show me your code

> strtod 不是 JSON 语法合法性的依据。 > 请参考 JSON 对 number 的语法定义。 这个我看了您的专栏，了解过了。但是我觉得lept_parse_number现在针对处理0123这种数字的处理不太友好，strtod()会 eat了0123四个字符,然后设置了type=NUMBER, 但是我们的cursor变量却只在p=='0'中++自增了1，导致处理的实际位置和游标位置不对等，目前parse_number是能成功解析0123，但是实际解析到了0，但是n=123, 最后回到parse_value（）里检测到1返回了lept_parse_root_not_sigular. 我认为lept_parse_number()就应该想办法对这种不符合json标准的token返回invalid value, 目前我尝试优化这一问题

> 不严格的来讲，可以粗略认为db_write_buffer_size是WAL的上限，write_buffer_size为下限（在未手动设置max_wal_size和flush cf的前提下）。大多数情况下，每个cf的数据量和负载是不一样的，所以同时写满的概率极低。拿咱们的list来说，一个为meta cf，一个为data cf，显然data cf的数据量和负载更大，更容易写满（触发flush，切换WAL）。 您好 想咨询下 我看rocksdb每个cf是有独立的memtable， 但是多个cf共用wal 还是以lists为例，dataCF和metaCF 共用wal, 这种情况下 dataCF应该很容易触发memtable-flush的 但是metaCF却不一定， 这会不会因为MetaCF改动小很久才flush 导致wal迟迟无法删除。 我理解是必须dataCF的memtable和metaCF的memtable都flush了 相关的wal才能被删除的

> i 'm trying my best~

@ystaticy Hi~ Why did this PR add is_bottomost_level limitations, can you explain your original intention to me ？ the change: ``` if !raw_value.is_valid(self.current_ts) { self.raw_handle_delete(); } ``` to ``` if...

I also had this problem， hope you pr helpful

any progress ? i also meet this segfault in v6.29.5, cpp version

@tonyxuqqi @Connor1996 May I ask, what are the possible reasons for high apply wait? I have a TikV cluster here, and the applyWaitDuration P99 can reach 3-5 seconds, but the...

@LykxSassinator In my scenario, apply is fast, but apply_wait is high. it think that apply_wait be the time it stays in the queue? Shouldn't it involve the Rocksdb Mutex and...

Here is my personal analysis: Although PD scheduling (merge / split) is suspended before import, tikv will still trigger split check and split region by itself The importer only obtains...

Which version fix this ? my redisson verson is 2.13.2 When I cyclically switched the master of the Redis cluster, the Redis client seemed to be working normally without any...