4.5. Performance and Scalability

4.5.1. [Critical] Performance degradation with durable writer history

In release 7.0.0, a significant performance degradation was introduced in DataWriter operations when the DataWriter was configured to use durable writer history.

This issue was caused by missing database indexes that should have been created to optimize performance. Without these indexes, certain database operations became substantially slower, affecting overall DataWriter throughput.

[RTI Issue ID CORE-16122]

4.5.2. [Critical] Performance degradation with Durable Writer History in write-intensive scenarios

In release 7.3.1, the throughput of write-intensive scenarios for a DataWriter configured with Durable Writer History was lower than in previous releases. This regression was caused by performance optimizations introduced in that version to improve read-intensive scenarios (for example, when handling late joiners)—see CORE-16122 above.

The fix for this issue improves the overall performance of write-intensive workloads. However, some degradation may still remain compared to earlier releases. If this issue affects your application, please contact support@rti.com for further assistance.

[RTI Issue ID CORE-16211]

4.5.3. [Major] Inefficient repair of fragmented samples caused performance degradation during large data transmission

When reliable, DDS-fragmented data needed to be repaired, only fragments from a single sample were requested per heartbeat. This led to significant performance degradation and slow recovery when transmitting large data, as multiple heartbeat round trips were required to repair multiple samples.

This issue has been resolved by allowing all missing fragments from all announced samples to be requested at the same time, greatly improving repair efficiency and large data transmission throughput in lossy network environments.

[RTI Issue ID CORE-14751]