Skip to content

Commit 8093767

Browse files
ddrechseddrechse
authored
Fix Helidon JVM requests-per-second dashboard query (#1423)
* Fix Helidon JVM requests-per-second dashboard query * Fix Helidon dashboard summaries to exclude stale pod metrics and clarify current versus peak values
1 parent 067c336 commit 8093767

3 files changed

Lines changed: 74 additions & 74 deletions

File tree

‎helm/infra-charts/obaas/dashboards/2/helidon_jvm_details.json‎

Lines changed: 52 additions & 52 deletions
Original file line numberDiff line numberDiff line change
@@ -450,7 +450,7 @@
450450
"key": "memory_usedHeap_bytes",
451451
"type": "Gauge"
452452
},
453-
"aggregateOperator": "latest",
453+
"aggregateOperator": "max",
454454
"dataSource": "metrics",
455455
"disabled": false,
456456
"expression": "A",
@@ -488,7 +488,7 @@
488488
"promql": [
489489
{
490490
"name": "A",
491-
"query": "sum(memory_usedHeap_bytes{namespace=~\"$namespace\", mp_app=~\"$app_name\"})",
491+
"query": "sum(last_over_time(memory_usedHeap_bytes{namespace=~\"$namespace\",mp_app=~\"$app_name\"}[2m]))",
492492
"legend": "memory_usedHeap_bytes"
493493
}
494494
],
@@ -618,7 +618,7 @@
618618
"promql": [
619619
{
620620
"name": "A",
621-
"query": "sum(memory_maxHeap_bytes{namespace=~\"$namespace\", mp_app=~\"$app_name\"})",
621+
"query": "sum(last_over_time(memory_maxHeap_bytes{namespace=~\"$namespace\",mp_app=~\"$app_name\"}[2m]))",
622622
"legend": "memory_maxHeap_bytes"
623623
}
624624
],
@@ -683,7 +683,7 @@
683683
"stackedBarChart": false,
684684
"thresholds": [],
685685
"timePreferance": "GLOBAL_TIME",
686-
"title": "Total Heap Available",
686+
"title": "Total Heap Max",
687687
"yAxisUnit": "decbytes"
688688
},
689689
{
@@ -787,7 +787,7 @@
787787
"promql": [
788788
{
789789
"name": "A",
790-
"query": "(sum(memory_usedHeap_bytes{namespace=~\"$namespace\", mp_app=~\"$app_name\"}))/(sum(memory_maxHeap_bytes{namespace=~\"$namespace\", mp_app=~\"$app_name\"}))",
790+
"query": "sum(last_over_time(memory_usedHeap_bytes{namespace=~\"$namespace\",mp_app=~\"$app_name\"}[2m])) / sum(last_over_time(memory_maxHeap_bytes{namespace=~\"$namespace\",mp_app=~\"$app_name\"}[2m]))",
791791
"legend": ""
792792
}
793793
],
@@ -931,7 +931,7 @@
931931
"promql": [
932932
{
933933
"name": "A",
934-
"query": "avg(thread_count{namespace=~\"$namespace\", mp_app=~\"$app_name\"})",
934+
"query": "sum(last_over_time(thread_count{namespace=~\"$namespace\",mp_app=~\"$app_name\"}[2m]))",
935935
"legend": "thread_count"
936936
}
937937
],
@@ -1061,7 +1061,7 @@
10611061
"promql": [
10621062
{
10631063
"name": "A",
1064-
"query": "sum(jvm_uptime_seconds{namespace=~\"$namespace\", mp_app=~\"$app_name\"})",
1064+
"query": "max(last_over_time(jvm_uptime_seconds{namespace=~\"$namespace\",mp_app=~\"$app_name\"}[2m]))",
10651065
"legend": "jvm_uptime_seconds"
10661066
}
10671067
],
@@ -1126,7 +1126,7 @@
11261126
"stackedBarChart": false,
11271127
"thresholds": [],
11281128
"timePreferance": "GLOBAL_TIME",
1129-
"title": "JVM Uptime",
1129+
"title": "JVM Uptime (Longest Running)",
11301130
"yAxisUnit": "s"
11311131
},
11321132
{
@@ -1168,7 +1168,7 @@
11681168
"limit": null,
11691169
"orderBy": [],
11701170
"queryName": "A",
1171-
"reduceTo": "sum",
1171+
"reduceTo": "last",
11721172
"spaceAggregation": "sum",
11731173
"stepInterval": 60,
11741174
"timeAggregation": "increase",
@@ -1256,7 +1256,7 @@
12561256
"stackedBarChart": false,
12571257
"thresholds": [],
12581258
"timePreferance": "GLOBAL_TIME",
1259-
"title": "Total GC's",
1259+
"title": "GC Collections (Last 5m)",
12601260
"yAxisUnit": "none"
12611261
},
12621262
{
@@ -1310,7 +1310,7 @@
13101310
"limit": null,
13111311
"orderBy": [],
13121312
"queryName": "A",
1313-
"reduceTo": "sum",
1313+
"reduceTo": "last",
13141314
"spaceAggregation": "sum",
13151315
"stepInterval": 60,
13161316
"timeAggregation": "increase",
@@ -1398,7 +1398,7 @@
13981398
"stackedBarChart": false,
13991399
"thresholds": [],
14001400
"timePreferance": "GLOBAL_TIME",
1401-
"title": "Total GC Time",
1401+
"title": "GC Time (Last 5m)",
14021402
"yAxisUnit": "s"
14031403
},
14041404
{
@@ -1468,7 +1468,7 @@
14681468
"functions": [],
14691469
"groupBy": [],
14701470
"having": [],
1471-
"legend": "Total Heap Available",
1471+
"legend": "Total Heap Max",
14721472
"limit": null,
14731473
"orderBy": [],
14741474
"queryName": "B",
@@ -1501,7 +1501,7 @@
15011501
{
15021502
"name": "B",
15031503
"query": "sum(memory_maxHeap_bytes{namespace=~\"$namespace\", mp_app=~\"$app_name\"})",
1504-
"legend": "Total Heap Available"
1504+
"legend": "Total Heap Max"
15051505
}
15061506
],
15071507
"queryType": "promql"
@@ -1614,7 +1614,7 @@
16141614
"functions": [],
16151615
"groupBy": [],
16161616
"having": [],
1617-
"legend": "Total Heap Used Last",
1617+
"legend": "Current Heap Used",
16181618
"limit": null,
16191619
"orderBy": [],
16201620
"queryName": "A",
@@ -1646,7 +1646,7 @@
16461646
"functions": [],
16471647
"groupBy": [],
16481648
"having": [],
1649-
"legend": "Total Heap Available Last",
1649+
"legend": "Current Heap Max",
16501650
"limit": null,
16511651
"orderBy": [],
16521652
"queryName": "B",
@@ -1667,7 +1667,7 @@
16671667
"key": "memory_usedHeap_bytes",
16681668
"type": "Gauge"
16691669
},
1670-
"aggregateOperator": "max",
1670+
"aggregateOperator": "latest",
16711671
"dataSource": "metrics",
16721672
"disabled": false,
16731673
"expression": "C",
@@ -1678,7 +1678,7 @@
16781678
"functions": [],
16791679
"groupBy": [],
16801680
"having": [],
1681-
"legend": "Total Heap Used Max",
1681+
"legend": "Peak Heap Used (5m)",
16821682
"limit": null,
16831683
"orderBy": [],
16841684
"queryName": "C",
@@ -1710,7 +1710,7 @@
17101710
"functions": [],
17111711
"groupBy": [],
17121712
"having": [],
1713-
"legend": "Total Heap Available Max",
1713+
"legend": "Peak Heap Max (5m)",
17141714
"limit": null,
17151715
"orderBy": [],
17161716
"queryName": "D",
@@ -1737,23 +1737,23 @@
17371737
"promql": [
17381738
{
17391739
"name": "A",
1740-
"query": "sum(memory_usedHeap_bytes{namespace=~\"$namespace\", mp_app=~\"$app_name\"})",
1741-
"legend": "Total Heap Used Last"
1740+
"query": "sum(last_over_time(memory_usedHeap_bytes{namespace=~\"$namespace\",mp_app=~\"$app_name\"}[2m]))",
1741+
"legend": "Current Heap Used"
17421742
},
17431743
{
17441744
"name": "B",
1745-
"query": "sum(memory_maxHeap_bytes{namespace=~\"$namespace\", mp_app=~\"$app_name\"})",
1746-
"legend": "Total Heap Available Last"
1745+
"query": "sum(last_over_time(memory_maxHeap_bytes{namespace=~\"$namespace\",mp_app=~\"$app_name\"}[2m]))",
1746+
"legend": "Current Heap Max"
17471747
},
17481748
{
17491749
"name": "C",
1750-
"query": "sum(memory_usedHeap_bytes{namespace=~\"$namespace\", mp_app=~\"$app_name\"})",
1751-
"legend": "Total Heap Used Max"
1750+
"query": "sum(max_over_time(memory_usedHeap_bytes{namespace=~\"$namespace\",mp_app=~\"$app_name\"}[5m]))",
1751+
"legend": "Peak Heap Used (5m)"
17521752
},
17531753
{
17541754
"name": "D",
1755-
"query": "sum(memory_maxHeap_bytes{namespace=~\"$namespace\", mp_app=~\"$app_name\"})",
1756-
"legend": "Total Heap Available Max"
1755+
"query": "sum(max_over_time(memory_maxHeap_bytes{namespace=~\"$namespace\",mp_app=~\"$app_name\"}[5m]))",
1756+
"legend": "Peak Heap Max (5m)"
17571757
}
17581758
],
17591759
"queryType": "promql"
@@ -1817,7 +1817,7 @@
18171817
"stackedBarChart": false,
18181818
"thresholds": [],
18191819
"timePreferance": "GLOBAL_TIME",
1820-
"title": "Memory Usage",
1820+
"title": "Memory Usage (Current and 5m Peak)",
18211821
"yAxisUnit": "decbytes"
18221822
},
18231823
{
@@ -2124,7 +2124,7 @@
21242124
"functions": [],
21252125
"groupBy": [],
21262126
"having": [],
2127-
"legend": "CPU Load Average Last",
2127+
"legend": "Current CPU Load",
21282128
"limit": null,
21292129
"orderBy": [],
21302130
"queryName": "A",
@@ -2156,7 +2156,7 @@
21562156
"functions": [],
21572157
"groupBy": [],
21582158
"having": [],
2159-
"legend": "CPU Load Average Max",
2159+
"legend": "Peak CPU Load (5m)",
21602160
"limit": null,
21612161
"orderBy": [],
21622162
"queryName": "B",
@@ -2183,13 +2183,13 @@
21832183
"promql": [
21842184
{
21852185
"name": "A",
2186-
"query": "sum(cpu_systemLoadAverage{namespace=~\"$namespace\", mp_app=~\"$app_name\"})",
2187-
"legend": "CPU Load Average Last"
2186+
"query": "sum(last_over_time(cpu_systemLoadAverage{namespace=~\"$namespace\",mp_app=~\"$app_name\"}[2m]))",
2187+
"legend": "Current CPU Load"
21882188
},
21892189
{
21902190
"name": "B",
2191-
"query": "sum(cpu_systemLoadAverage{namespace=~\"$namespace\", mp_app=~\"$app_name\"})",
2192-
"legend": "CPU Load Average Max"
2191+
"query": "sum(max_over_time(cpu_systemLoadAverage{namespace=~\"$namespace\",mp_app=~\"$app_name\"}[5m]))",
2192+
"legend": "Peak CPU Load (5m)"
21932193
}
21942194
],
21952195
"queryType": "promql"
@@ -2284,7 +2284,7 @@
22842284
"reduceTo": "avg",
22852285
"spaceAggregation": "sum",
22862286
"temporality": "",
2287-
"timeAggregation": "increase"
2287+
"timeAggregation": "rate"
22882288
}
22892289
],
22902290
"dataSource": "metrics",
@@ -2324,7 +2324,7 @@
23242324
"promql": [
23252325
{
23262326
"name": "B",
2327-
"query": "sum(increase(requests_count_total{namespace=~\"$namespace\", mp_app=~\"$app_name\"}[5m]))",
2327+
"query": "sum(rate(requests_count_total{namespace=~\"$namespace\", mp_app=~\"$app_name\"}[1m]))",
23282328
"legend": "Requests Per Second"
23292329
}
23302330
],
@@ -2433,14 +2433,14 @@
24332433
"functions": [],
24342434
"groupBy": [],
24352435
"having": [],
2436-
"legend": "Peak Active Virtual Threads",
2436+
"legend": "Current Active Virtual Threads",
24372437
"limit": null,
24382438
"orderBy": [],
24392439
"queryName": "A",
2440-
"reduceTo": "max",
2440+
"reduceTo": "last",
24412441
"spaceAggregation": "sum",
24422442
"stepInterval": 60,
2443-
"timeAggregation": "max",
2443+
"timeAggregation": "latest",
24442444
"filter": {
24452445
"expression": ""
24462446
}
@@ -2460,8 +2460,8 @@
24602460
"promql": [
24612461
{
24622462
"name": "A",
2463-
"query": "sum(vthreads_count{namespace=~\"$namespace\", mp_app=~\"$app_name\"})",
2464-
"legend": "Active Virtual Threads"
2463+
"query": "sum(last_over_time(vthreads_count{namespace=~\"$namespace\",mp_app=~\"$app_name\"}[2m]))",
2464+
"legend": "Current Active Virtual Threads"
24652465
}
24662466
],
24672467
"queryType": "promql"
@@ -2525,7 +2525,7 @@
25252525
"stackedBarChart": false,
25262526
"thresholds": [],
25272527
"timePreferance": "GLOBAL_TIME",
2528-
"title": "Peak Active Virtual Threads",
2528+
"title": "Current Active Virtual Threads",
25292529
"yAxisUnit": "none"
25302530
},
25312531
{
@@ -2590,7 +2590,7 @@
25902590
"promql": [
25912591
{
25922592
"name": "A",
2593-
"query": "sum(vthreads_starts{namespace=~\"$namespace\", mp_app=~\"$app_name\"})",
2593+
"query": "sum(last_over_time(vthreads_starts{namespace=~\"$namespace\",mp_app=~\"$app_name\"}[2m]))",
25942594
"legend": "Virtual Thread Starts"
25952595
}
25962596
],
@@ -2682,7 +2682,7 @@
26822682
"key": "vthreads_pinned",
26832683
"type": "Gauge"
26842684
},
2685-
"aggregateOperator": "max",
2685+
"aggregateOperator": "latest",
26862686
"dataSource": "metrics",
26872687
"disabled": false,
26882688
"expression": "A",
@@ -2693,14 +2693,14 @@
26932693
"functions": [],
26942694
"groupBy": [],
26952695
"having": [],
2696-
"legend": "Peak Pinned Virtual Threads",
2696+
"legend": "Current Pinned Virtual Threads",
26972697
"limit": null,
26982698
"orderBy": [],
26992699
"queryName": "A",
2700-
"reduceTo": "max",
2700+
"reduceTo": "last",
27012701
"spaceAggregation": "sum",
27022702
"stepInterval": 60,
2703-
"timeAggregation": "max",
2703+
"timeAggregation": "latest",
27042704
"filter": {
27052705
"expression": ""
27062706
}
@@ -2720,8 +2720,8 @@
27202720
"promql": [
27212721
{
27222722
"name": "A",
2723-
"query": "sum(vthreads_pinned{namespace=~\"$namespace\", mp_app=~\"$app_name\"})",
2724-
"legend": "Pinned Virtual Threads"
2723+
"query": "sum(last_over_time(vthreads_pinned{namespace=~\"$namespace\",mp_app=~\"$app_name\"}[2m]))",
2724+
"legend": "Current Pinned Virtual Threads"
27252725
}
27262726
],
27272727
"queryType": "promql"
@@ -2785,7 +2785,7 @@
27852785
"stackedBarChart": false,
27862786
"thresholds": [],
27872787
"timePreferance": "GLOBAL_TIME",
2788-
"title": "Peak Pinned Virtual Threads",
2788+
"title": "Current Pinned Virtual Threads",
27892789
"yAxisUnit": "none"
27902790
},
27912791
{
@@ -2850,7 +2850,7 @@
28502850
"promql": [
28512851
{
28522852
"name": "A",
2853-
"query": "sum(vthreads_submitFailures{namespace=~\"$namespace\", mp_app=~\"$app_name\"})",
2853+
"query": "sum(last_over_time(vthreads_submitFailures{namespace=~\"$namespace\",mp_app=~\"$app_name\"}[2m]))",
28542854
"legend": "Submit Failures"
28552855
}
28562856
],
@@ -3110,7 +3110,7 @@
31103110
"promql": [
31113111
{
31123112
"name": "A",
3113-
"query": "max(vthreads_recentPinned_seconds{namespace=~\"$namespace\", mp_app=~\"$app_name\", quantile=\"0.95\"})",
3113+
"query": "max(last_over_time(vthreads_recentPinned_seconds{namespace=~\"$namespace\",mp_app=~\"$app_name\",quantile=\"0.95\"}[2m]))",
31143114
"legend": "Pinned Duration p95"
31153115
}
31163116
],

‎helm/infra-charts/obaas/dashboards/2/helidon_main_dashboard.json‎

Lines changed: 1 addition & 1 deletion
Large diffs are not rendered by default.

0 commit comments

Comments
 (0)