Connor
Connor
## Development Task On cloud env, TiKV is equipped with AWS EBS storage for a single node which provides the durability of 99.99%. Moreover, TiKV organizes 3 Raft replicas on...
## Description Before, we added an [io snooper supported by BPF](https://github.com/tikv/tikv/pull/9153) to get the actual read flow categorized by threads. With the limitation of BPF that needs sudo permission, it...
Signed-off-by: Connor1996 ### What is changed and how it works? Issue Number: Ref https://github.com/tikv/tikv/issues/12876 What's Changed: ```commit-message Introduce witness peer ``` ### Related changes - PR to update `pingcap/docs`/`pingcap/docs-cn`: -...
When doing a long scan with 1000 kvs on master, find it wastes too much CPU time on blob cache mutex and affect scan performance a lot.  But for...
When blob zstd dictionary compression is enabled, all the values will be buffered and replayed after the compression dictionary is finalized. So if there are multiple concurrent flushes and compactions,...
When calling `DestroyColumnFamilyHandle` we may remove related blob storage directly. But if there are multiples column family handles, Titan removes related blob storage on the first time to call `DestroyColumnFamilyHandle`,...
By `SetOptions`, we should able to change following configs dynamically - [ ] disable-gc - [ ] min-blob-size - [ ] min-gc-batch-size - [ ] max-gc-batch-size - [ ] discardable-ratio...
 Have tried to downgrade Titan to vanilla RocksDB, found there are some blob files still with 0 discardable ratio so that they can't be cleaned by GC. Whereas after...
Found by https://asktug.com/t/topic/37263 But the log is missing, Titan can not restart due to blob file has been deleted twice
In this PR https://github.com/facebook/rocksdb/pull/6342, it fixes the issue that OnFlushCompleted and OnCompactionCompleted are called out of order which is the root cause of what #172 fixes. After it is merged...