-
Notifications
You must be signed in to change notification settings - Fork 6.5k
/
self.yaml
81 lines (80 loc) · 4.73 KB
/
self.yaml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# This will parse a textual representation of a duration. The formats
# accepted are based on the ISO-8601 duration format {@code PnDTnHnMn.nS}
# with days considered to be exactly 24 hours.
# <p>
# Examples:
# <pre>
# "PT20.345S" -- parses as "20.345 seconds"
# "PT15M" -- parses as "15 minutes" (where a minute is 60 seconds)
# "PT10H" -- parses as "10 hours" (where an hour is 3600 seconds)
# "P2D" -- parses as "2 days" (where a day is 24 hours or 86400 seconds)
# "P2DT3H4M" -- parses as "2 days, 3 hours and 4 minutes"
# "P-6H3M" -- parses as "-6 hours and +3 minutes"
# "-P6H3M" -- parses as "-6 hours and -3 minutes"
# "-P-6H+3M" -- parses as "+6 hours and -3 minutes"
# </pre>
fetcherInterval: PT15S
fetcherTimeout: PT10S
metricsPath: /metrics
staticConfig:
# targets will be labeled as "instance"
targets:
- url: http://localhost:1234
sslCaFilePath:
labels:
service: oap-server
expSuffix: tag({tags -> tags.service = 'oap::' + tags.service}).instance(['service'], ['instance'])
metricPrefix: meter_oap
metricsRules:
- name: instance_cpu_percentage
exp: (process_cpu_seconds_total * 100).sum(['service', 'instance']).rate('PT1M')
- name: instance_jvm_memory_bytes_used
exp: jvm_memory_bytes_used.sum(['service', 'instance'])
- name: instance_jvm_young_gc_count
exp: jvm_gc_collection_seconds_count.tagMatch('gc', 'PS Scavenge|Copy|ParNew|G1 Young Generation').sum(['service', 'instance']).increase('PT1M')
- name: instance_jvm_young_gc_time
exp: jvm_gc_collection_seconds_sum.tagMatch('gc', 'PS Scavenge|Copy|ParNew|G1 Young Generation').sum(['service', 'instance']) * 1000
- name: instance_jvm_old_gc_count
exp: jvm_gc_collection_seconds_count.tagMatch('gc', 'PS MarkSweep|MarkSweepCompact|ConcurrentMarkSweep|G1 Old Generation').sum(['service', 'instance']).increase('PT1M')
- name: instance_jvm_old_gc_time
exp: jvm_gc_collection_seconds_sum.tagMatch('gc', 'PS MarkSweep|MarkSweepCompact|ConcurrentMarkSweep|G1 Old Generation').sum(['service', 'instance']) * 1000
- name: instance_trace_count
exp: trace_in_latency_count.sum(['service', 'instance']).increase('PT1M')
- name: instance_trace_latency_percentile
exp: trace_in_latency.sum(['le', 'service', 'instance']).increase('PT1M').histogram().histogram_percentile([50,70,90,99])
- name: instance_trace_analysis_error_count
exp: trace_analysis_error_count.sum(['service', 'instance']).increase('PT1M')
- name: instance_mesh_count
exp: mesh_analysis_latency_count.sum(['service', 'instance']).increase('PT1M')
- name: instance_mesh_latency_percentile
exp: mesh_analysis_latency.sum(['le', 'service', 'instance']).increase('PT1M').histogram().histogram_percentile([50,70,90,99])
- name: instance_mesh_analysis_error_count
exp: mesh_analysis_error_count.sum(['service', 'instance']).increase('PT1M')
- name: instance_metrics_first_aggregation
exp: metrics_aggregation.tagEqual('dimensionality', 'minute', 'level', '1').sum(['service', 'instance']).increase('PT5M')
- name: instance_metrics_second_aggregation
exp: metrics_aggregation.tagEqual('dimensionality', 'minute', 'level', '2').sum(['service', 'instance']).increase('PT5M')
- name: instance_persistence_execute_percentile
exp: persistence_timer_bulk_execute_latency.sum(['le', 'service', 'instance']).increase('PT5M').histogram().histogram_percentile([50,70,90,99])
- name: instance_persistence_prepare_percentile
exp: persistence_timer_bulk_prepare_latency.sum(['le', 'service', 'instance']).increase('PT5M').histogram().histogram_percentile([50,70,90,99])
- name: instance_persistence_error_count
exp: persistence_timer_bulk_error_count.sum(['service', 'instance']).increase('PT5M')
- name: instance_persistence_execute_count
exp: persistence_timer_bulk_execute_latency_count.sum(['service', 'instance']).increase('PT5M')
- name: instance_persistence_prepare_count
exp: persistence_timer_bulk_prepare_latency_count.sum(['service', 'instance']).increase('PT5M')