Release 01/10/2024

alert-policies/browser/AjaxTimetoSettle.yml

@@ -11,7 +11,7 @@ type: BASELINE
 # NRQL query
 nrql:
   # Baseline alerts can use an optional FACET
-  query: "SELECT average(timeToSettle) FROM AjaxRequest WHERE appName like '%' FACET appName TIMESERIES"
+  query: "SELECT average(timeToSettle) FROM AjaxRequest WHERE appName like '%' FACET appName"
 
 # Direction in which baseline is set (Default: LOWER_ONLY)
 baselineDirection: UPPER_ONLY

alert-policies/langchain-vectordb/APIResponseTime.yml

@@ -10,7 +10,7 @@ type: STATIC
 
 # NRQL query
 nrql:
-  query: "FROM LlmVectorSearch SELECT latest(response_time) WHERE applicationName IN ('LangChain observability trace') TIMESERIES"
+  query: "FROM LlmVectorSearch SELECT latest(response_time) WHERE applicationName IN ('LangChain observability trace')"
 
 # Function used to aggregate the NRQL query value(s) for comparison to the terms.threshold (Default: SINGLE_VALUE)
 valueFunction: SINGLE_VALUE

alert-policies/llm-application/APIResponseTime.yml

@@ -10,7 +10,7 @@ type: STATIC
 
 # NRQL query
 nrql:
-  query: "FROM LlmChatCompletionSummary, LlmCompletion, LlmEmbedding SELECT percentile(response_time, 95) TIMESERIES FACET entity.guid"
+  query: "FROM LlmChatCompletionSummary, LlmCompletion, LlmEmbedding SELECT percentile(response_time, 95) FACET entity.guid"
 
 # Function used to aggregate the NRQL query value(s) for comparison to the terms.threshold (Default: SINGLE_VALUE)
 valueFunction: SINGLE_VALUE

alert-policies/nextcloud/ScrapeErrors.yml → alert-policies/nextcloud/CPUUsage.yml

@@ -1,11 +1,11 @@
-name: Scrape Errors
+name: CPU Usage
 
 description: |+
-  This alert is triggered  when the cache size limit is reached above 4 for at least 5 minutes.
+  This alert is triggered  when the CPU Usage exceeds 90% for at least 5 minutes.
 
 type: STATIC
 nrql:
-  query: "FROM Metric SELECT sum(nextcloud_scrape_errors_total) As 'Scrape Errors'"
+  query: "SELECT average(host.cpuPercent) AS '(%) used CPU' FROM Metric"
 
 # Function used to aggregate the NRQL query value(s) for comparison to the terms.threshold (Default: SINGLE_VALUE).
 valueFunction: SINGLE_VALUE
@@ -16,7 +16,7 @@ terms:
     # Operator used to compare against the threshold.
     operator: ABOVE
     # Value that triggers a violation.
-    threshold: 4  
+    threshold: 90 
     # Time in seconds; 120 - 3600
     thresholdDuration: 300
     # How many data points must be in violation for the duration?
@@ -26,7 +26,7 @@ terms:
     # Operator used to compare against the threshold.
     operator: ABOVE
     # Value that triggers a violation.
-    threshold: 1  
+    threshold: 80 
     # Time in seconds; 120 - 3600
     thresholdDuration: 300
     # How many data points must be in violation for the duration?

alert-policies/nextcloud/HeapMemoryUsage.yml → alert-policies/nextcloud/MemoryUsage.yml

@@ -1,11 +1,11 @@
-name: Heap Memory Usage
+name: Memory Usage 
 
 description: |+
-  This alert is triggered  when the Heap Memory Usage is below 2 for at least 5 minutes.
+  This alert is triggered  when the Memory Usage exceeds 90% for at least 5 minutes.
 
 type: STATIC
 nrql:
-  query: "FROM Metric select latest(go_memstats_heap_inuse_bytes)/1e+6 As 'Heap Memory Usage'"
+  query: "FROM NextcloudFlexMetrics select (latest(ocs.data.server.php.opcache.memory_usage.used_memory) / 1e+6) / (latest(ocs.data.server.php.opcache.memory_usage.free_memory) / 1e+6) * 100 AS '(%) used memory'"
 
 # Function used to aggregate the NRQL query value(s) for comparison to the terms.threshold (Default: SINGLE_VALUE).
 valueFunction: SINGLE_VALUE
@@ -14,19 +14,19 @@ valueFunction: SINGLE_VALUE
 terms:
   - priority: CRITICAL
     # Operator used to compare against the threshold.
-    operator: BELOW
+    operator: ABOVE
     # Value that triggers a violation.
-    threshold: 2  
+    threshold: 90 
     # Time in seconds; 120 - 3600
     thresholdDuration: 300
     # How many data points must be in violation for the duration?
     thresholdOccurrences: ALL
 
   - priority: WARNING
     # Operator used to compare against the threshold.
-    operator: BELOW
+    operator: ABOVE
     # Value that triggers a violation.
-    threshold: 4  
+    threshold: 80 
     # Time in seconds; 120 - 3600
     thresholdDuration: 300
     # How many data points must be in violation for the duration?

alert-policies/postfix/ConnectionLost.yml → alert-policies/postfix/BouncedEmails.yml

@@ -1,16 +1,16 @@
 # Name of the alert
-name: SMTPD Connection Lost (%)
+name: Bounced Emails
 
 # Description and details
 description: |+
-  This alert is triggered when the lost connections exceed 5%.
+  This alert is triggered when bounced emails exceed 5.
 
 # Type of alert
 type: STATIC
 
 # NRQL query
 nrql:
-  query: "SELECT (latest(PostfixSMTPDconnectionLost.value) * 100) / (SELECT latest(value) FROM PostfixSMTPDconnection) AS '(%) connection lost' FROM PostfixSMTPDconnectionLost"
+  query: "SELECT latest(bounced) As 'Bounced - failed emails' FROM `unixMonitor:postfix_messagesTotalRecords`"
 
 # Function used to aggregate the NRQL query value(s) for comparison to the terms.threshold (Default: SINGLE_VALUE)
 valueFunction: SINGLE_VALUE

alert-policies/postfix/ConnectionTimeout.yml → alert-policies/postfix/SMTPAuthenticationFails.yml

@@ -1,16 +1,16 @@
 # Name of the alert
-name: SMTPD Connection Timed Out (%)
+name: SMTP Authentication Fails
 
 # Description and details
 description: |+
-  This alert is triggered when the connection timeout exceeds 5%.
+  This alert is triggered when SMTP authentication fails exceed 5.
 
 # Type of alert
 type: STATIC
 
 # NRQL query
 nrql:
-  query: "SELECT (latest(PostfixSMTPDtimedOut.value) * 100) / (SELECT latest(value) FROM PostfixSMTPDconnection) AS '(%) connection timed out' FROM PostfixSMTPDtimedOut"
+  query: "SELECT latest(smtp_authfailed_count) FROM `unixMonitor:postfix_smtp_authFailed_today`"
 
 # Function used to aggregate the NRQL query value(s) for comparison to the terms.threshold (Default: SINGLE_VALUE)
 valueFunction: SINGLE_VALUE

dashboards/jfrog-artifactory/jfrog-artifactory.json

@@ -858,7 +858,7 @@
             "nrqlQueries": [
               {
                 "accountId": 0,
-                "query": "FROM Metric SELECT average(jfrog.artifactory.jfrt_http_connections_max_total) as 'Maximum', average(jfrog.artifactory.jfrt_http_connections_leased_total) as 'Leased', average(jfrog.artifactory.jfrt_http_connections_pending_total) as 'Pending', average(jfrog.artifactory.jfrt_http_connections_available_total) as 'Available' TIMESERIES"
+                "query": "FROM Metric SELECT average(jfrog.artifactory.jfrt_http_connections_max_%_total) as 'Maximum', average(jfrog.artifactory.jfrt_http_connections_leased_%_total) as 'Leased', average(jfrog.artifactory.jfrt_http_connections_pending_%_total) as 'Pending', average(jfrog.artifactory.jfrt_http_connections_available_%_total) as 'Available' TIMESERIES"
               }
             ],
             "platformOptions": {