When UBSAN is compiled, all memory will be tracked to the orphan (unknown) mem tracker, and the bthread context and mem tracker will no longer be switched.
The supplementary fixes are as follows: #20999
Before, refresh the TabletsChannel profile in the LoadChannelMgr refresh memory statistics thread
This means that enable_profile=false will refresh and have performance loss in stress test
fix pipeline task call finish_p_dependency more than once
When pipeline task meet eos->PENDING_FINISH->CANCELED, this task will call finish_p_dependency twice.
Sometimes connection cannot be released properly during on_free. We need
on_close callback as the last resort.
Signed-off-by: freemandealer <freeman.zhang1992@gmail.com>
1. Add hdfs file handle cache for hdfs file reader
Copied from Impala, `https://github.com/apache/impala/blob/master/be/src/util/lru-multi-cache.h`. (Thanks for the Impala team)
This is a lru cache that can store multi entries with same key.
The key is build with {file name + modification time}
The value is the hdfsFile pointer that point to a certain hdfs file.
This cache is to avoid reopen same hdfs file mutli time, which can save
query time.
Add a BE config `max_hdfs_file_handle_cache_num` to limit the max number
of file handle cache, default is 20000.
2. Add file meta cache
The file meta cache is a lru cache. the key is {file name + modification time},
the value is the parsed file meta info of the certain file, which can save
the time of re-parsing file meta everytime.
Currently, it is only used for caching parquet file footer.
The test show that is cache is hit, the `FileOpenTime` and `ParseFooterTime` is reduce to almost 0
in query profile, which can save time when there are lots of files to read.
start time: Wed 07 Jun 2023 06:50:14 PM CST
*** Query id: e9000000e9-eb00000073 ***
*** Aborted at 1686136356 (unix time) try "date -d @1686136356" if you are using GNU date ***
*** Current BE git commitID: 5c33dd7a2c ***
*** SIGSEGV address not mapped to object (@0x23000000235) received by PID 2131238 (TID 2132258 OR 0x7f708eff7700) from PID 565; stack trace: ***
0# doris::signal::(anonymous namespace)::FailureSignalHandler(int, siginfo_t*, void*) at /mnt/hdd01/repo_center/doris_branch-2.0-beta/doris/be/src/common/signal_handler.h:413
1# 0x00007F727BBE3090 in /lib/x86_64-linux-gnu/libc.so.6
2# doris::AttachTask::AttachTask(doris::RuntimeState*) at /mnt/hdd01/repo_center/doris_branch-2.0-beta/doris/be/src/runtime/thread_context.cpp:43
3# std::_Function_handler<void (doris::PTabletWriterAddBlockResult const&, bool), doris::stream_load::VNodeChannel::open_wait()::$_1>::_M_invoke(std::_Any_data const&, doris::PTabletWriterAddBlockResult const&, bool&&) at /var/local/ldb_toolchain/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/std_function.h:291
4# doris::stream_load::ReusableClosure<doris::PTabletWriterAddBlockResult>::Run() at /mnt/hdd01/repo_center/doris_branch-2.0-beta/doris/be/src/vec/sink/vtablet_sink.h:176
5# brpc::Controller::EndRPC(brpc::Controller::CompletionInfo const&) in /root/20230607171843-doris-branch-2.0-beta-5c33dd7a/be/lib/doris_be
6# brpc::Controller::OnVersionedRPCReturned(brpc::Controller::CompletionInfo const&, bool, int) in /root/20230607171843-doris-branch-2.0-beta-5c33dd7a/be/lib/doris_be
7# brpc::policy::ProcessRpcResponse(brpc::InputMessageBase*) in /root/20230607171843-doris-branch-2.0-beta-5c33dd7a/be/lib/doris_be
8# brpc::InputMessenger::InputMessageClosure::~InputMessageClosure() in /root/20230607171843-doris-branch-2.0-beta-5c33dd7a/be/lib/doris_be
9# brpc::InputMessenger::OnNewMessages(brpc::Socket*) in /root/20230607171843-doris-branch-2.0-beta-5c33dd7a/be/lib/doris_be
10# brpc::Socket::ProcessEvent(void*) in /root/20230607171843-doris-branch-2.0-beta-5c33dd7a/be/lib/doris_be
11# bthread::TaskGroup::task_runner(long) in /root/20230607171843-doris-branch-2.0-beta-5c33dd7a/be/lib/doris_be
12# bthread_make_fcontext in /root/20230607171843-doris-branch-2.0-beta-5c33dd7a/be/lib/doris_be
Only switch to bthread local when modifying the mem tracker in the thread context. No longer switches to bthread local by default when bthread starts
mem tracker increases brpc IOBufBlockMemory memory
remove thread mem tracker metrics
For routine load (kafka load), user can produce all data for different
table into single topic and doris will dispatch them into corresponding
table.
Signed-off-by: freemandealer <freeman.zhang1992@gmail.com>
* [fix](load) in strict mode, return error for load and insert if datatype convert fails
Revert "[fix](MySQL) the way Doris handles boolean type is consistent with MySQL (#19416)"
This reverts commit 68eb420cabe5b26b09d6d4a2724ae12699bdee87.
Since it changed other behaviours, e.g. in strict mode insert into t_int values ("a"),
it will result 0 is inserted into table, but it should return error instead.
* fix be ut
* fix regression tests
The memory released by the query end is recorded in the query mem tracker, main memory in _runtime_state.
fix page no cache memory tracking
Now the main reason for the inaccurate query memory tracking is that the virtual memory used by the query is sometimes much larger than the actual memory. And the mem hook counts virtual memory.
Parallel scanning can result in some read amplification, for example, select * from xx where limit 1 actually requires only one row of data. However, due to parallel scanning of multiple tablets, read amplification occurs, leading to performance bottlenecks in high-concurrency scenarios. This PR Adding a SessionVariable to enforce serial scanning can help mitigate this issue.
* [Improve](performance) introduce SchemaCache to cache TabletSchame & Schema
1. When the system is under high-concurrency load with wide table point queries, the frequent memory allocation and deallocation of Schema become evident system bottlenecks. Additionally, the initialization of TabletSchema and Schema also becomes a CPU hotspot.Therefore, the introduction of a SchemaCache is implemented to cache these resources for reuse.
2. Make some variables wrapped with std::unique<unique_ptr>
Performance:
| 状态 | QPS | 平均响应时间 (avg) | P99 响应时间 |
|------------------|-----|------------------|-------------|
| 开启 SchemaCache | 501 | 20ms | 34ms |
| 关闭 SchemaCache | 321 | 31ms | 61ms |
* handle schema change with schema version
* remove useless header
* rebase
Refactoring the filtering conditions in the current ExecNode from an expression tree to an array can simplify the process of adding runtime filters. It eliminates the need for complex merge operations and removes the requirement for the frontend to combine expressions into a single entity.
By representing the filtering conditions as an array, each condition can be treated individually, making it easier to add runtime filters without the need for complex merging logic. The array can store the individual conditions, and the runtime filter logic can iterate through the array to apply the filters as needed.
This refactoring simplifies the codebase, improves readability, and reduces the complexity associated with handling filtering conditions and adding runtime filters. It separates the conditions into discrete entities, enabling more straightforward manipulation and management within the execution node.
