mirror of
https://github.com/ClickHouse/ClickHouse.git
synced 2024-09-19 16:20:50 +00:00
Merge branch 'master' into keeper-some-improvement2
This commit is contained in:
Antonio Andelic
commit
5a86371b02
2
contrib/curl
vendored
2
contrib/curl
vendored
@ -1 +1 @@
|
||||
Subproject commit de7b3e89218467159a7af72d58cea8425946e97d
|
||||
Subproject commit 83bedbd730d62b83744cc26fa0433d3f6e2e4cd6
|
||||
@ -34,7 +34,7 @@ RUN arch=${TARGETARCH:-amd64} \
|
||||
# lts / testing / prestable / etc
|
||||
ARG REPO_CHANNEL="stable"
|
||||
ARG REPOSITORY="https://packages.clickhouse.com/tgz/${REPO_CHANNEL}"
|
||||
ARG VERSION="24.8.3.59"
|
||||
ARG VERSION="24.8.4.13"
|
||||
ARG PACKAGES="clickhouse-keeper"
|
||||
ARG DIRECT_DOWNLOAD_URLS=""
|
||||
|
||||
|
||||
@ -32,7 +32,7 @@ RUN arch=${TARGETARCH:-amd64} \
|
||||
# lts / testing / prestable / etc
|
||||
ARG REPO_CHANNEL="stable"
|
||||
ARG REPOSITORY="https://packages.clickhouse.com/tgz/${REPO_CHANNEL}"
|
||||
ARG VERSION="24.8.3.59"
|
||||
ARG VERSION="24.8.4.13"
|
||||
ARG PACKAGES="clickhouse-client clickhouse-server clickhouse-common-static"
|
||||
ARG DIRECT_DOWNLOAD_URLS=""
|
||||
|
||||
|
||||
@ -28,7 +28,7 @@ RUN sed -i "s|http://archive.ubuntu.com|${apt_archive}|g" /etc/apt/sources.list
|
||||
|
||||
ARG REPO_CHANNEL="stable"
|
||||
ARG REPOSITORY="deb [signed-by=/usr/share/keyrings/clickhouse-keyring.gpg] https://packages.clickhouse.com/deb ${REPO_CHANNEL} main"
|
||||
ARG VERSION="24.8.3.59"
|
||||
ARG VERSION="24.8.4.13"
|
||||
ARG PACKAGES="clickhouse-client clickhouse-server clickhouse-common-static"
|
||||
|
||||
#docker-official-library:off
|
||||
|
||||
17
docs/changelogs/v24.3.11.7-lts.md
Normal file
17
docs/changelogs/v24.3.11.7-lts.md
Normal file
@ -0,0 +1,17 @@
|
||||
---
|
||||
sidebar_position: 1
|
||||
sidebar_label: 2024
|
||||
---
|
||||
|
||||
# 2024 Changelog
|
||||
|
||||
### ClickHouse release v24.3.11.7-lts (28795d0a47e) FIXME as compared to v24.3.10.33-lts (37b6502ebf0)
|
||||
|
||||
#### Bug Fix (user-visible misbehavior in an official stable release)
|
||||
* Backported in [#67479](https://github.com/ClickHouse/ClickHouse/issues/67479): In rare cases ClickHouse could consider parts as broken because of some unexpected projections on disk. Now it's fixed. [#66898](https://github.com/ClickHouse/ClickHouse/pull/66898) ([alesapin](https://github.com/alesapin)).
|
||||
* Backported in [#69243](https://github.com/ClickHouse/ClickHouse/issues/69243): `UNION` clause in subqueries wasn't handled correctly in queries with parallel replicas and lead to LOGICAL_ERROR `Duplicate announcement received for replica`. [#69146](https://github.com/ClickHouse/ClickHouse/pull/69146) ([Igor Nikonov](https://github.com/devcrafter)).
|
||||
|
||||
#### NOT FOR CHANGELOG / INSIGNIFICANT
|
||||
|
||||
* Backported in [#69221](https://github.com/ClickHouse/ClickHouse/issues/69221): Disable memory test with sanitizer. [#69193](https://github.com/ClickHouse/ClickHouse/pull/69193) ([alesapin](https://github.com/alesapin)).
|
||||
|
||||
18
docs/changelogs/v24.5.8.10-stable.md
Normal file
18
docs/changelogs/v24.5.8.10-stable.md
Normal file
@ -0,0 +1,18 @@
|
||||
---
|
||||
sidebar_position: 1
|
||||
sidebar_label: 2024
|
||||
---
|
||||
|
||||
# 2024 Changelog
|
||||
|
||||
### ClickHouse release v24.5.8.10-stable (f11729638ea) FIXME as compared to v24.5.7.31-stable (6c185e9aec1)
|
||||
|
||||
#### Bug Fix (user-visible misbehavior in an official stable release)
|
||||
* Backported in [#69295](https://github.com/ClickHouse/ClickHouse/issues/69295): TODO. [#68744](https://github.com/ClickHouse/ClickHouse/pull/68744) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
|
||||
* Backported in [#69245](https://github.com/ClickHouse/ClickHouse/issues/69245): `UNION` clause in subqueries wasn't handled correctly in queries with parallel replicas and lead to LOGICAL_ERROR `Duplicate announcement received for replica`. [#69146](https://github.com/ClickHouse/ClickHouse/pull/69146) ([Igor Nikonov](https://github.com/devcrafter)).
|
||||
* Fix crash when using `s3` table function with GLOB paths and filters. [#69176](https://github.com/ClickHouse/ClickHouse/pull/69176) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
|
||||
|
||||
#### NOT FOR CHANGELOG / INSIGNIFICANT
|
||||
|
||||
* Backported in [#69223](https://github.com/ClickHouse/ClickHouse/issues/69223): Disable memory test with sanitizer. [#69193](https://github.com/ClickHouse/ClickHouse/pull/69193) ([alesapin](https://github.com/alesapin)).
|
||||
|
||||
16
docs/changelogs/v24.6.6.6-stable.md
Normal file
16
docs/changelogs/v24.6.6.6-stable.md
Normal file
@ -0,0 +1,16 @@
|
||||
---
|
||||
sidebar_position: 1
|
||||
sidebar_label: 2024
|
||||
---
|
||||
|
||||
# 2024 Changelog
|
||||
|
||||
### ClickHouse release v24.6.6.6-stable (a4c4580e639) FIXME as compared to v24.6.5.30-stable (e6e196c92d6)
|
||||
|
||||
#### Bug Fix (user-visible misbehavior in an official stable release)
|
||||
* Backported in [#69197](https://github.com/ClickHouse/ClickHouse/issues/69197): TODO. [#68744](https://github.com/ClickHouse/ClickHouse/pull/68744) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
|
||||
|
||||
#### NOT FOR CHANGELOG / INSIGNIFICANT
|
||||
|
||||
* Backported in [#69225](https://github.com/ClickHouse/ClickHouse/issues/69225): Disable memory test with sanitizer. [#69193](https://github.com/ClickHouse/ClickHouse/pull/69193) ([alesapin](https://github.com/alesapin)).
|
||||
|
||||
17
docs/changelogs/v24.7.6.8-stable.md
Normal file
17
docs/changelogs/v24.7.6.8-stable.md
Normal file
@ -0,0 +1,17 @@
|
||||
---
|
||||
sidebar_position: 1
|
||||
sidebar_label: 2024
|
||||
---
|
||||
|
||||
# 2024 Changelog
|
||||
|
||||
### ClickHouse release v24.7.6.8-stable (7779883593a) FIXME as compared to v24.7.5.37-stable (f2533ca97be)
|
||||
|
||||
#### Bug Fix (user-visible misbehavior in an official stable release)
|
||||
* Backported in [#69198](https://github.com/ClickHouse/ClickHouse/issues/69198): TODO. [#68744](https://github.com/ClickHouse/ClickHouse/pull/68744) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
|
||||
* Backported in [#69249](https://github.com/ClickHouse/ClickHouse/issues/69249): `UNION` clause in subqueries wasn't handled correctly in queries with parallel replicas and lead to LOGICAL_ERROR `Duplicate announcement received for replica`. [#69146](https://github.com/ClickHouse/ClickHouse/pull/69146) ([Igor Nikonov](https://github.com/devcrafter)).
|
||||
|
||||
#### NOT FOR CHANGELOG / INSIGNIFICANT
|
||||
|
||||
* Backported in [#69227](https://github.com/ClickHouse/ClickHouse/issues/69227): Disable memory test with sanitizer. [#69193](https://github.com/ClickHouse/ClickHouse/pull/69193) ([alesapin](https://github.com/alesapin)).
|
||||
|
||||
22
docs/changelogs/v24.8.4.13-lts.md
Normal file
22
docs/changelogs/v24.8.4.13-lts.md
Normal file
@ -0,0 +1,22 @@
|
||||
---
|
||||
sidebar_position: 1
|
||||
sidebar_label: 2024
|
||||
---
|
||||
|
||||
# 2024 Changelog
|
||||
|
||||
### ClickHouse release v24.8.4.13-lts (53195bc189b) FIXME as compared to v24.8.3.59-lts (e729b9fa40e)
|
||||
|
||||
#### Improvement
|
||||
* Backported in [#68699](https://github.com/ClickHouse/ClickHouse/issues/68699): Delete old code of named collections from dictionaries and substitute it to the new, which allows to use DDL created named collections in dictionaries. Closes [#60936](https://github.com/ClickHouse/ClickHouse/issues/60936), closes [#36890](https://github.com/ClickHouse/ClickHouse/issues/36890). [#68412](https://github.com/ClickHouse/ClickHouse/pull/68412) ([Kseniia Sumarokova](https://github.com/kssenii)).
|
||||
|
||||
#### Bug Fix (user-visible misbehavior in an official stable release)
|
||||
* Backported in [#69231](https://github.com/ClickHouse/ClickHouse/issues/69231): Fix parsing error when null should be inserted as default in some cases during JSON type parsing. [#68955](https://github.com/ClickHouse/ClickHouse/pull/68955) ([Kruglov Pavel](https://github.com/Avogar)).
|
||||
* Backported in [#69251](https://github.com/ClickHouse/ClickHouse/issues/69251): `UNION` clause in subqueries wasn't handled correctly in queries with parallel replicas and lead to LOGICAL_ERROR `Duplicate announcement received for replica`. [#69146](https://github.com/ClickHouse/ClickHouse/pull/69146) ([Igor Nikonov](https://github.com/devcrafter)).
|
||||
|
||||
#### NOT FOR CHANGELOG / INSIGNIFICANT
|
||||
|
||||
* Backported in [#69189](https://github.com/ClickHouse/ClickHouse/issues/69189): Don't create Object type if use_json_alias_for_old_object_type=1 but allow_experimental_object_type=0. [#69150](https://github.com/ClickHouse/ClickHouse/pull/69150) ([Kruglov Pavel](https://github.com/Avogar)).
|
||||
* Backported in [#69229](https://github.com/ClickHouse/ClickHouse/issues/69229): Disable memory test with sanitizer. [#69193](https://github.com/ClickHouse/ClickHouse/pull/69193) ([alesapin](https://github.com/alesapin)).
|
||||
* Backported in [#69219](https://github.com/ClickHouse/ClickHouse/issues/69219): Disable perf-like test with sanitizers. [#69194](https://github.com/ClickHouse/ClickHouse/pull/69194) ([alesapin](https://github.com/alesapin)).
|
||||
|
||||
@ -989,7 +989,11 @@ ALTER TABLE tab DROP STATISTICS a;
|
||||
These lightweight statistics aggregate information about distribution of values in columns. Statistics are stored in every part and updated when every insert comes.
|
||||
They can be used for prewhere optimization only if we enable `set allow_statistics_optimize = 1`.
|
||||
|
||||
#### Available Types of Column Statistics {#available-types-of-column-statistics}
|
||||
### Available Types of Column Statistics {#available-types-of-column-statistics}
|
||||
|
||||
- `MinMax`
|
||||
|
||||
The minimum and maximum column value which allows to estimate the selectivity of range filters on numeric columns.
|
||||
|
||||
- `TDigest`
|
||||
|
||||
@ -1003,6 +1007,27 @@ They can be used for prewhere optimization only if we enable `set allow_statisti
|
||||
|
||||
[Count-min](https://en.wikipedia.org/wiki/Count%E2%80%93min_sketch) sketches which provide an approximate count of the frequency of each value in a column.
|
||||
|
||||
|
||||
### Supported Data Types {#supported-data-types}
|
||||
|
||||
| | (U)Int* | Float* | Decimal(*) | Date* | Boolean | Enum* | (Fixed)String |
|
||||
|-----------|---------|--------|------------|-------|---------|-------|------------------|
|
||||
| count_min | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ |
|
||||
| MinMax | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✗ |
|
||||
| TDigest | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✗ |
|
||||
| Uniq | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ |
|
||||
|
||||
|
||||
### Supported Operations {#supported-operations}
|
||||
|
||||
| | Equality filters (==) | Range filters (>, >=, <, <=) |
|
||||
|-----------|-----------------------|------------------------------|
|
||||
| count_min | ✔ | ✗ |
|
||||
| MinMax | ✗ | ✔ |
|
||||
| TDigest | ✗ | ✔ |
|
||||
| Uniq | ✔ | ✗ |
|
||||
|
||||
|
||||
## Column-level Settings {#column-level-settings}
|
||||
|
||||
Certain MergeTree settings can be overridden at column level:
|
||||
|
||||
@ -1896,6 +1896,21 @@ void ClientBase::processParsedSingleQuery(const String & full_query, const Strin
|
||||
/// Temporarily apply query settings to context.
|
||||
std::optional<Settings> old_settings;
|
||||
SCOPE_EXIT_SAFE({
|
||||
try
|
||||
{
|
||||
/// We need to park ParallelFormating threads,
|
||||
/// because they can use settings from global context
|
||||
/// and it can lead to data race with `setSettings`
|
||||
resetOutput();
|
||||
}
|
||||
catch (...)
|
||||
{
|
||||
if (!have_error)
|
||||
{
|
||||
client_exception = std::make_unique<Exception>(getCurrentExceptionMessageAndPattern(print_stack_trace), getCurrentExceptionCode());
|
||||
have_error = true;
|
||||
}
|
||||
}
|
||||
if (old_settings)
|
||||
client_context->setSettings(*old_settings);
|
||||
});
|
||||
|
||||
@ -781,14 +781,14 @@ InterpreterCreateQuery::TableProperties InterpreterCreateQuery::getTableProperti
|
||||
|
||||
const auto & settings = getContext()->getSettingsRef();
|
||||
if (index_desc.type == FULL_TEXT_INDEX_NAME && !settings.allow_experimental_full_text_index)
|
||||
throw Exception(ErrorCodes::SUPPORT_IS_DISABLED, "Experimental full-text index feature is not enabled (the setting 'allow_experimental_full_text_index')");
|
||||
throw Exception(ErrorCodes::SUPPORT_IS_DISABLED, "Experimental full-text index feature is disabled. Turn on setting 'allow_experimental_full_text_index'");
|
||||
/// ----
|
||||
/// Temporary check during a transition period. Please remove at the end of 2024.
|
||||
if (index_desc.type == INVERTED_INDEX_NAME && !settings.allow_experimental_inverted_index)
|
||||
throw Exception(ErrorCodes::ILLEGAL_INDEX, "Please use index type 'full_text' instead of 'inverted'");
|
||||
/// ----
|
||||
if (index_desc.type == "vector_similarity" && !settings.allow_experimental_vector_similarity_index)
|
||||
throw Exception(ErrorCodes::INCORRECT_QUERY, "Vector similarity index is disabled. Turn on allow_experimental_vector_similarity_index");
|
||||
throw Exception(ErrorCodes::SUPPORT_IS_DISABLED, "Experimental vector similarity index is disabled. Turn on setting 'allow_experimental_vector_similarity_index'");
|
||||
|
||||
properties.indices.push_back(index_desc);
|
||||
}
|
||||
|
||||
@ -198,6 +198,7 @@ FiltersForTableExpressionMap collectFiltersForAnalysis(const QueryTreeNodePtr &
|
||||
auto & result_query_plan = planner.getQueryPlan();
|
||||
|
||||
auto optimization_settings = QueryPlanOptimizationSettings::fromContext(query_context);
|
||||
optimization_settings.build_sets = false; // no need to build sets to collect filters
|
||||
result_query_plan.optimize(optimization_settings);
|
||||
|
||||
FiltersForTableExpressionMap res;
|
||||
|
||||
@ -16,7 +16,7 @@ void optimizeTreeFirstPass(const QueryPlanOptimizationSettings & settings, Query
|
||||
void optimizeTreeSecondPass(const QueryPlanOptimizationSettings & optimization_settings, QueryPlan::Node & root, QueryPlan::Nodes & nodes);
|
||||
/// Third pass is used to apply filters such as key conditions and skip indexes to the storages that support them.
|
||||
/// After that it add CreateSetsStep for the subqueries that has not be used in the filters.
|
||||
void optimizeTreeThirdPass(QueryPlan & plan, QueryPlan::Node & root, QueryPlan::Nodes & nodes);
|
||||
void addStepsToBuildSets(QueryPlan & plan, QueryPlan::Node & root, QueryPlan::Nodes & nodes);
|
||||
|
||||
/// Optimization (first pass) is a function applied to QueryPlan::Node.
|
||||
/// It can read and update subtree of specified node.
|
||||
|
||||
@ -75,6 +75,8 @@ struct QueryPlanOptimizationSettings
|
||||
String force_projection_name;
|
||||
bool optimize_use_implicit_projections = false;
|
||||
|
||||
bool build_sets = true;
|
||||
|
||||
static QueryPlanOptimizationSettings fromSettings(const Settings & from);
|
||||
static QueryPlanOptimizationSettings fromContext(ContextPtr from);
|
||||
};
|
||||
|
||||
@ -216,7 +216,7 @@ void optimizeTreeSecondPass(const QueryPlanOptimizationSettings & optimization_s
|
||||
optimization_settings.force_projection_name);
|
||||
}
|
||||
|
||||
void optimizeTreeThirdPass(QueryPlan & plan, QueryPlan::Node & root, QueryPlan::Nodes & nodes)
|
||||
void addStepsToBuildSets(QueryPlan & plan, QueryPlan::Node & root, QueryPlan::Nodes & nodes)
|
||||
{
|
||||
Stack stack;
|
||||
stack.push_back({.node = &root});
|
||||
|
||||
@ -504,7 +504,8 @@ void QueryPlan::optimize(const QueryPlanOptimizationSettings & optimization_sett
|
||||
|
||||
QueryPlanOptimizations::optimizeTreeFirstPass(optimization_settings, *root, nodes);
|
||||
QueryPlanOptimizations::optimizeTreeSecondPass(optimization_settings, *root, nodes);
|
||||
QueryPlanOptimizations::optimizeTreeThirdPass(*this, *root, nodes);
|
||||
if (optimization_settings.build_sets)
|
||||
QueryPlanOptimizations::addStepsToBuildSets(*this, *root, nodes);
|
||||
|
||||
updateDataStreams(*root);
|
||||
}
|
||||
|
||||
@ -1142,6 +1142,16 @@ bool AlterCommands::hasFullTextIndex(const StorageInMemoryMetadata & metadata)
|
||||
return false;
|
||||
}
|
||||
|
||||
bool AlterCommands::hasVectorSimilarityIndex(const StorageInMemoryMetadata & metadata)
|
||||
{
|
||||
for (const auto & index : metadata.secondary_indices)
|
||||
{
|
||||
if (index.type == "vector_similarity")
|
||||
return true;
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
void AlterCommands::apply(StorageInMemoryMetadata & metadata, ContextPtr context) const
|
||||
{
|
||||
if (!prepared)
|
||||
|
||||
@ -237,6 +237,9 @@ public:
|
||||
|
||||
/// Check if commands have any full-text index
|
||||
static bool hasFullTextIndex(const StorageInMemoryMetadata & metadata);
|
||||
|
||||
/// Check if commands have any vector similarity index
|
||||
static bool hasVectorSimilarityIndex(const StorageInMemoryMetadata & metadata);
|
||||
};
|
||||
|
||||
}
|
||||
|
||||
@ -3230,6 +3230,10 @@ void MergeTreeData::checkAlterIsPossible(const AlterCommands & commands, Context
|
||||
throw Exception(ErrorCodes::SUPPORT_IS_DISABLED,
|
||||
"Experimental full-text index feature is not enabled (turn on setting 'allow_experimental_full_text_index')");
|
||||
|
||||
if (AlterCommands::hasVectorSimilarityIndex(new_metadata) && !settings.allow_experimental_vector_similarity_index)
|
||||
throw Exception(ErrorCodes::SUPPORT_IS_DISABLED,
|
||||
"Experimental vector similarity index is disabled (turn on setting 'allow_experimental_vector_similarity_index')");
|
||||
|
||||
for (const auto & disk : getDisks())
|
||||
if (!disk->supportsHardLinks() && !commands.isSettingsAlter() && !commands.isCommentAlter())
|
||||
throw Exception(
|
||||
|
||||
@ -195,7 +195,7 @@ void MergeTreeIndexGranuleVectorSimilarity::serializeBinary(WriteBuffer & ostr)
|
||||
LOG_TRACE(logger, "Start writing vector similarity index");
|
||||
|
||||
if (empty())
|
||||
throw Exception(ErrorCodes::LOGICAL_ERROR, "Attempt to write empty minmax index {}", backQuote(index_name));
|
||||
throw Exception(ErrorCodes::LOGICAL_ERROR, "Attempt to write empty vector similarity index {}", backQuote(index_name));
|
||||
|
||||
writeIntBinary(FILE_FORMAT_VERSION, ostr);
|
||||
|
||||
|
||||
@ -40,10 +40,12 @@ void extractReferenceVectorFromLiteral(std::vector<Float64> & reference_vector,
|
||||
}
|
||||
}
|
||||
|
||||
VectorSimilarityCondition::Info::DistanceFunction stringToDistanceFunction(std::string_view distance_function)
|
||||
VectorSimilarityCondition::Info::DistanceFunction stringToDistanceFunction(const String & distance_function)
|
||||
{
|
||||
if (distance_function == "L2Distance")
|
||||
return VectorSimilarityCondition::Info::DistanceFunction::L2;
|
||||
else if (distance_function == "cosineDistance")
|
||||
return VectorSimilarityCondition::Info::DistanceFunction::Cosine;
|
||||
else
|
||||
return VectorSimilarityCondition::Info::DistanceFunction::Unknown;
|
||||
}
|
||||
@ -57,7 +59,7 @@ VectorSimilarityCondition::VectorSimilarityCondition(const SelectQueryInfo & que
|
||||
, index_is_useful(checkQueryStructure(query_info))
|
||||
{}
|
||||
|
||||
bool VectorSimilarityCondition::alwaysUnknownOrTrue(String distance_function) const
|
||||
bool VectorSimilarityCondition::alwaysUnknownOrTrue(const String & distance_function) const
|
||||
{
|
||||
if (!index_is_useful)
|
||||
return true; /// query isn't supported
|
||||
|
||||
@ -57,7 +57,8 @@ public:
|
||||
enum class DistanceFunction : uint8_t
|
||||
{
|
||||
Unknown,
|
||||
L2
|
||||
L2,
|
||||
Cosine
|
||||
};
|
||||
|
||||
std::vector<Float64> reference_vector;
|
||||
@ -68,7 +69,7 @@ public:
|
||||
};
|
||||
|
||||
/// Returns false if query can be speeded up by an ANN index, true otherwise.
|
||||
bool alwaysUnknownOrTrue(String distance_function) const;
|
||||
bool alwaysUnknownOrTrue(const String & distance_function) const;
|
||||
|
||||
std::vector<Float64> getReferenceVector() const;
|
||||
size_t getDimensions() const;
|
||||
@ -141,18 +142,12 @@ private:
|
||||
/// Traverses the AST of ORDERBY section
|
||||
void traverseOrderByAST(const ASTPtr & node, RPN & rpn);
|
||||
|
||||
/// Returns true and stores ANNExpr if the query has valid WHERE section
|
||||
static bool matchRPNWhere(RPN & rpn, Info & info);
|
||||
|
||||
/// Returns true and stores ANNExpr if the query has valid ORDERBY section
|
||||
static bool matchRPNOrderBy(RPN & rpn, Info & info);
|
||||
|
||||
/// Returns true and stores Length if we have valid LIMIT clause in query
|
||||
static bool matchRPNLimit(RPNElement & rpn, UInt64 & limit);
|
||||
|
||||
/// Matches dist function, reference vector, column name
|
||||
static bool matchMainParts(RPN::iterator & iter, const RPN::iterator & end, Info & info);
|
||||
|
||||
/// Gets float or int from AST node
|
||||
static float getFloatOrIntLiteralOrPanic(const RPN::iterator& iter);
|
||||
|
||||
|
||||
@ -9,6 +9,7 @@
|
||||
#include <Storages/ColumnsDescription.h>
|
||||
#include <Storages/Statistics/ConditionSelectivityEstimator.h>
|
||||
#include <Storages/Statistics/StatisticsCountMinSketch.h>
|
||||
#include <Storages/Statistics/StatisticsMinMax.h>
|
||||
#include <Storages/Statistics/StatisticsTDigest.h>
|
||||
#include <Storages/Statistics/StatisticsUniq.h>
|
||||
#include <Storages/StatisticsDescription.h>
|
||||
@ -101,6 +102,8 @@ Float64 ColumnStatistics::estimateLess(const Field & val) const
|
||||
{
|
||||
if (stats.contains(StatisticsType::TDigest))
|
||||
return stats.at(StatisticsType::TDigest)->estimateLess(val);
|
||||
if (stats.contains(StatisticsType::MinMax))
|
||||
return stats.at(StatisticsType::MinMax)->estimateLess(val);
|
||||
return rows * ConditionSelectivityEstimator::default_cond_range_factor;
|
||||
}
|
||||
|
||||
@ -121,6 +124,14 @@ Float64 ColumnStatistics::estimateEqual(const Field & val) const
|
||||
if (stats.contains(StatisticsType::CountMinSketch))
|
||||
return stats.at(StatisticsType::CountMinSketch)->estimateEqual(val);
|
||||
#endif
|
||||
if (stats.contains(StatisticsType::Uniq))
|
||||
{
|
||||
UInt64 cardinality = stats.at(StatisticsType::Uniq)->estimateCardinality();
|
||||
if (cardinality == 0 || rows == 0)
|
||||
return 0;
|
||||
return 1.0 / cardinality * rows; /// assume uniform distribution
|
||||
}
|
||||
|
||||
return rows * ConditionSelectivityEstimator::default_cond_equal_factor;
|
||||
}
|
||||
|
||||
@ -198,6 +209,9 @@ void MergeTreeStatisticsFactory::registerValidator(StatisticsType stats_type, Va
|
||||
|
||||
MergeTreeStatisticsFactory::MergeTreeStatisticsFactory()
|
||||
{
|
||||
registerValidator(StatisticsType::MinMax, minMaxStatisticsValidator);
|
||||
registerCreator(StatisticsType::MinMax, minMaxStatisticsCreator);
|
||||
|
||||
registerValidator(StatisticsType::TDigest, tdigestStatisticsValidator);
|
||||
registerCreator(StatisticsType::TDigest, tdigestStatisticsCreator);
|
||||
|
||||
@ -234,7 +248,7 @@ ColumnStatisticsPtr MergeTreeStatisticsFactory::get(const ColumnDescription & co
|
||||
{
|
||||
auto it = creators.find(type);
|
||||
if (it == creators.end())
|
||||
throw Exception(ErrorCodes::INCORRECT_QUERY, "Unknown statistic type '{}'. Available types: 'tdigest' 'uniq' and 'count_min'", type);
|
||||
throw Exception(ErrorCodes::INCORRECT_QUERY, "Unknown statistic type '{}'. Available types: 'count_min', 'minmax', 'tdigest' and 'uniq'", type);
|
||||
auto stat_ptr = (it->second)(desc, column_desc.type);
|
||||
column_stat->stats[type] = stat_ptr;
|
||||
}
|
||||
|
||||
@ -1,4 +1,3 @@
|
||||
|
||||
#include <Storages/Statistics/StatisticsCountMinSketch.h>
|
||||
#include <DataTypes/DataTypeLowCardinality.h>
|
||||
#include <DataTypes/DataTypeNullable.h>
|
||||
|
||||
86
src/Storages/Statistics/StatisticsMinMax.cpp
Normal file
86
src/Storages/Statistics/StatisticsMinMax.cpp
Normal file
@ -0,0 +1,86 @@
|
||||
#include <Storages/Statistics/StatisticsMinMax.h>
|
||||
#include <DataTypes/DataTypeLowCardinality.h>
|
||||
#include <DataTypes/DataTypeNullable.h>
|
||||
#include <IO/ReadHelpers.h>
|
||||
#include <IO/WriteHelpers.h>
|
||||
|
||||
#include <algorithm>
|
||||
|
||||
|
||||
namespace DB
|
||||
{
|
||||
|
||||
namespace ErrorCodes
|
||||
{
|
||||
extern const int ILLEGAL_STATISTICS;
|
||||
}
|
||||
|
||||
StatisticsMinMax::StatisticsMinMax(const SingleStatisticsDescription & description, const DataTypePtr & data_type_)
|
||||
: IStatistics(description)
|
||||
, data_type(data_type_)
|
||||
{
|
||||
}
|
||||
|
||||
void StatisticsMinMax::update(const ColumnPtr & column)
|
||||
{
|
||||
for (size_t row = 0; row < column->size(); ++row)
|
||||
{
|
||||
if (column->isNullAt(row))
|
||||
continue;
|
||||
|
||||
auto value = column->getFloat64(row);
|
||||
min = std::min(value, min);
|
||||
max = std::max(value, max);
|
||||
}
|
||||
row_count += column->size();
|
||||
}
|
||||
|
||||
void StatisticsMinMax::serialize(WriteBuffer & buf)
|
||||
{
|
||||
writeIntBinary(row_count, buf);
|
||||
writeFloatBinary(min, buf);
|
||||
writeFloatBinary(max, buf);
|
||||
}
|
||||
|
||||
void StatisticsMinMax::deserialize(ReadBuffer & buf)
|
||||
{
|
||||
readIntBinary(row_count, buf);
|
||||
readFloatBinary(min, buf);
|
||||
readFloatBinary(max, buf);
|
||||
}
|
||||
|
||||
Float64 StatisticsMinMax::estimateLess(const Field & val) const
|
||||
{
|
||||
if (row_count == 0)
|
||||
return 0;
|
||||
|
||||
auto val_as_float = StatisticsUtils::tryConvertToFloat64(val, data_type);
|
||||
if (!val_as_float.has_value())
|
||||
return 0;
|
||||
|
||||
if (val_as_float < min)
|
||||
return 0;
|
||||
|
||||
if (val_as_float > max)
|
||||
return row_count;
|
||||
|
||||
if (min == max)
|
||||
return (val_as_float != max) ? 0 : row_count;
|
||||
|
||||
return ((*val_as_float - min) / (max - min)) * row_count;
|
||||
}
|
||||
|
||||
void minMaxStatisticsValidator(const SingleStatisticsDescription & /*description*/, const DataTypePtr & data_type)
|
||||
{
|
||||
auto inner_data_type = removeNullable(data_type);
|
||||
inner_data_type = removeLowCardinalityAndNullable(inner_data_type);
|
||||
if (!inner_data_type->isValueRepresentedByNumber())
|
||||
throw Exception(ErrorCodes::ILLEGAL_STATISTICS, "Statistics of type 'minmax' do not support type {}", data_type->getName());
|
||||
}
|
||||
|
||||
StatisticsPtr minMaxStatisticsCreator(const SingleStatisticsDescription & description, const DataTypePtr & data_type)
|
||||
{
|
||||
return std::make_shared<StatisticsMinMax>(description, data_type);
|
||||
}
|
||||
|
||||
}
|
||||
33
src/Storages/Statistics/StatisticsMinMax.h
Normal file
33
src/Storages/Statistics/StatisticsMinMax.h
Normal file
@ -0,0 +1,33 @@
|
||||
#pragma once
|
||||
|
||||
#include <Storages/Statistics/Statistics.h>
|
||||
#include <DataTypes/IDataType.h>
|
||||
|
||||
|
||||
namespace DB
|
||||
{
|
||||
|
||||
class StatisticsMinMax : public IStatistics
|
||||
{
|
||||
public:
|
||||
StatisticsMinMax(const SingleStatisticsDescription & statistics_description, const DataTypePtr & data_type_);
|
||||
|
||||
void update(const ColumnPtr & column) override;
|
||||
|
||||
void serialize(WriteBuffer & buf) override;
|
||||
void deserialize(ReadBuffer & buf) override;
|
||||
|
||||
Float64 estimateLess(const Field & val) const override;
|
||||
|
||||
private:
|
||||
Float64 min = std::numeric_limits<Float64>::max();
|
||||
Float64 max = std::numeric_limits<Float64>::min();
|
||||
UInt64 row_count = 0;
|
||||
|
||||
DataTypePtr data_type;
|
||||
};
|
||||
|
||||
void minMaxStatisticsValidator(const SingleStatisticsDescription & description, const DataTypePtr & data_type);
|
||||
StatisticsPtr minMaxStatisticsCreator(const SingleStatisticsDescription & description, const DataTypePtr & data_type);
|
||||
|
||||
}
|
||||
@ -56,7 +56,7 @@ void uniqStatisticsValidator(const SingleStatisticsDescription & /*description*/
|
||||
{
|
||||
DataTypePtr inner_data_type = removeNullable(data_type);
|
||||
inner_data_type = removeLowCardinalityAndNullable(inner_data_type);
|
||||
if (!inner_data_type->isValueRepresentedByNumber())
|
||||
if (!inner_data_type->isValueRepresentedByNumber() && !isStringOrFixedString(inner_data_type))
|
||||
throw Exception(ErrorCodes::ILLEGAL_STATISTICS, "Statistics of type 'uniq' do not support type {}", data_type->getName());
|
||||
}
|
||||
|
||||
|
||||
@ -50,7 +50,9 @@ static StatisticsType stringToStatisticsType(String type)
|
||||
return StatisticsType::Uniq;
|
||||
if (type == "count_min")
|
||||
return StatisticsType::CountMinSketch;
|
||||
throw Exception(ErrorCodes::INCORRECT_QUERY, "Unknown statistics type: {}. Supported statistics types are 'tdigest', 'uniq' and 'count_min'.", type);
|
||||
if (type == "minmax")
|
||||
return StatisticsType::MinMax;
|
||||
throw Exception(ErrorCodes::INCORRECT_QUERY, "Unknown statistics type: {}. Supported statistics types are 'count_min', 'minmax', 'tdigest' and 'uniq'.", type);
|
||||
}
|
||||
|
||||
String SingleStatisticsDescription::getTypeName() const
|
||||
@ -63,8 +65,10 @@ String SingleStatisticsDescription::getTypeName() const
|
||||
return "Uniq";
|
||||
case StatisticsType::CountMinSketch:
|
||||
return "count_min";
|
||||
case StatisticsType::MinMax:
|
||||
return "minmax";
|
||||
default:
|
||||
throw Exception(ErrorCodes::LOGICAL_ERROR, "Unknown statistics type: {}. Supported statistics types are 'tdigest', 'uniq' and 'count_min'.", type);
|
||||
throw Exception(ErrorCodes::LOGICAL_ERROR, "Unknown statistics type: {}. Supported statistics types are 'count_min', 'minmax', 'tdigest' and 'uniq'.", type);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@ -14,6 +14,7 @@ enum class StatisticsType : UInt8
|
||||
TDigest = 0,
|
||||
Uniq = 1,
|
||||
CountMinSketch = 2,
|
||||
MinMax = 3,
|
||||
|
||||
Max = 63,
|
||||
};
|
||||
|
||||
@ -410,7 +410,9 @@ class CI:
|
||||
num_batches=6,
|
||||
),
|
||||
JobNames.INTEGRATION_TEST_TSAN: CommonJobConfigs.INTEGRATION_TEST.with_properties(
|
||||
required_builds=[BuildNames.PACKAGE_TSAN], num_batches=6
|
||||
required_builds=[BuildNames.PACKAGE_TSAN],
|
||||
num_batches=6,
|
||||
timeout=9000, # the job timed out with default value (7200)
|
||||
),
|
||||
JobNames.INTEGRATION_TEST_ARM: CommonJobConfigs.INTEGRATION_TEST.with_properties(
|
||||
required_builds=[BuildNames.PACKAGE_AARCH64],
|
||||
|
||||
@ -343,6 +343,13 @@ def test_increment_backup_without_changes():
|
||||
|
||||
|
||||
def test_incremental_backup_overflow():
|
||||
if (
|
||||
instance.is_built_with_thread_sanitizer()
|
||||
or instance.is_built_with_memory_sanitizer()
|
||||
or instance.is_built_with_address_sanitizer()
|
||||
):
|
||||
pytest.skip("The test is slow in builds with sanitizer")
|
||||
|
||||
backup_name = new_backup_name()
|
||||
incremental_backup_name = new_backup_name()
|
||||
|
||||
|
||||
@ -154,6 +154,13 @@ def test_aggregate_states(start_cluster):
|
||||
|
||||
|
||||
def test_string_functions(start_cluster):
|
||||
if (
|
||||
upstream.is_built_with_thread_sanitizer()
|
||||
or upstream.is_built_with_memory_sanitizer()
|
||||
or upstream.is_built_with_address_sanitizer()
|
||||
):
|
||||
pytest.skip("The test is slow in builds with sanitizer")
|
||||
|
||||
functions = backward.query(
|
||||
"""
|
||||
SELECT if(NOT empty(alias_to), alias_to, name)
|
||||
|
||||
@ -5,6 +5,7 @@
|
||||
<access_key_id>minio</access_key_id>
|
||||
<secret_access_key>minio123</secret_access_key>
|
||||
</s3_snapshot>
|
||||
<use_cluster>false</use_cluster>
|
||||
<tcp_port>9181</tcp_port>
|
||||
<server_id>1</server_id>
|
||||
<log_storage_path>/var/lib/clickhouse/coordination/log</log_storage_path>
|
||||
|
||||
@ -5,6 +5,7 @@
|
||||
<access_key_id>minio</access_key_id>
|
||||
<secret_access_key>minio123</secret_access_key>
|
||||
</s3_snapshot>
|
||||
<use_cluster>false</use_cluster>
|
||||
<tcp_port>9181</tcp_port>
|
||||
<server_id>2</server_id>
|
||||
<log_storage_path>/var/lib/clickhouse/coordination/log</log_storage_path>
|
||||
|
||||
@ -5,6 +5,7 @@
|
||||
<access_key_id>minio</access_key_id>
|
||||
<secret_access_key>minio123</secret_access_key>
|
||||
</s3_snapshot>
|
||||
<use_cluster>false</use_cluster>
|
||||
<tcp_port>9181</tcp_port>
|
||||
<server_id>3</server_id>
|
||||
<log_storage_path>/var/lib/clickhouse/coordination/log</log_storage_path>
|
||||
|
||||
@ -2,6 +2,9 @@ import pytest
|
||||
from helpers.cluster import ClickHouseCluster
|
||||
from time import sleep
|
||||
from retry import retry
|
||||
from multiprocessing.dummy import Pool
|
||||
import helpers.keeper_utils as keeper_utils
|
||||
from minio.deleteobjects import DeleteObject
|
||||
|
||||
from kazoo.client import KazooClient
|
||||
|
||||
@ -75,7 +78,18 @@ def wait_node(node):
|
||||
raise Exception("Can't wait node", node.name, "to become ready")
|
||||
|
||||
|
||||
def delete_keeper_snapshots_logs(nodex):
|
||||
nodex.exec_in_container(
|
||||
[
|
||||
"bash",
|
||||
"-c",
|
||||
"rm -rf /var/lib/clickhouse/coordination/log /var/lib/clickhouse/coordination/snapshots",
|
||||
]
|
||||
)
|
||||
|
||||
|
||||
def test_s3_upload(started_cluster):
|
||||
|
||||
node1_zk = get_fake_zk(node1.name)
|
||||
|
||||
# we defined in configs snapshot_distance as 50
|
||||
@ -89,6 +103,11 @@ def test_s3_upload(started_cluster):
|
||||
for obj in list(cluster.minio_client.list_objects("snapshots"))
|
||||
]
|
||||
|
||||
def delete_s3_snapshots():
|
||||
snapshots = cluster.minio_client.list_objects("snapshots")
|
||||
for s in snapshots:
|
||||
cluster.minio_client.remove_object("snapshots", s.object_name)
|
||||
|
||||
# Keeper sends snapshots asynchornously, hence we need to retry.
|
||||
@retry(AssertionError, tries=10, delay=2)
|
||||
def _check_snapshots():
|
||||
@ -125,3 +144,26 @@ def test_s3_upload(started_cluster):
|
||||
)
|
||||
|
||||
destroy_zk_client(node2_zk)
|
||||
node2.stop_clickhouse()
|
||||
delete_keeper_snapshots_logs(node2)
|
||||
node3.stop_clickhouse()
|
||||
delete_keeper_snapshots_logs(node3)
|
||||
delete_keeper_snapshots_logs(node1)
|
||||
p = Pool(3)
|
||||
waiters = []
|
||||
|
||||
def start_clickhouse(node):
|
||||
node.start_clickhouse()
|
||||
|
||||
waiters.append(p.apply_async(start_clickhouse, args=(node1,)))
|
||||
waiters.append(p.apply_async(start_clickhouse, args=(node2,)))
|
||||
waiters.append(p.apply_async(start_clickhouse, args=(node3,)))
|
||||
|
||||
delete_s3_snapshots() # for next iteration
|
||||
|
||||
for waiter in waiters:
|
||||
waiter.wait()
|
||||
|
||||
keeper_utils.wait_until_connected(cluster, node1)
|
||||
keeper_utils.wait_until_connected(cluster, node2)
|
||||
keeper_utils.wait_until_connected(cluster, node3)
|
||||
|
||||
@ -629,5 +629,6 @@ def test_roles_cache():
|
||||
check()
|
||||
|
||||
instance.query("DROP USER " + ", ".join(users))
|
||||
instance.query("DROP ROLE " + ", ".join(roles))
|
||||
if roles:
|
||||
instance.query("DROP ROLE " + ", ".join(roles))
|
||||
instance.query("DROP TABLE tbl")
|
||||
|
||||
@ -10,6 +10,8 @@ import string
|
||||
import ast
|
||||
import math
|
||||
|
||||
from multiprocessing.dummy import Pool
|
||||
|
||||
import avro.schema
|
||||
import avro.io
|
||||
import avro.datafile
|
||||
@ -998,7 +1000,11 @@ def test_kafka_formats(kafka_cluster, create_query_generator):
|
||||
}
|
||||
|
||||
topic_postfix = str(hash(create_query_generator))
|
||||
for format_name, format_opts in list(all_formats.items()):
|
||||
|
||||
p = Pool(10)
|
||||
results = []
|
||||
|
||||
def run_for_format(format_name, format_opts):
|
||||
logging.debug(f"Set up {format_name}")
|
||||
topic_name = f"format_tests_{format_name}-{topic_postfix}"
|
||||
data_sample = format_opts["data_sample"]
|
||||
@ -1034,6 +1040,13 @@ def test_kafka_formats(kafka_cluster, create_query_generator):
|
||||
),
|
||||
)
|
||||
)
|
||||
|
||||
for format_name, format_opts in list(all_formats.items()):
|
||||
results.append(p.apply_async(run_for_format, args=(format_name, format_opts)))
|
||||
|
||||
for result in results:
|
||||
result.get()
|
||||
|
||||
raw_expected = """\
|
||||
0 0 AM 0.5 1 {topic_name} 0 {offset_0}
|
||||
1 0 AM 0.5 1 {topic_name} 0 {offset_1}
|
||||
@ -1064,7 +1077,9 @@ def test_kafka_formats(kafka_cluster, create_query_generator):
|
||||
)
|
||||
assert result_checker(res)
|
||||
|
||||
for format_name, format_opts in list(all_formats.items()):
|
||||
results = []
|
||||
|
||||
def run_for_format2(format_name, format_opts):
|
||||
logging.debug(("Checking {}".format(format_name)))
|
||||
topic_name = f"format_tests_{format_name}-{topic_postfix}"
|
||||
# shift offsets by 1 if format supports empty value
|
||||
@ -1088,6 +1103,12 @@ def test_kafka_formats(kafka_cluster, create_query_generator):
|
||||
)
|
||||
kafka_delete_topic(get_admin_client(kafka_cluster), topic_name)
|
||||
|
||||
for format_name, format_opts in list(all_formats.items()):
|
||||
results.append(p.apply_async(run_for_format2, args=(format_name, format_opts)))
|
||||
|
||||
for result in results:
|
||||
result.get()
|
||||
|
||||
|
||||
# Since everything is async and shaky when receiving messages from Kafka,
|
||||
# we may want to try and check results multiple times in a loop.
|
||||
@ -4237,7 +4258,11 @@ def test_kafka_formats_with_broken_message(kafka_cluster, create_query_generator
|
||||
|
||||
topic_name_prefix = "format_tests_4_stream_"
|
||||
topic_name_postfix = get_topic_postfix(create_query_generator)
|
||||
for format_name, format_opts in list(all_formats.items()):
|
||||
|
||||
p = Pool(10)
|
||||
results = []
|
||||
|
||||
def run_for_format(format_name, format_opts):
|
||||
logging.debug(f"Set up {format_name}")
|
||||
topic_name = f"{topic_name_prefix}{format_name}{topic_name_postfix}"
|
||||
data_sample = format_opts["data_sample"]
|
||||
@ -4278,6 +4303,12 @@ def test_kafka_formats_with_broken_message(kafka_cluster, create_query_generator
|
||||
"""
|
||||
)
|
||||
|
||||
for format_name, format_opts in list(all_formats.items()):
|
||||
results.append(p.apply_async(run_for_format, args=(format_name, format_opts)))
|
||||
|
||||
for result in results:
|
||||
result.get()
|
||||
|
||||
raw_expected = """\
|
||||
0 0 AM 0.5 1 {topic_name} 0 {offset_0}
|
||||
1 0 AM 0.5 1 {topic_name} 0 {offset_1}
|
||||
@ -4308,7 +4339,9 @@ def test_kafka_formats_with_broken_message(kafka_cluster, create_query_generator
|
||||
)
|
||||
assert result_checker(res)
|
||||
|
||||
for format_name, format_opts in list(all_formats.items()):
|
||||
results = []
|
||||
|
||||
def run_for_format2(format_name, format_opts):
|
||||
logging.debug(f"Checking {format_name}")
|
||||
topic_name = f"{topic_name_prefix}{format_name}{topic_name_postfix}"
|
||||
# shift offsets by 1 if format supports empty value
|
||||
@ -4348,6 +4381,12 @@ def test_kafka_formats_with_broken_message(kafka_cluster, create_query_generator
|
||||
), "Proper error for format: {}".format(format_name)
|
||||
kafka_delete_topic(admin_client, topic_name)
|
||||
|
||||
for format_name, format_opts in list(all_formats.items()):
|
||||
results.append(p.apply_async(run_for_format2, args=(format_name, format_opts)))
|
||||
|
||||
for result in results:
|
||||
result.get()
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"create_query_generator",
|
||||
@ -4831,27 +4870,13 @@ def test_max_rows_per_message(kafka_cluster, create_query_generator):
|
||||
def test_row_based_formats(kafka_cluster, create_query_generator):
|
||||
admin_client = get_admin_client(kafka_cluster)
|
||||
|
||||
for format_name in [
|
||||
"TSV",
|
||||
"TSVWithNamesAndTypes",
|
||||
"TSKV",
|
||||
"CSV",
|
||||
"CSVWithNamesAndTypes",
|
||||
"CustomSeparatedWithNamesAndTypes",
|
||||
"Values",
|
||||
"JSON",
|
||||
"JSONEachRow",
|
||||
"JSONCompactEachRow",
|
||||
"JSONCompactEachRowWithNamesAndTypes",
|
||||
"JSONObjectEachRow",
|
||||
"Avro",
|
||||
"RowBinary",
|
||||
"RowBinaryWithNamesAndTypes",
|
||||
"MsgPack",
|
||||
]:
|
||||
p = Pool(10)
|
||||
|
||||
def run_for_format_name(format_name):
|
||||
logging.debug("Checking {format_name}")
|
||||
|
||||
topic_name = format_name + get_topic_postfix(create_query_generator)
|
||||
view_name = f"kafka_view_{format_name}"
|
||||
table_name = f"kafka_{format_name}"
|
||||
|
||||
with kafka_topic(admin_client, topic_name):
|
||||
@ -4870,12 +4895,12 @@ def test_row_based_formats(kafka_cluster, create_query_generator):
|
||||
|
||||
instance.query(
|
||||
f"""
|
||||
DROP TABLE IF EXISTS test.view;
|
||||
DROP TABLE IF EXISTS test.{view_name};
|
||||
DROP TABLE IF EXISTS test.{table_name};
|
||||
|
||||
{create_query};
|
||||
|
||||
CREATE MATERIALIZED VIEW test.view ENGINE=MergeTree ORDER BY (key, value) AS
|
||||
CREATE MATERIALIZED VIEW test.{view_name} ENGINE=MergeTree ORDER BY (key, value) AS
|
||||
SELECT key, value FROM test.{table_name};
|
||||
|
||||
INSERT INTO test.{table_name} SELECT number * 10 as key, number * 100 as value FROM numbers({num_rows});
|
||||
@ -4886,18 +4911,44 @@ def test_row_based_formats(kafka_cluster, create_query_generator):
|
||||
kafka_cluster, topic_name, message_count, need_decode=False
|
||||
)
|
||||
|
||||
assert len(messages) == message_count
|
||||
assert (
|
||||
len(messages) == message_count
|
||||
), f"Invalid message count for {format_name}"
|
||||
|
||||
instance.query_with_retry(
|
||||
"SELECT count() FROM test.view",
|
||||
f"SELECT count() FROM test.{view_name}",
|
||||
check_callback=lambda res: int(res) == num_rows,
|
||||
)
|
||||
|
||||
result = instance.query("SELECT * FROM test.view")
|
||||
result = instance.query(f"SELECT * FROM test.{view_name}")
|
||||
expected = ""
|
||||
for i in range(num_rows):
|
||||
expected += str(i * 10) + "\t" + str(i * 100) + "\n"
|
||||
assert result == expected
|
||||
assert result == expected, f"Invalid result for {format_name}"
|
||||
|
||||
results = []
|
||||
for format_name in [
|
||||
"TSV",
|
||||
"TSVWithNamesAndTypes",
|
||||
"TSKV",
|
||||
"CSV",
|
||||
"CSVWithNamesAndTypes",
|
||||
"CustomSeparatedWithNamesAndTypes",
|
||||
"Values",
|
||||
"JSON",
|
||||
"JSONEachRow",
|
||||
"JSONCompactEachRow",
|
||||
"JSONCompactEachRowWithNamesAndTypes",
|
||||
"JSONObjectEachRow",
|
||||
"Avro",
|
||||
"RowBinary",
|
||||
"RowBinaryWithNamesAndTypes",
|
||||
"MsgPack",
|
||||
]:
|
||||
results.append(p.apply_async(run_for_format_name, args=(format_name,)))
|
||||
|
||||
for result in results:
|
||||
result.get()
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
@ -4955,16 +5006,12 @@ def test_block_based_formats_2(kafka_cluster, create_query_generator):
|
||||
num_rows = 100
|
||||
message_count = 9
|
||||
|
||||
for format_name in [
|
||||
"JSONColumns",
|
||||
"Native",
|
||||
"Arrow",
|
||||
"Parquet",
|
||||
"ORC",
|
||||
"JSONCompactColumns",
|
||||
]:
|
||||
p = Pool(10)
|
||||
|
||||
def run_for_format_name(format_name):
|
||||
topic_name = format_name + get_topic_postfix(create_query_generator)
|
||||
table_name = f"kafka_{format_name}"
|
||||
view_name = f"kafka_view_{format_name}"
|
||||
logging.debug(f"Checking format {format_name}")
|
||||
with kafka_topic(admin_client, topic_name):
|
||||
create_query = create_query_generator(
|
||||
@ -4977,12 +5024,12 @@ def test_block_based_formats_2(kafka_cluster, create_query_generator):
|
||||
|
||||
instance.query(
|
||||
f"""
|
||||
DROP TABLE IF EXISTS test.view;
|
||||
DROP TABLE IF EXISTS test.{view_name};
|
||||
DROP TABLE IF EXISTS test.{table_name};
|
||||
|
||||
{create_query};
|
||||
|
||||
CREATE MATERIALIZED VIEW test.view ENGINE=MergeTree ORDER BY (key, value) AS
|
||||
CREATE MATERIALIZED VIEW test.{view_name} ENGINE=MergeTree ORDER BY (key, value) AS
|
||||
SELECT key, value FROM test.{table_name};
|
||||
|
||||
INSERT INTO test.{table_name} SELECT number * 10 as key, number * 100 as value FROM numbers({num_rows}) settings max_block_size=12, optimize_trivial_insert_select=0;
|
||||
@ -4991,22 +5038,38 @@ def test_block_based_formats_2(kafka_cluster, create_query_generator):
|
||||
messages = kafka_consume_with_retry(
|
||||
kafka_cluster, topic_name, message_count, need_decode=False
|
||||
)
|
||||
assert len(messages) == message_count
|
||||
assert (
|
||||
len(messages) == message_count
|
||||
), f"Invalid message count for {format_name}"
|
||||
|
||||
rows = int(
|
||||
instance.query_with_retry(
|
||||
"SELECT count() FROM test.view",
|
||||
f"SELECT count() FROM test.{view_name}",
|
||||
check_callback=lambda res: int(res) == num_rows,
|
||||
)
|
||||
)
|
||||
|
||||
assert rows == num_rows
|
||||
assert rows == num_rows, f"Invalid row count for {format_name}"
|
||||
|
||||
result = instance.query("SELECT * FROM test.view ORDER by key")
|
||||
result = instance.query(f"SELECT * FROM test.{view_name} ORDER by key")
|
||||
expected = ""
|
||||
for i in range(num_rows):
|
||||
expected += str(i * 10) + "\t" + str(i * 100) + "\n"
|
||||
assert result == expected
|
||||
assert result == expected, f"Invalid result for {format_name}"
|
||||
|
||||
results = []
|
||||
for format_name in [
|
||||
"JSONColumns",
|
||||
"Native",
|
||||
"Arrow",
|
||||
"Parquet",
|
||||
"ORC",
|
||||
"JSONCompactColumns",
|
||||
]:
|
||||
results.append(p.apply_async(run_for_format_name, args=(format_name,)))
|
||||
|
||||
for result in results:
|
||||
result.get()
|
||||
|
||||
|
||||
def test_system_kafka_consumers(kafka_cluster):
|
||||
@ -5300,6 +5363,54 @@ def test_formats_errors(kafka_cluster):
|
||||
bootstrap_servers="localhost:{}".format(kafka_cluster.kafka_port)
|
||||
)
|
||||
|
||||
p = Pool(10)
|
||||
|
||||
def run_for_format_name(format_name):
|
||||
with kafka_topic(admin_client, format_name):
|
||||
table_name = f"kafka_{format_name}"
|
||||
view_name = f"kafka_view_{format_name}"
|
||||
|
||||
instance.query(
|
||||
f"""
|
||||
DROP TABLE IF EXISTS test.{view_name};
|
||||
DROP TABLE IF EXISTS test.{table_name};
|
||||
|
||||
CREATE TABLE test.{table_name} (key UInt64, value UInt64)
|
||||
ENGINE = Kafka
|
||||
SETTINGS kafka_broker_list = 'kafka1:19092',
|
||||
kafka_topic_list = '{format_name}',
|
||||
kafka_group_name = '{format_name}',
|
||||
kafka_format = '{format_name}',
|
||||
kafka_max_rows_per_message = 5,
|
||||
format_template_row='template_row.format',
|
||||
format_regexp='id: (.+?)',
|
||||
input_format_with_names_use_header=0,
|
||||
format_schema='key_value_message:Message';
|
||||
|
||||
CREATE MATERIALIZED VIEW test.{view_name} ENGINE=MergeTree ORDER BY (key, value) AS
|
||||
SELECT key, value FROM test.{table_name};
|
||||
"""
|
||||
)
|
||||
|
||||
kafka_produce(
|
||||
kafka_cluster,
|
||||
format_name,
|
||||
["Broken message\nBroken message\nBroken message\n"],
|
||||
)
|
||||
|
||||
num_errors = int(
|
||||
instance.query_with_retry(
|
||||
f"SELECT length(exceptions.text) from system.kafka_consumers where database = 'test' and table = '{table_name}'",
|
||||
check_callback=lambda res: int(res) > 0,
|
||||
)
|
||||
)
|
||||
|
||||
assert num_errors > 0, f"No errors for {format_name}"
|
||||
|
||||
instance.query(f"DROP TABLE test.{table_name}")
|
||||
instance.query(f"DROP TABLE test.{view_name}")
|
||||
|
||||
results = []
|
||||
for format_name in [
|
||||
"Template",
|
||||
"Regexp",
|
||||
@ -5342,48 +5453,10 @@ def test_formats_errors(kafka_cluster):
|
||||
"HiveText",
|
||||
"MySQLDump",
|
||||
]:
|
||||
with kafka_topic(admin_client, format_name):
|
||||
table_name = f"kafka_{format_name}"
|
||||
results.append(p.apply_async(run_for_format_name, args=(format_name,)))
|
||||
|
||||
instance.query(
|
||||
f"""
|
||||
DROP TABLE IF EXISTS test.view;
|
||||
DROP TABLE IF EXISTS test.{table_name};
|
||||
|
||||
CREATE TABLE test.{table_name} (key UInt64, value UInt64)
|
||||
ENGINE = Kafka
|
||||
SETTINGS kafka_broker_list = 'kafka1:19092',
|
||||
kafka_topic_list = '{format_name}',
|
||||
kafka_group_name = '{format_name}',
|
||||
kafka_format = '{format_name}',
|
||||
kafka_max_rows_per_message = 5,
|
||||
format_template_row='template_row.format',
|
||||
format_regexp='id: (.+?)',
|
||||
input_format_with_names_use_header=0,
|
||||
format_schema='key_value_message:Message';
|
||||
|
||||
CREATE MATERIALIZED VIEW test.view ENGINE=MergeTree ORDER BY (key, value) AS
|
||||
SELECT key, value FROM test.{table_name};
|
||||
"""
|
||||
)
|
||||
|
||||
kafka_produce(
|
||||
kafka_cluster,
|
||||
format_name,
|
||||
["Broken message\nBroken message\nBroken message\n"],
|
||||
)
|
||||
|
||||
num_errors = int(
|
||||
instance.query_with_retry(
|
||||
f"SELECT length(exceptions.text) from system.kafka_consumers where database = 'test' and table = '{table_name}'",
|
||||
check_callback=lambda res: int(res) > 0,
|
||||
)
|
||||
)
|
||||
|
||||
assert num_errors > 0
|
||||
|
||||
instance.query(f"DROP TABLE test.{table_name}")
|
||||
instance.query("DROP TABLE test.view")
|
||||
for result in results:
|
||||
result.get()
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
|
||||
@ -0,0 +1,32 @@
|
||||
-- Tags: no-fasttest, no-ordinary-database
|
||||
|
||||
-- Tests that CREATE TABLE and ADD INDEX respect setting 'allow_experimental_vector_similarity_index'.
|
||||
|
||||
DROP TABLE IF EXISTS tab;
|
||||
|
||||
-- Test CREATE TABLE
|
||||
|
||||
SET allow_experimental_vector_similarity_index = 0;
|
||||
CREATE TABLE tab (id UInt32, vec Array(Float32), INDEX idx vec TYPE vector_similarity('hnsw', 'L2Distance')) ENGINE = MergeTree ORDER BY tuple(); -- { serverError SUPPORT_IS_DISABLED }
|
||||
|
||||
SET allow_experimental_vector_similarity_index = 1;
|
||||
CREATE TABLE tab (id UInt32, vec Array(Float32), INDEX idx vec TYPE vector_similarity('hnsw', 'L2Distance')) ENGINE = MergeTree ORDER BY tuple();
|
||||
DROP TABLE tab;
|
||||
|
||||
-- Test ADD INDEX
|
||||
|
||||
CREATE TABLE tab (id UInt32, vec Array(Float32)) ENGINE = MergeTree ORDER BY tuple();
|
||||
|
||||
SET allow_experimental_vector_similarity_index = 0;
|
||||
ALTER TABLE tab ADD INDEX idx vec TYPE vector_similarity('hnsw', 'L2Distance'); -- { serverError SUPPORT_IS_DISABLED }
|
||||
|
||||
SET allow_experimental_vector_similarity_index = 1;
|
||||
ALTER TABLE tab ADD INDEX idx vec TYPE vector_similarity('hnsw', 'L2Distance');
|
||||
|
||||
-- Other index DDL must work regardless of the setting
|
||||
SET allow_experimental_vector_similarity_index = 0;
|
||||
ALTER TABLE tab MATERIALIZE INDEX idx;
|
||||
-- ALTER TABLE tab CLEAR INDEX idx; -- <-- Should work but doesn't w/o enabled setting. Unexpected but not terrible.
|
||||
ALTER TABLE tab DROP INDEX idx;
|
||||
|
||||
DROP TABLE tab;
|
||||
@ -41,6 +41,21 @@ Special cases
|
||||
6 [1,9.3] 0.005731362878640178
|
||||
1 [2,3.2] 0.15200169244542905
|
||||
7 [5.5,4.7] 0.3503476876550442
|
||||
Expression (Projection)
|
||||
Limit (preliminary LIMIT (without OFFSET))
|
||||
Sorting (Sorting for ORDER BY)
|
||||
Expression (Before ORDER BY)
|
||||
ReadFromMergeTree (default.tab)
|
||||
Indexes:
|
||||
PrimaryKey
|
||||
Condition: true
|
||||
Parts: 1/1
|
||||
Granules: 4/4
|
||||
Skip
|
||||
Name: idx
|
||||
Description: vector_similarity GRANULARITY 2
|
||||
Parts: 1/1
|
||||
Granules: 2/4
|
||||
-- Setting "max_limit_for_ann_queries"
|
||||
Expression (Projection)
|
||||
Limit (preliminary LIMIT (without OFFSET))
|
||||
|
||||
@ -63,6 +63,13 @@ FROM tab
|
||||
ORDER BY cosineDistance(vec, reference_vec)
|
||||
LIMIT 3;
|
||||
|
||||
EXPLAIN indexes = 1
|
||||
WITH [0.0, 2.0] AS reference_vec
|
||||
SELECT id, vec, cosineDistance(vec, reference_vec)
|
||||
FROM tab
|
||||
ORDER BY cosineDistance(vec, reference_vec)
|
||||
LIMIT 3;
|
||||
|
||||
SELECT '-- Setting "max_limit_for_ann_queries"';
|
||||
EXPLAIN indexes=1
|
||||
WITH [0.0, 2.0] as reference_vec
|
||||
|
||||
77
tests/queries/0_stateless/02378_part_log_profile_events.sh
Executable file
77
tests/queries/0_stateless/02378_part_log_profile_events.sh
Executable file
@ -0,0 +1,77 @@
|
||||
#!/usr/bin/env bash
|
||||
# Tags: no-shared-merge-tree
|
||||
# Tag no-shared-merge-tree: depend on events with local disk
|
||||
|
||||
CUR_DIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)
|
||||
# shellcheck source=../shell_config.sh
|
||||
. "$CUR_DIR"/../shell_config.sh
|
||||
|
||||
${CLICKHOUSE_CLIENT} --query "
|
||||
DROP TABLE IF EXISTS test;
|
||||
|
||||
CREATE TABLE test (key UInt64, val UInt64) engine = MergeTree Order by key PARTITION BY key >= 128;
|
||||
SET max_block_size = 64, max_insert_block_size = 64, min_insert_block_size_rows = 64;
|
||||
INSERT INTO test SELECT number AS key, sipHash64(number) AS val FROM numbers(512);
|
||||
"
|
||||
|
||||
${CLICKHOUSE_CLIENT} --query "
|
||||
SYSTEM FLUSH LOGS;
|
||||
SELECT
|
||||
if(count(DISTINCT query_id) == 1, 'Ok', 'Error: ' || toString(count(DISTINCT query_id))),
|
||||
if(count() == 512 / 64, 'Ok', 'Error: ' || toString(count())), -- 512 rows inserted, 64 rows per block
|
||||
if(SUM(ProfileEvents['MergeTreeDataWriterRows']) == 512, 'Ok', 'Error: ' || toString(SUM(ProfileEvents['MergeTreeDataWriterRows']))),
|
||||
if(SUM(ProfileEvents['MergeTreeDataWriterUncompressedBytes']) >= 1024, 'Ok', 'Error: ' || toString(SUM(ProfileEvents['MergeTreeDataWriterUncompressedBytes']))),
|
||||
if(SUM(ProfileEvents['MergeTreeDataWriterCompressedBytes']) >= 1024, 'Ok', 'Error: ' || toString(SUM(ProfileEvents['MergeTreeDataWriterCompressedBytes']))),
|
||||
if(SUM(ProfileEvents['MergeTreeDataWriterBlocks']) >= 8, 'Ok', 'Error: ' || toString(SUM(ProfileEvents['MergeTreeDataWriterBlocks'])))
|
||||
FROM system.part_log
|
||||
WHERE event_time > now() - INTERVAL 10 MINUTE
|
||||
AND database == currentDatabase() AND table == 'test'
|
||||
AND event_type == 'NewPart';
|
||||
"
|
||||
|
||||
${CLICKHOUSE_CLIENT} --query "OPTIMIZE TABLE test FINAL;"
|
||||
|
||||
${CLICKHOUSE_CLIENT} --query "
|
||||
SYSTEM FLUSH LOGS;
|
||||
SELECT
|
||||
if(count() > 2, 'Ok', 'Error: ' || toString(count())),
|
||||
if(SUM(ProfileEvents['MergedRows']) >= 512, 'Ok', 'Error: ' || toString(SUM(ProfileEvents['MergedRows'])))
|
||||
FROM system.part_log
|
||||
WHERE event_time > now() - INTERVAL 10 MINUTE
|
||||
AND database == currentDatabase() AND table == 'test'
|
||||
AND event_type == 'MergeParts';
|
||||
"
|
||||
|
||||
${CLICKHOUSE_CLIENT} --query "
|
||||
ALTER TABLE test UPDATE val = 0 WHERE key % 2 == 0 SETTINGS mutations_sync = 2
|
||||
"
|
||||
|
||||
# The mutation query may return before the entry is added to the system.part_log table.
|
||||
# Retry SYSTEM FLUSH LOGS until all entries are fully flushed.
|
||||
for _ in {1..10}; do
|
||||
${CLICKHOUSE_CLIENT} --query "SYSTEM FLUSH LOGS"
|
||||
res=$(${CLICKHOUSE_CLIENT} --query "
|
||||
SELECT count() FROM system.part_log
|
||||
WHERE event_time > now() - INTERVAL 10 MINUTE
|
||||
AND database == currentDatabase() AND table == 'test'
|
||||
AND event_type == 'MutatePart';"
|
||||
)
|
||||
if [[ $res -eq 2 ]]; then
|
||||
break
|
||||
fi
|
||||
|
||||
sleep 2.0
|
||||
done
|
||||
|
||||
${CLICKHOUSE_CLIENT} --query "
|
||||
SELECT
|
||||
if(count() == 2, 'Ok', 'Error: ' || toString(count())),
|
||||
if(SUM(ProfileEvents['MutatedRows']) == 512, 'Ok', 'Error: ' || toString(SUM(ProfileEvents['MutatedRows']))),
|
||||
if(SUM(ProfileEvents['FileOpen']) > 1, 'Ok', 'Error: ' || toString(SUM(ProfileEvents['FileOpen'])))
|
||||
FROM system.part_log
|
||||
WHERE event_time > now() - INTERVAL 10 MINUTE
|
||||
AND database == currentDatabase() AND table == 'test'
|
||||
AND event_type == 'MutatePart';
|
||||
"
|
||||
|
||||
${CLICKHOUSE_CLIENT} --query "DROP TABLE test"
|
||||
@ -1,50 +0,0 @@
|
||||
DROP TABLE IF EXISTS test;
|
||||
|
||||
CREATE TABLE test (key UInt64, val UInt64) engine = MergeTree Order by key PARTITION BY key >= 128;
|
||||
|
||||
SET max_block_size = 64, max_insert_block_size = 64, min_insert_block_size_rows = 64;
|
||||
|
||||
INSERT INTO test SELECT number AS key, sipHash64(number) AS val FROM numbers(512);
|
||||
|
||||
SYSTEM FLUSH LOGS;
|
||||
|
||||
SELECT
|
||||
if(count(DISTINCT query_id) == 1, 'Ok', 'Error: ' || toString(count(DISTINCT query_id))),
|
||||
if(count() == 512 / 64, 'Ok', 'Error: ' || toString(count())), -- 512 rows inserted, 64 rows per block
|
||||
if(SUM(ProfileEvents['MergeTreeDataWriterRows']) == 512, 'Ok', 'Error: ' || toString(SUM(ProfileEvents['MergeTreeDataWriterRows']))),
|
||||
if(SUM(ProfileEvents['MergeTreeDataWriterUncompressedBytes']) >= 1024, 'Ok', 'Error: ' || toString(SUM(ProfileEvents['MergeTreeDataWriterUncompressedBytes']))),
|
||||
if(SUM(ProfileEvents['MergeTreeDataWriterCompressedBytes']) >= 1024, 'Ok', 'Error: ' || toString(SUM(ProfileEvents['MergeTreeDataWriterCompressedBytes']))),
|
||||
if(SUM(ProfileEvents['MergeTreeDataWriterBlocks']) >= 8, 'Ok', 'Error: ' || toString(SUM(ProfileEvents['MergeTreeDataWriterBlocks'])))
|
||||
FROM system.part_log
|
||||
WHERE event_time > now() - INTERVAL 10 MINUTE
|
||||
AND database == currentDatabase() AND table == 'test'
|
||||
AND event_type == 'NewPart'
|
||||
;
|
||||
|
||||
OPTIMIZE TABLE test FINAL;
|
||||
|
||||
SYSTEM FLUSH LOGS;
|
||||
SELECT
|
||||
if(count() > 2, 'Ok', 'Error: ' || toString(count())),
|
||||
if(SUM(ProfileEvents['MergedRows']) >= 512, 'Ok', 'Error: ' || toString(SUM(ProfileEvents['MergedRows'])))
|
||||
FROM system.part_log
|
||||
WHERE event_time > now() - INTERVAL 10 MINUTE
|
||||
AND database == currentDatabase() AND table == 'test'
|
||||
AND event_type == 'MergeParts'
|
||||
;
|
||||
|
||||
ALTER TABLE test UPDATE val = 0 WHERE key % 2 == 0 SETTINGS mutations_sync = 2;
|
||||
|
||||
SYSTEM FLUSH LOGS;
|
||||
|
||||
SELECT
|
||||
if(count() == 2, 'Ok', 'Error: ' || toString(count())),
|
||||
if(SUM(ProfileEvents['MutatedRows']) == 512, 'Ok', 'Error: ' || toString(SUM(ProfileEvents['MutatedRows']))),
|
||||
if(SUM(ProfileEvents['FileOpen']) > 1, 'Ok', 'Error: ' || toString(SUM(ProfileEvents['FileOpen'])))
|
||||
FROM system.part_log
|
||||
WHERE event_time > now() - INTERVAL 10 MINUTE
|
||||
AND database == currentDatabase() AND table == 'test'
|
||||
AND event_type == 'MutatePart'
|
||||
;
|
||||
|
||||
DROP TABLE test;
|
||||
@ -0,0 +1,5 @@
|
||||
Test create statistics:
|
||||
CREATE TABLE default.tab\n(\n `a` LowCardinality(Int64) STATISTICS(tdigest, uniq, count_min, minmax),\n `b` LowCardinality(Nullable(String)) STATISTICS(uniq, count_min),\n `c` LowCardinality(Nullable(Int64)) STATISTICS(tdigest, uniq, count_min, minmax),\n `d` DateTime STATISTICS(tdigest, uniq, count_min, minmax),\n `pk` String\n)\nENGINE = MergeTree\nORDER BY pk\nSETTINGS index_granularity = 8192
|
||||
Test materialize and drop statistics:
|
||||
CREATE TABLE default.tab\n(\n `a` LowCardinality(Int64),\n `b` LowCardinality(Nullable(String)) STATISTICS(uniq, count_min),\n `c` LowCardinality(Nullable(Int64)),\n `d` DateTime,\n `pk` String\n)\nENGINE = MergeTree\nORDER BY pk\nSETTINGS index_granularity = 8192
|
||||
CREATE TABLE default.tab\n(\n `a` LowCardinality(Int64),\n `b` LowCardinality(Nullable(String)),\n `c` LowCardinality(Nullable(Int64)),\n `d` DateTime,\n `pk` String\n)\nENGINE = MergeTree\nORDER BY pk\nSETTINGS index_granularity = 8192
|
||||
@ -0,0 +1,35 @@
|
||||
-- Tags: no-fasttest
|
||||
|
||||
DROP TABLE IF EXISTS tab SYNC;
|
||||
|
||||
SET allow_experimental_statistics = 1;
|
||||
SET allow_statistics_optimize = 1;
|
||||
SET allow_suspicious_low_cardinality_types=1;
|
||||
SET mutations_sync = 2;
|
||||
|
||||
|
||||
SELECT 'Test create statistics:';
|
||||
|
||||
CREATE TABLE tab
|
||||
(
|
||||
a LowCardinality(Int64) STATISTICS(count_min, minmax, tdigest, uniq),
|
||||
b LowCardinality(Nullable(String)) STATISTICS(count_min, uniq),
|
||||
c LowCardinality(Nullable(Int64)) STATISTICS(count_min, minmax, tdigest, uniq),
|
||||
d DateTime STATISTICS(count_min, minmax, tdigest, uniq),
|
||||
pk String,
|
||||
) Engine = MergeTree() ORDER BY pk;
|
||||
|
||||
INSERT INTO tab select number, number, number, toDateTime(number), generateUUIDv4() FROM system.numbers LIMIT 10000;
|
||||
SHOW CREATE TABLE tab;
|
||||
|
||||
|
||||
SELECT 'Test materialize and drop statistics:';
|
||||
ALTER TABLE tab DROP STATISTICS a, b, c, d;
|
||||
ALTER TABLE tab ADD STATISTICS b TYPE count_min, uniq;
|
||||
ALTER TABLE tab MATERIALIZE STATISTICS b;
|
||||
SHOW CREATE TABLE tab;
|
||||
|
||||
ALTER TABLE tab DROP STATISTICS b;
|
||||
SHOW CREATE TABLE tab;
|
||||
|
||||
DROP TABLE IF EXISTS tab SYNC;
|
||||
@ -7,6 +7,7 @@ SET mutations_sync = 1;
|
||||
|
||||
DROP TABLE IF EXISTS tab;
|
||||
|
||||
SET allow_experimental_statistics = 0;
|
||||
-- Error case: Can't create statistics when allow_experimental_statistics = 0
|
||||
CREATE TABLE tab (col Float64 STATISTICS(tdigest)) Engine = MergeTree() ORDER BY tuple(); -- { serverError INCORRECT_QUERY }
|
||||
|
||||
@ -46,7 +47,7 @@ CREATE TABLE tab (col Map(UInt64, UInt64) STATISTICS(tdigest)) Engine = MergeTre
|
||||
CREATE TABLE tab (col UUID STATISTICS(tdigest)) Engine = MergeTree() ORDER BY tuple(); -- { serverError ILLEGAL_STATISTICS }
|
||||
CREATE TABLE tab (col IPv6 STATISTICS(tdigest)) Engine = MergeTree() ORDER BY tuple(); -- { serverError ILLEGAL_STATISTICS }
|
||||
|
||||
-- uniq requires data_type.isValueRepresentedByInteger
|
||||
-- uniq requires data_type.isValueRepresentedByInteger or (Fixed)String
|
||||
-- These types work:
|
||||
CREATE TABLE tab (col UInt8 STATISTICS(uniq)) Engine = MergeTree() ORDER BY tuple(); DROP TABLE tab;
|
||||
CREATE TABLE tab (col UInt256 STATISTICS(uniq)) Engine = MergeTree() ORDER BY tuple(); DROP TABLE tab;
|
||||
@ -61,9 +62,9 @@ CREATE TABLE tab (col IPv4 STATISTICS(uniq)) Engine = MergeTree() ORDER BY tuple
|
||||
CREATE TABLE tab (col Nullable(UInt8) STATISTICS(uniq)) Engine = MergeTree() ORDER BY tuple(); DROP TABLE tab;
|
||||
CREATE TABLE tab (col LowCardinality(UInt8) STATISTICS(uniq)) Engine = MergeTree() ORDER BY tuple(); DROP TABLE tab;
|
||||
CREATE TABLE tab (col LowCardinality(Nullable(UInt8)) STATISTICS(uniq)) Engine = MergeTree() ORDER BY tuple(); DROP TABLE tab;
|
||||
CREATE TABLE tab (col String STATISTICS(uniq)) Engine = MergeTree() ORDER BY tuple(); DROP TABLE tab;
|
||||
CREATE TABLE tab (col FixedString(1) STATISTICS(uniq)) Engine = MergeTree() ORDER BY tuple(); DROP TABLE tab;
|
||||
-- These types don't work:
|
||||
CREATE TABLE tab (col String STATISTICS(uniq)) Engine = MergeTree() ORDER BY tuple(); -- { serverError ILLEGAL_STATISTICS }
|
||||
CREATE TABLE tab (col FixedString(1) STATISTICS(uniq)) Engine = MergeTree() ORDER BY tuple(); -- { serverError ILLEGAL_STATISTICS }
|
||||
CREATE TABLE tab (col Array(Float64) STATISTICS(uniq)) Engine = MergeTree() ORDER BY tuple(); -- { serverError ILLEGAL_STATISTICS }
|
||||
CREATE TABLE tab (col Tuple(Float64, Float64) STATISTICS(uniq)) Engine = MergeTree() ORDER BY tuple(); -- { serverError ILLEGAL_STATISTICS }
|
||||
CREATE TABLE tab (col Map(UInt64, UInt64) STATISTICS(uniq)) Engine = MergeTree() ORDER BY tuple(); -- { serverError ILLEGAL_STATISTICS }
|
||||
@ -94,6 +95,30 @@ CREATE TABLE tab (col Map(UInt64, UInt64) STATISTICS(count_min)) Engine = MergeT
|
||||
CREATE TABLE tab (col UUID STATISTICS(count_min)) Engine = MergeTree() ORDER BY tuple(); -- { serverError ILLEGAL_STATISTICS }
|
||||
CREATE TABLE tab (col IPv6 STATISTICS(count_min)) Engine = MergeTree() ORDER BY tuple(); -- { serverError ILLEGAL_STATISTICS }
|
||||
|
||||
-- minmax requires data_type.isValueRepresentedByInteger
|
||||
-- These types work:
|
||||
CREATE TABLE tab (col UInt8 STATISTICS(minmax)) Engine = MergeTree() ORDER BY tuple(); DROP TABLE tab;
|
||||
CREATE TABLE tab (col UInt256 STATISTICS(minmax)) Engine = MergeTree() ORDER BY tuple(); DROP TABLE tab;
|
||||
CREATE TABLE tab (col Float32 STATISTICS(minmax)) Engine = MergeTree() ORDER BY tuple(); DROP TABLE tab;
|
||||
CREATE TABLE tab (col Decimal32(3) STATISTICS(minmax)) Engine = MergeTree() ORDER BY tuple(); DROP TABLE tab;
|
||||
CREATE TABLE tab (col Date STATISTICS(minmax)) Engine = MergeTree() ORDER BY tuple(); DROP TABLE tab;
|
||||
CREATE TABLE tab (col Date32 STATISTICS(minmax)) Engine = MergeTree() ORDER BY tuple(); DROP TABLE tab;
|
||||
CREATE TABLE tab (col DateTime STATISTICS(minmax)) Engine = MergeTree() ORDER BY tuple(); DROP TABLE tab;
|
||||
CREATE TABLE tab (col DateTime64 STATISTICS(minmax)) Engine = MergeTree() ORDER BY tuple(); DROP TABLE tab;
|
||||
CREATE TABLE tab (col Enum('hello', 'world') STATISTICS(minmax)) Engine = MergeTree() ORDER BY tuple(); DROP TABLE tab;
|
||||
CREATE TABLE tab (col IPv4 STATISTICS(minmax)) Engine = MergeTree() ORDER BY tuple(); DROP TABLE tab;
|
||||
CREATE TABLE tab (col Nullable(UInt8) STATISTICS(minmax)) Engine = MergeTree() ORDER BY tuple(); DROP TABLE tab;
|
||||
CREATE TABLE tab (col LowCardinality(UInt8) STATISTICS(minmax)) Engine = MergeTree() ORDER BY tuple(); DROP TABLE tab;
|
||||
CREATE TABLE tab (col LowCardinality(Nullable(UInt8)) STATISTICS(minmax)) Engine = MergeTree() ORDER BY tuple(); DROP TABLE tab;
|
||||
-- These types don't work:
|
||||
CREATE TABLE tab (col String STATISTICS(minmax)) Engine = MergeTree() ORDER BY tuple(); -- { serverError ILLEGAL_STATISTICS }
|
||||
CREATE TABLE tab (col FixedString(1) STATISTICS(minmax)) Engine = MergeTree() ORDER BY tuple(); -- { serverError ILLEGAL_STATISTICS }
|
||||
CREATE TABLE tab (col Array(Float64) STATISTICS(minmax)) Engine = MergeTree() ORDER BY tuple(); -- { serverError ILLEGAL_STATISTICS }
|
||||
CREATE TABLE tab (col Tuple(Float64, Float64) STATISTICS(minmax)) Engine = MergeTree() ORDER BY tuple(); -- { serverError ILLEGAL_STATISTICS }
|
||||
CREATE TABLE tab (col Map(UInt64, UInt64) STATISTICS(minmax)) Engine = MergeTree() ORDER BY tuple(); -- { serverError ILLEGAL_STATISTICS }
|
||||
CREATE TABLE tab (col UUID STATISTICS(minmax)) Engine = MergeTree() ORDER BY tuple(); -- { serverError ILLEGAL_STATISTICS }
|
||||
CREATE TABLE tab (col IPv6 STATISTICS(minmax)) Engine = MergeTree() ORDER BY tuple(); -- { serverError ILLEGAL_STATISTICS }
|
||||
|
||||
-- CREATE TABLE was easy, ALTER is more fun
|
||||
|
||||
CREATE TABLE tab
|
||||
@ -173,6 +198,13 @@ ALTER TABLE tab MODIFY STATISTICS f64 TYPE count_min; ALTER TABLE tab DROP STATI
|
||||
-- Doesn't work:
|
||||
ALTER TABLE tab ADD STATISTICS a TYPE count_min; -- { serverError ILLEGAL_STATISTICS }
|
||||
ALTER TABLE tab MODIFY STATISTICS a TYPE count_min; -- { serverError ILLEGAL_STATISTICS }
|
||||
-- minmax
|
||||
-- Works:
|
||||
ALTER TABLE tab ADD STATISTICS f64 TYPE minmax; ALTER TABLE tab DROP STATISTICS f64;
|
||||
ALTER TABLE tab MODIFY STATISTICS f64 TYPE minmax; ALTER TABLE tab DROP STATISTICS f64;
|
||||
-- Doesn't work:
|
||||
ALTER TABLE tab ADD STATISTICS a TYPE minmax; -- { serverError ILLEGAL_STATISTICS }
|
||||
ALTER TABLE tab MODIFY STATISTICS a TYPE minmax; -- { serverError ILLEGAL_STATISTICS }
|
||||
|
||||
-- Any data type changes on columns with statistics are disallowed, for simplicity even if the new data type is compatible with all existing
|
||||
-- statistics objects (e.g. tdigest can be created on Float64 and UInt64)
|
||||
|
||||
@ -3,10 +3,13 @@ u64 and =
|
||||
10
|
||||
10
|
||||
10
|
||||
10
|
||||
0
|
||||
0
|
||||
0
|
||||
0
|
||||
0
|
||||
10
|
||||
10
|
||||
10
|
||||
10
|
||||
@ -16,10 +19,13 @@ u64 and <
|
||||
70
|
||||
70
|
||||
70
|
||||
70
|
||||
80
|
||||
80
|
||||
80
|
||||
80
|
||||
80
|
||||
70
|
||||
70
|
||||
70
|
||||
70
|
||||
@ -29,6 +35,8 @@ f64 and =
|
||||
10
|
||||
10
|
||||
10
|
||||
10
|
||||
0
|
||||
0
|
||||
0
|
||||
0
|
||||
@ -37,6 +45,8 @@ f64 and =
|
||||
10
|
||||
10
|
||||
10
|
||||
10
|
||||
0
|
||||
0
|
||||
0
|
||||
0
|
||||
@ -46,6 +56,8 @@ f64 and <
|
||||
70
|
||||
70
|
||||
70
|
||||
70
|
||||
80
|
||||
80
|
||||
80
|
||||
80
|
||||
@ -54,6 +66,8 @@ f64 and <
|
||||
70
|
||||
70
|
||||
70
|
||||
70
|
||||
80
|
||||
80
|
||||
80
|
||||
80
|
||||
@ -63,6 +77,8 @@ dt and =
|
||||
0
|
||||
0
|
||||
0
|
||||
0
|
||||
10
|
||||
10
|
||||
10
|
||||
10
|
||||
@ -72,6 +88,8 @@ dt and <
|
||||
10000
|
||||
10000
|
||||
10000
|
||||
10000
|
||||
70
|
||||
70
|
||||
70
|
||||
70
|
||||
@ -89,6 +107,10 @@ b and =
|
||||
5000
|
||||
5000
|
||||
5000
|
||||
5000
|
||||
5000
|
||||
5000
|
||||
0
|
||||
0
|
||||
0
|
||||
0
|
||||
@ -96,3 +118,4 @@ b and =
|
||||
s and =
|
||||
10
|
||||
10
|
||||
10
|
||||
|
||||
@ -12,46 +12,56 @@ CREATE TABLE tab
|
||||
(
|
||||
u64 UInt64,
|
||||
u64_tdigest UInt64 STATISTICS(tdigest),
|
||||
u64_minmax UInt64 STATISTICS(minmax),
|
||||
u64_count_min UInt64 STATISTICS(count_min),
|
||||
u64_uniq UInt64 STATISTICS(uniq),
|
||||
f64 Float64,
|
||||
f64_tdigest Float64 STATISTICS(tdigest),
|
||||
f64_minmax Float64 STATISTICS(minmax),
|
||||
f64_count_min Float64 STATISTICS(count_min),
|
||||
f64_uniq Float64 STATISTICS(uniq),
|
||||
dt DateTime,
|
||||
dt_tdigest DateTime STATISTICS(tdigest),
|
||||
dt_minmax DateTime STATISTICS(minmax),
|
||||
dt_count_min DateTime STATISTICS(count_min),
|
||||
dt_uniq DateTime STATISTICS(uniq),
|
||||
b Bool,
|
||||
b_tdigest Bool STATISTICS(tdigest),
|
||||
b_minmax Bool STATISTICS(minmax),
|
||||
b_count_min Bool STATISTICS(count_min),
|
||||
b_uniq Bool STATISTICS(uniq),
|
||||
s String,
|
||||
-- s_tdigest String STATISTICS(tdigest), -- not supported by tdigest
|
||||
s_count_min String STATISTICS(count_min)
|
||||
-- s_uniq String STATISTICS(uniq), -- not supported by uniq
|
||||
-- s_minmax String STATISTICS(minmax), -- not supported by minmax
|
||||
s_count_min String STATISTICS(count_min),
|
||||
s_uniq String STATISTICS(uniq)
|
||||
) Engine = MergeTree() ORDER BY tuple()
|
||||
SETTINGS min_bytes_for_wide_part = 0;
|
||||
|
||||
INSERT INTO tab
|
||||
-- SELECT number % 10000, number % 1000, -(number % 100) FROM system.numbers LIMIT 10000;
|
||||
SELECT number % 1000,
|
||||
SELECT number % 1000, -- u64
|
||||
number % 1000,
|
||||
number % 1000,
|
||||
number % 1000,
|
||||
number % 1000,
|
||||
number % 1000, -- f64
|
||||
number % 1000,
|
||||
number % 1000,
|
||||
number % 1000,
|
||||
number % 1000,
|
||||
number % 1000, -- dt
|
||||
number % 1000,
|
||||
number % 1000,
|
||||
number % 1000,
|
||||
number % 1000,
|
||||
number % 2, -- b
|
||||
number % 2,
|
||||
number % 2,
|
||||
number % 2,
|
||||
number % 2,
|
||||
toString(number % 1000),
|
||||
toString(number % 1000),
|
||||
toString(number % 1000)
|
||||
FROM system.numbers LIMIT 10000;
|
||||
|
||||
@ -61,21 +71,25 @@ SELECT 'u64 and =';
|
||||
|
||||
SELECT count(*) FROM tab WHERE u64 = 7;
|
||||
SELECT count(*) FROM tab WHERE u64_tdigest = 7;
|
||||
SELECT count(*) FROM tab WHERE u64_minmax = 7;
|
||||
SELECT count(*) FROM tab WHERE u64_count_min = 7;
|
||||
SELECT count(*) FROM tab WHERE u64_uniq = 7;
|
||||
|
||||
SELECT count(*) FROM tab WHERE u64 = 7.7;
|
||||
SELECT count(*) FROM tab WHERE u64_tdigest = 7.7;
|
||||
SELECT count(*) FROM tab WHERE u64_minmax = 7.7;
|
||||
SELECT count(*) FROM tab WHERE u64_count_min = 7.7;
|
||||
SELECT count(*) FROM tab WHERE u64_uniq = 7.7;
|
||||
|
||||
SELECT count(*) FROM tab WHERE u64 = '7';
|
||||
SELECT count(*) FROM tab WHERE u64_tdigest = '7';
|
||||
SELECT count(*) FROM tab WHERE u64_minmax = '7';
|
||||
SELECT count(*) FROM tab WHERE u64_count_min = '7';
|
||||
SELECT count(*) FROM tab WHERE u64_uniq = '7';
|
||||
|
||||
SELECT count(*) FROM tab WHERE u64 = '7.7'; -- { serverError TYPE_MISMATCH }
|
||||
SELECT count(*) FROM tab WHERE u64_tdigest = '7.7'; -- { serverError TYPE_MISMATCH }
|
||||
SELECT count(*) FROM tab WHERE u64_minmax = '7.7'; -- { serverError TYPE_MISMATCH }
|
||||
SELECT count(*) FROM tab WHERE u64_count_min = '7.7'; -- { serverError TYPE_MISMATCH }
|
||||
SELECT count(*) FROM tab WHERE u64_uniq = '7.7'; -- { serverError TYPE_MISMATCH }
|
||||
|
||||
@ -83,21 +97,25 @@ SELECT 'u64 and <';
|
||||
|
||||
SELECT count(*) FROM tab WHERE u64 < 7;
|
||||
SELECT count(*) FROM tab WHERE u64_tdigest < 7;
|
||||
SELECT count(*) FROM tab WHERE u64_minmax < 7;
|
||||
SELECT count(*) FROM tab WHERE u64_count_min < 7;
|
||||
SELECT count(*) FROM tab WHERE u64_uniq < 7;
|
||||
|
||||
SELECT count(*) FROM tab WHERE u64 < 7.7;
|
||||
SELECT count(*) FROM tab WHERE u64_tdigest < 7.7;
|
||||
SELECT count(*) FROM tab WHERE u64_minmax < 7.7;
|
||||
SELECT count(*) FROM tab WHERE u64_count_min < 7.7;
|
||||
SELECT count(*) FROM tab WHERE u64_uniq < 7.7;
|
||||
|
||||
SELECT count(*) FROM tab WHERE u64 < '7';
|
||||
SELECT count(*) FROM tab WHERE u64_tdigest < '7';
|
||||
SELECT count(*) FROM tab WHERE u64_minmax < '7';
|
||||
SELECT count(*) FROM tab WHERE u64_count_min < '7';
|
||||
SELECT count(*) FROM tab WHERE u64_uniq < '7';
|
||||
|
||||
SELECT count(*) FROM tab WHERE u64 < '7.7'; -- { serverError TYPE_MISMATCH }
|
||||
SELECT count(*) FROM tab WHERE u64_tdigest < '7.7'; -- { serverError TYPE_MISMATCH }
|
||||
SELECT count(*) FROM tab WHERE u64_minmax < '7.7'; -- { serverError TYPE_MISMATCH }
|
||||
SELECT count(*) FROM tab WHERE u64_count_min < '7.7'; -- { serverError TYPE_MISMATCH }
|
||||
SELECT count(*) FROM tab WHERE u64_uniq < '7.7'; -- { serverError TYPE_MISMATCH }
|
||||
|
||||
@ -107,21 +125,25 @@ SELECT 'f64 and =';
|
||||
|
||||
SELECT count(*) FROM tab WHERE f64 = 7;
|
||||
SELECT count(*) FROM tab WHERE f64_tdigest = 7;
|
||||
SELECT count(*) FROM tab WHERE f64_minmax = 7;
|
||||
SELECT count(*) FROM tab WHERE f64_count_min = 7;
|
||||
SELECT count(*) FROM tab WHERE f64_uniq = 7;
|
||||
|
||||
SELECT count(*) FROM tab WHERE f64 = 7.7;
|
||||
SELECT count(*) FROM tab WHERE f64_tdigest = 7.7;
|
||||
SELECT count(*) FROM tab WHERE f64_minmax = 7.7;
|
||||
SELECT count(*) FROM tab WHERE f64_count_min = 7.7;
|
||||
SELECT count(*) FROM tab WHERE f64_uniq = 7.7;
|
||||
|
||||
SELECT count(*) FROM tab WHERE f64 = '7';
|
||||
SELECT count(*) FROM tab WHERE f64_tdigest = '7';
|
||||
SELECT count(*) FROM tab WHERE f64_minmax = '7';
|
||||
SELECT count(*) FROM tab WHERE f64_count_min = '7';
|
||||
SELECT count(*) FROM tab WHERE f64_uniq = '7';
|
||||
|
||||
SELECT count(*) FROM tab WHERE f64 = '7.7';
|
||||
SELECT count(*) FROM tab WHERE f64_tdigest = '7.7';
|
||||
SELECT count(*) FROM tab WHERE f64_minmax = '7.7';
|
||||
SELECT count(*) FROM tab WHERE f64_count_min = '7.7';
|
||||
SELECT count(*) FROM tab WHERE f64_uniq = '7.7';
|
||||
|
||||
@ -129,21 +151,25 @@ SELECT 'f64 and <';
|
||||
|
||||
SELECT count(*) FROM tab WHERE f64 < 7;
|
||||
SELECT count(*) FROM tab WHERE f64_tdigest < 7;
|
||||
SELECT count(*) FROM tab WHERE f64_minmax < 7;
|
||||
SELECT count(*) FROM tab WHERE f64_count_min < 7;
|
||||
SELECT count(*) FROM tab WHERE f64_uniq < 7;
|
||||
|
||||
SELECT count(*) FROM tab WHERE f64 < 7.7;
|
||||
SELECT count(*) FROM tab WHERE f64_tdigest < 7.7;
|
||||
SELECT count(*) FROM tab WHERE f64_minmax < 7.7;
|
||||
SELECT count(*) FROM tab WHERE f64_count_min < 7.7;
|
||||
SELECT count(*) FROM tab WHERE f64_uniq < 7.7;
|
||||
|
||||
SELECT count(*) FROM tab WHERE f64 < '7';
|
||||
SELECT count(*) FROM tab WHERE f64_tdigest < '7';
|
||||
SELECT count(*) FROM tab WHERE f64_minmax < '7';
|
||||
SELECT count(*) FROM tab WHERE f64_count_min < '7';
|
||||
SELECT count(*) FROM tab WHERE f64_uniq < '7';
|
||||
|
||||
SELECT count(*) FROM tab WHERE f64 < '7.7';
|
||||
SELECT count(*) FROM tab WHERE f64_tdigest < '7.7';
|
||||
SELECT count(*) FROM tab WHERE f64_minmax < '7.7';
|
||||
SELECT count(*) FROM tab WHERE f64_count_min < '7.7';
|
||||
SELECT count(*) FROM tab WHERE f64_uniq < '7.7';
|
||||
|
||||
@ -153,11 +179,13 @@ SELECT 'dt and =';
|
||||
|
||||
SELECT count(*) FROM tab WHERE dt = '2024-08-08 11:12:13';
|
||||
SELECT count(*) FROM tab WHERE dt_tdigest = '2024-08-08 11:12:13';
|
||||
SELECT count(*) FROM tab WHERE dt_minmax = '2024-08-08 11:12:13';
|
||||
SELECT count(*) FROM tab WHERE dt_count_min = '2024-08-08 11:12:13';
|
||||
SELECT count(*) FROM tab WHERE dt_uniq = '2024-08-08 11:12:13';
|
||||
|
||||
SELECT count(*) FROM tab WHERE dt = 7;
|
||||
SELECT count(*) FROM tab WHERE dt_tdigest = 7;
|
||||
SELECT count(*) FROM tab WHERE dt_minmax = 7;
|
||||
SELECT count(*) FROM tab WHERE dt_count_min = 7;
|
||||
SELECT count(*) FROM tab WHERE dt_uniq = 7;
|
||||
|
||||
@ -165,11 +193,13 @@ SELECT 'dt and <';
|
||||
|
||||
SELECT count(*) FROM tab WHERE dt < '2024-08-08 11:12:13';
|
||||
SELECT count(*) FROM tab WHERE dt_tdigest < '2024-08-08 11:12:13';
|
||||
SELECT count(*) FROM tab WHERE dt_minmax < '2024-08-08 11:12:13';
|
||||
SELECT count(*) FROM tab WHERE dt_count_min < '2024-08-08 11:12:13';
|
||||
SELECT count(*) FROM tab WHERE dt_uniq < '2024-08-08 11:12:13';
|
||||
|
||||
SELECT count(*) FROM tab WHERE dt < 7;
|
||||
SELECT count(*) FROM tab WHERE dt_tdigest < 7;
|
||||
SELECT count(*) FROM tab WHERE dt_minmax < 7;
|
||||
SELECT count(*) FROM tab WHERE dt_count_min < 7;
|
||||
SELECT count(*) FROM tab WHERE dt_uniq < 7;
|
||||
|
||||
@ -179,21 +209,25 @@ SELECT 'b and =';
|
||||
|
||||
SELECT count(*) FROM tab WHERE b = true;
|
||||
SELECT count(*) FROM tab WHERE b_tdigest = true;
|
||||
SELECT count(*) FROM tab WHERE b_minmax = true;
|
||||
SELECT count(*) FROM tab WHERE b_count_min = true;
|
||||
SELECT count(*) FROM tab WHERE b_uniq = true;
|
||||
|
||||
SELECT count(*) FROM tab WHERE b = 'true';
|
||||
SELECT count(*) FROM tab WHERE b_tdigest = 'true';
|
||||
SELECT count(*) FROM tab WHERE b_minmax = 'true';
|
||||
SELECT count(*) FROM tab WHERE b_count_min = 'true';
|
||||
SELECT count(*) FROM tab WHERE b_uniq = 'true';
|
||||
|
||||
SELECT count(*) FROM tab WHERE b = 1;
|
||||
SELECT count(*) FROM tab WHERE b_tdigest = 1;
|
||||
SELECT count(*) FROM tab WHERE b_minmax = 1;
|
||||
SELECT count(*) FROM tab WHERE b_count_min = 1;
|
||||
SELECT count(*) FROM tab WHERE b_uniq = 1;
|
||||
|
||||
SELECT count(*) FROM tab WHERE b = 1.1;
|
||||
SELECT count(*) FROM tab WHERE b_tdigest = 1.1;
|
||||
SELECT count(*) FROM tab WHERE b_minmax = 1.1;
|
||||
SELECT count(*) FROM tab WHERE b_count_min = 1.1;
|
||||
SELECT count(*) FROM tab WHERE b_uniq = 1.1;
|
||||
|
||||
@ -203,12 +237,14 @@ SELECT 's and =';
|
||||
|
||||
SELECT count(*) FROM tab WHERE s = 7; -- { serverError NO_COMMON_TYPE }
|
||||
-- SELECT count(*) FROM tab WHERE s_tdigest = 7; -- not supported
|
||||
-- SELECT count(*) FROM tab WHERE s_minmax = 7; -- not supported
|
||||
SELECT count(*) FROM tab WHERE s_count_min = 7; -- { serverError NO_COMMON_TYPE }
|
||||
-- SELECT count(*) FROM tab WHERE s_uniq = 7; -- not supported
|
||||
SELECT count(*) FROM tab WHERE s_uniq = 7; -- { serverError NO_COMMON_TYPE }
|
||||
|
||||
SELECT count(*) FROM tab WHERE s = '7';
|
||||
-- SELECT count(*) FROM tab WHERE s_tdigest = '7'; -- not supported
|
||||
-- SELECT count(*) FROM tab WHERE s_minmax = '7'; -- not supported
|
||||
SELECT count(*) FROM tab WHERE s_count_min = '7';
|
||||
-- SELECT count(*) FROM tab WHERE s_uniq = '7'; -- not supported
|
||||
SELECT count(*) FROM tab WHERE s_uniq = '7';
|
||||
|
||||
DROP TABLE tab;
|
||||
|
||||
18
tests/queries/0_stateless/03232_pr_not_ready_set.sql
Normal file
18
tests/queries/0_stateless/03232_pr_not_ready_set.sql
Normal file
@ -0,0 +1,18 @@
|
||||
SELECT
|
||||
is_initial_query,
|
||||
count() AS c,
|
||||
replaceRegexpAll(query, '_data_(\\d+)_(\\d+)', '_data_') AS query
|
||||
FROM system.query_log
|
||||
WHERE (event_date >= yesterday()) AND (type = 'QueryFinish') AND (ignore(54, 0, ignore('QueryFinish', 11, toLowCardinality(toLowCardinality(11)), 11, 11, 11), 'QueryFinish', materialize(11), toUInt128(11)) IN (
|
||||
SELECT query_id
|
||||
FROM system.query_log
|
||||
WHERE (current_database = currentDatabase()) AND (event_date >= yesterday()) AND (type = 'QueryFinish') AND (query LIKE '-- Parallel inner query alone%')
|
||||
))
|
||||
GROUP BY
|
||||
is_initial_query,
|
||||
query
|
||||
ORDER BY
|
||||
is_initial_query ASC,
|
||||
c ASC,
|
||||
query ASC
|
||||
SETTINGS allow_experimental_parallel_reading_from_replicas=1, max_parallel_replicas=3, cluster_for_parallel_replicas='test_cluster_one_shard_three_replicas_localhost', parallel_replicas_for_non_replicated_merge_tree=1, parallel_replicas_min_number_of_rows_per_replica=10;
|
||||
@ -1,16 +1,22 @@
|
||||
v24.8.4.13-lts 2024-09-06
|
||||
v24.8.3.59-lts 2024-09-03
|
||||
v24.8.2.3-lts 2024-08-22
|
||||
v24.8.1.2684-lts 2024-08-21
|
||||
v24.7.6.8-stable 2024-09-06
|
||||
v24.7.5.37-stable 2024-09-03
|
||||
v24.7.4.51-stable 2024-08-23
|
||||
v24.7.3.47-stable 2024-09-04
|
||||
v24.7.3.42-stable 2024-08-08
|
||||
v24.7.2.13-stable 2024-08-01
|
||||
v24.7.1.2915-stable 2024-07-30
|
||||
v24.6.6.6-stable 2024-09-06
|
||||
v24.6.5.30-stable 2024-09-03
|
||||
v24.6.4.42-stable 2024-08-23
|
||||
v24.6.3.95-stable 2024-08-06
|
||||
v24.6.3.38-stable 2024-09-04
|
||||
v24.6.2.17-stable 2024-07-05
|
||||
v24.6.1.4423-stable 2024-07-01
|
||||
v24.5.8.10-stable 2024-09-06
|
||||
v24.5.7.31-stable 2024-09-03
|
||||
v24.5.6.45-stable 2024-08-23
|
||||
v24.5.5.78-stable 2024-08-05
|
||||
@ -22,6 +28,7 @@ v24.4.4.113-stable 2024-08-02
|
||||
v24.4.3.25-stable 2024-06-14
|
||||
v24.4.2.141-stable 2024-06-07
|
||||
v24.4.1.2088-stable 2024-05-01
|
||||
v24.3.11.7-lts 2024-09-06
|
||||
v24.3.10.33-lts 2024-09-03
|
||||
v24.3.9.5-lts 2024-08-22
|
||||
v24.3.8.13-lts 2024-08-20
|
||||
|
||||
|
Loading…
Reference in New Issue
Block a user