We can observe the workload of BE, and also it's a way to check
whether there is any problem in BE, like some container increase
too large and lead to OOM.
This patch add the following metrics:
```
Name Description
rowset_count_generated_and_in_use The total count of rowset id generated and in use since BE last start
unused_rowsets_count The total count of unused rowset waiting to be GC
broker_count The total count of brokers in management
data_stream_receiver_count The total count of data stream receivers in management
fragment_endpoint_count The total count of fragment endpoints of data stream in management, should always equal to data_stream_receiver_count
active_scan_context_count The total count of active scan contexts
plan_fragment_count The total count of plan fragments in executing
load_channel_count The total count of load channels in management
result_buffer_block_count The total count of result buffer blocks for queries, each block has a limited queue size (default 1024)
result_block_queue_count The total count of queues for fragments, each queue has a limited size (default 20, by config::max_memory_sink_batch_count)
routine_load_task_count The total count of routine load tasks in executing
small_file_cache_count The total count of cached small files' digest info
stream_load_pipe_count The total count of stream load pipes, each pipe has a limited buffer size (default 1M)
tablet_writer_count The total count of tablet writers
brpc_endpoint_stub_count The total count of brpc endpoints
```
In the past, when we want to modify some BE configs, we have to modify be.conf and then restart BE.
This patch provides a way to modify configs in the type of 'threshold', 'interval', 'enable flag'
when BE is running without restarting it.
You can update a single config once by BE's http API: `be_host:be_http_port/api/update_config?config_name=new_value`
Earlier we introduced `BlockManager` to separate data access logic from
underlying file read and write logic.
This CL further unifies all `SegmentV2` data access to the `BlockManager`,
removes the previous `FileManager` class, and move the file cache to the `FileBlockManager`.
There are no logical changes to this CL.
After this CL, all user table data is read through the `WritableBlock` and `ReadableBlock`
returned by the `BlockManager`, and no file operations are performed directly.
Remove unused LLVM related codes of directory (step 3):be/src/exprs (#2910)
there are many LLVM related codes in code base, but these codes are not really used.
The higher version of GCC is not compatible with the LLVM 3.4.2 version currently used by Doris.
The PR delete all LLVM related code of directory: be/src/exprs
For a tablet, there may be multiple memtables, which will be
flushed to disk one by one in the order of generation.
If a memtable flush fails, then the load job will definitely
fail, but the previous implementation will overwrite `_flush_status`,
which may make the error can not be detected, leads to an error
load job to be success.
This patch also have two other changes:
1. Use `std::bind` to replace `boost::bind`;
2. Removes some unneeded headers.
Thread pool design point:
All tasks submitted directly to the thread pool enter a FIFO queue and are
dispatched to a worker thread when one becomes free. Tasks may also be
submitted via ThreadPoolTokens. The token wait() and shutdown() functions
can then be used to block on logical groups of tasks.
A token operates in one of two ExecutionModes, determined at token
construction time:
1. SERIAL: submitted tasks are run one at a time.
2. CONCURRENT: submitted tasks may be run in parallel.
This isn't unlike submitted without a token, but the logical grouping that tokens
impart can be useful when a pool is shared by many contexts (e.g. to
safely shut down one context, to derive context-specific metrics, etc.).
Tasks submitted without a token or via ExecutionMode::CONCURRENT tokens are
processed in FIFO order. On the other hand, ExecutionMode::SERIAL tokens are
processed in a round-robin fashion, one task at a time. This prevents them
from starving one another. However, tokenless (and CONCURRENT token-based)
tasks can starve SERIAL token-based tasks.
Thread design point:
1. It is a thin wrapper around pthread that can register itself with the singleton ThreadMgr
(a private class implemented in thread.cpp entirely, which tracks all live threads so
that they may be monitored via the debug webpages). This class has a limited subset of
boost::thread's API. Construction is almost the same, but clients must supply a
category and a name for each thread so that they can be identified in the debug web
UI. Otherwise, join() is the only supported method from boost::thread.
2. Each Thread object knows its operating system thread ID (TID), which can be used to
attach debuggers to specific threads, to retrieve resource-usage statistics from the
operating system, and to assign threads to resource control groups.
3. Threads are shared objects, but in a degenerate way. They may only have
up to two referents: the caller that created the thread (parent), and
the thread itself (child). Moreover, the only two methods to mutate state
(join() and the destructor) are constrained: the child may not join() on
itself, and the destructor is only run when there's one referent left.
These constraints allow us to access thread internals without any locks.
1. MonoTime/MonoDelta
MonoTime: The MonoTime represents a particular point in time, relative to some fixed but unspecified reference point.
MonoDelta: The MonoDelta class represents an elapsed duration of time, the delta between two MonoTime instances.
2. CountDownLatch
This is a C++ implementation of the Java CountDownLatch
Note that the methods in path_util are only related to path processing,
and do not involve any file and IO operations
The upcoming patch will use these util methods, used to extract operations
such as concatenation of directory strings from processing logic.
Fixes#2771
Main changes in this CL
* RoaringBitmap is renamed to BitmapValue and moved into bitmap_value.h
* leveraging Roaring64Map to support unsigned BIGINT for BITMAP type
* introduces two new format (SINGLE64 and BITMAP64) for BITMAP type
So far we have three storage format for BITMAP type
```
EMPTY := TypeCode(0x00)
SINGLE32 := TypeCode(0x01), UInt32LittleEndian
BITMAP32 := TypeCode(0x02), RoaringBitmap(defined by https://github.com/RoaringBitmap/RoaringFormatSpec/)
```
In order to support BIGINT element and keep backward compatibility, introduce two new format
```
SINGLE64 := TypeCode(0x03), UInt64LittleEndian
BITMAP64 := TypeCode(0x04), CustomRoaringBitmap64
```
Please note that SINGLE64/BITMAP64 doesn't replace SINGLE32/BITMAP32. Doris will choose the smaller (in terms of space) type automatically during serializing. For example, BITMAP32 is preferred over BITMAP64 when the maximum element is <= UINT32_MAX. This will also make BE rollback possible as long as user didn't write element larger than UINT32_MAX into bitmap column.
Another important design decision is that we fork and maintain our own version of Roaring64Map instead of using the one in "roaring/roaring64map.hh". The reasons are
1. RoaringBitmap doesn't define a standard for the binary format of 64-bits bitmap. As a result, different implementations of Roaring64Map use different format. For example the [C++ version](https://github.com/RoaringBitmap/CRoaring/blob/v0.2.60/cpp/roaring64map.hh#L545) is different from the [Java version](35104c564e/src/main/java/org/roaringbitmap/longlong/Roaring64NavigableMap.java (L1097)). Even for CRoaring, the format may change in future releases. However Doris require the serialized format to be stable across versions. Fork is a safe way to achieve this.
2. We may want to make some code changes to Roaring64Map according to our needs. For example, in order to use the BITMAP32 format when the maximum element can be represented in 32 bits, we may want to access the private member of Roaring64Map. Another example is we want to further customize and optimize the format for BITMAP64 case, such as using vint64 instead of uint64 for map size.
This CL changes:
1. add function bitmap_to_string and bitmap_from_string, which will
convert a bitmap to/from string which contains all bit in bitmap
2. add function murmur_hash3_32, which will compute murmur hash for
input strings
3. make the function cast float to string the same with user result
logic
1. upgrade gutil code from imapla to new verison， include `cpuinfo`, `spinlock` and `linux_syscall_support `
2. impliments arm version utf8 check code
3. remove incompatible code from stopwatch
This CL supports arrow's zero copy read interface, which can make code
comply with arrow 0.15.
And the schema change unit test has some problem, I disable it in run-ut.sh
1 Because we don't support array type currently, so I use variable arguments instead.
2 intersect_count directly return final count, not bitmap like bitmap_union, because intersect_count return bitmap is more complex and need more serialize. If we really need bitmap format from intersect_count, we could do that in another PR and which won't have compatibility problems.
This CL fixes the following problems
1. check whether TabletsChannel has been closed/cancelled in `reduce_mem_usage` to avoid using a closed DeltaWriter
2. make `FlushHandle.wait` wait for all submitted tasks to finish so that memtable is deallocated before its delta writer
3. make `~MemTracker()` release its consumption bytes to accommodate situations in aggregate_func.h that bitmap and hll call `MemTracker::consume` without corresponding `MemTracker::release`, which cause the consumption of root tracker never drops to zero
After replacing Arena with MemPool, we can achieve one copy for string
value read from segment v2. We can exchange MemPool's chunk between
RowBlockV2 and RowBlock. This change only replace Arena, this work will
be done in other change list.
Leverage gitattributes to enable auto convert end-of-line to LF when
checking in. Convert already exist CRLF to LF by removing all files and
checking out with new .gitattributes file. Except .gitattributes, all
files are only modified at the end of line.
Remove the default constructor for UniqueID
Add a gen_uid method in UniqueId. If need to generate a new uid, users should call this api explicitly.
Reuse boost random generator not generate a new one every time.
The current load process is:
Tablet Sink -> Tablet Channel Mgr -> Tablets Channel -> Delta Writer -> MemTable -> Flush to disk
In the path of Tablets Channel -> DeltaWriter -> MemTable -> Flush to disk, the following operations are performed:
Insert tuple into different memtables according to tablet ID
When the memtable size reaches the threshold, it is written to disk.
The above operations are equivalent to single thread execution for a single load task.
In fact, the insertion of memtable and the flush of memtable can be executed synchronously.
Perform these operation in single thread prevents the insertion of memtable from being delayed due to slow disk writing.
In the new implementation, I added a MemTableFlushExecutor class with a set of flush queues and corresponding worker threads.
By default, each data directory uses two worker threads for flush, which can be modified by the parameter flush_thread_num_per_store of BE.
DeltaWriter will push the full memtable to MemTableFlushExecutor for flush operation and generate a new memtable for receiving new data.
This design can improve the performance of load large files.
In single host testing, the time to load a 1GB text file is reduced from 48 seconds to 29 seconds.
NOTE: This patch would modify all Backend's data.
And this will cause a very long time to restart be.
So if you want to interferer your product environment,
you should upgrade backend one by one.
1. Refactoring be is to clarify the structure the codes.
2. Use unique id to indicate a rowset.
Nameing rowset with tablet_id and version will lead to
many conflicts among compaction, clone, restore.
3. Extract an rowset interface to encapsulate rowsets
with different format.
* Enhence the usabilities
1. Add metrics to monitor transactions and steaming load process in BE.
2. Modify BE config 'result_buffer_cancelled_interval_time' to 300s.
3. Modify FE config 'enable_metric_calculator' to true.
4. Add more log for tracing broker load process.
5. Modify the query report process, to cancel query immediately if some instance failed.
* Fix bugs
1. Avoid NullPointer when enabling colocation join with broker load
2. Return immediately when pull load task coordinator execution failed
