I am pretty new to the Kapacitor, I am trying to get the failure rate of the individual application, so in same measurement for the individual application I have failure and success message so i am trying to compute the percentage of the failure for the individual application. I am using the below tick script: But as you can see below Join is not processing any results.
Any help is much appreciated.
var fail = stream
|from()
.measurement(‘apm_event’)
.where(lambda: “component_category” == ‘HTTP_FILTER’ AND “status” == ‘FAIL’)
|window()
.period(5m)
.every(10s)
|groupBy(‘appl_id’)
|count(‘elapse_time’)
.as(‘elapse_time’)
var total = stream
|from()
.measurement(‘apm_event’)
.where(lambda: “component_category” == ‘HTTP_FILTER’)
|window()
.period(5m)
.every(10s)
|groupBy(‘appl_id’)
|count(‘elapse_time’)
.as(‘elapse_time’)
fail
|join(total)
.as(‘fails’, ‘totals’)
.on(‘appl_id’)
// |eval(lambda: 100.0 * float(“fails.elapse_time”) / float(“totals.elapse_time”))
// .as(‘value’)
|alert()
.crit(lambda: “value” > 0)
.log(’/tmp/alerts4.log’)
DOT:
digraph service_failure_alerts {
graph [throughput=“48.00 points/s”];
stream0 [avg_exec_time_ns=“0s” errors=“0” working_cardinality=“0” ];
stream0 -> from5 [processed=“4190”];
stream0 -> from1 [processed=“4190”];
from5 [avg_exec_time_ns=“2.86µs” errors=“0” working_cardinality=“0” ];
from5 -> window6 [processed=“2884”];
window6 [avg_exec_time_ns=“2.577µs” errors=“0” working_cardinality=“1” ];
window6 -> groupby7 [processed=“4”];
groupby7 [avg_exec_time_ns=“0s” errors=“0” working_cardinality=“46” ];
groupby7 -> count8 [processed=“102”];
count8 [avg_exec_time_ns=“255.908µs” errors=“0” working_cardinality=“0” ];
count8 -> join10 [processed=“102”];
from1 [avg_exec_time_ns=“4.991µs” errors=“0” working_cardinality=“0” ];
from1 -> window2 [processed=“42”];
window2 [avg_exec_time_ns=“2.4µs” errors=“0” working_cardinality=“1” ];
window2 -> groupby3 [processed=“3”];
groupby3 [avg_exec_time_ns=“0s” errors=“0” working_cardinality=“3” ];
groupby3 -> count4 [processed=“3”];
count4 [avg_exec_time_ns=“0s” errors=“0” working_cardinality=“0” ];
count4 -> join10 [processed=“3”];
join10 [avg_exec_time_ns=“11.406µs” errors=“0” working_cardinality=“0” ];
join10 -> alert11 [processed=“0”];
alert11 [alerts_triggered=“0” avg_exec_time_ns=“0s” crits_triggered=“0” errors=“0” infos_triggered=“0” oks_triggered=“0” warns_triggered=“0” working_cardinality=“0” ];
