mirror of
https://github.com/ClickHouse/ClickHouse.git
synced 2024-11-21 23:21:59 +00:00
Merge branch 'master' into ldap-role-mapping
* master: (50 commits) Update documentation-issue.md Add an option to use existing tables to perf.py DOCSUP-4280: Update the SELECT query (#17231) DOCSUP-3584 edit and translate (#17176) Fixed flaky test_storage_s3::test_custom_auth_headers Update 01560_merge_distributed_join.sql Minor improvements Slightly more correct Auto version update to [20.13.1.1] [54444] Auto version update to [20.12.1.5236] [54443] Update roadmap Add favicon; add loading indicator Fix race condition; history and sharing capabilities Update bitmap-functions.md Fix exception message Use default value for read-only flag in metadata for Disk3. ISSUES-16605 try fix review comment trigger CI ISSUES-16605 try fix integration failure ISSUES-16605 try fix integration test failure ...
This commit is contained in:
Denis Glazachev
commit
b02f2cf1ca
@ -2,8 +2,7 @@
|
||||
name: Documentation issue
|
||||
about: Report something incorrect or missing in documentation
|
||||
title: ''
|
||||
labels: documentation
|
||||
assignees: BayoNet
|
||||
labels: comp-documentation
|
||||
|
||||
---
|
||||
|
||||
|
||||
@ -1,6 +1,7 @@
|
||||
#pragma once
|
||||
|
||||
#include <cassert>
|
||||
#include <stdexcept> // for std::logic_error
|
||||
#include <string>
|
||||
#include <vector>
|
||||
#include <functional>
|
||||
|
||||
@ -1,9 +1,9 @@
|
||||
# This strings autochanged from release_lib.sh:
|
||||
SET(VERSION_REVISION 54443)
|
||||
SET(VERSION_REVISION 54444)
|
||||
SET(VERSION_MAJOR 20)
|
||||
SET(VERSION_MINOR 12)
|
||||
SET(VERSION_MINOR 13)
|
||||
SET(VERSION_PATCH 1)
|
||||
SET(VERSION_GITHASH c53725fb1f846fda074347607ab582fbb9c6f7a1)
|
||||
SET(VERSION_DESCRIBE v20.12.1.1-prestable)
|
||||
SET(VERSION_STRING 20.12.1.1)
|
||||
SET(VERSION_GITHASH e581f9ccfc5c64867b0f488cce72412fd2966471)
|
||||
SET(VERSION_DESCRIBE v20.13.1.1-prestable)
|
||||
SET(VERSION_STRING 20.13.1.1)
|
||||
# end of autochange
|
||||
|
||||
2
contrib/cctz
vendored
2
contrib/cctz
vendored
@ -1 +1 @@
|
||||
Subproject commit 7a2db4ece6e0f1b246173cbdb62711ae258ee841
|
||||
Subproject commit 260ba195ef6c489968bae8c88c62a67cdac5ff9d
|
||||
4
debian/changelog
vendored
4
debian/changelog
vendored
@ -1,5 +1,5 @@
|
||||
clickhouse (20.12.1.1) unstable; urgency=low
|
||||
clickhouse (20.13.1.1) unstable; urgency=low
|
||||
|
||||
* Modified source code
|
||||
|
||||
-- clickhouse-release <clickhouse-release@yandex-team.ru> Thu, 05 Nov 2020 21:52:47 +0300
|
||||
-- clickhouse-release <clickhouse-release@yandex-team.ru> Mon, 23 Nov 2020 10:29:24 +0300
|
||||
|
||||
@ -1,7 +1,7 @@
|
||||
FROM ubuntu:18.04
|
||||
|
||||
ARG repository="deb https://repo.clickhouse.tech/deb/stable/ main/"
|
||||
ARG version=20.12.1.*
|
||||
ARG version=20.13.1.*
|
||||
|
||||
RUN apt-get update \
|
||||
&& apt-get install --yes --no-install-recommends \
|
||||
|
||||
@ -1,7 +1,7 @@
|
||||
FROM ubuntu:20.04
|
||||
|
||||
ARG repository="deb https://repo.clickhouse.tech/deb/stable/ main/"
|
||||
ARG version=20.12.1.*
|
||||
ARG version=20.13.1.*
|
||||
ARG gosu_ver=1.10
|
||||
|
||||
RUN apt-get update \
|
||||
|
||||
@ -1,7 +1,7 @@
|
||||
FROM ubuntu:18.04
|
||||
|
||||
ARG repository="deb https://repo.clickhouse.tech/deb/stable/ main/"
|
||||
ARG version=20.12.1.*
|
||||
ARG version=20.13.1.*
|
||||
|
||||
RUN apt-get update && \
|
||||
apt-get install -y apt-transport-https dirmngr && \
|
||||
|
||||
@ -15,6 +15,9 @@ stage=${stage:-}
|
||||
# empty parameter.
|
||||
read -ra FASTTEST_CMAKE_FLAGS <<< "${FASTTEST_CMAKE_FLAGS:-}"
|
||||
|
||||
# Run only matching tests.
|
||||
FASTTEST_FOCUS=${FASTTEST_FOCUS:-""}
|
||||
|
||||
FASTTEST_WORKSPACE=$(readlink -f "${FASTTEST_WORKSPACE:-.}")
|
||||
FASTTEST_SOURCE=$(readlink -f "${FASTTEST_SOURCE:-$FASTTEST_WORKSPACE/ch}")
|
||||
FASTTEST_BUILD=$(readlink -f "${FASTTEST_BUILD:-${BUILD:-$FASTTEST_WORKSPACE/build}}")
|
||||
@ -291,7 +294,7 @@ TESTS_TO_SKIP=(
|
||||
01563_distributed_query_finish
|
||||
)
|
||||
|
||||
time clickhouse-test -j 8 --order=random --no-long --testname --shard --zookeeper --skip "${TESTS_TO_SKIP[@]}" 2>&1 | ts '%Y-%m-%d %H:%M:%S' | tee "$FASTTEST_OUTPUT/test_log.txt"
|
||||
time clickhouse-test -j 8 --order=random --no-long --testname --shard --zookeeper --skip "${TESTS_TO_SKIP[@]}" -- "$FASTTEST_FOCUS" 2>&1 | ts '%Y-%m-%d %H:%M:%S' | tee "$FASTTEST_OUTPUT/test_log.txt"
|
||||
|
||||
# substr is to remove semicolon after test name
|
||||
readarray -t FAILED_TESTS < <(awk '/FAIL|TIMEOUT|ERROR/ { print substr($3, 1, length($3)-1) }' "$FASTTEST_OUTPUT/test_log.txt" | tee "$FASTTEST_OUTPUT/failed-parallel-tests.txt")
|
||||
|
||||
@ -30,7 +30,7 @@ RUN apt-get update \
|
||||
tzdata \
|
||||
vim \
|
||||
wget \
|
||||
&& pip3 --no-cache-dir install clickhouse_driver scipy \
|
||||
&& pip3 --no-cache-dir install 'clickhouse-driver>=0.1.5' scipy \
|
||||
&& apt-get purge --yes python3-dev g++ \
|
||||
&& apt-get autoremove --yes \
|
||||
&& apt-get clean \
|
||||
|
||||
@ -14,10 +14,12 @@ import string
|
||||
import sys
|
||||
import time
|
||||
import traceback
|
||||
import logging
|
||||
import xml.etree.ElementTree as et
|
||||
from threading import Thread
|
||||
from scipy import stats
|
||||
|
||||
logging.basicConfig(format='%(asctime)s: %(levelname)s: %(module)s: %(message)s', level='WARNING')
|
||||
|
||||
total_start_seconds = time.perf_counter()
|
||||
stage_start_seconds = total_start_seconds
|
||||
@ -46,6 +48,8 @@ parser.add_argument('--profile-seconds', type=int, default=0, help='For how many
|
||||
parser.add_argument('--long', action='store_true', help='Do not skip the tests tagged as long.')
|
||||
parser.add_argument('--print-queries', action='store_true', help='Print test queries and exit.')
|
||||
parser.add_argument('--print-settings', action='store_true', help='Print test settings and exit.')
|
||||
parser.add_argument('--keep-created-tables', action='store_true', help="Don't drop the created tables after the test.")
|
||||
parser.add_argument('--use-existing-tables', action='store_true', help="Don't create or drop the tables, use the existing ones instead.")
|
||||
args = parser.parse_args()
|
||||
|
||||
reportStageEnd('start')
|
||||
@ -146,20 +150,21 @@ for i, s in enumerate(servers):
|
||||
|
||||
reportStageEnd('connect')
|
||||
|
||||
# Run drop queries, ignoring errors. Do this before all other activity, because
|
||||
# clickhouse_driver disconnects on error (this is not configurable), and the new
|
||||
# connection loses the changes in settings.
|
||||
drop_query_templates = [q.text for q in root.findall('drop_query')]
|
||||
drop_queries = substitute_parameters(drop_query_templates)
|
||||
for conn_index, c in enumerate(all_connections):
|
||||
for q in drop_queries:
|
||||
try:
|
||||
c.execute(q)
|
||||
print(f'drop\t{conn_index}\t{c.last_query.elapsed}\t{tsv_escape(q)}')
|
||||
except:
|
||||
pass
|
||||
if not args.use_existing_tables:
|
||||
# Run drop queries, ignoring errors. Do this before all other activity,
|
||||
# because clickhouse_driver disconnects on error (this is not configurable),
|
||||
# and the new connection loses the changes in settings.
|
||||
drop_query_templates = [q.text for q in root.findall('drop_query')]
|
||||
drop_queries = substitute_parameters(drop_query_templates)
|
||||
for conn_index, c in enumerate(all_connections):
|
||||
for q in drop_queries:
|
||||
try:
|
||||
c.execute(q)
|
||||
print(f'drop\t{conn_index}\t{c.last_query.elapsed}\t{tsv_escape(q)}')
|
||||
except:
|
||||
pass
|
||||
|
||||
reportStageEnd('drop-1')
|
||||
reportStageEnd('drop-1')
|
||||
|
||||
# Apply settings.
|
||||
# If there are errors, report them and continue -- maybe a new test uses a setting
|
||||
@ -171,12 +176,9 @@ reportStageEnd('drop-1')
|
||||
settings = root.findall('settings/*')
|
||||
for conn_index, c in enumerate(all_connections):
|
||||
for s in settings:
|
||||
try:
|
||||
q = f"set {s.tag} = '{s.text}'"
|
||||
c.execute(q)
|
||||
print(f'set\t{conn_index}\t{c.last_query.elapsed}\t{tsv_escape(q)}')
|
||||
except:
|
||||
print(traceback.format_exc(), file=sys.stderr)
|
||||
# requires clickhouse-driver >= 1.1.5 to accept arbitrary new settings
|
||||
# (https://github.com/mymarilyn/clickhouse-driver/pull/142)
|
||||
c.settings[s.tag] = s.text
|
||||
|
||||
reportStageEnd('settings')
|
||||
|
||||
@ -194,37 +196,40 @@ for t in tables:
|
||||
|
||||
reportStageEnd('preconditions')
|
||||
|
||||
# Run create and fill queries. We will run them simultaneously for both servers,
|
||||
# to save time.
|
||||
# The weird search is to keep the relative order of elements, which matters, and
|
||||
# etree doesn't support the appropriate xpath query.
|
||||
create_query_templates = [q.text for q in root.findall('./*') if q.tag in ('create_query', 'fill_query')]
|
||||
create_queries = substitute_parameters(create_query_templates)
|
||||
if not args.use_existing_tables:
|
||||
# Run create and fill queries. We will run them simultaneously for both
|
||||
# servers, to save time. The weird XML search + filter is because we want to
|
||||
# keep the relative order of elements, and etree doesn't support the
|
||||
# appropriate xpath query.
|
||||
create_query_templates = [q.text for q in root.findall('./*')
|
||||
if q.tag in ('create_query', 'fill_query')]
|
||||
create_queries = substitute_parameters(create_query_templates)
|
||||
|
||||
# Disallow temporary tables, because the clickhouse_driver reconnects on errors,
|
||||
# and temporary tables are destroyed. We want to be able to continue after some
|
||||
# errors.
|
||||
for q in create_queries:
|
||||
if re.search('create temporary table', q, flags=re.IGNORECASE):
|
||||
print(f"Temporary tables are not allowed in performance tests: '{q}'",
|
||||
file = sys.stderr)
|
||||
sys.exit(1)
|
||||
# Disallow temporary tables, because the clickhouse_driver reconnects on
|
||||
# errors, and temporary tables are destroyed. We want to be able to continue
|
||||
# after some errors.
|
||||
for q in create_queries:
|
||||
if re.search('create temporary table', q, flags=re.IGNORECASE):
|
||||
print(f"Temporary tables are not allowed in performance tests: '{q}'",
|
||||
file = sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
def do_create(connection, index, queries):
|
||||
for q in queries:
|
||||
connection.execute(q)
|
||||
print(f'create\t{index}\t{connection.last_query.elapsed}\t{tsv_escape(q)}')
|
||||
def do_create(connection, index, queries):
|
||||
for q in queries:
|
||||
connection.execute(q)
|
||||
print(f'create\t{index}\t{connection.last_query.elapsed}\t{tsv_escape(q)}')
|
||||
|
||||
threads = [Thread(target = do_create, args = (connection, index, create_queries))
|
||||
for index, connection in enumerate(all_connections)]
|
||||
threads = [
|
||||
Thread(target = do_create, args = (connection, index, create_queries))
|
||||
for index, connection in enumerate(all_connections)]
|
||||
|
||||
for t in threads:
|
||||
t.start()
|
||||
for t in threads:
|
||||
t.start()
|
||||
|
||||
for t in threads:
|
||||
t.join()
|
||||
for t in threads:
|
||||
t.join()
|
||||
|
||||
reportStageEnd('create')
|
||||
reportStageEnd('create')
|
||||
|
||||
# By default, test all queries.
|
||||
queries_to_run = range(0, len(test_queries))
|
||||
@ -403,10 +408,11 @@ print(f'profile-total\t{profile_total_seconds}')
|
||||
reportStageEnd('run')
|
||||
|
||||
# Run drop queries
|
||||
drop_queries = substitute_parameters(drop_query_templates)
|
||||
for conn_index, c in enumerate(all_connections):
|
||||
for q in drop_queries:
|
||||
c.execute(q)
|
||||
print(f'drop\t{conn_index}\t{c.last_query.elapsed}\t{tsv_escape(q)}')
|
||||
if not args.keep_created_tables and not args.use_existing_tables:
|
||||
drop_queries = substitute_parameters(drop_query_templates)
|
||||
for conn_index, c in enumerate(all_connections):
|
||||
for q in drop_queries:
|
||||
c.execute(q)
|
||||
print(f'drop\t{conn_index}\t{c.last_query.elapsed}\t{tsv_escape(q)}')
|
||||
|
||||
reportStageEnd('drop-2')
|
||||
|
||||
@ -1,42 +1,42 @@
|
||||
# ClickHouse obfuscator
|
||||
|
||||
Simple tool for table data obfuscation.
|
||||
|
||||
It reads input table and produces output table, that retain some properties of input, but contains different data.
|
||||
It allows to publish almost real production data for usage in benchmarks.
|
||||
|
||||
It is designed to retain the following properties of data:
|
||||
- cardinalities of values (number of distinct values) for every column and for every tuple of columns;
|
||||
- conditional cardinalities: number of distinct values of one column under condition on value of another column;
|
||||
- probability distributions of absolute value of integers; sign of signed integers; exponent and sign for floats;
|
||||
- probability distributions of length of strings;
|
||||
- probability of zero values of numbers; empty strings and arrays, NULLs;
|
||||
- data compression ratio when compressed with LZ77 and entropy family of codecs;
|
||||
- continuity (magnitude of difference) of time values across table; continuity of floating point values.
|
||||
- date component of DateTime values;
|
||||
- UTF-8 validity of string values;
|
||||
- string values continue to look somewhat natural.
|
||||
|
||||
Most of the properties above are viable for performance testing:
|
||||
|
||||
reading data, filtering, aggregation and sorting will work at almost the same speed
|
||||
as on original data due to saved cardinalities, magnitudes, compression ratios, etc.
|
||||
|
||||
It works in deterministic fashion: you define a seed value and transform is totally determined by input data and by seed.
|
||||
Some transforms are one to one and could be reversed, so you need to have large enough seed and keep it in secret.
|
||||
|
||||
It use some cryptographic primitives to transform data, but from the cryptographic point of view,
|
||||
It doesn't do anything properly and you should never consider the result as secure, unless you have other reasons for it.
|
||||
|
||||
It may retain some data you don't want to publish.
|
||||
|
||||
It always leave numbers 0, 1, -1 as is. Also it leaves dates, lengths of arrays and null flags exactly as in source data.
|
||||
For example, you have a column IsMobile in your table with values 0 and 1. In transformed data, it will have the same value.
|
||||
So, the user will be able to count exact ratio of mobile traffic.
|
||||
|
||||
Another example, suppose you have some private data in your table, like user email and you don't want to publish any single email address.
|
||||
If your table is large enough and contain multiple different emails and there is no email that have very high frequency than all others,
|
||||
It will perfectly anonymize all data. But if you have small amount of different values in a column, it can possibly reproduce some of them.
|
||||
And you should take care and look at exact algorithm, how this tool works, and probably fine tune some of it command line parameters.
|
||||
|
||||
This tool works fine only with reasonable amount of data (at least 1000s of rows).
|
||||
# ClickHouse obfuscator
|
||||
|
||||
A simple tool for table data obfuscation.
|
||||
|
||||
It reads an input table and produces an output table, that retains some properties of input, but contains different data.
|
||||
It allows publishing almost real production data for usage in benchmarks.
|
||||
|
||||
It is designed to retain the following properties of data:
|
||||
- cardinalities of values (number of distinct values) for every column and every tuple of columns;
|
||||
- conditional cardinalities: number of distinct values of one column under the condition on the value of another column;
|
||||
- probability distributions of the absolute value of integers; the sign of signed integers; exponent and sign for floats;
|
||||
- probability distributions of the length of strings;
|
||||
- probability of zero values of numbers; empty strings and arrays, `NULL`s;
|
||||
|
||||
- data compression ratio when compressed with LZ77 and entropy family of codecs;
|
||||
- continuity (magnitude of difference) of time values across the table; continuity of floating-point values;
|
||||
- date component of `DateTime` values;
|
||||
|
||||
- UTF-8 validity of string values;
|
||||
- string values look natural.
|
||||
|
||||
Most of the properties above are viable for performance testing:
|
||||
|
||||
reading data, filtering, aggregatio, and sorting will work at almost the same speed
|
||||
as on original data due to saved cardinalities, magnitudes, compression ratios, etc.
|
||||
|
||||
It works in a deterministic fashion: you define a seed value and the transformation is determined by input data and by seed.
|
||||
Some transformations are one to one and could be reversed, so you need to have a large seed and keep it in secret.
|
||||
|
||||
It uses some cryptographic primitives to transform data but from the cryptographic point of view, it doesn't do it properly, that is why you should not consider the result as secure unless you have another reason. The result may retain some data you don't want to publish.
|
||||
|
||||
|
||||
It always leaves 0, 1, -1 numbers, dates, lengths of arrays, and null flags exactly as in source data.
|
||||
For example, you have a column `IsMobile` in your table with values 0 and 1. In transformed data, it will have the same value.
|
||||
|
||||
So, the user will be able to count the exact ratio of mobile traffic.
|
||||
|
||||
Let's give another example. When you have some private data in your table, like user email and you don't want to publish any single email address.
|
||||
If your table is large enough and contains multiple different emails and no email has a very high frequency than all others, it will anonymize all data. But if you have a small number of different values in a column, it can reproduce some of them.
|
||||
You should look at the working algorithm of this tool works, and fine-tune its command line parameters.
|
||||
|
||||
This tool works fine only with an average amount of data (at least 1000s of rows).
|
||||
|
||||
@ -44,8 +44,6 @@ SELECT sum(y) FROM t_null_big
|
||||
└────────┘
|
||||
```
|
||||
|
||||
The `sum` function interprets `NULL` as `0`. In particular, this means that if the function receives input of a selection where all the values are `NULL`, then the result will be `0`, not `NULL`.
|
||||
|
||||
Now you can use the `groupArray` function to create an array from the `y` column:
|
||||
|
||||
``` sql
|
||||
|
||||
@ -0,0 +1,37 @@
|
||||
---
|
||||
toc_priority: 150
|
||||
---
|
||||
|
||||
## initializeAggregation {#initializeaggregation}
|
||||
|
||||
Initializes aggregation for your input rows. It is intended for the functions with the suffix `State`.
|
||||
Use it for tests or to process columns of types `AggregateFunction` and `AggregationgMergeTree`.
|
||||
|
||||
**Syntax**
|
||||
|
||||
``` sql
|
||||
initializeAggregation (aggregate_function, column_1, column_2);
|
||||
```
|
||||
|
||||
**Parameters**
|
||||
|
||||
- `aggregate_function` — Name of the aggregation function. The state of this function — the creating one. [String](../../../sql-reference/data-types/string.md#string).
|
||||
- `column_n` — The column to translate it into the function as it's argument. [String](../../../sql-reference/data-types/string.md#string).
|
||||
|
||||
**Returned value(s)**
|
||||
|
||||
Returns the result of the aggregation for your input rows. The return type will be the same as the return type of function, that `initializeAgregation` takes as first argument.
|
||||
For example for functions with the suffix `State` the return type will be `AggregateFunction`.
|
||||
|
||||
**Example**
|
||||
|
||||
Query:
|
||||
|
||||
```sql
|
||||
SELECT uniqMerge(state) FROM (SELECT initializeAggregation('uniqState', number % 3) AS state FROM system.numbers LIMIT 10000);
|
||||
```
|
||||
Result:
|
||||
|
||||
┌─uniqMerge(state)─┐
|
||||
│ 3 │
|
||||
└──────────────────┘
|
||||
@ -535,18 +535,7 @@ dateDiff('unit', startdate, enddate, [timezone])
|
||||
|
||||
- `unit` — Time unit, in which the returned value is expressed. [String](../../sql-reference/syntax.md#syntax-string-literal).
|
||||
|
||||
Supported values:
|
||||
|
||||
| unit |
|
||||
| ---- |
|
||||
|second |
|
||||
|minute |
|
||||
|hour |
|
||||
|day |
|
||||
|week |
|
||||
|month |
|
||||
|quarter |
|
||||
|year |
|
||||
Supported values: second, minute, hour, day, week, month, quarter, year.
|
||||
|
||||
- `startdate` — The first time value to compare. [Date](../../sql-reference/data-types/date.md) or [DateTime](../../sql-reference/data-types/datetime.md).
|
||||
|
||||
|
||||
@ -6,7 +6,7 @@ toc_title: GROUP BY
|
||||
|
||||
`GROUP BY` clause switches the `SELECT` query into an aggregation mode, which works as follows:
|
||||
|
||||
- `GROUP BY` clause contains a list of expressions (or a single expression, which is considered to be the list of length one). This list acts as a “grouping key”, while each individual expression will be referred to as a “key expressions”.
|
||||
- `GROUP BY` clause contains a list of expressions (or a single expression, which is considered to be the list of length one). This list acts as a “grouping key”, while each individual expression will be referred to as a “key expression”.
|
||||
- All the expressions in the [SELECT](../../../sql-reference/statements/select/index.md), [HAVING](../../../sql-reference/statements/select/having.md), and [ORDER BY](../../../sql-reference/statements/select/order-by.md) clauses **must** be calculated based on key expressions **or** on [aggregate functions](../../../sql-reference/aggregate-functions/index.md) over non-key expressions (including plain columns). In other words, each column selected from the table must be used either in a key expression or inside an aggregate function, but not both.
|
||||
- Result of aggregating `SELECT` query will contain as many rows as there were unique values of “grouping key” in source table. Usually this signficantly reduces the row count, often by orders of magnitude, but not necessarily: row count stays the same if all “grouping key” values were distinct.
|
||||
|
||||
@ -45,6 +45,154 @@ You can see that `GROUP BY` for `y = NULL` summed up `x`, as if `NULL` is this v
|
||||
|
||||
If you pass several keys to `GROUP BY`, the result will give you all the combinations of the selection, as if `NULL` were a specific value.
|
||||
|
||||
## WITH ROLLUP Modifier {#with-rollup-modifier}
|
||||
|
||||
`WITH ROLLUP` modifier is used to calculate subtotals for the key expressions, based on their order in the `GROUP BY` list. The subtotals rows are added after the result table.
|
||||
|
||||
The subtotals are calculated in the reverse order: at first subtotals are calculated for the last key expression in the list, then for the previous one, and so on up to the first key expression.
|
||||
|
||||
In the subtotals rows the values of already "grouped" key expressions are set to `0` or empty line.
|
||||
|
||||
!!! note "Note"
|
||||
Mind that [HAVING](../../../sql-reference/statements/select/having.md) clause can affect the subtotals results.
|
||||
|
||||
**Example**
|
||||
|
||||
Consider the table t:
|
||||
|
||||
```text
|
||||
┌─year─┬─month─┬─day─┐
|
||||
│ 2019 │ 1 │ 5 │
|
||||
│ 2019 │ 1 │ 15 │
|
||||
│ 2020 │ 1 │ 5 │
|
||||
│ 2020 │ 1 │ 15 │
|
||||
│ 2020 │ 10 │ 5 │
|
||||
│ 2020 │ 10 │ 15 │
|
||||
└──────┴───────┴─────┘
|
||||
```
|
||||
|
||||
Query:
|
||||
|
||||
```sql
|
||||
SELECT year, month, day, count(*) FROM t GROUP BY year, month, day WITH ROLLUP;
|
||||
```
|
||||
As `GROUP BY` section has three key expressions, the result contains four tables with subtotals "rolled up" from right to left:
|
||||
|
||||
- `GROUP BY year, month, day`;
|
||||
- `GROUP BY year, month` (and `day` column is filled with zeros);
|
||||
- `GROUP BY year` (now `month, day` columns are both filled with zeros);
|
||||
- and totals (and all three key expression columns are zeros).
|
||||
|
||||
```text
|
||||
┌─year─┬─month─┬─day─┬─count()─┐
|
||||
│ 2020 │ 10 │ 15 │ 1 │
|
||||
│ 2020 │ 1 │ 5 │ 1 │
|
||||
│ 2019 │ 1 │ 5 │ 1 │
|
||||
│ 2020 │ 1 │ 15 │ 1 │
|
||||
│ 2019 │ 1 │ 15 │ 1 │
|
||||
│ 2020 │ 10 │ 5 │ 1 │
|
||||
└──────┴───────┴─────┴─────────┘
|
||||
┌─year─┬─month─┬─day─┬─count()─┐
|
||||
│ 2019 │ 1 │ 0 │ 2 │
|
||||
│ 2020 │ 1 │ 0 │ 2 │
|
||||
│ 2020 │ 10 │ 0 │ 2 │
|
||||
└──────┴───────┴─────┴─────────┘
|
||||
┌─year─┬─month─┬─day─┬─count()─┐
|
||||
│ 2019 │ 0 │ 0 │ 2 │
|
||||
│ 2020 │ 0 │ 0 │ 4 │
|
||||
└──────┴───────┴─────┴─────────┘
|
||||
┌─year─┬─month─┬─day─┬─count()─┐
|
||||
│ 0 │ 0 │ 0 │ 6 │
|
||||
└──────┴───────┴─────┴─────────┘
|
||||
```
|
||||
|
||||
## WITH CUBE Modifier {#with-cube-modifier}
|
||||
|
||||
`WITH CUBE` modifier is used to calculate subtotals for every combination of the key expressions in the `GROUP BY` list. The subtotals rows are added after the result table.
|
||||
|
||||
In the subtotals rows the values of all "grouped" key expressions are set to `0` or empty line.
|
||||
|
||||
!!! note "Note"
|
||||
Mind that [HAVING](../../../sql-reference/statements/select/having.md) clause can affect the subtotals results.
|
||||
|
||||
**Example**
|
||||
|
||||
Consider the table t:
|
||||
|
||||
```text
|
||||
┌─year─┬─month─┬─day─┐
|
||||
│ 2019 │ 1 │ 5 │
|
||||
│ 2019 │ 1 │ 15 │
|
||||
│ 2020 │ 1 │ 5 │
|
||||
│ 2020 │ 1 │ 15 │
|
||||
│ 2020 │ 10 │ 5 │
|
||||
│ 2020 │ 10 │ 15 │
|
||||
└──────┴───────┴─────┘
|
||||
```
|
||||
|
||||
Query:
|
||||
|
||||
```sql
|
||||
SELECT year, month, day, count(*) FROM t GROUP BY year, month, day WITH CUBE;
|
||||
```
|
||||
|
||||
As `GROUP BY` section has three key expressions, the result contains eight tables with subtotals for all key expression combinations:
|
||||
|
||||
- `GROUP BY year, month, day`
|
||||
- `GROUP BY year, month`
|
||||
- `GROUP BY year, day`
|
||||
- `GROUP BY year`
|
||||
- `GROUP BY month, day`
|
||||
- `GROUP BY month`
|
||||
- `GROUP BY day`
|
||||
- and totals.
|
||||
|
||||
Columns, excluded from `GROUP BY`, are filled with zeros.
|
||||
|
||||
```text
|
||||
┌─year─┬─month─┬─day─┬─count()─┐
|
||||
│ 2020 │ 10 │ 15 │ 1 │
|
||||
│ 2020 │ 1 │ 5 │ 1 │
|
||||
│ 2019 │ 1 │ 5 │ 1 │
|
||||
│ 2020 │ 1 │ 15 │ 1 │
|
||||
│ 2019 │ 1 │ 15 │ 1 │
|
||||
│ 2020 │ 10 │ 5 │ 1 │
|
||||
└──────┴───────┴─────┴─────────┘
|
||||
┌─year─┬─month─┬─day─┬─count()─┐
|
||||
│ 2019 │ 1 │ 0 │ 2 │
|
||||
│ 2020 │ 1 │ 0 │ 2 │
|
||||
│ 2020 │ 10 │ 0 │ 2 │
|
||||
└──────┴───────┴─────┴─────────┘
|
||||
┌─year─┬─month─┬─day─┬─count()─┐
|
||||
│ 2020 │ 0 │ 5 │ 2 │
|
||||
│ 2019 │ 0 │ 5 │ 1 │
|
||||
│ 2020 │ 0 │ 15 │ 2 │
|
||||
│ 2019 │ 0 │ 15 │ 1 │
|
||||
└──────┴───────┴─────┴─────────┘
|
||||
┌─year─┬─month─┬─day─┬─count()─┐
|
||||
│ 2019 │ 0 │ 0 │ 2 │
|
||||
│ 2020 │ 0 │ 0 │ 4 │
|
||||
└──────┴───────┴─────┴─────────┘
|
||||
┌─year─┬─month─┬─day─┬─count()─┐
|
||||
│ 0 │ 1 │ 5 │ 2 │
|
||||
│ 0 │ 10 │ 15 │ 1 │
|
||||
│ 0 │ 10 │ 5 │ 1 │
|
||||
│ 0 │ 1 │ 15 │ 2 │
|
||||
└──────┴───────┴─────┴─────────┘
|
||||
┌─year─┬─month─┬─day─┬─count()─┐
|
||||
│ 0 │ 1 │ 0 │ 4 │
|
||||
│ 0 │ 10 │ 0 │ 2 │
|
||||
└──────┴───────┴─────┴─────────┘
|
||||
┌─year─┬─month─┬─day─┬─count()─┐
|
||||
│ 0 │ 0 │ 5 │ 3 │
|
||||
│ 0 │ 0 │ 15 │ 3 │
|
||||
└──────┴───────┴─────┴─────────┘
|
||||
┌─year─┬─month─┬─day─┬─count()─┐
|
||||
│ 0 │ 0 │ 0 │ 6 │
|
||||
└──────┴───────┴─────┴─────────┘
|
||||
```
|
||||
|
||||
|
||||
## WITH TOTALS Modifier {#with-totals-modifier}
|
||||
|
||||
If the `WITH TOTALS` modifier is specified, another row will be calculated. This row will have key columns containing default values (zeros or empty lines), and columns of aggregate functions with the values calculated across all the rows (the “total” values).
|
||||
@ -88,8 +236,6 @@ SELECT
|
||||
FROM hits
|
||||
```
|
||||
|
||||
However, in contrast to standard SQL, if the table doesn’t have any rows (either there aren’t any at all, or there aren’t any after using WHERE to filter), an empty result is returned, and not the result from one of the rows containing the initial values of aggregate functions.
|
||||
|
||||
As opposed to MySQL (and conforming to standard SQL), you can’t get some value of some column that is not in a key or aggregate function (except constant expressions). To work around this, you can use the ‘any’ aggregate function (get the first encountered value) or ‘min/max’.
|
||||
|
||||
Example:
|
||||
@ -105,10 +251,6 @@ GROUP BY domain
|
||||
|
||||
For every different key value encountered, `GROUP BY` calculates a set of aggregate function values.
|
||||
|
||||
`GROUP BY` is not supported for array columns.
|
||||
|
||||
A constant can’t be specified as arguments for aggregate functions. Example: `sum(1)`. Instead of this, you can get rid of the constant. Example: `count()`.
|
||||
|
||||
## Implementation Details {#implementation-details}
|
||||
|
||||
Aggregation is one of the most important features of a column-oriented DBMS, and thus it’s implementation is one of the most heavily optimized parts of ClickHouse. By default, aggregation is done in memory using a hash-table. It has 40+ specializations that are chosen automatically depending on “grouping key” data types.
|
||||
|
||||
@ -20,7 +20,7 @@ SELECT [DISTINCT] expr_list
|
||||
[GLOBAL] [ANY|ALL|ASOF] [INNER|LEFT|RIGHT|FULL|CROSS] [OUTER|SEMI|ANTI] JOIN (subquery)|table (ON <expr_list>)|(USING <column_list>)
|
||||
[PREWHERE expr]
|
||||
[WHERE expr]
|
||||
[GROUP BY expr_list] [WITH TOTALS]
|
||||
[GROUP BY expr_list] [WITH ROLLUP|WITH CUBE] [WITH TOTALS]
|
||||
[HAVING expr]
|
||||
[ORDER BY expr_list] [WITH FILL] [FROM expr] [TO expr] [STEP expr]
|
||||
[LIMIT [offset_value, ]n BY columns]
|
||||
@ -159,4 +159,111 @@ If the query omits the `DISTINCT`, `GROUP BY` and `ORDER BY` clauses and the `IN
|
||||
|
||||
For more information, see the section “Settings”. It is possible to use external sorting (saving temporary tables to a disk) and external aggregation.
|
||||
|
||||
{## [Original article](https://clickhouse.tech/docs/en/sql-reference/statements/select/) ##}
|
||||
## SELECT modifiers {#select-modifiers}
|
||||
|
||||
You can use the following modifiers in `SELECT` queries.
|
||||
|
||||
### APPLY {#apply-modifier}
|
||||
|
||||
Allows you to invoke some function for each row returned by an outer table expression of a query.
|
||||
|
||||
**Syntax:**
|
||||
|
||||
``` sql
|
||||
SELECT <expr> APPLY( <func> ) FROM [db.]table_name
|
||||
```
|
||||
|
||||
**Example:**
|
||||
|
||||
``` sql
|
||||
CREATE TABLE columns_transformers (i Int64, j Int16, k Int64) ENGINE = MergeTree ORDER by (i);
|
||||
INSERT INTO columns_transformers VALUES (100, 10, 324), (120, 8, 23);
|
||||
SELECT * APPLY(sum) FROM columns_transformers;
|
||||
```
|
||||
|
||||
```
|
||||
┌─sum(i)─┬─sum(j)─┬─sum(k)─┐
|
||||
│ 220 │ 18 │ 347 │
|
||||
└────────┴────────┴────────┘
|
||||
```
|
||||
|
||||
### EXCEPT {#except-modifier}
|
||||
|
||||
Specifies the names of one or more columns to exclude from the result. All matching column names are omitted from the output.
|
||||
|
||||
**Syntax:**
|
||||
|
||||
``` sql
|
||||
SELECT <expr> EXCEPT ( col_name1 [, col_name2, col_name3, ...] ) FROM [db.]table_name
|
||||
```
|
||||
|
||||
**Example:**
|
||||
|
||||
``` sql
|
||||
SELECT * EXCEPT (i) from columns_transformers;
|
||||
```
|
||||
|
||||
```
|
||||
┌──j─┬───k─┐
|
||||
│ 10 │ 324 │
|
||||
│ 8 │ 23 │
|
||||
└────┴─────┘
|
||||
```
|
||||
|
||||
### REPLACE {#replace-modifier}
|
||||
|
||||
Specifies one or more [expression aliases](../../../sql-reference/syntax.md#syntax-expression_aliases). Each alias must match a column name from the `SELECT *` statement. In the output column list, the column that matches the alias is replaced by the expression in that `REPLACE`.
|
||||
|
||||
This modifier does not change the names or order of columns. However, it can change the value and the value type.
|
||||
|
||||
**Syntax:**
|
||||
|
||||
``` sql
|
||||
SELECT <expr> REPLACE( <expr> AS col_name) from [db.]table_name
|
||||
```
|
||||
|
||||
**Example:**
|
||||
|
||||
``` sql
|
||||
SELECT * REPLACE(i + 1 AS i) from columns_transformers;
|
||||
```
|
||||
|
||||
```
|
||||
┌───i─┬──j─┬───k─┐
|
||||
│ 101 │ 10 │ 324 │
|
||||
│ 121 │ 8 │ 23 │
|
||||
└─────┴────┴─────┘
|
||||
```
|
||||
|
||||
### Modifier Combinations {#modifier-combinations}
|
||||
|
||||
You can use each modifier separately or combine them.
|
||||
|
||||
**Examples:**
|
||||
|
||||
Using the same modifier multiple times.
|
||||
|
||||
``` sql
|
||||
SELECT COLUMNS('[jk]') APPLY(toString) APPLY(length) APPLY(max) from columns_transformers;
|
||||
```
|
||||
|
||||
```
|
||||
┌─max(length(toString(j)))─┬─max(length(toString(k)))─┐
|
||||
│ 2 │ 3 │
|
||||
└──────────────────────────┴──────────────────────────┘
|
||||
```
|
||||
|
||||
Using multiple modifiers in a single query.
|
||||
|
||||
``` sql
|
||||
SELECT * REPLACE(i + 1 AS i) EXCEPT (j) APPLY(sum) from columns_transformers;
|
||||
```
|
||||
|
||||
```
|
||||
┌─sum(plus(i, 1))─┬─sum(k)─┐
|
||||
│ 222 │ 347 │
|
||||
└─────────────────┴────────┘
|
||||
```
|
||||
|
||||
[Original article](https://clickhouse.tech/docs/en/sql-reference/statements/select/)
|
||||
<!--hide-->
|
||||
|
||||
43
docs/ru/operations/utilities/clickhouse-obfuscator.md
Normal file
43
docs/ru/operations/utilities/clickhouse-obfuscator.md
Normal file
@ -0,0 +1,43 @@
|
||||
# Обфускатор ClickHouse
|
||||
|
||||
Простой инструмент для обфускации табличных данных.
|
||||
|
||||
Он считывает данные входной таблицы и создает выходную таблицу, которая сохраняет некоторые свойства входных данных, но при этом содержит другие данные.
|
||||
|
||||
Это позволяет публиковать практически реальные данные и использовать их в тестах на производительность.
|
||||
|
||||
Обфускатор предназначен для сохранения следующих свойств данных:
|
||||
- кардинальность (количество уникальных данных) для каждого столбца и каждого кортежа столбцов;
|
||||
- условная кардинальность: количество уникальных данных одного столбца в соответствии со значением другого столбца;
|
||||
- вероятностные распределения абсолютного значения целых чисел; знак числа типа Int; показатель степени и знак для чисел с плавающей запятой;
|
||||
- вероятностное распределение длины строк;
|
||||
- вероятность нулевых значений чисел; пустые строки и массивы, `NULL`;
|
||||
- степень сжатия данных алгоритмом LZ77 и семейством энтропийных кодеков;
|
||||
|
||||
- непрерывность (величина разницы) значений времени в таблице; непрерывность значений с плавающей запятой;
|
||||
- дату из значений `DateTime`;
|
||||
|
||||
- кодировка UTF-8 значений строки;
|
||||
- строковые значения выглядят естественным образом.
|
||||
|
||||
|
||||
Большинство перечисленных выше свойств пригодны для тестирования производительности. Чтение данных, фильтрация, агрегирование и сортировка будут работать почти с той же скоростью, что и исходные данные, благодаря сохраненной кардинальности, величине, степени сжатия и т. д.
|
||||
|
||||
Он работает детерминированно. Вы задаёте значение инициализатора, а преобразование полностью определяется входными данными и инициализатором.
|
||||
|
||||
Некоторые преобразования выполняются один к одному, и их можно отменить. Поэтому нужно использовать большое значение инициализатора и хранить его в секрете.
|
||||
|
||||
|
||||
Обфускатор использует некоторые криптографические примитивы для преобразования данных, но, с криптографической точки зрения, результат будет небезопасным. В нем могут сохраниться данные, которые не следует публиковать.
|
||||
|
||||
|
||||
Он всегда оставляет без изменений числа 0, 1, -1, даты, длины массивов и нулевые флаги.
|
||||
Например, если у вас есть столбец `IsMobile` в таблице со значениями 0 и 1, то в преобразованных данных он будет иметь то же значение.
|
||||
|
||||
Таким образом, пользователь сможет посчитать точное соотношение мобильного трафика.
|
||||
|
||||
Давайте рассмотрим случай, когда у вас есть какие-то личные данные в таблице (например, электронная почта пользователя), и вы не хотите их публиковать.
|
||||
Если ваша таблица достаточно большая и содержит несколько разных электронных почтовых адресов, и ни один из них не встречается часто, то обфускатор полностью анонимизирует все данные. Но, если у вас есть небольшое количество разных значений в столбце, он может скопировать некоторые из них.
|
||||
В этом случае вам следует посмотреть на алгоритм работы инструмента и настроить параметры командной строки.
|
||||
|
||||
Обфускатор полезен в работе со средним объемом данных (не менее 1000 строк).
|
||||
@ -44,8 +44,6 @@ SELECT sum(y) FROM t_null_big
|
||||
└────────┘
|
||||
```
|
||||
|
||||
Функция `sum` работает с `NULL` как с `0`. В частности, это означает, что если на вход в функцию подать выборку, где все значения `NULL`, то результат будет `0`, а не `NULL`.
|
||||
|
||||
Теперь с помощью функции `groupArray` сформируем массив из столбца `y`:
|
||||
|
||||
``` sql
|
||||
|
||||
@ -0,0 +1,40 @@
|
||||
---
|
||||
toc_priority: 150
|
||||
---
|
||||
|
||||
## initializeAggregation {#initializeaggregation}
|
||||
|
||||
Инициализирует агрегацию для введеных строчек. Предназначена для функций с суффиксом `State`.
|
||||
Поможет вам проводить тесты или работать со столбцами типов: `AggregateFunction` и `AggregationgMergeTree`.
|
||||
|
||||
**Синтаксис**
|
||||
|
||||
``` sql
|
||||
initializeAggregation (aggregate_function, column_1, column_2);
|
||||
```
|
||||
|
||||
**Параметры**
|
||||
|
||||
- `aggregate_function` — название функции агрегации, состояние которой нужно создать. [String](../../../sql-reference/data-types/string.md#string).
|
||||
- `column_n` — столбец, который передается в функцию агрегации как аргумент. [String](../../../sql-reference/data-types/string.md#string).
|
||||
|
||||
**Возвращаемое значение**
|
||||
|
||||
Возвращает результат агрегации введенной информации. Тип возвращаемого значения такой же, как и для функции, которая становится первым аргументом для `initializeAgregation`.
|
||||
|
||||
Пример:
|
||||
|
||||
Возвращаемый тип функций с суффиксом `State` — `AggregateFunction`.
|
||||
|
||||
**Пример**
|
||||
|
||||
Запрос:
|
||||
|
||||
```sql
|
||||
SELECT uniqMerge(state) FROM (SELECT initializeAggregation('uniqState', number % 3) AS state FROM system.numbers LIMIT 10000);
|
||||
```
|
||||
Результат:
|
||||
|
||||
┌─uniqMerge(state)─┐
|
||||
│ 3 │
|
||||
└──────────────────┘
|
||||
@ -43,6 +43,153 @@ toc_title: GROUP BY
|
||||
|
||||
Если в `GROUP BY` передать несколько ключей, то в результате мы получим все комбинации выборки, как если бы `NULL` был конкретным значением.
|
||||
|
||||
## Модификатор WITH ROLLUP {#with-rollup-modifier}
|
||||
|
||||
Модификатор `WITH ROLLUP` применяется для подсчета подытогов для ключевых выражений. При этом учитывается порядок следования ключевых выражений в списке `GROUP BY`. Подытоги подсчитываются в обратном порядке: сначала для последнего ключевого выражения в списке, потом для предпоследнего и так далее вплоть до самого первого ключевого выражения.
|
||||
|
||||
Строки с подытогами добавляются в конец результирующей таблицы. В колонках, по которым строки уже сгруппированы, указывается значение `0` или пустая строка.
|
||||
|
||||
!!! note "Примечание"
|
||||
Если в запросе есть секция [HAVING](../../../sql-reference/statements/select/having.md), она может повлиять на результаты расчета подытогов.
|
||||
|
||||
**Пример**
|
||||
|
||||
Рассмотрим таблицу t:
|
||||
|
||||
```text
|
||||
┌─year─┬─month─┬─day─┐
|
||||
│ 2019 │ 1 │ 5 │
|
||||
│ 2019 │ 1 │ 15 │
|
||||
│ 2020 │ 1 │ 5 │
|
||||
│ 2020 │ 1 │ 15 │
|
||||
│ 2020 │ 10 │ 5 │
|
||||
│ 2020 │ 10 │ 15 │
|
||||
└──────┴───────┴─────┘
|
||||
```
|
||||
|
||||
Запрос:
|
||||
|
||||
```sql
|
||||
SELECT year, month, day, count(*) FROM t GROUP BY year, month, day WITH ROLLUP;
|
||||
```
|
||||
|
||||
Поскольку секция `GROUP BY` содержит три ключевых выражения, результат состоит из четырех таблиц с подытогами, которые как бы "сворачиваются" справа налево:
|
||||
|
||||
- `GROUP BY year, month, day`;
|
||||
- `GROUP BY year, month` (а колонка `day` заполнена нулями);
|
||||
- `GROUP BY year` (теперь обе колонки `month, day` заполнены нулями);
|
||||
- и общий итог (все три колонки с ключевыми выражениями заполнены нулями).
|
||||
|
||||
```text
|
||||
┌─year─┬─month─┬─day─┬─count()─┐
|
||||
│ 2020 │ 10 │ 15 │ 1 │
|
||||
│ 2020 │ 1 │ 5 │ 1 │
|
||||
│ 2019 │ 1 │ 5 │ 1 │
|
||||
│ 2020 │ 1 │ 15 │ 1 │
|
||||
│ 2019 │ 1 │ 15 │ 1 │
|
||||
│ 2020 │ 10 │ 5 │ 1 │
|
||||
└──────┴───────┴─────┴─────────┘
|
||||
┌─year─┬─month─┬─day─┬─count()─┐
|
||||
│ 2019 │ 1 │ 0 │ 2 │
|
||||
│ 2020 │ 1 │ 0 │ 2 │
|
||||
│ 2020 │ 10 │ 0 │ 2 │
|
||||
└──────┴───────┴─────┴─────────┘
|
||||
┌─year─┬─month─┬─day─┬─count()─┐
|
||||
│ 2019 │ 0 │ 0 │ 2 │
|
||||
│ 2020 │ 0 │ 0 │ 4 │
|
||||
└──────┴───────┴─────┴─────────┘
|
||||
┌─year─┬─month─┬─day─┬─count()─┐
|
||||
│ 0 │ 0 │ 0 │ 6 │
|
||||
└──────┴───────┴─────┴─────────┘
|
||||
```
|
||||
|
||||
## Модификатор WITH CUBE {#with-cube-modifier}
|
||||
|
||||
Модификатор `WITH CUBE` применятеся для расчета подытогов по всем комбинациям группировки ключевых выражений в списке `GROUP BY`.
|
||||
|
||||
Строки с подытогами добавляются в конец результирующей таблицы. В колонках, по которым выполняется группировка, указывается значение `0` или пустая строка.
|
||||
|
||||
!!! note "Примечание"
|
||||
Если в запросе есть секция [HAVING](../../../sql-reference/statements/select/having.md), она может повлиять на результаты расчета подытогов.
|
||||
|
||||
**Пример**
|
||||
|
||||
Рассмотрим таблицу t:
|
||||
|
||||
```text
|
||||
┌─year─┬─month─┬─day─┐
|
||||
│ 2019 │ 1 │ 5 │
|
||||
│ 2019 │ 1 │ 15 │
|
||||
│ 2020 │ 1 │ 5 │
|
||||
│ 2020 │ 1 │ 15 │
|
||||
│ 2020 │ 10 │ 5 │
|
||||
│ 2020 │ 10 │ 15 │
|
||||
└──────┴───────┴─────┘
|
||||
```
|
||||
|
||||
Query:
|
||||
|
||||
```sql
|
||||
SELECT year, month, day, count(*) FROM t GROUP BY year, month, day WITH CUBE;
|
||||
```
|
||||
|
||||
Поскольку секция `GROUP BY` содержит три ключевых выражения, результат состоит из восьми таблиц с подытогами — по таблице для каждой комбинации ключевых выражений:
|
||||
|
||||
- `GROUP BY year, month, day`
|
||||
- `GROUP BY year, month`
|
||||
- `GROUP BY year, day`
|
||||
- `GROUP BY year`
|
||||
- `GROUP BY month, day`
|
||||
- `GROUP BY month`
|
||||
- `GROUP BY day`
|
||||
- и общий итог.
|
||||
|
||||
Колонки, которые не участвуют в `GROUP BY`, заполнены нулями.
|
||||
|
||||
```text
|
||||
┌─year─┬─month─┬─day─┬─count()─┐
|
||||
│ 2020 │ 10 │ 15 │ 1 │
|
||||
│ 2020 │ 1 │ 5 │ 1 │
|
||||
│ 2019 │ 1 │ 5 │ 1 │
|
||||
│ 2020 │ 1 │ 15 │ 1 │
|
||||
│ 2019 │ 1 │ 15 │ 1 │
|
||||
│ 2020 │ 10 │ 5 │ 1 │
|
||||
└──────┴───────┴─────┴─────────┘
|
||||
┌─year─┬─month─┬─day─┬─count()─┐
|
||||
│ 2019 │ 1 │ 0 │ 2 │
|
||||
│ 2020 │ 1 │ 0 │ 2 │
|
||||
│ 2020 │ 10 │ 0 │ 2 │
|
||||
└──────┴───────┴─────┴─────────┘
|
||||
┌─year─┬─month─┬─day─┬─count()─┐
|
||||
│ 2020 │ 0 │ 5 │ 2 │
|
||||
│ 2019 │ 0 │ 5 │ 1 │
|
||||
│ 2020 │ 0 │ 15 │ 2 │
|
||||
│ 2019 │ 0 │ 15 │ 1 │
|
||||
└──────┴───────┴─────┴─────────┘
|
||||
┌─year─┬─month─┬─day─┬─count()─┐
|
||||
│ 2019 │ 0 │ 0 │ 2 │
|
||||
│ 2020 │ 0 │ 0 │ 4 │
|
||||
└──────┴───────┴─────┴─────────┘
|
||||
┌─year─┬─month─┬─day─┬─count()─┐
|
||||
│ 0 │ 1 │ 5 │ 2 │
|
||||
│ 0 │ 10 │ 15 │ 1 │
|
||||
│ 0 │ 10 │ 5 │ 1 │
|
||||
│ 0 │ 1 │ 15 │ 2 │
|
||||
└──────┴───────┴─────┴─────────┘
|
||||
┌─year─┬─month─┬─day─┬─count()─┐
|
||||
│ 0 │ 1 │ 0 │ 4 │
|
||||
│ 0 │ 10 │ 0 │ 2 │
|
||||
└──────┴───────┴─────┴─────────┘
|
||||
┌─year─┬─month─┬─day─┬─count()─┐
|
||||
│ 0 │ 0 │ 5 │ 3 │
|
||||
│ 0 │ 0 │ 15 │ 3 │
|
||||
└──────┴───────┴─────┴─────────┘
|
||||
┌─year─┬─month─┬─day─┬─count()─┐
|
||||
│ 0 │ 0 │ 0 │ 6 │
|
||||
└──────┴───────┴─────┴─────────┘
|
||||
```
|
||||
|
||||
|
||||
## Модификатор WITH TOTALS {#with-totals-modifier}
|
||||
|
||||
Если указан модификатор `WITH TOTALS`, то будет посчитана ещё одна строчка, в которой в столбцах-ключах будут содержаться значения по умолчанию (нули, пустые строки), а в столбцах агрегатных функций - значения, посчитанные по всем строкам («тотальные» значения).
|
||||
@ -86,8 +233,6 @@ SELECT
|
||||
FROM hits
|
||||
```
|
||||
|
||||
Но, в отличие от стандартного SQL, если в таблице нет строк (вообще нет или после фильтрации с помощью WHERE), в качестве результата возвращается пустой результат, а не результат из одной строки, содержащий «начальные» значения агрегатных функций.
|
||||
|
||||
В отличие от MySQL (и в соответствии со стандартом SQL), вы не можете получить какое-нибудь значение некоторого столбца, не входящего в ключ или агрегатную функцию (за исключением константных выражений). Для обхода этого вы можете воспользоваться агрегатной функцией any (получить первое попавшееся значение) или min/max.
|
||||
|
||||
Пример:
|
||||
@ -103,10 +248,6 @@ GROUP BY domain
|
||||
|
||||
GROUP BY вычисляет для каждого встретившегося различного значения ключей, набор значений агрегатных функций.
|
||||
|
||||
Не поддерживается GROUP BY по столбцам-массивам.
|
||||
|
||||
Не поддерживается указание констант в качестве аргументов агрегатных функций. Пример: `sum(1)`. Вместо этого, вы можете избавиться от констант. Пример: `count()`.
|
||||
|
||||
## Детали реализации {#implementation-details}
|
||||
|
||||
Агрегация является одной из наиболее важных возможностей столбцовых СУБД, и поэтому её реализация является одной из наиболее сильно оптимизированных частей ClickHouse. По умолчанию агрегирование выполняется в памяти с помощью хэш-таблицы. Она имеет более 40 специализаций, которые выбираются автоматически в зависимости от типов данных ключа группировки.
|
||||
|
||||
@ -18,7 +18,7 @@ SELECT [DISTINCT] expr_list
|
||||
[GLOBAL] [ANY|ALL|ASOF] [INNER|LEFT|RIGHT|FULL|CROSS] [OUTER|SEMI|ANTI] JOIN (subquery)|table (ON <expr_list>)|(USING <column_list>)
|
||||
[PREWHERE expr]
|
||||
[WHERE expr]
|
||||
[GROUP BY expr_list] [WITH TOTALS]
|
||||
[GROUP BY expr_list] [WITH ROLLUP|WITH CUBE] [WITH TOTALS]
|
||||
[HAVING expr]
|
||||
[ORDER BY expr_list] [WITH FILL] [FROM expr] [TO expr] [STEP expr]
|
||||
[LIMIT [offset_value, ]n BY columns]
|
||||
|
||||
@ -6,7 +6,7 @@
|
||||
|
||||
我们使用RoaringBitmap实际存储位图对象，当基数小于或等于32时，它使用Set保存。当基数大于32时，它使用RoaringBitmap保存。这也是为什么低基数集的存储更快的原因。
|
||||
|
||||
有关RoaringBitmap的更多信息，请参阅：[呻吟声](https://github.com/RoaringBitmap/CRoaring)。
|
||||
有关RoaringBitmap的更多信息，请参阅：[RoaringBitmap](https://github.com/RoaringBitmap/CRoaring)。
|
||||
|
||||
## bitmapBuild {#bitmapbuild}
|
||||
|
||||
|
||||
1
programs/server/config.d/logging_no_rotate.xml
Symbolic link
1
programs/server/config.d/logging_no_rotate.xml
Symbolic link
@ -0,0 +1 @@
|
||||
../../../tests/config/config.d/logging_no_rotate.xml
|
||||
@ -11,6 +11,9 @@
|
||||
<level>trace</level>
|
||||
<log>/var/log/clickhouse-server/clickhouse-server.log</log>
|
||||
<errorlog>/var/log/clickhouse-server/clickhouse-server.err.log</errorlog>
|
||||
<!-- Rotation policy
|
||||
See https://github.com/pocoproject/poco/blob/poco-1.9.4-release/Foundation/include/Poco/FileChannel.h#L54-L85
|
||||
-->
|
||||
<size>1000M</size>
|
||||
<count>10</count>
|
||||
<!-- <console>1</console> --> <!-- Default behavior is autodetection (log to console if not daemon mode and is tty) -->
|
||||
|
||||
@ -1,6 +1,7 @@
|
||||
<html> <!-- TODO If I write DOCTYPE HTML something changes but I don't know what. -->
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<link rel="icon" href="data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHdpZHRoPSI1NCIgaGVpZ2h0PSI0OCIgdmlld0JveD0iMCAwIDkgOCI+PHN0eWxlPi5ve2ZpbGw6I2ZjMH0ucntmaWxsOnJlZH08L3N0eWxlPjxwYXRoIGQ9Ik0wLDcgaDEgdjEgaC0xIHoiIGNsYXNzPSJyIi8+PHBhdGggZD0iTTAsMCBoMSB2NyBoLTEgeiIgY2xhc3M9Im8iLz48cGF0aCBkPSJNMiwwIGgxIHY4IGgtMSB6IiBjbGFzcz0ibyIvPjxwYXRoIGQ9Ik00LDAgaDEgdjggaC0xIHoiIGNsYXNzPSJvIi8+PHBhdGggZD0iTTYsMCBoMSB2OCBoLTEgeiIgY2xhc3M9Im8iLz48cGF0aCBkPSJNOCwzLjI1IGgxIHYxLjUgaC0xIHoiIGNsYXNzPSJvIi8+PC9zdmc+">
|
||||
<title>ClickHouse Query</title>
|
||||
|
||||
<!-- Code Style:
|
||||
@ -21,26 +22,11 @@
|
||||
|
||||
<!-- Development Roadmap:
|
||||
|
||||
1. Add indication that the query was sent and when the query has been finished.
|
||||
Do not use any animated spinners. Just a text or check mark.
|
||||
Eliminate race conditions (results from the previous query should be ignored on arrival, the previous request should be cancelled).
|
||||
|
||||
2. Support readonly servers.
|
||||
1. Support readonly servers.
|
||||
Check if readonly = 1 (with SELECT FROM system.settings) to avoid sending settings. It can be done once on address/credentials change.
|
||||
It can be done in background, e.g. wait 100 ms after address/credentials change and do the check.
|
||||
Also it can provide visual indication that credentials are correct.
|
||||
|
||||
3. Add history in localstorage. Integrate with history API.
|
||||
There can be a counter in localstorage, that will be appended to location #fragment.
|
||||
The 'back', 'forward' buttons in browser should work.
|
||||
Also there should be UI element to list all the queries from history and select from the list.
|
||||
|
||||
4. Trivial sharing capabilities.
|
||||
Sharing is only possible when system.query_log is accessible. Read the X-ClickHouse-QueryId from the response.
|
||||
Share button will: - emit SYSTEM FLUSH LOGS if not readonly; - find the query in the query_log;
|
||||
- generate an URL with the query id and: server address if not equal to the URL's host; user name if not default;
|
||||
indication that password should be entered in case of non-empty password.
|
||||
|
||||
-->
|
||||
|
||||
<style type="text/css">
|
||||
@ -273,6 +259,22 @@
|
||||
{
|
||||
color: var(--null-color);
|
||||
}
|
||||
|
||||
#hourglass
|
||||
{
|
||||
display: none;
|
||||
padding-left: 1rem;
|
||||
font-size: 110%;
|
||||
color: #888;
|
||||
}
|
||||
|
||||
#check-mark
|
||||
{
|
||||
display: none;
|
||||
padding-left: 1rem;
|
||||
font-size: 110%;
|
||||
color: #080;
|
||||
}
|
||||
</style>
|
||||
</head>
|
||||
|
||||
@ -286,6 +288,8 @@
|
||||
<div id="run_div">
|
||||
<button class="shadow" id="run">Run</button>
|
||||
<span class="hint"> (Ctrl+Enter)</span>
|
||||
<span id="hourglass">⧗</span>
|
||||
<span id="check-mark">✔</span>
|
||||
<span id="stats"></span>
|
||||
<span id="toggle-dark">🌑</span><span id="toggle-light">🌞</span>
|
||||
</div>
|
||||
@ -299,50 +303,117 @@
|
||||
|
||||
<script type="text/javascript">
|
||||
|
||||
/// Incremental request number. When response is received,
|
||||
/// if it's request number does not equal to the current request number, response will be ignored.
|
||||
/// This is to avoid race conditions.
|
||||
var request_num = 0;
|
||||
|
||||
/// Save query in history only if it is different.
|
||||
var previous_query = '';
|
||||
|
||||
/// Substitute the address of the server where the page is served.
|
||||
if (location.protocol != 'file:') {
|
||||
document.getElementById('url').value = location.origin;
|
||||
}
|
||||
|
||||
function post()
|
||||
/// Substitute user name if it's specified in the query string
|
||||
var user_from_url = (new URL(window.location)).searchParams.get('user');
|
||||
if (user_from_url) {
|
||||
document.getElementById('user').value = user_from_url;
|
||||
}
|
||||
|
||||
function postImpl(posted_request_num, query)
|
||||
{
|
||||
/// TODO: Avoid race condition on subsequent requests when responses may come out of order.
|
||||
/// TODO: Check if URL already contains query string (append parameters).
|
||||
|
||||
var user = document.getElementById('user').value;
|
||||
var password = document.getElementById('password').value;
|
||||
|
||||
var url = document.getElementById('url').value +
|
||||
/// Ask server to allow cross-domain requests.
|
||||
'?add_http_cors_header=1' +
|
||||
'&user=' + encodeURIComponent(document.getElementById('user').value) +
|
||||
'&password=' + encodeURIComponent(document.getElementById('password').value) +
|
||||
'&user=' + encodeURIComponent(user) +
|
||||
'&password=' + encodeURIComponent(password) +
|
||||
'&default_format=JSONCompact' +
|
||||
/// Safety settings to prevent results that browser cannot display.
|
||||
'&max_result_rows=1000&max_result_bytes=10000000&result_overflow_mode=break';
|
||||
|
||||
var query = document.getElementById('query').value;
|
||||
var xhr = new XMLHttpRequest;
|
||||
|
||||
xhr.open('POST', url, true);
|
||||
xhr.send(query);
|
||||
|
||||
xhr.onreadystatechange = function()
|
||||
{
|
||||
if (this.readyState === XMLHttpRequest.DONE) {
|
||||
if (this.status === 200) {
|
||||
var json;
|
||||
try { json = JSON.parse(this.response); } catch (e) {}
|
||||
if (json !== undefined && json.statistics !== undefined) {
|
||||
renderResult(json);
|
||||
} else {
|
||||
renderUnparsedResult(this.response);
|
||||
}
|
||||
} else {
|
||||
/// TODO: Proper rendering of network errors.
|
||||
renderError(this.response);
|
||||
if (posted_request_num != request_num) {
|
||||
return;
|
||||
} else if (this.readyState === XMLHttpRequest.DONE) {
|
||||
renderResponse(this.status, this.response);
|
||||
|
||||
/// The query is saved in browser history (in state JSON object)
|
||||
/// as well as in URL fragment identifier.
|
||||
if (query != previous_query) {
|
||||
previous_query = query;
|
||||
var title = "ClickHouse Query: " + query;
|
||||
history.pushState(
|
||||
{
|
||||
query: query,
|
||||
status: this.status,
|
||||
response: this.response.length > 100000 ? null : this.response /// Lower than the browser's limit.
|
||||
},
|
||||
title,
|
||||
window.location.pathname + '?user=' + encodeURIComponent(user) + '#' + window.btoa(query));
|
||||
document.title = title;
|
||||
}
|
||||
} else {
|
||||
//console.log(this);
|
||||
}
|
||||
}
|
||||
|
||||
document.getElementById('check-mark').style.display = 'none';
|
||||
document.getElementById('hourglass').style.display = 'inline';
|
||||
|
||||
xhr.send(query);
|
||||
}
|
||||
|
||||
function renderResponse(status, response) {
|
||||
document.getElementById('hourglass').style.display = 'none';
|
||||
|
||||
if (status === 200) {
|
||||
var json;
|
||||
try { json = JSON.parse(response); } catch (e) {}
|
||||
if (json !== undefined && json.statistics !== undefined) {
|
||||
renderResult(json);
|
||||
} else {
|
||||
renderUnparsedResult(response);
|
||||
}
|
||||
document.getElementById('check-mark').style.display = 'inline';
|
||||
} else {
|
||||
/// TODO: Proper rendering of network errors.
|
||||
renderError(response);
|
||||
}
|
||||
}
|
||||
|
||||
window.onpopstate = function(event) {
|
||||
if (!event.state) {
|
||||
return;
|
||||
}
|
||||
document.getElementById('query').value = event.state.query;
|
||||
if (!event.state.response) {
|
||||
clear();
|
||||
return;
|
||||
}
|
||||
renderResponse(event.state.status, event.state.response);
|
||||
};
|
||||
|
||||
if (window.location.hash) {
|
||||
document.getElementById('query').value = window.atob(window.location.hash.substr(1));
|
||||
}
|
||||
|
||||
function post()
|
||||
{
|
||||
++request_num;
|
||||
var query = document.getElementById('query').value;
|
||||
postImpl(request_num, query);
|
||||
}
|
||||
|
||||
document.getElementById('run').onclick = function()
|
||||
@ -350,7 +421,7 @@
|
||||
post();
|
||||
}
|
||||
|
||||
document.getElementById('query').onkeypress = function(event)
|
||||
document.onkeypress = function(event)
|
||||
{
|
||||
/// Firefox has code 13 for Enter and Chromium has code 10.
|
||||
if (event.ctrlKey && (event.charCode == 13 || event.charCode == 10)) {
|
||||
@ -372,6 +443,9 @@
|
||||
document.getElementById('error').style.display = 'none';
|
||||
|
||||
document.getElementById('stats').innerText = '';
|
||||
|
||||
document.getElementById('hourglass').style.display = 'none';
|
||||
document.getElementById('check-mark').style.display = 'none';
|
||||
}
|
||||
|
||||
function renderResult(response)
|
||||
@ -443,7 +517,7 @@
|
||||
function renderError(response)
|
||||
{
|
||||
clear();
|
||||
document.getElementById('error').innerText = response;
|
||||
document.getElementById('error').innerText = response ? response : "No response.";
|
||||
document.getElementById('error').style.display = 'block';
|
||||
}
|
||||
|
||||
|
||||
@ -80,7 +80,7 @@ public:
|
||||
}
|
||||
|
||||
if (!isUnsignedInteger(arguments[1]))
|
||||
throw Exception("Second argument of aggregate function " + getName() + " must be integer.", ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT);
|
||||
throw Exception("Second argument of aggregate function " + getName() + " must be unsigned integer.", ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT);
|
||||
|
||||
if (default_value.isNull())
|
||||
default_value = type->getDefault();
|
||||
|
||||
@ -44,10 +44,10 @@ namespace
|
||||
}
|
||||
}
|
||||
|
||||
DatabaseDictionary::DatabaseDictionary(const String & name_, const Context & global_context_)
|
||||
DatabaseDictionary::DatabaseDictionary(const String & name_, const Context & context_)
|
||||
: IDatabase(name_)
|
||||
, log(&Poco::Logger::get("DatabaseDictionary(" + database_name + ")"))
|
||||
, global_context(global_context_.getGlobalContext())
|
||||
, global_context(context_.getGlobalContext())
|
||||
{
|
||||
}
|
||||
|
||||
|
||||
@ -22,7 +22,7 @@ namespace DB
|
||||
class DatabaseDictionary final : public IDatabase
|
||||
{
|
||||
public:
|
||||
DatabaseDictionary(const String & name_, const Context & global_context);
|
||||
DatabaseDictionary(const String & name_, const Context & context_);
|
||||
|
||||
String getEngineName() const override
|
||||
{
|
||||
|
||||
@ -13,6 +13,7 @@
|
||||
# include <Databases/MySQL/FetchTablesColumnsList.h>
|
||||
# include <Formats/MySQLBlockInputStream.h>
|
||||
# include <IO/Operators.h>
|
||||
# include <Interpreters/Context.h>
|
||||
# include <Parsers/ASTCreateQuery.h>
|
||||
# include <Parsers/ASTFunction.h>
|
||||
# include <Parsers/ParserCreateQuery.h>
|
||||
|
||||
@ -120,7 +120,7 @@ XDBCDictionarySource::XDBCDictionarySource(
|
||||
, invalidate_query{config_.getString(config_prefix_ + ".invalidate_query", "")}
|
||||
, bridge_helper{bridge_}
|
||||
, timeouts{ConnectionTimeouts::getHTTPTimeouts(context_)}
|
||||
, global_context(context_)
|
||||
, global_context(context_.getGlobalContext())
|
||||
{
|
||||
bridge_url = bridge_helper->getMainURI();
|
||||
|
||||
|
||||
@ -34,6 +34,7 @@ namespace ErrorCodes
|
||||
extern const int UNKNOWN_FORMAT;
|
||||
extern const int INCORRECT_DISK_INDEX;
|
||||
extern const int NOT_IMPLEMENTED;
|
||||
extern const int PATH_ACCESS_DENIED;
|
||||
}
|
||||
|
||||
|
||||
@ -93,6 +94,7 @@ namespace
|
||||
/// Metadata file version.
|
||||
static constexpr UInt32 VERSION_ABSOLUTE_PATHS = 1;
|
||||
static constexpr UInt32 VERSION_RELATIVE_PATHS = 2;
|
||||
static constexpr UInt32 VERSION_READ_ONLY_FLAG = 3;
|
||||
|
||||
using PathAndSize = std::pair<String, size_t>;
|
||||
|
||||
@ -109,6 +111,8 @@ namespace
|
||||
std::vector<PathAndSize> s3_objects;
|
||||
/// Number of references (hardlinks) to this metadata file.
|
||||
UInt32 ref_count;
|
||||
/// Flag indicates that file is read only.
|
||||
bool read_only = false;
|
||||
|
||||
/// Load metadata by path or create empty if `create` flag is set.
|
||||
explicit Metadata(const String & s3_root_path_, const String & disk_path_, const String & metadata_file_path_, bool create = false)
|
||||
@ -122,10 +126,10 @@ namespace
|
||||
UInt32 version;
|
||||
readIntText(version, buf);
|
||||
|
||||
if (version != VERSION_RELATIVE_PATHS && version != VERSION_ABSOLUTE_PATHS)
|
||||
if (version < VERSION_ABSOLUTE_PATHS || version > VERSION_READ_ONLY_FLAG)
|
||||
throw Exception(
|
||||
"Unknown metadata file version. Path: " + disk_path + metadata_file_path
|
||||
+ " Version: " + std::to_string(version) + ", Maximum expected version: " + std::to_string(VERSION_RELATIVE_PATHS),
|
||||
+ " Version: " + std::to_string(version) + ", Maximum expected version: " + std::to_string(VERSION_READ_ONLY_FLAG),
|
||||
ErrorCodes::UNKNOWN_FORMAT);
|
||||
|
||||
assertChar('\n', buf);
|
||||
@ -158,6 +162,12 @@ namespace
|
||||
|
||||
readIntText(ref_count, buf);
|
||||
assertChar('\n', buf);
|
||||
|
||||
if (version >= VERSION_READ_ONLY_FLAG)
|
||||
{
|
||||
readBoolText(read_only, buf);
|
||||
assertChar('\n', buf);
|
||||
}
|
||||
}
|
||||
|
||||
void addObject(const String & path, size_t size)
|
||||
@ -189,6 +199,9 @@ namespace
|
||||
writeIntText(ref_count, buf);
|
||||
writeChar('\n', buf);
|
||||
|
||||
writeBoolText(read_only, buf);
|
||||
writeChar('\n', buf);
|
||||
|
||||
buf.finalize();
|
||||
if (sync)
|
||||
buf.sync();
|
||||
@ -632,6 +645,12 @@ std::unique_ptr<ReadBufferFromFileBase> DiskS3::readFile(const String & path, si
|
||||
std::unique_ptr<WriteBufferFromFileBase> DiskS3::writeFile(const String & path, size_t buf_size, WriteMode mode, size_t estimated_size, size_t)
|
||||
{
|
||||
bool exist = exists(path);
|
||||
if (exist)
|
||||
{
|
||||
Metadata metadata(s3_root_path, metadata_path, path);
|
||||
if (metadata.read_only)
|
||||
throw Exception("File is read-only: " + path, ErrorCodes::PATH_ACCESS_DENIED);
|
||||
}
|
||||
/// Path to store new S3 object.
|
||||
auto s3_path = getRandomName();
|
||||
bool is_multipart = estimated_size >= min_multi_part_upload_size;
|
||||
@ -797,7 +816,11 @@ void DiskS3::createFile(const String & path)
|
||||
|
||||
void DiskS3::setReadOnly(const String & path)
|
||||
{
|
||||
Poco::File(metadata_path + path).setReadOnly(true);
|
||||
/// We should store read only flag inside metadata file (instead of using FS flag),
|
||||
/// because we modify metadata file when create hard-links from it.
|
||||
Metadata metadata(s3_root_path, metadata_path, path);
|
||||
metadata.read_only = true;
|
||||
metadata.save();
|
||||
}
|
||||
|
||||
int DiskS3::open(const String & /*path*/, mode_t /*mode*/) const
|
||||
|
||||
@ -154,6 +154,9 @@ struct ConvertImpl
|
||||
{
|
||||
if constexpr (std::is_same_v<FromFieldType, UInt128> || std::is_same_v<ToFieldType, UInt128>)
|
||||
throw Exception("Unexpected UInt128 to big int conversion", ErrorCodes::NOT_IMPLEMENTED);
|
||||
/// If From Data is Nan or Inf, throw exception
|
||||
else if (!isFinite(vec_from[i]))
|
||||
throw Exception("Unexpected inf or nan to big int conversion", ErrorCodes::NOT_IMPLEMENTED);
|
||||
else
|
||||
vec_to[i] = bigint_cast<ToFieldType>(vec_from[i]);
|
||||
}
|
||||
|
||||
@ -336,9 +336,9 @@ struct ContextShared
|
||||
ReplicatedFetchList replicated_fetch_list;
|
||||
ConfigurationPtr users_config; /// Config with the users, profiles and quotas sections.
|
||||
InterserverIOHandler interserver_io_handler; /// Handler for interserver communication.
|
||||
std::optional<BackgroundSchedulePool> buffer_flush_schedule_pool; /// A thread pool that can do background flush for Buffer tables.
|
||||
std::optional<BackgroundSchedulePool> schedule_pool; /// A thread pool that can run different jobs in background (used in replicated tables)
|
||||
std::optional<BackgroundSchedulePool> distributed_schedule_pool; /// A thread pool that can run different jobs in background (used for distributed sends)
|
||||
mutable std::optional<BackgroundSchedulePool> buffer_flush_schedule_pool; /// A thread pool that can do background flush for Buffer tables.
|
||||
mutable std::optional<BackgroundSchedulePool> schedule_pool; /// A thread pool that can run different jobs in background (used in replicated tables)
|
||||
mutable std::optional<BackgroundSchedulePool> distributed_schedule_pool; /// A thread pool that can run different jobs in background (used for distributed sends)
|
||||
MultiVersion<Macros> macros; /// Substitutions extracted from config.
|
||||
std::unique_ptr<DDLWorker> ddl_worker; /// Process ddl commands from zk.
|
||||
/// Rules for selecting the compression settings, depending on the size of the part.
|
||||
@ -484,7 +484,7 @@ Context Context::createGlobal(ContextShared * shared)
|
||||
|
||||
void Context::initGlobal()
|
||||
{
|
||||
DatabaseCatalog::init(this);
|
||||
DatabaseCatalog::init(*this);
|
||||
TemporaryLiveViewCleaner::init(*this);
|
||||
}
|
||||
|
||||
@ -1401,7 +1401,7 @@ void Context::dropCaches() const
|
||||
shared->mark_cache->reset();
|
||||
}
|
||||
|
||||
BackgroundSchedulePool & Context::getBufferFlushSchedulePool()
|
||||
BackgroundSchedulePool & Context::getBufferFlushSchedulePool() const
|
||||
{
|
||||
auto lock = getLock();
|
||||
if (!shared->buffer_flush_schedule_pool)
|
||||
@ -1443,7 +1443,7 @@ BackgroundTaskSchedulingSettings Context::getBackgroundMoveTaskSchedulingSetting
|
||||
return task_settings;
|
||||
}
|
||||
|
||||
BackgroundSchedulePool & Context::getSchedulePool()
|
||||
BackgroundSchedulePool & Context::getSchedulePool() const
|
||||
{
|
||||
auto lock = getLock();
|
||||
if (!shared->schedule_pool)
|
||||
@ -1454,7 +1454,7 @@ BackgroundSchedulePool & Context::getSchedulePool()
|
||||
return *shared->schedule_pool;
|
||||
}
|
||||
|
||||
BackgroundSchedulePool & Context::getDistributedSchedulePool()
|
||||
BackgroundSchedulePool & Context::getDistributedSchedulePool() const
|
||||
{
|
||||
auto lock = getLock();
|
||||
if (!shared->distributed_schedule_pool)
|
||||
|
||||
@ -519,9 +519,9 @@ public:
|
||||
BackgroundTaskSchedulingSettings getBackgroundProcessingTaskSchedulingSettings() const;
|
||||
BackgroundTaskSchedulingSettings getBackgroundMoveTaskSchedulingSettings() const;
|
||||
|
||||
BackgroundSchedulePool & getBufferFlushSchedulePool();
|
||||
BackgroundSchedulePool & getSchedulePool();
|
||||
BackgroundSchedulePool & getDistributedSchedulePool();
|
||||
BackgroundSchedulePool & getBufferFlushSchedulePool() const;
|
||||
BackgroundSchedulePool & getSchedulePool() const;
|
||||
BackgroundSchedulePool & getDistributedSchedulePool() const;
|
||||
|
||||
/// Has distributed_ddl configuration or not.
|
||||
bool hasDistributedDDL() const;
|
||||
|
||||
@ -39,7 +39,7 @@ namespace ErrorCodes
|
||||
|
||||
TemporaryTableHolder::TemporaryTableHolder(const Context & context_,
|
||||
const TemporaryTableHolder::Creator & creator, const ASTPtr & query)
|
||||
: global_context(&context_.getGlobalContext())
|
||||
: global_context(context_.getGlobalContext())
|
||||
, temporary_tables(DatabaseCatalog::instance().getDatabaseForTemporaryTables().get())
|
||||
{
|
||||
ASTPtr original_create;
|
||||
@ -62,7 +62,7 @@ TemporaryTableHolder::TemporaryTableHolder(const Context & context_,
|
||||
}
|
||||
auto table_id = StorageID(DatabaseCatalog::TEMPORARY_DATABASE, global_name, id);
|
||||
auto table = creator(table_id);
|
||||
temporary_tables->createTable(*global_context, global_name, table, original_create);
|
||||
temporary_tables->createTable(global_context, global_name, table, original_create);
|
||||
table->startup();
|
||||
}
|
||||
|
||||
@ -107,7 +107,7 @@ TemporaryTableHolder & TemporaryTableHolder::operator = (TemporaryTableHolder &&
|
||||
TemporaryTableHolder::~TemporaryTableHolder()
|
||||
{
|
||||
if (id != UUIDHelpers::Nil)
|
||||
temporary_tables->dropTable(*global_context, "_tmp_" + toString(id));
|
||||
temporary_tables->dropTable(global_context, "_tmp_" + toString(id));
|
||||
}
|
||||
|
||||
StorageID TemporaryTableHolder::getGlobalTableID() const
|
||||
@ -117,7 +117,7 @@ StorageID TemporaryTableHolder::getGlobalTableID() const
|
||||
|
||||
StoragePtr TemporaryTableHolder::getTable() const
|
||||
{
|
||||
auto table = temporary_tables->tryGetTable("_tmp_" + toString(id), *global_context);
|
||||
auto table = temporary_tables->tryGetTable("_tmp_" + toString(id), global_context);
|
||||
if (!table)
|
||||
throw Exception("Temporary table " + getGlobalTableID().getNameForLogs() + " not found", ErrorCodes::LOGICAL_ERROR);
|
||||
return table;
|
||||
@ -126,13 +126,13 @@ StoragePtr TemporaryTableHolder::getTable() const
|
||||
|
||||
void DatabaseCatalog::loadDatabases()
|
||||
{
|
||||
drop_delay_sec = global_context->getConfigRef().getInt("database_atomic_delay_before_drop_table_sec", default_drop_delay_sec);
|
||||
drop_delay_sec = global_context.getConfigRef().getInt("database_atomic_delay_before_drop_table_sec", default_drop_delay_sec);
|
||||
|
||||
auto db_for_temporary_and_external_tables = std::make_shared<DatabaseMemory>(TEMPORARY_DATABASE, *global_context);
|
||||
auto db_for_temporary_and_external_tables = std::make_shared<DatabaseMemory>(TEMPORARY_DATABASE, global_context);
|
||||
attachDatabase(TEMPORARY_DATABASE, db_for_temporary_and_external_tables);
|
||||
|
||||
loadMarkedAsDroppedTables();
|
||||
auto task_holder = global_context->getSchedulePool().createTask("DatabaseCatalog", [this](){ this->dropTableDataTask(); });
|
||||
auto task_holder = global_context.getSchedulePool().createTask("DatabaseCatalog", [this](){ this->dropTableDataTask(); });
|
||||
drop_task = std::make_unique<BackgroundSchedulePoolTaskHolder>(std::move(task_holder));
|
||||
(*drop_task)->activate();
|
||||
std::lock_guard lock{tables_marked_dropped_mutex};
|
||||
@ -328,11 +328,11 @@ DatabasePtr DatabaseCatalog::detachDatabase(const String & database_name, bool d
|
||||
if (drop)
|
||||
{
|
||||
/// Delete the database.
|
||||
db->drop(*global_context);
|
||||
db->drop(global_context);
|
||||
|
||||
/// Old ClickHouse versions did not store database.sql files
|
||||
Poco::File database_metadata_file(
|
||||
global_context->getPath() + "metadata/" + escapeForFileName(database_name) + ".sql");
|
||||
global_context.getPath() + "metadata/" + escapeForFileName(database_name) + ".sql");
|
||||
if (database_metadata_file.exists())
|
||||
database_metadata_file.remove(false);
|
||||
}
|
||||
@ -505,14 +505,12 @@ void DatabaseCatalog::updateUUIDMapping(const UUID & uuid, DatabasePtr database,
|
||||
|
||||
std::unique_ptr<DatabaseCatalog> DatabaseCatalog::database_catalog;
|
||||
|
||||
DatabaseCatalog::DatabaseCatalog(Context * global_context_)
|
||||
DatabaseCatalog::DatabaseCatalog(Context & global_context_)
|
||||
: global_context(global_context_), log(&Poco::Logger::get("DatabaseCatalog"))
|
||||
{
|
||||
if (!global_context)
|
||||
throw Exception("DatabaseCatalog is not initialized. It's a bug.", ErrorCodes::LOGICAL_ERROR);
|
||||
}
|
||||
|
||||
DatabaseCatalog & DatabaseCatalog::init(Context * global_context_)
|
||||
DatabaseCatalog & DatabaseCatalog::init(Context & global_context_)
|
||||
{
|
||||
if (database_catalog)
|
||||
{
|
||||
@ -651,7 +649,7 @@ void DatabaseCatalog::loadMarkedAsDroppedTables()
|
||||
/// we should load them and enqueue cleanup to remove data from store/ and metadata from ZooKeeper
|
||||
|
||||
std::map<String, StorageID> dropped_metadata;
|
||||
String path = global_context->getPath() + "metadata_dropped/";
|
||||
String path = global_context.getPath() + "metadata_dropped/";
|
||||
|
||||
if (!std::filesystem::exists(path))
|
||||
{
|
||||
@ -706,7 +704,7 @@ void DatabaseCatalog::loadMarkedAsDroppedTables()
|
||||
|
||||
String DatabaseCatalog::getPathForDroppedMetadata(const StorageID & table_id) const
|
||||
{
|
||||
return global_context->getPath() + "metadata_dropped/" +
|
||||
return global_context.getPath() + "metadata_dropped/" +
|
||||
escapeForFileName(table_id.getDatabaseName()) + "." +
|
||||
escapeForFileName(table_id.getTableName()) + "." +
|
||||
toString(table_id.uuid) + ".sql";
|
||||
@ -729,7 +727,7 @@ void DatabaseCatalog::enqueueDroppedTableCleanup(StorageID table_id, StoragePtr
|
||||
{
|
||||
/// Try load table from metadata to drop it correctly (e.g. remove metadata from zk or remove data from all volumes)
|
||||
LOG_INFO(log, "Trying load partially dropped table {} from {}", table_id.getNameForLogs(), dropped_metadata_path);
|
||||
ASTPtr ast = DatabaseOnDisk::parseQueryFromMetadata(log, *global_context, dropped_metadata_path, /*throw_on_error*/ false, /*remove_empty*/false);
|
||||
ASTPtr ast = DatabaseOnDisk::parseQueryFromMetadata(log, global_context, dropped_metadata_path, /*throw_on_error*/ false, /*remove_empty*/false);
|
||||
auto * create = typeid_cast<ASTCreateQuery *>(ast.get());
|
||||
assert(!create || create->uuid == table_id.uuid);
|
||||
|
||||
@ -740,7 +738,7 @@ void DatabaseCatalog::enqueueDroppedTableCleanup(StorageID table_id, StoragePtr
|
||||
create->table = table_id.table_name;
|
||||
try
|
||||
{
|
||||
table = createTableFromAST(*create, table_id.getDatabaseName(), data_path, *global_context, false).second;
|
||||
table = createTableFromAST(*create, table_id.getDatabaseName(), data_path, global_context, false).second;
|
||||
table->is_dropped = true;
|
||||
}
|
||||
catch (...)
|
||||
@ -867,7 +865,7 @@ void DatabaseCatalog::dropTableFinally(const TableMarkedAsDropped & table)
|
||||
|
||||
/// Even if table is not loaded, try remove its data from disk.
|
||||
/// TODO remove data from all volumes
|
||||
String data_path = global_context->getPath() + "store/" + getPathForUUID(table.table_id.uuid);
|
||||
String data_path = global_context.getPath() + "store/" + getPathForUUID(table.table_id.uuid);
|
||||
Poco::File table_data_dir{data_path};
|
||||
if (table_data_dir.exists())
|
||||
{
|
||||
@ -901,7 +899,7 @@ String DatabaseCatalog::resolveDictionaryName(const String & name) const
|
||||
String maybe_database_name = name.substr(0, pos);
|
||||
String maybe_table_name = name.substr(pos + 1);
|
||||
|
||||
auto db_and_table = tryGetDatabaseAndTable({maybe_database_name, maybe_table_name}, *global_context);
|
||||
auto db_and_table = tryGetDatabaseAndTable({maybe_database_name, maybe_table_name}, global_context);
|
||||
if (!db_and_table.first)
|
||||
return name;
|
||||
assert(db_and_table.second);
|
||||
|
||||
@ -73,7 +73,6 @@ struct TemporaryTableHolder : boost::noncopyable
|
||||
{
|
||||
typedef std::function<StoragePtr(const StorageID &)> Creator;
|
||||
|
||||
TemporaryTableHolder() = default;
|
||||
TemporaryTableHolder(const Context & context, const Creator & creator, const ASTPtr & query = {});
|
||||
|
||||
/// Creates temporary table with Engine=Memory
|
||||
@ -95,7 +94,7 @@ struct TemporaryTableHolder : boost::noncopyable
|
||||
|
||||
operator bool () const { return id != UUIDHelpers::Nil; }
|
||||
|
||||
const Context * global_context = nullptr;
|
||||
const Context & global_context;
|
||||
IDatabase * temporary_tables = nullptr;
|
||||
UUID id = UUIDHelpers::Nil;
|
||||
};
|
||||
@ -111,7 +110,7 @@ public:
|
||||
static constexpr const char * TEMPORARY_DATABASE = "_temporary_and_external_tables";
|
||||
static constexpr const char * SYSTEM_DATABASE = "system";
|
||||
|
||||
static DatabaseCatalog & init(Context * global_context_);
|
||||
static DatabaseCatalog & init(Context & global_context_);
|
||||
static DatabaseCatalog & instance();
|
||||
static void shutdown();
|
||||
|
||||
@ -199,7 +198,7 @@ private:
|
||||
// make emplace(global_context_) compile with private constructor ¯\_(ツ)_/¯.
|
||||
static std::unique_ptr<DatabaseCatalog> database_catalog;
|
||||
|
||||
DatabaseCatalog(Context * global_context_);
|
||||
DatabaseCatalog(Context & global_context_);
|
||||
void assertDatabaseExistsUnlocked(const String & database_name) const;
|
||||
void assertDatabaseDoesntExistUnlocked(const String & database_name) const;
|
||||
|
||||
@ -240,7 +239,7 @@ private:
|
||||
using UUIDToDatabaseMap = std::unordered_map<UUID, DatabasePtr>;
|
||||
|
||||
/// For some reason Context is required to get Storage from Database object
|
||||
Context * global_context;
|
||||
Context & global_context;
|
||||
mutable std::mutex databases_mutex;
|
||||
|
||||
ViewDependencies view_dependencies;
|
||||
|
||||
@ -42,8 +42,8 @@ namespace
|
||||
}
|
||||
|
||||
|
||||
ExternalLoaderDatabaseConfigRepository::ExternalLoaderDatabaseConfigRepository(IDatabase & database_, const Context & global_context_)
|
||||
: global_context(global_context_.getGlobalContext())
|
||||
ExternalLoaderDatabaseConfigRepository::ExternalLoaderDatabaseConfigRepository(IDatabase & database_, const Context & context_)
|
||||
: global_context(context_.getGlobalContext())
|
||||
, database_name(database_.getDatabaseName())
|
||||
, database(database_)
|
||||
{
|
||||
|
||||
@ -77,7 +77,7 @@ ASTs InterpreterShowAccessQuery::getCreateAndGrantQueries() const
|
||||
for (const auto & entity : entities)
|
||||
{
|
||||
create_queries.push_back(InterpreterShowCreateAccessEntityQuery::getCreateQuery(*entity, access_control));
|
||||
if (entity->isTypeOf(EntityType::USER) || entity->isTypeOf(EntityType::USER))
|
||||
if (entity->isTypeOf(EntityType::USER) || entity->isTypeOf(EntityType::ROLE))
|
||||
boost::range::push_back(grant_queries, InterpreterShowGrantsQuery::getGrantQueries(*entity, access_control));
|
||||
}
|
||||
|
||||
|
||||
@ -225,7 +225,7 @@ void JSONCompactEachRowRowInputFormat::readField(size_t index, MutableColumns &
|
||||
}
|
||||
catch (Exception & e)
|
||||
{
|
||||
e.addMessage("(while read the value of key " + getPort().getHeader().getByPosition(index).name + ")");
|
||||
e.addMessage("(while reading the value of key " + getPort().getHeader().getByPosition(index).name + ")");
|
||||
throw;
|
||||
}
|
||||
}
|
||||
|
||||
@ -163,7 +163,7 @@ void JSONEachRowRowInputFormat::readField(size_t index, MutableColumns & columns
|
||||
}
|
||||
catch (Exception & e)
|
||||
{
|
||||
e.addMessage("(while read the value of key " + columnName(index) + ")");
|
||||
e.addMessage("(while reading the value of key " + columnName(index) + ")");
|
||||
throw;
|
||||
}
|
||||
}
|
||||
|
||||
@ -102,7 +102,7 @@ bool RegexpRowInputFormat::readField(size_t index, MutableColumns & columns)
|
||||
}
|
||||
catch (Exception & e)
|
||||
{
|
||||
e.addMessage("(while read the value of column " + getPort().getHeader().getByPosition(index).name + ")");
|
||||
e.addMessage("(while reading the value of column " + getPort().getHeader().getByPosition(index).name + ")");
|
||||
throw;
|
||||
}
|
||||
return read;
|
||||
|
||||
@ -328,6 +328,16 @@ void MySQLHandler::comQuery(ReadBuffer & payload)
|
||||
|
||||
Context query_context = connection_context;
|
||||
|
||||
std::atomic<size_t> affected_rows {0};
|
||||
auto prev = query_context.getProgressCallback();
|
||||
query_context.setProgressCallback([&, prev = prev](const Progress & progress)
|
||||
{
|
||||
if (prev)
|
||||
prev(progress);
|
||||
|
||||
affected_rows += progress.written_rows;
|
||||
});
|
||||
|
||||
executeQuery(should_replace ? replacement : payload, *out, true, query_context,
|
||||
[&with_output](const String &, const String &, const String &, const String &)
|
||||
{
|
||||
@ -336,7 +346,7 @@ void MySQLHandler::comQuery(ReadBuffer & payload)
|
||||
);
|
||||
|
||||
if (!with_output)
|
||||
packet_endpoint->sendPacket(OKPacket(0x00, client_capability_flags, 0, 0, 0), true);
|
||||
packet_endpoint->sendPacket(OKPacket(0x00, client_capability_flags, affected_rows, 0, 0), true);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@ -83,13 +83,13 @@ StorageDistributedDirectoryMonitor::StorageDistributedDirectoryMonitor(
|
||||
: storage(storage_)
|
||||
, pool(std::move(pool_))
|
||||
, path{path_ + '/'}
|
||||
, should_batch_inserts(storage.global_context->getSettingsRef().distributed_directory_monitor_batch_inserts)
|
||||
, min_batched_block_size_rows(storage.global_context->getSettingsRef().min_insert_block_size_rows)
|
||||
, min_batched_block_size_bytes(storage.global_context->getSettingsRef().min_insert_block_size_bytes)
|
||||
, should_batch_inserts(storage.global_context.getSettingsRef().distributed_directory_monitor_batch_inserts)
|
||||
, min_batched_block_size_rows(storage.global_context.getSettingsRef().min_insert_block_size_rows)
|
||||
, min_batched_block_size_bytes(storage.global_context.getSettingsRef().min_insert_block_size_bytes)
|
||||
, current_batch_file_path{path + "current_batch.txt"}
|
||||
, default_sleep_time{storage.global_context->getSettingsRef().distributed_directory_monitor_sleep_time_ms.totalMilliseconds()}
|
||||
, default_sleep_time{storage.global_context.getSettingsRef().distributed_directory_monitor_sleep_time_ms.totalMilliseconds()}
|
||||
, sleep_time{default_sleep_time}
|
||||
, max_sleep_time{storage.global_context->getSettingsRef().distributed_directory_monitor_max_sleep_time_ms.totalMilliseconds()}
|
||||
, max_sleep_time{storage.global_context.getSettingsRef().distributed_directory_monitor_max_sleep_time_ms.totalMilliseconds()}
|
||||
, log{&Poco::Logger::get(getLoggerName())}
|
||||
, monitor_blocker(monitor_blocker_)
|
||||
, metric_pending_files(CurrentMetrics::DistributedFilesToInsert, 0)
|
||||
@ -249,7 +249,7 @@ ConnectionPoolPtr StorageDistributedDirectoryMonitor::createPool(const std::stri
|
||||
|
||||
auto pools = createPoolsForAddresses(name, pool_factory);
|
||||
|
||||
const auto settings = storage.global_context->getSettings();
|
||||
const auto settings = storage.global_context.getSettings();
|
||||
return pools.size() == 1 ? pools.front() : std::make_shared<ConnectionPoolWithFailover>(pools,
|
||||
settings.load_balancing,
|
||||
settings.distributed_replica_error_half_life.totalSeconds(),
|
||||
@ -308,7 +308,7 @@ bool StorageDistributedDirectoryMonitor::processFiles(const std::map<UInt64, std
|
||||
void StorageDistributedDirectoryMonitor::processFile(const std::string & file_path)
|
||||
{
|
||||
LOG_TRACE(log, "Started processing `{}`", file_path);
|
||||
auto timeouts = ConnectionTimeouts::getTCPTimeoutsWithFailover(storage.global_context->getSettingsRef());
|
||||
auto timeouts = ConnectionTimeouts::getTCPTimeoutsWithFailover(storage.global_context.getSettingsRef());
|
||||
|
||||
try
|
||||
{
|
||||
@ -483,7 +483,7 @@ struct StorageDistributedDirectoryMonitor::Batch
|
||||
|
||||
Poco::File{tmp_file}.renameTo(parent.current_batch_file_path);
|
||||
}
|
||||
auto timeouts = ConnectionTimeouts::getTCPTimeoutsWithFailover(parent.storage.global_context->getSettingsRef());
|
||||
auto timeouts = ConnectionTimeouts::getTCPTimeoutsWithFailover(parent.storage.global_context.getSettingsRef());
|
||||
auto connection = parent.pool->get(timeouts);
|
||||
|
||||
bool batch_broken = false;
|
||||
|
||||
@ -6,6 +6,7 @@
|
||||
#include <Storages/Kafka/ReadBufferFromKafkaConsumer.h>
|
||||
#include <Processors/Formats/InputStreamFromInputFormat.h>
|
||||
#include <common/logger_useful.h>
|
||||
#include <Interpreters/Context.h>
|
||||
|
||||
namespace DB
|
||||
{
|
||||
|
||||
@ -1,7 +1,6 @@
|
||||
#pragma once
|
||||
|
||||
#include <DataStreams/IBlockInputStream.h>
|
||||
#include <Interpreters/Context.h>
|
||||
|
||||
#include <Storages/Kafka/StorageKafka.h>
|
||||
#include <Storages/Kafka/ReadBufferFromKafkaConsumer.h>
|
||||
|
||||
@ -1,4 +1,4 @@
|
||||
#include "KafkaBlockOutputStream.h"
|
||||
#include <Storages/Kafka/KafkaBlockOutputStream.h>
|
||||
|
||||
#include <Formats/FormatFactory.h>
|
||||
#include <Storages/Kafka/WriteBufferToKafkaProducer.h>
|
||||
|
||||
@ -1,7 +1,6 @@
|
||||
#pragma once
|
||||
|
||||
#include <DataStreams/IBlockOutputStream.h>
|
||||
#include <Interpreters/Context.h>
|
||||
#include <Storages/Kafka/StorageKafka.h>
|
||||
|
||||
namespace DB
|
||||
|
||||
@ -33,6 +33,7 @@
|
||||
#include <Common/typeid_cast.h>
|
||||
#include <common/logger_useful.h>
|
||||
#include <Common/quoteString.h>
|
||||
#include <Interpreters/Context.h>
|
||||
#include <Processors/Sources/SourceFromInputStream.h>
|
||||
#include <librdkafka/rdkafka.h>
|
||||
#include <common/getFQDNOrHostName.h>
|
||||
@ -169,7 +170,7 @@ namespace
|
||||
|
||||
StorageKafka::StorageKafka(
|
||||
const StorageID & table_id_,
|
||||
Context & context_,
|
||||
const Context & context_,
|
||||
const ColumnsDescription & columns_,
|
||||
std::unique_ptr<KafkaSettings> kafka_settings_)
|
||||
: IStorage(table_id_)
|
||||
|
||||
@ -4,7 +4,6 @@
|
||||
#include <Storages/IStorage.h>
|
||||
#include <Storages/Kafka/Buffer_fwd.h>
|
||||
#include <Storages/Kafka/KafkaSettings.h>
|
||||
#include <Interpreters/Context.h>
|
||||
#include <Common/SettingsChanges.h>
|
||||
|
||||
#include <Poco/Semaphore.h>
|
||||
@ -69,13 +68,13 @@ public:
|
||||
protected:
|
||||
StorageKafka(
|
||||
const StorageID & table_id_,
|
||||
Context & context_,
|
||||
const Context & context_,
|
||||
const ColumnsDescription & columns_,
|
||||
std::unique_ptr<KafkaSettings> kafka_settings_);
|
||||
|
||||
private:
|
||||
// Configuration and state
|
||||
Context & global_context;
|
||||
const Context & global_context;
|
||||
std::unique_ptr<KafkaSettings> kafka_settings;
|
||||
const Names topics;
|
||||
const String brokers;
|
||||
|
||||
@ -45,6 +45,7 @@ constexpr auto REPLICATION_PROTOCOL_VERSION_WITH_PARTS_SIZE = 1;
|
||||
constexpr auto REPLICATION_PROTOCOL_VERSION_WITH_PARTS_SIZE_AND_TTL_INFOS = 2;
|
||||
constexpr auto REPLICATION_PROTOCOL_VERSION_WITH_PARTS_TYPE = 3;
|
||||
constexpr auto REPLICATION_PROTOCOL_VERSION_WITH_PARTS_DEFAULT_COMPRESSION = 4;
|
||||
constexpr auto REPLICATION_PROTOCOL_VERSION_WITH_PARTS_UUID = 5;
|
||||
|
||||
|
||||
std::string getEndpointId(const std::string & node_id)
|
||||
@ -109,7 +110,7 @@ void Service::processQuery(const Poco::Net::HTMLForm & params, ReadBuffer & /*bo
|
||||
}
|
||||
|
||||
/// We pretend to work as older server version, to be sure that client will correctly process our version
|
||||
response.addCookie({"server_protocol_version", toString(std::min(client_protocol_version, REPLICATION_PROTOCOL_VERSION_WITH_PARTS_DEFAULT_COMPRESSION))});
|
||||
response.addCookie({"server_protocol_version", toString(std::min(client_protocol_version, REPLICATION_PROTOCOL_VERSION_WITH_PARTS_UUID))});
|
||||
|
||||
++total_sends;
|
||||
SCOPE_EXIT({--total_sends;});
|
||||
@ -138,12 +139,14 @@ void Service::processQuery(const Poco::Net::HTMLForm & params, ReadBuffer & /*bo
|
||||
if (client_protocol_version >= REPLICATION_PROTOCOL_VERSION_WITH_PARTS_TYPE)
|
||||
writeStringBinary(part->getType().toString(), out);
|
||||
|
||||
if (client_protocol_version >= REPLICATION_PROTOCOL_VERSION_WITH_PARTS_UUID)
|
||||
writeUUIDText(part->uuid, out);
|
||||
|
||||
if (isInMemoryPart(part))
|
||||
sendPartFromMemory(part, out);
|
||||
else
|
||||
{
|
||||
bool send_default_compression_file = client_protocol_version >= REPLICATION_PROTOCOL_VERSION_WITH_PARTS_DEFAULT_COMPRESSION;
|
||||
sendPartFromDisk(part, out, send_default_compression_file);
|
||||
sendPartFromDisk(part, out, client_protocol_version);
|
||||
}
|
||||
}
|
||||
catch (const NetException &)
|
||||
@ -176,7 +179,7 @@ void Service::sendPartFromMemory(const MergeTreeData::DataPartPtr & part, WriteB
|
||||
block_out.write(part_in_memory->block);
|
||||
}
|
||||
|
||||
void Service::sendPartFromDisk(const MergeTreeData::DataPartPtr & part, WriteBuffer & out, bool send_default_compression_file)
|
||||
void Service::sendPartFromDisk(const MergeTreeData::DataPartPtr & part, WriteBuffer & out, int client_protocol_version)
|
||||
{
|
||||
/// We'll take a list of files from the list of checksums.
|
||||
MergeTreeData::DataPart::Checksums checksums = part->checksums;
|
||||
@ -184,8 +187,9 @@ void Service::sendPartFromDisk(const MergeTreeData::DataPartPtr & part, WriteBuf
|
||||
auto file_names_without_checksums = part->getFileNamesWithoutChecksums();
|
||||
for (const auto & file_name : file_names_without_checksums)
|
||||
{
|
||||
if (!send_default_compression_file && file_name == IMergeTreeDataPart::DEFAULT_COMPRESSION_CODEC_FILE_NAME)
|
||||
if (client_protocol_version < REPLICATION_PROTOCOL_VERSION_WITH_PARTS_DEFAULT_COMPRESSION && file_name == IMergeTreeDataPart::DEFAULT_COMPRESSION_CODEC_FILE_NAME)
|
||||
continue;
|
||||
|
||||
checksums.files[file_name] = {};
|
||||
}
|
||||
|
||||
@ -263,7 +267,7 @@ MergeTreeData::MutableDataPartPtr Fetcher::fetchPart(
|
||||
{
|
||||
{"endpoint", getEndpointId(replica_path)},
|
||||
{"part", part_name},
|
||||
{"client_protocol_version", toString(REPLICATION_PROTOCOL_VERSION_WITH_PARTS_DEFAULT_COMPRESSION)},
|
||||
{"client_protocol_version", toString(REPLICATION_PROTOCOL_VERSION_WITH_PARTS_UUID)},
|
||||
{"compress", "false"}
|
||||
});
|
||||
|
||||
@ -318,6 +322,10 @@ MergeTreeData::MutableDataPartPtr Fetcher::fetchPart(
|
||||
if (server_protocol_version >= REPLICATION_PROTOCOL_VERSION_WITH_PARTS_TYPE)
|
||||
readStringBinary(part_type, in);
|
||||
|
||||
UUID part_uuid = UUIDHelpers::Nil;
|
||||
if (server_protocol_version >= REPLICATION_PROTOCOL_VERSION_WITH_PARTS_UUID)
|
||||
readUUIDText(part_uuid, in);
|
||||
|
||||
auto storage_id = data.getStorageID();
|
||||
String new_part_path = part_type == "InMemory" ? "memory" : data.getFullPathOnDisk(reservation->getDisk()) + part_name + "/";
|
||||
auto entry = data.global_context.getReplicatedFetchList().insert(
|
||||
@ -327,12 +335,14 @@ MergeTreeData::MutableDataPartPtr Fetcher::fetchPart(
|
||||
|
||||
in.setNextCallback(ReplicatedFetchReadCallback(*entry));
|
||||
|
||||
return part_type == "InMemory" ? downloadPartToMemory(part_name, metadata_snapshot, std::move(reservation), in)
|
||||
: downloadPartToDisk(part_name, replica_path, to_detached, tmp_prefix_, sync, std::move(reservation), in);
|
||||
|
||||
return part_type == "InMemory" ? downloadPartToMemory(part_name, part_uuid, metadata_snapshot, std::move(reservation), in)
|
||||
: downloadPartToDisk(part_name, replica_path, to_detached, tmp_prefix_, sync, std::move(reservation), in);
|
||||
}
|
||||
|
||||
MergeTreeData::MutableDataPartPtr Fetcher::downloadPartToMemory(
|
||||
const String & part_name,
|
||||
const UUID & part_uuid,
|
||||
const StorageMetadataPtr & metadata_snapshot,
|
||||
ReservationPtr reservation,
|
||||
PooledReadWriteBufferFromHTTP & in)
|
||||
@ -348,6 +358,7 @@ MergeTreeData::MutableDataPartPtr Fetcher::downloadPartToMemory(
|
||||
MergeTreeData::MutableDataPartPtr new_data_part =
|
||||
std::make_shared<MergeTreeDataPartInMemory>(data, part_name, volume);
|
||||
|
||||
new_data_part->uuid = part_uuid;
|
||||
new_data_part->is_temp = true;
|
||||
new_data_part->setColumns(block.getNamesAndTypesList());
|
||||
new_data_part->minmax_idx.update(block, data.minmax_idx_columns);
|
||||
|
||||
@ -32,7 +32,7 @@ public:
|
||||
private:
|
||||
MergeTreeData::DataPartPtr findPart(const String & name);
|
||||
void sendPartFromMemory(const MergeTreeData::DataPartPtr & part, WriteBuffer & out);
|
||||
void sendPartFromDisk(const MergeTreeData::DataPartPtr & part, WriteBuffer & out, bool send_default_compression_file);
|
||||
void sendPartFromDisk(const MergeTreeData::DataPartPtr & part, WriteBuffer & out, int client_protocol_version);
|
||||
|
||||
private:
|
||||
/// StorageReplicatedMergeTree::shutdown() waits for all parts exchange handlers to finish,
|
||||
@ -80,6 +80,7 @@ private:
|
||||
|
||||
MergeTreeData::MutableDataPartPtr downloadPartToMemory(
|
||||
const String & part_name,
|
||||
const UUID & part_uuid,
|
||||
const StorageMetadataPtr & metadata_snapshot,
|
||||
ReservationPtr reservation,
|
||||
PooledReadWriteBufferFromHTTP & in);
|
||||
|
||||
@ -410,6 +410,7 @@ void IMergeTreeDataPart::loadColumnsChecksumsIndexes(bool require_columns_checks
|
||||
/// Motivation: memory for index is shared between queries - not belong to the query itself.
|
||||
MemoryTracker::BlockerInThread temporarily_disable_memory_tracker;
|
||||
|
||||
loadUUID();
|
||||
loadColumns(require_columns_checksums);
|
||||
loadChecksums(require_columns_checksums);
|
||||
loadIndexGranularity();
|
||||
@ -482,6 +483,7 @@ NameSet IMergeTreeDataPart::getFileNamesWithoutChecksums() const
|
||||
|
||||
NameSet result = {"checksums.txt", "columns.txt"};
|
||||
String default_codec_path = getFullRelativePath() + DEFAULT_COMPRESSION_CODEC_FILE_NAME;
|
||||
|
||||
if (volume->getDisk()->exists(default_codec_path))
|
||||
result.emplace(DEFAULT_COMPRESSION_CODEC_FILE_NAME);
|
||||
|
||||
@ -726,6 +728,19 @@ void IMergeTreeDataPart::loadTTLInfos()
|
||||
}
|
||||
}
|
||||
|
||||
void IMergeTreeDataPart::loadUUID()
|
||||
{
|
||||
String path = getFullRelativePath() + UUID_FILE_NAME;
|
||||
|
||||
if (volume->getDisk()->exists(path))
|
||||
{
|
||||
auto in = openForReading(volume->getDisk(), path);
|
||||
readText(uuid, *in);
|
||||
if (uuid == UUIDHelpers::Nil)
|
||||
throw Exception("Unexpected empty " + String(UUID_FILE_NAME) + " in part: " + name, ErrorCodes::LOGICAL_ERROR);
|
||||
}
|
||||
}
|
||||
|
||||
void IMergeTreeDataPart::loadColumns(bool require)
|
||||
{
|
||||
String path = getFullRelativePath() + "columns.txt";
|
||||
|
||||
@ -164,6 +164,11 @@ public:
|
||||
String name;
|
||||
MergeTreePartInfo info;
|
||||
|
||||
/// Part unique identifier.
|
||||
/// The intention is to use it for identifying cases where the same part is
|
||||
/// processed by multiple shards.
|
||||
UUID uuid = UUIDHelpers::Nil;
|
||||
|
||||
VolumePtr volume;
|
||||
|
||||
/// A directory path (relative to storage's path) where part data is actually stored
|
||||
@ -348,6 +353,8 @@ public:
|
||||
|
||||
static inline constexpr auto DELETE_ON_DESTROY_MARKER_FILE_NAME = "delete-on-destroy.txt";
|
||||
|
||||
static inline constexpr auto UUID_FILE_NAME = "uuid.txt";
|
||||
|
||||
/// Checks that all TTLs (table min/max, column ttls, so on) for part
|
||||
/// calculated. Part without calculated TTL may exist if TTL was added after
|
||||
/// part creation (using alter query with materialize_ttl setting).
|
||||
@ -384,6 +391,9 @@ private:
|
||||
/// In compact parts order of columns is necessary
|
||||
NameToPosition column_name_to_position;
|
||||
|
||||
/// Reads part unique identifier (if exists) from uuid.txt
|
||||
void loadUUID();
|
||||
|
||||
/// Reads columns names and types from columns.txt
|
||||
void loadColumns(bool require);
|
||||
|
||||
|
||||
@ -134,7 +134,7 @@ MergeTreeData::MergeTreeData(
|
||||
bool attach,
|
||||
BrokenPartCallback broken_part_callback_)
|
||||
: IStorage(table_id_)
|
||||
, global_context(context_)
|
||||
, global_context(context_.getGlobalContext())
|
||||
, merging_params(merging_params_)
|
||||
, require_part_metadata(require_part_metadata_)
|
||||
, relative_data_path(relative_data_path_)
|
||||
@ -2003,7 +2003,7 @@ bool MergeTreeData::renameTempPartAndReplace(
|
||||
if (part_in_memory && getSettings()->in_memory_parts_enable_wal)
|
||||
{
|
||||
auto wal = getWriteAheadLog();
|
||||
wal->addPart(part_in_memory->block, part_in_memory->name);
|
||||
wal->addPart(part_in_memory);
|
||||
}
|
||||
|
||||
if (out_covered_parts)
|
||||
|
||||
@ -732,6 +732,7 @@ protected:
|
||||
friend class MergeTreeDataMergerMutator;
|
||||
friend struct ReplicatedMergeTreeTableMetadata;
|
||||
friend class StorageReplicatedMergeTree;
|
||||
friend class MergeTreeDataWriter;
|
||||
|
||||
bool require_part_metadata;
|
||||
|
||||
|
||||
@ -681,6 +681,7 @@ MergeTreeData::MutableDataPartPtr MergeTreeDataMergerMutator::mergePartsToTempor
|
||||
single_disk_volume,
|
||||
TMP_PREFIX + future_part.name);
|
||||
|
||||
new_data_part->uuid = future_part.uuid;
|
||||
new_data_part->setColumns(storage_columns);
|
||||
new_data_part->partition.assign(future_part.getPartition());
|
||||
new_data_part->is_temp = true;
|
||||
@ -1137,6 +1138,7 @@ MergeTreeData::MutableDataPartPtr MergeTreeDataMergerMutator::mutatePartToTempor
|
||||
auto new_data_part = data.createPart(
|
||||
future_part.name, future_part.type, future_part.part_info, single_disk_volume, "tmp_mut_" + future_part.name);
|
||||
|
||||
new_data_part->uuid = future_part.uuid;
|
||||
new_data_part->is_temp = true;
|
||||
new_data_part->ttl_infos = source_part->ttl_infos;
|
||||
|
||||
@ -1818,6 +1820,16 @@ void MergeTreeDataMergerMutator::finalizeMutatedPart(
|
||||
const CompressionCodecPtr & codec)
|
||||
{
|
||||
auto disk = new_data_part->volume->getDisk();
|
||||
|
||||
if (new_data_part->uuid != UUIDHelpers::Nil)
|
||||
{
|
||||
auto out = disk->writeFile(new_data_part->getFullRelativePath() + IMergeTreeDataPart::UUID_FILE_NAME, 4096);
|
||||
HashingWriteBuffer out_hashing(*out);
|
||||
writeUUIDText(new_data_part->uuid, out_hashing);
|
||||
new_data_part->checksums.files[IMergeTreeDataPart::UUID_FILE_NAME].file_size = out_hashing.count();
|
||||
new_data_part->checksums.files[IMergeTreeDataPart::UUID_FILE_NAME].file_hash = out_hashing.getHash();
|
||||
}
|
||||
|
||||
if (need_remove_expired_values)
|
||||
{
|
||||
/// Write a file with ttl infos in json format.
|
||||
|
||||
@ -19,6 +19,7 @@ class MergeProgressCallback;
|
||||
struct FutureMergedMutatedPart
|
||||
{
|
||||
String name;
|
||||
UUID uuid = UUIDHelpers::Nil;
|
||||
String path;
|
||||
MergeTreeDataPartType type;
|
||||
MergeTreePartInfo part_info;
|
||||
|
||||
@ -74,6 +74,7 @@ void MergeTreeDataPartInMemory::flushToDisk(const String & base_path, const Stri
|
||||
auto new_type = storage.choosePartTypeOnDisk(block.bytes(), rows_count);
|
||||
auto new_data_part = storage.createPart(name, new_type, info, volume, new_relative_path);
|
||||
|
||||
new_data_part->uuid = uuid;
|
||||
new_data_part->setColumns(columns);
|
||||
new_data_part->partition.value.assign(partition.value);
|
||||
new_data_part->minmax_idx = minmax_idx;
|
||||
|
||||
@ -247,6 +247,9 @@ MergeTreeData::MutableDataPartPtr MergeTreeDataWriter::writeTempPart(BlockWithPa
|
||||
createVolumeFromReservation(reservation, volume),
|
||||
TMP_PREFIX + part_name);
|
||||
|
||||
if (data.storage_settings.get()->assign_part_uuids)
|
||||
new_data_part->uuid = UUIDHelpers::generateV4();
|
||||
|
||||
new_data_part->setColumns(columns);
|
||||
new_data_part->partition = std::move(partition);
|
||||
new_data_part->minmax_idx = std::move(minmax_idx);
|
||||
|
||||
@ -107,6 +107,7 @@ struct Settings;
|
||||
M(String, storage_policy, "default", "Name of storage disk policy", 0) \
|
||||
M(Bool, allow_nullable_key, false, "Allow Nullable types as primary keys.", 0) \
|
||||
M(Bool, remove_empty_parts, true, "Remove empty parts after they were pruned by TTL, mutation, or collapsing merge algorithm", 0) \
|
||||
M(Bool, assign_part_uuids, false, "Generate UUIDs for parts. Before enabling check that all replicas support new format.", 0) \
|
||||
\
|
||||
/** Settings for testing purposes */ \
|
||||
M(Bool, randomize_part_type, false, "For testing purposes only. Randomizes part type between wide and compact", 0) \
|
||||
|
||||
@ -2,8 +2,13 @@
|
||||
#include <Storages/MergeTree/MergeTreeDataPartInMemory.h>
|
||||
#include <Storages/MergeTree/MergeTreeData.h>
|
||||
#include <Storages/MergeTree/MergedBlockOutputStream.h>
|
||||
#include <IO/MemoryReadWriteBuffer.h>
|
||||
#include <IO/ReadHelpers.h>
|
||||
#include <Poco/File.h>
|
||||
#include <IO/copyData.h>
|
||||
#include <Poco/JSON/JSON.h>
|
||||
#include <Poco/JSON/Object.h>
|
||||
#include <Poco/JSON/Stringifier.h>
|
||||
#include <Poco/JSON/Parser.h>
|
||||
#include <sys/time.h>
|
||||
|
||||
namespace DB
|
||||
@ -56,18 +61,23 @@ void MergeTreeWriteAheadLog::init()
|
||||
bytes_at_last_sync = 0;
|
||||
}
|
||||
|
||||
void MergeTreeWriteAheadLog::addPart(const Block & block, const String & part_name)
|
||||
void MergeTreeWriteAheadLog::addPart(DataPartInMemoryPtr & part)
|
||||
{
|
||||
std::unique_lock lock(write_mutex);
|
||||
|
||||
auto part_info = MergeTreePartInfo::fromPartName(part_name, storage.format_version);
|
||||
auto part_info = MergeTreePartInfo::fromPartName(part->name, storage.format_version);
|
||||
min_block_number = std::min(min_block_number, part_info.min_block);
|
||||
max_block_number = std::max(max_block_number, part_info.max_block);
|
||||
|
||||
writeIntBinary(WAL_VERSION, *out);
|
||||
|
||||
ActionMetadata metadata{};
|
||||
metadata.part_uuid = part->uuid;
|
||||
metadata.write(*out);
|
||||
|
||||
writeIntBinary(static_cast<UInt8>(ActionType::ADD_PART), *out);
|
||||
writeStringBinary(part_name, *out);
|
||||
block_out->write(block);
|
||||
writeStringBinary(part->name, *out);
|
||||
block_out->write(part->block);
|
||||
block_out->flush();
|
||||
sync(lock);
|
||||
|
||||
@ -81,6 +91,10 @@ void MergeTreeWriteAheadLog::dropPart(const String & part_name)
|
||||
std::unique_lock lock(write_mutex);
|
||||
|
||||
writeIntBinary(WAL_VERSION, *out);
|
||||
|
||||
ActionMetadata metadata{};
|
||||
metadata.write(*out);
|
||||
|
||||
writeIntBinary(static_cast<UInt8>(ActionType::DROP_PART), *out);
|
||||
writeStringBinary(part_name, *out);
|
||||
out->next();
|
||||
@ -143,6 +157,8 @@ MergeTreeData::MutableDataPartsVector MergeTreeWriteAheadLog::restore(const Stor
|
||||
single_disk_volume,
|
||||
part_name);
|
||||
|
||||
part->uuid = metadata.part_uuid;
|
||||
|
||||
block = block_in.read();
|
||||
}
|
||||
else
|
||||
@ -237,6 +253,29 @@ MergeTreeWriteAheadLog::tryParseMinMaxBlockNumber(const String & filename)
|
||||
return std::make_pair(min_block, max_block);
|
||||
}
|
||||
|
||||
String MergeTreeWriteAheadLog::ActionMetadata::toJSON() const
|
||||
{
|
||||
Poco::JSON::Object json;
|
||||
|
||||
if (part_uuid != UUIDHelpers::Nil)
|
||||
json.set(JSON_KEY_PART_UUID, toString(part_uuid));
|
||||
|
||||
std::ostringstream oss; // STYLE_CHECK_ALLOW_STD_STRING_STREAM
|
||||
oss.exceptions(std::ios::failbit);
|
||||
json.stringify(oss);
|
||||
|
||||
return oss.str();
|
||||
}
|
||||
|
||||
void MergeTreeWriteAheadLog::ActionMetadata::fromJSON(const String & buf)
|
||||
{
|
||||
Poco::JSON::Parser parser;
|
||||
auto json = parser.parse(buf).extract<Poco::JSON::Object::Ptr>();
|
||||
|
||||
if (json->has(JSON_KEY_PART_UUID))
|
||||
part_uuid = parseFromString<UUID>(json->getValue<std::string>(JSON_KEY_PART_UUID));
|
||||
}
|
||||
|
||||
void MergeTreeWriteAheadLog::ActionMetadata::read(ReadBuffer & meta_in)
|
||||
{
|
||||
readIntBinary(min_compatible_version, meta_in);
|
||||
@ -247,19 +286,23 @@ void MergeTreeWriteAheadLog::ActionMetadata::read(ReadBuffer & meta_in)
|
||||
size_t metadata_size;
|
||||
readVarUInt(metadata_size, meta_in);
|
||||
|
||||
UInt32 metadata_start = meta_in.offset();
|
||||
if (metadata_size == 0)
|
||||
return;
|
||||
|
||||
/// For the future: read metadata here.
|
||||
String buf(metadata_size, ' ');
|
||||
meta_in.readStrict(buf.data(), metadata_size);
|
||||
|
||||
|
||||
/// Skip extra fields if any. If min_compatible_version is lower than WAL_VERSION it means
|
||||
/// that the fields are not critical for the correctness.
|
||||
meta_in.ignore(metadata_size - (meta_in.offset() - metadata_start));
|
||||
fromJSON(buf);
|
||||
}
|
||||
|
||||
void MergeTreeWriteAheadLog::ActionMetadata::write(WriteBuffer & meta_out) const
|
||||
{
|
||||
writeIntBinary(min_compatible_version, meta_out);
|
||||
writeVarUInt(static_cast<UInt32>(0), meta_out);
|
||||
|
||||
String ser_meta = toJSON();
|
||||
|
||||
writeVarUInt(static_cast<UInt32>(ser_meta.length()), meta_out);
|
||||
writeString(ser_meta, meta_out);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
@ -2,9 +2,10 @@
|
||||
|
||||
#include <DataStreams/NativeBlockInputStream.h>
|
||||
#include <DataStreams/NativeBlockOutputStream.h>
|
||||
#include <Storages/MergeTree/IMergeTreeDataPart.h>
|
||||
#include <Core/BackgroundSchedulePool.h>
|
||||
#include <Disks/IDisk.h>
|
||||
#include <Storages/MergeTree/IMergeTreeDataPart.h>
|
||||
#include <Storages/MergeTree/MergeTreeDataPartInMemory.h>
|
||||
|
||||
namespace DB
|
||||
{
|
||||
@ -36,11 +37,20 @@ public:
|
||||
/// The same approach can be used recursively inside metadata.
|
||||
UInt8 min_compatible_version = 0;
|
||||
|
||||
/// Actual metadata.
|
||||
UUID part_uuid = UUIDHelpers::Nil;
|
||||
|
||||
void write(WriteBuffer & meta_out) const;
|
||||
void read(ReadBuffer & meta_in);
|
||||
|
||||
private:
|
||||
static constexpr auto JSON_KEY_PART_UUID = "part_uuid";
|
||||
|
||||
String toJSON() const;
|
||||
void fromJSON(const String & buf);
|
||||
};
|
||||
|
||||
constexpr static UInt8 WAL_VERSION = 0;
|
||||
constexpr static UInt8 WAL_VERSION = 1;
|
||||
constexpr static auto WAL_FILE_NAME = "wal";
|
||||
constexpr static auto WAL_FILE_EXTENSION = ".bin";
|
||||
constexpr static auto DEFAULT_WAL_FILE_NAME = "wal.bin";
|
||||
@ -50,7 +60,7 @@ public:
|
||||
|
||||
~MergeTreeWriteAheadLog();
|
||||
|
||||
void addPart(const Block & block, const String & part_name);
|
||||
void addPart(DataPartInMemoryPtr & part);
|
||||
void dropPart(const String & part_name);
|
||||
std::vector<MergeTreeMutableDataPartPtr> restore(const StorageMetadataPtr & metadata_snapshot);
|
||||
|
||||
|
||||
@ -133,6 +133,18 @@ void MergedBlockOutputStream::finalizePartOnDisk(
|
||||
MergeTreeData::DataPart::Checksums & checksums,
|
||||
bool sync)
|
||||
{
|
||||
if (new_part->uuid != UUIDHelpers::Nil)
|
||||
{
|
||||
auto out = volume->getDisk()->writeFile(part_path + IMergeTreeDataPart::UUID_FILE_NAME, 4096);
|
||||
HashingWriteBuffer out_hashing(*out);
|
||||
writeUUIDText(new_part->uuid, out_hashing);
|
||||
checksums.files[IMergeTreeDataPart::UUID_FILE_NAME].file_size = out_hashing.count();
|
||||
checksums.files[IMergeTreeDataPart::UUID_FILE_NAME].file_hash = out_hashing.getHash();
|
||||
out->finalize();
|
||||
if (sync)
|
||||
out->sync();
|
||||
}
|
||||
|
||||
if (storage.format_version >= MERGE_TREE_DATA_MIN_FORMAT_VERSION_WITH_CUSTOM_PARTITIONING || isCompactPart(new_part))
|
||||
{
|
||||
new_part->partition.store(storage, volume->getDisk(), part_path, checksums);
|
||||
|
||||
@ -264,6 +264,7 @@ void ReplicatedMergeTreeBlockOutputStream::commitPart(
|
||||
log_entry.create_time = time(nullptr);
|
||||
log_entry.source_replica = storage.replica_name;
|
||||
log_entry.new_part_name = part->name;
|
||||
/// TODO maybe add UUID here as well?
|
||||
log_entry.quorum = quorum;
|
||||
log_entry.block_id = block_id;
|
||||
log_entry.new_part_type = part->getType();
|
||||
|
||||
@ -19,7 +19,14 @@ namespace ErrorCodes
|
||||
|
||||
void ReplicatedMergeTreeLogEntryData::writeText(WriteBuffer & out) const
|
||||
{
|
||||
out << "format version: 4\n"
|
||||
UInt8 format_version = 4;
|
||||
|
||||
/// Conditionally bump format_version only when uuid has been assigned.
|
||||
/// If some other feature requires bumping format_version to >= 5 then this code becomes no-op.
|
||||
if (new_part_uuid != UUIDHelpers::Nil)
|
||||
format_version = std::max(format_version, static_cast<UInt8>(5));
|
||||
|
||||
out << "format version: " << format_version << "\n"
|
||||
<< "create_time: " << LocalDateTime(create_time ? create_time : time(nullptr)) << "\n"
|
||||
<< "source replica: " << source_replica << '\n'
|
||||
<< "block_id: " << escape << block_id << '\n';
|
||||
@ -36,8 +43,13 @@ void ReplicatedMergeTreeLogEntryData::writeText(WriteBuffer & out) const
|
||||
out << s << '\n';
|
||||
out << "into\n" << new_part_name;
|
||||
out << "\ndeduplicate: " << deduplicate;
|
||||
|
||||
if (merge_type != MergeType::REGULAR)
|
||||
out <<"\nmerge_type: " << static_cast<UInt64>(merge_type);
|
||||
|
||||
if (new_part_uuid != UUIDHelpers::Nil)
|
||||
out << "\ninto_uuid: " << new_part_uuid;
|
||||
|
||||
break;
|
||||
|
||||
case DROP_RANGE:
|
||||
@ -75,6 +87,10 @@ void ReplicatedMergeTreeLogEntryData::writeText(WriteBuffer & out) const
|
||||
<< "to\n"
|
||||
<< new_part_name;
|
||||
|
||||
if (new_part_uuid != UUIDHelpers::Nil)
|
||||
out << "\nto_uuid\n"
|
||||
<< new_part_uuid;
|
||||
|
||||
if (isAlterMutation())
|
||||
out << "\nalter_version\n" << alter_version;
|
||||
break;
|
||||
@ -113,7 +129,7 @@ void ReplicatedMergeTreeLogEntryData::readText(ReadBuffer & in)
|
||||
|
||||
in >> "format version: " >> format_version >> "\n";
|
||||
|
||||
if (format_version < 1 || format_version > 4)
|
||||
if (format_version < 1 || format_version > 5)
|
||||
throw Exception("Unknown ReplicatedMergeTreeLogEntry format version: " + DB::toString(format_version), ErrorCodes::UNKNOWN_FORMAT_VERSION);
|
||||
|
||||
if (format_version >= 2)
|
||||
@ -156,15 +172,21 @@ void ReplicatedMergeTreeLogEntryData::readText(ReadBuffer & in)
|
||||
in >> "\ndeduplicate: " >> deduplicate;
|
||||
|
||||
/// Trying to be more backward compatible
|
||||
in >> "\n";
|
||||
if (checkString("merge_type: ", in))
|
||||
while (!trailing_newline_found)
|
||||
{
|
||||
UInt64 value;
|
||||
in >> value;
|
||||
merge_type = checkAndGetMergeType(value);
|
||||
in >> "\n";
|
||||
|
||||
if (checkString("merge_type: ", in))
|
||||
{
|
||||
UInt64 value;
|
||||
in >> value;
|
||||
merge_type = checkAndGetMergeType(value);
|
||||
}
|
||||
else if (checkString("into_uuid: ", in))
|
||||
in >> new_part_uuid;
|
||||
else
|
||||
trailing_newline_found = true;
|
||||
}
|
||||
else
|
||||
trailing_newline_found = true;
|
||||
}
|
||||
}
|
||||
else if (type_str == "drop" || type_str == "detach")
|
||||
@ -198,12 +220,17 @@ void ReplicatedMergeTreeLogEntryData::readText(ReadBuffer & in)
|
||||
>> new_part_name;
|
||||
source_parts.push_back(source_part);
|
||||
|
||||
in >> "\n";
|
||||
while (!trailing_newline_found)
|
||||
{
|
||||
in >> "\n";
|
||||
|
||||
if (in.eof())
|
||||
trailing_newline_found = true;
|
||||
else if (checkString("alter_version\n", in))
|
||||
in >> alter_version;
|
||||
if (checkString("alter_version\n", in))
|
||||
in >> alter_version;
|
||||
else if (checkString("to_uuid\n", in))
|
||||
in >> new_part_uuid;
|
||||
else
|
||||
trailing_newline_found = true;
|
||||
}
|
||||
}
|
||||
else if (type_str == "alter")
|
||||
{
|
||||
|
||||
@ -77,6 +77,7 @@ struct ReplicatedMergeTreeLogEntryData
|
||||
MergeTreeDataPartType new_part_type;
|
||||
String block_id; /// For parts of level zero, the block identifier for deduplication (node name in /blocks/).
|
||||
mutable String actual_new_part_name; /// GET_PART could actually fetch a part covering 'new_part_name'.
|
||||
UUID new_part_uuid = UUIDHelpers::Nil;
|
||||
|
||||
Strings source_parts;
|
||||
bool deduplicate = false; /// Do deduplicate on merge
|
||||
|
||||
@ -1,6 +1,8 @@
|
||||
#include <Formats/FormatFactory.h>
|
||||
#include <Processors/Formats/InputStreamFromInputFormat.h>
|
||||
#include <Storages/RabbitMQ/RabbitMQBlockInputStream.h>
|
||||
|
||||
#include <Formats/FormatFactory.h>
|
||||
#include <Interpreters/Context.h>
|
||||
#include <Processors/Formats/InputStreamFromInputFormat.h>
|
||||
#include <Storages/RabbitMQ/ReadBufferFromRabbitMQConsumer.h>
|
||||
|
||||
namespace ErrorCodes
|
||||
|
||||
@ -1,7 +1,6 @@
|
||||
#pragma once
|
||||
|
||||
#include <DataStreams/IBlockInputStream.h>
|
||||
#include <Interpreters/Context.h>
|
||||
#include <Storages/RabbitMQ/StorageRabbitMQ.h>
|
||||
#include <Storages/RabbitMQ/ReadBufferFromRabbitMQConsumer.h>
|
||||
|
||||
@ -38,7 +37,7 @@ public:
|
||||
private:
|
||||
StorageRabbitMQ & storage;
|
||||
StorageMetadataPtr metadata_snapshot;
|
||||
Context context;
|
||||
const Context & context;
|
||||
Names column_names;
|
||||
const size_t max_block_size;
|
||||
bool ack_in_suffix;
|
||||
|
||||
@ -1,7 +1,6 @@
|
||||
#pragma once
|
||||
|
||||
#include <DataStreams/IBlockOutputStream.h>
|
||||
#include <Interpreters/Context.h>
|
||||
#include <Storages/RabbitMQ/StorageRabbitMQ.h>
|
||||
|
||||
|
||||
@ -23,7 +22,7 @@ public:
|
||||
private:
|
||||
StorageRabbitMQ & storage;
|
||||
StorageMetadataPtr metadata_snapshot;
|
||||
Context context;
|
||||
const Context & context;
|
||||
ProducerBufferPtr buffer;
|
||||
BlockOutputStreamPtr child;
|
||||
};
|
||||
|
||||
@ -69,7 +69,7 @@ namespace ExchangeType
|
||||
|
||||
StorageRabbitMQ::StorageRabbitMQ(
|
||||
const StorageID & table_id_,
|
||||
Context & context_,
|
||||
const Context & context_,
|
||||
const ColumnsDescription & columns_,
|
||||
std::unique_ptr<RabbitMQSettings> rabbitmq_settings_)
|
||||
: IStorage(table_id_)
|
||||
|
||||
@ -67,12 +67,12 @@ public:
|
||||
protected:
|
||||
StorageRabbitMQ(
|
||||
const StorageID & table_id_,
|
||||
Context & context_,
|
||||
const Context & context_,
|
||||
const ColumnsDescription & columns_,
|
||||
std::unique_ptr<RabbitMQSettings> rabbitmq_settings_);
|
||||
|
||||
private:
|
||||
Context global_context;
|
||||
const Context & global_context;
|
||||
Context rabbitmq_context;
|
||||
std::unique_ptr<RabbitMQSettings> rabbitmq_settings;
|
||||
|
||||
|
||||
@ -1,7 +1,9 @@
|
||||
#include <Storages/RabbitMQ/WriteBufferToRabbitMQProducer.h>
|
||||
#include "Core/Block.h"
|
||||
#include "Columns/ColumnString.h"
|
||||
#include "Columns/ColumnsNumber.h"
|
||||
|
||||
#include <Core/Block.h>
|
||||
#include <Columns/ColumnString.h>
|
||||
#include <Columns/ColumnsNumber.h>
|
||||
#include <Interpreters/Context.h>
|
||||
#include <common/logger_useful.h>
|
||||
#include <amqpcpp.h>
|
||||
#include <uv.h>
|
||||
@ -25,7 +27,7 @@ namespace ErrorCodes
|
||||
|
||||
WriteBufferToRabbitMQProducer::WriteBufferToRabbitMQProducer(
|
||||
std::pair<String, UInt16> & parsed_address_,
|
||||
Context & global_context,
|
||||
const Context & global_context,
|
||||
const std::pair<String, String> & login_password_,
|
||||
const Names & routing_keys_,
|
||||
const String & exchange_name_,
|
||||
|
||||
@ -9,7 +9,7 @@
|
||||
#include <Storages/RabbitMQ/RabbitMQHandler.h>
|
||||
#include <Common/ConcurrentBoundedQueue.h>
|
||||
#include <Core/BackgroundSchedulePool.h>
|
||||
#include <Interpreters/Context.h>
|
||||
#include <Core/Names.h>
|
||||
|
||||
namespace DB
|
||||
{
|
||||
@ -19,7 +19,7 @@ class WriteBufferToRabbitMQProducer : public WriteBuffer
|
||||
public:
|
||||
WriteBufferToRabbitMQProducer(
|
||||
std::pair<String, UInt16> & parsed_address_,
|
||||
Context & global_context,
|
||||
const Context & global_context,
|
||||
const std::pair<String, String> & login_password_,
|
||||
const Names & routing_keys_,
|
||||
const String & exchange_name_,
|
||||
|
||||
@ -65,14 +65,14 @@ StorageBuffer::StorageBuffer(
|
||||
const StorageID & table_id_,
|
||||
const ColumnsDescription & columns_,
|
||||
const ConstraintsDescription & constraints_,
|
||||
Context & context_,
|
||||
const Context & context_,
|
||||
size_t num_shards_,
|
||||
const Thresholds & min_thresholds_,
|
||||
const Thresholds & max_thresholds_,
|
||||
const StorageID & destination_id_,
|
||||
bool allow_materialized_)
|
||||
: IStorage(table_id_)
|
||||
, global_context(context_)
|
||||
, global_context(context_.getGlobalContext())
|
||||
, num_shards(num_shards_), buffers(num_shards_)
|
||||
, min_thresholds(min_thresholds_)
|
||||
, max_thresholds(max_thresholds_)
|
||||
|
||||
@ -9,7 +9,6 @@
|
||||
#include <Storages/IStorage.h>
|
||||
#include <DataStreams/IBlockOutputStream.h>
|
||||
#include <Poco/Event.h>
|
||||
#include <Interpreters/Context.h>
|
||||
|
||||
|
||||
namespace Poco { class Logger; }
|
||||
@ -82,7 +81,13 @@ public:
|
||||
void startup() override;
|
||||
/// Flush all buffers into the subordinate table and stop background thread.
|
||||
void shutdown() override;
|
||||
bool optimize(const ASTPtr & query, const StorageMetadataPtr & metadata_snapshot, const ASTPtr & partition, bool final, bool deduplicate, const Context & context) override;
|
||||
bool optimize(
|
||||
const ASTPtr & query,
|
||||
const StorageMetadataPtr & metadata_snapshot,
|
||||
const ASTPtr & partition,
|
||||
bool final,
|
||||
bool deduplicate,
|
||||
const Context & context) override;
|
||||
|
||||
bool supportsSampling() const override { return true; }
|
||||
bool supportsPrewhere() const override
|
||||
@ -112,7 +117,7 @@ public:
|
||||
|
||||
|
||||
private:
|
||||
Context global_context;
|
||||
const Context & global_context;
|
||||
|
||||
struct Buffer
|
||||
{
|
||||
@ -165,7 +170,7 @@ protected:
|
||||
const StorageID & table_id_,
|
||||
const ColumnsDescription & columns_,
|
||||
const ConstraintsDescription & constraints_,
|
||||
Context & context_,
|
||||
const Context & context_,
|
||||
size_t num_shards_,
|
||||
const Thresholds & min_thresholds_,
|
||||
const Thresholds & max_thresholds_,
|
||||
|
||||
@ -366,10 +366,10 @@ StorageDistributed::StorageDistributed(
|
||||
: IStorage(id_)
|
||||
, remote_database(remote_database_)
|
||||
, remote_table(remote_table_)
|
||||
, global_context(std::make_unique<Context>(context_))
|
||||
, global_context(context_.getGlobalContext())
|
||||
, log(&Poco::Logger::get("StorageDistributed (" + id_.table_name + ")"))
|
||||
, owned_cluster(std::move(owned_cluster_))
|
||||
, cluster_name(global_context->getMacros()->expand(cluster_name_))
|
||||
, cluster_name(global_context.getMacros()->expand(cluster_name_))
|
||||
, has_sharding_key(sharding_key_)
|
||||
, relative_data_path(relative_data_path_)
|
||||
{
|
||||
@ -380,14 +380,14 @@ StorageDistributed::StorageDistributed(
|
||||
|
||||
if (sharding_key_)
|
||||
{
|
||||
sharding_key_expr = buildShardingKeyExpression(sharding_key_, *global_context, storage_metadata.getColumns().getAllPhysical(), false);
|
||||
sharding_key_expr = buildShardingKeyExpression(sharding_key_, global_context, storage_metadata.getColumns().getAllPhysical(), false);
|
||||
sharding_key_column_name = sharding_key_->getColumnName();
|
||||
sharding_key_is_deterministic = isExpressionActionsDeterministics(sharding_key_expr);
|
||||
}
|
||||
|
||||
if (!relative_data_path.empty())
|
||||
{
|
||||
storage_policy = global_context->getStoragePolicy(storage_policy_name_);
|
||||
storage_policy = global_context.getStoragePolicy(storage_policy_name_);
|
||||
data_volume = storage_policy->getVolume(0);
|
||||
if (storage_policy->getVolumes().size() > 1)
|
||||
LOG_WARNING(log, "Storage policy for Distributed table has multiple volumes. "
|
||||
@ -397,7 +397,7 @@ StorageDistributed::StorageDistributed(
|
||||
/// Sanity check. Skip check if the table is already created to allow the server to start.
|
||||
if (!attach_ && !cluster_name.empty())
|
||||
{
|
||||
size_t num_local_shards = global_context->getCluster(cluster_name)->getLocalShardCount();
|
||||
size_t num_local_shards = global_context.getCluster(cluster_name)->getLocalShardCount();
|
||||
if (num_local_shards && remote_database == id_.database_name && remote_table == id_.table_name)
|
||||
throw Exception("Distributed table " + id_.table_name + " looks at itself", ErrorCodes::INFINITE_LOOP);
|
||||
}
|
||||
@ -719,7 +719,7 @@ StorageDistributedDirectoryMonitor& StorageDistributed::requireDirectoryMonitor(
|
||||
{
|
||||
node_data.connection_pool = StorageDistributedDirectoryMonitor::createPool(name, *this);
|
||||
node_data.directory_monitor = std::make_unique<StorageDistributedDirectoryMonitor>(
|
||||
*this, path, node_data.connection_pool, monitors_blocker, global_context->getDistributedSchedulePool());
|
||||
*this, path, node_data.connection_pool, monitors_blocker, global_context.getDistributedSchedulePool());
|
||||
}
|
||||
return *node_data.directory_monitor;
|
||||
}
|
||||
@ -741,7 +741,7 @@ size_t StorageDistributed::getShardCount() const
|
||||
|
||||
ClusterPtr StorageDistributed::getCluster() const
|
||||
{
|
||||
return owned_cluster ? owned_cluster : global_context->getCluster(cluster_name);
|
||||
return owned_cluster ? owned_cluster : global_context.getCluster(cluster_name);
|
||||
}
|
||||
|
||||
ClusterPtr StorageDistributed::getOptimizedCluster(const Context & context, const StorageMetadataPtr & metadata_snapshot, const ASTPtr & query_ptr) const
|
||||
|
||||
@ -130,7 +130,7 @@ public:
|
||||
String remote_table;
|
||||
ASTPtr remote_table_function_ptr;
|
||||
|
||||
std::unique_ptr<Context> global_context;
|
||||
const Context & global_context;
|
||||
Poco::Logger * log;
|
||||
|
||||
/// Used to implement TableFunctionRemote.
|
||||
|
||||
@ -5,6 +5,7 @@
|
||||
#include <Storages/StorageFactory.h>
|
||||
#include <Storages/VirtualColumnUtils.h>
|
||||
#include <Storages/AlterCommands.h>
|
||||
#include <Interpreters/Context.h>
|
||||
#include <Interpreters/TreeRewriter.h>
|
||||
#include <Interpreters/ExpressionActions.h>
|
||||
#include <Interpreters/evaluateConstantExpression.h>
|
||||
@ -76,7 +77,7 @@ StorageMerge::StorageMerge(
|
||||
: IStorage(table_id_)
|
||||
, source_database(source_database_)
|
||||
, table_name_regexp(table_name_regexp_)
|
||||
, global_context(context_)
|
||||
, global_context(context_.getGlobalContext())
|
||||
{
|
||||
StorageInMemoryMetadata storage_metadata;
|
||||
storage_metadata.setColumns(columns_);
|
||||
@ -134,6 +135,18 @@ bool StorageMerge::mayBenefitFromIndexForIn(const ASTPtr & left_in_operand, cons
|
||||
|
||||
QueryProcessingStage::Enum StorageMerge::getQueryProcessingStage(const Context & context, QueryProcessingStage::Enum to_stage, SelectQueryInfo & query_info) const
|
||||
{
|
||||
ASTPtr modified_query = query_info.query->clone();
|
||||
auto & modified_select = modified_query->as<ASTSelectQuery &>();
|
||||
/// In case of JOIN the first stage (which includes JOIN)
|
||||
/// should be done on the initiator always.
|
||||
///
|
||||
/// Since in case of JOIN query on shards will receive query w/o JOIN (and their columns).
|
||||
/// (see modifySelect()/removeJoin())
|
||||
///
|
||||
/// And for this we need to return FetchColumns.
|
||||
if (removeJoin(modified_select))
|
||||
return QueryProcessingStage::FetchColumns;
|
||||
|
||||
auto stage_in_source_tables = QueryProcessingStage::FetchColumns;
|
||||
|
||||
DatabaseTablesIteratorPtr iterator = getDatabaseIterator(context);
|
||||
|
||||
@ -4,7 +4,6 @@
|
||||
|
||||
#include <Common/OptimizedRegularExpression.h>
|
||||
#include <Storages/IStorage.h>
|
||||
#include <Interpreters/Context.h>
|
||||
|
||||
|
||||
namespace DB
|
||||
@ -50,7 +49,7 @@ public:
|
||||
private:
|
||||
String source_database;
|
||||
OptimizedRegularExpression table_name_regexp;
|
||||
Context global_context;
|
||||
const Context & global_context;
|
||||
|
||||
using StorageWithLockAndName = std::tuple<StoragePtr, TableLockHolder, String>;
|
||||
using StorageListWithLocks = std::list<StorageWithLockAndName>;
|
||||
|
||||
@ -642,6 +642,9 @@ std::shared_ptr<StorageMergeTree::MergeMutateSelectedEntry> StorageMergeTree::se
|
||||
|
||||
FutureMergedMutatedPart future_part;
|
||||
|
||||
if (storage_settings.get()->assign_part_uuids)
|
||||
future_part.uuid = UUIDHelpers::generateV4();
|
||||
|
||||
/// You must call destructor with unlocked `currently_processing_in_background_mutex`.
|
||||
CurrentlyMergingPartsTaggerPtr merging_tagger;
|
||||
MergeList::EntryPtr merge_entry;
|
||||
@ -796,6 +799,9 @@ std::shared_ptr<StorageMergeTree::MergeMutateSelectedEntry> StorageMergeTree::se
|
||||
size_t max_ast_elements = global_context.getSettingsRef().max_expanded_ast_elements;
|
||||
|
||||
FutureMergedMutatedPart future_part;
|
||||
if (storage_settings.get()->assign_part_uuids)
|
||||
future_part.uuid = UUIDHelpers::generateV4();
|
||||
|
||||
MutationCommands commands;
|
||||
|
||||
CurrentlyMergingPartsTaggerPtr tagger;
|
||||
|
||||
@ -34,8 +34,7 @@ StorageMongoDB::StorageMongoDB(
|
||||
const std::string & username_,
|
||||
const std::string & password_,
|
||||
const ColumnsDescription & columns_,
|
||||
const ConstraintsDescription & constraints_,
|
||||
const Context & context_)
|
||||
const ConstraintsDescription & constraints_)
|
||||
: IStorage(table_id_)
|
||||
, host(host_)
|
||||
, port(port_)
|
||||
@ -43,7 +42,6 @@ StorageMongoDB::StorageMongoDB(
|
||||
, collection_name(collection_name_)
|
||||
, username(username_)
|
||||
, password(password_)
|
||||
, global_context(context_)
|
||||
, connection{std::make_shared<Poco::MongoDB::Connection>(host, port)}
|
||||
{
|
||||
StorageInMemoryMetadata storage_metadata;
|
||||
@ -114,8 +112,7 @@ void registerStorageMongoDB(StorageFactory & factory)
|
||||
username,
|
||||
password,
|
||||
args.columns,
|
||||
args.constraints,
|
||||
args.context);
|
||||
args.constraints);
|
||||
},
|
||||
{
|
||||
.source_access_type = AccessType::MONGO,
|
||||
|
||||
@ -3,7 +3,6 @@
|
||||
#include <ext/shared_ptr_helper.h>
|
||||
|
||||
#include <Storages/IStorage.h>
|
||||
#include <Interpreters/Context.h>
|
||||
|
||||
#include <Poco/MongoDB/Connection.h>
|
||||
|
||||
@ -28,8 +27,7 @@ public:
|
||||
const std::string & username_,
|
||||
const std::string & password_,
|
||||
const ColumnsDescription & columns_,
|
||||
const ConstraintsDescription & constraints_,
|
||||
const Context & context_);
|
||||
const ConstraintsDescription & constraints_);
|
||||
|
||||
std::string getName() const override { return "MongoDB"; }
|
||||
|
||||
@ -51,7 +49,6 @@ private:
|
||||
std::string username;
|
||||
std::string password;
|
||||
|
||||
Context global_context;
|
||||
std::shared_ptr<Poco::MongoDB::Connection> connection;
|
||||
};
|
||||
|
||||
|
||||
@ -55,7 +55,7 @@ StorageMySQL::StorageMySQL(
|
||||
, replace_query{replace_query_}
|
||||
, on_duplicate_clause{on_duplicate_clause_}
|
||||
, pool(std::move(pool_))
|
||||
, global_context(context_)
|
||||
, global_context(context_.getGlobalContext())
|
||||
{
|
||||
StorageInMemoryMetadata storage_metadata;
|
||||
storage_metadata.setColumns(columns_);
|
||||
|
||||
@ -8,7 +8,6 @@
|
||||
|
||||
# include <ext/shared_ptr_helper.h>
|
||||
|
||||
# include <Interpreters/Context.h>
|
||||
# include <Storages/IStorage.h>
|
||||
# include <mysqlxx/Pool.h>
|
||||
|
||||
@ -57,7 +56,7 @@ private:
|
||||
std::string on_duplicate_clause;
|
||||
|
||||
mysqlxx::Pool pool;
|
||||
Context global_context;
|
||||
const Context & global_context;
|
||||
};
|
||||
|
||||
}
|
||||
|
||||
@ -1443,6 +1443,7 @@ bool StorageReplicatedMergeTree::tryExecuteMerge(const LogEntry & entry)
|
||||
throw Exception("Future merged part name " + backQuote(future_merged_part.name) + " differs from part name in log entry: "
|
||||
+ backQuote(entry.new_part_name), ErrorCodes::BAD_DATA_PART_NAME);
|
||||
}
|
||||
future_merged_part.uuid = entry.new_part_uuid;
|
||||
future_merged_part.updatePath(*this, reserved_space);
|
||||
future_merged_part.merge_type = entry.merge_type;
|
||||
|
||||
@ -1567,9 +1568,10 @@ bool StorageReplicatedMergeTree::tryExecutePartMutation(const StorageReplicatedM
|
||||
Transaction transaction(*this);
|
||||
|
||||
FutureMergedMutatedPart future_mutated_part;
|
||||
future_mutated_part.name = entry.new_part_name;
|
||||
future_mutated_part.uuid = entry.new_part_uuid;
|
||||
future_mutated_part.parts.push_back(source_part);
|
||||
future_mutated_part.part_info = new_part_info;
|
||||
future_mutated_part.name = entry.new_part_name;
|
||||
future_mutated_part.updatePath(*this, reserved_space);
|
||||
future_mutated_part.type = source_part->getType();
|
||||
|
||||
@ -2705,11 +2707,22 @@ void StorageReplicatedMergeTree::mergeSelectingTask()
|
||||
getTotalMergesWithTTLInMergeList() < storage_settings_ptr->max_number_of_merges_with_ttl_in_pool;
|
||||
|
||||
FutureMergedMutatedPart future_merged_part;
|
||||
if (storage_settings.get()->assign_part_uuids)
|
||||
future_merged_part.uuid = UUIDHelpers::generateV4();
|
||||
|
||||
if (max_source_parts_size_for_merge > 0 &&
|
||||
merger_mutator.selectPartsToMerge(future_merged_part, false, max_source_parts_size_for_merge, merge_pred, merge_with_ttl_allowed, nullptr))
|
||||
{
|
||||
create_result = createLogEntryToMergeParts(zookeeper, future_merged_part.parts,
|
||||
future_merged_part.name, future_merged_part.type, deduplicate, nullptr, merge_pred.getVersion(), future_merged_part.merge_type);
|
||||
create_result = createLogEntryToMergeParts(
|
||||
zookeeper,
|
||||
future_merged_part.parts,
|
||||
future_merged_part.name,
|
||||
future_merged_part.uuid,
|
||||
future_merged_part.type,
|
||||
deduplicate,
|
||||
nullptr,
|
||||
merge_pred.getVersion(),
|
||||
future_merged_part.merge_type);
|
||||
}
|
||||
/// If there are many mutations in queue, it may happen, that we cannot enqueue enough merges to merge all new parts
|
||||
else if (max_source_part_size_for_mutation > 0 && queue.countMutations() > 0
|
||||
@ -2726,8 +2739,12 @@ void StorageReplicatedMergeTree::mergeSelectingTask()
|
||||
if (!desired_mutation_version)
|
||||
continue;
|
||||
|
||||
create_result = createLogEntryToMutatePart(*part,
|
||||
desired_mutation_version->first, desired_mutation_version->second, merge_pred.getVersion());
|
||||
create_result = createLogEntryToMutatePart(
|
||||
*part,
|
||||
future_merged_part.uuid,
|
||||
desired_mutation_version->first,
|
||||
desired_mutation_version->second,
|
||||
merge_pred.getVersion());
|
||||
|
||||
if (create_result == CreateMergeEntryResult::Ok)
|
||||
break;
|
||||
@ -2789,6 +2806,7 @@ StorageReplicatedMergeTree::CreateMergeEntryResult StorageReplicatedMergeTree::c
|
||||
zkutil::ZooKeeperPtr & zookeeper,
|
||||
const DataPartsVector & parts,
|
||||
const String & merged_name,
|
||||
const UUID & merged_part_uuid,
|
||||
const MergeTreeDataPartType & merged_part_type,
|
||||
bool deduplicate,
|
||||
ReplicatedMergeTreeLogEntryData * out_log_entry,
|
||||
@ -2824,6 +2842,7 @@ StorageReplicatedMergeTree::CreateMergeEntryResult StorageReplicatedMergeTree::c
|
||||
entry.type = LogEntry::MERGE_PARTS;
|
||||
entry.source_replica = replica_name;
|
||||
entry.new_part_name = merged_name;
|
||||
entry.new_part_uuid = merged_part_uuid;
|
||||
entry.new_part_type = merged_part_type;
|
||||
entry.merge_type = merge_type;
|
||||
entry.deduplicate = deduplicate;
|
||||
@ -2872,7 +2891,7 @@ StorageReplicatedMergeTree::CreateMergeEntryResult StorageReplicatedMergeTree::c
|
||||
|
||||
|
||||
StorageReplicatedMergeTree::CreateMergeEntryResult StorageReplicatedMergeTree::createLogEntryToMutatePart(
|
||||
const IMergeTreeDataPart & part, Int64 mutation_version, int32_t alter_version, int32_t log_version)
|
||||
const IMergeTreeDataPart & part, const UUID & new_part_uuid, Int64 mutation_version, int32_t alter_version, int32_t log_version)
|
||||
{
|
||||
auto zookeeper = getZooKeeper();
|
||||
|
||||
@ -2899,6 +2918,7 @@ StorageReplicatedMergeTree::CreateMergeEntryResult StorageReplicatedMergeTree::c
|
||||
entry.source_replica = replica_name;
|
||||
entry.source_parts.push_back(part.name);
|
||||
entry.new_part_name = new_part_name;
|
||||
entry.new_part_uuid = new_part_uuid;
|
||||
entry.create_time = time(nullptr);
|
||||
entry.alter_version = alter_version;
|
||||
|
||||
@ -3842,6 +3862,9 @@ bool StorageReplicatedMergeTree::optimize(
|
||||
ReplicatedMergeTreeMergePredicate can_merge = queue.getMergePredicate(zookeeper);
|
||||
|
||||
FutureMergedMutatedPart future_merged_part;
|
||||
if (storage_settings.get()->assign_part_uuids)
|
||||
future_merged_part.uuid = UUIDHelpers::generateV4();
|
||||
|
||||
bool selected = merger_mutator.selectAllPartsToMergeWithinPartition(
|
||||
future_merged_part, disk_space, can_merge, partition_id, true, nullptr);
|
||||
|
||||
@ -3851,7 +3874,7 @@ bool StorageReplicatedMergeTree::optimize(
|
||||
ReplicatedMergeTreeLogEntryData merge_entry;
|
||||
CreateMergeEntryResult create_result = createLogEntryToMergeParts(
|
||||
zookeeper, future_merged_part.parts,
|
||||
future_merged_part.name, future_merged_part.type, deduplicate,
|
||||
future_merged_part.name, future_merged_part.uuid, future_merged_part.type, deduplicate,
|
||||
&merge_entry, can_merge.getVersion(), future_merged_part.merge_type);
|
||||
|
||||
if (create_result == CreateMergeEntryResult::MissingPart)
|
||||
@ -3877,6 +3900,9 @@ bool StorageReplicatedMergeTree::optimize(
|
||||
ReplicatedMergeTreeMergePredicate can_merge = queue.getMergePredicate(zookeeper);
|
||||
|
||||
FutureMergedMutatedPart future_merged_part;
|
||||
if (storage_settings.get()->assign_part_uuids)
|
||||
future_merged_part.uuid = UUIDHelpers::generateV4();
|
||||
|
||||
String disable_reason;
|
||||
bool selected = false;
|
||||
if (!partition)
|
||||
@ -3905,7 +3931,7 @@ bool StorageReplicatedMergeTree::optimize(
|
||||
ReplicatedMergeTreeLogEntryData merge_entry;
|
||||
CreateMergeEntryResult create_result = createLogEntryToMergeParts(
|
||||
zookeeper, future_merged_part.parts,
|
||||
future_merged_part.name, future_merged_part.type, deduplicate,
|
||||
future_merged_part.name, future_merged_part.uuid, future_merged_part.type, deduplicate,
|
||||
&merge_entry, can_merge.getVersion(), future_merged_part.merge_type);
|
||||
|
||||
if (create_result == CreateMergeEntryResult::MissingPart)
|
||||
|
||||
@ -464,6 +464,7 @@ private:
|
||||
zkutil::ZooKeeperPtr & zookeeper,
|
||||
const DataPartsVector & parts,
|
||||
const String & merged_name,
|
||||
const UUID & merged_part_uuid,
|
||||
const MergeTreeDataPartType & merged_part_type,
|
||||
bool deduplicate,
|
||||
ReplicatedMergeTreeLogEntryData * out_log_entry,
|
||||
@ -472,6 +473,7 @@ private:
|
||||
|
||||
CreateMergeEntryResult createLogEntryToMutatePart(
|
||||
const IMergeTreeDataPart & part,
|
||||
const UUID & new_part_uuid,
|
||||
Int64 mutation_version,
|
||||
int32_t alter_version,
|
||||
int32_t log_version);
|
||||
|
||||
@ -194,17 +194,17 @@ StorageS3::StorageS3(
|
||||
UInt64 min_upload_part_size_,
|
||||
const ColumnsDescription & columns_,
|
||||
const ConstraintsDescription & constraints_,
|
||||
Context & context_,
|
||||
const Context & context_,
|
||||
const String & compression_method_)
|
||||
: IStorage(table_id_)
|
||||
, uri(uri_)
|
||||
, context_global(context_)
|
||||
, global_context(context_.getGlobalContext())
|
||||
, format_name(format_name_)
|
||||
, min_upload_part_size(min_upload_part_size_)
|
||||
, compression_method(compression_method_)
|
||||
, name(uri_.storage_name)
|
||||
{
|
||||
context_global.getRemoteHostFilter().checkURL(uri_.uri);
|
||||
global_context.getRemoteHostFilter().checkURL(uri_.uri);
|
||||
StorageInMemoryMetadata storage_metadata;
|
||||
storage_metadata.setColumns(columns_);
|
||||
storage_metadata.setConstraints(constraints_);
|
||||
@ -325,7 +325,7 @@ BlockOutputStreamPtr StorageS3::write(const ASTPtr & /*query*/, const StorageMet
|
||||
{
|
||||
return std::make_shared<StorageS3BlockOutputStream>(
|
||||
format_name, min_upload_part_size, metadata_snapshot->getSampleBlock(),
|
||||
context_global, chooseCompressionMethod(uri.endpoint, compression_method),
|
||||
global_context, chooseCompressionMethod(uri.endpoint, compression_method),
|
||||
client, uri.bucket, uri.key);
|
||||
}
|
||||
|
||||
|
||||
@ -33,7 +33,7 @@ public:
|
||||
UInt64 min_upload_part_size_,
|
||||
const ColumnsDescription & columns_,
|
||||
const ConstraintsDescription & constraints_,
|
||||
Context & context_,
|
||||
const Context & context_,
|
||||
const String & compression_method_ = "");
|
||||
|
||||
String getName() const override
|
||||
@ -56,7 +56,7 @@ public:
|
||||
|
||||
private:
|
||||
S3::URI uri;
|
||||
const Context & context_global;
|
||||
const Context & global_context;
|
||||
|
||||
String format_name;
|
||||
UInt64 min_upload_part_size;
|
||||
|
||||
@ -93,6 +93,7 @@ const char * auto_contributors[] {
|
||||
"Anton Zhabolenko",
|
||||
"Ariel Robaldo",
|
||||
"Arsen Hakobyan",
|
||||
"ArtCorp",
|
||||
"Artem Andreenko",
|
||||
"Artem Gavrilov",
|
||||
"Artem Hnilov",
|
||||
@ -104,6 +105,7 @@ const char * auto_contributors[] {
|
||||
"Arthur Petukhovsky",
|
||||
"Arthur Tokarchuk",
|
||||
"Arthur Wong",
|
||||
"Artur",
|
||||
"Artur Beglaryan",
|
||||
"AsiaKorushkina",
|
||||
"Atri Sharma",
|
||||
@ -259,6 +261,7 @@ const char * auto_contributors[] {
|
||||
"Jochen Schalanda",
|
||||
"John",
|
||||
"Jonatas Freitas",
|
||||
"Kang Liu",
|
||||
"Karl Pietrzak",
|
||||
"Keiji Yoshida",
|
||||
"Kiran",
|
||||
@ -353,6 +356,7 @@ const char * auto_contributors[] {
|
||||
"NeZeD [Mac Pro]",
|
||||
"Neeke Gao",
|
||||
"Nico Mandery",
|
||||
"Nico Piderman",
|
||||
"Nicolae Vartolomei",
|
||||
"Nik",
|
||||
"Nikhil Raman",
|
||||
@ -379,7 +383,9 @@ const char * auto_contributors[] {
|
||||
"Olga Revyakina",
|
||||
"Orivej Desh",
|
||||
"Oskar Wojciski",
|
||||
"OuO",
|
||||
"Paramtamtam",
|
||||
"Patrick Zippenfenig",
|
||||
"Pavel",
|
||||
"Pavel Kartaviy",
|
||||
"Pavel Kartavyy",
|
||||
@ -461,6 +467,7 @@ const char * auto_contributors[] {
|
||||
"Tsarkova Anastasia",
|
||||
"Ubuntu",
|
||||
"Ubus",
|
||||
"V",
|
||||
"VDimir",
|
||||
"Vadim",
|
||||
"Vadim Plakhtinskiy",
|
||||
@ -527,6 +534,7 @@ const char * auto_contributors[] {
|
||||
"Yury Stankevich",
|
||||
"Zhichang Yu",
|
||||
"Zhipeng",
|
||||
"a.palagashvili",
|
||||
"abdrakhmanov",
|
||||
"abyss7",
|
||||
"achimbab",
|
||||
@ -546,6 +554,7 @@ const char * auto_contributors[] {
|
||||
"ana-uvarova",
|
||||
"andrei-karpliuk",
|
||||
"andrewsg",
|
||||
"annvsh",
|
||||
"anrodigina",
|
||||
"antikvist",
|
||||
"anton",
|
||||
@ -613,8 +622,10 @@ const char * auto_contributors[] {
|
||||
"ggerogery",
|
||||
"giordyb",
|
||||
"glockbender",
|
||||
"gyuton",
|
||||
"hao.he",
|
||||
"hcz",
|
||||
"heng zhao",
|
||||
"hexiaoting",
|
||||
"hotid",
|
||||
"hustnn",
|
||||
@ -694,6 +705,7 @@ const char * auto_contributors[] {
|
||||
"pufit",
|
||||
"pyos",
|
||||
"qianlixiang",
|
||||
"qianmoQ",
|
||||
"quid",
|
||||
"r1j1k",
|
||||
"rainbowsysu",
|
||||
@ -716,6 +728,7 @@ const char * auto_contributors[] {
|
||||
"spyros87",
|
||||
"stavrolia",
|
||||
"stepenhu",
|
||||
"su-houzhen",
|
||||
"sundy",
|
||||
"sundy-li",
|
||||
"sundyli",
|
||||
@ -727,6 +740,7 @@ const char * auto_contributors[] {
|
||||
"tavplubix",
|
||||
"topvisor",
|
||||
"tyrionhuang",
|
||||
"ubuntu",
|
||||
"unegare",
|
||||
"unknown",
|
||||
"urgordeadbeef",
|
||||
|
||||
@ -7,6 +7,7 @@
|
||||
#include <DataTypes/DataTypesNumber.h>
|
||||
#include <DataTypes/DataTypeDateTime.h>
|
||||
#include <DataTypes/DataTypeDate.h>
|
||||
#include <DataTypes/DataTypeUUID.h>
|
||||
#include <Storages/VirtualColumnUtils.h>
|
||||
#include <Databases/IDatabase.h>
|
||||
#include <Parsers/queryToString.h>
|
||||
@ -20,6 +21,7 @@ StorageSystemParts::StorageSystemParts(const StorageID & table_id_)
|
||||
{
|
||||
{"partition", std::make_shared<DataTypeString>()},
|
||||
{"name", std::make_shared<DataTypeString>()},
|
||||
{"uuid", std::make_shared<DataTypeUUID>()},
|
||||
{"part_type", std::make_shared<DataTypeString>()},
|
||||
{"active", std::make_shared<DataTypeUInt8>()},
|
||||
{"marks", std::make_shared<DataTypeUInt64>()},
|
||||
@ -93,6 +95,7 @@ void StorageSystemParts::processNextStorage(MutableColumns & columns_, const Sto
|
||||
columns_[i++]->insert(out.str());
|
||||
}
|
||||
columns_[i++]->insert(part->name);
|
||||
columns_[i++]->insert(part->uuid);
|
||||
columns_[i++]->insert(part->getTypeName());
|
||||
columns_[i++]->insert(part_state == State::Committed);
|
||||
columns_[i++]->insert(part->getMarksCount());
|
||||
|
||||
@ -10,6 +10,7 @@
|
||||
# include <DataTypes/convertMySQLDataType.h>
|
||||
# include <Formats/MySQLBlockInputStream.h>
|
||||
# include <IO/Operators.h>
|
||||
# include <Interpreters/Context.h>
|
||||
# include <Interpreters/evaluateConstantExpression.h>
|
||||
# include <Parsers/ASTFunction.h>
|
||||
# include <Parsers/ASTLiteral.h>
|
||||
|
||||
8
tests/config/config.d/logging_no_rotate.xml
Normal file
8
tests/config/config.d/logging_no_rotate.xml
Normal file
@ -0,0 +1,8 @@
|
||||
<yandex>
|
||||
<logger>
|
||||
<!-- Disable rotation
|
||||
https://pocoproject.org/docs/Poco.FileChannel.html
|
||||
-->
|
||||
<size>never</size>
|
||||
</logger>
|
||||
</yandex>
|
||||
@ -28,6 +28,7 @@ ln -sf $SRC_PATH/config.d/clusters.xml $DEST_SERVER_PATH/config.d/
|
||||
ln -sf $SRC_PATH/config.d/graphite.xml $DEST_SERVER_PATH/config.d/
|
||||
ln -sf $SRC_PATH/config.d/database_atomic.xml $DEST_SERVER_PATH/config.d/
|
||||
ln -sf $SRC_PATH/config.d/test_cluster_with_incorrect_pw.xml $DEST_SERVER_PATH/config.d/
|
||||
ln -sf $SRC_PATH/config.d/logging_no_rotate.xml $DEST_SERVER_PATH/config.d/
|
||||
ln -sf $SRC_PATH/users.d/log_queries.xml $DEST_SERVER_PATH/users.d/
|
||||
ln -sf $SRC_PATH/users.d/readonly.xml $DEST_SERVER_PATH/users.d/
|
||||
ln -sf $SRC_PATH/users.d/access_management.xml $DEST_SERVER_PATH/users.d/
|
||||
|
||||
@ -154,6 +154,36 @@ def test_mysql_client_exception(mysql_client, server_address):
|
||||
"ERROR 1000 (00000) at line 1: Poco::Exception. Code: 1000, e.code() = 2002, e.displayText() = mysqlxx::ConnectionFailed: Can't connect to MySQL server on '127.0.0.1' (115) ((nullptr):0)"
|
||||
|
||||
|
||||
def test_mysql_affected_rows(mysql_client, server_address):
|
||||
code, (stdout, stderr) = mysql_client.exec_run('''
|
||||
mysql --protocol tcp -h {host} -P {port} default -u default --password=123
|
||||
-e "CREATE TABLE IF NOT EXISTS default.t1 (n UInt64) ENGINE MergeTree() ORDER BY tuple();"
|
||||
'''.format(host=server_address, port=server_port), demux=True)
|
||||
assert code == 0
|
||||
|
||||
code, (stdout, stderr) = mysql_client.exec_run('''
|
||||
mysql -vvv --protocol tcp -h {host} -P {port} default -u default --password=123
|
||||
-e "INSERT INTO default.t1(n) VALUES(1);"
|
||||
'''.format(host=server_address, port=server_port), demux=True)
|
||||
|
||||
assert code == 0
|
||||
assert "1 row affected" in stdout.decode()
|
||||
|
||||
code, (stdout, stderr) = mysql_client.exec_run('''
|
||||
mysql -vvv --protocol tcp -h {host} -P {port} default -u default --password=123
|
||||
-e "INSERT INTO default.t1(n) SELECT * FROM numbers(1000)"
|
||||
'''.format(host=server_address, port=server_port), demux=True)
|
||||
|
||||
assert code == 0
|
||||
assert "1000 rows affected" in stdout.decode()
|
||||
|
||||
code, (stdout, stderr) = mysql_client.exec_run('''
|
||||
mysql --protocol tcp -h {host} -P {port} default -u default --password=123
|
||||
-e "DROP TABLE default.t1;"
|
||||
'''.format(host=server_address, port=server_port), demux=True)
|
||||
assert code == 0
|
||||
|
||||
|
||||
def test_mysql_replacement_query(mysql_client, server_address):
|
||||
# SHOW TABLE STATUS LIKE.
|
||||
code, (stdout, stderr) = mysql_client.exec_run('''
|
||||
|
||||
0
tests/integration/test_part_uuid/__init__.py
Normal file
0
tests/integration/test_part_uuid/__init__.py
Normal file
@ -0,0 +1,6 @@
|
||||
<yandex>
|
||||
<merge_tree>
|
||||
<min_rows_for_compact_part>1000</min_rows_for_compact_part>
|
||||
<min_rows_for_wide_part>1000</min_rows_for_wide_part>
|
||||
</merge_tree>
|
||||
</yandex>
|
||||
@ -0,0 +1,5 @@
|
||||
<yandex>
|
||||
<merge_tree>
|
||||
<assign_part_uuids>1</assign_part_uuids>
|
||||
</merge_tree>
|
||||
</yandex>
|
||||
18
tests/integration/test_part_uuid/configs/remote_servers.xml
Normal file
18
tests/integration/test_part_uuid/configs/remote_servers.xml
Normal file
@ -0,0 +1,18 @@
|
||||
<yandex>
|
||||
<remote_servers>
|
||||
<test_cluster>
|
||||
<shard>
|
||||
<replica>
|
||||
<host>node1</host>
|
||||
<port>9000</port>
|
||||
</replica>
|
||||
</shard>
|
||||
<shard>
|
||||
<replica>
|
||||
<host>node2</host>
|
||||
<port>9000</port>
|
||||
</replica>
|
||||
</shard>
|
||||
</test_cluster>
|
||||
</remote_servers>
|
||||
</yandex>
|
||||
108
tests/integration/test_part_uuid/test.py
Normal file
108
tests/integration/test_part_uuid/test.py
Normal file
@ -0,0 +1,108 @@
|
||||
import uuid
|
||||
|
||||
import pytest
|
||||
|
||||
from helpers.cluster import ClickHouseCluster
|
||||
|
||||
cluster = ClickHouseCluster(__file__)
|
||||
|
||||
node1 = cluster.add_instance(
|
||||
'node1',
|
||||
main_configs=['configs/remote_servers.xml', 'configs/merge_tree_uuids.xml'],
|
||||
with_zookeeper=True)
|
||||
|
||||
node2 = cluster.add_instance(
|
||||
'node2',
|
||||
main_configs=['configs/remote_servers.xml', 'configs/merge_tree_uuids.xml', 'configs/merge_tree_in_memory.xml'],
|
||||
with_zookeeper=True)
|
||||
|
||||
|
||||
@pytest.fixture(scope="module")
|
||||
def started_cluster():
|
||||
try:
|
||||
cluster.start()
|
||||
yield cluster
|
||||
finally:
|
||||
cluster.shutdown()
|
||||
|
||||
|
||||
def test_part_uuid(started_cluster):
|
||||
uuid_zero = uuid.UUID(bytes=b"\x00" * 16)
|
||||
|
||||
for ix, n in enumerate([node1, node2]):
|
||||
n.query("""
|
||||
CREATE TABLE t(key UInt64, value UInt64)
|
||||
ENGINE ReplicatedMergeTree('/clickhouse/tables/t', '{}')
|
||||
ORDER BY tuple()
|
||||
""".format(ix))
|
||||
|
||||
# Test insert assigns uuid to part.
|
||||
node1.query("INSERT INTO t VALUES (1, 1)")
|
||||
|
||||
uuids = set()
|
||||
for node in [node1, node2]:
|
||||
node.query("SYSTEM SYNC REPLICA t")
|
||||
part_initial_uuid = uuid.UUID(node.query("SELECT uuid FROM system.parts WHERE table = 't' AND active ORDER BY name").strip())
|
||||
uuids.add(part_initial_uuid)
|
||||
assert uuid_zero != part_initial_uuid
|
||||
assert len(uuids) == 1, "expect the same uuid on all the replicas"
|
||||
|
||||
# Test detach / attach.
|
||||
node1.query("ALTER TABLE t DETACH PARTITION tuple(); ALTER TABLE t ATTACH PARTITION tuple()")
|
||||
|
||||
for node in [node1, node2]:
|
||||
node.query("SYSTEM SYNC REPLICA t")
|
||||
part_reattach_uuid = uuid.UUID(node.query(
|
||||
"SELECT uuid FROM system.parts WHERE table = 't' AND active ORDER BY name").strip())
|
||||
assert part_initial_uuid == part_reattach_uuid
|
||||
|
||||
# Test mutation assigns new non-zero uuids.
|
||||
node1.query("ALTER TABLE t UPDATE value = 1 WHERE key = 1 SETTINGS mutations_sync = 2")
|
||||
part_mutate_uuid = uuid.UUID(node1.query("SELECT uuid FROM system.parts WHERE table = 't' AND active ORDER BY name").strip())
|
||||
assert part_mutate_uuid not in [uuid_zero, part_initial_uuid]
|
||||
|
||||
node2.query("SYSTEM SYNC REPLICA t")
|
||||
assert part_mutate_uuid == uuid.UUID(node2.query(
|
||||
"SELECT uuid FROM system.parts WHERE table = 't' AND active ORDER BY name").strip())
|
||||
|
||||
# Test merge assigns new non-zero uuids.
|
||||
node2.query("INSERT INTO t VALUES (1, 1)")
|
||||
node2.query("OPTIMIZE TABLE t FINAL")
|
||||
|
||||
uuids = set()
|
||||
for node in [node1, node2]:
|
||||
node.query("SYSTEM SYNC REPLICA t")
|
||||
part_merge_uuid = uuid.UUID(node.query(
|
||||
"SELECT uuid FROM system.parts WHERE table = 't' AND active ORDER BY name").strip())
|
||||
uuids.add(part_merge_uuid)
|
||||
assert part_mutate_uuid not in [uuid_zero, part_merge_uuid]
|
||||
assert len(uuids) == 1, "expect the same uuid on all the replicas"
|
||||
|
||||
|
||||
def test_part_uuid_wal(started_cluster):
|
||||
uuid_zero = uuid.UUID(bytes=b"\x00" * 16)
|
||||
|
||||
for ix, n in enumerate([node1, node2]):
|
||||
n.query("""
|
||||
CREATE TABLE t_wal(key UInt64, value UInt64)
|
||||
ENGINE ReplicatedMergeTree('/clickhouse/tables/t_wal', '{}')
|
||||
ORDER BY tuple()
|
||||
""".format(ix))
|
||||
|
||||
node2.query("INSERT INTO t_wal VALUES (1, 1)")
|
||||
|
||||
uuids = set()
|
||||
for node in [node1, node2]:
|
||||
node.query("SYSTEM SYNC REPLICA t")
|
||||
part_initial_uuid = uuid.UUID(node.query("SELECT uuid FROM system.parts WHERE table = 't_wal' AND active ORDER BY name").strip())
|
||||
assert "InMemory" == node.query("SELECT part_type FROM system.parts WHERE table = 't_wal' AND active ORDER BY name").strip()
|
||||
uuids.add(part_initial_uuid)
|
||||
assert uuid_zero != part_initial_uuid
|
||||
assert len(uuids) == 1, "expect the same uuid on all the replicas"
|
||||
|
||||
# Test detach / attach table to trigger WAL processing.
|
||||
for node in [node1, node2]:
|
||||
node.query("DETACH TABLE t_wal; ATTACH TABLE t_wal")
|
||||
part_reattach_uuid = uuid.UUID(node.query(
|
||||
"SELECT uuid FROM system.parts WHERE table = 't_wal' AND active ORDER BY name").strip())
|
||||
assert part_initial_uuid == part_reattach_uuid
|
||||
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue
Block a user