summaryrefslogtreecommitdiffstats
path: root/monitoring/ceph-mixin/tests_alerts/test_alerts.yml
blob: 4768af7de408279ed444d9758ad0691798ccdeeb (plain)
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
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
rule_files:
  - ../prometheus_alerts.yml
evaluation_interval: 5m
tests:
 # health error
 - interval: 5m
   input_series:
    - series: 'ceph_health_status{instance="ceph:9283",job="ceph"}'
      values: '2 2 2 2 2 2 2'
   promql_expr_test:
    - expr: ceph_health_status == 2
      eval_time: 5m
      exp_samples:
       - labels: 'ceph_health_status{instance="ceph:9283",job="ceph"}'
         value: 2
   alert_rule_test:
    - eval_time: 1m
      alertname: CephHealthError
    - eval_time: 6m
      alertname: CephHealthError
      exp_alerts:
      - exp_labels:
          instance: ceph:9283
          job: ceph
          oid: 1.3.6.1.4.1.50495.1.2.1.2.1
          type: ceph_default
          severity: critical
        exp_annotations:
          summary: Ceph is in the ERROR state
          description: The cluster state has been HEALTH_ERROR for more than 5 minutes. Please check 'ceph health detail' for more information.

 # health warning
 - interval: 5m
   input_series:
    - series: 'ceph_health_status{instance="ceph:9283",job="ceph"}'
      values: '1 1 1 1 1 1 1 1 1 1'
   promql_expr_test:
     - expr: ceph_health_status == 1
       eval_time: 15m
       exp_samples:
         - labels: 'ceph_health_status{instance="ceph:9283",job="ceph"}'
           value: 1
   alert_rule_test:
    - eval_time: 10m
      alertname: CephHealthWarning
    - eval_time: 20m
      alertname: CephHealthWarning
      exp_alerts:
      - exp_labels:
          instance: ceph:9283
          job: ceph
          type: ceph_default
          severity: warning
        exp_annotations:
          summary: Ceph is in the WARNING state
          description: The cluster state has been HEALTH_WARN for more than 15 minutes. Please check 'ceph health detail' for more information.

 # 10% OSDs down
 - interval: 1m
   input_series:
    - series: 'ceph_osd_up{ceph_daemon="osd.0",instance="ceph:9283",job="ceph"}'
      values: '1 1 1 1 1'
    - series: 'ceph_osd_up{ceph_daemon="osd.1",instance="ceph:9283",job="ceph"}'
      values: '0 0 0 0 0'
    - series: 'ceph_osd_up{ceph_daemon="osd.2",instance="ceph:9283",job="ceph"}'
      values: '1 1 1 1 1'
    - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.0",
      ceph_version="ceph version 17.0.0-189-g3558fd72
      (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)",
      cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0",
      hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore",
      public_addr="172.20.0.2"}'
      values: '1 1 1 1 1'
    - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.1",
      ceph_version="ceph version 17.0.0-189-g3558fd72
      (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)",
      cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0",
      hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore",
      public_addr="172.20.0.2"}'
      values: '1 1 1 1 1'
    - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.2",
      ceph_version="ceph version 17.0.0-189-g3558fd72
      (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)",
      cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0",
      hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore",
      public_addr="172.20.0.2"}'
      values: '1 1 1 1 1'
   promql_expr_test:
     - expr: count(ceph_osd_up == 0) / count(ceph_osd_up) * 100 >= 10
       eval_time: 1m
       exp_samples:
         - labels: '{}'
           value: 3.333333333333333E+01
   alert_rule_test:
     - eval_time: 1m
       alertname: CephOSDDownHigh
       exp_alerts:
       - exp_labels:
           oid: 1.3.6.1.4.1.50495.1.2.1.4.1
           type: ceph_default
           severity: critical
         exp_annotations:
           summary: More than 10% of OSDs are down
           description: "33.33% or 1 of 3 OSDs are down (>= 10%). The following OSDs are down: - osd.1 on ceph"

 # flapping OSD
 - interval: 1s
   input_series:
    - series: 'ceph_osd_up{ceph_daemon="osd.0",instance="ceph:9283",job="ceph"}'
      values: '1+1x100'
    - series: 'ceph_osd_up{ceph_daemon="osd.1",instance="ceph:9283",job="ceph"}'
      values: '1+0x100'
    - series: 'ceph_osd_up{ceph_daemon="osd.2",instance="ceph:9283",job="ceph"}'
      values: '1+0x100'
    - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.0",
      ceph_version="ceph version 17.0.0-189-g3558fd72
      (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)",
      cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0",
      hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore",
      public_addr="172.20.0.2"}'
      values: '1 1 1 1 1 1'
    - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.1",
      ceph_version="ceph version 17.0.0-189-g3558fd72
      (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)",
      cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0",
      hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore",
      public_addr="172.20.0.2"}'
      values: '1 1 1 1 1 1'
    - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.2",
      ceph_version="ceph version 17.0.0-189-g3558fd72
      (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)",
      cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0",
      hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore",
      public_addr="172.20.0.2"}'
      values: '1 1 1 1 1 1'
   promql_expr_test:
     - expr: |
         (
           rate(ceph_osd_up[5m])
           * on(ceph_daemon) group_left(hostname) ceph_osd_metadata
         ) * 60 > 1
       eval_time: 1m
       exp_samples:
         - labels: '{ceph_daemon="osd.0", hostname="ceph", instance="ceph:9283",
           job="ceph"}'
           value: 1.2200000000000001E+01
   alert_rule_test:
     - eval_time: 5m
       alertname: CephOSDFlapping
       exp_alerts:
       - exp_labels:
           ceph_daemon: osd.0
           hostname: ceph
           instance: ceph:9283
           job: ceph
           oid: 1.3.6.1.4.1.50495.1.2.1.4.4
           severity: warning
           type: ceph_default
         exp_annotations:
           documentation: https://docs.ceph.com/en/latest/rados/troubleshooting/troubleshooting-osd#flapping-osds
           summary: Network issues are causing OSDs to flap (mark each other down)
           description: "OSD osd.0 on ceph was marked down and back up 20.1 times once a minute for 5 minutes. This may indicate a network issue (latency, packet loss, MTU mismatch) on the cluster network, or the public network if no cluster network is deployed. Check the network stats on the listed host(s)."

 # high pg count deviation
 - interval: 1m
   input_series:
    - series: 'ceph_osd_numpg{ceph_daemon="osd.0",instance="ceph:9283",
      job="ceph"}'
      values: '100 100 100 100 100 160'
    - series: 'ceph_osd_numpg{ceph_daemon="osd.1",instance="ceph:9283",
      job="ceph"}'
      values: '100 100 100 100 100 320'
    - series: 'ceph_osd_numpg{ceph_daemon="osd.2",instance="ceph:9283",
      job="ceph"}'
      values: '100 100 100 100 100 160'
    - series: 'ceph_osd_numpg{ceph_daemon="osd.3",instance="ceph:9283",
      job="ceph"}'
      values: '100 100 100 100 100 160'
    - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.0",
      ceph_version="ceph version 17.0.0-189-g3558fd72
      (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)",
      cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0",
      hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore",
      public_addr="172.20.0.2"}'
      values: '1 1 1 1 1 1'
    - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.1",
      ceph_version="ceph version 17.0.0-189-g3558fd72
      (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)",
      cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0",
      hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore",
      public_addr="172.20.0.2"}'
      values: '1 1 1 1 1 1'
    - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.2",
      ceph_version="ceph version 17.0.0-189-g3558fd72
      (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)",
      cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0",
      hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore",
      public_addr="172.20.0.2"}'
      values: '1 1 1 1 1 1'
    - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.3",
      ceph_version="ceph version 17.0.0-189-g3558fd72
      (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)",
      cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0",
      hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore",
      public_addr="172.20.0.2"}'
      values: '1 1 1 1 1 1'
   promql_expr_test:
     - expr: |
         abs(
           (
             (ceph_osd_numpg > 0) - on (job) group_left avg(ceph_osd_numpg > 0)
             by (job)
           ) / on (job) group_left avg(ceph_osd_numpg > 0) by (job)
         ) * on(ceph_daemon) group_left(hostname) ceph_osd_metadata > 0.30

       eval_time: 5m
       exp_samples:
         - labels: '{ceph_daemon="osd.1", hostname="ceph", instance="ceph:9283",
           job="ceph"}'
           value: 6E-01
   alert_rule_test:
     - eval_time: 10m
       alertname: CephPGImbalance
       exp_alerts:
       - exp_labels:
           ceph_daemon: osd.1
           hostname: ceph
           instance: ceph:9283
           job: ceph
           oid: 1.3.6.1.4.1.50495.1.2.1.4.5
           severity: warning
           type: ceph_default
         exp_annotations:
           summary: PGs are not balanced across OSDs
           description: "OSD osd.1 on ceph deviates by more than 30% from average PG count."

 # pgs inactive
 - interval: 1m
   input_series:
    - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
      name="device_health_metrics",pool_id="1"}'
      values: '1 1 1 1 1 1 1 1'
    - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
      name="device_health_metrics",pool_id="2"}'
      values: '1 1 1 1 1 1 1 1'
    - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
      name="device_health_metrics",pool_id="3"}'
      values: '1 1 1 1 1 1 1 1'
    - series: 'ceph_pg_total{instance="ceph:9283",job="ceph",pool_id="1"}'
      values: '1 1 1 1 1 1 1 1'
    - series: 'ceph_pg_total{instance="ceph:9283",job="ceph",pool_id="2"}'
      values: '32 32 32 32 32 32 32 32'
    - series: 'ceph_pg_total{instance="ceph:9283",job="ceph",pool_id="3"}'
      values: '33 32 32 32 32 33 33 32'
    - series: 'ceph_pg_active{instance="ceph:9283",job="ceph",pool_id="1"}'
      values: '1 1 1 1 1 1 1 1 1'
    - series: 'ceph_pg_active{instance="ceph:9283",job="ceph",pool_id="2"}'
      values: '32 32 32 32 32 32 32 32'
    - series: 'ceph_pg_active{instance="ceph:9283",job="ceph",pool_id="3"}'
      values: '32 32 32 32 32 32 32 32'
   promql_expr_test:
     - expr: ceph_pool_metadata * on(pool_id,instance) group_left()
             (ceph_pg_total - ceph_pg_active) > 0
       eval_time: 5m
       exp_samples:
         - labels: '{instance="ceph:9283", job="ceph",
           name="device_health_metrics",
           pool_id="3"}'
           value: 1
   alert_rule_test:
     - eval_time: 5m
       alertname: CephPGsInactive
       exp_alerts:
       - exp_labels:
           instance: ceph:9283
           job: ceph
           name: device_health_metrics
           oid: 1.3.6.1.4.1.50495.1.2.1.7.1
           pool_id: 3
           severity: critical
           type: ceph_default
         exp_annotations:
           summary: One or more placement groups are inactive
           description: "1 PGs have been inactive for more than 5 minutes in pool device_health_metrics. Inactive placement groups are not able to serve read/write requests."

 #pgs unclean
 - interval: 1m
   input_series:
    - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
      name="device_health_metrics",pool_id="1"}'
      values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
    - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
      name="device_health_metrics",pool_id="2"}'
      values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
    - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
      name="device_health_metrics",pool_id="3"}'
      values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
    - series: 'ceph_pg_total{instance="ceph:9283",job="ceph",pool_id="1"}'
      values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
    - series: 'ceph_pg_total{instance="ceph:9283",job="ceph",pool_id="2"}'
      values: '32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32
      32 32 32'
    - series: 'ceph_pg_total{instance="ceph:9283",job="ceph",pool_id="3"}'
      values: '33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33
      33 33'
    - series: 'ceph_pg_clean{instance="ceph:9283",job="ceph",pool_id="1"}'
      values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
    - series: 'ceph_pg_clean{instance="ceph:9283",job="ceph",pool_id="2"}'
      values: '32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32
      32 32'
    - series: 'ceph_pg_clean{instance="ceph:9283",job="ceph",pool_id="3"}'
      values: '32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32
      32 32'
   promql_expr_test:
     - expr: ceph_pool_metadata * on(pool_id,instance) group_left()
             (ceph_pg_total - ceph_pg_clean) > 0
       eval_time: 15m
       exp_samples:
         - labels: '{instance="ceph:9283", job="ceph",
           name="device_health_metrics", pool_id="3"}'
           value: 1
   alert_rule_test:
     - eval_time: 16m
       alertname: CephPGsUnclean
       exp_alerts:
       - exp_labels:
           instance: ceph:9283
           job: ceph
           name: device_health_metrics
           oid: 1.3.6.1.4.1.50495.1.2.1.7.2
           pool_id: 3
           severity: warning
           type: ceph_default
         exp_annotations:
           summary: One or more placement groups are marked unclean
           description: "1 PGs have been unclean for more than 15 minutes in pool device_health_metrics. Unclean PGs have not recovered from a previous failure."

 # root volume full
 - interval: 1m
   input_series:
    - series: 'node_filesystem_avail_bytes{device="/dev/mapper/fedora_localhost
      --live-home",fstype="ext4",instance="node-exporter",job="node-exporter",
      mountpoint="/"}'
      values: '35336400896 35336400896 35336400896 35336400896 35336400896
      3525385519.104 3533640089'
    - series: 'node_filesystem_size_bytes{device="/dev/mapper/fedora_localhost
      --live-home",fstype="ext4",instance="node-exporter",job="node-exporter",
      mountpoint="/"}'
      values: '73445531648 73445531648 73445531648 73445531648 73445531648
      73445531648 73445531648'
   promql_expr_test:
     - expr: node_filesystem_avail_bytes{mountpoint="/"} /
             node_filesystem_size_bytes{mountpoint="/"} * 100 < 5
       eval_time: 5m
       exp_samples:
         - labels: '{device="/dev/mapper/fedora_localhost --live-home",
           fstype="ext4", instance="node-exporter", job="node-exporter",
           mountpoint="/"}'
           value: 4.8E+00
   alert_rule_test:
     - eval_time: 10m
       alertname: CephNodeRootFilesystemFull
       exp_alerts:
       - exp_labels:
           device: /dev/mapper/fedora_localhost --live-home
           fstype: ext4
           instance: node-exporter
           job: node-exporter
           mountpoint: /
           oid: 1.3.6.1.4.1.50495.1.2.1.8.1
           severity: critical
           type: ceph_default
         exp_annotations:
           summary: Root filesystem is dangerously full
           description: "Root volume is dangerously full: 4.811% free."

 # network packets dropped
 - interval: 1m
   input_series:
    - series: 'node_network_receive_drop_total{device="eth0",
      instance="node-exporter",job="node-exporter"}'
      values: '0+600x10'
    - series: 'node_network_transmit_drop_total{device="eth0",
      instance="node-exporter",job="node-exporter"}'
      values: '0+600x10'
    - series: 'node_network_receive_packets_total{device="eth0",
      instance="node-exporter",job="node-exporter"}'
      values: '0+750x10'
    - series: 'node_network_transmit_packets_total{device="eth0",
      instance="node-exporter",job="node-exporter"}'
      values: '0+750x10'
   promql_expr_test:
     - expr: |
         (
           rate(node_network_receive_drop_total{device!="lo"}[1m]) +
           rate(node_network_transmit_drop_total{device!="lo"}[1m])
         ) / (
           rate(node_network_receive_packets_total{device!="lo"}[1m]) +
           rate(node_network_transmit_packets_total{device!="lo"}[1m])
         ) >= 0.0050000000000000001 and (
           rate(node_network_receive_drop_total{device!="lo"}[1m]) +
           rate(node_network_transmit_drop_total{device!="lo"}[1m])
         ) >= 10

       eval_time: 5m
       exp_samples:
         - labels: '{device="eth0", instance="node-exporter",
           job="node-exporter"}'
           value: 8E-1
   alert_rule_test:
     - eval_time: 5m
       alertname: CephNodeNetworkPacketDrops
       exp_alerts:
       - exp_labels:
           device: eth0
           instance: node-exporter
           job: node-exporter
           oid: 1.3.6.1.4.1.50495.1.2.1.8.2
           severity: warning
           type: ceph_default
         exp_annotations:
           summary: One or more NICs reports packet drops
           description: "Node node-exporter experiences packet drop > 0.5% or > 10 packets/s on interface eth0."

 # network packets errors
 - interval: 1m
   input_series:
    - series: 'node_network_receive_errs_total{device="eth0",
      instance="node-exporter",job="node-exporter"}'
      values: '0+600x10'
    - series: 'node_network_transmit_errs_total{device="eth0",
      instance="node-exporter",job="node-exporter"}'
      values: '0+600x10'
    - series: 'node_network_transmit_packets_total{device="eth0",
      instance="node-exporter",job="node-exporter"}'
      values: '0+750x10'
    - series: 'node_network_receive_packets_total{device="eth0",
      instance="node-exporter",job="node-exporter"}'
      values: '0+750x10'
   promql_expr_test:
     - expr: |
         (
           rate(node_network_receive_errs_total{device!="lo"}[1m]) +
           rate(node_network_transmit_errs_total{device!="lo"}[1m])
         ) / (
           rate(node_network_receive_packets_total{device!="lo"}[1m]) +
           rate(node_network_transmit_packets_total{device!="lo"}[1m])
         ) >= 0.0001 or (
           rate(node_network_receive_errs_total{device!="lo"}[1m]) +
           rate(node_network_transmit_errs_total{device!="lo"}[1m])
         ) >= 10

       eval_time: 5m
       exp_samples:
         - labels: '{device="eth0", instance="node-exporter",
           job="node-exporter"}'
           value: 8E-01
   alert_rule_test:
     - eval_time: 5m
       alertname: CephNodeNetworkPacketErrors
       exp_alerts:
       - exp_labels:
           device: eth0
           instance: node-exporter
           job: node-exporter
           oid: 1.3.6.1.4.1.50495.1.2.1.8.3
           severity: warning
           type: ceph_default
         exp_annotations: 
           summary: One or more NICs reports packet errors
           description: "Node node-exporter experiences packet errors > 0.01% or > 10 packets/s on interface eth0."

 # Bond is missing a peer
 - interval: 1m
   input_series:
    - series: 'node_bonding_active{master="bond0",
      instance="node-exporter",job="node-exporter"}'
      values: '3'
    - series: 'node_bonding_slaves{master="bond0",
      instance="node-exporter",job="node-exporter"}'
      values: '4'
   promql_expr_test:
     - expr: |
         node_bonding_slaves - node_bonding_active != 0
       eval_time: 5m
       exp_samples:
         - labels: '{master="bond0", instance="node-exporter",
           job="node-exporter"}'
           value: 1
   alert_rule_test:
     - eval_time: 5m
       alertname: CephNodeNetworkBondDegraded
       exp_alerts:
       - exp_labels:
           master: bond0
           instance: node-exporter
           job: node-exporter
           severity: warning
           type: ceph_default
         exp_annotations:
           summary: Degraded Bond on Node node-exporter
           description: "Bond bond0 is degraded on Node node-exporter."

# Node Storage disk space filling up
 - interval: 1m
   # 20GB = 21474836480, 256MB = 268435456
   input_series:
    - series: 'node_filesystem_free_bytes{device="/dev/mapper/vg-root",
      fstype="xfs",instance="node-1",mountpoint="/rootfs"}'
      values: '21474836480-268435456x48'
    - series: 'node_filesystem_free_bytes{device="/dev/mapper/vg-root",
      fstype="xfs",instance="node-2",mountpoint="/rootfs"}'
      values: '21474836480+0x48'
    - series: 'node_uname_info{instance="node-1", nodename="node-1.unittests.com"}'
      values: 1+0x48
    - series: 'node_uname_info{instance="node-2", nodename="node-2.unittests.com"}'
      values: 1+0x48
   promql_expr_test:
     - expr: |
         predict_linear(node_filesystem_free_bytes{device=~"/.*"}[2d], 3600 * 24 * 5) *
          on(instance) group_left(nodename) node_uname_info < 0
       eval_time: 5m
       exp_samples:
         - labels: '{device="/dev/mapper/vg-root",instance="node-1",fstype="xfs",
         mountpoint="/rootfs",nodename="node-1.unittests.com"}'
           value: -1.912602624E+12
   alert_rule_test:
     - eval_time: 5m
       alertname: CephNodeDiskspaceWarning
       exp_alerts:
       - exp_labels:
           severity: warning
           type: ceph_default
           oid: 1.3.6.1.4.1.50495.1.2.1.8.4
           device: /dev/mapper/vg-root
           fstype: xfs
           instance: node-1
           mountpoint: /rootfs
           nodename: node-1.unittests.com
         exp_annotations:
           summary: Host filesystem free space is getting low
           description: "Mountpoint /rootfs on node-1.unittests.com will be full in less than 5 days based on the 48 hour trailing fill rate."
 # MTU Mismatch
 - interval: 1m
   input_series:
    - series: 'node_network_mtu_bytes{device="eth0",instance="node-exporter",
      job="node-exporter"}'
      values: '1500 1500 1500 1500 1500'
    - series: 'node_network_mtu_bytes{device="eth1",instance="node-exporter",
      job="node-exporter"}'
      values: '1500 1500 1500 1500 1500'
    - series: 'node_network_mtu_bytes{device="eth2",instance="node-exporter",
      job="node-exporter"}'
      values: '1500 1500 1500 1500 1500'
    - series: 'node_network_mtu_bytes{device="eth3",instance="node-exporter",
      job="node-exporter"}'
      values: '1500 1500 1500 1500 1500'
    - series: 'node_network_mtu_bytes{device="eth4",instance="node-exporter",
      job="node-exporter"}'
      values: '9000 9000 9000 9000 9000'
    - series: 'node_network_mtu_bytes{device="eth4",instance="hostname1",
      job="node-exporter"}'
      values: '2200 2200 2200 2200 2200'
    - series: 'node_network_mtu_bytes{device="eth4",instance="hostname2",
      job="node-exporter"}'
      values: '2400 2400 2400 2400 2400'
    - series: 'node_network_up{device="eth0",instance="node-exporter",
      job="node-exporter"}'
      values: '0 0 0 0 0'
    - series: 'node_network_up{device="eth1",instance="node-exporter",
      job="node-exporter"}'
      values: '0 0 0 0 0'
    - series: 'node_network_up{device="eth2",instance="node-exporter",
      job="node-exporter"}'
      values: '1 1 1 1 1'
    - series: 'node_network_up{device="eth3",instance="node-exporter",
      job="node-exporter"}'
      values: '1 1 1 1 1'
    - series: 'node_network_up{device="eth4",instance="node-exporter",
      job="node-exporter"}'
      values: '1 1 1 1 1'
    - series: 'node_network_up{device="eth4",instance="hostname1",
      job="node-exporter"}'
      values: '1 1 1 1 1'
    - series: 'node_network_up{device="eth4",instance="hostname2",
      job="node-exporter"}'
      values: '0 0 0 0 0'
   promql_expr_test:
     - expr: |
          node_network_mtu_bytes * (node_network_up{device!="lo"} > 0) ==
            scalar(
              max by (device) (node_network_mtu_bytes * (node_network_up{device!="lo"} > 0)) !=
                quantile by (device) (.5, node_network_mtu_bytes * (node_network_up{device!="lo"} > 0))
            )
          or
          node_network_mtu_bytes * (node_network_up{device!="lo"} > 0) ==
            scalar(
              min by (device) (node_network_mtu_bytes * (node_network_up{device!="lo"} > 0)) !=
                quantile by (device) (.5, node_network_mtu_bytes * (node_network_up{device!="lo"} > 0))
            )
       eval_time: 1m
       exp_samples:
         - labels: '{device="eth4", instance="node-exporter", job="node-exporter"}'
           value: 9000
         - labels: '{device="eth4", instance="hostname1", job="node-exporter"}'
           value: 2200
   alert_rule_test:
     - eval_time: 1m
       alertname: CephNodeInconsistentMTU
       exp_alerts:
       - exp_labels:
           device: eth4
           instance: hostname1
           job: node-exporter
           severity: warning
           type: ceph_default
         exp_annotations:
           summary: MTU settings across Ceph hosts are inconsistent
           description: "Node hostname1 has a different MTU size (2200) than the median of devices named eth4."
       - exp_labels:
           device: eth4
           instance: node-exporter
           job: node-exporter
           severity: warning
           type: ceph_default
         exp_annotations:
           summary: MTU settings across Ceph hosts are inconsistent
           description: "Node node-exporter has a different MTU size (9000) than the median of devices named eth4."

 # pool full, data series has 6 but using topk(5) so to ensure the
 # results are working as expected
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="POOL_FULL"}'
      values: '0 0 0 1 1 1 1 1 1 1 1'
    - series: 'ceph_pool_percent_used{pool_id="1"}'
      values: '32+0x10'
    - series: 'ceph_pool_percent_used{pool_id="2"}'
      values: '96+0x10'
    - series: 'ceph_pool_percent_used{pool_id="3"}'
      values: '90+0x10'
    - series: 'ceph_pool_percent_used{pool_id="4"}'
      values: '72+0x10'
    - series: 'ceph_pool_percent_used{pool_id="5"}'
      values: '19+0x10'
    - series: 'ceph_pool_percent_used{pool_id="6"}'
      values: '10+0x10'
    - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
      name="cephfs_data",pool_id="1"}'
      values: '1 1 1 1 1 1 1 1 1'
    - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
      name="rbd",pool_id="2"}'
      values: '1 1 1 1 1 1 1 1 1'
    - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
      name="iscsi",pool_id="3"}'
      values: '1 1 1 1 1 1 1 1 1'
    - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
      name="default.rgw.index",pool_id="4"}'
      values: '1 1 1 1 1 1 1 1 1'
    - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
      name="default.rgw.log",pool_id="5"}'
      values: '1 1 1 1 1 1 1 1 1'
    - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph",
      name="dummy",pool_id="6"}'
      values: '1 1 1 1 1 1 1 1 1'
   promql_expr_test:
     - expr: ceph_health_detail{name="POOL_FULL"} > 0
       eval_time: 5m
       exp_samples:
         - labels:  '{__name__="ceph_health_detail", name="POOL_FULL"}'
           value: 1
   alert_rule_test:
     - eval_time: 1m
       alertname: CephPoolFull
     - eval_time: 10m
       alertname: CephPoolFull
       exp_alerts:
       - exp_labels:
           name: POOL_FULL
           severity: critical
           type: ceph_default
           oid: 1.3.6.1.4.1.50495.1.2.1.9.1
         exp_annotations:
           documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pool-full
           summary: Pool is full - writes are blocked
           description: "A pool has reached its MAX quota, or OSDs supporting the pool have reached the FULL threshold. Until this is resolved, writes to the pool will be blocked. Pool Breakdown (top 5) - rbd at 96% - iscsi at 90% - default.rgw.index at 72% - cephfs_data at 32% - default.rgw.log at 19% Increase the pool's quota, or add capacity to the cluster first then increase the pool's quota (e.g. ceph osd pool set quota <pool_name> max_bytes <bytes>)"
 # slow OSD ops
 - interval : 1m
   input_series:
    - series: 'ceph_healthcheck_slow_ops{instance="ceph:9283",job="ceph"}'
      values: '1+0x120'
   promql_expr_test:
     - expr: ceph_healthcheck_slow_ops > 0
       eval_time: 1m
       exp_samples:
         - labels: '{__name__="ceph_healthcheck_slow_ops", instance="ceph:9283",
           job="ceph"}'
           value: 1
   alert_rule_test:
     - eval_time: 20m
       alertname: CephSlowOps
       exp_alerts:
       - exp_labels:
           instance: ceph:9283
           job: ceph
           severity: warning
           type: ceph_default
         exp_annotations:
           documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#slow-ops
           summary: OSD operations are slow to complete
           description: "1 OSD requests are taking too long to process (osd_op_complaint_time exceeded)"

 # slow daemon ops
 - interval : 1m
   input_series:
    - series: 'ceph_daemon_health_metrics{ceph_daemon="osd.1", instance="ceph:9283",job="ceph", type="SLOW_OPS"}'
      values: '1+0x120'
   promql_expr_test:
     - expr: 'ceph_daemon_health_metrics{type="SLOW_OPS"} > 0'
       eval_time: 1m
       exp_samples:
         - labels: '{__name__="ceph_daemon_health_metrics", ceph_daemon="osd.1",instance="ceph:9283",
           job="ceph", type="SLOW_OPS"}'
           value: 1
   alert_rule_test:
     - eval_time: 20m
       alertname: CephDaemonSlowOps
       exp_alerts:
       - exp_labels:
           instance: ceph:9283
           ceph_daemon: "osd.1"
           job: ceph
           severity: warning
           type: ceph_default
         exp_annotations:
           documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#slow-ops
           summary: osd.1 operations are slow to complete
           description: "osd.1 operations are taking too long to process (complaint time exceeded)"

# CEPHADM orchestrator alert triggers
 - interval: 30s
   input_series:
    - series: 'ceph_health_detail{name="UPGRADE_EXCEPTION"}'
      values: '1+0x40'
   promql_expr_test:
     - expr: ceph_health_detail{name="UPGRADE_EXCEPTION"} > 0
       eval_time: 2m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="UPGRADE_EXCEPTION"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: CephadmUpgradeFailed
    - eval_time: 5m
      alertname: CephadmUpgradeFailed
      exp_alerts:
      - exp_labels:
          name: UPGRADE_EXCEPTION
          severity: critical
          type: ceph_default
          oid: 1.3.6.1.4.1.50495.1.2.1.11.2
        exp_annotations:
          summary: Ceph version upgrade has failed
          description: "The cephadm cluster upgrade process has failed. The cluster remains in an undetermined state. Please review the cephadm logs, to understand the nature of the issue"
 - interval: 30s
   input_series:
    - series: 'ceph_health_detail{name="CEPHADM_FAILED_DAEMON"}'
      values: '1+0x40'
   promql_expr_test:
     - expr: ceph_health_detail{name="CEPHADM_FAILED_DAEMON"} > 0
       eval_time: 2m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="CEPHADM_FAILED_DAEMON"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: CephadmDaemonFailed
    - eval_time: 5m
      alertname: CephadmDaemonFailed
      exp_alerts:
      - exp_labels:
          name: CEPHADM_FAILED_DAEMON
          severity: critical
          type: ceph_default
          oid: 1.3.6.1.4.1.50495.1.2.1.11.1
        exp_annotations:
          summary: A ceph daemon manged by cephadm is down
          description: "A daemon managed by cephadm is no longer active. Determine, which daemon is down with 'ceph health detail'. you may start daemons with the 'ceph orch daemon start <daemon_id>'"
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="CEPHADM_PAUSED"}'
      values: '1 1 1 1 1 1 1 1 1'
   promql_expr_test:
     - expr: ceph_health_detail{name="CEPHADM_PAUSED"} > 0
       eval_time: 2m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="CEPHADM_PAUSED"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: CephadmPaused
    - eval_time: 5m
      alertname: CephadmPaused
      exp_alerts:
      - exp_labels:
          name: CEPHADM_PAUSED
          severity: warning
          type: ceph_default
        exp_annotations:
          documentation: https://docs.ceph.com/en/latest/cephadm/operations#cephadm-paused
          summary: Orchestration tasks via cephadm are PAUSED
          description: "Cluster management has been paused manually. This will prevent the orchestrator from service management and reconciliation. If this is not intentional, resume cephadm operations with 'ceph orch resume'"
# MDS
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="MDS_DAMAGE"}'
      values: '1 1 1 1 1 1 1 1 1'
   promql_expr_test:
     - expr: ceph_health_detail{name="MDS_DAMAGE"} > 0
       eval_time: 2m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="MDS_DAMAGE"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: CephFilesystemDamaged
    - eval_time: 5m
      alertname: CephFilesystemDamaged
      exp_alerts:
      - exp_labels:
          name: MDS_DAMAGE
          severity: critical
          type: ceph_default
          oid: 1.3.6.1.4.1.50495.1.2.1.5.1
        exp_annotations:
          documentation: https://docs.ceph.com/en/latest/cephfs/health-messages#cephfs-health-messages
          summary: CephFS filesystem is damaged.
          description: "Filesystem metadata has been corrupted. Data may be inaccessible. Analyze metrics from the MDS daemon admin socket, or escalate to support."
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="MDS_HEALTH_READ_ONLY"}'
      values: '1 1 1 1 1 1 1 1 1'
   promql_expr_test:
     - expr: ceph_health_detail{name="MDS_HEALTH_READ_ONLY"} > 0
       eval_time: 2m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="MDS_HEALTH_READ_ONLY"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: CephFilesystemReadOnly
    - eval_time: 5m
      alertname: CephFilesystemReadOnly
      exp_alerts:
      - exp_labels:
          name: MDS_HEALTH_READ_ONLY
          severity: critical
          type: ceph_default
          oid: 1.3.6.1.4.1.50495.1.2.1.5.2
        exp_annotations:
          documentation: https://docs.ceph.com/en/latest/cephfs/health-messages#cephfs-health-messages
          summary: CephFS filesystem in read only mode due to write error(s)
          description: "The filesystem has switched to READ ONLY due to an unexpected error when writing to the metadata pool. Either analyze the output from the MDS daemon admin socket, or escalate to support."
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="MDS_ALL_DOWN"}'
      values: '0 0 1 1 1 1 1 1 1 1 1'
   promql_expr_test:
     - expr: ceph_health_detail{name="MDS_ALL_DOWN"} > 0
       eval_time: 2m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="MDS_ALL_DOWN"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: CephFilesystemOffline
    - eval_time: 10m
      alertname: CephFilesystemOffline
      exp_alerts:
      - exp_labels:
          name: MDS_ALL_DOWN
          severity: critical
          type: ceph_default
          oid: 1.3.6.1.4.1.50495.1.2.1.5.3
        exp_annotations:
          documentation: https://docs.ceph.com/en/latest/cephfs/health-messages/#mds-all-down
          summary: CephFS filesystem is offline
          description: "All MDS ranks are unavailable. The MDS daemons managing metadata are down, rendering the filesystem offline."
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="FS_DEGRADED"}'
      values: '0 0 1 1 1 1 1 1 1 1 1'
   promql_expr_test:
     - expr: ceph_health_detail{name="FS_DEGRADED"} > 0
       eval_time: 2m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="FS_DEGRADED"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: CephFilesystemDegraded
    - eval_time: 10m
      alertname: CephFilesystemDegraded
      exp_alerts:
      - exp_labels:
          name: FS_DEGRADED
          severity: critical
          type: ceph_default
          oid: 1.3.6.1.4.1.50495.1.2.1.5.4
        exp_annotations:
          documentation: https://docs.ceph.com/en/latest/cephfs/health-messages/#fs-degraded
          summary: CephFS filesystem is degraded
          description: "One or more metadata daemons (MDS ranks) are failed or in a damaged state. At best the filesystem is partially available, at worst the filesystem is completely unusable."
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="MDS_INSUFFICIENT_STANDBY"}'
      values: '0 0 1 1 1 1 1 1 1 1 1'
   promql_expr_test:
     - expr: ceph_health_detail{name="MDS_INSUFFICIENT_STANDBY"} > 0
       eval_time: 2m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="MDS_INSUFFICIENT_STANDBY"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: CephFilesystemInsufficientStandby
    - eval_time: 10m
      alertname: CephFilesystemInsufficientStandby
      exp_alerts:
      - exp_labels:
          name: MDS_INSUFFICIENT_STANDBY
          severity: warning
          type: ceph_default
        exp_annotations:
          documentation: https://docs.ceph.com/en/latest/cephfs/health-messages/#mds-insufficient-standby
          summary: Ceph filesystem standby daemons too few
          description: "The minimum number of standby daemons required by standby_count_wanted is less than the current number of standby daemons. Adjust the standby count or increase the number of MDS daemons."
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="FS_WITH_FAILED_MDS"}'
      values: '0 0 1 1 1 1 1 1 1 1 1'
   promql_expr_test:
     - expr: ceph_health_detail{name="FS_WITH_FAILED_MDS"} > 0
       eval_time: 2m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="FS_WITH_FAILED_MDS"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: CephFilesystemFailureNoStandby
    - eval_time: 10m
      alertname: CephFilesystemFailureNoStandby
      exp_alerts:
      - exp_labels:
          name: FS_WITH_FAILED_MDS
          severity: critical
          type: ceph_default
          oid: 1.3.6.1.4.1.50495.1.2.1.5.5
        exp_annotations:
          documentation: https://docs.ceph.com/en/latest/cephfs/health-messages/#fs-with-failed-mds
          summary: MDS daemon failed, no further standby available
          description: "An MDS daemon has failed, leaving only one active rank and no available standby. Investigate the cause of the failure or add a standby MDS."
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="MDS_UP_LESS_THAN_MAX"}'
      values: '0 0 1 1 1 1 1 1 1 1 1'
   promql_expr_test:
     - expr: ceph_health_detail{name="MDS_UP_LESS_THAN_MAX"} > 0
       eval_time: 2m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="MDS_UP_LESS_THAN_MAX"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: CephFilesystemMDSRanksLow
    - eval_time: 10m
      alertname: CephFilesystemMDSRanksLow
      exp_alerts:
      - exp_labels:
          name: MDS_UP_LESS_THAN_MAX
          severity: warning
          type: ceph_default
        exp_annotations:
          documentation: https://docs.ceph.com/en/latest/cephfs/health-messages/#mds-up-less-than-max
          summary: Ceph MDS daemon count is lower than configured
          description: "The filesystem's 'max_mds' setting defines the number of MDS ranks in the filesystem. The current number of active MDS daemons is less than this value."
# MGR
 - interval: 1m
   input_series:
    - series: 'up{job="ceph", instance="ceph-mgr:9283"}'
      values: '1+0x2 0+0x10'
   promql_expr_test:
     - expr: up{job="ceph"} == 0
       eval_time: 3m
       exp_samples:
         - labels: '{__name__="up", job="ceph", instance="ceph-mgr:9283"}'
           value: 0
   alert_rule_test:
    - eval_time: 1m
      alertname: CephMgrPrometheusModuleInactive
    - eval_time: 10m
      alertname: CephMgrPrometheusModuleInactive
      exp_alerts:
      - exp_labels:
          instance: ceph-mgr:9283
          job: ceph
          severity: critical
          type: ceph_default
          oid: 1.3.6.1.4.1.50495.1.2.1.6.2
        exp_annotations:
          summary: The mgr/prometheus module is not available
          description: "The mgr/prometheus module at ceph-mgr:9283 is unreachable. This could mean that the module has been disabled or the mgr daemon itself is down. Without the mgr/prometheus module metrics and alerts will no longer function. Open a shell to an admin node or toolbox pod and use 'ceph -s' to to determine whether the mgr is active. If the mgr is not active, restart it, otherwise you can determine module status with 'ceph mgr module ls'. If it is not listed as enabled, enable it with 'ceph mgr module enable prometheus'."
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="RECENT_MGR_MODULE_CRASH"}'
      values: '0+0x2 1+0x20'
   promql_expr_test:
     - expr: ceph_health_detail{name="RECENT_MGR_MODULE_CRASH"} == 1
       eval_time: 3m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="RECENT_MGR_MODULE_CRASH"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: CephMgrModuleCrash
    - eval_time: 15m
      alertname: CephMgrModuleCrash
      exp_alerts:
      - exp_labels:
          name: RECENT_MGR_MODULE_CRASH
          severity: critical
          type: ceph_default
          oid: 1.3.6.1.4.1.50495.1.2.1.6.1
        exp_annotations:
          documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#recent-mgr-module-crash
          summary: A manager module has recently crashed
          description: "One or more mgr modules have crashed and have yet to be acknowledged by an administrator. A crashed module may impact functionality within the cluster. Use the 'ceph crash' command to determine which module has failed, and archive it to acknowledge the failure."
# MON
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="MON_DISK_CRIT"}'
      values: '0+0x2 1+0x10'
    - series: 'ceph_mon_metadata{ceph_daemon="mon.a", hostname="ceph-mon-a"}'
      values: '1+0x13'
   promql_expr_test:
     - expr: ceph_health_detail{name="MON_DISK_CRIT"} == 1
       eval_time: 3m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="MON_DISK_CRIT"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: CephMonDiskspaceCritical
    - eval_time: 10m
      alertname: CephMonDiskspaceCritical
      exp_alerts:
      - exp_labels:
          name: "MON_DISK_CRIT"
          severity: critical
          type: ceph_default
          oid: 1.3.6.1.4.1.50495.1.2.1.3.2
        exp_annotations:
          documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-disk-crit
          summary: Filesystem space on at least one monitor is critically low
          description: "The free space available to a monitor's store is critically low. You should increase the space available to the monitor(s). The default directory is /var/lib/ceph/mon-*/data/store.db on traditional deployments, and /var/lib/rook/mon-*/data/store.db on the mon pod's worker node for Rook. Look for old, rotated versions of *.log and MANIFEST*. Do NOT touch any *.sst files. Also check any other directories under /var/lib/rook and other directories on the same filesystem, often /var/log and /var/tmp are culprits. Your monitor hosts are; - ceph-mon-a"
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="MON_DISK_LOW"}'
      values: '0+0x2 1+0x10'
    - series: 'ceph_mon_metadata{ceph_daemon="mon.a", hostname="ceph-mon-a"}'
      values: '1+0x13'
   promql_expr_test:
     - expr: ceph_health_detail{name="MON_DISK_LOW"} == 1
       eval_time: 3m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="MON_DISK_LOW"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: CephMonDiskspaceLow
    - eval_time: 10m
      alertname: CephMonDiskspaceLow
      exp_alerts:
      - exp_labels:
          name: "MON_DISK_LOW"
          severity: warning
          type: ceph_default
        exp_annotations:
          documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-disk-low
          summary: Drive space on at least one monitor is approaching full
          description: "The space available to a monitor's store is approaching full (>70% is the default). You should increase the space available to the monitor(s). The default directory is /var/lib/ceph/mon-*/data/store.db on traditional deployments, and /var/lib/rook/mon-*/data/store.db on the mon pod's worker node for Rook. Look for old, rotated versions of *.log and MANIFEST*.  Do NOT touch any *.sst files. Also check any other directories under /var/lib/rook and other directories on the same filesystem, often /var/log and /var/tmp are culprits. Your monitor hosts are; - ceph-mon-a"
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="MON_CLOCK_SKEW"}'
      values: '0+0x2 1+0x10'
   promql_expr_test:
     - expr: ceph_health_detail{name="MON_CLOCK_SKEW"} == 1
       eval_time: 3m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="MON_CLOCK_SKEW"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: CephMonClockSkew
    - eval_time: 10m
      alertname: CephMonClockSkew
      exp_alerts:
      - exp_labels:
          name: "MON_CLOCK_SKEW"
          severity: warning
          type: ceph_default
        exp_annotations:
          documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-clock-skew
          summary: Clock skew detected among monitors
          description: "Ceph monitors rely on closely synchronized time to maintain quorum and cluster consistency. This event indicates that the time on at least one mon has drifted too far from the lead mon. Review cluster status with ceph -s. This will show which monitors are affected. Check the time sync status on each monitor host with 'ceph time-sync-status' and the state and peers of your ntpd or chrony daemon."

# Check 3 mons one down, quorum at risk
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="MON_DOWN"}'
      values: '0+0x2 1+0x12'
    - series: 'ceph_mon_quorum_status{ceph_daemon="mon.a"}'
      values: '1+0x14'
    - series: 'ceph_mon_quorum_status{ceph_daemon="mon.b"}'
      values: '1+0x14'
    - series: 'ceph_mon_quorum_status{ceph_daemon="mon.c"}'
      values: '1+0x2 0+0x12'
    - series: 'ceph_mon_metadata{ceph_daemon="mon.a", hostname="ceph-mon-1"}'
      values: '1+0x14'
    - series: 'ceph_mon_metadata{ceph_daemon="mon.b", hostname="ceph-mon-2"}'
      values: '1+0x14'
    - series: 'ceph_mon_metadata{ceph_daemon="mon.c", hostname="ceph-mon-3"}'
      values: '1+0x14'
   promql_expr_test:
     - expr: ((ceph_health_detail{name="MON_DOWN"} == 1) * on() (count(ceph_mon_quorum_status == 1) == bool (floor(count(ceph_mon_metadata) / 2) + 1))) == 1
       eval_time: 3m
       exp_samples:
         - labels: '{}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: CephMonDownQuorumAtRisk
      # shouldn't fire
    - eval_time: 10m
      alertname: CephMonDownQuorumAtRisk
      exp_alerts:
      - exp_labels:
          severity: critical
          type: ceph_default
          oid: 1.3.6.1.4.1.50495.1.2.1.3.1
        exp_annotations:
          documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-down
          summary: Monitor quorum is at risk
          description: "Quorum requires a majority of monitors (x 2) to be active. Without quorum the cluster will become inoperable, affecting all services and connected clients. The following monitors are down: - mon.c on ceph-mon-3"
# check 5 mons, 1 down - warning only
 - interval: 1m
   input_series:
    - series: 'ceph_mon_quorum_status{ceph_daemon="mon.a"}'
      values: '1+0x14'
    - series: 'ceph_mon_quorum_status{ceph_daemon="mon.b"}'
      values: '1+0x14'
    - series: 'ceph_mon_quorum_status{ceph_daemon="mon.c"}'
      values: '1+0x14'
    - series: 'ceph_mon_quorum_status{ceph_daemon="mon.d"}'
      values: '1+0x14'
    - series: 'ceph_mon_quorum_status{ceph_daemon="mon.e"}'
      values: '1+0x2 0+0x12'
    - series: 'ceph_mon_metadata{ceph_daemon="mon.a", hostname="ceph-mon-1"}'
      values: '1+0x14'
    - series: 'ceph_mon_metadata{ceph_daemon="mon.b", hostname="ceph-mon-2"}'
      values: '1+0x14'
    - series: 'ceph_mon_metadata{ceph_daemon="mon.c", hostname="ceph-mon-3"}'
      values: '1+0x14'
    - series: 'ceph_mon_metadata{ceph_daemon="mon.d", hostname="ceph-mon-4"}'
      values: '1+0x14'
    - series: 'ceph_mon_metadata{ceph_daemon="mon.e", hostname="ceph-mon-5"}'
      values: '1+0x14'
   promql_expr_test:
     - expr: (count(ceph_mon_quorum_status == 0) <= (count(ceph_mon_metadata) - floor(count(ceph_mon_metadata) / 2) + 1))
       eval_time: 3m
       exp_samples:
         - labels: '{}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: CephMonDown
    - eval_time: 10m
      alertname: CephMonDown
      exp_alerts:
      - exp_labels:
          severity: warning
          type: ceph_default
        exp_annotations:
          documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-down
          summary: One or more monitors down
          description: "You have 1 monitor down. Quorum is still intact, but the loss of an additional monitor will make your cluster inoperable.  The following monitors are down:   - mon.e on ceph-mon-5\n"
# Device Health
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="DEVICE_HEALTH"}'
      values: '0+0x2 1+0x10'
   promql_expr_test:
     - expr: ceph_health_detail{name="DEVICE_HEALTH"} == 1
       eval_time: 3m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="DEVICE_HEALTH"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: CephDeviceFailurePredicted
    - eval_time: 10m
      alertname: CephDeviceFailurePredicted
      exp_alerts:
      - exp_labels:
          name: "DEVICE_HEALTH"
          severity: warning
          type: ceph_default
        exp_annotations:
          documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#id2
          summary: Device(s) predicted to fail soon
          description: "The device health module has determined that one or more devices will fail soon. To review device status use 'ceph device ls'. To show a specific device use 'ceph device info <dev id>'. Mark the OSD out so that data may migrate to other OSDs. Once the OSD has drained, destroy the OSD, replace the device, and redeploy the OSD."
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="DEVICE_HEALTH_TOOMANY"}'
      values: '0+0x2 1+0x10'
   promql_expr_test:
     - expr: ceph_health_detail{name="DEVICE_HEALTH_TOOMANY"} == 1
       eval_time: 3m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="DEVICE_HEALTH_TOOMANY"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: CephDeviceFailurePredictionTooHigh
    - eval_time: 10m
      alertname: CephDeviceFailurePredictionTooHigh
      exp_alerts:
      - exp_labels:
          name: "DEVICE_HEALTH_TOOMANY"
          severity: critical
          type: ceph_default
          oid: 1.3.6.1.4.1.50495.1.2.1.4.7
        exp_annotations:
          documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#device-health-toomany
          summary: Too many devices are predicted to fail, unable to resolve
          description: "The device health module has determined that devices predicted to fail can not be remediated automatically, since too many OSDs would be removed from the cluster to ensure performance and availabililty. Prevent data integrity issues by adding new OSDs so that data may be relocated."
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="DEVICE_HEALTH_IN_USE"}'
      values: '0+0x2 1+0x10'
   promql_expr_test:
     - expr: ceph_health_detail{name="DEVICE_HEALTH_IN_USE"} == 1
       eval_time: 3m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="DEVICE_HEALTH_IN_USE"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: CephDeviceFailureRelocationIncomplete
    - eval_time: 10m
      alertname: CephDeviceFailureRelocationIncomplete
      exp_alerts:
      - exp_labels:
          name: "DEVICE_HEALTH_IN_USE"
          severity: warning
          type: ceph_default
        exp_annotations:
          documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#device-health-in-use
          summary: Device failure is predicted, but unable to relocate data
          description: "The device health module has determined that one or more devices will fail soon, but the normal process of relocating the data on the device to other OSDs in the cluster is blocked. \nEnsure that the cluster has available free space. It may be necessary to add capacity to the cluster to allow data from the failing device to successfully migrate, or to enable the balancer."
# OSD
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="OSD_HOST_DOWN"}'
      values: '0+0x2 1+0x10'
    - series: 'ceph_osd_up{ceph_daemon="osd.0"}'
      values: '1+0x2 0+0x10'
    - series: 'ceph_osd_metadata{ceph_daemon="osd.0", hostname="ceph-osd-1"}'
      values: '1+0x12'
   promql_expr_test:
     - expr: ceph_health_detail{name="OSD_HOST_DOWN"} == 1
       eval_time: 3m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="OSD_HOST_DOWN"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: CephOSDHostDown
    - eval_time: 10m
      alertname: CephOSDHostDown
      exp_alerts:
      - exp_labels:
          name: "OSD_HOST_DOWN"
          severity: warning
          type: ceph_default
          oid: 1.3.6.1.4.1.50495.1.2.1.4.8
        exp_annotations:
          summary: An OSD host is offline
          description: "The following OSDs are down: - ceph-osd-1 : osd.0"
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="OSD_SLOW_PING_TIME_FRONT"}'
      values: '0+0x2 1+0x20'
   promql_expr_test:
     - expr: ceph_health_detail{name="OSD_SLOW_PING_TIME_FRONT"} == 0
       eval_time: 1m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="OSD_SLOW_PING_TIME_FRONT"}'
           value: 0
   alert_rule_test:
    - eval_time: 1m
      alertname: CephOSDTimeoutsPublicNetwork
    - eval_time: 10m
      alertname: CephOSDTimeoutsPublicNetwork
      exp_alerts:
      - exp_labels:
          name: "OSD_SLOW_PING_TIME_FRONT"
          severity: warning
          type: ceph_default
        exp_annotations:
          summary: Network issues delaying OSD heartbeats (public network)
          description: "OSD heartbeats on the cluster's 'public' network (frontend) are running slow. Investigate the network for latency or loss issues. Use 'ceph health detail' to show the affected OSDs."
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="OSD_SLOW_PING_TIME_BACK"}'
      values: '0+0x2 1+0x20'
   promql_expr_test:
     - expr: ceph_health_detail{name="OSD_SLOW_PING_TIME_BACK"} == 0
       eval_time: 1m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="OSD_SLOW_PING_TIME_BACK"}'
           value: 0
   alert_rule_test:
    - eval_time: 1m
      alertname: CephOSDTimeoutsClusterNetwork
    - eval_time: 10m
      alertname: CephOSDTimeoutsClusterNetwork
      exp_alerts:
      - exp_labels:
          name: "OSD_SLOW_PING_TIME_BACK"
          severity: warning
          type: ceph_default
        exp_annotations:
          summary: Network issues delaying OSD heartbeats (cluster network)
          description: "OSD heartbeats on the cluster's 'cluster' network (backend) are slow. Investigate the network for latency issues on this subnet. Use 'ceph health detail' to show the affected OSDs."
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="BLUESTORE_DISK_SIZE_MISMATCH"}'
      values: '0+0x2 1+0x20'
   promql_expr_test:
     - expr: ceph_health_detail{name="BLUESTORE_DISK_SIZE_MISMATCH"} == 0
       eval_time: 1m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="BLUESTORE_DISK_SIZE_MISMATCH"}'
           value: 0
   alert_rule_test:
    - eval_time: 1m
      alertname: CephOSDInternalDiskSizeMismatch
    - eval_time: 10m
      alertname: CephOSDInternalDiskSizeMismatch
      exp_alerts:
      - exp_labels:
          name: "BLUESTORE_DISK_SIZE_MISMATCH"
          severity: warning
          type: ceph_default
        exp_annotations:
          documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#bluestore-disk-size-mismatch
          summary: OSD size inconsistency error
          description: "One or more OSDs have an internal inconsistency between metadata and the size of the device. This could lead to the OSD(s) crashing in future. You should redeploy the affected OSDs."
 - interval: 30s
   input_series:
    - series: 'ceph_health_detail{name="BLUESTORE_SPURIOUS_READ_ERRORS"}'
      values: '0+0x2 1+0x20'
   promql_expr_test:
     - expr: ceph_health_detail{name="BLUESTORE_SPURIOUS_READ_ERRORS"} == 1
       eval_time: 3m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="BLUESTORE_SPURIOUS_READ_ERRORS"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: CephOSDReadErrors
    - eval_time: 10m
      alertname: CephOSDReadErrors
      exp_alerts:
      - exp_labels:
          name: "BLUESTORE_SPURIOUS_READ_ERRORS"
          severity: warning
          type: ceph_default
        exp_annotations:
          documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#bluestore-spurious-read-errors
          summary: Device read errors detected
          description: "An OSD has encountered read errors, but the OSD has recovered by retrying the reads. This may indicate an issue with hardware or the kernel."
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="OSD_DOWN"}'
      values: '0+0x2 1+0x10'
    - series: 'ceph_osd_up{ceph_daemon="osd.0"}'
      values: '1+0x12'
    - series: 'ceph_osd_up{ceph_daemon="osd.1"}'
      values: '1+0x2 0+0x10'
    - series: 'ceph_osd_up{ceph_daemon="osd.2"}'
      values: '1+0x12'
    - series: 'ceph_osd_metadata{ceph_daemon="osd.0", hostname="ceph-osd-1"}'
      values: '1+0x12'
    - series: 'ceph_osd_metadata{ceph_daemon="osd.1", hostname="ceph-osd-2"}'
      values: '1+0x12'
    - series: 'ceph_osd_metadata{ceph_daemon="osd.2", hostname="ceph-osd-3"}'
      values: '1+0x12'
   promql_expr_test:
     - expr: ceph_health_detail{name="OSD_DOWN"} == 1
       eval_time: 3m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="OSD_DOWN"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: CephOSDDown
    - eval_time: 10m
      alertname: CephOSDDown
      exp_alerts:
      - exp_labels:
          name: "OSD_DOWN"
          severity: warning
          type: ceph_default
          oid: 1.3.6.1.4.1.50495.1.2.1.4.2
        exp_annotations:
          documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-down
          summary: An OSD has been marked down
          description: "1 OSD down for over 5mins. The following OSD is down: - osd.1 on ceph-osd-2\n"
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="OSD_NEARFULL"}'
      values: '0+0x2 1+0x10'
   promql_expr_test:
     - expr: ceph_health_detail{name="OSD_NEARFULL"} == 1
       eval_time: 3m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="OSD_NEARFULL"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: CephOSDNearFull
    - eval_time: 10m
      alertname: CephOSDNearFull
      exp_alerts:
      - exp_labels:
          name: "OSD_NEARFULL"
          severity: warning
          type: ceph_default
          oid: 1.3.6.1.4.1.50495.1.2.1.4.3
        exp_annotations:
          documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-nearfull
          summary: OSD(s) running low on free space (NEARFULL)
          description: One or more OSDs have reached the NEARFULL threshold. Use 'ceph health detail' and 'ceph osd df' to identify the problem. To resolve, add capacity to the affected OSD's failure domain, restore down/out OSDs, or delete unwanted data.
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="OSD_FULL"}'
      values: '0+0x2 1+0x10'
   promql_expr_test:
     - expr: ceph_health_detail{name="OSD_FULL"} == 1
       eval_time: 3m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="OSD_FULL"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: CephOSDFull
    - eval_time: 10m
      alertname: CephOSDFull
      exp_alerts:
      - exp_labels:
          name: "OSD_FULL"
          severity: critical
          type: ceph_default
          oid: 1.3.6.1.4.1.50495.1.2.1.4.6
        exp_annotations:
          documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-full
          summary: OSD full, writes blocked
          description: An OSD has reached the FULL threshold. Writes to pools that share the affected OSD will be blocked. Use 'ceph health detail' and 'ceph osd df' to identify the problem. To resolve, add capacity to the affected OSD's failure domain, restore down/out OSDs, or delete unwanted data.
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="OSD_BACKFILLFULL"}'
      values: '0+0x2 1+0x10'
   promql_expr_test:
     - expr: ceph_health_detail{name="OSD_BACKFILLFULL"} == 1
       eval_time: 3m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="OSD_BACKFILLFULL"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: CephOSDBackfillFull
    - eval_time: 10m
      alertname: CephOSDBackfillFull
      exp_alerts:
      - exp_labels:
          name: "OSD_BACKFILLFULL"
          severity: warning
          type: ceph_default
        exp_annotations:
          documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-backfillfull
          summary: OSD(s) too full for backfill operations
          description: "An OSD has reached the BACKFILL FULL threshold. This will prevent rebalance operations from completing. Use 'ceph health detail' and 'ceph osd df' to identify the problem. To resolve, add capacity to the affected OSD's failure domain, restore down/out OSDs, or delete unwanted data."
 - interval: 30s
   input_series:
    - series: 'ceph_health_detail{name="OSD_TOO_MANY_REPAIRS"}'
      values: '0+0x2 1+0x20'
   promql_expr_test:
     - expr: ceph_health_detail{name="OSD_TOO_MANY_REPAIRS"} == 0
       eval_time: 1m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="OSD_TOO_MANY_REPAIRS"}'
           value: 0
   alert_rule_test:
    - eval_time: 1m
      alertname: CephOSDTooManyRepairs
    - eval_time: 10m
      alertname: CephOSDTooManyRepairs
      exp_alerts:
      - exp_labels:
          name: "OSD_TOO_MANY_REPAIRS"
          severity: warning
          type: ceph_default
        exp_annotations:
          documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-too-many-repairs
          summary: OSD reports a high number of read errors
          description: Reads from an OSD have used a secondary PG to return data to the client, indicating a potential failing drive.
# Pools
   # trigger percent full prediction on pools 1 and 2 only
 - interval: 12h
   input_series:
    - series: 'ceph_pool_percent_used{pool_id="1", instance="9090"}'
      values: '1 1 1 1 1'
    - series: 'ceph_pool_percent_used{pool_id="1", instance="8090"}'
      values: '78 89 79 98 78'
    - series: 'ceph_pool_percent_used{pool_id="2", instance="9090"}'
      values: '1 1 1 1 1'
    - series: 'ceph_pool_percent_used{pool_id="2", instance="8090"}'
      values: '22 22 23 23 24'
    - series: 'ceph_pool_metadata{pool_id="1" , instance="9090" ,name="rbd",type="replicated"}'
      values: '1 1 1 1 1'
    - series: 'ceph_pool_metadata{pool_id="1", instance="8090",name="default.rgw.index",type="replicated"}'
      values: '1 1 1 1 1'
    - series: 'ceph_pool_metadata{pool_id="2" , instance="9090" ,name="rbd",type="replicated"}'
      values: '1 1 1 1 1'
    - series: 'ceph_pool_metadata{pool_id="2", instance="8090",name="default.rgw.index",type="replicated"}'
      values: '1 1 1 1 1'
   promql_expr_test:
     - expr: |
         (predict_linear(ceph_pool_percent_used[2d], 3600 * 24 * 5) * on(pool_id, instance)
              group_right() ceph_pool_metadata) >= 95
       eval_time: 36h
       exp_samples:
         - labels: '{instance="8090",name="default.rgw.index",pool_id="1",type="replicated"}'
           value: 1.435E+02 # 142%
   alert_rule_test:
    - eval_time: 48h
      alertname: CephPoolGrowthWarning
      exp_alerts:
      - exp_labels:
          instance: 8090
          name: default.rgw.index
          pool_id: 1
          severity: warning
          type: ceph_default
          oid: 1.3.6.1.4.1.50495.1.2.1.9.2
        exp_annotations:
          summary: Pool growth rate may soon exceed capacity
          description: Pool 'default.rgw.index' will be full in less than 5 days assuming the average fill-up rate of the past 48 hours.
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="POOL_BACKFILLFULL"}'
      values: '0+0x2 1+0x10'
   promql_expr_test:
     - expr: ceph_health_detail{name="POOL_BACKFILLFULL"} == 1
       eval_time: 3m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="POOL_BACKFILLFULL"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: CephPoolBackfillFull
    - eval_time: 5m
      alertname: CephPoolBackfillFull
      exp_alerts:
      - exp_labels:
          name: "POOL_BACKFILLFULL"
          severity: warning
          type: ceph_default
        exp_annotations:
          summary: Free space in a pool is too low for recovery/backfill
          description: A pool is approaching the near full threshold, which will prevent recovery/backfill operations from completing. Consider adding more capacity.

 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="POOL_NEAR_FULL"}'
      values: '0+0x2 1+0x10'
   promql_expr_test:
     - expr: ceph_health_detail{name="POOL_NEAR_FULL"} == 1
       eval_time: 3m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="POOL_NEAR_FULL"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: CephPoolNearFull
    - eval_time: 10m
      alertname: CephPoolNearFull
      exp_alerts:
      - exp_labels:
          name: "POOL_NEAR_FULL"
          severity: warning
          type: ceph_default
        exp_annotations:
          summary: One or more Ceph pools are nearly full
          description: "A pool has exceeded the warning (percent full) threshold, or OSDs supporting the pool have reached the NEARFULL threshold. Writes may continue, but you are at risk of the pool going read-only if more capacity isn't made available. Determine the affected pool with 'ceph df detail', looking at QUOTA BYTES and STORED. Increase the pool's quota, or add capacity to the cluster first then increase the pool's quota (e.g. ceph osd pool set quota <pool_name> max_bytes <bytes>). Also ensure that the balancer is active."

# PGs
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="PG_NOT_SCRUBBED"}'
      values: '0+0x2 1+0x10'
   promql_expr_test:
     - expr: ceph_health_detail{name="PG_NOT_SCRUBBED"} == 1
       eval_time: 3m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="PG_NOT_SCRUBBED"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: CephPGNotScrubbed
    - eval_time: 10m
      alertname: CephPGNotScrubbed
      exp_alerts:
      - exp_labels:
          name: "PG_NOT_SCRUBBED"
          severity: warning
          type: ceph_default
        exp_annotations:
          documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-not-scrubbed
          summary: Placement group(s) have not been scrubbed
          description: "One or more PGs have not been scrubbed recently. Scrubs check metadata integrity, protecting against bit-rot. They check that metadata is consistent across data replicas. When PGs miss their scrub interval, it may indicate that the scrub window is too small, or PGs were not in a 'clean' state during the scrub window. You can manually initiate a scrub with: ceph pg scrub <pgid>"
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="PG_DAMAGED"}'
      values: '0+0x4 1+0x20'
   promql_expr_test:
     - expr: ceph_health_detail{name=~"PG_DAMAGED|OSD_SCRUB_ERRORS"} == 1
       eval_time: 5m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="PG_DAMAGED"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: CephPGsDamaged
    - eval_time: 10m
      alertname: CephPGsDamaged
      exp_alerts:
      - exp_labels:
          name: "PG_DAMAGED"
          severity: critical
          type: ceph_default
          oid: 1.3.6.1.4.1.50495.1.2.1.7.4
        exp_annotations:
          documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-damaged
          summary: Placement group damaged, manual intervention needed
          description: During data consistency checks (scrub), at least one PG has been flagged as being damaged or inconsistent. Check to see which PG is affected, and attempt a manual repair if necessary. To list problematic placement groups, use 'rados list-inconsistent-pg <pool>'. To repair PGs use the 'ceph pg repair <pg_num>' command.
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="TOO_MANY_PGS"}'
      values: '0+0x4 1+0x20'
   promql_expr_test:
     - expr: ceph_health_detail{name="TOO_MANY_PGS"} == 1
       eval_time: 5m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="TOO_MANY_PGS"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: CephPGsHighPerOSD
    - eval_time: 10m
      alertname: CephPGsHighPerOSD
      exp_alerts:
      - exp_labels:
          name: "TOO_MANY_PGS"
          severity: warning
          type: ceph_default
        exp_annotations:
          documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks/#too-many-pgs
          summary: Placement groups per OSD is too high
          description: "The number of placement groups per OSD is too high (exceeds the mon_max_pg_per_osd setting).\n Check that the pg_autoscaler has not been disabled for any pools with 'ceph osd pool autoscale-status', and that the profile selected is appropriate. You may also adjust the target_size_ratio of a pool to guide the autoscaler based on the expected relative size of the pool ('ceph osd pool set cephfs.cephfs.meta target_size_ratio .1') or set the pg_autoscaler mode to 'warn' and adjust pg_num appropriately for one or more pools."
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="PG_RECOVERY_FULL"}'
      values: '0+0x2 1+0x20'
   promql_expr_test:
     - expr: ceph_health_detail{name="PG_RECOVERY_FULL"} == 0
       eval_time: 1m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="PG_RECOVERY_FULL"}'
           value: 0
   alert_rule_test:
    - eval_time: 1m
      alertname: CephPGRecoveryAtRisk
    - eval_time: 10m
      alertname: CephPGRecoveryAtRisk
      exp_alerts:
      - exp_labels:
          name: "PG_RECOVERY_FULL"
          severity: critical
          type: ceph_default
          oid: 1.3.6.1.4.1.50495.1.2.1.7.5
        exp_annotations:
          documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-recovery-full
          summary: OSDs are too full for recovery
          description: Data redundancy is at risk since one or more OSDs are at or above the 'full' threshold. Add more capacity to the cluster, restore down/out OSDs, or delete unwanted data.
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="PG_BACKFILL_FULL"}'
      values: '0+0x2 1+0x20'
   promql_expr_test:
     - expr: ceph_health_detail{name="PG_BACKFILL_FULL"} == 0
       eval_time: 1m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="PG_BACKFILL_FULL"}'
           value: 0
   alert_rule_test:
    - eval_time: 1m
      alertname: CephPGBackfillAtRisk
    - eval_time: 10m
      alertname: CephPGBackfillAtRisk
      exp_alerts:
      - exp_labels:
          name: "PG_BACKFILL_FULL"
          severity: critical
          type: ceph_default
          oid: 1.3.6.1.4.1.50495.1.2.1.7.6
        exp_annotations:
          documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-backfill-full
          summary: Backfill operations are blocked due to lack of free space
          description: Data redundancy may be at risk due to lack of free space within the cluster. One or more OSDs have reached the 'backfillfull' threshold. Add more capacity, or delete unwanted data.
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="PG_AVAILABILITY"}'
      values: '0 0 0 1 1 1 1 1 1 1 1 1 1 1 1 1'
    - series: 'ceph_health_detail{name="OSD_DOWN"}'
      values: '0 0 0 1 1 1 1 1 1 0 0 0 0 0 0 0'
   promql_expr_test:
     - expr: ((ceph_health_detail{name="PG_AVAILABILITY"} == 1) - scalar(ceph_health_detail{name="OSD_DOWN"}))
       eval_time: 1m
       # empty set at 1m
       exp_samples:
   alert_rule_test:
    # PG_AVAILABILITY and OSD_DOWN not firing .. no alert
    - eval_time: 1m
      alertname: CephPGUnavilableBlockingIO
      exp_alerts:
    # PG_AVAILABILITY firing, but osd_down is active .. no alert
    - eval_time: 5m
      alertname: CephPGUnavilableBlockingIO
      exp_alerts:
    # PG_AVAILABILITY firing, AND OSD_DOWN is not active...raise the alert
    - eval_time: 15m
      alertname: CephPGUnavilableBlockingIO
      exp_alerts:
      - exp_labels:
          name: "PG_AVAILABILITY"
          severity: critical
          type: ceph_default
          oid: 1.3.6.1.4.1.50495.1.2.1.7.3
        exp_annotations:
          documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-availability
          summary: PG is unavailable, blocking I/O
          description: Data availability is reduced, impacting the cluster's ability to service I/O. One or more placement groups (PGs) are in a state that blocks I/O.
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="PG_NOT_DEEP_SCRUBBED"}'
      values: '0+0x2 1+0x10'
   promql_expr_test:
     - expr: ceph_health_detail{name="PG_NOT_DEEP_SCRUBBED"} == 1
       eval_time: 3m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="PG_NOT_DEEP_SCRUBBED"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: CephPGNotDeepScrubbed
    - eval_time: 10m
      alertname: CephPGNotDeepScrubbed
      exp_alerts:
      - exp_labels:
          name: "PG_NOT_DEEP_SCRUBBED"
          severity: warning
          type: ceph_default
        exp_annotations:
          documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-not-deep-scrubbed
          summary: Placement group(s) have not been deep scrubbed
          description: One or more PGs have not been deep scrubbed recently. Deep scrubs protect against bit-rot. They compare data replicas to ensure consistency. When PGs miss their deep scrub interval, it may indicate that the window is too small or PGs were not in a 'clean' state during the deep-scrub window.

# Prometheus
 - interval: 1m
   input_series:
    - series: 'up{job="myjob"}'
      values: '1+0x10'
   promql_expr_test:
     - expr: absent(up{job="ceph"})
       eval_time: 1m
       exp_samples:
         - labels: '{job="ceph"}'
           value: 1
   alert_rule_test:
    - eval_time: 5m
      alertname: PrometheusJobMissing
      exp_alerts:
      - exp_labels:
          job: ceph
          severity: critical
          type: ceph_default
          oid: 1.3.6.1.4.1.50495.1.2.1.12.1
        exp_annotations:
          summary: The scrape job for Ceph is missing from Prometheus
          description: The prometheus job that scrapes from Ceph is no longer defined, this will effectively mean you'll have no metrics or alerts for the cluster.  Please review the job definitions in the prometheus.yml file of the prometheus instance.
# RADOS
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="OBJECT_UNFOUND"}'
      values: '0 0 0 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
    - series: 'ceph_osd_up{ceph_daemon="osd.0"}'
      values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
    - series: 'ceph_osd_up{ceph_daemon="osd.1"}'
      values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
    - series: 'ceph_osd_up{ceph_daemon="osd.2"}'
      values: '1 1 1 0 0 0 0 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
    - series: 'ceph_osd_metadata{ceph_daemon="osd.0"}'
      values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
    - series: 'ceph_osd_metadata{ceph_daemon="osd.1"}'
      values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
    - series: 'ceph_osd_metadata{ceph_daemon="osd.2"}'
      values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1'
   promql_expr_test:
     - expr: (ceph_health_detail{name="OBJECT_UNFOUND"} == 1) * on() (count(ceph_osd_up == 1) == bool count(ceph_osd_metadata)) == 1
       eval_time: 1m
       exp_samples:
   alert_rule_test:
    # OBJECT_UNFOUND but osd.2 is down, so don't fire
    - eval_time: 5m
      alertname: CephObjectMissing
      exp_alerts:
    # OBJECT_UNFOUND and all osd's are online, so fire
    - eval_time: 15m
      alertname: CephObjectMissing
      exp_alerts:
      - exp_labels:
          severity: critical
          type: ceph_default
          oid: 1.3.6.1.4.1.50495.1.2.1.10.1
        exp_annotations:
          documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#object-unfound
          summary: Object(s) marked UNFOUND
          description: The latest version of a RADOS object can not be found, even though all OSDs are up. I/O requests for this object from clients will block (hang). Resolving this issue may require the object to be rolled back to a prior version manually, and manually verified.
# Generic Alerts
 - interval: 1m
   input_series:
    - series: 'ceph_health_detail{name="RECENT_CRASH"}'
      values: '0 0 0 1 1 1 1 1 1 1 1'
   promql_expr_test:
     - expr: ceph_health_detail{name="RECENT_CRASH"} == 1
       eval_time: 1m
       exp_samples:
   alert_rule_test:
    # not firing
    - eval_time: 1m
      alertname: CephDaemonCrash
      exp_alerts:
    # firing
    - eval_time: 10m
      alertname: CephDaemonCrash
      exp_alerts:
      - exp_labels:
          name: RECENT_CRASH
          severity: critical
          type: ceph_default
          oid: 1.3.6.1.4.1.50495.1.2.1.1.2
        exp_annotations:
          documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks/#recent-crash
          summary: One or more Ceph daemons have crashed, and are pending acknowledgement
          description: One or more daemons have crashed recently, and need to be acknowledged. This notification ensures that software crashes do not go unseen. To acknowledge a crash, use the 'ceph crash archive <id>' command.
 - interval: 30s
   input_series:
    - series: 'ceph_health_detail{name="HARDWARE_STORAGE"}'
      values: '1+0x40'
   promql_expr_test:
     - expr: ceph_health_detail{name="HARDWARE_STORAGE"} > 0
       eval_time: 2m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="HARDWARE_STORAGE"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: HardwareStorageError
    - eval_time: 5m
      alertname: HardwareStorageError
      exp_alerts:
      - exp_labels:
          name: HARDWARE_STORAGE
          severity: critical
          type: ceph_default
          oid: 1.3.6.1.4.1.50495.1.2.1.13.1
        exp_annotations:
          summary: Storage devices error(s) detected
          description: "Some storage devices are in error. Check `ceph health detail`."
 - interval: 30s
   input_series:
    - series: 'ceph_health_detail{name="HARDWARE_MEMORY"}'
      values: '1+0x40'
   promql_expr_test:
     - expr: ceph_health_detail{name="HARDWARE_MEMORY"} > 0
       eval_time: 2m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="HARDWARE_MEMORY"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: HardwareMemoryError
    - eval_time: 5m
      alertname: HardwareMemoryError
      exp_alerts:
      - exp_labels:
          name: HARDWARE_MEMORY
          severity: critical
          type: ceph_default
          oid: 1.3.6.1.4.1.50495.1.2.1.13.2
        exp_annotations:
          summary: DIMM error(s) detected
          description: "DIMM error(s) detected. Check `ceph health detail`."
 - interval: 30s
   input_series:
    - series: 'ceph_health_detail{name="HARDWARE_PROCESSOR"}'
      values: '1+0x40'
   promql_expr_test:
     - expr: ceph_health_detail{name="HARDWARE_PROCESSOR"} > 0
       eval_time: 2m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="HARDWARE_PROCESSOR"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: HardwareProcessorError
    - eval_time: 5m
      alertname: HardwareProcessorError
      exp_alerts:
      - exp_labels:
          name: HARDWARE_PROCESSOR
          severity: critical
          type: ceph_default
          oid: 1.3.6.1.4.1.50495.1.2.1.13.3
        exp_annotations:
          summary: Processor error(s) detected
          description: "Processor error(s) detected. Check `ceph health detail`."
 - interval: 30s
   input_series:
    - series: 'ceph_health_detail{name="HARDWARE_NETWORK"}'
      values: '1+0x40'
   promql_expr_test:
     - expr: ceph_health_detail{name="HARDWARE_NETWORK"} > 0
       eval_time: 2m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="HARDWARE_NETWORK"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: HardwareNetworkError
    - eval_time: 5m
      alertname: HardwareNetworkError
      exp_alerts:
      - exp_labels:
          name: HARDWARE_NETWORK
          severity: critical
          type: ceph_default
          oid: 1.3.6.1.4.1.50495.1.2.1.13.4
        exp_annotations:
          summary: Network error(s) detected
          description: "Network error(s) detected. Check `ceph health detail`."
 - interval: 30s
   input_series:
    - series: 'ceph_health_detail{name="HARDWARE_POWER"}'
      values: '1+0x40'
   promql_expr_test:
     - expr: ceph_health_detail{name="HARDWARE_POWER"} > 0
       eval_time: 2m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="HARDWARE_POWER"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: HardwarePowerError
    - eval_time: 5m
      alertname: HardwarePowerError
      exp_alerts:
      - exp_labels:
          name: HARDWARE_POWER
          severity: critical
          type: ceph_default
          oid: 1.3.6.1.4.1.50495.1.2.1.13.5
        exp_annotations:
          summary: Power supply error(s) detected
          description: "Power supply error(s) detected. Check `ceph health detail`."
 - interval: 30s
   input_series:
    - series: 'ceph_health_detail{name="HARDWARE_FANS"}'
      values: '1+0x40'
   promql_expr_test:
     - expr: ceph_health_detail{name="HARDWARE_FANS"} > 0
       eval_time: 2m
       exp_samples:
         - labels: '{__name__="ceph_health_detail", name="HARDWARE_FANS"}'
           value: 1
   alert_rule_test:
    - eval_time: 1m
      alertname: HardwareFanError
    - eval_time: 5m
      alertname: HardwareFanError
      exp_alerts:
      - exp_labels:
          name: HARDWARE_FANS
          severity: critical
          type: ceph_default
          oid: 1.3.6.1.4.1.50495.1.2.1.13.6
        exp_annotations:
          summary: Fan error(s) detected
          description: "Fan error(s) detected. Check `ceph health detail`."