galaio
galaio
> 充血模型不等于一定要把状态加载到内存中去操作，重点在于把业务规则封装到对象中 > 非要加载到内存中去操作，是人为制造问题然后又来提解决方案 > 做DDD/MSA应该保持无状态，整体架构是很简单清晰的 同意，在于行为抽象，具体持久化和防并发完全可以依靠于db。
图挂了。。。楼主有空补一下么？感谢
> Great you found the fix! but we need to follow the procedure from here: https://github.com/paradigmxyz/reth/tree/main/crates/storage/libmdbx-rs (I think it trims down some files) Hi @rakita , I reproduce libmdbx code...
> I would like to ask one more question, we now have 3 flags (history.state, history.transactions, history.blocks) to clear historical data, what data do we still have that is not...
> And I'd like to point out that we must avoid a situation where history.transactions > history.blocks. In such a case we will not be able to do indexTransactions/unindexTransactions, because...
Hi the log shows the data is broken. Could you provide any start/stop logs? or can you try to resync from the latest [snapshot](https://github.com/bnb-chain/bsc-snapshots)?
Hi, how's it going now? Is there anything else I can help you with?
Hi, why not increase txpool slot size to buffer more txs? what is the difference between them?