ashb commented on a change in pull request #8:
URL: https://github.com/apache/airflow-ci-infra/pull/8#discussion_r594209516
##########
File path: cloud-init.yml
##########
@@ -242,23 +251,50 @@ write_files:
timeout_ms = 250
[transforms.grok-runner-logs]
- type = "grok_parser"
+ type = "remap"
inputs=["runner-logs"]
- pattern = "(?m)\\[%{TIMESTAMP_ISO8601:timestamp} %{LOGLEVEL:level}
%{NOTSPACE:logger}\\] %{GREEDYDATA:message}"
- types.timestamp = "timestamp|%F %TZ"
+ source = '''
+ structured, err = parse_grok(.message,
"(?m)\\[%{TIMESTAMP_ISO8601:timestamp} %{LOGLEVEL:level} %{NOTSPACE:logger}\\]
%{GREEDYDATA:message}")
+
+ if err != null {
+ .err = err
+ } else {
+ . = merge(., structured)
+ }
+ '''
+ [transforms.filter-runner-logs]
+ type = "filter"
+ inputs = ['grok-runner-logs']
+ condition.type = "remap"
+ condition.source = '''
+ if .logger == "JobServerQueue" {
+ !match!(.message, r'Try to append \d+ batches web console lines
for record')
+ } else if .logger == "HostContext" {
+ !starts_with!(.message, "Well known directory")
+ } else {
+ true
+ }
+ '''
+
+ [sources.job-logs]
+ type = "file"
+ include = ["/home/runner/actions-runner/_diag/pages/*.log"]
- [transforms.without_systemd_fields]
- type = "remove_fields"
- inputs = ["logs"]
- fields = ["_CAP_EFFECTIVE", "_SYSTEMD_SLICE", "_SYSTEMD_CGROUP",
- "_SYSTEMD_INVOCATION_ID", "_SELINUX_CONTEXT", "_COMM", "_BOOT_ID",
- "_MACHINE_ID", "_STREAM_ID", "_PID", "_GID", "_UID","_TRANSPORT",
- "__MONOTONIC_TIMESTAMP", "SYSLOG_IDENTIFIER", "PRIORITY",
- "source_type"]
+ [transforms.grok-job-logs]
+ type = "remap"
+ inputs = ["job-logs"]
+ source = '''
+ structured, err = parse_grok(.message,
"%{TIMESTAMP_ISO8601:timestamp} %{GREEDYDATA:message}")
+
+ if err == null {
+ . = merge(., structured)
+ .type = "job-output"
Review comment:
This adds a field to the log messages that we can then filter by to get
log output.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
