Like #15641, we should reduce the size of executables on macOS arm64. Otherwise, we can not run doris_be and doris_be_test with ASAN build type on macOS arm64 now.
Manually track query/load/compaction/etc. memory in Allocator instead of mem hook.
Can still use Mem Hook when cannot manually track memory code segments and find memory locations during debugging.
This will cause memory tracking loss for Query, loss less than 10% compared to the past, but this is expected to be more controllable.
Similarly, Mem Hook will no longer track unowned memory to the orphan mem tracker by default, so the total memory of all MemTrackers will be less than before.
Not need to get memory size from jemalloc in Mem Hook each memory alloc and free, which would lose performance in the past.
Not require caching bthread local in pthread local for memory hook, in the past this has caused core dumps inside bthread, seems to be a bug in bthread.
ThreadContext life cycle to manual control
In the past, ThreadContext was automatically created when it was used for the first time (this was usually in the Jemalloc Hook when the first malloc memory), and was automatically destroyed when the thread exited.
Now instead of manually controlling the create and destroy of ThreadContext, it is mainly created manually when the task thread start and destroyed before the task thread end.
Run 43 clickbench query tests.
Use MemHook in the past:
1. closure should be managed by a unique ptr and released by brpc , should not hold by our code. If hold by our code, we need to wait brpc finished during cancel or close.
2. closure should be exception safe, if any exception happens, should not memory leak.
3. using a specific callback interface to be implemented by Doris's code, we could write any code and doris should manage callback's lifecycle.
4. using a weak ptr between callback and closure. If callback is deconstruted before closure'Run, should not core.
In previous, when using file scan node(eq, querying hive table), the max number of scanner for each scan node
will be the `doris_scanner_thread_pool_thread_num`(default is 48).
And if the query parallelism is N, the total number of scanner would be 48 * N, which is too many.
In this PR, I change the logic, the max number of scanner for each scan node
will be the `doris_scanner_thread_pool_thread_num / query parallelism`. So that the total number of scanners
will be up to `doris_scanner_thread_pool_thread_num`.
Reduce the number of scanner can significantly reduce the memory usage of query.
Under some workload the `multiget_data` maybe stuck and raise rpc timeout.
Inorder to to minimize the latency of point queries, so it should be placed in `_light_work_pool`, since
it's typically finished in hundreds of millisecond
If a failure occurs, doris may retry. Due to ctx->is_read_schema is a global variable that has not been reset in a timely manner, which may cause exceptions.
---------
Co-authored-by: yiguolei <676222867@qq.com>
BE will crash because done run twice when try_offer() failed in
request_slave_tablet_pull_rowset.
Signed-off-by: freemandealer <freeman.zhang1992@gmail.com>
* Add more log for ingest_binlog && Fix ingest_binlog not rewrite
rowset_meta tablet_uid
Signed-off-by: Jack Drogon <jack.xsuperman@gmail.com>
* Add lost thrift TDebugProtocol
Signed-off-by: Jack Drogon <jack.xsuperman@gmail.com>
---------
Signed-off-by: Jack Drogon <jack.xsuperman@gmail.com>
