Merge pull request #67098 from ClickHouse/add-numactl

Try calculating available memory if ClickHouse is bound to subset of NUMA nodes

.gitmodules

@@ -372,3 +372,6 @@
 [submodule "contrib/double-conversion"]
 	path = contrib/double-conversion
 	url = https://github.com/ClickHouse/double-conversion.git
+[submodule "contrib/numactl"]
+	path = contrib/numactl
+	url = https://github.com/ClickHouse/numactl.git

base/base/CMakeLists.txt

@@ -32,6 +32,7 @@ set (SRCS
     StringRef.cpp
     safeExit.cpp
     throwError.cpp
+    Numa.cpp
 )
 
 add_library (common ${SRCS})
@@ -46,6 +47,10 @@ if (TARGET ch_contrib::crc32_s390x)
     target_link_libraries(common PUBLIC ch_contrib::crc32_s390x)
 endif()
 
+if (TARGET ch_contrib::numactl)
+    target_link_libraries(common PUBLIC ch_contrib::numactl)
+endif()
+
 target_include_directories(common PUBLIC .. "${CMAKE_CURRENT_BINARY_DIR}/..")
 
 target_link_libraries (common

base/base/Numa.cpp

@@ -0,0 +1,37 @@
+#include <base/Numa.h>
+
+#include "config.h"
+
+#if USE_NUMACTL
+#    include <numa.h>
+#endif
+
+namespace DB
+{
+
+std::optional<size_t> getNumaNodesTotalMemory()
+{
+    std::optional<size_t> total_memory;
+#if USE_NUMACTL
+    if (numa_available() != -1)
+    {
+        auto * membind = numa_get_membind();
+        if (!numa_bitmask_equal(membind, numa_all_nodes_ptr))
+        {
+            total_memory.emplace(0);
+            auto max_node = numa_max_node();
+            for (int i = 0; i <= max_node; ++i)
+            {
+                if (numa_bitmask_isbitset(membind, i))
+                    *total_memory += numa_node_size(i, nullptr);
+            }
+        }
+
+        numa_bitmask_free(membind);
+    }
+
+#endif
+    return total_memory;
+}
+
+}

base/base/Numa.h

@@ -0,0 +1,12 @@
+#pragma once
+
+#include <optional>
+
+namespace DB
+{
+
+/// return total memory of NUMA nodes the process is bound to
+/// if NUMA is not supported or process can use all nodes, std::nullopt is returned
+std::optional<size_t> getNumaNodesTotalMemory();
+
+}

base/base/getMemoryAmount.cpp

@@ -2,15 +2,14 @@
 
 #include <base/cgroupsv2.h>
 #include <base/getPageSize.h>
+#include <base/Numa.h>
 
 #include <fstream>
-#include <stdexcept>
 
 #include <unistd.h>
 #include <sys/types.h>
 #include <sys/param.h>
 
-
 namespace
 {
 
@@ -63,6 +62,9 @@ uint64_t getMemoryAmountOrZero()
 
     uint64_t memory_amount = num_pages * page_size;
 
+    if (auto total_numa_memory = DB::getNumaNodesTotalMemory(); total_numa_memory.has_value())
+        memory_amount = *total_numa_memory;
+
     /// Respect the memory limit set by cgroups v2.
     auto limit_v2 = getCgroupsV2MemoryLimit();
     if (limit_v2.has_value() && *limit_v2 < memory_amount)

contrib/CMakeLists.txt

@@ -230,6 +230,8 @@ add_contrib (libssh-cmake libssh)
 
 add_contrib (prometheus-protobufs-cmake prometheus-protobufs prometheus-protobufs-gogo)
 
+add_contrib(numactl-cmake numactl)
+
 # Put all targets defined here and in subdirectories under "contrib/<immediate-subdir>" folders in GUI-based IDEs.
 # Some of third-party projects may override CMAKE_FOLDER or FOLDER property of their targets, so they would not appear
 # in "contrib/..." as originally planned, so we workaround this by fixing FOLDER properties of all targets manually,

contrib/numactl

@@ -0,0 +1 @@
+Subproject commit 8d13d63a05f0c3cd88bf777cbb61541202b7da08

contrib/numactl-cmake/CMakeLists.txt

@@ -0,0 +1,30 @@
+if (NOT (
+    OS_LINUX AND (ARCH_AMD64 OR ARCH_AARCH64 OR ARCH_LOONGARCH64))
+)
+    if (ENABLE_NUMACTL)
+        message (${RECONFIGURE_MESSAGE_LEVEL}
+            "numactl is disabled implicitly because the OS or architecture is not supported. Use -DENABLE_NUMACTL=0")
+    endif ()
+    set (ENABLE_NUMACTL OFF)
+else()
+    option (ENABLE_NUMACTL "Enable numactl" ${ENABLE_LIBRARIES})
+endif()
+
+if (NOT ENABLE_NUMACTL)
+    message (STATUS "Not using numactl")
+    return()
+endif ()
+
+set (LIBRARY_DIR "${ClickHouse_SOURCE_DIR}/contrib/numactl")
+
+set (SRCS
+    "${LIBRARY_DIR}/libnuma.c"
+    "${LIBRARY_DIR}/syscall.c"
+)
+
+add_library(_numactl ${SRCS})
+
+target_include_directories(_numactl SYSTEM PRIVATE include)
+target_include_directories(_numactl SYSTEM PUBLIC "${LIBRARY_DIR}")
+
+add_library(ch_contrib::numactl ALIAS _numactl)

contrib/numactl-cmake/include/config.h

@@ -0,0 +1,82 @@
+/* config.h.  Generated from config.h.in by configure.  */
+/* config.h.in.  Generated from configure.ac by autoheader.  */
+
+/* Checking for symver attribute */
+#define HAVE_ATTRIBUTE_SYMVER 0
+
+/* Define to 1 if you have the <dlfcn.h> header file. */
+#define HAVE_DLFCN_H 1
+
+/* Define to 1 if you have the <inttypes.h> header file. */
+#define HAVE_INTTYPES_H 1
+
+/* Define to 1 if you have the <stdint.h> header file. */
+#define HAVE_STDINT_H 1
+
+/* Define to 1 if you have the <stdio.h> header file. */
+#define HAVE_STDIO_H 1
+
+/* Define to 1 if you have the <stdlib.h> header file. */
+#define HAVE_STDLIB_H 1
+
+/* Define to 1 if you have the <strings.h> header file. */
+#define HAVE_STRINGS_H 1
+
+/* Define to 1 if you have the <string.h> header file. */
+#define HAVE_STRING_H 1
+
+/* Define to 1 if you have the <sys/stat.h> header file. */
+#define HAVE_SYS_STAT_H 1
+
+/* Define to 1 if you have the <sys/types.h> header file. */
+#define HAVE_SYS_TYPES_H 1
+
+/* Define to 1 if you have the <unistd.h> header file. */
+#define HAVE_UNISTD_H 1
+
+/* Define to the sub-directory where libtool stores uninstalled libraries. */
+#define LT_OBJDIR ".libs/"
+
+/* Name of package */
+#define PACKAGE "numactl"
+
+/* Define to the address where bug reports for this package should be sent. */
+#define PACKAGE_BUGREPORT ""
+
+/* Define to the full name of this package. */
+#define PACKAGE_NAME "numactl"
+
+/* Define to the full name and version of this package. */
+#define PACKAGE_STRING "numactl 2.1"
+
+/* Define to the one symbol short name of this package. */
+#define PACKAGE_TARNAME "numactl"
+
+/* Define to the home page for this package. */
+#define PACKAGE_URL ""
+
+/* Define to the version of this package. */
+#define PACKAGE_VERSION "2.1"
+
+/* Define to 1 if all of the C89 standard headers exist (not just the ones
+   required in a freestanding environment). This macro is provided for
+   backward compatibility; new code need not use it. */
+#define STDC_HEADERS 1
+
+/* If the compiler supports a TLS storage class define it to that here */
+#define TLS __thread
+
+/* Version number of package */
+#define VERSION "2.1"
+
+/* Number of bits in a file offset, on hosts where this is settable. */
+/* #undef _FILE_OFFSET_BITS */
+
+/* Define to 1 on platforms where this makes off_t a 64-bit type. */
+/* #undef _LARGE_FILES */
+
+/* Number of bits in time_t, on hosts where this is settable. */
+/* #undef _TIME_BITS */
+
+/* Define to 1 on platforms where this makes time_t a 64-bit type. */
+/* #undef __MINGW_USE_VC2005_COMPAT */

docker/test/performance-comparison/run.sh

@@ -13,6 +13,7 @@ entry="/usr/share/clickhouse-test/performance/scripts/entrypoint.sh"
 # https://www.kernel.org/doc/Documentation/filesystems/tmpfs.txt
 # Double-escaped backslashes are a tribute to the engineering wonder of docker --
 # it gives '/bin/sh: 1: [bash,: not found' otherwise.
+numactl --hardware
 node=$(( RANDOM % $(numactl --hardware | sed -n 's/^.*available:\(.*\)nodes.*$/\1/p') ));
 echo Will bind to NUMA node $node;
 numactl --cpunodebind=$node --membind=$node $entry

programs/keeper/Keeper.cpp

@@ -19,6 +19,7 @@
 #include <base/getMemoryAmount.h>
 #include <base/scope_guard.h>
 #include <base/safeExit.h>
+#include <base/Numa.h>
 #include <Poco/Net/NetException.h>
 #include <Poco/Net/TCPServerParams.h>
 #include <Poco/Net/TCPServer.h>
@@ -311,6 +312,12 @@ try
 
     MainThreadStatus::getInstance();
 
+    if (auto total_numa_memory = getNumaNodesTotalMemory(); total_numa_memory.has_value())
+    {
+        LOG_INFO(
+            log, "Keeper is bound to a subset of NUMA nodes. Total memory of all available nodes: {}", ReadableSize(*total_numa_memory));
+    }
+
 #if !defined(NDEBUG) || !defined(__OPTIMIZE__)
     LOG_WARNING(log, "Keeper was built in debug mode. It will work slowly.");
 #endif

programs/server/Server.cpp

@@ -22,6 +22,7 @@
 #include <base/coverage.h>
 #include <base/getFQDNOrHostName.h>
 #include <base/safeExit.h>
+#include <base/Numa.h>
 #include <Common/PoolId.h>
 #include <Common/MemoryTracker.h>
 #include <Common/ClickHouseRevision.h>
@@ -140,6 +141,7 @@
 #   include <azure/core/diagnostics/logger.hpp>
 #endif
 
+
 #include <incbin.h>
 /// A minimal file used when the server is run without installation
 INCBIN(resource_embedded_xml, SOURCE_DIR "/programs/server/embedded.xml");
@@ -754,6 +756,12 @@ try
         setenv("OPENSSL_CONF", config_dir.c_str(), true); /// NOLINT
     }
 
+    if (auto total_numa_memory = getNumaNodesTotalMemory(); total_numa_memory.has_value())
+    {
+        LOG_INFO(
+            log, "ClickHouse is bound to a subset of NUMA nodes. Total memory of all available nodes: {}", ReadableSize(*total_numa_memory));
+    }
+
     registerInterpreters();
     registerFunctions();
     registerAggregateFunctions();

src/Common/config.h.in

@@ -64,6 +64,7 @@
 #cmakedefine01 USE_LIBARCHIVE
 #cmakedefine01 USE_POCKETFFT
 #cmakedefine01 USE_PROMETHEUS_PROTOBUFS
+#cmakedefine01 USE_NUMACTL
 
 /// This is needed for .incbin in assembly. For some reason, include paths don't work there in presence of LTO.
 /// That's why we use absolute paths.

src/configure_config.cmake

@@ -173,5 +173,8 @@ endif()
 if (TARGET ch_contrib::prometheus_protobufs)
     set(USE_PROMETHEUS_PROTOBUFS 1)
 endif()
+if (TARGET ch_contrib::numactl)
+    set(USE_NUMACTL 1)
+endif()
 
 set(SOURCE_DIR ${PROJECT_SOURCE_DIR})