databuild/databuild/metric_templates.rs

523 lines
No EOL
20 KiB
Rust

use crate::{JobLogEntry, job_log_entry, WrapperJobEvent};
use std::collections::HashMap;
/// Template for metric extraction from job events
#[derive(Debug, Clone)]
pub struct MetricTemplate {
pub name: String,
pub help: String,
pub metric_type: MetricType,
pub extractor: MetricExtractor,
pub labels: Vec<String>, // Static label names for this metric
}
/// Prometheus metric types
#[derive(Debug, Clone)]
pub enum MetricType {
Counter,
Gauge,
Histogram,
Summary,
}
/// Strategy for extracting metric values from job events
#[derive(Debug, Clone)]
pub enum MetricExtractor {
/// Extract from job event metadata by key
EventMetadata {
event_type: String,
metadata_key: String,
/// Optional conversion function name for non-numeric values
converter: Option<MetricConverter>,
},
/// Count occurrences of specific event types
EventCount {
event_type: String,
},
/// Extract job duration from start/end events
JobDuration,
/// Extract peak memory from job summary
PeakMemory,
/// Extract total CPU time from job summary
TotalCpuTime,
/// Extract exit code from job events
ExitCode,
}
/// Converters for non-numeric metadata values
#[derive(Debug, Clone)]
pub enum MetricConverter {
/// Convert boolean strings to 0/1
BoolToFloat,
/// Convert status strings to numeric codes
StatusToCode(HashMap<String, f64>),
/// Parse duration strings like "123ms" to seconds
DurationToSeconds,
}
/// Result of metric extraction
#[derive(Debug)]
pub struct ExtractedMetric {
pub name: String,
pub value: f64,
pub labels: HashMap<String, String>,
pub help: String,
pub metric_type: MetricType,
}
impl MetricTemplate {
/// Extract a metric from a job log entry if applicable
pub fn extract(&self, entry: &JobLogEntry) -> Option<ExtractedMetric> {
let value = match &self.extractor {
MetricExtractor::EventMetadata { event_type, metadata_key, converter } => {
if let Some(job_log_entry::Content::JobEvent(event)) = &entry.content {
if event.event_type == *event_type {
if let Some(raw_value) = event.metadata.get(metadata_key) {
self.convert_value(raw_value, converter)?
} else {
return None;
}
} else {
return None;
}
} else {
return None;
}
},
MetricExtractor::EventCount { event_type } => {
if let Some(job_log_entry::Content::JobEvent(event)) = &entry.content {
if event.event_type == *event_type {
1.0
} else {
return None;
}
} else {
return None;
}
},
MetricExtractor::JobDuration => {
if let Some(job_log_entry::Content::JobEvent(event)) = &entry.content {
if event.event_type == "job_summary" {
if let Some(runtime_str) = event.metadata.get("runtime_ms") {
runtime_str.parse::<f64>().ok()? / 1000.0 // Convert to seconds
} else {
return None;
}
} else {
return None;
}
} else {
return None;
}
},
MetricExtractor::PeakMemory => {
if let Some(job_log_entry::Content::JobEvent(event)) = &entry.content {
if event.event_type == "job_summary" {
if let Some(memory_str) = event.metadata.get("peak_memory_mb") {
memory_str.parse::<f64>().ok()?
} else {
return None;
}
} else {
return None;
}
} else {
return None;
}
},
MetricExtractor::TotalCpuTime => {
if let Some(job_log_entry::Content::JobEvent(event)) = &entry.content {
if event.event_type == "job_summary" {
if let Some(cpu_str) = event.metadata.get("total_cpu_ms") {
cpu_str.parse::<f64>().ok()? / 1000.0 // Convert to seconds
} else {
return None;
}
} else {
return None;
}
} else {
return None;
}
},
MetricExtractor::ExitCode => {
if let Some(job_log_entry::Content::JobEvent(event)) = &entry.content {
if let Some(exit_code) = event.exit_code {
exit_code as f64
} else {
return None;
}
} else {
return None;
}
},
};
// Generate labels for this metric
let mut labels = HashMap::new();
// Always include job_id as a label (but this is excluded by default for cardinality safety)
labels.insert("job_id".to_string(), entry.job_id.clone());
// Extract job label from manifest if available - this is the low-cardinality identifier
if let Some(job_log_entry::Content::Manifest(manifest)) = &entry.content {
if let Some(task) = &manifest.task {
if let Some(job) = &task.job {
labels.insert("job_label".to_string(), job.label.clone());
}
}
}
// Add job status and job label if available from job events
if let Some(job_log_entry::Content::JobEvent(event)) = &entry.content {
if let Some(job_status) = &event.job_status {
labels.insert("job_status".to_string(), job_status.clone());
}
if let Some(job_label) = &event.job_label {
labels.insert("job_label".to_string(), job_label.clone());
}
}
Some(ExtractedMetric {
name: self.name.clone(),
value,
labels,
help: self.help.clone(),
metric_type: self.metric_type.clone(),
})
}
fn convert_value(&self, raw_value: &str, converter: &Option<MetricConverter>) -> Option<f64> {
match converter {
None => raw_value.parse().ok(),
Some(MetricConverter::BoolToFloat) => {
match raw_value.to_lowercase().as_str() {
"true" | "1" | "yes" => Some(1.0),
"false" | "0" | "no" => Some(0.0),
_ => None,
}
},
Some(MetricConverter::StatusToCode(mapping)) => {
mapping.get(raw_value).copied()
},
Some(MetricConverter::DurationToSeconds) => {
// Parse formats like "123ms", "45s", "2.5m"
if raw_value.ends_with("ms") {
raw_value.trim_end_matches("ms").parse::<f64>().ok().map(|v| v / 1000.0)
} else if raw_value.ends_with("s") {
raw_value.trim_end_matches("s").parse::<f64>().ok()
} else if raw_value.ends_with("m") {
raw_value.trim_end_matches("m").parse::<f64>().ok().map(|v| v * 60.0)
} else {
raw_value.parse::<f64>().ok()
}
},
}
}
}
/// Get standard DataBuild metric templates
pub fn get_standard_metrics() -> Vec<MetricTemplate> {
vec![
// Job execution metrics
MetricTemplate {
name: "databuild_job_duration_seconds".to_string(),
help: "Duration of job execution in seconds".to_string(),
metric_type: MetricType::Histogram,
extractor: MetricExtractor::JobDuration,
labels: vec!["job_label".to_string()],
},
MetricTemplate {
name: "databuild_job_peak_memory_mb".to_string(),
help: "Peak memory usage of job in megabytes".to_string(),
metric_type: MetricType::Gauge,
extractor: MetricExtractor::PeakMemory,
labels: vec!["job_label".to_string()],
},
MetricTemplate {
name: "databuild_job_cpu_time_seconds".to_string(),
help: "Total CPU time consumed by job in seconds".to_string(),
metric_type: MetricType::Counter,
extractor: MetricExtractor::TotalCpuTime,
labels: vec!["job_label".to_string()],
},
MetricTemplate {
name: "databuild_job_exit_code".to_string(),
help: "Exit code of job execution".to_string(),
metric_type: MetricType::Gauge,
extractor: MetricExtractor::ExitCode,
labels: vec!["job_label".to_string(), "job_status".to_string()],
},
// Job event counters
MetricTemplate {
name: "databuild_job_events_total".to_string(),
help: "Total number of job events".to_string(),
metric_type: MetricType::Counter,
extractor: MetricExtractor::EventCount { event_type: "task_success".to_string() },
labels: vec!["job_label".to_string()],
},
MetricTemplate {
name: "databuild_job_failures_total".to_string(),
help: "Total number of job failures".to_string(),
metric_type: MetricType::Counter,
extractor: MetricExtractor::EventCount { event_type: "task_failed".to_string() },
labels: vec!["job_label".to_string()],
},
MetricTemplate {
name: "databuild_heartbeats_total".to_string(),
help: "Total number of heartbeat events".to_string(),
metric_type: MetricType::Counter,
extractor: MetricExtractor::EventCount { event_type: "heartbeat".to_string() },
labels: vec!["job_label".to_string()],
},
]
}
#[cfg(test)]
mod tests {
use super::*;
use crate::{PartitionRef, log_message, LogMessage};
fn create_test_job_summary_entry(job_id: &str, runtime_ms: &str, memory_mb: &str, cpu_ms: &str, exit_code: i32) -> JobLogEntry {
let mut metadata = HashMap::new();
metadata.insert("runtime_ms".to_string(), runtime_ms.to_string());
metadata.insert("peak_memory_mb".to_string(), memory_mb.to_string());
metadata.insert("total_cpu_ms".to_string(), cpu_ms.to_string());
metadata.insert("exit_code".to_string(), exit_code.to_string());
JobLogEntry {
timestamp: "1234567890".to_string(),
job_id: job_id.to_string(),
outputs: vec![PartitionRef { r#str: "reviews/date=2025-01-27".to_string() }],
sequence_number: 1,
content: Some(job_log_entry::Content::JobEvent(WrapperJobEvent {
event_type: "job_summary".to_string(),
job_status: Some("JOB_COMPLETED".to_string()),
exit_code: Some(exit_code),
metadata,
job_label: None,
})),
}
}
fn create_test_task_success_entry(job_id: &str) -> JobLogEntry {
JobLogEntry {
timestamp: "1234567890".to_string(),
job_id: job_id.to_string(),
outputs: vec![PartitionRef { r#str: "podcasts/date=2025-01-27".to_string() }],
sequence_number: 2,
content: Some(job_log_entry::Content::JobEvent(WrapperJobEvent {
event_type: "task_success".to_string(),
job_status: Some("JOB_COMPLETED".to_string()),
exit_code: Some(0),
metadata: HashMap::new(),
job_label: None,
})),
}
}
#[test]
fn test_job_duration_extraction() {
let template = MetricTemplate {
name: "test_duration".to_string(),
help: "Test duration".to_string(),
metric_type: MetricType::Histogram,
extractor: MetricExtractor::JobDuration,
labels: vec![],
};
let entry = create_test_job_summary_entry("test-job", "2500", "64.5", "1200", 0);
let metric = template.extract(&entry).unwrap();
assert_eq!(metric.name, "test_duration");
assert_eq!(metric.value, 2.5); // 2500ms -> 2.5s
assert_eq!(metric.labels.get("job_id").unwrap(), "test-job");
// Note: job_label would only be available from manifest entries, not job_summary
}
#[test]
fn test_memory_extraction() {
let template = MetricTemplate {
name: "test_memory".to_string(),
help: "Test memory".to_string(),
metric_type: MetricType::Gauge,
extractor: MetricExtractor::PeakMemory,
labels: vec![],
};
let entry = create_test_job_summary_entry("test-job", "2500", "128.75", "1200", 0);
let metric = template.extract(&entry).unwrap();
assert_eq!(metric.value, 128.75);
}
#[test]
fn test_cpu_time_extraction() {
let template = MetricTemplate {
name: "test_cpu".to_string(),
help: "Test CPU".to_string(),
metric_type: MetricType::Counter,
extractor: MetricExtractor::TotalCpuTime,
labels: vec![],
};
let entry = create_test_job_summary_entry("test-job", "2500", "64.5", "1500", 0);
let metric = template.extract(&entry).unwrap();
assert_eq!(metric.value, 1.5); // 1500ms -> 1.5s
}
#[test]
fn test_exit_code_extraction() {
let template = MetricTemplate {
name: "test_exit_code".to_string(),
help: "Test exit code".to_string(),
metric_type: MetricType::Gauge,
extractor: MetricExtractor::ExitCode,
labels: vec![],
};
let entry = create_test_job_summary_entry("test-job", "2500", "64.5", "1200", 42);
let metric = template.extract(&entry).unwrap();
assert_eq!(metric.value, 42.0);
assert_eq!(metric.labels.get("job_status").unwrap(), "JOB_COMPLETED");
}
#[test]
fn test_event_count_extraction() {
let template = MetricTemplate {
name: "test_success_count".to_string(),
help: "Test success count".to_string(),
metric_type: MetricType::Counter,
extractor: MetricExtractor::EventCount { event_type: "task_success".to_string() },
labels: vec![],
};
let entry = create_test_task_success_entry("test-job");
let metric = template.extract(&entry).unwrap();
assert_eq!(metric.value, 1.0);
// Note: job_label would only be available from manifest entries, not job events
}
#[test]
fn test_event_metadata_extraction() {
let template = MetricTemplate {
name: "test_runtime".to_string(),
help: "Test runtime from metadata".to_string(),
metric_type: MetricType::Gauge,
extractor: MetricExtractor::EventMetadata {
event_type: "job_summary".to_string(),
metadata_key: "runtime_ms".to_string(),
converter: None,
},
labels: vec![],
};
let entry = create_test_job_summary_entry("test-job", "3000", "64.5", "1200", 0);
let metric = template.extract(&entry).unwrap();
assert_eq!(metric.value, 3000.0);
}
#[test]
fn test_bool_converter() {
let template = MetricTemplate {
name: "test_bool".to_string(),
help: "Test bool".to_string(),
metric_type: MetricType::Gauge,
extractor: MetricExtractor::EventMetadata {
event_type: "test_event".to_string(),
metadata_key: "success".to_string(),
converter: Some(MetricConverter::BoolToFloat),
},
labels: vec![],
};
assert_eq!(template.convert_value("true", &Some(MetricConverter::BoolToFloat)), Some(1.0));
assert_eq!(template.convert_value("false", &Some(MetricConverter::BoolToFloat)), Some(0.0));
assert_eq!(template.convert_value("yes", &Some(MetricConverter::BoolToFloat)), Some(1.0));
assert_eq!(template.convert_value("no", &Some(MetricConverter::BoolToFloat)), Some(0.0));
assert_eq!(template.convert_value("invalid", &Some(MetricConverter::BoolToFloat)), None);
}
#[test]
fn test_duration_converter() {
let template = MetricTemplate {
name: "test_duration".to_string(),
help: "Test duration".to_string(),
metric_type: MetricType::Gauge,
extractor: MetricExtractor::EventMetadata {
event_type: "test_event".to_string(),
metadata_key: "duration".to_string(),
converter: Some(MetricConverter::DurationToSeconds),
},
labels: vec![],
};
assert_eq!(template.convert_value("1000ms", &Some(MetricConverter::DurationToSeconds)), Some(1.0));
assert_eq!(template.convert_value("5s", &Some(MetricConverter::DurationToSeconds)), Some(5.0));
assert_eq!(template.convert_value("2.5m", &Some(MetricConverter::DurationToSeconds)), Some(150.0));
assert_eq!(template.convert_value("42", &Some(MetricConverter::DurationToSeconds)), Some(42.0));
}
#[test]
fn test_standard_metrics() {
let metrics = get_standard_metrics();
assert!(!metrics.is_empty());
// Verify we have the key metrics
let metric_names: Vec<&String> = metrics.iter().map(|m| &m.name).collect();
assert!(metric_names.contains(&&"databuild_job_duration_seconds".to_string()));
assert!(metric_names.contains(&&"databuild_job_peak_memory_mb".to_string()));
assert!(metric_names.contains(&&"databuild_job_cpu_time_seconds".to_string()));
assert!(metric_names.contains(&&"databuild_job_failures_total".to_string()));
}
#[test]
fn test_no_extraction_for_wrong_event_type() {
let template = MetricTemplate {
name: "test_metric".to_string(),
help: "Test".to_string(),
metric_type: MetricType::Counter,
extractor: MetricExtractor::EventCount { event_type: "task_failed".to_string() },
labels: vec![],
};
let entry = create_test_task_success_entry("test-job"); // This is task_success, not task_failed
let result = template.extract(&entry);
assert!(result.is_none());
}
#[test]
fn test_no_extraction_for_log_entries() {
let template = MetricTemplate {
name: "test_metric".to_string(),
help: "Test".to_string(),
metric_type: MetricType::Counter,
extractor: MetricExtractor::JobDuration,
labels: vec![],
};
// Create a log entry instead of job event
let entry = JobLogEntry {
timestamp: "1234567890".to_string(),
job_id: "test-job".to_string(),
outputs: vec![PartitionRef { r#str: "test/partition".to_string() }],
sequence_number: 1,
content: Some(job_log_entry::Content::Log(LogMessage {
level: log_message::LogLevel::Info as i32,
message: "Test log message".to_string(),
fields: HashMap::new(),
})),
};
let result = template.extract(&entry);
assert!(result.is_none());
}
}