Skip to content

Commit a878460

Browse files
committed
monitoring: add tests for 2 new nvmeof alerts
Add test for alerts NVMeoFMissingListener and NVMeoFZeroListenerSubsystem to test_alerts.yml. Signed-off-by: Vallari Agrawal <vallari.agrawal@ibm.com>
1 parent 7994fea commit a878460

1 file changed

Lines changed: 69 additions & 0 deletions

File tree

monitoring/ceph-mixin/tests_alerts/test_alerts.yml

Lines changed: 69 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -2522,6 +2522,75 @@ tests:
25222522
exp_annotations:
25232523
summary: "The number of clients connected to nqn1 is too high on cluster mycluster"
25242524
description: "The supported limit for clients connecting to a subsystem is 32"
2525+
2526+
# NVMeoFMissingListener
2527+
- interval: 1m
2528+
input_series:
2529+
- series: 'ceph_nvmeof_subsystem_listener_count{nqn="nqn1", instance="node-1:9100"}'
2530+
values: '0 0 0 0 0 0 0 0 0 0 0'
2531+
- series: 'ceph_nvmeof_subsystem_listener_count{nqn="nqn1", instance="node-2:9100"}'
2532+
values: '1 1 1 1 1 1 1 1 1 1 1'
2533+
- series: 'ceph_nvmeof_subsystem_listener_count{nqn="nqn1", instance="node-3:9100"}'
2534+
values: '1 1 1 1 1 1 1 1 1 1 1'
2535+
- series: 'ceph_nvmeof_gateway_info{addr="1.1.1.1", instance="node-1:9100"}'
2536+
values: '1+0x20'
2537+
- series: 'ceph_nvmeof_gateway_info{addr="1.1.1.2", instance="node-2:9100"}'
2538+
values: '1+0x20'
2539+
- series: 'ceph_nvmeof_gateway_info{addr="1.1.1.3", instance="node-3:9100"}'
2540+
values: '1+0x20'
2541+
- series: 'ceph_nvmeof_gateway_info{addr="1.1.1.4", instance="node-4:9100"}'
2542+
values: '1+0x20'
2543+
promql_expr_test:
2544+
- expr: ceph_nvmeof_subsystem_listener_count == 0 and on(nqn) sum(ceph_nvmeof_subsystem_listener_count) by (nqn) > 0
2545+
eval_time: 1m
2546+
exp_samples:
2547+
- labels: '{__name__="ceph_nvmeof_subsystem_listener_count", instance="node-1:9100", nqn="nqn1"}'
2548+
value: 0
2549+
alert_rule_test:
2550+
- eval_time: 10m
2551+
alertname: NVMeoFMissingListener
2552+
exp_alerts:
2553+
- exp_labels:
2554+
instance: node-1:9100
2555+
nqn: nqn1
2556+
severity: warning
2557+
type: ceph_default
2558+
exp_annotations:
2559+
summary: "No listener added for node-1:9100 NVMe-oF Gateway to nqn1 subsystem"
2560+
description: "For every subsystem, each gateway should have a listener to balance traffic between gateways."
2561+
2562+
# NVMeoFZeroListenerSubsystem
2563+
- interval: 1m
2564+
input_series:
2565+
- series: 'ceph_nvmeof_subsystem_listener_count{nqn="nqn1"}'
2566+
values: '0 0 0 0 0 0 0 0'
2567+
- series: 'ceph_nvmeof_subsystem_listener_count{nqn="nqn2"}'
2568+
values: '0 1 1 1 2 2 3 4'
2569+
- series: 'ceph_nvmeof_gateway_info{addr="1.1.1.1"}'
2570+
values: '1+0x20'
2571+
- series: 'ceph_nvmeof_gateway_info{addr="1.1.1.2"}'
2572+
values: '1+0x20'
2573+
- series: 'ceph_nvmeof_gateway_info{addr="1.1.1.3"}'
2574+
values: '1+0x20'
2575+
- series: 'ceph_nvmeof_gateway_info{addr="1.1.1.4"}'
2576+
values: '1+0x20'
2577+
promql_expr_test:
2578+
- expr: ceph_nvmeof_subsystem_listener_count == 0
2579+
eval_time: 1m
2580+
exp_samples:
2581+
- labels: '{__name__="ceph_nvmeof_subsystem_listener_count",nqn="nqn1"}'
2582+
value: 0
2583+
alert_rule_test:
2584+
- eval_time: 10m
2585+
alertname: NVMeoFZeroListenerSubsystem
2586+
exp_alerts:
2587+
- exp_labels:
2588+
nqn: nqn1
2589+
severity: warning
2590+
type: ceph_default
2591+
exp_annotations:
2592+
summary: "No listeners added to nqn1 subsystem"
2593+
description: "NVMeoF gateway configuration incomplete; one of the subsystems have zero listeners."
25252594

25262595
# NVMeoFHighHostCPU
25272596
- interval: 1m

0 commit comments

Comments
 (0)