This is an automated email from the ASF dual-hosted git repository.
wlo pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/gobblin.git
The following commit(s) were added to refs/heads/master by this push:
new 5d1461f43 [GOBBLIN-1750] Add schemas for observability events in GaaS
(#3610)
5d1461f43 is described below
commit 5d1461f43d181b18675b52a7de7c411346b867cd
Author: William Lo <[email protected]>
AuthorDate: Tue Jan 3 11:11:39 2023 -0800
[GOBBLIN-1750] Add schemas for observability events in GaaS (#3610)
* Add schemas for observability events in GaaS
* Address reviews
* Address reviews
* Clean up schema, address review for GaaSObservabilityEvent
* Clarify default types, add failure types
* Fix schema type array
* Modify proxy user field to be user identification
* Address final review
* Rename userIdentity to executionUserUrn
---
.../avro/GaaSObservabilityEventExperimental.avsc | 167 +++++++++++++++++++++
1 file changed, 167 insertions(+)
diff --git
a/gobblin-metrics-libs/gobblin-metrics-base/src/main/avro/GaaSObservabilityEventExperimental.avsc
b/gobblin-metrics-libs/gobblin-metrics-base/src/main/avro/GaaSObservabilityEventExperimental.avsc
new file mode 100644
index 000000000..47c9be6c9
--- /dev/null
+++
b/gobblin-metrics-libs/gobblin-metrics-base/src/main/avro/GaaSObservabilityEventExperimental.avsc
@@ -0,0 +1,167 @@
+{
+ "type": "record",
+ "name": "GaaSObservabilityEventExperimental",
+ "namespace": "org.apache.gobblin.metrics",
+ "doc": "An experimental format for GaaS to emit events during and after a
job is executed.",
+ "fields": [
+ {
+ "name": "timestamp",
+ "type": "long",
+ "doc": "Time at which event was created in millis"
+ },
+ {
+ "name": "flowGroup",
+ "type": "string",
+ "doc": "Flow group for the GaaS flow",
+ "compliance": "NONE"
+ },
+ {
+ "name": "flowName",
+ "type": "string",
+ "doc": "Flow name for the GaaS flow",
+ "compliance": "NONE"
+ },
+ {
+ "name": "flowExecutionId",
+ "type": "long",
+ "doc": "Flow execution id for the GaaS flow",
+ "compliance": "NONE"
+ },
+ {
+ "name": "lastFlowModificationTime",
+ "type": "long",
+ "doc": "Timestamp in millis since Epoch when the flow config was last
modified"
+ },
+ {
+ "name": "flowGraphEdgeId",
+ "type": "string",
+ "doc": "Flow edge id, in format <src_node>_<dest_node>_<edge_id>",
+ "compliance": "NONE"
+ },
+ {
+ "name": "jobName",
+ "type": "string",
+ "doc": "The name of the Gobblin job, found in the job template. One edge
can contain multiple jobs",
+ "compliance": "NONE"
+ },
+ {
+ "name": "jobStatus",
+ "type": {
+ "type": "enum",
+ "name": "JobStatus",
+ "symbols": [
+ "SUCCEEDED",
+ "COMPILATION_FAILURE",
+ "SUBMISSION_FAILURE",
+ "EXEUCTION_FAILURE",
+ "CANCELLED"
+ ],
+ "doc": "Final job status for this job in the GaaS flow",
+ "compliance": "NONE"
+ }
+ },
+ {
+ "name": "jobOrchestratedTime",
+ "type": [
+ "null",
+ "long"
+ ],
+ "doc": "Timestamp when the job was successfully sent to the job
executor, null if it was unable to be sent."
+ },
+ {
+ "name": "jobStartTime",
+ "type": "long",
+ "doc": "Start time of the job in millis since Epoch",
+ "compliance": "NONE"
+ },
+ {
+ "name": "jobEndTime",
+ "type": "long",
+ "doc": "Finish time of the job in millis since Epoch",
+ "compliance": "NONE"
+ },
+ {
+ "name": "executionUserUrn",
+ "type": [
+ "null",
+ "string"
+ ],
+ "doc": "User URN (if applicable) that runs the underlying Gobblin job",
+ "compliance": "NONE"
+ },
+ {
+ "name": "executorUrl",
+ "type": [
+ "null",
+ "string"
+ ],
+ "doc": "Link to where the job ran, currently limited to Azkaban, if it
was executed",
+ "compliance": "NONE"
+ },
+ {
+ "name": "executorId",
+ "type": "string",
+ "doc": "The ID of the spec executor that ran or would have ran the job",
+ "compliance": "NONE"
+ },
+ {
+ "name": "issues",
+ "type": [
+ "null",
+ {
+ "type": "array",
+ "items": {
+ "type": "record",
+ "name": "Issue",
+ "doc": "Issue describes a specific unique problem in the job or
application.\n\nIssue can be generated from log entries, health checks, and
other places.",
+ "fields": [
+ {
+ "name": "timestamp",
+ "type": "long",
+ "doc": "Time when the issue occurred"
+ },
+ {
+ "name": "severity",
+ "type": {
+ "type": "enum",
+ "name": "IssueSeverity",
+ "symbols": [
+ "DEBUG",
+ "INFO",
+ "WARN",
+ "ERROR",
+ "FATAL"
+ ]
+ },
+ "doc": "Severity from DEBUG to FATAL"
+ },
+ {
+ "name": "code",
+ "type": "string",
+ "doc": "Unique machine-readable code that identifies a
specific problem.\n\nIt can be used for making programmatic decisions on how to
handle and recover from this issue.\n\nIssues representing the same kind of
problem will have the same code.\n"
+ },
+ {
+ "name": "summary",
+ "type": "string",
+ "doc": "Short, human-readable description of the issue.\n\nIt
should focus on what is the root cause of the problem, and what steps the user
should do to resolve it."
+ },
+ {
+ "name": "details",
+ "type": "string",
+ "doc": "Human-readable issue details that can include
exception stack trace and additional information about the problem."
+ },
+ {
+ "name": "properties",
+ "type": {
+ "type": "map",
+ "values": "string"
+ },
+ "doc": "Additional machine-readable properties of the issue.\n"
+ }
+ ]
+ }
+ }
+ ]
+ }]
+}
+
