Merge "add logic for updating ceph client caps"
diff --git a/ceph/backup.sls b/ceph/backup.sls
index 7963e5c..5067012 100644
--- a/ceph/backup.sls
+++ b/ceph/backup.sls
@@ -54,6 +54,8 @@
{%- endif %}
{%- if backup.client.backup_times.minute is defined %}
- minute: {{ backup.client.backup_times.minute }}
+{%- else %}
+ - minute: 0
{%- endif %}
{%- elif backup.client.hours_before_incr is defined %}
- minute: 0
@@ -155,6 +157,8 @@
{%- endif %}
{%- if backup.server.backup_times.minute is defined %}
- minute: {{ backup.server.backup_times.minute }}
+{%- else %}
+ - minute: 0
{%- endif %}
{%- elif backup.server.hours_before_incr is defined %}
- minute: 0
diff --git a/ceph/files/grafana_dashboards/ceph-cluster_prometheus.json b/ceph/files/grafana_dashboards/ceph-cluster_prometheus.json
index e88d09f..5770143 100644
--- a/ceph/files/grafana_dashboards/ceph-cluster_prometheus.json
+++ b/ceph/files/grafana_dashboards/ceph-cluster_prometheus.json
@@ -758,14 +758,14 @@
"steppedLine": false,
"targets": [
{
- "expr": "sum(irate(ceph_osd_op_w_in_bytes{instance=~\"$instance\"}[1m]))",
+ "expr": "sum(irate(ceph_osd_op_w_in_bytes{instance=~\"$instance\"}[$rate_interval]))",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "Writes",
"refId": "A"
},
{
- "expr": "sum(irate(ceph_osd_op_r_out_bytes{instance=~\"$instance\"}[1m]))",
+ "expr": "sum(irate(ceph_osd_op_r_out_bytes{instance=~\"$instance\"}[$rate_interval]))",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "Reads",
@@ -849,7 +849,7 @@
"steppedLine": false,
"targets": [
{
- "expr": "sum(deriv(ceph_pool_bytes_used{instance=~\"$instance\"}[1m]))",
+ "expr": "sum(deriv(ceph_pool_bytes_used{instance=~\"$instance\"}[$rate_interval]))",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "Bytes",
@@ -1059,7 +1059,7 @@
"steppedLine": false,
"targets": [
{
- "expr": "sum(irate(ceph_osd_recovery_ops[1m]))",
+ "expr": "sum(irate(ceph_osd_recovery_ops[$rate_interval]))",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "Op/s",
@@ -1218,6 +1218,49 @@
"tagsQuery": "",
"type": "query",
"useTags": false
+ },
+ {
+ "allValue": null,
+ "current": {
+ "tags": [],
+ "text": "3m",
+ "value": "3m"
+ },
+ "hide": 0,
+ "includeAll": false,
+ "label": "rate_interval",
+ "multi": false,
+ "name": "rate_interval",
+ "options": [
+ {
+ "selected": false,
+ "text": "1m",
+ "value": "1m"
+ },
+ {
+ "selected": true,
+ "text": "3m",
+ "value": "3m"
+ },
+ {
+ "selected": false,
+ "text": "5m",
+ "value": "5m"
+ },
+ {
+ "selected": false,
+ "text": "10m",
+ "value": "10m"
+ },
+ {
+ "selected": false,
+ "text": "15m",
+ "value": "15m"
+ }
+ ],
+ "query": "1m,3m,5m,10m,15m",
+ "skipUrlSync": false,
+ "type": "custom"
}
]
},
diff --git a/ceph/files/grafana_dashboards/hosts-overview_prometheus.json b/ceph/files/grafana_dashboards/hosts-overview_prometheus.json
index 8112cee..921f886 100644
--- a/ceph/files/grafana_dashboards/hosts-overview_prometheus.json
+++ b/ceph/files/grafana_dashboards/hosts-overview_prometheus.json
@@ -577,7 +577,7 @@
"tableColumn": "Value",
"targets": [
{
- "expr": "avg ( (irate(diskio_io_time{host=~\"($osd_hosts).*\"}[5m]) / 10 ) )",
+ "expr": "avg ( (irate(diskio_io_time{host=~\"($osd_hosts).*\"}[5m])) )",
"format": "table",
"instant": true,
"intervalFactor": 1,
@@ -660,7 +660,7 @@
"tableColumn": "Value",
"targets": [
{
- "expr": "sum (\n irate(net_bytes_recv{host=~\"($osd_hosts|mon_hosts|rgw_hosts).*\",device!=\"lo\"}[1m])\n ) +\nsum (\n irate(net_bytes_sent{host=~\"($osd_hosts|mon_hosts|rgw_hosts).*\",device!=\"lo\"}[1m]) \n )",
+ "expr": "sum (\n irate(net_bytes_recv{host=~\"($osd_hosts|mon_hosts|rgw_hosts).*\",device!=\"lo\"}[$rate_interval])\n ) +\nsum (\n irate(net_bytes_sent{host=~\"($osd_hosts|mon_hosts|rgw_hosts).*\",device!=\"lo\"}[$rate_interval]) \n )",
"format": "table",
"instant": true,
"intervalFactor": 1,
@@ -814,7 +814,7 @@
"steppedLine": false,
"targets": [
{
- "expr": "topk(10, (sum by(host) (\n (\n irate(net_bytes_recv{host=~\"($osd_hosts|mon_hosts|rgw_hosts).*\",device!=\"lo\"}[1m])\n ) +\n (\n irate(net_bytes_sent{host=~\"($osd_hosts|mon_hosts|rgw_hosts).*\",device!=\"lo\"}[1m])\n ))\n )\n)",
+ "expr": "topk(10, (sum by(host) (\n (\n irate(net_bytes_recv{host=~\"($osd_hosts|mon_hosts|rgw_hosts).*\",device!=\"lo\"}[$rate_interval])\n ) +\n (\n irate(net_bytes_sent{host=~\"($osd_hosts|mon_hosts|rgw_hosts).*\",device!=\"lo\"}[$rate_interval])\n ))\n )\n)",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{host}}",
@@ -1029,6 +1029,48 @@
"tagsQuery": "",
"type": "query",
"useTags": false
+ },
+ {
+ "allValue": null,
+ "current": {
+ "text": "3m",
+ "value": "3m"
+ },
+ "hide": 0,
+ "includeAll": false,
+ "label": "rate_interval",
+ "multi": false,
+ "name": "rate_interval",
+ "options": [
+ {
+ "selected": false,
+ "text": "1m",
+ "value": "1m"
+ },
+ {
+ "selected": true,
+ "text": "3m",
+ "value": "3m"
+ },
+ {
+ "selected": false,
+ "text": "5m",
+ "value": "5m"
+ },
+ {
+ "selected": false,
+ "text": "10m",
+ "value": "10m"
+ },
+ {
+ "selected": false,
+ "text": "15m",
+ "value": "15m"
+ }
+ ],
+ "query": "1m,3m,5m,10m,15m",
+ "skipUrlSync": false,
+ "type": "custom"
}
]
},
diff --git a/ceph/files/grafana_dashboards/osds-detail_prometheus.json b/ceph/files/grafana_dashboards/osds-detail_prometheus.json
index b9b950b..f02abbb 100644
--- a/ceph/files/grafana_dashboards/osds-detail_prometheus.json
+++ b/ceph/files/grafana_dashboards/osds-detail_prometheus.json
@@ -70,14 +70,14 @@
"steppedLine": false,
"targets": [
{
- "expr": "irate(ceph_osd_op_r_latency_sum{ceph_daemon=~\"osd.[[osd_id]]\"}[1m]) / on (ceph_daemon) irate(ceph_osd_op_r_latency_count[1m]) * 1000",
+ "expr": "irate(ceph_osd_op_r_latency_sum{ceph_daemon=~\"osd.[[osd_id]]\"}[$rate_interval]) / on (ceph_daemon) irate(ceph_osd_op_r_latency_count[$rate_interval]) * 1000",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "READs",
"refId": "A"
},
{
- "expr": "irate(ceph_osd_op_w_latency_sum{ceph_daemon=~\"osd.[[osd_id]]\"}[1m]) / on (ceph_daemon) irate(ceph_osd_op_w_latency_count[1m]) * 1000",
+ "expr": "irate(ceph_osd_op_w_latency_sum{ceph_daemon=~\"osd.[[osd_id]]\"}[$rate_interval]) / on (ceph_daemon) irate(ceph_osd_op_w_latency_count[$rate_interval]) * 1000",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "WRITEs",
@@ -161,14 +161,14 @@
"steppedLine": false,
"targets": [
{
- "expr": "irate(ceph_osd_op_r{ceph_daemon=~\"osd.[[osd_id]]\"}[1m])",
+ "expr": "irate(ceph_osd_op_r{ceph_daemon=~\"osd.[[osd_id]]\"}[$rate_interval])",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "Reads",
"refId": "A"
},
{
- "expr": "irate(ceph_osd_op_w{ceph_daemon=~\"osd.[[osd_id]]\"}[1m])",
+ "expr": "irate(ceph_osd_op_w{ceph_daemon=~\"osd.[[osd_id]]\"}[$rate_interval])",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "Writes",
@@ -252,14 +252,14 @@
"steppedLine": false,
"targets": [
{
- "expr": "irate(ceph_osd_op_r_out_bytes{ceph_daemon=~\"osd.[[osd_id]]\"}[1m])",
+ "expr": "irate(ceph_osd_op_r_out_bytes{ceph_daemon=~\"osd.[[osd_id]]\"}[$rate_interval])",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "Read Bytes",
"refId": "A"
},
{
- "expr": "irate(ceph_osd_op_w_in_bytes{ceph_daemon=~\"osd.[[osd_id]]\"}[1m])",
+ "expr": "irate(ceph_osd_op_w_in_bytes{ceph_daemon=~\"osd.[[osd_id]]\"}[$rate_interval])",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "Write Bytes",
@@ -356,14 +356,14 @@
"steppedLine": false,
"targets": [
{
- "expr": "label_replace(label_replace(irate(diskio_read_time[1m]), \"instance\", \"$1\", \"host\", \"(.+)\"), \"device\", \"$1\", \"name\", \"(.+)\") / label_replace(label_replace(irate(diskio_reads[1m]), \"instance\", \"$1\", \"host\", \"(.+)\"), \"device\", \"$1\", \"name\", \"(.+)\") and on (instance, device) ceph_disk_occupation{ceph_daemon=~\"osd.[[osd_id]]\"}",
+ "expr": "label_replace(label_replace(irate(diskio_read_time[$rate_interval]), \"instance\", \"$1\", \"host\", \"(.+)\"), \"device\", \"$1\", \"name\", \"(.+)\") / label_replace(label_replace(irate(diskio_reads[$rate_interval]), \"instance\", \"$1\", \"host\", \"(.+)\"), \"device\", \"$1\", \"name\", \"(.+)\") and on (instance, device) ceph_disk_occupation{ceph_daemon=~\"osd.[[osd_id]]\"}",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{instance}}/{{device}} Reads",
"refId": "A"
},
{
- "expr": "label_replace(label_replace(irate(diskio_write_time[1m]), \"instance\", \"$1\", \"host\", \"(.+)\"), \"device\", \"$1\", \"name\", \"(.+)\") / label_replace(label_replace(irate(diskio_writes[1m]), \"instance\", \"$1\", \"host\", \"(.+)\"), \"device\", \"$1\", \"name\", \"(.+)\") and on (instance, device) ceph_disk_occupation{ceph_daemon=~\"osd.[[osd_id]]\"}",
+ "expr": "label_replace(label_replace(irate(diskio_write_time[$rate_interval]), \"instance\", \"$1\", \"host\", \"(.+)\"), \"device\", \"$1\", \"name\", \"(.+)\") / label_replace(label_replace(irate(diskio_writes[$rate_interval]), \"instance\", \"$1\", \"host\", \"(.+)\"), \"device\", \"$1\", \"name\", \"(.+)\") and on (instance, device) ceph_disk_occupation{ceph_daemon=~\"osd.[[osd_id]]\"}",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{instance}}/{{device}} Writes",
@@ -447,14 +447,14 @@
"steppedLine": false,
"targets": [
{
- "expr": "label_replace(label_replace(irate(diskio_reads[1m]), \"instance\", \"$1\", \"host\", \"(.+)\"), \"device\", \"$1\", \"name\", \"(.+)\") and on (instance, device) ceph_disk_occupation{ceph_daemon=~\"osd.[[osd_id]]\"}",
+ "expr": "label_replace(label_replace(irate(diskio_reads[$rate_interval]), \"instance\", \"$1\", \"host\", \"(.+)\"), \"device\", \"$1\", \"name\", \"(.+)\") and on (instance, device) ceph_disk_occupation{ceph_daemon=~\"osd.[[osd_id]]\"}",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{instance}} {{device}} READS",
"refId": "A"
},
{
- "expr": "label_replace(label_replace(irate(diskio_writes[1m]), \"instance\", \"$1\", \"host\", \"(.+)\"), \"device\", \"$1\", \"name\", \"(.+)\") and on (instance, device) ceph_disk_occupation{ceph_daemon=~\"osd.[[osd_id]]\"}",
+ "expr": "label_replace(label_replace(irate(diskio_writes[$rate_interval]), \"instance\", \"$1\", \"host\", \"(.+)\"), \"device\", \"$1\", \"name\", \"(.+)\") and on (instance, device) ceph_disk_occupation{ceph_daemon=~\"osd.[[osd_id]]\"}",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{instance}} {{device}} WRITES",
@@ -538,14 +538,14 @@
"steppedLine": false,
"targets": [
{
- "expr": "label_replace(label_replace(irate(diskio_read_bytes[1m]), \"instance\", \"$1\", \"host\", \"(.+)\"), \"device\", \"$1\", \"name\", \"(.+)\") and on (instance, device) ceph_disk_occupation{ceph_daemon=~\"osd.[[osd_id]]\"}",
+ "expr": "label_replace(label_replace(irate(diskio_read_bytes[$rate_interval]), \"instance\", \"$1\", \"host\", \"(.+)\"), \"device\", \"$1\", \"name\", \"(.+)\") and on (instance, device) ceph_disk_occupation{ceph_daemon=~\"osd.[[osd_id]]\"}",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{instance}} {{device}} READS",
"refId": "A"
},
{
- "expr": "label_replace(label_replace(irate(diskio_write_bytes[1m]), \"instance\", \"$1\", \"host\", \"(.+)\"), \"device\", \"$1\", \"name\", \"(.+)\") and on (instance, device) ceph_disk_occupation{ceph_daemon=~\"osd.[[osd_id]]\"}",
+ "expr": "label_replace(label_replace(irate(diskio_write_bytes[$rate_interval]), \"instance\", \"$1\", \"host\", \"(.+)\"), \"device\", \"$1\", \"name\", \"(.+)\") and on (instance, device) ceph_disk_occupation{ceph_daemon=~\"osd.[[osd_id]]\"}",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{instance}} {{device}} WRITES",
@@ -629,7 +629,7 @@
"steppedLine": false,
"targets": [
{
- "expr": "label_replace(label_replace(irate(diskio_io_time[1m]), \"instance\", \"$1\", \"host\", \"(.+)\"), \"device\", \"$1\", \"name\", \"(.+)\") and on (instance, device) ceph_disk_occupation{ceph_daemon=~\"osd.[[osd_id]]\"}",
+ "expr": "label_replace(label_replace(irate(diskio_io_time[$rate_interval]), \"instance\", \"$1\", \"host\", \"(.+)\"), \"device\", \"$1\", \"name\", \"(.+)\") and on (instance, device) ceph_disk_occupation{ceph_daemon=~\"osd.[[osd_id]]\"}",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{instance}} {{device}}",
@@ -708,6 +708,48 @@
"tagsQuery": "",
"type": "query",
"useTags": false
+ },
+ {
+ "allValue": null,
+ "current": {
+ "text": "3m",
+ "value": "3m"
+ },
+ "hide": 0,
+ "includeAll": false,
+ "label": "rate_interval",
+ "multi": false,
+ "name": "rate_interval",
+ "options": [
+ {
+ "selected": false,
+ "text": "1m",
+ "value": "1m"
+ },
+ {
+ "selected": true,
+ "text": "3m",
+ "value": "3m"
+ },
+ {
+ "selected": false,
+ "text": "5m",
+ "value": "5m"
+ },
+ {
+ "selected": false,
+ "text": "10m",
+ "value": "10m"
+ },
+ {
+ "selected": false,
+ "text": "15m",
+ "value": "15m"
+ }
+ ],
+ "query": "1m,3m,5m,10m,15m",
+ "skipUrlSync": false,
+ "type": "custom"
}
]
},
diff --git a/ceph/files/grafana_dashboards/osds-overview_prometheus.json b/ceph/files/grafana_dashboards/osds-overview_prometheus.json
index c399fc0..49c1cb5 100644
--- a/ceph/files/grafana_dashboards/osds-overview_prometheus.json
+++ b/ceph/files/grafana_dashboards/osds-overview_prometheus.json
@@ -58,21 +58,21 @@
"steppedLine": false,
"targets": [
{
- "expr": "avg (irate(ceph_osd_op_r_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_r_latency_count[1m]) * 1000)",
+ "expr": "avg (irate(ceph_osd_op_r_latency_sum[$rate_interval]) / on (ceph_daemon) irate(ceph_osd_op_r_latency_count[$rate_interval]) * 1000)",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "AVG read",
"refId": "A"
},
{
- "expr": "max (irate(ceph_osd_op_r_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_r_latency_count[1m]) * 1000)",
+ "expr": "max (irate(ceph_osd_op_r_latency_sum[$rate_interval]) / on (ceph_daemon) irate(ceph_osd_op_r_latency_count[$rate_interval]) * 1000)",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "MAX read",
"refId": "B"
},
{
- "expr": "quantile(0.95,\n (irate(ceph_osd_op_r_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_r_latency_count[1m]) * 1000)\n)",
+ "expr": "quantile(0.95,\n (irate(ceph_osd_op_r_latency_sum[$rate_interval]) / on (ceph_daemon) irate(ceph_osd_op_r_latency_count[$rate_interval]) * 1000)\n)",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "@95%ile",
@@ -188,7 +188,7 @@
],
"targets": [
{
- "expr": "topk(10,\n (sort(\n (irate(ceph_osd_op_r_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_r_latency_count[1m]) * 1000)\n ))\n)\n\n",
+ "expr": "topk(10,\n (sort(\n (irate(ceph_osd_op_r_latency_sum[$rate_interval]) / on (ceph_daemon) irate(ceph_osd_op_r_latency_count[$rate_interval]) * 1000)\n ))\n)\n\n",
"format": "table",
"instant": true,
"intervalFactor": 1,
@@ -239,21 +239,21 @@
"steppedLine": false,
"targets": [
{
- "expr": "avg (irate(ceph_osd_op_w_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_w_latency_count[1m]) * 1000)",
+ "expr": "avg (irate(ceph_osd_op_w_latency_sum[$rate_interval]) / on (ceph_daemon) irate(ceph_osd_op_w_latency_count[$rate_interval]) * 1000)",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "AVG write",
"refId": "A"
},
{
- "expr": "max (irate(ceph_osd_op_w_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_w_latency_count[1m]) * 1000)",
+ "expr": "max (irate(ceph_osd_op_w_latency_sum[$rate_interval]) / on (ceph_daemon) irate(ceph_osd_op_w_latency_count[$rate_interval]) * 1000)",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "MAX write",
"refId": "B"
},
{
- "expr": "quantile(0.95,\n (irate(ceph_osd_op_w_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_w_latency_count[1m]) * 1000)\n)",
+ "expr": "quantile(0.95,\n (irate(ceph_osd_op_w_latency_sum[$rate_interval]) / on (ceph_daemon) irate(ceph_osd_op_w_latency_count[$rate_interval]) * 1000)\n)",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "@95%ile write",
@@ -369,7 +369,7 @@
],
"targets": [
{
- "expr": "topk(10,\n (sort(\n (irate(ceph_osd_op_w_latency_sum[1m]) / on (ceph_daemon) irate(ceph_osd_op_w_latency_count[1m]) * 1000)\n ))\n)\n\n",
+ "expr": "topk(10,\n (sort(\n (irate(ceph_osd_op_w_latency_sum[$rate_interval]) / on (ceph_daemon) irate(ceph_osd_op_w_latency_count[$rate_interval]) * 1000)\n ))\n)\n\n",
"format": "table",
"instant": true,
"intervalFactor": 1,
@@ -526,7 +526,7 @@
"steppedLine": false,
"targets": [
{
- "expr": "round(sum(irate(ceph_pool_rd[1m])))",
+ "expr": "round(sum(irate(ceph_pool_rd[$rate_interval])))",
"format": "time_series",
"hide": false,
"instant": false,
@@ -536,7 +536,7 @@
"refId": "A"
},
{
- "expr": "round(sum(irate(ceph_pool_wr[1m])))",
+ "expr": "round(sum(irate(ceph_pool_wr[$rate_interval])))",
"format": "time_series",
"instant": false,
"interval": "",
@@ -594,7 +594,51 @@
"osd"
],
"templating": {
- "list": []
+ "list": [
+ {
+ "allValue": null,
+ "current": {
+ "tags": [],
+ "text": "3m",
+ "value": "3m"
+ },
+ "hide": 0,
+ "includeAll": false,
+ "label": "rate_interval",
+ "multi": false,
+ "name": "rate_interval",
+ "options": [
+ {
+ "selected": false,
+ "text": "1m",
+ "value": "1m"
+ },
+ {
+ "selected": true,
+ "text": "3m",
+ "value": "3m"
+ },
+ {
+ "selected": false,
+ "text": "5m",
+ "value": "5m"
+ },
+ {
+ "selected": false,
+ "text": "10m",
+ "value": "10m"
+ },
+ {
+ "selected": false,
+ "text": "15m",
+ "value": "15m"
+ }
+ ],
+ "query": "1m,3m,5m,10m,15m",
+ "skipUrlSync": false,
+ "type": "custom"
+ }
+ ]
},
"time": {
"from": "now-1h",
diff --git a/ceph/files/grafana_dashboards/pool-overview_prometheus.json b/ceph/files/grafana_dashboards/pool-overview_prometheus.json
index a58e6a2..1d50c9a 100644
--- a/ceph/files/grafana_dashboards/pool-overview_prometheus.json
+++ b/ceph/files/grafana_dashboards/pool-overview_prometheus.json
@@ -72,7 +72,7 @@
"steppedLine": false,
"targets": [
{
- "expr": "avg((rate(ceph_pool_rd{pool_id=~\"[[pool_id]]\"}[1m]) + rate(ceph_pool_wr{pool_id=~\"[[pool_id]]\"}[1m])) + on(pool_id,instance) group_left(name) ceph_pool_metadata{pool_id=~\"[[pool_id]]\"}) without (instance)",
+ "expr": "avg((rate(ceph_pool_rd{pool_id=~\"[[pool_id]]\"}[$rate_interval]) + rate(ceph_pool_wr{pool_id=~\"[[pool_id]]\"}[$rate_interval])) + on(pool_id,instance) group_left(name) ceph_pool_metadata{pool_id=~\"[[pool_id]]\"}) without (instance)",
"format": "time_series",
"hide": false,
"intervalFactor": 1,
@@ -158,7 +158,7 @@
"steppedLine": false,
"targets": [
{
- "expr": "avg((rate(ceph_pool_rd_bytes{pool_id=~\"[[pool_id]]\"}[1m]) + rate(ceph_pool_wr_bytes{pool_id=~\"[[pool_id]]\"}[1m])) + on(pool_id,instance) group_left(name) ceph_pool_metadata{pool_id=~\"[[pool_id]]\"}) without (instance)",
+ "expr": "avg((rate(ceph_pool_rd_bytes{pool_id=~\"[[pool_id]]\"}[$rate_interval]) + rate(ceph_pool_wr_bytes{pool_id=~\"[[pool_id]]\"}[$rate_interval])) + on(pool_id,instance) group_left(name) ceph_pool_metadata{pool_id=~\"[[pool_id]]\"}) without (instance)",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{name}}",
@@ -354,7 +354,7 @@
],
"targets": [
{
- "expr": "topk(5,(label_replace((irate(ceph_pool_rd{pool_id=~\"[[pool_id]]\"}[1m]) + irate(ceph_pool_wr{pool_id=~\"[[pool_id]]\"}[1m])),\"id\", \"$1\", \"pool_id\", \"(.*)\") + on(pool_id) group_left(instance,name) ceph_pool_metadata{pool_id=~\"[[pool_id]]\"}) )",
+ "expr": "topk(5,(label_replace((irate(ceph_pool_rd{pool_id=~\"[[pool_id]]\"}[$rate_interval]) + irate(ceph_pool_wr{pool_id=~\"[[pool_id]]\"}[$rate_interval])),\"id\", \"$1\", \"pool_id\", \"(.*)\") + on(pool_id) group_left(instance,name) ceph_pool_metadata{pool_id=~\"[[pool_id]]\"}) )",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -491,7 +491,7 @@
],
"targets": [
{
- "expr": "(label_replace((irate(ceph_pool_rd_bytes{pool_id=~\"[[pool_id]]\"}[1m]) + irate(ceph_pool_wr_bytes{pool_id=~\"[[pool_id]]\"}[1m])),\"id\", \"$1\", \"pool_id\", \"(.*)\") + on(pool_id) group_left(instance,name) ceph_pool_metadata{pool_id=~\"[[pool_id]]\"}) ",
+ "expr": "(label_replace((irate(ceph_pool_rd_bytes{pool_id=~\"[[pool_id]]\"}[$rate_interval]) + irate(ceph_pool_wr_bytes{pool_id=~\"[[pool_id]]\"}[$rate_interval])),\"id\", \"$1\", \"pool_id\", \"(.*)\") + on(pool_id) group_left(instance,name) ceph_pool_metadata{pool_id=~\"[[pool_id]]\"}) ",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -690,6 +690,48 @@
"tagsQuery": "",
"type": "query",
"useTags": false
+ },
+ {
+ "allValue": null,
+ "current": {
+ "text": "3m",
+ "value": "3m"
+ },
+ "hide": 0,
+ "includeAll": false,
+ "label": "rate_interval",
+ "multi": false,
+ "name": "rate_interval",
+ "options": [
+ {
+ "selected": false,
+ "text": "1m",
+ "value": "1m"
+ },
+ {
+ "selected": true,
+ "text": "3m",
+ "value": "3m"
+ },
+ {
+ "selected": false,
+ "text": "5m",
+ "value": "5m"
+ },
+ {
+ "selected": false,
+ "text": "10m",
+ "value": "10m"
+ },
+ {
+ "selected": false,
+ "text": "15m",
+ "value": "15m"
+ }
+ ],
+ "query": "1m,3m,5m,10m,15m",
+ "skipUrlSync": false,
+ "type": "custom"
}
]
},
diff --git a/ceph/files/grafana_dashboards/radosgw-detail_prometheus.json b/ceph/files/grafana_dashboards/radosgw-detail_prometheus.json
index fa95510..c536351 100644
--- a/ceph/files/grafana_dashboards/radosgw-detail_prometheus.json
+++ b/ceph/files/grafana_dashboards/radosgw-detail_prometheus.json
@@ -71,14 +71,14 @@
"steppedLine": false,
"targets": [
{
- "expr": "rate(ceph_rgw_get_initial_lat_sum{ceph_daemon=~\"($rgw_servers)\"}[1m]) / rate(ceph_rgw_get_initial_lat_count{ceph_daemon=~\"($rgw_servers)\"}[1m])",
+ "expr": "rate(ceph_rgw_get_initial_lat_sum{ceph_daemon=~\"($rgw_servers)\"}[$rate_interval]) / rate(ceph_rgw_get_initial_lat_count{ceph_daemon=~\"($rgw_servers)\"}[$rate_interval])",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "GET {{ceph_daemon}}",
"refId": "A"
},
{
- "expr": "rate(ceph_rgw_put_initial_lat_sum{ceph_daemon=~\"($rgw_servers)\"}[1m]) / rate(ceph_rgw_put_initial_lat_count{ceph_daemon=~\"($rgw_servers)\"}[1m])",
+ "expr": "rate(ceph_rgw_put_initial_lat_sum{ceph_daemon=~\"($rgw_servers)\"}[$rate_interval]) / rate(ceph_rgw_put_initial_lat_count{ceph_daemon=~\"($rgw_servers)\"}[$rate_interval])",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "PUT {{ceph_daemon}}",
@@ -162,14 +162,14 @@
"steppedLine": false,
"targets": [
{
- "expr": "rate(ceph_rgw_get_b{ceph_daemon=~\"[[rgw_servers]]\"}[1m])",
+ "expr": "rate(ceph_rgw_get_b{ceph_daemon=~\"[[rgw_servers]]\"}[$rate_interval])",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "GETs {{ceph_daemon}}",
"refId": "B"
},
{
- "expr": "rate(ceph_rgw_put_b{ceph_daemon=~\"[[rgw_servers]]\"}[1m])",
+ "expr": "rate(ceph_rgw_put_b{ceph_daemon=~\"[[rgw_servers]]\"}[$rate_interval])",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "PUTs {{ceph_daemon}}",
@@ -260,28 +260,28 @@
"steppedLine": false,
"targets": [
{
- "expr": "rate(ceph_rgw_failed_req{ceph_daemon=~\"[[rgw_servers]]\"}[1m])",
+ "expr": "rate(ceph_rgw_failed_req{ceph_daemon=~\"[[rgw_servers]]\"}[$rate_interval])",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "Requests Failed {{ceph_daemon}}",
"refId": "B"
},
{
- "expr": "rate(ceph_rgw_get{ceph_daemon=~\"[[rgw_servers]]\"}[1m])",
+ "expr": "rate(ceph_rgw_get{ceph_daemon=~\"[[rgw_servers]]\"}[$rate_interval])",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "GETs {{ceph_daemon}}",
"refId": "C"
},
{
- "expr": "rate(ceph_rgw_put{ceph_daemon=~\"[[rgw_servers]]\"}[1m])",
+ "expr": "rate(ceph_rgw_put{ceph_daemon=~\"[[rgw_servers]]\"}[$rate_interval])",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "PUTs {{ceph_daemon}}",
"refId": "D"
},
{
- "expr": "rate(ceph_rgw_req{ceph_daemon=~\"[[rgw_servers]]\"}[1m]) -\n (rate(ceph_rgw_get{ceph_daemon=~\"[[rgw_servers]]\"}[1m]) +\n rate(ceph_rgw_put{ceph_daemon=~\"[[rgw_servers]]\"}[1m]))",
+ "expr": "rate(ceph_rgw_req{ceph_daemon=~\"[[rgw_servers]]\"}[$rate_interval]) -\n (rate(ceph_rgw_get{ceph_daemon=~\"[[rgw_servers]]\"}[$rate_interval]) +\n rate(ceph_rgw_put{ceph_daemon=~\"[[rgw_servers]]\"}[$rate_interval]))",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "Other {{ceph_daemon}}",
@@ -361,6 +361,48 @@
"tagsQuery": "",
"type": "query",
"useTags": false
+ },
+ {
+ "allValue": null,
+ "current": {
+ "text": "3m",
+ "value": "3m"
+ },
+ "hide": 0,
+ "includeAll": false,
+ "label": "rate_interval",
+ "multi": false,
+ "name": "rate_interval",
+ "options": [
+ {
+ "selected": false,
+ "text": "1m",
+ "value": "1m"
+ },
+ {
+ "selected": true,
+ "text": "3m",
+ "value": "3m"
+ },
+ {
+ "selected": false,
+ "text": "5m",
+ "value": "5m"
+ },
+ {
+ "selected": false,
+ "text": "10m",
+ "value": "10m"
+ },
+ {
+ "selected": false,
+ "text": "15m",
+ "value": "15m"
+ }
+ ],
+ "query": "1m,3m,5m,10m,15m",
+ "skipUrlSync": false,
+ "type": "custom"
}
]
},
diff --git a/ceph/files/grafana_dashboards/radosgw-overview_prometheus.json b/ceph/files/grafana_dashboards/radosgw-overview_prometheus.json
index 1cafb7a..4a69c5c 100644
--- a/ceph/files/grafana_dashboards/radosgw-overview_prometheus.json
+++ b/ceph/files/grafana_dashboards/radosgw-overview_prometheus.json
@@ -70,14 +70,14 @@
"steppedLine": false,
"targets": [
{
- "expr": "avg(rate(ceph_rgw_get_initial_lat_sum[1m]) / rate(ceph_rgw_get_initial_lat_count[1m]))",
+ "expr": "avg(rate(ceph_rgw_get_initial_lat_sum[$rate_interval]) / rate(ceph_rgw_get_initial_lat_count[$rate_interval]))",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "GET AVG",
"refId": "A"
},
{
- "expr": "avg(rate(ceph_rgw_put_initial_lat_sum[1m]) / rate(ceph_rgw_put_initial_lat_count[1m]))",
+ "expr": "avg(rate(ceph_rgw_put_initial_lat_sum[$rate_interval]) / rate(ceph_rgw_put_initial_lat_count[$rate_interval]))",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "PUT AVG",
@@ -161,7 +161,7 @@
"steppedLine": false,
"targets": [
{
- "expr": "sum by(rgw_host) (label_replace(rate(ceph_rgw_req[1m]), \"rgw_host\", \"$1\", \"ceph_daemon\", \"rgw.(.*)\"))",
+ "expr": "sum by(rgw_host) (label_replace(rate(ceph_rgw_req[$rate_interval]), \"rgw_host\", \"$1\", \"ceph_daemon\", \"rgw.(.*)\"))",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{rgw_host}}",
@@ -247,7 +247,7 @@
"steppedLine": false,
"targets": [
{
- "expr": "label_replace(rate(ceph_rgw_get_initial_lat_sum[1m]),\"rgw_host\",\"$1\",\"ceph_daemon\",\"rgw.(.*)\") / \nlabel_replace(rate(ceph_rgw_get_initial_lat_count[1m]),\"rgw_host\",\"$1\",\"ceph_daemon\",\"rgw.(.*)\")",
+ "expr": "label_replace(rate(ceph_rgw_get_initial_lat_sum[$rate_interval]),\"rgw_host\",\"$1\",\"ceph_daemon\",\"rgw.(.*)\") / \nlabel_replace(rate(ceph_rgw_get_initial_lat_count[$rate_interval]),\"rgw_host\",\"$1\",\"ceph_daemon\",\"rgw.(.*)\")",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{rgw_host}}",
@@ -333,14 +333,14 @@
"steppedLine": false,
"targets": [
{
- "expr": "sum(rate(ceph_rgw_get_b[1m]))",
+ "expr": "sum(rate(ceph_rgw_get_b[$rate_interval]))",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "GETs",
"refId": "A"
},
{
- "expr": "sum(rate(ceph_rgw_put_b[1m]))",
+ "expr": "sum(rate(ceph_rgw_put_b[$rate_interval]))",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "PUTs",
@@ -425,7 +425,7 @@
"steppedLine": false,
"targets": [
{
- "expr": "sum by(rgw_host) (\n (label_replace(rate(ceph_rgw_get_b[1m]), \"rgw_host\",\"$1\",\"ceph_daemon\",\"rgw.(.*)\")) + \n (label_replace(rate(ceph_rgw_put_b[1m]), \"rgw_host\",\"$1\",\"ceph_daemon\",\"rgw.(.*)\"))\n)",
+ "expr": "sum by(rgw_host) (\n (label_replace(rate(ceph_rgw_get_b[$rate_interval]), \"rgw_host\",\"$1\",\"ceph_daemon\",\"rgw.(.*)\")) + \n (label_replace(rate(ceph_rgw_put_b[$rate_interval]), \"rgw_host\",\"$1\",\"ceph_daemon\",\"rgw.(.*)\"))\n)",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{rgw_host}}",
@@ -510,7 +510,7 @@
"steppedLine": false,
"targets": [
{
- "expr": "label_replace(rate(ceph_rgw_put_initial_lat_sum[1m]),\"rgw_host\",\"$1\",\"ceph_daemon\",\"rgw.(.*)\") / \nlabel_replace(rate(ceph_rgw_put_initial_lat_count[1m]),\"rgw_host\",\"$1\",\"ceph_daemon\",\"rgw.(.*)\")",
+ "expr": "label_replace(rate(ceph_rgw_put_initial_lat_sum[$rate_interval]),\"rgw_host\",\"$1\",\"ceph_daemon\",\"rgw.(.*)\") / \nlabel_replace(rate(ceph_rgw_put_initial_lat_count[$rate_interval]),\"rgw_host\",\"$1\",\"ceph_daemon\",\"rgw.(.*)\")",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{rgw_host}}",
@@ -591,6 +591,48 @@
"tagsQuery": "",
"type": "query",
"useTags": false
+ },
+ {
+ "allValue": null,
+ "current": {
+ "text": "3m",
+ "value": "3m"
+ },
+ "hide": 0,
+ "includeAll": false,
+ "label": "rate_interval",
+ "multi": false,
+ "name": "rate_interval",
+ "options": [
+ {
+ "selected": false,
+ "text": "1m",
+ "value": "1m"
+ },
+ {
+ "selected": true,
+ "text": "3m",
+ "value": "3m"
+ },
+ {
+ "selected": false,
+ "text": "5m",
+ "value": "5m"
+ },
+ {
+ "selected": false,
+ "text": "10m",
+ "value": "10m"
+ },
+ {
+ "selected": false,
+ "text": "15m",
+ "value": "15m"
+ }
+ ],
+ "query": "1m,3m,5m,10m,15m",
+ "skipUrlSync": false,
+ "type": "custom"
}
]
},
diff --git a/ceph/osd/setup.sls b/ceph/osd/setup.sls
index 5b1a832..ab03da1 100644
--- a/ceph/osd/setup.sls
+++ b/ceph/osd/setup.sls
@@ -21,7 +21,7 @@
{%- if disk.get('enabled', True) %}
-{% set dev = disk.dev %}
+{% set dev = '`readlink -f ' + disk.dev + '`' %}
# for uniqueness
{% set dev_device = dev + disk.get('data_partition_prefix', '') + disk.get('data_partition', 1)|string %}
diff --git a/metadata/service/common/cluster.yml b/metadata/service/common/cluster.yml
index 6974fe6..09ca6c2 100644
--- a/metadata/service/common/cluster.yml
+++ b/metadata/service/common/cluster.yml
@@ -7,6 +7,9 @@
ceph_mon_node03_hostname: cmn03
ceph:
common:
+ config:
+ global:
+ mon_max_pg_per_osd: 600
enabled: true
version: ${_param:ceph_version}
fsid: ${_param:ceph_cluster_fsid}
@@ -17,4 +20,3 @@
host: ${_param:ceph_mon_node02_address}
- name: ${_param:ceph_mon_node03_hostname}
host: ${_param:ceph_mon_node03_address}
-
diff --git a/metadata/service/common/single.yml b/metadata/service/common/single.yml
index 7aec939..c81947b 100644
--- a/metadata/service/common/single.yml
+++ b/metadata/service/common/single.yml
@@ -5,6 +5,9 @@
ceph_mon_node01_hostname: cmn01
ceph:
common:
+ config:
+ global:
+ mon_max_pg_per_osd: 600
enabled: true
version: ${_param:ceph_version}
fsid: ${_param:ceph_cluster_fsid}
diff --git a/metadata/service/mon/cluster.yml b/metadata/service/mon/cluster.yml
index 94c484b..6a10da2 100644
--- a/metadata/service/mon/cluster.yml
+++ b/metadata/service/mon/cluster.yml
@@ -7,7 +7,3 @@
ceph:
mon:
enabled: true
- common:
- config:
- mon:
- mon_max_pg_per_osd: 600
diff --git a/metadata/service/mon/single.yml b/metadata/service/mon/single.yml
index ea04ea0..8be5da5 100644
--- a/metadata/service/mon/single.yml
+++ b/metadata/service/mon/single.yml
@@ -12,9 +12,6 @@
caps:
mon: "allow *"
common:
- config:
- mon:
- mon_max_pg_per_osd: 600
keyring:
admin:
caps: