1. Add a new FE config `colocate_group_relocate_delay_second`
The relocation of a colocation group may involve a large number of tablets moving within the cluster.
Therefore, we should use a more conservative strategy to avoid relocation of colocation groups as much as possible.
Relocation usually occurs after a BE node goes offline or goes down.
This config is used to delay the determination of BE node unavailability.
The default is 30 minutes, i.e., if a BE node recovers within 30 minutes, relocation of the colocation group
will not be triggered.
2. Change the priority of colocate tablet repair and balance task from HIGH to NORMAL
3. Add a new FE config allow_replica_on_same_host
If set to true, when creating table, Doris will allow to locate replicas of a tablet
on same host. And also the tablet repair and balance will be disabled.
This is only for local test, so that we can deploy multi BE on same host and create table
with multi replicas.
# Proposed changes
Issue Number: close#6238
Co-authored-by: HappenLee <happenlee@hotmail.com>
Co-authored-by: stdpain <34912776+stdpain@users.noreply.github.com>
Co-authored-by: Zhengguo Yang <yangzhgg@gmail.com>
Co-authored-by: wangbo <506340561@qq.com>
Co-authored-by: emmymiao87 <522274284@qq.com>
Co-authored-by: Pxl <952130278@qq.com>
Co-authored-by: zhangstar333 <87313068+zhangstar333@users.noreply.github.com>
Co-authored-by: thinker <zchw100@qq.com>
Co-authored-by: Zeno Yang <1521564989@qq.com>
Co-authored-by: Wang Shuo <wangshuo128@gmail.com>
Co-authored-by: zhoubintao <35688959+zbtzbtzbt@users.noreply.github.com>
Co-authored-by: Gabriel <gabrielleebuaa@gmail.com>
Co-authored-by: xinghuayu007 <1450306854@qq.com>
Co-authored-by: weizuo93 <weizuo@apache.org>
Co-authored-by: yiguolei <guoleiyi@tencent.com>
Co-authored-by: anneji-dev <85534151+anneji-dev@users.noreply.github.com>
Co-authored-by: awakeljw <993007281@qq.com>
Co-authored-by: taberylyang <95272637+taberylyang@users.noreply.github.com>
Co-authored-by: Cui Kaifeng <48012748+azurenake@users.noreply.github.com>
## Problem Summary:
### 1. Some code from clickhouse
**ClickHouse is an excellent implementation of the vectorized execution engine database,
so here we have referenced and learned a lot from its excellent implementation in terms of
data structure and function implementation.
We are based on ClickHouse v19.16.2.2 and would like to thank the ClickHouse community and developers.**
The following comment has been added to the code from Clickhouse, eg:
// This file is copied from
// https://github.com/ClickHouse/ClickHouse/blob/master/src/Interpreters/AggregationCommon.h
// and modified by Doris
### 2. Support exec node and query:
* vaggregation_node
* vanalytic_eval_node
* vassert_num_rows_node
* vblocking_join_node
* vcross_join_node
* vempty_set_node
* ves_http_scan_node
* vexcept_node
* vexchange_node
* vintersect_node
* vmysql_scan_node
* vodbc_scan_node
* volap_scan_node
* vrepeat_node
* vschema_scan_node
* vselect_node
* vset_operation_node
* vsort_node
* vunion_node
* vhash_join_node
You can run exec engine of SSB/TPCH and 70% TPCDS stand query test set.
### 3. Data Model
Vec Exec Engine Support **Dup/Agg/Unq** table, Support Block Reader Vectorized.
Segment Vec is working in process.
### 4. How to use
1. Set the environment variable `set enable_vectorized_engine = true; `(required)
2. Set the environment variable `set batch_size = 4096; ` (recommended)
### 5. Some diff from origin exec engine
https://github.com/doris-vectorized/doris-vectorized/issues/294
## Checklist(Required)
1. Does it affect the original behavior: (No)
2. Has unit tests been added: (Yes)
3. Has document been added or modified: (No)
4. Does it need to update dependencies: (No)
5. Are there any changes that cannot be rolled back: (Yes)
If an load task has a relatively short timeout, then we need to ensure that
each RPC of this task does not get blocked for a long time.
And an RPC is usually blocked for two reasons.
1. handling "memory exceeds limit" in the RPC
If the system finds that the memory occupied by the load exceeds the threshold,
it will select the load channel that occupies the most memory and flush the memtable in it.
this operation is done in the RPC, which may be more time consuming.
2. close the load channel
When the load channel receives the last batch, it will end the task.
It will wait for all memtables flushes to finish synchronously. This process is also time consuming.
Therefore, this PR solves this problem by.
1. Use timeout to determine whether it is a high-priority load task
If the timeout of an load task is relatively short, then we mark it as a high-priority task.
2. not processing "memory exceeds limit" for high priority tasks
3. use a separate flush thread to flush memtable for high priority tasks.
* 1.Remove import doris via csv in Dataxwriter, only support via json;
2.Format Dataxwriter code;
3.Optimize exception handling and reduce multiple output of exception logs;
4.Update the dataxwriter's documentation;
* Delete DorisCsvCodec.java
delete unused file extension/DataX/doriswriter/src/main/java/com/alibaba/datax/plugin/writer/doriswriter/DorisCsvCodec.java
* 1.remove `format` config key;
2.Optimize serialization code in DorisJsonCodec class
Support merge IN predicate when exist remote target(e.g. shuffle hash join).
Remote the code that IN predicate implicit conversion to Bloom filter then exist remote target.
Close related #7546
Add a new FE config `repair_slow_replica`
when this config is true, Doris will try to delete the replica
with the largest number of versions, and then rebalance the replica.
Usually, when the number of versions of a certain replica is much higher
then that of other replicas, there are some problems with the current be's compilation.
Migrating to other machines can typically solve this problem.
Add partitionNum, tabletNum, cardinality in SqlBlockRule to block large/slow sql.
1. set partitionNum, tabletNum, cardinality as limitations to block sqls
2. compatible with lower version
3. add unit tests
4. add docs
This pr is for #7096 , which is add a rewrite rule for infer predicate.
For example:
origin stmt: select * from t1, t2, t3 where t1.id=t2.id and t2.i=t3.id and t2.id = 1
rewrite stmt: select * from t1, t2, t3 where t1.id=t2.id and t2.i=t3.id and t2.id = 1 and t1.id=1 and t3.id=1
+ Add a switch enable_infer_predicate to control whether to perform predicate expansion.
+ Register a new rule InferFiltersrule and add it to GlobalState.
+ Traverse Conjunct to construct on/where equivalence connection, numerical connection and isNullPredicate.
+ Infer all equivalence connections
+ Construct additional numerical connections and isNullPredicate
1. Change `brpc_socket_max_unwritten_bytes` to 1GB
This can make the system more fault-tolerant.
Especially in the case of high system load, try to reduce EOVERCROWDED errors.
2. Change `brpc_max_body_size` to 3GB
To handle some large object such as bitmap or string.
1. Refactor the scheduling logic of broker load. Details see #7367
2. Fix bug that loadedBytes in SHOW LOAD result is wrong.
3. Cancel the thread of LoadTimeoutChecker
Now for PENDING load jobs, there will be no timeout. And the timeout of a load job
start when pending load task is scheduled.
4. Fix a bug that the loading task is never submitted to the pool.
The logic of BlockedPolicy is wrong. We should make sure the task is submitted to the pool,
or the RejectedExecutionException should be thrown.
5. Now the transaction of a load job will begin in pending task, instead of when submitting the job.
