Verson 1.1.13

docs/releasenotes.rst

@@ -1,6 +1,14 @@
 Release notes
 #############
 
+=======
+Version 1.1.13
+==============
+
+- fix: Static span is defined in Burrow detailed view charts
+- fix: Prevents removed Burrow consumers to appear as low range when latest metrics available are part of the selected time range
+- fix: Missing group by statement for Burrow consumers monitoring in OOTB alert, generates unexpected output containing OK consumers, while alerts are correctly justified for ERR consumers
+
 Version 1.1.12
 ==============
 

telegraf-kafka/default/app.conf

@@ -16,4 +16,4 @@ label = Kafka Smart Monitoring
 [launcher]
 author = Guilhem Marchand
 description = Kafka Smart Monitoring provides advanced and fast monitoring of Kafka and Confluent streaming platform
-version = 1.1.12
+version = 1.1.13

telegraf-kafka/default/data/ui/views/telegraf-burrow-detailed.xml

@@ -41,7 +41,7 @@
 | lookup burrow_status status_code OUTPUT status, description
 | rangemap field=status_code low=1-1 elevated=2-2 default=severe
 | eval avg_lag=round(avg_lag, 3), delta_lastTime=now()-lastTime, lastTime=strftime(lastTime, "%H:%M:%S")
-| eval status=if(delta_lastTime>120, "UNKNOWN", status), description=if(delta_lastTime>120, "The delta in seconds between the last state received and now has exceeded 120 seconds", description)
+| eval status=if(delta_lastTime>120, "UNKNOWN", status), description=if(delta_lastTime>120, "The delta in seconds between the last state received and now has exceeded 120 seconds", description), range=if(delta_lastTime>120, "severe", range)
 | appendcols [ | mcatalog values(topic) as topics where metric_name="burrow_partition.lag" `telegraf_kafka_index` group="$group$" by group ]
 | fields group, topics, avg_lag, max_lag, current, sparkline, status, range, lastTime, description | rename description as "status description", topics as "consuming from topics"</query>
                     <earliest>$time.earliest$</earliest>
@@ -96,7 +96,7 @@
                 <title>Group consumer lag over time</title>
                 <search>
                     <query>| mstats max(_value) as value where `telegraf_kafka_index` metric_name="burrow_group.lag" env=$env$ label=$label$ group="$group$" span=10s
-| timechart span=1m avg(value) as "average lag", max(value) as "max lag"</query>
+| timechart `telegraf_kafka_span` avg(value) as "average lag", max(value) as "max lag"</query>
                     <earliest>$time.earliest$</earliest>
                     <latest>$time.latest$</latest>
                     <refresh>30s</refresh>
@@ -166,7 +166,7 @@
                 <title>By topic lag over time</title>
                 <search>
                     <query>| mstats max(_value) as value where `telegraf_kafka_index` metric_name="burrow_partition.lag" env=$env$ label=$label$ group="$group$" ($topic$) by topic span=10s
-| timechart useother=f limit=45 span=1m $bytopic_statsmode$(value) as lag by topic</query>
+| timechart useother=f limit=45 `telegraf_kafka_span` $bytopic_statsmode$(value) as lag by topic</query>
                     <earliest>$time.earliest$</earliest>
                     <latest>$time.latest$</latest>
                     <refresh>30s</refresh>
@@ -218,7 +218,7 @@
 | lookup burrow_status status_code OUTPUT status, description
 | rangemap field=status_code low=1-1 elevated=2-2 default=severe
 | eval avg_lag=round(avg_lag, 3), delta_lastTime=now()-lastTime, lastTime=strftime(lastTime, "%H:%M:%S")
-| eval status=if(delta_lastTime>120, "UNKNOWN", status), description=if(delta_lastTime>120, "The delta in seconds between the last state received and now has exceeded 120 seconds", description)
+| eval status=if(delta_lastTime>120, "UNKNOWN", status), description=if(delta_lastTime>120, "The delta in seconds between the last state received and now has exceeded 120 seconds", description), range=if(delta_lastTime>120, "severe", range)
 | join topic, partition [ | mstats latest(_value) prestats=t where metric_name="burrow_topic.offset" `telegraf_kafka_index` env=$env$ label=$label$ $topic$ by topic, partition
 | stats latest(_value) as topic_offset by topic, partition ]
 | fields topic, partition, topic_offset, current_offset, avg_lag, max_lag, current, sparkline, status, range, lastTime, description | rename description as "status description"</query>

telegraf-kafka/default/data/ui/views/telegraf-burrow.xml

@@ -110,7 +110,7 @@
 | lookup burrow_status status_code OUTPUT status, description
 | rangemap field=status_code low=1-1 elevated=2-2 default=severe
 | eval avg_lag=round(avg_lag, 3), delta_lastTime=now()-lastTime, lastTime=strftime(lastTime, "%H:%M:%S")
-| eval status=if(delta_lastTime>120, "UNKNOWN", status), description=if(delta_lastTime>120, "The delta in seconds between the last state received and now has exceeded 120 seconds", description)
+| eval status=if(delta_lastTime>120, "UNKNOWN", status), description=if(delta_lastTime>120, "The delta in seconds between the last state received and now has exceeded 120 seconds", description), range=if(delta_lastTime>120, "severe", range)
 | search ($group_status$)
 | fields env, label, cluster, group, avg_lag, max_lag, current, sparkline, status, range, lastTime, description | rename description as "status description"
 | lookup kafka_burrow_consumers_monitoring env, label, cluster, group OUTPUT monitoring_state</query>

telegraf-kafka/default/savedsearches.conf

@@ -1025,7 +1025,7 @@ search = | mstats latest(_value) as status_code where metric_name="burrow_group.
 | stats latest(status_code) as status_code, max(_time) as last_time by env, label, cluster, group\
 | lookup burrow_status status_code OUTPUT status, description as status_description\
 | append [ | inputlookup kafka_burrow_consumers_monitoring ]\
-| stats first(last_time) as last_time values(*) as "*" by env, label, cluster\
+| stats first(last_time) as last_time values(*) as "*" by env, label, cluster, group\
 | eval now=now(), delta_seconds=now-last_time, now=strftime(now, "%d/%m/%Y %H:%M:%S"), last_time=strftime(last_time, "%d/%m/%Y %H:%M:%S")\
 | eval state=case(status_code!=1, "severe", status_code=1, "low"), state=if(delta_seconds>120, "severe", state), status=if(delta_seconds>120, "unknown", status), status_description=if(delta_seconds>120, "The delta in seconds between the last state received and now has exceeded 120 seconds", status_description)\
 | eval last_time=if(isnull(last_time), "out of time range scope", last_time), delta_seconds=if(isnull(delta_seconds), "out of time range scope", delta_seconds)\