According to Foresight News, MegaETH co-founder Lei Yang recently addressed an RPC outage that revealed an intriguing edge case. The incident occurred when debugging RPC method calls led to the server allocating excessive memory for an overly long string, ultimately resulting in memory exhaustion. In response, the MegaETH team has decided to build their own RPC stack to implement various optimizations aimed at enhancing performance. While this approach has yielded positive performance results, it requires the team to manage infrastructure maintenance independently.
Yang anticipates more outages in the future and plans to release additional post-mortem reports, hoping these will spark engaging discussions. He encourages the community to share more edge cases for testing now, rather than encountering issues months later.