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.
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
* [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
In mow, primary key cache have a big impact on load performance, so we add a new cache type to seperate
it from page cache to make it more flexible in some cases
Currently, there are some useless includes in the codebase. We can use a tool named include-what-you-use to optimize these includes. By using a strict include-what-you-use policy, we can get lots of benefits from it.
Co-authored-by: ByteYue <[yj976240184@gmail.com](mailto:yj976240184@gmail.com)>
This PR is an optimization for https://github.com/apache/doris/pull/17478:
1. Change the buffer size of `LineReader` to 4MB to align with the size of prefetch buffer.
2. Lazily prefetch data in the first read to prevent wasted reading.
3. S3 block size is 32MB only, which is too small for a file split. Set 128MB as default file split size.
4. Add `_end_offset` for prefetch buffer to prevent wasted reading.
The query performance of reading data on object storage is improved by more than 3x+.
Follow #17586.
This PR mainly changes:
Remove env/
Remove FileUtils/FilesystemUtils
Some methods are moved to LocalFileSystem
Remove olap/file_cache
Add s3 client cache for s3 file system
In my test, the time of open s3 file can be reduced significantly
Fix cold/hot separation bug for s3 fs.
This is the last PR of #17764.
After this, all IO operation should be in io/fs.
Except for tests in #17586, I also tested some case related to fs io:
clone
concurrency query on local/s3/hdfs
load error log create and clean
disk metrics
* [enhancement](execute model) using thread pool to execute report or join task instead of staring too many thread
Doris will start report thread and join thread during fragment execution. There are many problems if create and destroy thread very frequently. Jemalloc may not behave very well, it may crashed.
jemalloc/jemalloc#1405
It is better to using thread pool to do these tasks.
---------
Co-authored-by: yiguolei <yiguolei@gmail.com>
Add cache for inverted index query match bitmap to accelerate common query keyword, especially for keyword matching many rows.
Tests result:
- large result: matching 99% out of 247 million rows shows 8x speed up.
- small result: matching 0.1% out of 247 million rows shows 2x speed up.
The origin scan pools are in exec_env.
But after enable new_load_scan_node by default, the scan pool in exec_env is no longer used.
All scan task will be submitted to the scan pool in scanner_scheduler.
BTW, reorganize the scan pool into 3 kinds:
local scan pool
For olap scan node
remote scan pool
For file scan node
limited scan pool
For query which set cpu resource limit or with small limit clause
TODO:
Use bthread to unify all IO task.
Some trivial issues:
fix bug that the memtable flush size printed in log is not right
Add RuntimeProfile param in VScanner
mem tracker can be logically divided into 4 layers: 1)process 2)type 3)query/load/compation task etc. 4)exec node etc.
type includes
enum Type {
GLOBAL = 0, // Life cycle is the same as the process, e.g. Cache and default Orphan
QUERY = 1, // Count the memory consumption of all Query tasks.
LOAD = 2, // Count the memory consumption of all Load tasks.
COMPACTION = 3, // Count the memory consumption of all Base and Cumulative tasks.
SCHEMA_CHANGE = 4, // Count the memory consumption of all SchemaChange tasks.
CLONE = 5, // Count the memory consumption of all EngineCloneTask. Note: Memory that does not contain make/release snapshots.
BATCHLOAD = 6, // Count the memory consumption of all EngineBatchLoadTask.
CONSISTENCY = 7 // Count the memory consumption of all EngineChecksumTask.
}
Object pointers are no longer saved between each layer, and the values of process and each type are periodically aggregated.
other fix:
In [fix](memtracker) Fix transmit_tracker null pointer because phamp is not thread safe #13528, I tried to separate the memory that was manually abandoned in the query from the orphan mem tracker. But in the actual test, the accuracy of this part of the memory cannot be guaranteed, so put it back to the orphan mem tracker again.
Previously, bthread_getspecific was called every time bthread local was used. In the test at #10823, it was found that frequent calls to bthread_getspecific had performance problems.
So a cache is implemented on pthread local based on the btls key, but the btls key cannot correctly sense bthread switching.
So, based on bthread_self to get the bthread id to implement the cache.
disable page cache by default
disable chunk allocator by default
not use chunk allocator for vectorized allocator by default
add a new config memory_linear_growth_threshold = 128Mb, not allocate memory by RoundUpToPowerOf2 if the allocated size is larger than this threshold. This config is added to MemPool, ChunkAllocator, PodArray, Arena.
In order to avoid different mem tracker consumption values of multiple queries/loads, and the difference between the virtual memory of alloc and the physical memory actually increased by the process.
The memory alloc in PODArray and mempool will not be recorded in the query/load mem tracker immediately, but will be gradually recorded in the mem tracker during the memory usage.
But mem pool allocates memory from chunk allocator. If this chunk is used after the second time, it may have used physical memory. The above mechanism will cause the load channel memory statistics to be less than the actual value.
