| commit | f561cd63b197e4153ce9771c6628294d11851448 | [log] [tgz] |
|---|---|---|
| author | CooooolFrog <zuliangwanghust@gmail.com> | Mon Oct 16 16:44:47 2023 +0800 |
| committer | GitHub <noreply@github.com> | Mon Oct 16 16:44:47 2023 +0800 |
| tree | cf1170f7f208ae08a71dbd115bd584a5c92d85a1 | |
| parent | bf4c026dd402e45546333c6c843a6008fe58e771 [diff] |
fix: modify the logic of pick shards (#259) ## Rationale We found that according to the current way of pick shards, the subtables of the partition table will be concentrated on some nodes, causing hot spots, so some modifications need to be made to avoid this phenomenon. ## Detailed Changes * Modify the logic of pick shard, when the number of tables is the same, sort according to the size of ShardID. ## Test Plan Pass all unit tests and integration test.
CeresMeta is the meta service for managing the CeresDB cluster.
The project is in a very early stage.
make build
Although CeresMeta is designed to deployed as a cluster with three or more instances, it can also be started standalone:
# ceresmeta0 mkdir /tmp/ceresmeta0 ./ceresmeta --config ./config/example-standalone.toml
Here is an example for starting CeresMeta in cluster mode (three instances) on single machine by using different ports:
# Create directories. mkdir /tmp/ceresmeta0 mkdir /tmp/ceresmeta1 mkdir /tmp/ceresmeta2 # Ceresmeta0 ./ceresmeta --config ./config/exampl-cluster0.toml # Ceresmeta1 ./ceresmeta --config ./config/exampl-cluster1.toml # Ceresmeta2 ./ceresmeta --config ./config/exampl-cluster2.toml
CeresMeta refers to the excellent project pd in design and some module and codes are forked from pd, thanks to the TiKV team.
The project is under rapid development so that any contribution is welcome. Check our Contributing Guide and make your first contribution!
CeresMeta is under Apache License 2.0.