Files
rustfs/.docker/observability/prometheus-rules/rustfs-dashboard.yml
T
houseme 73bde843d6 refactor(s3): consolidate semantic boundaries and remove s3-common (#3012)
* refactor(common): introduce rustfs-data-usage core crate

* refactor(concurrency): migrate workers crate into concurrency

* refactor(crypto): migrate appauth token APIs into crypto

* fix docs urls

* remove unused crate

* refactor(data-usage): switch consumers to rustfs-data-usage

* chore(fmt): apply cargo fmt and lockfile sync

* refactor(common): remove data_usage compatibility re-export

* refactor(capacity): move capacity_scope to object-capacity

* refactor(io-metrics): relocate internode metrics from common

* refactor(common): decouple scanner report from madmin

* chore(fmt): normalize import ordering after pre-commit

* refactor(s3): split s3 types and ops crates

* refactor(s3): centralize event version and safe parsing

* refactor(s3): add op-event compatibility guardrails

* refactor(s3): add runtime op-event mismatch observability

* refactor(s3): extract delete event mapping helper

* refactor(s3): extract put event mapping helper

* refactor(s3): consolidate remaining event semantic helpers

* refactor(s3): add op-event coverage checks and observability alerts

* refactor(s3-ops): consolidate op-event semantic mapping

* refactor(scanner): remove last_minute wrapper module

* refactor(scanner): consolidate duplicated data usage models
2026-05-19 12:50:25 +00:00

54 lines
3.3 KiB
YAML

groups:
- name: rustfs-dashboard
interval: 30s
rules:
- record: rustfs:http_server_requests:rate5m
expr: sum by (job) (rate(rustfs_http_server_requests_total[5m]))
- record: rustfs:http_server_request_duration_seconds:p50_5m
expr: histogram_quantile(0.50, sum by (le, job) (rate(rustfs_http_server_request_duration_seconds_bucket[5m])))
- record: rustfs:http_server_request_duration_seconds:p95_5m
expr: histogram_quantile(0.95, sum by (le, job) (rate(rustfs_http_server_request_duration_seconds_bucket[5m])))
- record: rustfs:http_server_request_duration_seconds:p99_5m
expr: histogram_quantile(0.99, sum by (le, job) (rate(rustfs_http_server_request_duration_seconds_bucket[5m])))
- record: rustfs:http_server_response_body_size_bytes:p50_5m
expr: histogram_quantile(0.50, sum by (le, job) (rate(rustfs_http_server_response_body_size_bytes_bucket[5m])))
- record: rustfs:http_server_response_body_size_bytes:p95_5m
expr: histogram_quantile(0.95, sum by (le, job) (rate(rustfs_http_server_response_body_size_bytes_bucket[5m])))
- record: rustfs:http_server_response_body_size_bytes:p99_5m
expr: histogram_quantile(0.99, sum by (le, job) (rate(rustfs_http_server_response_body_size_bytes_bucket[5m])))
- record: rustfs:log_cleaner_runs:rate15m
expr: sum by (job) (rate(rustfs_log_cleaner_runs_total[15m]))
- record: rustfs:log_cleaner_failure_ratio:rate5m
expr: sum by (job) (rate(rustfs_log_cleaner_run_failures_total[5m])) / clamp_min(sum by (job) (rate(rustfs_log_cleaner_runs_total[5m])), 1e-9)
- record: rustfs:log_cleaner_rotation_failure_ratio:rate5m
expr: sum by (job) (rate(rustfs_log_cleaner_rotation_failures_total[5m])) / clamp_min(sum by (job) (rate(rustfs_log_cleaner_rotation_total[5m])), 1e-9)
- record: rustfs:log_cleaner_rotation_duration_seconds:p95_5m
expr: histogram_quantile(0.95, sum by (le, job) (rate(rustfs_log_cleaner_rotation_duration_seconds_bucket[5m])))
- record: rustfs:log_cleaner_compress_duration_seconds:p95_5m
expr: histogram_quantile(0.95, sum by (le, job) (rate(rustfs_log_cleaner_compress_duration_seconds_bucket[5m])))
- record: rustfs:scanner_objects_scanned:rate5m
expr: sum by (job) (rate(rustfs_scanner_objects_scanned_total[5m]))
- record: rustfs:scanner_directories_scanned:rate5m
expr: sum by (job) (rate(rustfs_scanner_directories_scanned_total[5m]))
- record: rustfs:scanner_buckets_scanned:rate5m
expr: sum by (job) (rate(rustfs_scanner_buckets_scanned_total[5m]))
- record: rustfs:scanner_cycles_success:rate5m
expr: sum by (job) (rate(rustfs_scanner_cycles_total{result="success"}[5m]))
- record: rustfs:log_chain_op_event_mismatch:rate5m
expr: sum by (job) (rate(rustfs_log_chain_op_event_mismatch_total[5m]))
- alert: RustFSLogChainOpEventMismatchDetected
expr: rustfs:log_chain_op_event_mismatch:rate5m > 0
for: 10m
labels:
severity: warning
component: s3-log-chain
annotations:
summary: "RustFS log-chain op/event mismatch detected"
description: "job={{ $labels.job }} has non-zero rustfs_log_chain_op_event_mismatch_total rate for more than 10m. Check s3 op/event mapping changes."