Haonan

Results 127 comments of Haonan

Hi, would you mind doing some performance tests?

> Actually... What I mean is do you have some tests result of this PR? 😆

SNAPPY ``` 2022-07-28 18:26:02,294 [pool-6-IoTDB-Flush-1] INFO o.a.i.d.e.f.MemTableFlushTask:95 - The memTable size of SG root.test-0 is 1124046000, the avg series points num in chunk is 2310, total timeseries number is 25000...

> > SNAPPY > > ``` > > 2022-07-28 18:26:02,294 [pool-6-IoTDB-Flush-1] INFO o.a.i.d.e.f.MemTableFlushTask:95 - The memTable size of SG root.test-0 is 1124046000, the avg series points num in chunk is...

Hi, this is a known issue, we will solve it in v0.14. 您好,这是一个已知问题,我们将会在0.14版本里解决

Hi @zhouzhiy, it seems that it caused by memtable is too small and flushed too much times. You can try changing `avg_series_point_number_threshold` from `10000` to `1000000` to improve it.

可以看看datanode的error日志里有没有其他信息

文件存储用local会有这个问题吗? 另外,0.13 版本的分布式版本已经不维护了,可以关注一下master分支的新分布式。