Skip to content

Commit a85baa8

Browse files
authored
Merge pull request ceph#55314 from cloudbehl/rgw-dashboard-json
mgr/dashboard: Fixing RGW graph panels Reviewed-by: Aashish Sharma <[email protected]>
2 parents 137ea0f + 65e6714 commit a85baa8

File tree

6 files changed

+51
-51
lines changed

6 files changed

+51
-51
lines changed

monitoring/ceph-mixin/dashboards/rgw.libsonnet

Lines changed: 18 additions & 18 deletions
Original file line numberDiff line numberDiff line change
@@ -263,8 +263,8 @@ local u = import 'utils.libsonnet';
263263
'short',
264264
|||
265265
label_replace(
266-
rate(ceph_rgw_get_initial_lat_sum{%(matchers)s}[$__rate_interval]) /
267-
rate(ceph_rgw_get_initial_lat_count{%(matchers)s}[$__rate_interval]) *
266+
rate(ceph_rgw_op_get_obj_lat_sum{%(matchers)s}[$__rate_interval]) /
267+
rate(ceph_rgw_op_get_obj_lat_count{%(matchers)s}[$__rate_interval]) *
268268
on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{%(matchers)s},
269269
"rgw_host", "$1", "ceph_daemon", "rgw.(.*)"
270270
)
@@ -279,8 +279,8 @@ local u = import 'utils.libsonnet';
279279
$.addTargetSchema(
280280
|||
281281
label_replace(
282-
rate(ceph_rgw_put_initial_lat_sum{%(matchers)s}[$__rate_interval]) /
283-
rate(ceph_rgw_put_initial_lat_count{%(matchers)s}[$__rate_interval]) *
282+
rate(ceph_rgw_op_put_obj_lat_sum{%(matchers)s}[$__rate_interval]) /
283+
rate(ceph_rgw_op_put_obj_lat_count{%(matchers)s}[$__rate_interval]) *
284284
on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{%(matchers)s},
285285
"rgw_host", "$1", "ceph_daemon", "rgw.(.*)"
286286
)
@@ -316,8 +316,8 @@ local u = import 'utils.libsonnet';
316316
'short',
317317
|||
318318
label_replace(
319-
rate(ceph_rgw_get_initial_lat_sum{%(matchers)s}[$__rate_interval]) /
320-
rate(ceph_rgw_get_initial_lat_count{%(matchers)s}[$__rate_interval]) *
319+
rate(ceph_rgw_op_get_obj_lat_sum{%(matchers)s}[$__rate_interval]) /
320+
rate(ceph_rgw_op_get_obj_lat_count{%(matchers)s}[$__rate_interval]) *
321321
on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{%(matchers)s},
322322
"rgw_host", "$1", "ceph_daemon", "rgw.(.*)"
323323
)
@@ -333,14 +333,14 @@ local u = import 'utils.libsonnet';
333333
'Total bytes transferred in/out of all radosgw instances within the cluster',
334334
'bytes',
335335
'short',
336-
'sum(rate(ceph_rgw_get_b{%(matchers)s}[$__rate_interval]))' % $.matchers(),
336+
'sum(rate(ceph_rgw_op_get_obj_bytes{%(matchers)s}[$__rate_interval]))' % $.matchers(),
337337
'GETs',
338338
0,
339339
8,
340340
8,
341341
6
342342
).addTargets(
343-
[$.addTargetSchema('sum(rate(ceph_rgw_put_b{%(matchers)s}[$__rate_interval]))' % $.matchers(),
343+
[$.addTargetSchema('sum(rate(ceph_rgw_op_put_obj_bytes{%(matchers)s}[$__rate_interval]))' % $.matchers(),
344344
'PUTs')]
345345
),
346346
RgwOverviewPanel(
@@ -350,8 +350,8 @@ local u = import 'utils.libsonnet';
350350
'short',
351351
|||
352352
label_replace(sum by (instance_id) (
353-
rate(ceph_rgw_get_b{%(matchers)s}[$__rate_interval]) +
354-
rate(ceph_rgw_put_b{%(matchers)s}[$__rate_interval])) *
353+
rate(ceph_rgw_op_get_obj_bytes{%(matchers)s}[$__rate_interval]) +
354+
rate(ceph_rgw_op_put_obj_bytes{%(matchers)s}[$__rate_interval])) *
355355
on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{%(matchers)s},
356356
"rgw_host", "$1", "ceph_daemon", "rgw.(.*)"
357357
)
@@ -369,8 +369,8 @@ local u = import 'utils.libsonnet';
369369
'short',
370370
|||
371371
label_replace(
372-
rate(ceph_rgw_put_initial_lat_sum{%(matchers)s}[$__rate_interval]) /
373-
rate(ceph_rgw_put_initial_lat_count{%(matchers)s}[$__rate_interval]) *
372+
rate(ceph_rgw_op_put_obj_lat_sum{%(matchers)s}[$__rate_interval]) /
373+
rate(ceph_rgw_op_put_obj_lat_count{%(matchers)s}[$__rate_interval]) *
374374
on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{%(matchers)s},
375375
"rgw_host", "$1", "ceph_daemon", "rgw.(.*)"
376376
)
@@ -736,14 +736,14 @@ local u = import 'utils.libsonnet';
736736
'short',
737737
|||
738738
sum by (instance_id) (
739-
rate(ceph_rgw_get_initial_lat_sum{%(matchers)s}[$__rate_interval]) /
740-
rate(ceph_rgw_get_initial_lat_count{%(matchers)s}[$__rate_interval])
739+
rate(ceph_rgw_op_get_obj_lat_sum{%(matchers)s}[$__rate_interval]) /
740+
rate(ceph_rgw_op_get_obj_lat_count{%(matchers)s}[$__rate_interval])
741741
) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{%(matchers)s, ceph_daemon=~"$rgw_servers"}
742742
||| % $.matchers(),
743743
|||
744744
sum by (instance_id) (
745-
rate(ceph_rgw_put_initial_lat_sum{%(matchers)s}[$__rate_interval]) /
746-
rate(ceph_rgw_put_initial_lat_count{%(matchers)s}[$__rate_interval])
745+
rate(ceph_rgw_op_put_obj_lat_sum{%(matchers)s}[$__rate_interval]) /
746+
rate(ceph_rgw_op_put_obj_lat_count{%(matchers)s}[$__rate_interval])
747747
) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{%(matchers)s, ceph_daemon=~"$rgw_servers"}
748748
||| % $.matchers(),
749749
'GET {{ceph_daemon}}',
@@ -760,11 +760,11 @@ local u = import 'utils.libsonnet';
760760
'bytes',
761761
'short',
762762
|||
763-
rate(ceph_rgw_get_b{%(matchers)s}[$__rate_interval]) *
763+
rate(ceph_rgw_op_get_obj_bytes{%(matchers)s}[$__rate_interval]) *
764764
on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{%(matchers)s, ceph_daemon=~"$rgw_servers"}
765765
||| % $.matchers(),
766766
|||
767-
rate(ceph_rgw_put_b{%(matchers)s}[$__rate_interval]) *
767+
rate(ceph_rgw_op_put_obj_bytes{%(matchers)s}[$__rate_interval]) *
768768
on (instance_id) group_left (ceph_daemon)
769769
ceph_rgw_metadata{%(matchers)s, ceph_daemon=~"$rgw_servers"}
770770
||| % $.matchers(),

monitoring/ceph-mixin/dashboards_out/radosgw-detail.json

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -114,14 +114,14 @@
114114
"steppedLine": false,
115115
"targets": [
116116
{
117-
"expr": "sum by (instance_id) (\n rate(ceph_rgw_get_initial_lat_sum{job=~\"$job\"}[$__rate_interval]) /\n rate(ceph_rgw_get_initial_lat_count{job=~\"$job\"}[$__rate_interval])\n) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{job=~\"$job\", ceph_daemon=~\"$rgw_servers\"}\n",
117+
"expr": "sum by (instance_id) (\n rate(ceph_rgw_op_get_obj_lat_sum{job=~\"$job\"}[$__rate_interval]) /\n rate(ceph_rgw_op_get_obj_lat_count{job=~\"$job\"}[$__rate_interval])\n) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{job=~\"$job\", ceph_daemon=~\"$rgw_servers\"}\n",
118118
"format": "time_series",
119119
"intervalFactor": 1,
120120
"legendFormat": "GET {{ceph_daemon}}",
121121
"refId": "A"
122122
},
123123
{
124-
"expr": "sum by (instance_id) (\n rate(ceph_rgw_put_initial_lat_sum{job=~\"$job\"}[$__rate_interval]) /\n rate(ceph_rgw_put_initial_lat_count{job=~\"$job\"}[$__rate_interval])\n) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{job=~\"$job\", ceph_daemon=~\"$rgw_servers\"}\n",
124+
"expr": "sum by (instance_id) (\n rate(ceph_rgw_op_put_obj_lat_sum{job=~\"$job\"}[$__rate_interval]) /\n rate(ceph_rgw_op_put_obj_lat_count{job=~\"$job\"}[$__rate_interval])\n) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{job=~\"$job\", ceph_daemon=~\"$rgw_servers\"}\n",
125125
"format": "time_series",
126126
"intervalFactor": 1,
127127
"legendFormat": "PUT {{ceph_daemon}}",
@@ -216,14 +216,14 @@
216216
"steppedLine": false,
217217
"targets": [
218218
{
219-
"expr": "rate(ceph_rgw_get_b{job=~\"$job\"}[$__rate_interval]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{job=~\"$job\", ceph_daemon=~\"$rgw_servers\"}\n",
219+
"expr": "rate(ceph_rgw_op_get_obj_bytes{job=~\"$job\"}[$__rate_interval]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{job=~\"$job\", ceph_daemon=~\"$rgw_servers\"}\n",
220220
"format": "time_series",
221221
"intervalFactor": 1,
222222
"legendFormat": "GETs {{ceph_daemon}}",
223223
"refId": "A"
224224
},
225225
{
226-
"expr": "rate(ceph_rgw_put_b{job=~\"$job\"}[$__rate_interval]) *\n on (instance_id) group_left (ceph_daemon)\n ceph_rgw_metadata{job=~\"$job\", ceph_daemon=~\"$rgw_servers\"}\n",
226+
"expr": "rate(ceph_rgw_op_put_obj_bytes{job=~\"$job\"}[$__rate_interval]) *\n on (instance_id) group_left (ceph_daemon)\n ceph_rgw_metadata{job=~\"$job\", ceph_daemon=~\"$rgw_servers\"}\n",
227227
"format": "time_series",
228228
"intervalFactor": 1,
229229
"legendFormat": "PUTs {{ceph_daemon}}",

monitoring/ceph-mixin/dashboards_out/radosgw-overview.json

Lines changed: 7 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -108,14 +108,14 @@
108108
"steppedLine": false,
109109
"targets": [
110110
{
111-
"expr": "label_replace(\n rate(ceph_rgw_get_initial_lat_sum{job=~\"$job\"}[$__rate_interval]) /\n rate(ceph_rgw_get_initial_lat_count{job=~\"$job\"}[$__rate_interval]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{job=~\"$job\"},\n \"rgw_host\", \"$1\", \"ceph_daemon\", \"rgw.(.*)\"\n)\n",
111+
"expr": "label_replace(\n rate(ceph_rgw_op_get_obj_lat_sum{job=~\"$job\"}[$__rate_interval]) /\n rate(ceph_rgw_op_get_obj_lat_count{job=~\"$job\"}[$__rate_interval]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{job=~\"$job\"},\n \"rgw_host\", \"$1\", \"ceph_daemon\", \"rgw.(.*)\"\n)\n",
112112
"format": "time_series",
113113
"intervalFactor": 1,
114114
"legendFormat": "GET {{rgw_host}}",
115115
"refId": "A"
116116
},
117117
{
118-
"expr": "label_replace(\n rate(ceph_rgw_put_initial_lat_sum{job=~\"$job\"}[$__rate_interval]) /\n rate(ceph_rgw_put_initial_lat_count{job=~\"$job\"}[$__rate_interval]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{job=~\"$job\"},\n \"rgw_host\", \"$1\", \"ceph_daemon\", \"rgw.(.*)\"\n)\n",
118+
"expr": "label_replace(\n rate(ceph_rgw_op_put_obj_lat_sum{job=~\"$job\"}[$__rate_interval]) /\n rate(ceph_rgw_op_put_obj_lat_count{job=~\"$job\"}[$__rate_interval]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{job=~\"$job\"},\n \"rgw_host\", \"$1\", \"ceph_daemon\", \"rgw.(.*)\"\n)\n",
119119
"format": "time_series",
120120
"intervalFactor": 1,
121121
"legendFormat": "PUT {{rgw_host}}",
@@ -305,7 +305,7 @@
305305
"steppedLine": false,
306306
"targets": [
307307
{
308-
"expr": "label_replace(\n rate(ceph_rgw_get_initial_lat_sum{job=~\"$job\"}[$__rate_interval]) /\n rate(ceph_rgw_get_initial_lat_count{job=~\"$job\"}[$__rate_interval]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{job=~\"$job\"},\n \"rgw_host\", \"$1\", \"ceph_daemon\", \"rgw.(.*)\"\n)\n",
308+
"expr": "label_replace(\n rate(ceph_rgw_op_get_obj_lat_sum{job=~\"$job\"}[$__rate_interval]) /\n rate(ceph_rgw_op_get_obj_lat_count{job=~\"$job\"}[$__rate_interval]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{job=~\"$job\"},\n \"rgw_host\", \"$1\", \"ceph_daemon\", \"rgw.(.*)\"\n)\n",
309309
"format": "time_series",
310310
"intervalFactor": 1,
311311
"legendFormat": "{{rgw_host}}",
@@ -400,14 +400,14 @@
400400
"steppedLine": false,
401401
"targets": [
402402
{
403-
"expr": "sum(rate(ceph_rgw_get_b{job=~\"$job\"}[$__rate_interval]))",
403+
"expr": "sum(rate(ceph_rgw_op_get_obj_bytes{job=~\"$job\"}[$__rate_interval]))",
404404
"format": "time_series",
405405
"intervalFactor": 1,
406406
"legendFormat": "GETs",
407407
"refId": "A"
408408
},
409409
{
410-
"expr": "sum(rate(ceph_rgw_put_b{job=~\"$job\"}[$__rate_interval]))",
410+
"expr": "sum(rate(ceph_rgw_op_put_obj_bytes{job=~\"$job\"}[$__rate_interval]))",
411411
"format": "time_series",
412412
"intervalFactor": 1,
413413
"legendFormat": "PUTs",
@@ -502,7 +502,7 @@
502502
"steppedLine": false,
503503
"targets": [
504504
{
505-
"expr": "label_replace(sum by (instance_id) (\n rate(ceph_rgw_get_b{job=~\"$job\"}[$__rate_interval]) +\n rate(ceph_rgw_put_b{job=~\"$job\"}[$__rate_interval])) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{job=~\"$job\"},\n \"rgw_host\", \"$1\", \"ceph_daemon\", \"rgw.(.*)\"\n)\n",
505+
"expr": "label_replace(sum by (instance_id) (\n rate(ceph_rgw_op_get_obj_bytes{job=~\"$job\"}[$__rate_interval]) +\n rate(ceph_rgw_op_put_obj_bytes{job=~\"$job\"}[$__rate_interval])) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{job=~\"$job\"},\n \"rgw_host\", \"$1\", \"ceph_daemon\", \"rgw.(.*)\"\n)\n",
506506
"format": "time_series",
507507
"intervalFactor": 1,
508508
"legendFormat": "{{rgw_host}}",
@@ -597,7 +597,7 @@
597597
"steppedLine": false,
598598
"targets": [
599599
{
600-
"expr": "label_replace(\n rate(ceph_rgw_put_initial_lat_sum{job=~\"$job\"}[$__rate_interval]) /\n rate(ceph_rgw_put_initial_lat_count{job=~\"$job\"}[$__rate_interval]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{job=~\"$job\"},\n \"rgw_host\", \"$1\", \"ceph_daemon\", \"rgw.(.*)\"\n)\n",
600+
"expr": "label_replace(\n rate(ceph_rgw_op_put_obj_lat_sum{job=~\"$job\"}[$__rate_interval]) /\n rate(ceph_rgw_op_put_obj_lat_count{job=~\"$job\"}[$__rate_interval]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{job=~\"$job\"},\n \"rgw_host\", \"$1\", \"ceph_daemon\", \"rgw.(.*)\"\n)\n",
601601
"format": "time_series",
602602
"intervalFactor": 1,
603603
"legendFormat": "{{rgw_host}}",

monitoring/ceph-mixin/tests_dashboards/features/radosgw-detail.feature

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -3,8 +3,8 @@ Feature: RGW Host Detail Dashboard
33
Scenario: "Test $rgw_servers GET/PUT Latencies - GET"
44
Given the following series:
55
| metrics | values |
6-
| ceph_rgw_get_initial_lat_sum{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 10 50 100 |
7-
| ceph_rgw_get_initial_lat_count{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 20 60 80 |
6+
| ceph_rgw_op_get_obj_lat_sum{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 10 50 100 |
7+
| ceph_rgw_op_get_obj_lat_count{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 20 60 80 |
88
| ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
99
When interval is `30s`
1010
And variable `rgw_servers` is `rgw.foo`
@@ -15,8 +15,8 @@ Scenario: "Test $rgw_servers GET/PUT Latencies - GET"
1515
Scenario: "Test $rgw_servers GET/PUT Latencies - PUT"
1616
Given the following series:
1717
| metrics | values |
18-
| ceph_rgw_put_initial_lat_sum{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 15 35 55 |
19-
| ceph_rgw_put_initial_lat_count{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 10 30 50 |
18+
| ceph_rgw_op_put_obj_lat_sum{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 15 35 55 |
19+
| ceph_rgw_op_put_obj_lat_count{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 10 30 50 |
2020
| ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
2121
When interval is `30s`
2222
And variable `rgw_servers` is `rgw.foo`
@@ -27,7 +27,7 @@ Scenario: "Test $rgw_servers GET/PUT Latencies - PUT"
2727
Scenario: "Test Bandwidth by HTTP Operation - GET"
2828
Given the following series:
2929
| metrics | values |
30-
| ceph_rgw_get_b{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 10 50 100 |
30+
| ceph_rgw_op_get_obj_bytes{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 10 50 100 |
3131
| ceph_rgw_metadata{ceph_daemon="rgw.1", hostname="localhost", instance="127.0.0.1", instance_id="92806566", job="ceph"} | 1 1 1 |
3232
When interval is `30s`
3333
And variable `rgw_servers` is `rgw.1`
@@ -38,7 +38,7 @@ Scenario: "Test Bandwidth by HTTP Operation - GET"
3838
Scenario: "Test Bandwidth by HTTP Operation - PUT"
3939
Given the following series:
4040
| metrics | values |
41-
| ceph_rgw_put_b{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 5 20 50 |
41+
| ceph_rgw_op_put_obj_bytes{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 5 20 50 |
4242
| ceph_rgw_metadata{ceph_daemon="rgw.1", hostname="localhost", instance="127.0.0.1", instance_id="92806566", job="ceph"} | 1 1 1 |
4343
When interval is `30s`
4444
And variable `rgw_servers` is `rgw.1`

0 commit comments

Comments
 (0)