Apache PulsarMetricpulsar_storage_write_rate
The total message batches (entries) written to the storage for this namespace (message batches / second).Dimensions:None
Available on:
Datadog (1)
Datadog (1)Interface Metrics (1)
Datadog
Dimensions:None
Knowledge Base (6 documents, 0 chunks)
referenceApache Pulsar Broker | OpsRamp Documentation823 wordsscore: 0.95This is comprehensive reference documentation for monitoring Apache Pulsar Broker using OpsRamp's monitoring agent. It provides detailed specifications for 50+ metrics covering namespace operations, storage, lookups, connections, managed ledger cache performance, and Jetty web server statistics.
documentationPulsar monitoring | Apache SkyWalking541 wordsscore: 0.95This Apache SkyWalking documentation page describes how to monitor Apache Pulsar clusters using OpenTelemetry Collector to scrape Prometheus metrics and send them to SkyWalking OAP. It provides comprehensive tables of supported metrics for both cluster-level and node-level monitoring, including message rates, throughput, storage metrics, connections, and JVM metrics.
referencePulsar Metrics | Apache Pulsar4304 wordsscore: 1Official Apache Pulsar metrics reference documentation that comprehensively lists all Prometheus-format metrics exposed by Pulsar components including ZooKeeper, BookKeeper, brokers, functions, proxy, and SQL workers. Provides detailed descriptions of metric types (counter, gauge, histogram, summary), metric names, their purposes, and available labels.
guideHow to Design Pulsar Topics and Namespaces2962 wordsscore: 0.65This guide covers the design and organization of Apache Pulsar topics, namespaces, and tenants, explaining the hierarchical structure and how to create and configure these components. It includes code examples for producers, namespace management, and discusses partitioned vs non-partitioned topics with best practices for organizing messaging topologies.
troubleshooting[I] [Bug] With small entry sizes and high throughput, it's necessary to increase dispatcherMaxReadBatchSize and dispatcherMaxReadSizeBytes to utilize CPU on the broker [pulsar]438 wordsscore: 0.72This GitHub issue discusses a performance bug in Apache Pulsar where small entry sizes with high throughput require tuning dispatcherMaxReadBatchSize and dispatcherMaxReadSizeBytes configuration parameters to properly utilize CPU on the broker. The issue demonstrates that default settings limit consumption to ~11000 msgs/s while production can exceed 350000 msgs/s with 128-byte entries.
referencePulsar stats | Apache Pulsar2034 wordsscore: 0.95Official Apache Pulsar documentation detailing comprehensive statistics available for topics, producers, subscriptions, and consumers. This reference covers all key metrics that can be retrieved via the Pulsar stats API, including message rates, throughput, backlog metrics, and storage statistics.
Related Insights (1)
Storage Write Latency Spikes Indicate BookKeeper Bottleneckcritical
High storage write latency (>1s) signals that BookKeeper ledgers cannot persist messages fast enough, creating a bottleneck that cascades to producer publish latency and overall throughput degradation.
▸