MegaETH has decided to build its own RPC stack, and expects downtime during the testing period

News on March 8, MegaETH co-founder Lei Yang posted on social media that yesterday's RPC downtime incident exposed an interesting edge case. Debugging the invocation of RPC methods caused the server to allocate a large amount of memory for super-long strings, eventually leading to memory exhaustion. The MegaETH team decided to build their own RPC stack in order to apply multiple optimizations on it and improve performance. From a performance perspective, the results are good, but the cost is that the team needs to handle infrastructure operations themselves. It is expected that there will be more downtime incidents in the future and more post-incident analysis reports will also be released. They hope these reports can spark interesting discussions. He encourages everyone to provide more edge cases for testing now rather than encountering problems several months later.