Skip to content

Commit

Permalink
Merge branch 'main' into NR-174994
Browse files Browse the repository at this point in the history
  • Loading branch information
RamanaReddy8801 authored Nov 2, 2023
2 parents fee57b9 + aee3128 commit a03a091
Show file tree
Hide file tree
Showing 33 changed files with 623 additions and 27 deletions.
1 change: 1 addition & 0 deletions .github/CODEOWNERS
Validating CODEOWNERS rules …
Original file line number Diff line number Diff line change
Expand Up @@ -14,3 +14,4 @@ LICENSE @newrelic/developer-enablement

# product/content ownership
/dashboards/ @seemantk
/quickstarts/ @seemantk @rahulbasu-nr
Original file line number Diff line number Diff line change
@@ -0,0 +1,27 @@
name: High CPU Utilization

description: |+
This alert is triggered when the CPU Utilization is above 90%.
type: STATIC
nrql:
query: "SELECT average(`aws.dms.CPUUtilization`) as 'Query' FROM Metric"

# Function used to aggregate the NRQL query value(s) for comparison to the terms.threshold (Default: SINGLE_VALUE)
valueFunction: SINGLE_VALUE

# List of Critical and Warning thresholds for the condition
terms:
- priority: CRITICAL
# Operator used to compare against the threshold.
operator: ABOVE
# Value in % that triggers a violation
threshold: 90
# Time in seconds; 120 - 3600
thresholdDuration: 300
# How many data points must be in violation for the duration
thresholdOccurrences: ALL

# Duration after which a violation automatically closes
# Time in seconds; 300 - 2592000 (Default: 86400 [1 day])
violationTimeLimitSeconds: 86400
Original file line number Diff line number Diff line change
@@ -0,0 +1,37 @@
name: Low Freeable Memory

description: |+
This alert occurs when Freeable Memory go below 100 Bytes for 5 minutes
type: STATIC

nrql:
query: "SELECT average(aws.dms.FreeableMemory) from Metric"

# Function used to aggregate the NRQL query value(s) for comparison to the terms.threshold (Default: SINGLE_VALUE)
valueFunction: SINGLE_VALUE

# List of Critical and Warning thresholds for the condition
terms:
- priority: CRITICAL
# Operator used to compare against the threshold.
operator: BELOW
# Value in Bytes that triggers violation
threshold: 100
# Time in seconds; 120 - 3600
thresholdDuration: 300
# How many data points must be in violation for the duration
thresholdOccurrences: ALL

# Adding a Warning threshold is optional
- priority: WARNING
operator: BELOW
# Value in Bytes that triggers violation
threshold: 95
thresholdDuration: 300
thresholdOccurrences: ALL

# Duration after which a violation automatically closes
# Time in seconds; 300 - 2592000 (Default: 86400 [1 day])
violationTimeLimitSeconds: 86400

4 changes: 2 additions & 2 deletions alert-policies/amazon-sagemaker/HighModelInvocationErrors.yml
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ description: |+
type: STATIC
nrql:
query: "SELECT count(`aws.sagemaker.InvocationModelErrors`) as 'Query' FROM Metric"
query: "SELECT sum(`aws.sagemaker.InvocationModelErrors`) as 'Query' FROM Metric"

# Function used to aggregate the NRQL query value(s) for comparison to the terms.threshold (Default: SINGLE_VALUE)
valueFunction: SINGLE_VALUE
Expand All @@ -24,4 +24,4 @@ terms:

# Duration after which a violation automatically closes
# Time in seconds; 300 - 2592000 (Default: 86400 [1 day])
violationTimeLimitSeconds: 86400
violationTimeLimitSeconds: 86400
Loading

0 comments on commit a03a091

Please sign in to comment.