3A28.196628945%2B08%3A00&query=sum%28tikv_scheduler_contex_total%7Binstance%3D~%22%24instance%22%7D%29+by+%28instance%29&start=2019-09-19T21%3A48%3A28.196628945%2B08%3A00&step=30.000: dial tcp 10.0.66.228:9090: connect: connection refused" changing state to=alerting
t=2019-09-19T21:53:31+0800 lvl=eror msg="Alert Rule Result Error" logger=alerting.evalContext ruleId=2 name="server report failures alert" error="tsdb.HandleRequest() error Get http://10.0.66.228:9090/api/v1/query_range?end=2019-09-19T21%3A53%3A31.196574726%2B08%3A00&query=sum%28rate%28tikv_server_report_failure_msg_total%7Binstance%3D~%22%24instance%22%7D%5B1m%5D%29%29+by+%28type%2Cinstance%2Cstore_id%29&start=2019-09-19T21%3A53%3A21.196574726%2B08%3A00&step=30.000: dial tcp 10.0.66.228:9090: connect: connection refused" changing state to=alerting
t=2019-09-19T21:53:31+0800 lvl=eror msg="Alert Rule Result Error" logger=alerting.evalContext ruleId=3 name="TiKV channel full alert" error="tsdb.HandleRequest() error Get http://10.0.66.228:9090/api/v1/query_range?end=2019-09-19T21%3A53%3A31.196581594%2B08%3A00&query=sum%28rate%28tikv_channel_full_total%7Binstance%3D~%22%24instance%22%7D%5B1m%5D%29%29+by+%28instance%2C+type%29&start=2019-09-19T21%3A53%3A21.196581594%2B08%3A00&step=30.000: dial tcp 10.0.66.228:9090: connect: connection refused" changing state to=alerting
t=2019-09-19T21:53:32+0800 lvl=eror msg="Alert Rule Result Error" logger=alerting.evalContext ruleId=7 name="server report failures alert" error="tsdb.HandleRequest() error Get http://10.0.66.228:9090/api/v1/query_range?end=2019-09-19T21%3A53%3A32.196416388%2B08%3A00&query=sum%28rate%28tikv_server_report_failure_msg_total%7Binstance%3D~%22%24instance%22%7D%5B1m%5D%29%29+by+%28type%2Cinstance%2Cstore_id%29&start=2019-09-19T21%3A53%3A22.196416388%2B08%3A00&step=30.000: dial tcp 10.0.66.228:9090: connect: connection refused" changing state to=alerting
t=2019-09-19T21:53:35+0800 lvl=eror msg="Alert Rule Result Error" logger=alerting.evalContext ruleId=8 name="TiKV channel full alert" error="tsdb.HandleRequest() error Get http://10.0.66.228:9090/api/v1/query_range?end=2019-09-19T21%3A53%3A35.196605261%2B08%3A00&query=sum%28rate%28tikv_channel_full_total%7Binstance%3D~%22%24instance%22%7D%5B1m%5D%29%29+by+%28instance%2C+type%29&start=2019-09-19T21%3A53%3A25.196605261%2B08%3A00&step=30.000: dial tcp 10.0.66.228:9090: connect: connection refused" changing state to=alerting
t=2019-09-19T21:55:14+0800 lvl=eror msg="Data source with same name already exists" logger=context userId=1 orgId=1 uname=admin error="Data source with same name already exists"
t=2019-09-19T21:56:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T21:56:09+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T21:56:55+0800 lvl=eror msg="Alert Rule Result Error" logger=alerting.evalContext ruleId=8 name="TiKV channel full alert" error="tsdb.HandleRequest() error Get http://10.0.66.228:9090/api/v1/query_range?end=2019-09-19T21%3A56%3A55.487311686%2B08%3A00&query=sum%28rate%28tikv_channel_full_total%7Binstance%3D~%22%24instance%22%7D%5B1m%5D%29%29+by+%28instance%2C+type%29&start=2019-09-19T21%3A56%3A45.487311686%2B08%3A00&step=30.000: dial tcp 10.0.66.228:9090: connect: connection refused" changing state to=alerting
t=2019-09-19T21:57:01+0800 lvl=eror msg="Alert Rule Result Error" logger=alerting.evalContext ruleId=3 name="TiKV channel full alert" error="tsdb.HandleRequest() error Get http://10.0.66.228:9090/api/v1/query_range?end=2019-09-19T21%3A57%3A01.487519215%2B08%3A00&query=sum%28rate%28tikv_channel_full_total%7Binstance%3D~%22%24instance%22%7D%5B1m%5D%29%29+by+%28instance%2C+type%29&start=2019-09-19T21%3A56%3A51.487519215%2B08%3A00&step=30.000: dial tcp 10.0.66.228:9090: connect: connection refused" changing state to=alerting
t=2019-09-19T21:57:01+0800 lvl=eror msg="Alert Rule Result Error" logger=alerting.evalContext ruleId=2 name="server report failures alert" error="tsdb.HandleRequest() error Get http://10.0.66.228:9090/api/v1/query_range?end=2019-09-19T21%3A57%3A01.487817774%2B08%3A00&query=sum%28rate%28tikv_server_report_failure_msg_total%7Binstance%3D~%22%24instance%22%7D%5B1m%5D%29%29+by+%28type%2Cinstance%2Cstore_id%29&start=2019-09-19T21%3A56%3A51.487817774%2B08%3A00&step=30.000: dial tcp 10.0.66.228:9090: connect: connection refused" changing state to=alerting
t=2019-09-19T21:57:01+0800 lvl=eror msg="Alert Rule Result Error" logger=alerting.evalContext ruleId=1 name="Critical error alert" error="tsdb.HandleRequest() error Get http://10.0.66.228:9090/api/v1/query_range?end=2019-09-19T21%3A57%3A01.488056898%2B08%3A00&query=sum%28rate%28tikv_critical_error_total%7Binstance%3D~%22%24instance%22%7D%5B1m%5D%29%29+by+%28instance%2C+type%29&start=2019-09-19T21%3A52%3A01.488056898%2B08%3A00&step=30.000: dial tcp 10.0.66.228:9090: connect: connection refused" changing state to=alerting
t=2019-09-19T21:57:04+0800 lvl=eror msg="Alert Rule Result Error" logger=alerting.evalContext ruleId=7 name="server report failures alert" error="tsdb.HandleRequest() error Get http://10.0.66.228:9090/api/v1/query_range?end=2019-09-19T21%3A57%3A04.487594411%2B08%3A00&query=sum%28rate%28tikv_server_report_failure_msg_total%7Binstance%3D~%22%24instance%22%7D%5B1m%5D%29%29+by+%28type%2Cinstance%2Cstore_id%29&start=2019-09-19T21%3A56%3A54.487594411%2B08%3A00&step=30.000: dial tcp 10.0.66.228:9090: connect: connection refused" changing state to=alerting
t=2019-09-19T21:57:05+0800 lvl=eror msg="Alert Rule Result Error" logger=alerting.evalContext ruleId=4 name="approximate region size alert" error="tsdb.HandleRequest() error Get http://10.0.66.228:9090/api/v1/query_range?end=2019-09-19T21%3A57%3A05.4875177%2B08%3A00&query=histogram_quantile%280.99%2C+sum%28rate%28tikv_raftstore_region_size_bucket%7Binstance%3D~%22%24instance%22%7D%5B1m%5D%29%29+by+%28le%29%29&start=2019-09-19T21%3A56%3A05.4875177%2B08%3A00&step=30.000: dial tcp 10.0.66.228:9090: connect: connection refused" changing state to=alerting
t=2019-09-19T21:57:05+0800 lvl=eror msg="Alert Rule Result Error" logger=alerting.evalContext ruleId=8 name="TiKV channel full alert" error="tsdb.HandleRequest() error Get http://10.0.66.228:9090/api/v1/query_range?end=2019-09-19T21%3A57%3A05.487525132%2B08%3A00&query=sum%28rate%28tikv_channel_full_total%7Binstance%3D~%22%24instance%22%7D%5B1m%5D%29%29+by+%28instance%2C+type%29&start=2019-09-19T21%3A56%3A55.487525132%2B08%3A00&step=30.000: dial tcp 10.0.66.228:9090: connect: connection refused" changing state to=alerting
t=2019-09-19T21:57:11+0800 lvl=eror msg="Alert Rule Result Error" logger=alerting.evalContext ruleId=2 name="server report failures alert" error="tsdb.HandleRequest() error Get http://10.0.66.228:9090/api/v1/query_range?end=2019-09-19T21%3A57%3A11.487478078%2B08%3A00&query=sum%28rate%28tikv_server_report_failure_msg_total%7Binstance%3D~%22%24instance%22%7D%5B1m%5D%29%29+by+%28type%2Cinstance%2Cstore_id%29&start=2019-09-19T21%3A57%3A01.487478078%2B08%3A00&step=30.000: dial tcp 10.0.66.228:9090: connect: connection refused" changing state to=alerting
t=2019-09-19T21:57:11+0800 lvl=eror msg="Alert Rule Result Error" logger=alerting.evalContext ruleId=3 name="TiKV channel full alert" error="tsdb.HandleRequest() error Get http://10.0.66.228:9090/api/v1/query_range?end=2019-09-19T21%3A57%3A11.487518627%2B08%3A00&query=sum%28rate%28tikv_channel_full_total%7Binstance%3D~%22%24instance%22%7D%5B1m%5D%29%29+by+%28instance%2C+type%29&start=2019-09-19T21%3A57%3A01.487518627%2B08%3A00&step=30.000: dial tcp 10.0.66.228:9090: connect: connection refused" changing state to=alerting
t=2019-09-19T21:57:12+0800 lvl=eror msg="Alert Rule Result Error" logger=alerting.evalContext ruleId=7 name="server report failures alert" error="tsdb.HandleRequest() error Get http://10.0.66.228:9090/api/v1/query_range?end=2019-09-19T21%3A57%3A12.48931918%2B08%3A00&query=sum%28rate%28tikv_server_report_failure_msg_total%7Binstance%3D~%22%24instance%22%7D%5B1m%5D%29%29+by+%28type%2Cinstance%2Cstore_id%29&start=2019-09-19T21%3A57%3A02.48931918%2B08%3A00&step=30.000: dial tcp 10.0.66.228:9090: connect: connection refused" changing state to=alerting
t=2019-09-19T21:57:15+0800 lvl=eror msg="Alert Rule Result Error" logger=alerting.evalContext ruleId=8 name="TiKV channel full alert" error="tsdb.HandleRequest() error Get http://10.0.66.228:9090/api/v1/query_range?end=2019-09-19T21%3A57%3A15.487436859%2B08%3A00&query=sum%28rate%28tikv_channel_full_total%7Binstance%3D~%22%24instance%22%7D%5B1m%5D%29%29+by+%28instance%2C+type%29&start=2019-09-19T21%3A57%3A05.487436859%2B08%3A00&step=30.000: dial tcp 10.0.66.228:9090: connect: connection refused" changing state to=alerting
t=2019-09-19T21:58:36+0800 lvl=eror msg="Data source with same name already exists" logger=context userId=1 orgId=1 uname=admin error="Data source with same name already exists"
t=2019-09-19T21:59:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T21:59:13+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:00:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:00:22+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:01:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:01:08+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:02:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:02:17+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:03:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:03:03+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:04:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:04:12+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:05:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:05:21+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:06:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:06:07+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:07:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:07:16+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:08:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:08:02+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:09:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:09:11+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:10:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:10:20+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:11:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:11:06+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:12:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:12:15+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:13:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:13:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:14:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:14:10+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:15:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:15:19+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:16:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:16:05+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:17:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:17:14+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:18:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:18:23+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:19:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:19:09+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:20:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:20:18+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:21:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:21:04+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:22:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:22:13+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:23:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:23:22+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:24:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:24:08+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:25:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:25:17+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:26:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:26:03+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:27:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:27:12+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:28:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:28:21+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:29:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:29:07+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:30:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:30:16+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:31:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:31:02+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:32:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:32:11+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:33:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:33:20+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:34:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:34:06+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:35:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:35:15+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:36:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:36:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:37:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:37:10+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:38:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:38:19+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:39:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:39:05+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:40:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:40:14+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:41:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:41:23+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:42:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:42:09+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:43:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:43:18+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=6 name="Critical error alert" changing state to=no_data
t=2019-09-19T22:44:01+0800 lvl=info msg="Alert Rule returned no data" logger=alerting.evalContext ruleId=1 name="Critical error alert" changing state to=no_data
日志里面报错是这样的，烦请大佬帮忙看下
我发现部署完毕后都没有grafana的bin目录下都没有grafana_collector命令，这个是我的部署信息，麻烦帮忙看下有没有问题
## TiDB Cluster Part
[tidb_servers]
10.11.10.145
10.11.10.146
[tikv_servers]
10.11.10.142
10.11.10.143
10.11.10.144
[pd_servers]
10.11.10.145
10.11.10.146
10.11.10.147
[spark_master]
[spark_slaves]
[lightning_server]
[importer_server]
## Monitoring Part
# prometheus and pushgateway servers
[monitoring_servers]
monitoring_servers ansible_host=10.1.66.228 deploy_dir=/data/monitoring_servers/deploy
[grafana_servers]
grafana_servers ansible_host=10.1.66.228 deploy_dir=/data/grafana_servers/deploy
# node_exporter and blackbox_exporter servers
[monitored_servers]
10.11.10.142
10.11.10.143
10.11.10.144
10.11.10.145
10.11.10.146
10.11.10.147
10.1.66.228
[alertmanager_servers]
alertmanager_servers ansible_host=10.1.66.228 deploy_dir=/data/alertmanager_servers/deploy
[kafka_exporter_servers]
## Binlog Part
[pump_servers]
[drainer_servers]
## Group variables
[pd_servers:vars]
# location_labels = ["zone","rack","host"]
## Global variables
[all:vars]
deploy_dir = /data/deploy
## Connection
# ssh via normal user
ansible_user = tidb
cluster_name = tidb-cluster
tidb_version = v3.0.1
# process supervision, [systemd, supervise]
process_supervision = systemd
timezone = Asia/Shanghai
enable_firewalld = False
# check NTP service
enable_ntpd = True
set_hostname = False
## binlog trigger
enable_binlog = False
# kafka cluster address for monitoring, example:
# kafka_addrs = "192.168.0.11:9092,192.168.0.12:9092,192.168.0.13:9092"
kafka_addrs = ""
# zookeeper address of kafka cluster for monitoring, example:
# zookeeper_addrs = "192.168.0.11:2181,192.168.0.12:2181,192.168.0.13:2181"
zookeeper_addrs = ""
# enable TLS authentication in the TiDB cluster
enable_tls = False
# KV mode
deploy_without_tidb = False
# wait for region replication complete before start tidb-server.
wait_replication = True
# Optional: Set if you already have a alertmanager server.
# Format: alertmanager_host:alertmanager_port
alertmanager_target = ""
grafana_admin_user = "admin"
grafana_admin_password = "****"
### Collect diagnosis
collect_log_recent_hours = 2
enable_bandwidth_limit = True
# default: 10Mb/s, unit: Kbit/s
collect_bandwidth_limit = 10000
Data source怎么查看？
在 grafana 上面有个 data source 页面，看下是不是有多个数据源。另外没有 grafana_collector ，是不是 deploy 的时候有问题，看 inventory 文件没有什么问题。
depoly的时候显示都是ok的，没有报错
可以单独grafana和普罗米修斯重新部署下吗？
单独更新一下 grafana ： ansible-playbook rolling_update.yml --tags= grafana
单独更新之后还是一样的，情况还是和以前一样
[monitoring_servers] monitoring_servers ansible_host=10.1.66.228 deploy_dir=/data/monitoring_servers/deploy
[grafana_servers] grafana_servers ansible_host=10.1.66.228 deploy_dir=/data/grafana_servers/deploy
尝试这边的别名不要和 [] 标签名一样
后面我改了但是问题依旧，问题的核心是v3.0.1后面把grafana_collector给剔除掉了