From 3711430d9f97401d80dff14eaab68008bb03132c Mon Sep 17 00:00:00 2001
From: Vitaly Baranov <vitlibar@clickhouse.com>
Date: Thu, 15 Jun 2023 16:14:56 +0200
Subject: [PATCH 01/24] Rename member fields of CityHash_v1_0_2::uint128:
 "first" -> "low64", "second" -> "high64".

---
 base/base/wide_integer_impl.h                 | 16 ++++++++++++++++
 contrib/cityhash102/include/city.h            | 19 ++++++++++++++++---
 src/Compression/CompressedReadBufferBase.cpp  | 16 ++++++++--------
 src/Compression/CompressedWriteBuffer.cpp     |  8 ++++----
 .../DistributedAsyncInsertHeader.cpp          |  4 ++--
 .../MergeTree/DataPartStorageOnDiskBase.cpp   |  2 +-
 .../MergeTree/MergeTreeDataPartChecksum.cpp   |  8 ++++----
 .../PartMetadataManagerWithCache.cpp          |  8 ++++----
 src/Storages/System/StorageSystemParts.cpp    |  6 +++---
 .../System/StorageSystemProjectionParts.cpp   |  6 +++---
 10 files changed, 61 insertions(+), 32 deletions(-)

diff --git a/base/base/wide_integer_impl.h b/base/base/wide_integer_impl.h
index 4a80c176829..dc6a49694ae 100644
--- a/base/base/wide_integer_impl.h
+++ b/base/base/wide_integer_impl.h
@@ -15,6 +15,8 @@
 #include <boost/multiprecision/cpp_bin_float.hpp>
 #include <boost/math/special_functions/fpclassify.hpp>
 
+#include <city.h>
+
 // NOLINTBEGIN(*)
 
 /// Use same extended double for all platforms
@@ -281,6 +283,14 @@ struct integer<Bits, Signed>::_impl
         }
     }
 
+    constexpr static void wide_integer_from_cityhash_uint128(integer<Bits, Signed> & self, const CityHash_v1_0_2::uint128 & value) noexcept
+    {
+        if constexpr (std::endian::native == std::endian::little)
+            wide_integer_from_tuple_like(self, std::make_pair(value.low64, value.high64));
+        else
+            wide_integer_from_tuple_like(self, std::make_pair(value.high64, value.low64));
+    }
+
     /**
      * N.B. t is constructed from double, so max(t) = max(double) ~ 2^310
      * the recursive call happens when t / 2^64 > 2^64, so there won't be more than 5 of them.
@@ -1036,6 +1046,8 @@ constexpr integer<Bits, Signed>::integer(T rhs) noexcept
         _impl::wide_integer_from_wide_integer(*this, rhs);
     else if  constexpr (IsTupleLike<T>::value)
         _impl::wide_integer_from_tuple_like(*this, rhs);
+    else if constexpr (std::is_same_v<std::remove_cvref_t<T>, CityHash_v1_0_2::uint128>)
+        _impl::wide_integer_from_cityhash_uint128(*this, rhs);
     else
         _impl::wide_integer_from_builtin(*this, rhs);
 }
@@ -1051,6 +1063,8 @@ constexpr integer<Bits, Signed>::integer(std::initializer_list<T> il) noexcept
             _impl::wide_integer_from_wide_integer(*this, *il.begin());
         else if  constexpr (IsTupleLike<T>::value)
             _impl::wide_integer_from_tuple_like(*this, *il.begin());
+        else if constexpr (std::is_same_v<std::remove_cvref_t<T>, CityHash_v1_0_2::uint128>)
+            _impl::wide_integer_from_cityhash_uint128(*this, *il.begin());
         else
             _impl::wide_integer_from_builtin(*this, *il.begin());
     }
@@ -1088,6 +1102,8 @@ constexpr integer<Bits, Signed> & integer<Bits, Signed>::operator=(T rhs) noexce
 {
     if  constexpr (IsTupleLike<T>::value)
         _impl::wide_integer_from_tuple_like(*this, rhs);
+    else if constexpr (std::is_same_v<std::remove_cvref_t<T>, CityHash_v1_0_2::uint128>)
+        _impl::wide_integer_from_cityhash_uint128(*this, rhs);
     else
         _impl::wide_integer_from_builtin(*this, rhs);
     return *this;
diff --git a/contrib/cityhash102/include/city.h b/contrib/cityhash102/include/city.h
index 77d4c988cdd..87363d16444 100644
--- a/contrib/cityhash102/include/city.h
+++ b/contrib/cityhash102/include/city.h
@@ -61,11 +61,24 @@ namespace CityHash_v1_0_2
 typedef uint8_t uint8;
 typedef uint32_t uint32;
 typedef uint64_t uint64;
-typedef std::pair<uint64, uint64> uint128;
 
+/// Represent an unsigned integer of 128 bits as it's used in CityHash.
+/// Originally CityHash used `std::pair<uint64, uint64>` instead of this struct,
+/// however the members `first` and `second` could be easily confused so they were renamed to `low64` and `high64`:
+/// `first` -> `low64`, `second` -> `high64`.
+struct uint128
+{
+    uint64 low64 = 0;
+    uint64 high64 = 0;
 
-inline uint64 Uint128Low64(const uint128& x) { return x.first; }
-inline uint64 Uint128High64(const uint128& x) { return x.second; }
+    uint128() = default;
+    uint128(uint64 low64_, uint64 high64_) : low64(low64_), high64(high64_) {}
+    friend bool operator ==(const uint128 & x, const uint128 & y) { return (x.low64 == y.low64) && (x.high64 == y.high64); }
+    friend bool operator !=(const uint128 & x, const uint128 & y) { return !(x == y); }
+};
+
+inline uint64 Uint128Low64(const uint128 & x) { return x.low64; }
+inline uint64 Uint128High64(const uint128 & x) { return x.high64; }
 
 // Hash function for a byte array.
 uint64 CityHash64(const char *buf, size_t len);
diff --git a/src/Compression/CompressedReadBufferBase.cpp b/src/Compression/CompressedReadBufferBase.cpp
index 278210d770a..662cd6bf337 100644
--- a/src/Compression/CompressedReadBufferBase.cpp
+++ b/src/Compression/CompressedReadBufferBase.cpp
@@ -49,8 +49,8 @@ static void validateChecksum(char * data, size_t size, const Checksum expected_c
 
     /// TODO mess up of endianness in error message.
     message << "Checksum doesn't match: corrupted data."
-        " Reference: " + getHexUIntLowercase(expected_checksum.first) + getHexUIntLowercase(expected_checksum.second)
-        + ". Actual: " + getHexUIntLowercase(calculated_checksum.first) + getHexUIntLowercase(calculated_checksum.second)
+        " Reference: " + getHexUIntLowercase(expected_checksum.low64) + getHexUIntLowercase(expected_checksum.high64)
+        + ". Actual: " + getHexUIntLowercase(calculated_checksum.low64) + getHexUIntLowercase(calculated_checksum.high64)
         + ". Size of compressed block: " + toString(size);
 
     const char * message_hardware_failure = "This is most likely due to hardware failure. "
@@ -95,8 +95,8 @@ static void validateChecksum(char * data, size_t size, const Checksum expected_c
     }
 
     /// Check if the difference caused by single bit flip in stored checksum.
-    size_t difference = std::popcount(expected_checksum.first ^ calculated_checksum.first)
-        + std::popcount(expected_checksum.second ^ calculated_checksum.second);
+    size_t difference = std::popcount(expected_checksum.low64 ^ calculated_checksum.low64)
+        + std::popcount(expected_checksum.high64 ^ calculated_checksum.high64);
 
     if (difference == 1)
     {
@@ -194,8 +194,8 @@ size_t CompressedReadBufferBase::readCompressedData(size_t & size_decompressed,
     {
         Checksum checksum;
         ReadBufferFromMemory checksum_in(own_compressed_buffer.data(), sizeof(checksum));
-        readBinaryLittleEndian(checksum.first, checksum_in);
-        readBinaryLittleEndian(checksum.second, checksum_in);
+        readBinaryLittleEndian(checksum.low64, checksum_in);
+        readBinaryLittleEndian(checksum.high64, checksum_in);
 
         validateChecksum(compressed_buffer, size_compressed_without_checksum, checksum);
     }
@@ -238,8 +238,8 @@ size_t CompressedReadBufferBase::readCompressedDataBlockForAsynchronous(size_t &
         {
             Checksum checksum;
             ReadBufferFromMemory checksum_in(own_compressed_buffer.data(), sizeof(checksum));
-            readBinaryLittleEndian(checksum.first, checksum_in);
-            readBinaryLittleEndian(checksum.second, checksum_in);
+            readBinaryLittleEndian(checksum.low64, checksum_in);
+            readBinaryLittleEndian(checksum.high64, checksum_in);
 
             validateChecksum(compressed_buffer, size_compressed_without_checksum, checksum);
         }
diff --git a/src/Compression/CompressedWriteBuffer.cpp b/src/Compression/CompressedWriteBuffer.cpp
index cb2ee1140d0..f16330332ab 100644
--- a/src/Compression/CompressedWriteBuffer.cpp
+++ b/src/Compression/CompressedWriteBuffer.cpp
@@ -38,8 +38,8 @@ void CompressedWriteBuffer::nextImpl()
 
         CityHash_v1_0_2::uint128 checksum = CityHash_v1_0_2::CityHash128(out_compressed_ptr, compressed_size);
 
-        writeBinaryLittleEndian(checksum.first, out);
-        writeBinaryLittleEndian(checksum.second, out);
+        writeBinaryLittleEndian(checksum.low64, out);
+        writeBinaryLittleEndian(checksum.high64, out);
 
         out.position() += compressed_size;
     }
@@ -50,8 +50,8 @@ void CompressedWriteBuffer::nextImpl()
 
         CityHash_v1_0_2::uint128 checksum = CityHash_v1_0_2::CityHash128(compressed_buffer.data(), compressed_size);
 
-        writeBinaryLittleEndian(checksum.first, out);
-        writeBinaryLittleEndian(checksum.second, out);
+        writeBinaryLittleEndian(checksum.low64, out);
+        writeBinaryLittleEndian(checksum.high64, out);
 
         out.write(compressed_buffer.data(), compressed_size);
     }
diff --git a/src/Storages/Distributed/DistributedAsyncInsertHeader.cpp b/src/Storages/Distributed/DistributedAsyncInsertHeader.cpp
index 018c1d863bb..d815f671652 100644
--- a/src/Storages/Distributed/DistributedAsyncInsertHeader.cpp
+++ b/src/Storages/Distributed/DistributedAsyncInsertHeader.cpp
@@ -40,8 +40,8 @@ DistributedAsyncInsertHeader DistributedAsyncInsertHeader::read(ReadBufferFromFi
         {
             throw Exception(ErrorCodes::CHECKSUM_DOESNT_MATCH,
                             "Checksum of extra info doesn't match: corrupted data. Reference: {}{}. Actual: {}{}.",
-                            getHexUIntLowercase(expected_checksum.first), getHexUIntLowercase(expected_checksum.second),
-                            getHexUIntLowercase(calculated_checksum.first), getHexUIntLowercase(calculated_checksum.second));
+                            getHexUIntLowercase(expected_checksum.low64), getHexUIntLowercase(expected_checksum.high64),
+                            getHexUIntLowercase(calculated_checksum.low64), getHexUIntLowercase(calculated_checksum.high64));
         }
 
         /// Read the parts of the header.
diff --git a/src/Storages/MergeTree/DataPartStorageOnDiskBase.cpp b/src/Storages/MergeTree/DataPartStorageOnDiskBase.cpp
index 30776a8bc50..92e9005751e 100644
--- a/src/Storages/MergeTree/DataPartStorageOnDiskBase.cpp
+++ b/src/Storages/MergeTree/DataPartStorageOnDiskBase.cpp
@@ -400,7 +400,7 @@ void DataPartStorageOnDiskBase::backup(
         if (it != checksums.files.end())
         {
             file_size = it->second.file_size;
-            file_hash = {it->second.file_hash.first, it->second.file_hash.second};
+            file_hash = it->second.file_hash;
         }
 
         BackupEntryPtr backup_entry = std::make_unique<BackupEntryFromImmutableFile>(disk, filepath_on_disk, copy_encrypted, file_size, file_hash);
diff --git a/src/Storages/MergeTree/MergeTreeDataPartChecksum.cpp b/src/Storages/MergeTree/MergeTreeDataPartChecksum.cpp
index 78f68ea72fe..58ba7acb9ba 100644
--- a/src/Storages/MergeTree/MergeTreeDataPartChecksum.cpp
+++ b/src/Storages/MergeTree/MergeTreeDataPartChecksum.cpp
@@ -154,9 +154,9 @@ bool MergeTreeDataPartChecksums::readV2(ReadBuffer & in)
         assertString("\n\tsize: ", in);
         readText(sum.file_size, in);
         assertString("\n\thash: ", in);
-        readText(sum.file_hash.first, in);
+        readText(sum.file_hash.low64, in);
         assertString(" ", in);
-        readText(sum.file_hash.second, in);
+        readText(sum.file_hash.high64, in);
         assertString("\n\tcompressed: ", in);
         readText(sum.is_compressed, in);
         if (sum.is_compressed)
@@ -164,9 +164,9 @@ bool MergeTreeDataPartChecksums::readV2(ReadBuffer & in)
             assertString("\n\tuncompressed size: ", in);
             readText(sum.uncompressed_size, in);
             assertString("\n\tuncompressed hash: ", in);
-            readText(sum.uncompressed_hash.first, in);
+            readText(sum.uncompressed_hash.low64, in);
             assertString(" ", in);
-            readText(sum.uncompressed_hash.second, in);
+            readText(sum.uncompressed_hash.high64, in);
         }
         assertChar('\n', in);
 
diff --git a/src/Storages/MergeTree/PartMetadataManagerWithCache.cpp b/src/Storages/MergeTree/PartMetadataManagerWithCache.cpp
index 7c0aedf699b..7deae69750f 100644
--- a/src/Storages/MergeTree/PartMetadataManagerWithCache.cpp
+++ b/src/Storages/MergeTree/PartMetadataManagerWithCache.cpp
@@ -250,8 +250,8 @@ std::unordered_map<String, IPartMetadataManager::uint128> PartMetadataManagerWit
                     ErrorCodes::CORRUPTED_DATA,
                     "Checksums doesn't match in part {} for {}. Expected: {}. Found {}.",
                     part->name, file_path,
-                    getHexUIntUppercase(disk_checksum.first) + getHexUIntUppercase(disk_checksum.second),
-                    getHexUIntUppercase(cache_checksums[i].first) + getHexUIntUppercase(cache_checksums[i].second));
+                    getHexUIntUppercase(disk_checksum.low64) + getHexUIntUppercase(disk_checksum.high64),
+                    getHexUIntUppercase(cache_checksums[i].low64) + getHexUIntUppercase(cache_checksums[i].high64));
 
             disk_checksums.push_back(disk_checksum);
             continue;
@@ -287,8 +287,8 @@ std::unordered_map<String, IPartMetadataManager::uint128> PartMetadataManagerWit
                 ErrorCodes::CORRUPTED_DATA,
                 "Checksums doesn't match in projection part {} {}. Expected: {}. Found {}.",
                 part->name, proj_name,
-                getHexUIntUppercase(disk_checksum.first) + getHexUIntUppercase(disk_checksum.second),
-                getHexUIntUppercase(cache_checksums[i].first) + getHexUIntUppercase(cache_checksums[i].second));
+                getHexUIntUppercase(disk_checksum.low64) + getHexUIntUppercase(disk_checksum.high64),
+                getHexUIntUppercase(cache_checksums[i].low64) + getHexUIntUppercase(cache_checksums[i].high64));
         disk_checksums.push_back(disk_checksum);
     }
     return results;
diff --git a/src/Storages/System/StorageSystemParts.cpp b/src/Storages/System/StorageSystemParts.cpp
index 86ecb336b51..95bad0a20fe 100644
--- a/src/Storages/System/StorageSystemParts.cpp
+++ b/src/Storages/System/StorageSystemParts.cpp
@@ -252,17 +252,17 @@ void StorageSystemParts::processNextStorage(
             if (columns_mask[src_index++])
             {
                 auto checksum = helper.hash_of_all_files;
-                columns[res_index++]->insert(getHexUIntLowercase(checksum.first) + getHexUIntLowercase(checksum.second));
+                columns[res_index++]->insert(getHexUIntLowercase(checksum.low64) + getHexUIntLowercase(checksum.high64));
             }
             if (columns_mask[src_index++])
             {
                 auto checksum = helper.hash_of_uncompressed_files;
-                columns[res_index++]->insert(getHexUIntLowercase(checksum.first) + getHexUIntLowercase(checksum.second));
+                columns[res_index++]->insert(getHexUIntLowercase(checksum.low64) + getHexUIntLowercase(checksum.high64));
             }
             if (columns_mask[src_index++])
             {
                 auto checksum = helper.uncompressed_hash_of_compressed_files;
-                columns[res_index++]->insert(getHexUIntLowercase(checksum.first) + getHexUIntLowercase(checksum.second));
+                columns[res_index++]->insert(getHexUIntLowercase(checksum.low64) + getHexUIntLowercase(checksum.high64));
             }
         }
 
diff --git a/src/Storages/System/StorageSystemProjectionParts.cpp b/src/Storages/System/StorageSystemProjectionParts.cpp
index d2c6c3ef287..6508d062d37 100644
--- a/src/Storages/System/StorageSystemProjectionParts.cpp
+++ b/src/Storages/System/StorageSystemProjectionParts.cpp
@@ -221,17 +221,17 @@ void StorageSystemProjectionParts::processNextStorage(
             if (columns_mask[src_index++])
             {
                 auto checksum = helper.hash_of_all_files;
-                columns[res_index++]->insert(getHexUIntLowercase(checksum.first) + getHexUIntLowercase(checksum.second));
+                columns[res_index++]->insert(getHexUIntLowercase(checksum.low64) + getHexUIntLowercase(checksum.high64));
             }
             if (columns_mask[src_index++])
             {
                 auto checksum = helper.hash_of_uncompressed_files;
-                columns[res_index++]->insert(getHexUIntLowercase(checksum.first) + getHexUIntLowercase(checksum.second));
+                columns[res_index++]->insert(getHexUIntLowercase(checksum.low64) + getHexUIntLowercase(checksum.high64));
             }
             if (columns_mask[src_index++])
             {
                 auto checksum = helper.uncompressed_hash_of_compressed_files;
-                columns[res_index++]->insert(getHexUIntLowercase(checksum.first) + getHexUIntLowercase(checksum.second));
+                columns[res_index++]->insert(getHexUIntLowercase(checksum.low64) + getHexUIntLowercase(checksum.high64));
             }
         }
 

From f1f0daa654755b2d12ec9548262adfe4e87fe9b6 Mon Sep 17 00:00:00 2001
From: Vitaly Baranov <vitlibar@clickhouse.com>
Date: Thu, 15 Jun 2023 17:59:37 +0200
Subject: [PATCH 02/24] Show halves of checksums in "system.parts",
 "system.projection_parts" and error messages in the correct order.

---
 src/Compression/CompressedReadBufferBase.cpp              | 4 ++--
 src/Storages/Distributed/DistributedAsyncInsertHeader.cpp | 4 ++--
 src/Storages/MergeTree/PartMetadataManagerWithCache.cpp   | 8 ++++----
 src/Storages/System/StorageSystemParts.cpp                | 6 +++---
 src/Storages/System/StorageSystemProjectionParts.cpp      | 6 +++---
 utils/checksum-for-compressed-block/main.cpp              | 2 +-
 6 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/src/Compression/CompressedReadBufferBase.cpp b/src/Compression/CompressedReadBufferBase.cpp
index 662cd6bf337..bae52c8bece 100644
--- a/src/Compression/CompressedReadBufferBase.cpp
+++ b/src/Compression/CompressedReadBufferBase.cpp
@@ -49,8 +49,8 @@ static void validateChecksum(char * data, size_t size, const Checksum expected_c
 
     /// TODO mess up of endianness in error message.
     message << "Checksum doesn't match: corrupted data."
-        " Reference: " + getHexUIntLowercase(expected_checksum.low64) + getHexUIntLowercase(expected_checksum.high64)
-        + ". Actual: " + getHexUIntLowercase(calculated_checksum.low64) + getHexUIntLowercase(calculated_checksum.high64)
+        " Reference: " + getHexUIntLowercase(expected_checksum.high64) + getHexUIntLowercase(expected_checksum.low64)
+        + ". Actual: " + getHexUIntLowercase(calculated_checksum.high64) + getHexUIntLowercase(calculated_checksum.low64)
         + ". Size of compressed block: " + toString(size);
 
     const char * message_hardware_failure = "This is most likely due to hardware failure. "
diff --git a/src/Storages/Distributed/DistributedAsyncInsertHeader.cpp b/src/Storages/Distributed/DistributedAsyncInsertHeader.cpp
index d815f671652..e1b54304f23 100644
--- a/src/Storages/Distributed/DistributedAsyncInsertHeader.cpp
+++ b/src/Storages/Distributed/DistributedAsyncInsertHeader.cpp
@@ -40,8 +40,8 @@ DistributedAsyncInsertHeader DistributedAsyncInsertHeader::read(ReadBufferFromFi
         {
             throw Exception(ErrorCodes::CHECKSUM_DOESNT_MATCH,
                             "Checksum of extra info doesn't match: corrupted data. Reference: {}{}. Actual: {}{}.",
-                            getHexUIntLowercase(expected_checksum.low64), getHexUIntLowercase(expected_checksum.high64),
-                            getHexUIntLowercase(calculated_checksum.low64), getHexUIntLowercase(calculated_checksum.high64));
+                            getHexUIntLowercase(expected_checksum.high64), getHexUIntLowercase(expected_checksum.low64),
+                            getHexUIntLowercase(calculated_checksum.high64), getHexUIntLowercase(calculated_checksum.low64));
         }
 
         /// Read the parts of the header.
diff --git a/src/Storages/MergeTree/PartMetadataManagerWithCache.cpp b/src/Storages/MergeTree/PartMetadataManagerWithCache.cpp
index 7deae69750f..324bd4bbaee 100644
--- a/src/Storages/MergeTree/PartMetadataManagerWithCache.cpp
+++ b/src/Storages/MergeTree/PartMetadataManagerWithCache.cpp
@@ -250,8 +250,8 @@ std::unordered_map<String, IPartMetadataManager::uint128> PartMetadataManagerWit
                     ErrorCodes::CORRUPTED_DATA,
                     "Checksums doesn't match in part {} for {}. Expected: {}. Found {}.",
                     part->name, file_path,
-                    getHexUIntUppercase(disk_checksum.low64) + getHexUIntUppercase(disk_checksum.high64),
-                    getHexUIntUppercase(cache_checksums[i].low64) + getHexUIntUppercase(cache_checksums[i].high64));
+                    getHexUIntUppercase(disk_checksum.high64) + getHexUIntUppercase(disk_checksum.low64),
+                    getHexUIntUppercase(cache_checksums[i].high64) + getHexUIntUppercase(cache_checksums[i].low64));
 
             disk_checksums.push_back(disk_checksum);
             continue;
@@ -287,8 +287,8 @@ std::unordered_map<String, IPartMetadataManager::uint128> PartMetadataManagerWit
                 ErrorCodes::CORRUPTED_DATA,
                 "Checksums doesn't match in projection part {} {}. Expected: {}. Found {}.",
                 part->name, proj_name,
-                getHexUIntUppercase(disk_checksum.low64) + getHexUIntUppercase(disk_checksum.high64),
-                getHexUIntUppercase(cache_checksums[i].low64) + getHexUIntUppercase(cache_checksums[i].high64));
+                getHexUIntUppercase(disk_checksum.high64) + getHexUIntUppercase(disk_checksum.low64),
+                getHexUIntUppercase(cache_checksums[i].high64) + getHexUIntUppercase(cache_checksums[i].low64));
         disk_checksums.push_back(disk_checksum);
     }
     return results;
diff --git a/src/Storages/System/StorageSystemParts.cpp b/src/Storages/System/StorageSystemParts.cpp
index 95bad0a20fe..b642f4b5088 100644
--- a/src/Storages/System/StorageSystemParts.cpp
+++ b/src/Storages/System/StorageSystemParts.cpp
@@ -252,17 +252,17 @@ void StorageSystemParts::processNextStorage(
             if (columns_mask[src_index++])
             {
                 auto checksum = helper.hash_of_all_files;
-                columns[res_index++]->insert(getHexUIntLowercase(checksum.low64) + getHexUIntLowercase(checksum.high64));
+                columns[res_index++]->insert(getHexUIntLowercase(checksum.high64) + getHexUIntLowercase(checksum.low64));
             }
             if (columns_mask[src_index++])
             {
                 auto checksum = helper.hash_of_uncompressed_files;
-                columns[res_index++]->insert(getHexUIntLowercase(checksum.low64) + getHexUIntLowercase(checksum.high64));
+                columns[res_index++]->insert(getHexUIntLowercase(checksum.high64) + getHexUIntLowercase(checksum.low64));
             }
             if (columns_mask[src_index++])
             {
                 auto checksum = helper.uncompressed_hash_of_compressed_files;
-                columns[res_index++]->insert(getHexUIntLowercase(checksum.low64) + getHexUIntLowercase(checksum.high64));
+                columns[res_index++]->insert(getHexUIntLowercase(checksum.high64) + getHexUIntLowercase(checksum.low64));
             }
         }
 
diff --git a/src/Storages/System/StorageSystemProjectionParts.cpp b/src/Storages/System/StorageSystemProjectionParts.cpp
index 6508d062d37..05c83747c4d 100644
--- a/src/Storages/System/StorageSystemProjectionParts.cpp
+++ b/src/Storages/System/StorageSystemProjectionParts.cpp
@@ -221,17 +221,17 @@ void StorageSystemProjectionParts::processNextStorage(
             if (columns_mask[src_index++])
             {
                 auto checksum = helper.hash_of_all_files;
-                columns[res_index++]->insert(getHexUIntLowercase(checksum.low64) + getHexUIntLowercase(checksum.high64));
+                columns[res_index++]->insert(getHexUIntLowercase(checksum.high64) + getHexUIntLowercase(checksum.low64));
             }
             if (columns_mask[src_index++])
             {
                 auto checksum = helper.hash_of_uncompressed_files;
-                columns[res_index++]->insert(getHexUIntLowercase(checksum.low64) + getHexUIntLowercase(checksum.high64));
+                columns[res_index++]->insert(getHexUIntLowercase(checksum.high64) + getHexUIntLowercase(checksum.low64));
             }
             if (columns_mask[src_index++])
             {
                 auto checksum = helper.uncompressed_hash_of_compressed_files;
-                columns[res_index++]->insert(getHexUIntLowercase(checksum.low64) + getHexUIntLowercase(checksum.high64));
+                columns[res_index++]->insert(getHexUIntLowercase(checksum.high64) + getHexUIntLowercase(checksum.low64));
             }
         }
 
diff --git a/utils/checksum-for-compressed-block/main.cpp b/utils/checksum-for-compressed-block/main.cpp
index 4f9923e7638..d30a3798820 100644
--- a/utils/checksum-for-compressed-block/main.cpp
+++ b/utils/checksum-for-compressed-block/main.cpp
@@ -45,7 +45,7 @@ int main(int, char **)
     {
         auto flipped = flipBit(str, pos);
         auto checksum = CityHash_v1_0_2::CityHash128(flipped.data(), flipped.size());
-        std::cout << getHexUIntLowercase(checksum.first) << getHexUIntLowercase(checksum.second) << "\t" << pos / 8 << ", " << pos % 8 << "\n";
+        std::cout << getHexUIntLowercase(checksum.high64) << getHexUIntLowercase(checksum.low64) << "\t" << pos / 8 << ", " << pos % 8 << "\n";
     }
 
     return 0;

From 5eeda0a0d24ae14a78da79273870aec9fa6bd8a0 Mon Sep 17 00:00:00 2001
From: Vitaly Baranov <vitlibar@clickhouse.com>
Date: Sat, 24 Jun 2023 22:17:53 +0200
Subject: [PATCH 03/24] Fix test 00961_checksums_in_system_parts_columns_table

---
 .../00961_checksums_in_system_parts_columns_table.reference     | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/queries/0_stateless/00961_checksums_in_system_parts_columns_table.reference b/tests/queries/0_stateless/00961_checksums_in_system_parts_columns_table.reference
index 186f2feab79..4bf3cfe65a2 100644
--- a/tests/queries/0_stateless/00961_checksums_in_system_parts_columns_table.reference
+++ b/tests/queries/0_stateless/00961_checksums_in_system_parts_columns_table.reference
@@ -1 +1 @@
-20000101_1_1_0	test_00961	b5fce9c4ef1ca42ce4ed027389c208d2	fc3b062b646cd23d4c23d7f5920f89ae	da96ff1e527a8a1f908ddf2b1d0af239
+20000101_1_1_0	test_00961	e4ed027389c208d2b5fce9c4ef1ca42c	4c23d7f5920f89aefc3b062b646cd23d	908ddf2b1d0af239da96ff1e527a8a1f

From 71cded08ff2813f4c4757e71a773ca8cc0a293bf Mon Sep 17 00:00:00 2001
From: Vitaly Baranov <vitlibar@clickhouse.com>
Date: Sun, 25 Jun 2023 14:51:29 +0200
Subject: [PATCH 04/24] Remove unnecessary include <city.h> from
 wide_integer_impl.h

---
 base/base/wide_integer_impl.h | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/base/base/wide_integer_impl.h b/base/base/wide_integer_impl.h
index dc6a49694ae..411841e6d9f 100644
--- a/base/base/wide_integer_impl.h
+++ b/base/base/wide_integer_impl.h
@@ -15,8 +15,6 @@
 #include <boost/multiprecision/cpp_bin_float.hpp>
 #include <boost/math/special_functions/fpclassify.hpp>
 
-#include <city.h>
-
 // NOLINTBEGIN(*)
 
 /// Use same extended double for all platforms
@@ -29,6 +27,8 @@ using FromDoubleIntermediateType = long double;
 using FromDoubleIntermediateType = boost::multiprecision::cpp_bin_float_double_extended;
 #endif
 
+namespace CityHash_v1_0_2 { struct uint128; }
+
 namespace wide
 {
 
@@ -283,8 +283,11 @@ struct integer<Bits, Signed>::_impl
         }
     }
 
-    constexpr static void wide_integer_from_cityhash_uint128(integer<Bits, Signed> & self, const CityHash_v1_0_2::uint128 & value) noexcept
+    template <typename CityHashUInt128 = CityHash_v1_0_2::uint128>
+    constexpr static void wide_integer_from_cityhash_uint128(integer<Bits, Signed> & self, const CityHashUInt128 & value) noexcept
     {
+        static_assert(sizeof(item_count) >= 2);
+
         if constexpr (std::endian::native == std::endian::little)
             wide_integer_from_tuple_like(self, std::make_pair(value.low64, value.high64));
         else

From 1f60a6ed4e1040623f7482a64a2ae493996be3e7 Mon Sep 17 00:00:00 2001
From: kssenii <sumarokovakseniia@mail.ru>
Date: Mon, 26 Jun 2023 12:34:11 +0200
Subject: [PATCH 05/24] Fix

---
 src/Disks/IO/CachedOnDiskReadBufferFromFile.cpp | 5 +----
 src/Interpreters/Cache/FileSegment.cpp          | 2 +-
 src/Interpreters/Cache/FileSegment.h            | 2 --
 3 files changed, 2 insertions(+), 7 deletions(-)

diff --git a/src/Disks/IO/CachedOnDiskReadBufferFromFile.cpp b/src/Disks/IO/CachedOnDiskReadBufferFromFile.cpp
index 76d54f9d27c..960d2a72410 100644
--- a/src/Disks/IO/CachedOnDiskReadBufferFromFile.cpp
+++ b/src/Disks/IO/CachedOnDiskReadBufferFromFile.cpp
@@ -510,9 +510,6 @@ bool CachedOnDiskReadBufferFromFile::completeFileSegmentAndGetNext()
     current_file_segment->use();
     implementation_buffer = getImplementationBuffer(*current_file_segment);
 
-    if (read_type == ReadType::CACHED)
-        current_file_segment->incrementHitsCount();
-
     LOG_TEST(
         log, "New segment range: {}, old range: {}",
         current_file_segment->range().toString(), completed_range.toString());
@@ -857,7 +854,7 @@ bool CachedOnDiskReadBufferFromFile::nextImplStep()
         implementation_buffer = getImplementationBuffer(file_segments->front());
 
         if (read_type == ReadType::CACHED)
-            file_segments->front().incrementHitsCount();
+            file_segments->front().use();
     }
 
     chassert(!internal_buffer.empty());
diff --git a/src/Interpreters/Cache/FileSegment.cpp b/src/Interpreters/Cache/FileSegment.cpp
index 95592fc7c12..a77f0726d74 100644
--- a/src/Interpreters/Cache/FileSegment.cpp
+++ b/src/Interpreters/Cache/FileSegment.cpp
@@ -898,7 +898,7 @@ void FileSegment::use()
     if (it)
     {
         auto cache_lock = cache->lockCache();
-        it->use(cache_lock);
+        hits_count = it->use(cache_lock);
     }
 }
 
diff --git a/src/Interpreters/Cache/FileSegment.h b/src/Interpreters/Cache/FileSegment.h
index 681c0d719e4..2e6bbe5657e 100644
--- a/src/Interpreters/Cache/FileSegment.h
+++ b/src/Interpreters/Cache/FileSegment.h
@@ -180,8 +180,6 @@ public:
 
     size_t getRefCount() const { return ref_count; }
 
-    void incrementHitsCount() { ++hits_count; }
-
     size_t getCurrentWriteOffset(bool sync) const;
 
     size_t getFirstNonDownloadedOffset(bool sync) const;

From 7d8d19d8003ebaaac910a6af802ee4874e1821f8 Mon Sep 17 00:00:00 2001
From: kssenii <sumarokovakseniia@mail.ru>
Date: Mon, 26 Jun 2023 14:27:13 +0200
Subject: [PATCH 06/24] Add test

---
 .../tests/gtest_lru_file_cache.cpp            | 77 +++++++++++++++++++
 1 file changed, 77 insertions(+)

diff --git a/src/Interpreters/tests/gtest_lru_file_cache.cpp b/src/Interpreters/tests/gtest_lru_file_cache.cpp
index 3cba1e48e1e..9ff9f92afe4 100644
--- a/src/Interpreters/tests/gtest_lru_file_cache.cpp
+++ b/src/Interpreters/tests/gtest_lru_file_cache.cpp
@@ -22,6 +22,8 @@
 
 #include <Poco/ConsoleChannel.h>
 #include <Disks/IO/CachedOnDiskWriteBufferFromFile.h>
+#include <Disks/IO/CachedOnDiskReadBufferFromFile.h>
+#include <Disks/IO/createReadBufferFromFileBase.h>
 #include <Interpreters/Cache/WriteBufferToFileSegment.h>
 
 namespace fs = std::filesystem;
@@ -862,3 +864,78 @@ TEST_F(FileCacheTest, temporaryData)
     ASSERT_LE(file_cache.getUsedCacheSize(), size_used_before_temporary_data);
     ASSERT_LE(file_cache.getFileSegmentsNum(), segments_used_before_temporary_data);
 }
+
+TEST_F(FileCacheTest, CachedReadBuffer)
+{
+    DB::ThreadStatus thread_status;
+
+    /// To work with cache need query_id and query context.
+    std::string query_id = "query_id";
+
+    Poco::XML::DOMParser dom_parser;
+    std::string xml(R"CONFIG(<clickhouse>
+</clickhouse>)CONFIG");
+    Poco::AutoPtr<Poco::XML::Document> document = dom_parser.parseString(xml);
+    Poco::AutoPtr<Poco::Util::XMLConfiguration> config = new Poco::Util::XMLConfiguration(document);
+    getMutableContext().context->setConfig(config);
+
+    auto query_context = DB::Context::createCopy(getContext().context);
+    query_context->makeQueryContext();
+    query_context->setCurrentQueryId(query_id);
+    chassert(&DB::CurrentThread::get() == &thread_status);
+    DB::CurrentThread::QueryScope query_scope_holder(query_context);
+
+    DB::FileCacheSettings settings;
+    settings.base_path = cache_base_path;
+    settings.max_file_segment_size = 5;
+    settings.max_size = 30;
+    settings.max_elements = 10;
+    settings.boundary_alignment = 1;
+
+    ReadSettings read_settings;
+    read_settings.enable_filesystem_cache = 1;
+    read_settings.local_fs_method = LocalFSReadMethod::pread;
+
+    std::string file_path = fs::current_path() / "test";
+    auto read_buffer_creator = [&]()
+    {
+        return createReadBufferFromFileBase(file_path, read_settings, std::nullopt, std::nullopt);
+    };
+
+    auto wb = std::make_unique<WriteBufferFromFile>(file_path, DBMS_DEFAULT_BUFFER_SIZE);
+    std::string s(30, '*');
+    wb->write(s.data(), s.size());
+    wb->next();
+    wb->finalize();
+
+    auto cache = std::make_shared<DB::FileCache>(settings);
+    cache->initialize();
+    auto key = cache->createKeyForPath(file_path);
+
+    {
+        auto cached_buffer = std::make_shared<CachedOnDiskReadBufferFromFile>(
+            file_path, key, cache, read_buffer_creator, read_settings, "test", s.size(), false, false, std::nullopt, nullptr);
+
+        WriteBufferFromOwnString result;
+        copyData(*cached_buffer, result);
+        ASSERT_EQ(result.str(), s);
+
+        assertEqual(cache->dumpQueue(), { Range(0, 4), Range(5, 9), Range(10, 14), Range(15, 19), Range(20, 24), Range(25, 29) });
+    }
+
+    {
+        ReadSettings modified_settings{read_settings};
+        modified_settings.local_fs_buffer_size = 10;
+        modified_settings.remote_fs_buffer_size = 10;
+
+        auto cached_buffer = std::make_shared<CachedOnDiskReadBufferFromFile>(
+            file_path, key, cache, read_buffer_creator, modified_settings, "test", s.size(), false, false, std::nullopt, nullptr);
+
+        cached_buffer->next();
+        assertEqual(cache->dumpQueue(), { Range(5, 9), Range(10, 14), Range(15, 19), Range(20, 24), Range(25, 29), Range(0, 4) });
+
+        cached_buffer->position() = cached_buffer->buffer().end();
+        cached_buffer->next();
+        assertEqual(cache->dumpQueue(), {Range(10, 14), Range(15, 19), Range(20, 24), Range(25, 29), Range(0, 4), Range(5, 9) });
+    }
+}

From 4da82d10d0a7eba0a10fc8f02889d1bd533f7b82 Mon Sep 17 00:00:00 2001
From: Kseniia Sumarokova <54203879+kssenii@users.noreply.github.com>
Date: Mon, 26 Jun 2023 17:57:46 +0200
Subject: [PATCH 07/24] Update gtest_lru_file_cache.cpp

---
 src/Interpreters/tests/gtest_lru_file_cache.cpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/Interpreters/tests/gtest_lru_file_cache.cpp b/src/Interpreters/tests/gtest_lru_file_cache.cpp
index 9ff9f92afe4..58b1302a72c 100644
--- a/src/Interpreters/tests/gtest_lru_file_cache.cpp
+++ b/src/Interpreters/tests/gtest_lru_file_cache.cpp
@@ -893,7 +893,7 @@ TEST_F(FileCacheTest, CachedReadBuffer)
     settings.boundary_alignment = 1;
 
     ReadSettings read_settings;
-    read_settings.enable_filesystem_cache = 1;
+    read_settings.enable_filesystem_cache = true;
     read_settings.local_fs_method = LocalFSReadMethod::pread;
 
     std::string file_path = fs::current_path() / "test";

From d3b8b454f853c63da4b94ec97afdcb1528ffdc22 Mon Sep 17 00:00:00 2001
From: Ilya Yatsishin <2159081+qoega@users.noreply.github.com>
Date: Tue, 27 Jun 2023 19:19:58 +0200
Subject: [PATCH 08/24] Fix segfault in MathUnary

---
 src/Functions/FunctionMathUnary.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/src/Functions/FunctionMathUnary.h b/src/Functions/FunctionMathUnary.h
index 6e4bff7122d..9f400932356 100644
--- a/src/Functions/FunctionMathUnary.h
+++ b/src/Functions/FunctionMathUnary.h
@@ -154,6 +154,8 @@ private:
             using ColVecType = ColumnVectorOrDecimal<Type>;
 
             const auto col_vec = checkAndGetColumn<ColVecType>(col.column.get());
+            if (col_vec == nullptr)
+                return false;
             return (res = execute<Type, ReturnType>(col_vec)) != nullptr;
         };
 

From 575f3513977a21a8fea5ff30116636f2fc9ac2f1 Mon Sep 17 00:00:00 2001
From: Yatsishin Ilya <2159081+qoega@users.noreply.github.com>
Date: Tue, 27 Jun 2023 18:34:12 +0000
Subject: [PATCH 09/24] add test

---
 tests/queries/0_stateless/02807_math_unary_crash.reference | 2 ++
 tests/queries/0_stateless/02807_math_unary_crash.sql       | 4 ++++
 2 files changed, 6 insertions(+)
 create mode 100644 tests/queries/0_stateless/02807_math_unary_crash.reference
 create mode 100644 tests/queries/0_stateless/02807_math_unary_crash.sql

diff --git a/tests/queries/0_stateless/02807_math_unary_crash.reference b/tests/queries/0_stateless/02807_math_unary_crash.reference
new file mode 100644
index 00000000000..6ed281c757a
--- /dev/null
+++ b/tests/queries/0_stateless/02807_math_unary_crash.reference
@@ -0,0 +1,2 @@
+1
+1
diff --git a/tests/queries/0_stateless/02807_math_unary_crash.sql b/tests/queries/0_stateless/02807_math_unary_crash.sql
new file mode 100644
index 00000000000..16c3ba1e0ae
--- /dev/null
+++ b/tests/queries/0_stateless/02807_math_unary_crash.sql
@@ -0,0 +1,4 @@
+CREATE TABLE t10 (`c0` Int32) ENGINE = MergeTree ORDER BY tuple();
+INSERT INTO t10 (c0) FORMAT Values (-1);
+SELECT 1 FROM t10 GROUP BY erf(-sign(t10.c0));
+SELECT 1 FROM t10 GROUP BY -sign(t10.c0);

From 3e5abbbf48953288d5bcea4fab9f2431bd05873d Mon Sep 17 00:00:00 2001
From: Alexey Milovidov <milovidov@clickhouse.com>
Date: Tue, 27 Jun 2023 22:47:19 +0300
Subject: [PATCH 10/24] Update 02807_math_unary_crash.sql

---
 tests/queries/0_stateless/02807_math_unary_crash.sql | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tests/queries/0_stateless/02807_math_unary_crash.sql b/tests/queries/0_stateless/02807_math_unary_crash.sql
index 16c3ba1e0ae..fb693ac70f7 100644
--- a/tests/queries/0_stateless/02807_math_unary_crash.sql
+++ b/tests/queries/0_stateless/02807_math_unary_crash.sql
@@ -1,4 +1,6 @@
+DROP TABLE IF EXISTS t10;
 CREATE TABLE t10 (`c0` Int32) ENGINE = MergeTree ORDER BY tuple();
 INSERT INTO t10 (c0) FORMAT Values (-1);
 SELECT 1 FROM t10 GROUP BY erf(-sign(t10.c0));
 SELECT 1 FROM t10 GROUP BY -sign(t10.c0);
+DROP TABLE t10;

From 5a1bbe5a8d2f07960161100e0a17527e4bda6de2 Mon Sep 17 00:00:00 2001
From: Kseniia Sumarokova <54203879+kssenii@users.noreply.github.com>
Date: Wed, 28 Jun 2023 14:05:14 +0200
Subject: [PATCH 11/24] Update CachedOnDiskReadBufferFromFile.cpp

---
 src/Disks/IO/CachedOnDiskReadBufferFromFile.cpp | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/src/Disks/IO/CachedOnDiskReadBufferFromFile.cpp b/src/Disks/IO/CachedOnDiskReadBufferFromFile.cpp
index 960d2a72410..5b42f41fbf3 100644
--- a/src/Disks/IO/CachedOnDiskReadBufferFromFile.cpp
+++ b/src/Disks/IO/CachedOnDiskReadBufferFromFile.cpp
@@ -852,9 +852,7 @@ bool CachedOnDiskReadBufferFromFile::nextImplStep()
     else
     {
         implementation_buffer = getImplementationBuffer(file_segments->front());
-
-        if (read_type == ReadType::CACHED)
-            file_segments->front().use();
+        file_segments->front().use();
     }
 
     chassert(!internal_buffer.empty());

From c42bf37a141decb206e405470c2af6d85145bf3f Mon Sep 17 00:00:00 2001
From: DanRoscigno <dan@roscigno.com>
Date: Wed, 28 Jun 2023 09:59:32 -0400
Subject: [PATCH 12/24] list the disk types

---
 .../engines/table-engines/mergetree-family/mergetree.md   | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/docs/en/engines/table-engines/mergetree-family/mergetree.md b/docs/en/engines/table-engines/mergetree-family/mergetree.md
index 42454af6feb..c67ac8fa4ef 100644
--- a/docs/en/engines/table-engines/mergetree-family/mergetree.md
+++ b/docs/en/engines/table-engines/mergetree-family/mergetree.md
@@ -756,6 +756,14 @@ If you perform the `SELECT` query between merges, you may get expired data. To a
 - [ttl_only_drop_parts](/docs/en/operations/settings/settings.md/#ttl_only_drop_parts) setting
 
 
+## Disk types
+
+In addition to local block devices, ClickHouse supports other device types through table engines. These are the types:
+- [S3](#table_engine-mergetree-s3)
+- GCS (also supported using the [S3 table engine](#table_engine-mergetree-s3))
+- [Azure Blob Storage](#table_engine-mergetree-azure-blob-storage)
+- [HDFS](/docs/en/sql-reference/table-functions/hdfs.md)
+
 ## Using Multiple Block Devices for Data Storage {#table_engine-mergetree-multiple-volumes}
 
 ### Introduction {#introduction}

From bfcadabb927e5ea547c29df488d3fe6ea396a178 Mon Sep 17 00:00:00 2001
From: DanRoscigno <dan@roscigno.com>
Date: Wed, 28 Jun 2023 10:30:49 -0400
Subject: [PATCH 13/24] add web disk type

---
 docs/en/engines/table-engines/mergetree-family/mergetree.md | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/docs/en/engines/table-engines/mergetree-family/mergetree.md b/docs/en/engines/table-engines/mergetree-family/mergetree.md
index c67ac8fa4ef..1f084fe075b 100644
--- a/docs/en/engines/table-engines/mergetree-family/mergetree.md
+++ b/docs/en/engines/table-engines/mergetree-family/mergetree.md
@@ -763,6 +763,7 @@ In addition to local block devices, ClickHouse supports other device types throu
 - GCS (also supported using the [S3 table engine](#table_engine-mergetree-s3))
 - [Azure Blob Storage](#table_engine-mergetree-azure-blob-storage)
 - [HDFS](/docs/en/sql-reference/table-functions/hdfs.md)
+- [Web (read-only)](#web-storage)
 
 ## Using Multiple Block Devices for Data Storage {#table_engine-mergetree-multiple-volumes}
 
@@ -944,6 +945,8 @@ configuration files; all the settings are in the CREATE/ATTACH query.
 The example uses `type=web`, but any disk type can be configured as dynamic, even Local disk. Local disks require a path argument to be inside the server config parameter `custom_local_disks_base_directory`, which has no default, so set that also when using local disk.
 :::
 
+#### Example dynamic web storage {#web-storage}
+
 ```sql
 ATTACH TABLE uk_price_paid UUID 'cf712b4f-2ca8-435c-ac23-c4393efe52f7'
 (

From b392127304d8c14ce34bd86d0b8ca561e1559919 Mon Sep 17 00:00:00 2001
From: DanRoscigno <dan@roscigno.com>
Date: Wed, 28 Jun 2023 11:00:07 -0400
Subject: [PATCH 14/24] add example web config

---
 .../mergetree-family/mergetree.md             | 53 ++++++++++++++++++-
 1 file changed, 52 insertions(+), 1 deletion(-)

diff --git a/docs/en/engines/table-engines/mergetree-family/mergetree.md b/docs/en/engines/table-engines/mergetree-family/mergetree.md
index 1f084fe075b..b87c4d216cf 100644
--- a/docs/en/engines/table-engines/mergetree-family/mergetree.md
+++ b/docs/en/engines/table-engines/mergetree-family/mergetree.md
@@ -945,7 +945,7 @@ configuration files; all the settings are in the CREATE/ATTACH query.
 The example uses `type=web`, but any disk type can be configured as dynamic, even Local disk. Local disks require a path argument to be inside the server config parameter `custom_local_disks_base_directory`, which has no default, so set that also when using local disk.
 :::
 
-#### Example dynamic web storage {#web-storage}
+#### Example dynamic web storage
 
 ```sql
 ATTACH TABLE uk_price_paid UUID 'cf712b4f-2ca8-435c-ac23-c4393efe52f7'
@@ -1249,6 +1249,57 @@ Examples of working configurations can be found in integration tests directory (
   Zero-copy replication is disabled by default in ClickHouse version 22.8 and higher.  This feature is not recommended for production use.
   :::
 
+## Web storage (read-only) {#web-storage}
+
+Web storage can be used for read-only purposes. An example use is for hosting sample
+data, or for migrating data.
+
+:::tip
+Storage can also be configured temporarily within a query, if a web dataset is not expected
+to be used routinely, see [dynamic storage](#dynamic-storage) and skip editing the
+configuration file.
+:::
+
+In this sample configuration:
+- the disk is of type `web`
+- the data is hosted at `http://nginx:80/test1/`
+- a cache on local storage is used 
+
+```xml
+<clickhouse>
+    <storage_configuration>
+        <disks>
+            <web>
+                <type>web</type>
+                <endpoint>http://nginx:80/test1/</endpoint>
+            </web>
+            <cached_web>
+                <type>cache</type>
+                <disk>web</disk>
+                <path>cached_web_cache/</path>
+                <max_size>100000000</max_size>
+            </cached_web>
+        </disks>
+        <policies>
+            <web>
+                <volumes>
+                    <main>
+                        <disk>web</disk>
+                    </main>
+                </volumes>
+            </web>
+            <cached_web>
+                <volumes>
+                    <main>
+                        <disk>cached_web</disk>
+                    </main>
+                </volumes>
+            </cached_web>
+        </policies>
+    </storage_configuration>
+</clickhouse>
+```
+
 ## Virtual Columns {#virtual-columns}
 
 - `_part` — Name of a part.

From dd3a744cef6e736bc68782fd79853a1535bdebb8 Mon Sep 17 00:00:00 2001
From: DanRoscigno <dan@roscigno.com>
Date: Wed, 28 Jun 2023 11:17:16 -0400
Subject: [PATCH 15/24] add HDFS example

---
 .../mergetree-family/mergetree.md             | 38 ++++++++++++++++++-
 1 file changed, 37 insertions(+), 1 deletion(-)

diff --git a/docs/en/engines/table-engines/mergetree-family/mergetree.md b/docs/en/engines/table-engines/mergetree-family/mergetree.md
index b87c4d216cf..1b7f3263ab9 100644
--- a/docs/en/engines/table-engines/mergetree-family/mergetree.md
+++ b/docs/en/engines/table-engines/mergetree-family/mergetree.md
@@ -762,7 +762,7 @@ In addition to local block devices, ClickHouse supports other device types throu
 - [S3](#table_engine-mergetree-s3)
 - GCS (also supported using the [S3 table engine](#table_engine-mergetree-s3))
 - [Azure Blob Storage](#table_engine-mergetree-azure-blob-storage)
-- [HDFS](/docs/en/sql-reference/table-functions/hdfs.md)
+- [HDFS](#hdfs-storage)
 - [Web (read-only)](#web-storage)
 
 ## Using Multiple Block Devices for Data Storage {#table_engine-mergetree-multiple-volumes}
@@ -1249,6 +1249,42 @@ Examples of working configurations can be found in integration tests directory (
   Zero-copy replication is disabled by default in ClickHouse version 22.8 and higher.  This feature is not recommended for production use.
   :::
 
+## HDFS storage {#hdfs-storage}
+
+In this sample configuration:
+- the disk is of type `hdfs`
+- the data is hosted at `hdfs://hdfs1:9000/clickhouse/`
+
+```xml
+<clickhouse>
+    <storage_configuration>
+        <disks>
+            <hdfs>
+                <type>hdfs</type>
+                <endpoint>hdfs://hdfs1:9000/clickhouse/</endpoint>
+                <skip_access_check>true</skip_access_check>
+            </hdfs>
+            <hdd>
+                <type>local</type>
+                <path>/</path>
+            </hdd>
+        </disks>
+        <policies>
+            <hdfs>
+                <volumes>
+                    <main>
+                        <disk>hdfs</disk>
+                    </main>
+                    <external>
+                        <disk>hdd</disk>
+                    </external>
+                </volumes>
+            </hdfs>
+        </policies>
+    </storage_configuration>
+</clickhouse>
+```
+
 ## Web storage (read-only) {#web-storage}
 
 Web storage can be used for read-only purposes. An example use is for hosting sample

From 45cd7f35cdfb3c1ed17cd2451468761aa25a6bfb Mon Sep 17 00:00:00 2001
From: "Mikhail f. Shiryaev" <felixoid@clickhouse.com>
Date: Thu, 22 Jun 2023 02:16:56 +0200
Subject: [PATCH 16/24] Use clickhouse/integration-helper from changed images

---
 docker/test/integration/runner/dockerd-entrypoint.sh |  2 ++
 tests/integration/helpers/network.py                 | 11 +++++++----
 tests/integration/runner                             |  2 ++
 3 files changed, 11 insertions(+), 4 deletions(-)

diff --git a/docker/test/integration/runner/dockerd-entrypoint.sh b/docker/test/integration/runner/dockerd-entrypoint.sh
index fe47fc90951..347d904d5c0 100755
--- a/docker/test/integration/runner/dockerd-entrypoint.sh
+++ b/docker/test/integration/runner/dockerd-entrypoint.sh
@@ -52,6 +52,8 @@ export CLICKHOUSE_TESTS_BASE_CONFIG_DIR=/clickhouse-config
 export CLICKHOUSE_ODBC_BRIDGE_BINARY_PATH=/clickhouse-odbc-bridge
 export CLICKHOUSE_LIBRARY_BRIDGE_BINARY_PATH=/clickhouse-library-bridge
 
+export DOCKER_BASE_TAG=${DOCKER_BASE_TAG:=latest}
+export DOCKER_HELPER_TAG=${DOCKER_HELPER_TAG:=latest}
 export DOCKER_MYSQL_GOLANG_CLIENT_TAG=${DOCKER_MYSQL_GOLANG_CLIENT_TAG:=latest}
 export DOCKER_DOTNET_CLIENT_TAG=${DOCKER_DOTNET_CLIENT_TAG:=latest}
 export DOCKER_MYSQL_JAVA_CLIENT_TAG=${DOCKER_MYSQL_JAVA_CLIENT_TAG:=latest}
diff --git a/tests/integration/helpers/network.py b/tests/integration/helpers/network.py
index 471aa2bdc2e..4859a8c5946 100644
--- a/tests/integration/helpers/network.py
+++ b/tests/integration/helpers/network.py
@@ -231,6 +231,9 @@ class _NetworkManager:
 
     def _ensure_container(self):
         if self._container is None or self._container_expire_time <= time.time():
+            image_name = "clickhouse/integration-helper:" + os.getenv(
+                "DOCKER_HELPER_TAG", "latest"
+            )
             for i in range(5):
                 if self._container is not None:
                     try:
@@ -247,7 +250,7 @@ class _NetworkManager:
                         time.sleep(i)
 
             image = subprocess.check_output(
-                "docker images -q clickhouse/integration-helper 2>/dev/null", shell=True
+                f"docker images -q {image_name} 2>/dev/null", shell=True
             )
             if not image.strip():
                 print("No network image helper, will try download")
@@ -256,16 +259,16 @@ class _NetworkManager:
                 for i in range(5):
                     try:
                         subprocess.check_call(  # STYLE_CHECK_ALLOW_SUBPROCESS_CHECK_CALL
-                            "docker pull clickhouse/integration-helper", shell=True
+                            f"docker pull {image_name}", shell=True
                         )
                         break
                     except:
                         time.sleep(i)
                 else:
-                    raise Exception("Cannot pull clickhouse/integration-helper image")
+                    raise Exception(f"Cannot pull {image_name} image")
 
             self._container = self._docker_client.containers.run(
-                "clickhouse/integration-helper",
+                image_name,
                 auto_remove=True,
                 command=("sleep %s" % self.container_exit_timeout),
                 # /run/xtables.lock passed inside for correct iptables --wait
diff --git a/tests/integration/runner b/tests/integration/runner
index f658bac412b..301a707a78d 100755
--- a/tests/integration/runner
+++ b/tests/integration/runner
@@ -336,6 +336,8 @@ if __name__ == "__main__":
                 env_tags += "-e {}={} ".format("DOCKER_MYSQL_PHP_CLIENT_TAG", tag)
             elif image == "clickhouse/postgresql-java-client":
                 env_tags += "-e {}={} ".format("DOCKER_POSTGRESQL_JAVA_CLIENT_TAG", tag)
+            elif image == "clickhouse/integration-helper":
+                env_tags += "-e {}={} ".format("DOCKER_HELPER_TAG", tag)
             elif image == "clickhouse/integration-test":
                 env_tags += "-e {}={} ".format("DOCKER_BASE_TAG", tag)
             elif image == "clickhouse/kerberized-hadoop":

From eeb8cdbc19e69aab64b0da2de0b569d6e31f438f Mon Sep 17 00:00:00 2001
From: "Mikhail f. Shiryaev" <felixoid@clickhouse.com>
Date: Thu, 22 Jun 2023 02:36:30 +0200
Subject: [PATCH 17/24] Add way to define additional urls in test reports

---
 tests/ci/upload_result_helper.py | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/tests/ci/upload_result_helper.py b/tests/ci/upload_result_helper.py
index 150af7aff4a..fbb89ef8078 100644
--- a/tests/ci/upload_result_helper.py
+++ b/tests/ci/upload_result_helper.py
@@ -1,5 +1,5 @@
 from pathlib import Path
-from typing import Dict, List
+from typing import Dict, List, Optional
 import os
 import logging
 
@@ -58,14 +58,19 @@ def upload_results(
     test_results: TestResults,
     additional_files: List[str],
     check_name: str,
+    additional_urls: Optional[List[str]] = None,
 ) -> str:
     normalized_check_name = check_name.lower()
     for r in ((" ", "_"), ("(", "_"), (")", "_"), (",", "_"), ("/", "_")):
         normalized_check_name = normalized_check_name.replace(*r)
+
+    # Preserve additional_urls to not modify the original one
+    original_additional_urls = additional_urls or []
     s3_path_prefix = f"{pr_number}/{commit_sha}/{normalized_check_name}"
     additional_urls = process_logs(
         s3_client, additional_files, s3_path_prefix, test_results
     )
+    additional_urls.extend(original_additional_urls)
 
     branch_url = f"{GITHUB_SERVER_URL}/{GITHUB_REPOSITORY}/commits/master"
     branch_name = "master"

From f23bf9c5acdd885d61ec7f68bdf8be1b1fa79dee Mon Sep 17 00:00:00 2001
From: JackyWoo <wuchienchao@qq.com>
Date: Thu, 29 Jun 2023 10:04:36 +0800
Subject: [PATCH 18/24] Update redis.md

---
 .../engines/table-engines/integrations/redis.md  | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/docs/en/engines/table-engines/integrations/redis.md b/docs/en/engines/table-engines/integrations/redis.md
index 568179eb690..7ef87927bfd 100644
--- a/docs/en/engines/table-engines/integrations/redis.md
+++ b/docs/en/engines/table-engines/integrations/redis.md
@@ -44,9 +44,10 @@ Create a table in ClickHouse which allows to read data from Redis:
 ``` sql
 CREATE TABLE redis_table
 (
-    `k` String,
-    `m` String,
-    `n` UInt32
+    `key` String,
+    `v1` UInt32,
+    `v2` String,
+    `v3` Float32
 )
 ENGINE = Redis('redis1:6379') PRIMARY KEY(k);
 ```
@@ -111,9 +112,16 @@ Flush Redis db asynchronously. Also `Truncate` support SYNC mode.
 TRUNCATE TABLE redis_table SYNC;
 ```
 
+Join:
+
+Join with other tables.
+
+```
+SELECT * FROM redis_table JOIN merge_tree_table ON redis_table.key=merge_tree_table.key;
+```
 
 ## Limitations {#limitations}
 
 Redis engine also supports scanning queries, such as `where k > xx`, but it has some limitations:
-1. Scanning query may produce some duplicated keys in a very rare case when it is rehashing. See details in [Redis Scan](https://github.com/redis/redis/blob/e4d183afd33e0b2e6e8d1c79a832f678a04a7886/src/dict.c#L1186-L1269)
+1. Scanning query may produce some duplicated keys in a very rare case when it is rehashing. See details in [Redis Scan](https://github.com/redis/redis/blob/e4d183afd33e0b2e6e8d1c79a832f678a04a7886/src/dict.c#L1186-L1269).
 2. During the scanning, keys could be created and deleted, so the resulting dataset can not represent a valid point in time.

From f8f0b7d086d23f70a49be88233b19d152e99e3f4 Mon Sep 17 00:00:00 2001
From: JackyWoo <wuchienchao@qq.com>
Date: Thu, 29 Jun 2023 10:09:27 +0800
Subject: [PATCH 19/24] fix typo

---
 docs/en/engines/table-engines/integrations/redis.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/en/engines/table-engines/integrations/redis.md b/docs/en/engines/table-engines/integrations/redis.md
index 7ef87927bfd..2697abcf30e 100644
--- a/docs/en/engines/table-engines/integrations/redis.md
+++ b/docs/en/engines/table-engines/integrations/redis.md
@@ -49,7 +49,7 @@ CREATE TABLE redis_table
     `v2` String,
     `v3` Float32
 )
-ENGINE = Redis('redis1:6379') PRIMARY KEY(k);
+ENGINE = Redis('redis1:6379') PRIMARY KEY(key);
 ```
 
 Insert:

From 635ab9f9af3894c42b69ef093cc34e64cefce219 Mon Sep 17 00:00:00 2001
From: JackyWoo <wuchienchao@qq.com>
Date: Thu, 29 Jun 2023 12:53:23 +0800
Subject: [PATCH 20/24] move redis_table to right

---
 docs/en/engines/table-engines/integrations/redis.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/en/engines/table-engines/integrations/redis.md b/docs/en/engines/table-engines/integrations/redis.md
index 2697abcf30e..8086a6503b8 100644
--- a/docs/en/engines/table-engines/integrations/redis.md
+++ b/docs/en/engines/table-engines/integrations/redis.md
@@ -117,7 +117,7 @@ Join:
 Join with other tables.
 
 ```
-SELECT * FROM redis_table JOIN merge_tree_table ON redis_table.key=merge_tree_table.key;
+SELECT * FROM redis_table JOIN merge_tree_table ON merge_tree_table.key=redis_table.key;
 ```
 
 ## Limitations {#limitations}

From 5656d18690bd00b0db48c1e12e48e0446e263465 Mon Sep 17 00:00:00 2001
From: robot-clickhouse <robot-clickhouse@users.noreply.github.com>
Date: Thu, 29 Jun 2023 13:36:55 +0000
Subject: [PATCH 21/24] Update version_date.tsv and changelogs after
 v23.5.4.25-stable

---
 docker/keeper/Dockerfile             |  2 +-
 docker/server/Dockerfile.alpine      |  2 +-
 docker/server/Dockerfile.ubuntu      |  2 +-
 docs/changelogs/v23.5.4.25-stable.md | 31 ++++++++++++++++++++++++++++
 utils/list-versions/version_date.tsv |  1 +
 5 files changed, 35 insertions(+), 3 deletions(-)
 create mode 100644 docs/changelogs/v23.5.4.25-stable.md

diff --git a/docker/keeper/Dockerfile b/docker/keeper/Dockerfile
index 367f6043b90..6d53a6f4c51 100644
--- a/docker/keeper/Dockerfile
+++ b/docker/keeper/Dockerfile
@@ -32,7 +32,7 @@ RUN arch=${TARGETARCH:-amd64} \
     esac
 
 ARG REPOSITORY="https://s3.amazonaws.com/clickhouse-builds/22.4/31c367d3cd3aefd316778601ff6565119fe36682/package_release"
-ARG VERSION="23.5.3.24"
+ARG VERSION="23.5.4.25"
 ARG PACKAGES="clickhouse-keeper"
 
 # user/group precreated explicitly with fixed uid/gid on purpose.
diff --git a/docker/server/Dockerfile.alpine b/docker/server/Dockerfile.alpine
index e7e879fa95f..91b22346f13 100644
--- a/docker/server/Dockerfile.alpine
+++ b/docker/server/Dockerfile.alpine
@@ -33,7 +33,7 @@ RUN arch=${TARGETARCH:-amd64} \
 # lts / testing / prestable / etc
 ARG REPO_CHANNEL="stable"
 ARG REPOSITORY="https://packages.clickhouse.com/tgz/${REPO_CHANNEL}"
-ARG VERSION="23.5.3.24"
+ARG VERSION="23.5.4.25"
 ARG PACKAGES="clickhouse-client clickhouse-server clickhouse-common-static"
 
 # user/group precreated explicitly with fixed uid/gid on purpose.
diff --git a/docker/server/Dockerfile.ubuntu b/docker/server/Dockerfile.ubuntu
index 42ae81655d2..0ed0e4e1168 100644
--- a/docker/server/Dockerfile.ubuntu
+++ b/docker/server/Dockerfile.ubuntu
@@ -23,7 +23,7 @@ RUN sed -i "s|http://archive.ubuntu.com|${apt_archive}|g" /etc/apt/sources.list
 
 ARG REPO_CHANNEL="stable"
 ARG REPOSITORY="deb [signed-by=/usr/share/keyrings/clickhouse-keyring.gpg] https://packages.clickhouse.com/deb ${REPO_CHANNEL} main"
-ARG VERSION="23.5.3.24"
+ARG VERSION="23.5.4.25"
 ARG PACKAGES="clickhouse-client clickhouse-server clickhouse-common-static"
 
 # set non-empty deb_location_url url to create a docker image
diff --git a/docs/changelogs/v23.5.4.25-stable.md b/docs/changelogs/v23.5.4.25-stable.md
new file mode 100644
index 00000000000..53d3a7c9c0a
--- /dev/null
+++ b/docs/changelogs/v23.5.4.25-stable.md
@@ -0,0 +1,31 @@
+---
+sidebar_position: 1
+sidebar_label: 2023
+---
+
+# 2023 Changelog
+
+### ClickHouse release v23.5.4.25-stable (190f962abcf) FIXME as compared to v23.5.3.24-stable (76f54616d3b)
+
+#### Improvement
+* Backported in [#51235](https://github.com/ClickHouse/ClickHouse/issues/51235): Improve the progress bar for file/s3/hdfs/url table functions by using chunk size from source data and using incremental total size counting in each thread. Fix the progress bar for *Cluster functions. This closes [#47250](https://github.com/ClickHouse/ClickHouse/issues/47250). [#51088](https://github.com/ClickHouse/ClickHouse/pull/51088) ([Kruglov Pavel](https://github.com/Avogar)).
+* Backported in [#51255](https://github.com/ClickHouse/ClickHouse/issues/51255): Disable cache setting `do_not_evict_index_and_mark_files` (Was enabled in `23.5`). [#51222](https://github.com/ClickHouse/ClickHouse/pull/51222) ([Kseniia Sumarokova](https://github.com/kssenii)).
+
+#### Build/Testing/Packaging Improvement
+* Backported in [#51531](https://github.com/ClickHouse/ClickHouse/issues/51531): Split huge `RUN` in Dockerfile into smaller conditional. Install the necessary tools on demand in the same `RUN` layer, and remove them after that. Upgrade the OS only once at the beginning. Use a modern way to check the signed repository. Downgrade the base repo to ubuntu:20.04 to address the issues on older docker versions. Upgrade golang version to address golang vulnerabilities. [#51504](https://github.com/ClickHouse/ClickHouse/pull/51504) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Backported in [#51572](https://github.com/ClickHouse/ClickHouse/issues/51572): This a follow-up for [#51504](https://github.com/ClickHouse/ClickHouse/issues/51504), the cleanup was lost during refactoring. [#51564](https://github.com/ClickHouse/ClickHouse/pull/51564) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+
+#### Bug Fix (user-visible misbehavior in an official stable release)
+
+* Query Cache: Try to fix bad cast from ColumnConst to ColumnVector<char8_t> [#50704](https://github.com/ClickHouse/ClickHouse/pull/50704) ([Robert Schulze](https://github.com/rschu1ze)).
+* Fix type of LDAP server params hash in cache entry [#50865](https://github.com/ClickHouse/ClickHouse/pull/50865) ([Julian Maicher](https://github.com/jmaicher)).
+* Fallback to parsing big integer from String instead of exception in Parquet format [#50873](https://github.com/ClickHouse/ClickHouse/pull/50873) ([Kruglov Pavel](https://github.com/Avogar)).
+* Do not apply projection if read-in-order was enabled. [#50923](https://github.com/ClickHouse/ClickHouse/pull/50923) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Fix race azure blob storage iterator [#50936](https://github.com/ClickHouse/ClickHouse/pull/50936) ([SmitaRKulkarni](https://github.com/SmitaRKulkarni)).
+* Fix ineffective query cache for SELECTs with subqueries [#51132](https://github.com/ClickHouse/ClickHouse/pull/51132) ([Robert Schulze](https://github.com/rschu1ze)).
+* Fix fuzzer failure in ActionsDAG [#51301](https://github.com/ClickHouse/ClickHouse/pull/51301) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+
+#### NOT FOR CHANGELOG / INSIGNIFICANT
+
+* Fix ParallelReadBuffer seek [#50820](https://github.com/ClickHouse/ClickHouse/pull/50820) ([Michael Kolupaev](https://github.com/al13n321)).
+
diff --git a/utils/list-versions/version_date.tsv b/utils/list-versions/version_date.tsv
index 307ed97068f..5c8dd0d2481 100644
--- a/utils/list-versions/version_date.tsv
+++ b/utils/list-versions/version_date.tsv
@@ -1,3 +1,4 @@
+v23.5.4.25-stable	2023-06-29
 v23.5.3.24-stable	2023-06-17
 v23.5.2.7-stable	2023-06-10
 v23.5.1.3174-stable	2023-06-09

From 6ec85f9faa548e50ec1a6b4a2d7868c9f7e0079a Mon Sep 17 00:00:00 2001
From: Denny Crane <denis.zhuravlov@gmail.com>
Date: Thu, 29 Jun 2023 11:06:28 -0300
Subject: [PATCH 22/24] Update settings.md

---
 docs/en/operations/settings/settings.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/en/operations/settings/settings.md b/docs/en/operations/settings/settings.md
index cff65e049f3..cff13302cdc 100644
--- a/docs/en/operations/settings/settings.md
+++ b/docs/en/operations/settings/settings.md
@@ -1322,7 +1322,7 @@ Connection pool size for PostgreSQL table engine and database engine.
 
 Default value: 16
 
-## postgresql_connection_pool_size {#postgresql-connection-pool-size}
+## postgresql_connection_pool_wait_timeout {#postgresql-connection-pool-wait-timeout}
 
 Connection pool push/pop timeout on empty pool for PostgreSQL table engine and database engine. By default it will block on empty pool.
 

From 4ee094cab1a4aed4091679e54e6ac146b2423693 Mon Sep 17 00:00:00 2001
From: DanRoscigno <dan@roscigno.com>
Date: Thu, 29 Jun 2023 12:13:26 -0400
Subject: [PATCH 23/24] review comments

---
 .../table-engines/mergetree-family/mergetree.md    | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/docs/en/engines/table-engines/mergetree-family/mergetree.md b/docs/en/engines/table-engines/mergetree-family/mergetree.md
index 1b7f3263ab9..a1c2fbdbe50 100644
--- a/docs/en/engines/table-engines/mergetree-family/mergetree.md
+++ b/docs/en/engines/table-engines/mergetree-family/mergetree.md
@@ -758,12 +758,14 @@ If you perform the `SELECT` query between merges, you may get expired data. To a
 
 ## Disk types
 
-In addition to local block devices, ClickHouse supports other device types through table engines. These are the types:
-- [S3](#table_engine-mergetree-s3)
-- GCS (also supported using the [S3 table engine](#table_engine-mergetree-s3))
-- [Azure Blob Storage](#table_engine-mergetree-azure-blob-storage)
-- [HDFS](#hdfs-storage)
-- [Web (read-only)](#web-storage)
+In addition to local block devices, ClickHouse supports these storage types:
+- [`s3` for S3 and MinIO](#table_engine-mergetree-s3)
+- [`gcs` for GCS](/docs/en/integrations/data-ingestion/gcs/index.md/#creating-a-disk)
+- [`blob_storage_disk` for Azure Blob Storage](#table_engine-mergetree-azure-blob-storage)
+- [`hdfs` for HDFS](#hdfs-storage)
+- [`web` for read-only from web](#web-storage)
+- [`cache` for local caching](/docs/en/operations/storing-data.md/#using-local-cache)
+- [`s3_plain` for backups to S3](/docs/en/operations/backup#backuprestore-using-an-s3-disk)
 
 ## Using Multiple Block Devices for Data Storage {#table_engine-mergetree-multiple-volumes}
 

From 90129b92c1dd47c0aa86cd5ed7c8107758a74b51 Mon Sep 17 00:00:00 2001
From: Alexey Milovidov <milovidov@clickhouse.com>
Date: Thu, 29 Jun 2023 21:19:41 +0200
Subject: [PATCH 24/24] Update 23.6 changelog

---
 CHANGELOG.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index a2e7b021081..c1e0dba4465 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -21,7 +21,7 @@
 * Added `Overlay` database engine to combine multiple databases into one. Added `Filesystem` database engine to represent a directory in the filesystem as a set of implicitly available tables with auto-detected formats and structures. A new `S3` database engine allows to read-only interact with s3 storage by representing a prefix as a set of tables. A new `HDFS` database engine allows to interact with HDFS storage in the same way. [#48821](https://github.com/ClickHouse/ClickHouse/pull/48821) ([alekseygolub](https://github.com/alekseygolub)).
 * The function `transform` as well as `CASE` with value matching started to support all data types. This closes [#29730](https://github.com/ClickHouse/ClickHouse/issues/29730). This closes [#32387](https://github.com/ClickHouse/ClickHouse/issues/32387). This closes [#50827](https://github.com/ClickHouse/ClickHouse/issues/50827). This closes [#31336](https://github.com/ClickHouse/ClickHouse/issues/31336). This closes [#40493](https://github.com/ClickHouse/ClickHouse/issues/40493). [#51351](https://github.com/ClickHouse/ClickHouse/pull/51351) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
 * Added option `--rename_files_after_processing <pattern>`. This closes [#34207](https://github.com/ClickHouse/ClickHouse/issues/34207). [#49626](https://github.com/ClickHouse/ClickHouse/pull/49626) ([alekseygolub](https://github.com/alekseygolub)).
-* Add support for `APPEND` modifier in `INTO OUTFILE` clause. Suggest using `APPEND` or `TRUNCATE` for `INTO OUTFILE` when file exists. [#50950](https://github.com/ClickHouse/ClickHouse/pull/50950) ([alekar](https://github.com/alekar)).
+* Add support for `TRUNCATE` modifier in `INTO OUTFILE` clause. Suggest using `APPEND` or `TRUNCATE` for `INTO OUTFILE` when file exists. [#50950](https://github.com/ClickHouse/ClickHouse/pull/50950) ([alekar](https://github.com/alekar)).
 * Add table engine `Redis` and table function `redis`. It allows querying external Redis servers. [#50150](https://github.com/ClickHouse/ClickHouse/pull/50150) ([JackyWoo](https://github.com/JackyWoo)).
 * Allow to skip empty files in file/s3/url/hdfs table functions using settings `s3_skip_empty_files`, `hdfs_skip_empty_files`, `engine_file_skip_empty_files`, `engine_url_skip_empty_files`. [#50364](https://github.com/ClickHouse/ClickHouse/pull/50364) ([Kruglov Pavel](https://github.com/Avogar)).
 * Add a new setting named `use_mysql_types_in_show_columns` to alter the `SHOW COLUMNS` SQL statement to display MySQL equivalent types when a client is connected via the MySQL compatibility port. [#49577](https://github.com/ClickHouse/ClickHouse/pull/49577) ([Thomas Panetti](https://github.com/tpanetti)).
@@ -40,12 +40,12 @@
 * Make multiple list requests to ZooKeeper in parallel to speed up reading from system.zookeeper table. [#51042](https://github.com/ClickHouse/ClickHouse/pull/51042) ([Alexander Gololobov](https://github.com/davenger)).
 * Speedup initialization of DateTime lookup tables for time zones. This should reduce startup/connect time of clickhouse-client especially in debug build as it is rather heavy. [#51347](https://github.com/ClickHouse/ClickHouse/pull/51347) ([Alexander Gololobov](https://github.com/davenger)).
 * Fix data lakes slowness because of synchronous head requests. (Related to Iceberg/Deltalake/Hudi being slow with a lot of files). [#50976](https://github.com/ClickHouse/ClickHouse/pull/50976) ([Kseniia Sumarokova](https://github.com/kssenii)).
-* Do not replicate `ALTER PARTITION` queries and mutations through `Replicated` database if it has only one shard and the underlying table is `ReplicatedMergeTree`. [#51049](https://github.com/ClickHouse/ClickHouse/pull/51049) ([Alexander Tokmakov](https://github.com/tavplubix)).
 * Do not read all the columns from right GLOBAL JOIN table. [#50721](https://github.com/ClickHouse/ClickHouse/pull/50721) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
 
 #### Experimental Feature
 * Support parallel replicas with the analyzer. [#50441](https://github.com/ClickHouse/ClickHouse/pull/50441) ([Raúl Marín](https://github.com/Algunenano)).
 * Add random sleep before large merges/mutations execution to split load more evenly between replicas in case of zero-copy replication. [#51282](https://github.com/ClickHouse/ClickHouse/pull/51282) ([alesapin](https://github.com/alesapin)).
+* Do not replicate `ALTER PARTITION` queries and mutations through `Replicated` database if it has only one shard and the underlying table is `ReplicatedMergeTree`. [#51049](https://github.com/ClickHouse/ClickHouse/pull/51049) ([Alexander Tokmakov](https://github.com/tavplubix)).
 
 #### Improvement
 * Relax the thresholds for "too many parts" to be more modern. Return the backpressure during long-running insert queries. [#50856](https://github.com/ClickHouse/ClickHouse/pull/50856) ([Alexey Milovidov](https://github.com/alexey-milovidov)).