"operator_id" should be invisible, but the local shuffle is a planned operator in the BE (Backend), without a plan node ID. We use it in profiles and other places, and there might be duplicates. Therefore, we switch it to a negative number here to distinguish it as a plan node ID.
In the load process, if there are problems with the original data, we will store the error data in an error_log file on the disk for subsequent debugging. However, if there are many error data, it will occupy a lot of disk space. Now we want to limit the number of error data that is saved to the disk.
Be familiar with the usage of doris' import function and internal implementation process
Add a new be configuration item load_error_log_limit_bytes = default value 200MB
Use the newly added threshold to limit the amount of data that RuntimeState::append_error_msg_to_file writes to disk
Write regression cases for testing and verification
Co-authored-by: xy720 <22125576+xy720@users.noreply.github.com>
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:
Fix work load group GC, add cancel load and add logs.
Unify the format and change all to lowercase of GC logs, avoid unnecessary trouble when grep or less
Add logs to help locate the cause of slow GC.
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
This work is in the early stage, current progress is not accurate because the scan range will be too large
for gathering information, what's more, only file scan node and import job support new progress manager
## How it works
for example, when we use the following load query:
```
LOAD LABEL test_broker_load
(
DATA INFILE("XXX")
INTO TABLE `XXX`
......
)
```
Initial Progress: the query will call `BrokerLoadJob` to create job, then `coordinator` is called to calculate scan range and its location.
Update Progress: BE will report runtime_state to FE and FE update progress status according to jobID and fragmentID
we can use `show load` to see the progress
PENDING:
```
State: PENDING
Progress: 0.00%
```
LOADING:
```
State: LOADING
Progress: 14.29% (1/7)
```
FINISH:
```
State: FINISHED
Progress: 100.00% (7/7)
```
At current time, full output of `show load\G` looks like:
```
*************************** 1. row ***************************
JobId: 25052
Label: test_broker
State: LOADING
Progress: 0.00% (0/7)
Type: BROKER
EtlInfo: NULL
TaskInfo: cluster:N/A; timeout(s):250000; max_filter_ratio:0.0
ErrorMsg: NULL
CreateTime: 2023-05-03 20:53:13
EtlStartTime: 2023-05-03 20:53:15
EtlFinishTime: 2023-05-03 20:53:15
LoadStartTime: 2023-05-03 20:53:15
LoadFinishTime: NULL
URL: NULL
JobDetails: {"Unfinished backends":{"5a9a3ecd203049bc-85e39a765c043228":[10080]},"ScannedRows":39611808,"TaskNumber":1,"LoadBytes":7398908902,"All backends":{"5a9a3ecd203049bc-85e39a765c043228":[10080]},"FileNumber":1,"FileSize":7895697364}
TransactionId: 14015
ErrorTablets: {}
User: root
Comment:
```
## TODO:
1. The current partition granularity of scan range is too large, resulting in an uneven loading process for progress."
2. Only broker load supports the new Progress Manager, support progress for other query
TabletSink and LoadChannel in BE are M: N relationship,
Every once in a while LoadChannel will randomly return its own runtime profile to a TabletSink, so usually all LoadChannel runtime profiles are saved on each TabletSink, and the timeliness of the same LoadChannel profile saved on different TabletSinks is different, and each TabletSink will periodically send fe reports all the LoadChannel profiles saved by itself, and ensures to update the latest LoadChannel profile according to the timestamp.
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
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
Now we use a thrift message per fragment instance. However, there are many same messages between instances in a fragment. So this PR aims to extract the same messages and we only need to send thrift message once for a fragment
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
