thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-30 03:22:14 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix query cancellation in case of allow_experimental_parallel_reading_from_replicas

Browse Source 
CI found one hanged query [1], where the problem was that becase of
allow_experimental_parallel_reading_from_replicas the Cancel packet was
read by receivePartitionMergeTreeReadTaskResponseAssumeLocked() and so
the executor was not cancelled, while the code in
MergeTreeBaseSelectProcessor was not ready for this:

<details>

    {
        "is_initial_query": 0,
        "elapsed": 1727.714379573,
        "is_cancelled": 0,
        "read_rows": "196577",
        "read_bytes": "1179462",
        "written_rows": "0",
        "written_bytes": "0",
        "query": "SELECT `CounterID`, `EventDate` FROM `test`.`hits` ORDER BY `CounterID` DESC, `EventDate` ASC LIMIT 50",
        ...
     }

In logs:

    2021.12.31 12:11:55.384735 [ 101532 ] {7e5f551e-5960-4fda-9447-9bfdae4660c1} <Debug> executeQuery: (from [::ffff:127.0.0.1]:58094, initial_query_id: e2966ca5-e836-44ef-8f8e-d1c1b32a>
    2021.12.31 12:11:55.454379 [ 101532 ] {7e5f551e-5960-4fda-9447-9bfdae4660c1} <Trace> ContextAccess (default): Access granted: SELECT(EventDate, CounterID) ON test.hits
    2021.12.31 12:11:55.457583 [ 101532 ] {7e5f551e-5960-4fda-9447-9bfdae4660c1} <Trace> datasets.hits_v1: Parallel reading from replicas enabled true
    2021.12.31 12:11:55.459739 [ 101532 ] {7e5f551e-5960-4fda-9447-9bfdae4660c1} <Trace> InterpreterSelectQuery: FetchColumns -> WithMergeableStateAfterAggregationAndLimit
    2021.12.31 12:11:55.471048 [ 101532 ] {7e5f551e-5960-4fda-9447-9bfdae4660c1} <Debug> datasets.hits_v1 (SelectExecutor): Key condition: unknown
    2021.12.31 12:11:55.476514 [ 101532 ] {7e5f551e-5960-4fda-9447-9bfdae4660c1} <Debug> datasets.hits_v1 (SelectExecutor): MinMax index condition: unknown
    2021.12.31 12:11:55.488302 [ 101532 ] {7e5f551e-5960-4fda-9447-9bfdae4660c1} <Debug> datasets.hits_v1 (SelectExecutor): Selected 2/2 parts by partition key, 2 parts by primary key, >
    2021.12.31 12:11:55.494020 [ 101532 ] {7e5f551e-5960-4fda-9447-9bfdae4660c1} <Debug> MergeTreeReverseSelectProcessor: Reading 1 ranges in reverse order from part 201403_20_20_0, app>
    2021.12.31 12:11:55.497644 [ 101532 ] {7e5f551e-5960-4fda-9447-9bfdae4660c1} <Debug> MergeTreeReverseSelectProcessor: Reading 138 ranges in reverse order from part 201403_19_19_2, a>
    2021.12.31 12:11:55.536372 [ 170601 ] {7e5f551e-5960-4fda-9447-9bfdae4660c1} <Test> MergeTreeBaseSelectProcessor: Reading from Compact part, average mark size is 83886080
    2021.12.31 12:11:55.558783 [ 171701 ] {7e5f551e-5960-4fda-9447-9bfdae4660c1} <Test> MergeTreeBaseSelectProcessor: Reading from Wide part, average mark size is 3069
    2021.12.31 12:11:55.563960 [ 171701 ] {7e5f551e-5960-4fda-9447-9bfdae4660c1} <Test> MergeTreeBaseSelectProcessor: Reading from Wide part, average mark size is 3069
    2021.12.31 12:11:55.577512 [ 171701 ] {7e5f551e-5960-4fda-9447-9bfdae4660c1} <Test> MergeTreeBaseSelectProcessor: Reading from Wide part, average mark size is 3069
    2021.12.31 12:11:55.585660 [ 171701 ] {7e5f551e-5960-4fda-9447-9bfdae4660c1} <Test> MergeTreeBaseSelectProcessor: Reading from Wide part, average mark size is 3069
    2021.12.31 12:11:55.613694 [ 170601 ] {7e5f551e-5960-4fda-9447-9bfdae4660c1} <Test> MergeTreeBaseSelectProcessor: Reading from Wide part, average mark size is 3069
    2021.12.31 12:11:55.730597 [ 170601 ] {7e5f551e-5960-4fda-9447-9bfdae4660c1} <Test> MergeTreeBaseSelectProcessor: Reading from Wide part, average mark size is 3069
    2021.12.31 12:11:55.743554 [ 171701 ] {7e5f551e-5960-4fda-9447-9bfdae4660c1} <Debug> MergingSortedTransform: Merge sorted 3 blocks, 65567 rows in 0.243999671 sec., 268717.5754429603>
    2021.12.31 12:11:55.744196 [ 170601 ] {7e5f551e-5960-4fda-9447-9bfdae4660c1} <Test> MergeTreeBaseSelectProcessor: Reading from Wide part, average mark size is 3069
    2021.12.31 12:11:55.890923 [ 170601 ] {7e5f551e-5960-4fda-9447-9bfdae4660c1} <Test> MergeTreeBaseSelectProcessor: Reading from Wide part, average mark size is 3069
    2021.12.31 12:11:55.891222 [ 170601 ] {7e5f551e-5960-4fda-9447-9bfdae4660c1} <Test> MergeTreeBaseSelectProcessor: Reading from Wide part, average mark size is 3069

</details>

  [1]: https://s3.amazonaws.com/clickhouse-test-reports/33341/0685fd99855bacd0bce02507c00a3bd7709eea61/stress_test__address__actions_.html
This commit is contained in:
Azat Khuzhin 2022-01-07 19:33:03 +03:00
parent e8c7e5e8f0
commit 28e64020bd
1 changed files with 15 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
src/Storages/MergeTree/MergeTreeBaseSelectProcessor.cpp
View File

@ -22,6 +22,7 @@ namespace ErrorCodes
{ {
extern const int ILLEGAL_TYPE_OF_COLUMN_FOR_FILTER; extern const int ILLEGAL_TYPE_OF_COLUMN_FOR_FILTER;
extern const int LOGICAL_ERROR; extern const int LOGICAL_ERROR;
extern const int QUERY_WAS_CANCELLED;
} }
@ -131,8 +132,9 @@ bool MergeTreeBaseSelectProcessor::getTaskFromBuffer()
if (Status::Accepted == res) if (Status::Accepted == res)
return true; return true;
/// To avoid any possibility of ignoring cancellation, exception will be thrown.
if (Status::Cancelled == res) if (Status::Cancelled == res)
break; throw Exception(ErrorCodes::QUERY_WAS_CANCELLED, "Query had been cancelled");
} }
return false; return false;
} }
@ -164,9 +166,19 @@ bool MergeTreeBaseSelectProcessor::getDelayedTasks()
Chunk MergeTreeBaseSelectProcessor::generate() Chunk MergeTreeBaseSelectProcessor::generate()
{ {
while (!isCancelled()) while (!isCancelled())
{
try
{ {
if ((!task || task->isFinished()) && !getNewTask()) if ((!task || task->isFinished()) && !getNewTask())
return {}; return {};
}
catch (const Exception & e)
{
/// See MergeTreeBaseSelectProcessor::getTaskFromBuffer()
if (e.code() == ErrorCodes::QUERY_WAS_CANCELLED)
return {};
throw;
}
auto res = readFromPart(); auto res = readFromPart();