diff --git a/content/integrate/redis-data-integration/observability.md b/content/integrate/redis-data-integration/observability.md index ebb8368bde..5235950c5f 100644 --- a/content/integrate/redis-data-integration/observability.md +++ b/content/integrate/redis-data-integration/observability.md @@ -113,6 +113,25 @@ RDI reports with their descriptions. | `monitor_time_elapsed_created` | Gauge | Timestamp when the monitor time elapsed counter was created | Informational - no alerting needed | | `rdi_incoming_entries` | Gauge | Count of incoming events by `data_source` and `operation` type (pending, inserted, updated, deleted, filtered, rejected) | Informational - monitor for trends, alert only on "rejected" > 0 | | `rdi_stream_event_latency_ms` | Gauge | Latency in milliseconds of the oldest event in each data stream, labeled by `data_source` | Informational - monitor based on business SLA requirements | +| **Processor Performance Total Metrics** | | | | +| `rdi_processed_batches_total` | Counter | Total number of processed batches | Informational - use for data ingestion and load tracking | +| `rdi_processor_batch_size_total` | Counter | Total batch size across all processed batches | Informational - use for throughput analysis | +| `rdi_processor_read_time_ms_total` | Counter | Total read time in milliseconds across all batches | Informational - use for performance analysis | +| `rdi_processor_transform_time_ms_total` | Counter | Total transform time in milliseconds across all batches | Informational - use for performance analysis | +| `rdi_processor_write_time_ms_total` | Counter | Total write time in milliseconds across all batches | Informational - use for performance analysis | +| `rdi_processor_process_time_ms_total` | Counter | Total process time in milliseconds across all batches | Informational - use for performance analysis | +| `rdi_processor_ack_time_ms_total` | Counter | Total acknowledgment time in milliseconds across all batches | Informational - use for performance analysis | +| `rdi_processor_total_time_ms_total` | Counter | Sum of the total `read_time`, `process_time` and `ack_time` values in milliseconds across all batches | Informational - use for performance analysis | +| `rdi_processor_rec_per_sec_total` | Gauge | Total records per second across all batches | Informational - use for throughput analysis | +| **Processor Performance Last Batch Metrics** | | | | +| `rdi_processor_batch_size_last` | Gauge | Last batch size processed | Informational - use for real-time monitoring | +| `rdi_processor_read_time_ms_last` | Gauge | Last batch read time in milliseconds | Informational - use for real-time performance monitoring | +| `rdi_processor_transform_time_ms_last` | Gauge | Last batch transform time in milliseconds | Informational - use for real-time performance monitoring | +| `rdi_processor_write_time_ms_last` | Gauge | Last batch write time in milliseconds | Informational - use for real-time performance monitoring | +| `rdi_processor_process_time_ms_last` | Gauge | Last batch process time in milliseconds | Informational - use for real-time performance monitoring | +| `rdi_processor_ack_time_ms_last` | Gauge | Last batch acknowledgment time in milliseconds | Informational - use for real-time performance monitoring | +| `rdi_processor_total_time_ms_last` | Gauge | Last batch total time in milliseconds | Informational - use for real-time performance monitoring | +| `rdi_processor_rec_per_sec_last` | Gauge | Last batch records per second | Informational - use for real-time throughput monitoring | {{< note >}} **Additional information about stream processor metrics:** @@ -121,11 +140,14 @@ RDI reports with their descriptions. - Metrics with the `_created` suffix are automatically generated by Prometheus for counters and gauges to track when they were first created. - The `rdi_incoming_entries` metric provides a detailed breakdown for each data source by operation type. - The `rdi_stream_event_latency_ms` metric helps monitor data freshness and processing delays. +- The processor performance metrics are divided into two categories: + - **Total metrics**: Accumulate values across all processed batches for historical analysis + - **Last batch metrics**: Show real-time performance data for the most recently processed batch {{< /note >}} ## Recommended alerting strategy -The alerting strategy described in the sections below focuses on system failures and data integrity issues that require immediate attention. Most ther metrics are informational, so you should monitor them for trends rather than trigger alerts. +The alerting strategy described in the sections below focuses on system failures and data integrity issues that require immediate attention. Most other metrics are informational, so you should monitor them for trends rather than trigger alerts. ### Critical alerts (immediate response required) diff --git a/content/integrate/redis-data-integration/reference/api-reference/openapi.json b/content/integrate/redis-data-integration/reference/api-reference/openapi.json index 6c4808d85e..4dc13a24dd 100644 --- a/content/integrate/redis-data-integration/reference/api-reference/openapi.json +++ b/content/integrate/redis-data-integration/reference/api-reference/openapi.json @@ -4627,6 +4627,22 @@ 10.5 ] }, + "transform_time_avg": { + "type": "number", + "minimum": 0.0, + "title": "Transform Time Avg", + "examples": [ + 2.3 + ] + }, + "write_time_avg": { + "type": "number", + "minimum": 0.0, + "title": "Write Time Avg", + "examples": [ + 4.4 + ] + }, "process_time_avg": { "type": "number", "minimum": 0.0, @@ -4665,6 +4681,8 @@ "total_batches", "batch_size_avg", "read_time_avg", + "transform_time_avg", + "write_time_avg", "process_time_avg", "ack_time_avg", "total_time_avg",