tendis短期大量数据入库后，触发memtable和merge 的一些现象
Open
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 3.2k
- Forks
- 343
- Avg merge
- 2h 13m
- Merged PRs (30d)
- 4
Description
Description
背景：压测工具压了大批数据，memtier_benchmark -t1 -c1 -s -p --cluster-mode --ratio=1:1 -n5000 -d 512000000 (数据量io的瓶颈)，在其后，发现集群整体性能下降， 普通的测试也较之前很差的结果，是因为数据量大memtable的不停的切到固定，不停的触发合并compact所致吗？
这是普通测试的结果
这种情况下对线上可能有隐患，如何防止呢？还是我的使用有误
感谢大佬解答
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reproducing the reported workload with memtier_benchmark and compare cluster performance before and after the large import, using the attached benchmark results as context. Inspect the memtable rotation and merge/compact behavior; done means determining whether compaction explains the degradation and documenting a supported way to prevent or mitigate the production risk.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp
- Domain
- databases
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100