fix: #21136
mem tracker group uses class static variables instead of global variables
https://stackoverflow.com/questions/2204608/does-c-call-destructors-for-global-and-class-static-variables
TODO: A mem tracker manager is required, don't use global variables, it will sad
==3623982==ERROR: AddressSanitizer: heap-use-after-free on address 0x60f0000056b8 at pc 0x56478bbe3ae0 bp 0x7f20953d2270 sp 0x7f20953d2268
READ of size 8 at 0x60f0000056b8 thread T41 (memory_tracker_)
*** Query id: 0-0 ***
*** Aborted at 1689749969 (unix time) try "date -d @1689749969" if you are using GNU date ***
*** Current BE git commitID: b3e9cad48e ***
*** SIGSEGV address not mapped to object (@0x0) received by PID 3623982 (TID 3624277 OR 0x7f19e06dd640) from PID 0; stack trace: ***
#0 0x56478bbe3adf in std::__shared_ptr::operator bool() const /var/local/ldb_toolchain/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/shared_ptr_base.h:1295:16
#1 0x56478bbe306e in doris::MemTracker::refresh_profile_counter() /doris/be/src/runtime/memory/mem_tracker.h:149:13
#2 0x56478bbec669 in doris::MemTrackerLimiter::refresh_all_tracker_profile() /doris/be/src/runtime/memory/mem_tracker_limiter.cpp:119:22
#3 0x564788f53fa0 in doris::Daemon::memory_tracker_profile_refresh_thread() /doris/be/src/common/daemon.cpp:295:9
#4 0x564788f5d04b in doris::Daemon::start()::$_4::operator()() const /doris/be/src/common/daemon.cpp:473:30
#5 0x564788f5cff6 in void std::__invoke_impl(std::__invoke_other, doris::Daemon::start()::$_4&) /var/local/ldb_toolchain/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/invoke.h:61:14
#6 0x564788f5cf78 in std::enable_if, void>::type std::__invoke_r(doris::Daemon::start()::$_4&) /var/local/ldb_toolchain/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/invoke.h:111:2
#7 0x564788f5cdae in std::_Function_handler::_M_invoke(std::_Any_data const&) /var/local/ldb_toolchain/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/std_function.h:291:9
#8 0x56478903f576 in std::function::operator()() const /var/local/ldb_toolchain/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/std_function.h:560:9
#9 0x56478c4a35af in doris::Thread::supervise_thread(void*) /doris/be/src/util/thread.cpp:465:5
#10 0x7f217c8a244f in start_thread nptl/pthread_create.c:473:8
#11 0x7f217cb27d52 in __clone misc/../sysdeps/unix/sysv/linux/x86_64/clone.S:95
0x60f0000056b8 is located 56 bytes inside of 168-byte region [0x60f000005680,0x60f000005728)
freed by thread T0 here:
#0 0x564788e7280d in operator delete(void*) (/mnt/hdd01/dorisTestEnv/NEREIDS_ASAN/be/lib/doris_be+0x1758280d) (BuildId: 219493cc924323ee)
#1 0x56478acec1d5 in std::default_delete::operator()(doris::MemTrackerLimiter*) const /var/local/ldb_toolchain/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/unique_ptr.h:85:2
#2 0x56478ace9faf in std::unique_ptr >::~unique_ptr() /var/local/ldb_toolchain/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/unique_ptr.h:361:4
#3 0x56478ace1471 in doris::ShardedLRUCache::~ShardedLRUCache() /doris/be/src/olap/lru_cache.cpp:581:1
#4 0x56478ace14c8 in doris::ShardedLRUCache::~ShardedLRUCache() /doris/be/src/olap/lru_cache.cpp:572:37
#5 0x56478acd0984 in std::default_delete::operator()(doris::Cache*) const /var/local/ldb_toolchain/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/unique_ptr.h:85:2
#6 0x56478acceddf in std::unique_ptr >::~unique_ptr() /var/local/ldb_toolchain/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/unique_ptr.h:361:4
#7 0x56478ad96dc6 in doris::StoragePageCache::~StoragePageCache() /doris/be/src/olap/page_cache.h:78:7
#8 0x7f217ca54146 in __run_exit_handlers stdlib/exit.c:108:8
previously allocated by thread T0 here:
#0 0x564788e71fad in operator new(unsigned long) (/mnt/hdd01/dorisTestEnv/NEREIDS_ASAN/be/lib/doris_be+0x17581fad) (BuildId: 219493cc924323ee)
#1 0x56478ace9c90 in std::_MakeUniq::__single_object std::make_unique, std::allocator > const&>(doris::MemTrackerLimiter::Type&&, std::__cxx11::basic_string, std::allocator > const&) /var/local/ldb_toolchain/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/unique_ptr.h:962:30
#2 0x56478acde930 in doris::ShardedLRUCache::ShardedLRUCache(std::__cxx11::basic_string, std::allocator > const&, unsigned long, doris::LRUCacheType, unsigned int, unsigned int) /doris/be/src/olap/lru_cache.cpp:526:20
#3 0x56478ace22e1 in doris::new_lru_cache(std::__cxx11::basic_string, std::allocator > const&, unsigned long, doris::LRUCacheType, unsigned int) /doris/be/src/olap/lru_cache.cpp:670:16
#4 0x56478ad91da2 in doris::StoragePageCache::StoragePageCache(unsigned long, int, long, unsigned int) /doris/be/src/olap/page_cache.cpp:47:17
#5 0x56478ad9156e in doris::StoragePageCache::create_global_cache(unsigned long, int, long, unsigned int) /doris/be/src/olap/page_cache.cpp:31:29
#6 0x56478b98b3d3 in doris::ExecEnv::_init_mem_env() /doris/be/src/runtime/exec_env_init.cpp:251:5
#7 0x56478b98946c in doris::ExecEnv::_init(std::vector > const&) /doris/be/src/runtime/exec_env_init.cpp:182:5
#8 0x56478b987139 in doris::ExecEnv::init(doris::ExecEnv*, std::vector > const&) /doris/be/src/runtime/exec_env_init.cpp:98:17
#9 0x564788e79b50 in main /doris/be/src/service/doris_main.cpp:429:5
#10 0x7f217ca38564 in __libc_start_main csu/../csu/libc-start.c:332:16
Thread T41 (memory_tracker_) created by T0 here:
#0 0x564788e1fcaa in pthread_create (/mnt/hdd01/dorisTestEnv/NEREIDS_ASAN/be/lib/doris_be+0x1752fcaa) (BuildId: 219493cc924323ee)
#1 0x56478c4a2366 in doris::Thread::start_thread(std::__cxx11::basic_string, std::allocator > const&, std::__cxx11::basic_string, std::allocator > const&, std::function const&, unsigned long, scoped_refptr*) /doris/be/src/util/thread.cpp:419:15
#2 0x564788f59b91 in doris::Status doris::Thread::create(std::__cxx11::basic_string, std::allocator > const&, std::__cxx11::basic_string, std::allocator > const&, doris::Daemon::start()::$_4 const&, scoped_refptr*) /doris/be/src/util/thread.h:50:16
#3 0x564788f58165 in doris::Daemon::start() /doris/be/src/common/daemon.cpp:471:10
#4 0x564788e79a96 in main /doris/be/src/service/doris_main.cpp:420:12
#5 0x7f217ca38564 in __libc_start_main csu/../csu/libc-start.c:332:16
Jemalloc dirty page only use madvise MADV_FREE, memory is not release back to system, RSS won't reduce in time,
So when the process memory exceed limit or system available memory is insufficient,
manually transfer dirty page to the muzzy page, which will call MADV_DONTNEED to release the physical memory back to the system.
https://jemalloc.net/jemalloc.3.html#opt.dirty_decay_ms
Suppose three queries are executed in a resource group with a memory_limit of 8G, and they consume memory of query_a = 3G, query_b = 3G, and query_c = 3G. The total memory used is counted as 9G when the resource group GC is executed, which exceeds the resource group limit and cancels query_a.
When the resource group is next GC, the memory of query_a may not be freed yet, and it will be counted again in the total memory consumed by that resource group, which again exceeds the resource group limit and cancels query_b.
From the user's perspective, it is fine to execute query_a and query_b at the same time, but executing query_ a, query_b and query_c will be cancelled for two queries, which is not as expected.
This pr skips the queries that are cancelled when counting the memory used by the resource group. If this causes the process memory to grow, the process gc will handle it.
After the outer catch exception, faststring resize reserve build may throw a memory alloc failure exception from the Allocator.
Currently page body compress will catch memory alloc failure exception
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.
No check mem tracker limit and no cancel task in mem hook, only in Allocator. This helps in clearer analysis of memory issues and reduces performance loss.
PODArray/hash table/arena memory allocation will use Allocator.
Optimize mem limit exceeded log printing
Optimize compilation time
Remove page cache regular clear
Now the page cache is turned off by default. If the user manually opens the page cache, it can be considered that the user can accept the memory usage of the page cache, and then can consider adding a manual clear command to the cache.
fix memory gc cancel top memory query
jemalloc prof is not enabled by default
After the memory exceeds the limit, the previous query waited for memory free in the mem hook, and changed it to wait in the Allocator.
more controllable and safe
Problem:
1. FE will split the parquet file into split. So a file can have several splits.
2. BE will scan each split, read the footer of the parquet file.
3. If 2 splits belongs to a same parquet file, the footer of this file will be read twice.
This PR mainly changes:
1. Use kv cache to cache the footer of parquet file.
2. The kv cache is belong to a scan node, so all parquet reader belong to this scan node will share same kv cache.
3. In cache, the key is "meta_file_path", the value is parsed thrift footer.
The KV Cache is sharded into mutlti sub cache.
So that different file can use different sub cache, avoid blocking each other
In my test, a query with 26 splits can reduce the footer parse time from 4s -> 1s
Add a special counter for memtracker, faster, but relaxed ordering and not accurate in real time
Track thread create and destroy memory, which was previously removed due to performance loss and added back
Fix Redhat 4.x OS /proc/meminfo has no MemAvailable, disable MemAvailable to control memory.
vm_rss_str and mem_available_str recorded when gc is triggered, to avoid memory changes during gc and cause inaccurate logs.
join probe catch bad_alloc, this may alloc 64G memory at a time, avoid OOM.
Modify document doris_be_all_segments_num and doris_be_all_rowsets_num names.
MetricRegistry::trigger_all_hooks holds the metrics lock and is stuck in get_je_metrics, to_prometheus is waiting for MetricRegistry::trigger_all_hooks to release the lock, so get_je_metrics is no longer called in MetricRegistry::trigger_all_hooks.
1. When the process memory is insufficient, print the process memory statistics in a more timely and detailed manner.
2. Support regular GC cache, currently only page cache and chunk allocator are included, because many people reported that the memory does not drop after the query ends.
3. Reduce system available memory warning water mark to reduce memory waste
4. Optimize soft mem limit logging
Overcommit memory means that when the memory is sufficient, it no longer checks whether the memory of query/load exceeds the exec mem limit.
Instead, when the process memory exceeds the limit or the available system memory is insufficient, cancel the top overcommit query in minor gc, and cancel top memory query in full gc.
Previously only query supported overcommit memory, this pr supports load, including insert into and stream load.
Detailed explanation, I will update the memory document in these two days~
15bd56cd43/docs/zh-CN/docs/admin-manual/maint-monitor/memory-management/memory-limit-exceeded-analysis.md
Add conf enable_query_memroy_overcommit
If true, when the process does not exceed the soft mem limit, the query memory will not be limited; when the process memory exceeds the soft mem limit, the query with the largest ratio between the currently used memory and the exec_mem_limit will be canceled.
If false, cancel query when the memory used exceeds exec_mem_limit, same as before.
When the system MemAvailable is less than the warning water mark, or the memory used by the BE process exceeds the mem soft limit, run minor gc and try to release cache.
When the MemAvailable of the system is less than the low water mark, or the memory used by the BE process exceeds the mem limit, run fucc gc, try to release the cache, and start canceling from the query with the largest memory usage until the memory of mem_limit * 20% is released.
