thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-09-19 16:20:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

Changes to support the CRC32 in PowerPC to address the WeakHash collision issue. Update the reference to support the hash values based on the specific platform

Browse Source
This commit is contained in:
MeenaRenganathan22 2023-01-10 20:56:16 -08:00
parent 4b28b39f7c
commit 25c94dfa83
17 changed files with 1844 additions and 115 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
.gitmodules vendored
View File

@ -327,3 +327,6 @@
[submodule "contrib/aws-s2n-tls"]
path = contrib/aws-s2n-tls
url = https://github.com/ClickHouse/s2n-tls
[submodule "contrib/crc32-vpmsum"]
path = contrib/crc32-vpmsum
url = https://github.com/antonblanchard/crc32-vpmsum.git

1
contrib/CMakeLists.txt vendored
View File

@ -55,6 +55,7 @@ else ()
endif ()
add_contrib (miniselect-cmake miniselect)
add_contrib (pdqsort-cmake pdqsort)
add_contrib (crc32-vpmsum-cmake crc32-vpmsum)
add_contrib (sparsehash-c11-cmake sparsehash-c11)
add_contrib (abseil-cpp-cmake abseil-cpp)
add_contrib (magic-enum-cmake magic_enum)

1
contrib/crc32-vpmsum vendored Submodule

@ -0,0 +1 @@
Subproject commit 452155439389311fc7d143621eaf56a258e02476

12
contrib/crc32-vpmsum-cmake/CMakeLists.txt Normal file
View File

@ -0,0 +1,12 @@
if (NOT ARCH_PPC64LE)
message(STATUS "crc32-vpmsum library is only supported on ppc64le")
return()
endif()
SET(LIBRARY_DIR "${ClickHouse_SOURCE_DIR}/contrib/crc32-vpmsum")
add_library(_crc32-vpmsum
"${LIBRARY_DIR}/vec_crc32.c"
)
target_include_directories(_crc32-vpmsum SYSTEM BEFORE PUBLIC "${CMAKE_CURRENT_SOURCE_DIR}")
add_library(ch_contrib::crc32-vpmsum ALIAS _crc32-vpmsum)

8
contrib/crc32-vpmsum-cmake/README.md Normal file
View File

@ -0,0 +1,8 @@
# To Generate crc32_constants.h
- Run make file in `../crc32-vpmsum` diretory using folling options and CRC polynomial. These options should use the same polynomial and order used by intel intrinisic functions
```bash
make crc32_constants.h CRC="0x11EDC6F41" OPTIONS="-x -r -c"
```
- move the generated `crc32_constants.h` into this directory
- To understand more about this go here: https://masterchef2209.wordpress.com/2020/06/17/guide-to-intel-sse4-2-crc-intrinisics-implementation-for-simde/

1206
contrib/crc32-vpmsum-cmake/crc32_constants.h Normal file
View File

File diff suppressed because it is too large Load Diff

29
contrib/crc32-vpmsum-cmake/vec_crc32.h Normal file
View File

@ -0,0 +1,29 @@
#ifndef VEC_CRC32
#define VEC_CRC32
#ifdef __cplusplus
extern "C" {
#endif
unsigned int crc32_vpmsum(unsigned int crc, const unsigned char *p, unsigned long len);
static inline uint32_t crc32_ppc(uint64_t crc, unsigned char const *buffer, size_t len)
{
unsigned char *emptybuffer;
if (!buffer) {
emptybuffer = (unsigned char *)malloc(len);
bzero(emptybuffer, len);
crc = crc32_vpmsum(crc, emptybuffer, len);
free(emptybuffer);
} else {
crc = crc32_vpmsum(crc, buffer, (unsigned long)len);
}
return crc;
}
#ifdef __cplusplus
}
#endif
#endif

4
src/CMakeLists.txt
View File

@ -364,6 +364,10 @@ if (TARGET ch_contrib::crc32_s390x)
target_link_libraries(clickhouse_common_io PUBLIC ch_contrib::crc32_s390x)
endif()
if (TARGET ch_contrib::crc32-vpmsum)
target_link_libraries(clickhouse_common_io PUBLIC ch_contrib::crc32-vpmsum)
endif()
dbms_target_link_libraries(PUBLIC ch_contrib::abseil_swiss_tables)
target_link_libraries (clickhouse_common_io PUBLIC ch_contrib::abseil_swiss_tables)

8
src/Common/HashTable/Hash.h
View File

@ -48,6 +48,10 @@ inline DB::UInt64 intHash64(DB::UInt64 x)
#include <arm_acle.h>
#endif
#if (defined(__PPC64__) || defined(__powerpc64__)) && __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
#include "vec_crc32.h"
#endif
#if defined(__s390x__) && __BYTE_ORDER__==__ORDER_BIG_ENDIAN__
#include <crc32-s390x.h>
@ -89,6 +93,8 @@ inline DB::UInt64 intHashCRC32(DB::UInt64 x)
return __crc32cd(-1U, x);
#elif defined(__s390x__) && __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
return s390x_crc32(-1U, x)
#elif (defined(__PPC64__) || defined(__powerpc64__)) && __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
return crc32_ppc(-1U, reinterpret_cast<const unsigned char *>(&x), sizeof(x));
#else
/// On other platforms we do not have CRC32. NOTE This can be confusing.
/// NOTE: consider using intHash32()
@ -103,6 +109,8 @@ inline DB::UInt64 intHashCRC32(DB::UInt64 x, DB::UInt64 updated_value)
return __crc32cd(static_cast<UInt32>(updated_value), x);
#elif defined(__s390x__) && __BYTE_ORDER__==__ORDER_BIG_ENDIAN__
return s390x_crc32(updated_value, x);
#elif (defined(__PPC64__) || defined(__powerpc64__)) && __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
return crc32_ppc(updated_value, reinterpret_cast<const unsigned char *>(&x), sizeof(x));
#else
/// On other platforms we do not have CRC32. NOTE This can be confusing.
return intHash64(x) ^ updated_value;

4
src/Functions/CMakeLists.txt
View File

@ -86,6 +86,10 @@ if (TARGET ch_contrib::rapidjson)
list (APPEND PRIVATE_LIBS ch_contrib::rapidjson)
endif()
if (TARGET ch_contrib::crc32-vpmsum)
list (APPEND PUBLIC_LIBS ch_contrib::crc32-vpmsum)
endif()
add_subdirectory(GatherUtils)
list (APPEND PRIVATE_LIBS clickhouse_functions_gatherutils)

12
src/Functions/FunctionsStringHash.cpp
View File

@ -14,6 +14,10 @@
#include <city.h>
#if (defined(__PPC64__) || defined(__powerpc64__)) && __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
#include "vec_crc32.h"
#endif
namespace DB
{
@ -38,6 +42,8 @@ struct Hash
return __crc32cd(static_cast<UInt32>(crc), val);
#elif defined(__s390x__) && __BYTE_ORDER__==__ORDER_BIG_ENDIAN__
return s390x_crc32(crc, val);
#elif (defined(__PPC64__) || defined(__powerpc64__)) && __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
return crc32_ppc(crc, reinterpret_cast<const unsigned char *>(&val), sizeof(val));
#else
throw Exception("String hash is not implemented without sse4.2 support", ErrorCodes::NOT_IMPLEMENTED);
#endif
@ -51,6 +57,8 @@ struct Hash
return __crc32cw(crc, val);
#elif defined(__s390x__) && __BYTE_ORDER__==__ORDER_BIG_ENDIAN__
return s390x_crc32_u32(crc, val);
#elif (defined(__PPC64__) || defined(__powerpc64__)) && __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
return crc32_ppc(crc, reinterpret_cast<const unsigned char *>(&val), sizeof(val));
#else
throw Exception("String hash is not implemented without sse4.2 support", ErrorCodes::NOT_IMPLEMENTED);
#endif
@ -64,6 +72,8 @@ struct Hash
return __crc32ch(crc, val);
#elif defined(__s390x__) && __BYTE_ORDER__==__ORDER_BIG_ENDIAN__
return s390x_crc32_u16(crc, val);
#elif (defined(__PPC64__) || defined(__powerpc64__)) && __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
return crc32_ppc(crc, reinterpret_cast<const unsigned char *>(&val), sizeof(val));
#else
throw Exception("String hash is not implemented without sse4.2 support", ErrorCodes::NOT_IMPLEMENTED);
#endif
@ -77,6 +87,8 @@ struct Hash
return __crc32cb(crc, val);
#elif defined(__s390x__) && __BYTE_ORDER__==__ORDER_BIG_ENDIAN__
return s390x_crc32_u8(crc, val);
#elif (defined(__PPC64__) || defined(__powerpc64__)) && __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
return crc32_ppc(crc, reinterpret_cast<const unsigned char *>(&val), sizeof(val));
#else
throw Exception("String hash is not implemented without sse4.2 support", ErrorCodes::NOT_IMPLEMENTED);
#endif

6
src/Functions/FunctionsStringSimilarity.cpp
View File

@ -24,6 +24,10 @@
# include <arm_acle.h>
#endif
#if (defined(__PPC64__) || defined(__powerpc64__)) && __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
#include "vec_crc32.h"
#endif
namespace DB
{
/** Distance function implementation.
@ -72,6 +76,8 @@ struct NgramDistanceImpl
return __crc32cd(code_points[2], combined) & 0xFFFFu;
#elif defined(__s390x__) && __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
return s390x_crc32(code_points[2], combined) & 0xFFFFu;
#elif (defined(__PPC64__) || defined(__powerpc64__)) && __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
return crc32_ppc(code_points[2], reinterpret_cast<const unsigned char *>(&combined), sizeof(combined)) & 0xFFFFu;
#else
return (intHashCRC32(combined) ^ intHashCRC32(code_points[2])) & 0xFFFFu;
#endif

148
tests/queries/0_stateless/01016_simhash_minhash.ppc64le.reference Normal file
View File

@ -0,0 +1,148 @@
18446744073709551615
1737075136
1737075136
4018781633
4018781633
1846985414
1846985414
1846985414
1846985414
(10693559443859979498,10693559443859979498)
(12279482788274235946,6436413987527322272)
(12279482788274235946,6436413987527322272)
(13257488272755813409,6436413987527322272)
(13257488272755813409,6436413987527322272)
(13762864994695140861,13762864994695140861)
(13762864994695140861,13762864994695140861)
(13762864994695140861,13762864994695140861)
(13762864994695140861,13762864994695140861)
3023525975
3040303199
3023509591
3023510623
3040303191
3040303191
3023510615
3023510615
1999952988
926211140
1999699532
1999683148
1999952988
926211140
1999699532
1999683148
(16071125717475221203,9592059329600248798)
(16071125717475221203,1914899959549098907)
(16071125717475221203,7986182634218042944)
(16071125717475221203,7986182634218042944)
(16071125717475221203,9592059329600248798)
(16071125717475221203,1914899959549098907)
(16071125717475221203,7986182634218042944)
(16071125717475221203,7986182634218042944)
(10576877560263640956,4278250516018530743)
(16211512098526494023,11479872370566432466)
(13515070557027359649,17725505493832406849)
(12589381623326290380,575343713614534202)
(10576877560263640956,4278250516018530743)
(16211512098526494023,11479872370566432466)
(13515070557027359649,17725505493832406849)
(12589381623326290380,575343713614534202)
uniqExact 6
ngramSimHash
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns after decompression only). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all processing of your data: it loads all your structured data into the system and immediately becomes available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems.\n:::::::\nClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns after decompression only). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all processing of your data: it loads all structured data into the system and immediately becomes available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 2 1211135069
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns only after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all of your structured data into the system, and it is immediately available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 1546679389
ClickHouse uses all available hardware to its full potential to process each query as fast as possible. Peak processing performance for a single query stands at more than 2 terabytes per second (after decompression, only used columns). In distributed setup reads are automatically balanced among healthy replicas to avoid increasing latency.\nClickHouse supports multi-master asynchronous replication and can be deployed across multiple datacenters. All nodes are equal, which allows avoiding having single points of failure. Downtime of a single node or the whole datacenter wont affect the systems availability for both reads and writes.\nClickHouse is simple and works out-of-the-box. It streamlines all your data processing: ingest all your structured data into the system and it becomes instantly available for building reports. SQL dialect allows expressing the desired result without involving any custom non-standard API that could be found in some alternative systems. 1 2293265501
ClickHouse makes full use of all available hardware to process every request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (only used columns after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid single points of failure. Downtime for one site or the entire data center will not affect the system\'s read and write availability.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all your structured data into the system, and they immediately become available for building reports. The SQL dialect allows you to express the desired result without resorting to any non-standard APIs that can be found in some alternative systems. 1 3392173149
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (used columns only after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the system\'s read / write availability.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all your structured data into the system, and they are immediately available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 3627054169
ngramSimHashCaseInsensitive
ClickHouse uses all available hardware to its full potential to process each query as fast as possible. Peak processing performance for a single query stands at more than 2 terabytes per second (after decompression, only used columns). In distributed setup reads are automatically balanced among healthy replicas to avoid increasing latency.\nClickHouse supports multi-master asynchronous replication and can be deployed across multiple datacenters. All nodes are equal, which allows avoiding having single points of failure. Downtime of a single node or the whole datacenter wont affect the systems availability for both reads and writes.\nClickHouse is simple and works out-of-the-box. It streamlines all your data processing: ingest all your structured data into the system and it becomes instantly available for building reports. SQL dialect allows expressing the desired result without involving any custom non-standard API that could be found in some alternative systems. 1 2291168349
ClickHouse makes full use of all available hardware to process every request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (only used columns after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid single points of failure. Downtime for one site or the entire data center will not affect the system\'s read and write availability.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all your structured data into the system, and they immediately become available for building reports. The SQL dialect allows you to express the desired result without resorting to any non-standard APIs that can be found in some alternative systems.\n:::::::\nClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns after decompression only). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all processing of your data: it loads all your structured data into the system and immediately becomes available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems.\n:::::::\nClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns after decompression only). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all processing of your data: it loads all structured data into the system and immediately becomes available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 3 3358618717
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns only after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all of your structured data into the system, and it is immediately available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 3425727581
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (used columns only after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the system\'s read / write availability.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all your structured data into the system, and they are immediately available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 3627054429
ngramSimHashUTF8
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns after decompression only). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all processing of your data: it loads all your structured data into the system and immediately becomes available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems.\n:::::::\nClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns after decompression only). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all processing of your data: it loads all structured data into the system and immediately becomes available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 2 1211135069
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns only after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all of your structured data into the system, and it is immediately available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 1546679389
ClickHouse uses all available hardware to its full potential to process each query as fast as possible. Peak processing performance for a single query stands at more than 2 terabytes per second (after decompression, only used columns). In distributed setup reads are automatically balanced among healthy replicas to avoid increasing latency.\nClickHouse supports multi-master asynchronous replication and can be deployed across multiple datacenters. All nodes are equal, which allows avoiding having single points of failure. Downtime of a single node or the whole datacenter wont affect the systems availability for both reads and writes.\nClickHouse is simple and works out-of-the-box. It streamlines all your data processing: ingest all your structured data into the system and it becomes instantly available for building reports. SQL dialect allows expressing the desired result without involving any custom non-standard API that could be found in some alternative systems. 1 2284876893
ClickHouse makes full use of all available hardware to process every request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (only used columns after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid single points of failure. Downtime for one site or the entire data center will not affect the system\'s read and write availability.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all your structured data into the system, and they immediately become available for building reports. The SQL dialect allows you to express the desired result without resorting to any non-standard APIs that can be found in some alternative systems. 1 3459282013
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (used columns only after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the system\'s read / write availability.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all your structured data into the system, and they are immediately available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 3694163037
ngramSimHashCaseInsensitiveUTF8
ClickHouse uses all available hardware to its full potential to process each query as fast as possible. Peak processing performance for a single query stands at more than 2 terabytes per second (after decompression, only used columns). In distributed setup reads are automatically balanced among healthy replicas to avoid increasing latency.\nClickHouse supports multi-master asynchronous replication and can be deployed across multiple datacenters. All nodes are equal, which allows avoiding having single points of failure. Downtime of a single node or the whole datacenter wont affect the systems availability for both reads and writes.\nClickHouse is simple and works out-of-the-box. It streamlines all your data processing: ingest all your structured data into the system and it becomes instantly available for building reports. SQL dialect allows expressing the desired result without involving any custom non-standard API that could be found in some alternative systems. 1 2291168349
ClickHouse makes full use of all available hardware to process every request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (only used columns after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid single points of failure. Downtime for one site or the entire data center will not affect the system\'s read and write availability.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all your structured data into the system, and they immediately become available for building reports. The SQL dialect allows you to express the desired result without resorting to any non-standard APIs that can be found in some alternative systems.\n:::::::\nClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns after decompression only). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all processing of your data: it loads all your structured data into the system and immediately becomes available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems.\n:::::::\nClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns after decompression only). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all processing of your data: it loads all structured data into the system and immediately becomes available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 3 3358618717
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns only after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all of your structured data into the system, and it is immediately available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 3425727581
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (used columns only after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the system\'s read / write availability.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all your structured data into the system, and they are immediately available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 3627054429
wordShingleSimHash
ClickHouse makes full use of all available hardware to process every request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (only used columns after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid single points of failure. Downtime for one site or the entire data center will not affect the system\'s read and write availability.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all your structured data into the system, and they immediately become available for building reports. The SQL dialect allows you to express the desired result without resorting to any non-standard APIs that can be found in some alternative systems. 1 10637533
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (used columns only after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the system\'s read / write availability.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all your structured data into the system, and they are immediately available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 171136201
ClickHouse uses all available hardware to its full potential to process each query as fast as possible. Peak processing performance for a single query stands at more than 2 terabytes per second (after decompression, only used columns). In distributed setup reads are automatically balanced among healthy replicas to avoid increasing latency.\nClickHouse supports multi-master asynchronous replication and can be deployed across multiple datacenters. All nodes are equal, which allows avoiding having single points of failure. Downtime of a single node or the whole datacenter wont affect the systems availability for both reads and writes.\nClickHouse is simple and works out-of-the-box. It streamlines all your data processing: ingest all your structured data into the system and it becomes instantly available for building reports. SQL dialect allows expressing the desired result without involving any custom non-standard API that could be found in some alternative systems. 1 209864029
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns after decompression only). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all processing of your data: it loads all your structured data into the system and immediately becomes available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 413353165
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns after decompression only). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all processing of your data: it loads all structured data into the system and immediately becomes available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 413353677
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns only after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all of your structured data into the system, and it is immediately available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 418595033
wordShingleSimHashCaseInsensitive
ClickHouse uses all available hardware to its full potential to process each query as fast as possible. Peak processing performance for a single query stands at more than 2 terabytes per second (after decompression, only used columns). In distributed setup reads are automatically balanced among healthy replicas to avoid increasing latency.\nClickHouse supports multi-master asynchronous replication and can be deployed across multiple datacenters. All nodes are equal, which allows avoiding having single points of failure. Downtime of a single node or the whole datacenter wont affect the systems availability for both reads and writes.\nClickHouse is simple and works out-of-the-box. It streamlines all your data processing: ingest all your structured data into the system and it becomes instantly available for building reports. SQL dialect allows expressing the desired result without involving any custom non-standard API that could be found in some alternative systems. 1 218252892
ClickHouse makes full use of all available hardware to process every request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (only used columns after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid single points of failure. Downtime for one site or the entire data center will not affect the system\'s read and write availability.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all your structured data into the system, and they immediately become available for building reports. The SQL dialect allows you to express the desired result without resorting to any non-standard APIs that can be found in some alternative systems. 1 1218592985
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (used columns only after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the system\'s read / write availability.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all your structured data into the system, and they are immediately available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 1613919433
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns after decompression only). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all processing of your data: it loads all your structured data into the system and immediately becomes available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 2080524225
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns after decompression only). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all processing of your data: it loads all structured data into the system and immediately becomes available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 2088912577
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns only after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all of your structured data into the system, and it is immediately available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 2094163657
wordShingleSimHashUTF8
ClickHouse makes full use of all available hardware to process every request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (only used columns after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid single points of failure. Downtime for one site or the entire data center will not affect the system\'s read and write availability.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all your structured data into the system, and they immediately become available for building reports. The SQL dialect allows you to express the desired result without resorting to any non-standard APIs that can be found in some alternative systems. 1 10637533
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (used columns only after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the system\'s read / write availability.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all your structured data into the system, and they are immediately available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 171136201
ClickHouse uses all available hardware to its full potential to process each query as fast as possible. Peak processing performance for a single query stands at more than 2 terabytes per second (after decompression, only used columns). In distributed setup reads are automatically balanced among healthy replicas to avoid increasing latency.\nClickHouse supports multi-master asynchronous replication and can be deployed across multiple datacenters. All nodes are equal, which allows avoiding having single points of failure. Downtime of a single node or the whole datacenter wont affect the systems availability for both reads and writes.\nClickHouse is simple and works out-of-the-box. It streamlines all your data processing: ingest all your structured data into the system and it becomes instantly available for building reports. SQL dialect allows expressing the desired result without involving any custom non-standard API that could be found in some alternative systems. 1 209864029
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns after decompression only). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all processing of your data: it loads all your structured data into the system and immediately becomes available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 413353165
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns after decompression only). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all processing of your data: it loads all structured data into the system and immediately becomes available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 413353677
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns only after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all of your structured data into the system, and it is immediately available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 418595033
wordShingleSimHashCaseInsensitiveUTF8
ClickHouse uses all available hardware to its full potential to process each query as fast as possible. Peak processing performance for a single query stands at more than 2 terabytes per second (after decompression, only used columns). In distributed setup reads are automatically balanced among healthy replicas to avoid increasing latency.\nClickHouse supports multi-master asynchronous replication and can be deployed across multiple datacenters. All nodes are equal, which allows avoiding having single points of failure. Downtime of a single node or the whole datacenter wont affect the systems availability for both reads and writes.\nClickHouse is simple and works out-of-the-box. It streamlines all your data processing: ingest all your structured data into the system and it becomes instantly available for building reports. SQL dialect allows expressing the desired result without involving any custom non-standard API that could be found in some alternative systems. 1 218252892
ClickHouse makes full use of all available hardware to process every request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (only used columns after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid single points of failure. Downtime for one site or the entire data center will not affect the system\'s read and write availability.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all your structured data into the system, and they immediately become available for building reports. The SQL dialect allows you to express the desired result without resorting to any non-standard APIs that can be found in some alternative systems. 1 1218592985
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (used columns only after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the system\'s read / write availability.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all your structured data into the system, and they are immediately available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 1613919433
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns after decompression only). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all processing of your data: it loads all your structured data into the system and immediately becomes available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 2080524225
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns after decompression only). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all processing of your data: it loads all structured data into the system and immediately becomes available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 2088912577
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns only after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all of your structured data into the system, and it is immediately available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 2094163657
ngramMinHash
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (used columns only after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the system\'s read / write availability.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all your structured data into the system, and they are immediately available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 (2793448378579182412,5526633106516004292)
ClickHouse uses all available hardware to its full potential to process each query as fast as possible. Peak processing performance for a single query stands at more than 2 terabytes per second (after decompression, only used columns). In distributed setup reads are automatically balanced among healthy replicas to avoid increasing latency.\nClickHouse supports multi-master asynchronous replication and can be deployed across multiple datacenters. All nodes are equal, which allows avoiding having single points of failure. Downtime of a single node or the whole datacenter wont affect the systems availability for both reads and writes.\nClickHouse is simple and works out-of-the-box. It streamlines all your data processing: ingest all your structured data into the system and it becomes instantly available for building reports. SQL dialect allows expressing the desired result without involving any custom non-standard API that could be found in some alternative systems. 1 (8530889421347045182,5150364204263408031)
ClickHouse makes full use of all available hardware to process every request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (only used columns after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid single points of failure. Downtime for one site or the entire data center will not affect the system\'s read and write availability.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all your structured data into the system, and they immediately become available for building reports. The SQL dialect allows you to express the desired result without resorting to any non-standard APIs that can be found in some alternative systems. 1 (8992738078100405992,5526633106516004292)
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns only after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all of your structured data into the system, and it is immediately available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems.\n:::::::\nClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns after decompression only). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all processing of your data: it loads all your structured data into the system and immediately becomes available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems.\n:::::::\nClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns after decompression only). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all processing of your data: it loads all structured data into the system and immediately becomes available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 3 (15193387305258759701,5526633106516004292)
ngramMinHashCaseInsensitive
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (used columns only after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the system\'s read / write availability.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all your structured data into the system, and they are immediately available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 (2793448378579182412,5526633106516004292)
ClickHouse uses all available hardware to its full potential to process each query as fast as possible. Peak processing performance for a single query stands at more than 2 terabytes per second (after decompression, only used columns). In distributed setup reads are automatically balanced among healthy replicas to avoid increasing latency.\nClickHouse supports multi-master asynchronous replication and can be deployed across multiple datacenters. All nodes are equal, which allows avoiding having single points of failure. Downtime of a single node or the whole datacenter wont affect the systems availability for both reads and writes.\nClickHouse is simple and works out-of-the-box. It streamlines all your data processing: ingest all your structured data into the system and it becomes instantly available for building reports. SQL dialect allows expressing the desired result without involving any custom non-standard API that could be found in some alternative systems. 1 (8530889421347045182,5150364204263408031)
ClickHouse makes full use of all available hardware to process every request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (only used columns after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid single points of failure. Downtime for one site or the entire data center will not affect the system\'s read and write availability.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all your structured data into the system, and they immediately become available for building reports. The SQL dialect allows you to express the desired result without resorting to any non-standard APIs that can be found in some alternative systems. 1 (8992738078100405992,5526633106516004292)
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns only after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all of your structured data into the system, and it is immediately available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems.\n:::::::\nClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns after decompression only). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all processing of your data: it loads all your structured data into the system and immediately becomes available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems.\n:::::::\nClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns after decompression only). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all processing of your data: it loads all structured data into the system and immediately becomes available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 3 (15193387305258759701,5526633106516004292)
ngramMinHashUTF8
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (used columns only after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the system\'s read / write availability.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all your structured data into the system, and they are immediately available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 (2793448378579182412,5526633106516004292)
ClickHouse uses all available hardware to its full potential to process each query as fast as possible. Peak processing performance for a single query stands at more than 2 terabytes per second (after decompression, only used columns). In distributed setup reads are automatically balanced among healthy replicas to avoid increasing latency.\nClickHouse supports multi-master asynchronous replication and can be deployed across multiple datacenters. All nodes are equal, which allows avoiding having single points of failure. Downtime of a single node or the whole datacenter wont affect the systems availability for both reads and writes.\nClickHouse is simple and works out-of-the-box. It streamlines all your data processing: ingest all your structured data into the system and it becomes instantly available for building reports. SQL dialect allows expressing the desired result without involving any custom non-standard API that could be found in some alternative systems. 1 (8530889421347045182,5150364204263408031)
ClickHouse makes full use of all available hardware to process every request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (only used columns after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid single points of failure. Downtime for one site or the entire data center will not affect the system\'s read and write availability.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all your structured data into the system, and they immediately become available for building reports. The SQL dialect allows you to express the desired result without resorting to any non-standard APIs that can be found in some alternative systems. 1 (8992738078100405992,5526633106516004292)
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns only after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all of your structured data into the system, and it is immediately available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems.\n:::::::\nClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns after decompression only). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all processing of your data: it loads all your structured data into the system and immediately becomes available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems.\n:::::::\nClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns after decompression only). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all processing of your data: it loads all structured data into the system and immediately becomes available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 3 (15193387305258759701,5526633106516004292)
ngramMinHashCaseInsensitiveUTF8
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (used columns only after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the system\'s read / write availability.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all your structured data into the system, and they are immediately available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 (2793448378579182412,5526633106516004292)
ClickHouse uses all available hardware to its full potential to process each query as fast as possible. Peak processing performance for a single query stands at more than 2 terabytes per second (after decompression, only used columns). In distributed setup reads are automatically balanced among healthy replicas to avoid increasing latency.\nClickHouse supports multi-master asynchronous replication and can be deployed across multiple datacenters. All nodes are equal, which allows avoiding having single points of failure. Downtime of a single node or the whole datacenter wont affect the systems availability for both reads and writes.\nClickHouse is simple and works out-of-the-box. It streamlines all your data processing: ingest all your structured data into the system and it becomes instantly available for building reports. SQL dialect allows expressing the desired result without involving any custom non-standard API that could be found in some alternative systems. 1 (8530889421347045182,5150364204263408031)
ClickHouse makes full use of all available hardware to process every request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (only used columns after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid single points of failure. Downtime for one site or the entire data center will not affect the system\'s read and write availability.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all your structured data into the system, and they immediately become available for building reports. The SQL dialect allows you to express the desired result without resorting to any non-standard APIs that can be found in some alternative systems. 1 (8992738078100405992,5526633106516004292)
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns only after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all of your structured data into the system, and it is immediately available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems.\n:::::::\nClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns after decompression only). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all processing of your data: it loads all your structured data into the system and immediately becomes available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems.\n:::::::\nClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns after decompression only). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all processing of your data: it loads all structured data into the system and immediately becomes available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 3 (15193387305258759701,5526633106516004292)
wordShingleMinHash
ClickHouse makes full use of all available hardware to process every request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (only used columns after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid single points of failure. Downtime for one site or the entire data center will not affect the system\'s read and write availability.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all your structured data into the system, and they immediately become available for building reports. The SQL dialect allows you to express the desired result without resorting to any non-standard APIs that can be found in some alternative systems. 1 (3409292695558556998,3242671779450421938)
ClickHouse uses all available hardware to its full potential to process each query as fast as possible. Peak processing performance for a single query stands at more than 2 terabytes per second (after decompression, only used columns). In distributed setup reads are automatically balanced among healthy replicas to avoid increasing latency.\nClickHouse supports multi-master asynchronous replication and can be deployed across multiple datacenters. All nodes are equal, which allows avoiding having single points of failure. Downtime of a single node or the whole datacenter wont affect the systems availability for both reads and writes.\nClickHouse is simple and works out-of-the-box. It streamlines all your data processing: ingest all your structured data into the system and it becomes instantly available for building reports. SQL dialect allows expressing the desired result without involving any custom non-standard API that could be found in some alternative systems. 1 (11981468198903037199,5500630346333489583)
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (used columns only after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the system\'s read / write availability.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all your structured data into the system, and they are immediately available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems.\n:::::::\nClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns only after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all of your structured data into the system, and it is immediately available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 2 (12852656749419794093,678630951345180105)
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns after decompression only). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all processing of your data: it loads all structured data into the system and immediately becomes available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 (13105381013738345838,410122209669519134)
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns after decompression only). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all processing of your data: it loads all your structured data into the system and immediately becomes available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 (13105381013738345838,3365040177160857031)
wordShingleMinHashCaseInsensitive
ClickHouse makes full use of all available hardware to process every request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (only used columns after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid single points of failure. Downtime for one site or the entire data center will not affect the system\'s read and write availability.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all your structured data into the system, and they immediately become available for building reports. The SQL dialect allows you to express the desired result without resorting to any non-standard APIs that can be found in some alternative systems. 1 (712181695272576370,125062659592971094)
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (used columns only after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the system\'s read / write availability.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all your structured data into the system, and they are immediately available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems.\n:::::::\nClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns only after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all of your structured data into the system, and it is immediately available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 2 (3404326999173181417,12067981913120463876)
ClickHouse uses all available hardware to its full potential to process each query as fast as possible. Peak processing performance for a single query stands at more than 2 terabytes per second (after decompression, only used columns). In distributed setup reads are automatically balanced among healthy replicas to avoid increasing latency.\nClickHouse supports multi-master asynchronous replication and can be deployed across multiple datacenters. All nodes are equal, which allows avoiding having single points of failure. Downtime of a single node or the whole datacenter wont affect the systems availability for both reads and writes.\nClickHouse is simple and works out-of-the-box. It streamlines all your data processing: ingest all your structured data into the system and it becomes instantly available for building reports. SQL dialect allows expressing the desired result without involving any custom non-standard API that could be found in some alternative systems. 1 (13918035273694643957,5500630346333489583)
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns after decompression only). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all processing of your data: it loads all your structured data into the system and immediately becomes available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 (14132553626943388792,12467125901844798869)
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns after decompression only). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all processing of your data: it loads all structured data into the system and immediately becomes available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 (14132553626943388792,17567683680214055861)
wordShingleMinHashUTF8
ClickHouse makes full use of all available hardware to process every request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (only used columns after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid single points of failure. Downtime for one site or the entire data center will not affect the system\'s read and write availability.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all your structured data into the system, and they immediately become available for building reports. The SQL dialect allows you to express the desired result without resorting to any non-standard APIs that can be found in some alternative systems. 1 (3409292695558556998,3242671779450421938)
ClickHouse uses all available hardware to its full potential to process each query as fast as possible. Peak processing performance for a single query stands at more than 2 terabytes per second (after decompression, only used columns). In distributed setup reads are automatically balanced among healthy replicas to avoid increasing latency.\nClickHouse supports multi-master asynchronous replication and can be deployed across multiple datacenters. All nodes are equal, which allows avoiding having single points of failure. Downtime of a single node or the whole datacenter wont affect the systems availability for both reads and writes.\nClickHouse is simple and works out-of-the-box. It streamlines all your data processing: ingest all your structured data into the system and it becomes instantly available for building reports. SQL dialect allows expressing the desired result without involving any custom non-standard API that could be found in some alternative systems. 1 (11981468198903037199,5500630346333489583)
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (used columns only after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the system\'s read / write availability.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all your structured data into the system, and they are immediately available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems.\n:::::::\nClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns only after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all of your structured data into the system, and it is immediately available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 2 (12852656749419794093,678630951345180105)
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns after decompression only). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all processing of your data: it loads all structured data into the system and immediately becomes available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 (13105381013738345838,410122209669519134)
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns after decompression only). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all processing of your data: it loads all your structured data into the system and immediately becomes available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 (13105381013738345838,3365040177160857031)
wordShingleMinHashCaseInsensitiveUTF8
ClickHouse makes full use of all available hardware to process every request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (only used columns after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid single points of failure. Downtime for one site or the entire data center will not affect the system\'s read and write availability.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all your structured data into the system, and they immediately become available for building reports. The SQL dialect allows you to express the desired result without resorting to any non-standard APIs that can be found in some alternative systems. 1 (712181695272576370,125062659592971094)
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (used columns only after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the system\'s read / write availability.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all your structured data into the system, and they are immediately available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems.\n:::::::\nClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns only after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all of your structured data into the system, and it is immediately available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 2 (3404326999173181417,12067981913120463876)
ClickHouse uses all available hardware to its full potential to process each query as fast as possible. Peak processing performance for a single query stands at more than 2 terabytes per second (after decompression, only used columns). In distributed setup reads are automatically balanced among healthy replicas to avoid increasing latency.\nClickHouse supports multi-master asynchronous replication and can be deployed across multiple datacenters. All nodes are equal, which allows avoiding having single points of failure. Downtime of a single node or the whole datacenter wont affect the systems availability for both reads and writes.\nClickHouse is simple and works out-of-the-box. It streamlines all your data processing: ingest all your structured data into the system and it becomes instantly available for building reports. SQL dialect allows expressing the desired result without involving any custom non-standard API that could be found in some alternative systems. 1 (13918035273694643957,5500630346333489583)
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns after decompression only). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all processing of your data: it loads all your structured data into the system and immediately becomes available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 (14132553626943388792,12467125901844798869)
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns after decompression only). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.\nClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.\nClickHouse is simple and works out of the box. It simplifies all processing of your data: it loads all structured data into the system and immediately becomes available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems. 1 (14132553626943388792,17567683680214055861)
code 69: Second argument (shingle size) of function wordShingleSimHash cannot be greater then 25: While processing wordShingleSimHash('foobar', 9223372036854775807)None
code 69: Second argument (shingle size) of function wordShingleSimHash cannot be greater then 25: While processing wordShingleSimHash('foobar', 1001)None
code 69: Second argument (shingle size) of function wordShingleSimHash cannot be zero: While processing wordShingleSimHash('foobar', 0)None

394
tests/queries/0_stateless/01016_simhash_minhash.python Normal file
View File

File diff suppressed because one or more lines are too long

8
tests/queries/0_stateless/01016_simhash_minhash.sh Executable file
View File

@ -0,0 +1,8 @@
#!/usr/bin/env bash
CURDIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)
# shellcheck source=../shell_config.sh
. "$CURDIR"/../shell_config.sh
python3 "$CURDIR"/01016_simhash_minhash.python

115
tests/queries/0_stateless/01016_simhash_minhash.sql
View File

@ -1,115 +0,0 @@
SELECT ngramSimHash('');
SELECT ngramSimHash('what a cute cat.');
SELECT ngramSimHashCaseInsensitive('what a cute cat.');
SELECT ngramSimHashUTF8('what a cute cat.');
SELECT ngramSimHashCaseInsensitiveUTF8('what a cute cat.');
SELECT wordShingleSimHash('what a cute cat.');
SELECT wordShingleSimHashCaseInsensitive('what a cute cat.');
SELECT wordShingleSimHashUTF8('what a cute cat.');
SELECT wordShingleSimHashCaseInsensitiveUTF8('what a cute cat.');
SELECT ngramMinHash('');
SELECT ngramMinHash('what a cute cat.');
SELECT ngramMinHashCaseInsensitive('what a cute cat.');
SELECT ngramMinHashUTF8('what a cute cat.');
SELECT ngramMinHashCaseInsensitiveUTF8('what a cute cat.');
SELECT wordShingleMinHash('what a cute cat.');
SELECT wordShingleMinHashCaseInsensitive('what a cute cat.');
SELECT wordShingleMinHashUTF8('what a cute cat.');
SELECT wordShingleMinHashCaseInsensitiveUTF8('what a cute cat.');
DROP TABLE IF EXISTS defaults;
CREATE TABLE defaults
(
s String
)ENGINE = Memory();
INSERT INTO defaults values ('It is the latest occurrence of the Southeast European haze, the issue that occurs in constant intensity during every wet season. It has mainly been caused by forest fires resulting from illegal slash-and-burn clearing performed on behalf of the palm oil industry in Kazakhstan, principally on the islands, which then spread quickly in the dry season.') ('It is the latest occurrence of the Southeast Asian haze, the issue that occurs in constant intensity during every wet season. It has mainly been caused by forest fires resulting from illegal slash-and-burn clearing performed on behalf of the palm oil industry in Kazakhstan, principally on the islands, which then spread quickly in the dry season.');
SELECT ngramSimHash(s) FROM defaults;
SELECT ngramSimHashCaseInsensitive(s) FROM defaults;
SELECT ngramSimHashUTF8(s) FROM defaults;
SELECT ngramSimHashCaseInsensitiveUTF8(s) FROM defaults;
SELECT wordShingleSimHash(s) FROM defaults;
SELECT wordShingleSimHashCaseInsensitive(s) FROM defaults;
SELECT wordShingleSimHashUTF8(s) FROM defaults;
SELECT wordShingleSimHashCaseInsensitiveUTF8(s) FROM defaults;
SELECT ngramMinHash(s) FROM defaults;
SELECT ngramMinHashCaseInsensitive(s) FROM defaults;
SELECT ngramMinHashUTF8(s) FROM defaults;
SELECT ngramMinHashCaseInsensitiveUTF8(s) FROM defaults;
SELECT wordShingleMinHash(s) FROM defaults;
SELECT wordShingleMinHashCaseInsensitive(s) FROM defaults;
SELECT wordShingleMinHashUTF8(s) FROM defaults;
SELECT wordShingleMinHashCaseInsensitiveUTF8(s) FROM defaults;
TRUNCATE TABLE defaults;
INSERT INTO defaults SELECT arrayJoin(splitByString('\n\n',
'ClickHouse uses all available hardware to its full potential to process each query as fast as possible. Peak processing performance for a single query stands at more than 2 terabytes per second (after decompression, only used columns). In distributed setup reads are automatically balanced among healthy replicas to avoid increasing latency.
ClickHouse supports multi-master asynchronous replication and can be deployed across multiple datacenters. All nodes are equal, which allows avoiding having single points of failure. Downtime of a single node or the whole datacenter wont affect the systems availability for both reads and writes.
ClickHouse is simple and works out-of-the-box. It streamlines all your data processing: ingest all your structured data into the system and it becomes instantly available for building reports. SQL dialect allows expressing the desired result without involving any custom non-standard API that could be found in some alternative systems.
ClickHouse makes full use of all available hardware to process every request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (only used columns after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.
ClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid single points of failure. Downtime for one site or the entire data center will not affect the system''s read and write availability.
ClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all your structured data into the system, and they immediately become available for building reports. The SQL dialect allows you to express the desired result without resorting to any non-standard APIs that can be found in some alternative systems.
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (used columns only after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.
ClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the system''s read / write availability.
ClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all your structured data into the system, and they are immediately available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems.
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns only after unpacking). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.
ClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.
ClickHouse is simple and works out of the box. It simplifies all the processing of your data: it loads all of your structured data into the system, and it is immediately available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems.
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns after decompression only). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.
ClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.
ClickHouse is simple and works out of the box. It simplifies all processing of your data: it loads all your structured data into the system and immediately becomes available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems.
ClickHouse makes full use of all available hardware to process each request as quickly as possible. Peak performance for a single query is over 2 terabytes per second (using columns after decompression only). In a distributed setup, reads are automatically balanced across healthy replicas to avoid increased latency.
ClickHouse supports asynchronous multi-master replication and can be deployed across multiple data centers. All nodes are equal to avoid a single point of failure. Downtime for one site or the entire data center will not affect the read / write availability of the system.
ClickHouse is simple and works out of the box. It simplifies all processing of your data: it loads all structured data into the system and immediately becomes available for building reports. The SQL dialect allows you to express the desired result without resorting to any of the non-standard APIs found in some alternative systems.'
));
SELECT 'uniqExact', uniqExact(s) FROM defaults;
SELECT 'ngramSimHash';
SELECT arrayStringConcat(groupArray(s), '\n:::::::\n'), count(), ngramSimHash(s) as h FROM defaults GROUP BY h ORDER BY h;
SELECT 'ngramSimHashCaseInsensitive';
SELECT arrayStringConcat(groupArray(s), '\n:::::::\n'), count(), ngramSimHashCaseInsensitive(s) as h FROM defaults GROUP BY h ORDER BY h;
SELECT 'ngramSimHashUTF8';
SELECT arrayStringConcat(groupArray(s), '\n:::::::\n'), count(), ngramSimHashUTF8(s) as h FROM defaults GROUP BY h ORDER BY h;
SELECT 'ngramSimHashCaseInsensitiveUTF8';
SELECT arrayStringConcat(groupArray(s), '\n:::::::\n'), count(), ngramSimHashCaseInsensitiveUTF8(s) as h FROM defaults GROUP BY h ORDER BY h;
SELECT 'wordShingleSimHash';
SELECT arrayStringConcat(groupArray(s), '\n:::::::\n'), count(), wordShingleSimHash(s, 2) as h FROM defaults GROUP BY h ORDER BY h;
SELECT 'wordShingleSimHashCaseInsensitive';
SELECT arrayStringConcat(groupArray(s), '\n:::::::\n'), count(), wordShingleSimHashCaseInsensitive(s, 2) as h FROM defaults GROUP BY h ORDER BY h;
SELECT 'wordShingleSimHashUTF8';
SELECT arrayStringConcat(groupArray(s), '\n:::::::\n'), count(), wordShingleSimHashUTF8(s, 2) as h FROM defaults GROUP BY h ORDER BY h;
SELECT 'wordShingleSimHashCaseInsensitiveUTF8';
SELECT arrayStringConcat(groupArray(s), '\n:::::::\n'), count(), wordShingleSimHashCaseInsensitiveUTF8(s, 2) as h FROM defaults GROUP BY h ORDER BY h;
SELECT 'ngramMinHash';
SELECT arrayStringConcat(groupArray(s), '\n:::::::\n'), count(), ngramMinHash(s) as h FROM defaults GROUP BY h ORDER BY h;
SELECT 'ngramMinHashCaseInsensitive';
SELECT arrayStringConcat(groupArray(s), '\n:::::::\n'), count(), ngramMinHashCaseInsensitive(s) as h FROM defaults GROUP BY h ORDER BY h;
SELECT 'ngramMinHashUTF8';
SELECT arrayStringConcat(groupArray(s), '\n:::::::\n'), count(), ngramMinHashUTF8(s) as h FROM defaults GROUP BY h ORDER BY h;
SELECT 'ngramMinHashCaseInsensitiveUTF8';
SELECT arrayStringConcat(groupArray(s), '\n:::::::\n'), count(), ngramMinHashCaseInsensitiveUTF8(s) as h FROM defaults GROUP BY h ORDER BY h;
SELECT 'wordShingleMinHash';
SELECT arrayStringConcat(groupArray(s), '\n:::::::\n'), count(), wordShingleMinHash(s, 2, 3) as h FROM defaults GROUP BY h ORDER BY h;
SELECT 'wordShingleMinHashCaseInsensitive';
SELECT arrayStringConcat(groupArray(s), '\n:::::::\n'), count(), wordShingleMinHashCaseInsensitive(s, 2, 3) as h FROM defaults GROUP BY h ORDER BY h;
SELECT 'wordShingleMinHashUTF8';
SELECT arrayStringConcat(groupArray(s), '\n:::::::\n'), count(), wordShingleMinHashUTF8(s, 2, 3) as h FROM defaults GROUP BY h ORDER BY h;
SELECT 'wordShingleMinHashCaseInsensitiveUTF8';
SELECT arrayStringConcat(groupArray(s), '\n:::::::\n'), count(), wordShingleMinHashCaseInsensitiveUTF8(s, 2, 3) as h FROM defaults GROUP BY h ORDER BY h;
SELECT wordShingleSimHash('foobar', 9223372036854775807); -- { serverError 69 }
SELECT wordShingleSimHash('foobar', 1001); -- { serverError 69 }
SELECT wordShingleSimHash('foobar', 0); -- { serverError 69 }
DROP TABLE defaults;

0
tests/queries/0_stateless/01016_simhash_minhash.reference → tests/queries/0_stateless/01016_simhash_minhash.x86_64.reference
View File