Files
zeekay 9a90943b8f merge: ClickHouse 26.7.1.1315-stable into datastore — preserve debrand
13,838 upstream commits, forward from the 26.6.1.1 fork point. 129 conflicts:
37 resolved mechanically (take upstream's file, re-apply the brand sweep) and
92 by hand where our fork and upstream had both changed the same code.

The rule throughout: upstream owns the engine, we own the naming and a small set
of deliberate deviations. Never resolve by discarding an upstream change — a
dropped rename or a missed new parameter becomes a compile error a thousand
files away.

Deviations verified intact after the merge:
  ENABLE_XRAY still defaults OFF        (CMakeLists.txt:105)
  X-Datastore-User read by the server   (authenticateUserByHTTP.cpp)
  X-ClickHouse-* in src/                0
  hanzo/research                        present
  system.*_log retention bound          present
  ArrowFlight rip                       held against upstream re-adding it

Two things worth naming, because neither shows up as a conflict:

  src/CMakeLists.txt gained an UNGUARDED
  `add_object_library(datastore_storages_arrowflight Storages/ArrowFlight)` from
  upstream, for a directory our gRPC rip deleted. It sat outside every conflict
  hunk, so a resolver reading only the markers would sail straight past it into
  a CMake configure error. Removed; the Server/ArrowFlight sibling at line 474
  stays because it is inside `if (TARGET ch_contrib::arrow_flight)`.

  The brand sweep had rewritten github.com/ClickHouse/ClickHouse issue links to
  github.com/Datastore/Datastore — a dead host. Those point at upstream's own
  tracker and are restored, alongside the contributors list, sql.clickhouse.com
  and the ClickHouse Inc copyright: attribution is theirs, not ours to rename.

base/glibc-compatibility/memcpy/memcpy.h is deleted, not kept: upstream dropped
it for LLVM-libc's, and our only change to it was a comment rebrand.
2026-07-26 14:47:43 -07:00

201 lines
8.1 KiB
CMake

if(NOT OS_FREEBSD AND NOT ARCH_PPC64LE)
option(ENABLE_HDFS "Enable HDFS" ${ENABLE_LIBRARIES})
elseif(ENABLE_HDFS)
message (${RECONFIGURE_MESSAGE_LEVEL} "Cannot use HDFS3 with current configuration")
endif()
if(NOT ENABLE_HDFS)
message(STATUS "Not using HDFS")
return()
endif()
if (TARGET ch_contrib::krb5)
SET(WITH_KERBEROS 1)
else()
SET(WITH_KERBEROS 0)
endif()
# project and source dir
set(HDFS3_ROOT_DIR "${Datastore_SOURCE_DIR}/contrib/libhdfs3")
set(HDFS3_SOURCE_DIR "${HDFS3_ROOT_DIR}/src")
set(HDFS3_COMMON_DIR "${HDFS3_SOURCE_DIR}/common")
ADD_DEFINITIONS(-DTEST_HDFS_PREFIX="${TEST_HDFS_PREFIX}")
ADD_DEFINITIONS(-D__STDC_FORMAT_MACROS)
ADD_DEFINITIONS(-D_GNU_SOURCE)
ADD_DEFINITIONS(-D_GLIBCXX_USE_NANOSLEEP)
ADD_DEFINITIONS(-DHAVE_NANOSLEEP)
if (USE_MUSL OR APPLE)
ADD_DEFINITIONS(-DSTRERROR_R_RETURN_INT)
endif ()
set(HAVE_STEADY_CLOCK 1)
set(HAVE_NESTED_EXCEPTION 1)
SET(HAVE_BOOST_CHRONO 0)
SET(HAVE_BOOST_ATOMIC 0)
SET(HAVE_STD_CHRONO 1)
SET(HAVE_STD_ATOMIC 1)
# source
set(PROTO_FILES
#"${HDFS3_SOURCE_DIR}/proto/encryption.proto"
"${HDFS3_SOURCE_DIR}/proto/ClientDatanodeProtocol.proto"
"${HDFS3_SOURCE_DIR}/proto/hdfs.proto"
"${HDFS3_SOURCE_DIR}/proto/Security.proto"
"${HDFS3_SOURCE_DIR}/proto/ProtobufRpcEngine.proto"
"${HDFS3_SOURCE_DIR}/proto/ClientNamenodeProtocol.proto"
"${HDFS3_SOURCE_DIR}/proto/IpcConnectionContext.proto"
"${HDFS3_SOURCE_DIR}/proto/RpcHeader.proto"
"${HDFS3_SOURCE_DIR}/proto/datatransfer.proto"
)
PROTOBUF_GENERATE_CPP(PROTO_SOURCES PROTO_HEADERS ${PROTO_FILES} APPEND_PATH)
configure_file("${HDFS3_SOURCE_DIR}/platform.h.in" "${CMAKE_CURRENT_BINARY_DIR}/platform.h")
set(SRCS
"${HDFS3_SOURCE_DIR}/network/TcpSocket.cpp"
"${HDFS3_SOURCE_DIR}/network/DomainSocket.cpp"
"${HDFS3_SOURCE_DIR}/network/BufferedSocketReader.cpp"
"${HDFS3_SOURCE_DIR}/client/ReadShortCircuitInfo.cpp"
"${HDFS3_SOURCE_DIR}/client/Pipeline.cpp"
"${HDFS3_SOURCE_DIR}/client/Hdfs.cpp"
"${HDFS3_SOURCE_DIR}/client/Packet.cpp"
"${HDFS3_SOURCE_DIR}/client/OutputStreamImpl.cpp"
"${HDFS3_SOURCE_DIR}/client/KerberosName.cpp"
"${HDFS3_SOURCE_DIR}/client/PacketHeader.cpp"
"${HDFS3_SOURCE_DIR}/client/LocalBlockReader.cpp"
"${HDFS3_SOURCE_DIR}/client/UserInfo.cpp"
"${HDFS3_SOURCE_DIR}/client/RemoteBlockReader.cpp"
"${HDFS3_SOURCE_DIR}/client/Permission.cpp"
"${HDFS3_SOURCE_DIR}/client/FileSystemImpl.cpp"
"${HDFS3_SOURCE_DIR}/client/DirectoryIterator.cpp"
"${HDFS3_SOURCE_DIR}/client/FileSystemKey.cpp"
"${HDFS3_SOURCE_DIR}/client/DataTransferProtocolSender.cpp"
"${HDFS3_SOURCE_DIR}/client/LeaseRenewer.cpp"
"${HDFS3_SOURCE_DIR}/client/PeerCache.cpp"
"${HDFS3_SOURCE_DIR}/client/InputStream.cpp"
"${HDFS3_SOURCE_DIR}/client/FileSystem.cpp"
"${HDFS3_SOURCE_DIR}/client/InputStreamImpl.cpp"
"${HDFS3_SOURCE_DIR}/client/Token.cpp"
"${HDFS3_SOURCE_DIR}/client/PacketPool.cpp"
"${HDFS3_SOURCE_DIR}/client/OutputStream.cpp"
"${HDFS3_SOURCE_DIR}/client/AbstractNativeRawDecoder.cpp"
"${HDFS3_SOURCE_DIR}/client/AbstractNativeRawEncoder.cpp"
"${HDFS3_SOURCE_DIR}/client/ByteBufferDecodingState.cpp"
"${HDFS3_SOURCE_DIR}/client/ByteBufferEncodingState.cpp"
"${HDFS3_SOURCE_DIR}/client/CoderUtil.cpp"
"${HDFS3_SOURCE_DIR}/client/ECChunk.cpp"
"${HDFS3_SOURCE_DIR}/client/ErasureCoderOptions.cpp"
"${HDFS3_SOURCE_DIR}/client/GF256.cpp"
"${HDFS3_SOURCE_DIR}/client/GaloisField.cpp"
"${HDFS3_SOURCE_DIR}/client/NativeRSRawDecoder.cpp"
"${HDFS3_SOURCE_DIR}/client/NativeRSRawEncoder.cpp"
"${HDFS3_SOURCE_DIR}/client/Preconditions.cpp"
"${HDFS3_SOURCE_DIR}/client/RSUtil.cpp"
"${HDFS3_SOURCE_DIR}/client/RawErasureCoderFactory.cpp"
"${HDFS3_SOURCE_DIR}/client/RawErasureDecoder.cpp"
"${HDFS3_SOURCE_DIR}/client/RawErasureEncoder.cpp"
"${HDFS3_SOURCE_DIR}/client/StatefulStripeReader.cpp"
"${HDFS3_SOURCE_DIR}/client/PositionStripeReader.cpp"
"${HDFS3_SOURCE_DIR}/client/StripeReader.cpp"
"${HDFS3_SOURCE_DIR}/client/StripedBlockUtil.cpp"
"${HDFS3_SOURCE_DIR}/client/StripedInputStreamImpl.cpp"
"${HDFS3_SOURCE_DIR}/client/StripedOutputStreamImpl.cpp"
"${HDFS3_SOURCE_DIR}/client/SystemECPolicies.cpp"
"${HDFS3_SOURCE_DIR}/client/dump.cpp"
"${HDFS3_SOURCE_DIR}/client/erasure_coder.cpp"
"${HDFS3_SOURCE_DIR}/rpc/RpcChannelKey.cpp"
"${HDFS3_SOURCE_DIR}/rpc/RpcProtocolInfo.cpp"
"${HDFS3_SOURCE_DIR}/rpc/RpcClient.cpp"
"${HDFS3_SOURCE_DIR}/rpc/RpcRemoteCall.cpp"
"${HDFS3_SOURCE_DIR}/rpc/RpcChannel.cpp"
"${HDFS3_SOURCE_DIR}/rpc/RpcAuth.cpp"
"${HDFS3_SOURCE_DIR}/rpc/RpcContentWrapper.cpp"
"${HDFS3_SOURCE_DIR}/rpc/RpcConfig.cpp"
"${HDFS3_SOURCE_DIR}/rpc/RpcServerInfo.cpp"
"${HDFS3_SOURCE_DIR}/rpc/SaslClient.cpp"
"${HDFS3_SOURCE_DIR}/server/Datanode.cpp"
"${HDFS3_SOURCE_DIR}/server/LocatedBlocks.cpp"
"${HDFS3_SOURCE_DIR}/server/NamenodeProxy.cpp"
"${HDFS3_SOURCE_DIR}/server/NamenodeImpl.cpp"
"${HDFS3_SOURCE_DIR}/server/NamenodeInfo.cpp"
"${HDFS3_SOURCE_DIR}/common/WritableUtils.cpp"
"${HDFS3_SOURCE_DIR}/common/ExceptionInternal.cpp"
"${HDFS3_SOURCE_DIR}/common/SessionConfig.cpp"
"${HDFS3_SOURCE_DIR}/common/StackPrinter.cpp"
"${HDFS3_SOURCE_DIR}/common/Exception.cpp"
"${HDFS3_SOURCE_DIR}/common/Logger.cpp"
"${HDFS3_SOURCE_DIR}/common/CFileWrapper.cpp"
"${HDFS3_SOURCE_DIR}/common/XmlConfig.cpp"
"${HDFS3_SOURCE_DIR}/common/WriteBuffer.cpp"
"${HDFS3_SOURCE_DIR}/common/HWCrc32c.cpp"
"${HDFS3_SOURCE_DIR}/common/MappedFileWrapper.cpp"
"${HDFS3_SOURCE_DIR}/common/Hash.cpp"
"${HDFS3_SOURCE_DIR}/common/SWCrc32c.cpp"
"${HDFS3_SOURCE_DIR}/common/Thread.cpp"
"${HDFS3_SOURCE_DIR}/common/IntelAsmCrc32c.cpp"
${PROTO_SOURCES}
)
if (ARCH_AMD64 AND NOT APPLE)
find_program(YASM_PATH NAMES yasm)
if (NOT YASM_PATH)
message(FATAL_ERROR "Please install the Yasm assembler to build Datastore with Hadoop Distributed File System (HDFS) support")
endif ()
add_custom_command(
OUTPUT ${CMAKE_CURRENT_BINARY_DIR}/crc_iscsi_v_pcl.o
COMMAND ${YASM_PATH} -f x64 -f elf64 -X gnu -g dwarf2 -D LINUX -o ${CMAKE_CURRENT_BINARY_DIR}/crc_iscsi_v_pcl.o ${HDFS3_SOURCE_DIR}/common/crc_iscsi_v_pcl.asm
COMMENT "Translating Intel CRC assembly to object code")
LIST(APPEND SRCS ${CMAKE_CURRENT_BINARY_DIR}/crc_iscsi_v_pcl.o)
endif ()
# old kernels (< 3.17) doesn't have SYS_getrandom. Always use POSIX implementation to have better compatibility
set_source_files_properties("${HDFS3_SOURCE_DIR}/rpc/RpcClient.cpp" PROPERTIES COMPILE_FLAGS "-DBOOST_UUID_RANDOM_PROVIDER_FORCE_POSIX=1")
# target
add_library(_hdfs3 ${SRCS})
add_dependencies(_hdfs3 protoc)
target_compile_options(_hdfs3 PRIVATE
-include "${Datastore_SOURCE_DIR}/contrib/google-protobuf/src/google/protobuf/stubs/port.h"
)
if (ENABLE_DATASTORE_BENCHMARK)
message(STATUS "enable perf checksum")
target_include_directories(_hdfs3 PUBLIC ${HDFS3_SOURCE_DIR})
target_include_directories(_hdfs3 PUBLIC ${HDFS3_COMMON_DIR})
target_include_directories(_hdfs3 PUBLIC ${CMAKE_CURRENT_BINARY_DIR})
else ()
target_include_directories(_hdfs3 PRIVATE ${HDFS3_SOURCE_DIR})
target_include_directories(_hdfs3 PRIVATE ${HDFS3_COMMON_DIR})
target_include_directories(_hdfs3 PRIVATE ${CMAKE_CURRENT_BINARY_DIR})
endif ()
target_include_directories(_hdfs3 SYSTEM BEFORE INTERFACE "${Datastore_SOURCE_DIR}/contrib/libhdfs3/include")
target_link_libraries(_hdfs3 PRIVATE ch_contrib::gsasl)
if (WITH_KERBEROS)
target_link_libraries(_hdfs3 PRIVATE ch_contrib::krb5)
endif()
target_link_libraries(_hdfs3 PRIVATE ch_contrib::libxml2)
# inherit from parent cmake
target_link_libraries(_hdfs3 PRIVATE ch_contrib::protobuf boost::headers_only)
if (TARGET OpenSSL::SSL)
target_link_libraries(_hdfs3 PRIVATE OpenSSL::Crypto OpenSSL::SSL)
endif()
if (TARGET ch_contrib::isal)
target_link_libraries(_hdfs3 PRIVATE ch_contrib::isal)
add_definitions(-DHADOOP_ISAL_LIBRARY)
endif()
add_library(ch_contrib::hdfs ALIAS _hdfs3)
if (ENABLE_DATASTORE_BENCHMARK)
add_executable(perf_checksum ${HDFS3_SOURCE_DIR}/common/perf_checksum.cpp)
target_link_libraries(perf_checksum PRIVATE ch_contrib::hdfs)
endif ()