Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[improvement](routine-load) add routine load rows check #25818

Merged
merged 5 commits into from
Oct 25, 2023
Merged

[improvement](routine-load) add routine load rows check #25818

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
0f419c3
add routine load rows check
sollhui Oct 24, 2023
0513c95
Merge branch 'master' into routine_load_check
sollhui Oct 24, 2023
b13b4e8
update
sollhui Oct 24, 2023
f5d677d
update
sollhui Oct 24, 2023
bbae629
update
sollhui Oct 24, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion be/src/runtime/routine_load/data_consumer_group.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -125,9 +125,10 @@ Status KafkaDataConsumerGroup::start_all(std::shared_ptr<StreamLoadContext> ctx,
bool eos = false;
while (true) {
if (eos || left_time <= 0 || left_rows <= 0 || left_bytes <= 0) {
_rows = ctx->max_batch_rows - left_rows;
LOG(INFO) << "consumer group done: " << _grp_id
<< ". consume time(ms)=" << ctx->max_interval_s * 1000 - left_time
<< ", received rows=" << ctx->max_batch_rows - left_rows
<< ", received rows=" << _rows
<< ", received bytes=" << ctx->max_batch_size - left_bytes << ", eos: " << eos
<< ", left_time: " << left_time << ", left_rows: " << left_rows
<< ", left_bytes: " << left_bytes
Expand Down
11 changes: 10 additions & 1 deletion be/src/runtime/routine_load/data_consumer_group.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,7 +46,10 @@ class DataConsumerGroup {
typedef std::function<void(const Status&)> ConsumeFinishCallback;

DataConsumerGroup()
: _grp_id(UniqueId::gen_uid()), _thread_pool(3, 10, "data_consumer"), _counter(0) {}
: _grp_id(UniqueId::gen_uid()),
_thread_pool(3, 10, "data_consumer"),
_counter(0),
_rows(0) {}

virtual ~DataConsumerGroup() { _consumers.clear(); }

Expand All @@ -60,6 +63,10 @@ class DataConsumerGroup {
++_counter;
}

int64_t get_consumer_rows() const { return _rows; }

void set_consumer_rows(int64_t rows) { _rows = rows; }

// start all consumers
virtual Status start_all(std::shared_ptr<StreamLoadContext> ctx,
std::shared_ptr<io::KafkaConsumerPipe> kafka_pipe) {
Expand All @@ -77,6 +84,8 @@ class DataConsumerGroup {
// when the counter becomes zero, shutdown the queue to finish
std::mutex _mutex;
int _counter;
// received total rows
int64_t _rows;
sollhui marked this conversation as resolved.
Show resolved Hide resolved
};

// for kafka
Expand Down
9 changes: 9 additions & 0 deletions be/src/runtime/routine_load/routine_load_task_executor.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -355,6 +355,15 @@ void RoutineLoadTaskExecutor::exec_task(std::shared_ptr<StreamLoadContext> ctx,
// wait for all consumers finished
HANDLE_ERROR(ctx->future.get(), "consume failed");

// check received and load rows
LOG(INFO) << "routine load task received rows: " << consumer_grp.get()->get_consumer_rows()
<< " load total rows: " << ctx.get()->number_total_rows
<< " loaded rows: " << ctx.get()->number_loaded_rows
<< " filtered rows: " << ctx.get()->number_filtered_rows
<< " unselected rows: " << ctx.get()->number_unselected_rows;
DCHECK(consumer_grp.get()->get_consumer_rows() == ctx.get()->number_total_rows);
consumer_grp.get()->set_consumer_rows(0);

ctx->load_cost_millis = UnixMillis() - ctx->start_millis;

// return the consumer back to pool
Expand Down
Loading