现在多核处理器已经很普及了,市场主流是双核处理器,还有4核、8核等高端产品。而且Intel推广了超线程技术(Hyper-Threading Technology, HTT),可以将一个物理核心模拟为两个逻辑处理器。这一切使得“CPU数量”这一概念变得复杂起来,对于软件开发人员来说,希望能获得物理CPU数、CPU核心数、逻辑CPU数等详细信息。
在Windows平台,可以调用GetLogicalProcessorInformation函数来获取它们的详细信息。
一、背景知识
先来明确一下名词——
physical processor packages:物理处理器封装个数,即俗称的“物理CPU数”。例如一块“Intel Core i3-2310M”只有1个“物理处理器封装个数”。若对于有多个处理器插槽的服务器,“物理处理器封装个数”很可能会大于1。
processor cores:处理器核心数,即俗称的“CPU核心数”。例如“Intel Core i3-2310M”是双核处理器,它有2个“处理器核心数”。
logical processors:逻辑处理器数,即俗称的“逻辑CPU数”。例如“Intel Core i3-2310M”支持超线程,一个物理核心能模拟为两个逻辑处理器,即一块“Intel Core i3-2310M”有4个“逻辑处理器数”。
再来看看2个大家可能不太熟悉的名词——
SMP:Symmetrical Multi-Processing,对称多处理机。
NUMA:Non Uniform Memory Access,非均匀访存模型。http://msdn.microsoft.com/en-us/library/aa363804(v=vs.85).aspx
这个两个名词牵涉到很多专业知识,这里不做详细介绍,感兴趣的同学可以自行翻阅相关资料。
老版本的Windows系统(例如Windows XP)采用的是SMP模型。但后来因多核处理器及异构计算的发展,从Windows Server 2003开始使用NUMA模型,系统中支持多个NUMA节点。对于开发人员来说,当只有1个NUMA节点时,与SMP模型是差不多的。
对于 Windows XP,在打上SP3补丁后,也可以利用GetLogicalProcessorInformation函数获得NUMA等信息。
二、GetLogicalProcessorInformation函数的使用心得
在MSDN上我们可以查到GetLogicalProcessorInformation函数的帮助——
http://msdn.microsoft.com/en-us/library/ms683194(v=vs.85).aspx
GetLogicalProcessorInformation function
GetLogicalProcessorInformation函数还牵涉到一些结构体和枚举——
http://msdn.microsoft.com/en-us/library/ms686694(v=vs.85).aspx
SYSTEM_LOGICAL_PROCESSOR_INFORMATION structure
http://msdn.microsoft.com/en-us/library/ms684197(v=vs.85).aspx
LOGICAL_PROCESSOR_RELATIONSHIP enumeration
http://msdn.microsoft.com/en-us/library/ms681979(v=vs.85).aspx
CACHE_DESCRIPTOR structure
http://msdn.microsoft.com/en-us/library/ms684844(v=vs.85).aspx
PROCESSOR_CACHE_TYPE enumeration
GetLogicalProcessorInformation函数用起来是有一定复杂性的。因为它返回的是SYSTEM_LOGICAL_PROCESSOR_INFORMATION数组,数组中的每一项分别描述了不同的信息,学习曲线较陡峭。
虽然MSDN上有该函数的范例代码,但是它屏蔽了很多细节,对我们的帮助有限。于是我将该范例程序作了改进,显示了SYSTEM_LOGICAL_PROCESSOR_INFORMATION数组中每一项的详细信息。
心得——
1.SYSTEM_LOGICAL_PROCESSOR_INFORMATION结构ProcessorMask是ULONG_PTR类型的。在32位系统上是32位,64位系统上是64位。为了简化代码,建议强制转型为UINT64类型,调用printf等输出函数时使用“I64”格式码。
2.ProcessorMask是处理器掩码,每一位代表一个逻辑处理器。所以一般来说,32位系统最多支持32个逻辑处理器,64位系统最多支持64个逻辑处理器。
3.对于Windows 7和Windows Server 2008 R2来说,能突破64个逻辑处理器限制,最高支持256个逻辑处理器。新加了 处理器组(Processor Groups)概念,详见:http://msdn.microsoft.com/en-us/library/dd405503(v=vs.85).aspx。
三、全部代码
全部代码——
- #include <windows.h>
- #include <malloc.h>
- #include <stdio.h>
- #include <tchar.h>
-
- #if (_WIN32_WINNT < 0x0600) // [zyl910] 低版本的Windows SDK没有定义 RelationProcessorPackage 等常量
- #define RelationProcessorPackage 3
- #define RelationGroup 4
- #endif
- const LPTSTR Names_LOGICAL_PROCESSOR_RELATIONSHIP[] = {
- _T("RelationProcessorCore")
- ,_T("RelationNumaNode")
- ,_T("RelationCache")
- ,_T("RelationProcessorPackage")
- ,_T("RelationGroup")
- };
- const LPTSTR Names_PROCESSOR_CACHE_TYPE[] = {
- _T("CacheUnified")
- ,_T("CacheInstruction")
- ,_T("CacheData")
- ,_T("CacheTrace")
- };
-
- typedef BOOL (WINAPI *LPFN_GLPI)(
- PSYSTEM_LOGICAL_PROCESSOR_INFORMATION,
- PDWORD);
-
-
- DWORD CountSetBits(ULONG_PTR bitMask)
- {
- DWORD LSHIFT = sizeof(ULONG_PTR)*8 - 1;
- DWORD bitSetCount = 0;
- ULONG_PTR bitTest = (ULONG_PTR)1 << LSHIFT;
- DWORD i;
-
- for (i = 0; i <= LSHIFT; ++i)
- {
- bitSetCount += ((bitMask & bitTest)?1:0);
- bitTest/=2;
- }
-
- return bitSetCount;
- }
-
- int _cdecl _tmain ()
- {
- LPFN_GLPI glpi;
- BOOL done = FALSE;
- PSYSTEM_LOGICAL_PROCESSOR_INFORMATION buffer = NULL;
- PSYSTEM_LOGICAL_PROCESSOR_INFORMATION ptr = NULL;
- DWORD returnLength = 0;
- DWORD logicalProcessorCount = 0;
- DWORD numaNodeCount = 0;
- DWORD processorCoreCount = 0;
- DWORD processorL1CacheCount = 0;
- DWORD processorL2CacheCount = 0;
- DWORD processorL3CacheCount = 0;
- DWORD processorPackageCount = 0;
- DWORD byteOffset = 0;
- PCACHE_DESCRIPTOR Cache;
-
- glpi = (LPFN_GLPI) GetProcAddress(
- GetModuleHandle(TEXT("kernel32")),
- "GetLogicalProcessorInformation");
- if (NULL == glpi)
- {
- _tprintf(TEXT("\nGetLogicalProcessorInformation is not supported.\n"));
- return (1);
- }
-
- while (!done)
- {
- DWORD rc = glpi(buffer, &returnLength);
-
- if (FALSE == rc)
- {
- if (GetLastError() == ERROR_INSUFFICIENT_BUFFER)
- {
- if (buffer)
- free(buffer);
-
- buffer = (PSYSTEM_LOGICAL_PROCESSOR_INFORMATION)malloc(
- returnLength);
-
- if (NULL == buffer)
- {
- _tprintf(TEXT("\nError: Allocation failure\n"));
- return (2);
- }
- }
- else
- {
- _tprintf(TEXT("\nError %d\n"), GetLastError());
- return (3);
- }
- }
- else
- {
- done = TRUE;
- }
- }
-
- ptr = buffer;
-
- if (true)
- {
- DWORD cnt = returnLength / sizeof(SYSTEM_LOGICAL_PROCESSOR_INFORMATION);
- for(DWORD i=0; i<cnt; ++i)
- {
- _tprintf(TEXT("SYSTEM_LOGICAL_PROCESSOR_INFORMATION[%d]\n"), i);
- _tprintf(TEXT("\t.ProcessorMask:\t0x%.16I64X\t//%I64d\n"), (UINT64)ptr[i].ProcessorMask, (UINT64)ptr[i].ProcessorMask);
- _tprintf(TEXT("\t.Relationship:\t%d\t//%s\n"), ptr[i].Relationship, Names_LOGICAL_PROCESSOR_RELATIONSHIP[max(0,min(ptr[i].Relationship, RelationGroup))]);
- for(int j=0; j<2; ++j) _tprintf(TEXT("\t.Reserved[%d]:\t//0x%.16I64X\t%I64d\n"), j, (UINT64)ptr[i].Reserved[j], (UINT64)ptr[i].Reserved[j]);
- if (RelationCache==ptr[i].Relationship)
- {
- _tprintf(TEXT("\t.Cache.Level:\t%u\n"), ptr[i].Cache.Level);
- _tprintf(TEXT("\t.Cache.Associativity:\t0x%.2X\t//%u\n"), ptr[i].Cache.Associativity, ptr[i].Cache.Associativity);
- _tprintf(TEXT("\t.Cache.LineSize:\t0x%.4X\t//%u\n"), ptr[i].Cache.LineSize, ptr[i].Cache.LineSize);
- _tprintf(TEXT("\t.Cache.Size:\t0x%.8X\t//%u\n"), ptr[i].Cache.Size, ptr[i].Cache.Size);
- _tprintf(TEXT("\t.Cache.Type:\t%d\t//%s\n"), ptr[i].Cache.Type, Names_PROCESSOR_CACHE_TYPE[max(0,min(ptr[i].Cache.Type, CacheTrace))]);
- }
- }
- }
-
- while (byteOffset + sizeof(SYSTEM_LOGICAL_PROCESSOR_INFORMATION) <= returnLength)
- {
- switch (ptr->Relationship)
- {
- case RelationNumaNode:
-
- numaNodeCount++;
- break;
-
- case RelationProcessorCore:
- processorCoreCount++;
-
-
- logicalProcessorCount += CountSetBits(ptr->ProcessorMask);
- break;
-
- case RelationCache:
-
- Cache = &ptr->Cache;
- if (Cache->Level == 1)
- {
- processorL1CacheCount++;
- }
- else if (Cache->Level == 2)
- {
- processorL2CacheCount++;
- }
- else if (Cache->Level == 3)
- {
- processorL3CacheCount++;
- }
- break;
-
- case RelationProcessorPackage:
-
- processorPackageCount++;
- break;
-
- default:
- _tprintf(TEXT("\nError: Unsupported LOGICAL_PROCESSOR_RELATIONSHIP value.\n"));
- break;
- }
- byteOffset += sizeof(SYSTEM_LOGICAL_PROCESSOR_INFORMATION);
- ptr++;
- }
-
- _tprintf(TEXT("\nGetLogicalProcessorInformation results:\n"));
- _tprintf(TEXT("Number of NUMA nodes: %d\n"),
- numaNodeCount);
- _tprintf(TEXT("Number of physical processor packages: %d\n"),
- processorPackageCount);
- _tprintf(TEXT("Number of processor cores: %d\n"),
- processorCoreCount);
- _tprintf(TEXT("Number of logical processors: %d\n"),
- logicalProcessorCount);
- _tprintf(TEXT("Number of processor L1/L2/L3 caches: %d/%d/%d\n"),
- processorL1CacheCount,
- processorL2CacheCount,
- processorL3CacheCount);
-
- free(buffer);
-
- return 0;
- }
四、输出信息
例如我的处理器是“Intel Core i3-2310M”,该程序的输出信息为——
- SYSTEM_LOGICAL_PROCESSOR_INFORMATION[0]
- .ProcessorMask: 0x0000000000000005 //5
- .Relationship: 0 //RelationProcessorCore
- .Reserved[0]: //0x0000000000000001 1
- .Reserved[1]: //0x0000000000000000 0
- SYSTEM_LOGICAL_PROCESSOR_INFORMATION[1]
- .ProcessorMask: 0x0000000000000005 //5
- .Relationship: 2 //RelationCache
- .Reserved[0]: //0x0000800000400801 140737492551681
- .Reserved[1]: //0x0000000000000002 2
- .Cache.Level: 1
- .Cache.Associativity: 0x08 //8
- .Cache.LineSize: 0x0040 //64
- .Cache.Size: 0x00008000 //32768
- .Cache.Type: 2 //CacheData
- SYSTEM_LOGICAL_PROCESSOR_INFORMATION[2]
- .ProcessorMask: 0x0000000000000005 //5
- .Relationship: 2 //RelationCache
- .Reserved[0]: //0x0000800000400801 140737492551681
- .Reserved[1]: //0x0000000000000001 1
- .Cache.Level: 1
- .Cache.Associativity: 0x08 //8
- .Cache.LineSize: 0x0040 //64
- .Cache.Size: 0x00008000 //32768
- .Cache.Type: 1 //CacheInstruction
- SYSTEM_LOGICAL_PROCESSOR_INFORMATION[3]
- .ProcessorMask: 0x0000000000000005 //5
- .Relationship: 2 //RelationCache
- .Reserved[0]: //0x0004000000400802 1125899911038978
- .Reserved[1]: //0x0000000000000000 0
- .Cache.Level: 2
- .Cache.Associativity: 0x08 //8
- .Cache.LineSize: 0x0040 //64
- .Cache.Size: 0x00040000 //262144
- .Cache.Type: 0 //CacheUnified
- SYSTEM_LOGICAL_PROCESSOR_INFORMATION[4]
- .ProcessorMask: 0x000000000000000F //15
- .Relationship: 3 //RelationProcessorPackage
- .Reserved[0]: //0x0000000000000000 0
- .Reserved[1]: //0x0000000000000000 0
- SYSTEM_LOGICAL_PROCESSOR_INFORMATION[5]
- .ProcessorMask: 0x000000000000000A //10
- .Relationship: 0 //RelationProcessorCore
- .Reserved[0]: //0x0000000000000001 1
- .Reserved[1]: //0x0000000000000000 0
- SYSTEM_LOGICAL_PROCESSOR_INFORMATION[6]
- .ProcessorMask: 0x000000000000000A //10
- .Relationship: 2 //RelationCache
- .Reserved[0]: //0x0000800000400801 140737492551681
- .Reserved[1]: //0x0000000000000002 2
- .Cache.Level: 1
- .Cache.Associativity: 0x08 //8
- .Cache.LineSize: 0x0040 //64
- .Cache.Size: 0x00008000 //32768
- .Cache.Type: 2 //CacheData
- SYSTEM_LOGICAL_PROCESSOR_INFORMATION[7]
- .ProcessorMask: 0x000000000000000A //10
- .Relationship: 2 //RelationCache
- .Reserved[0]: //0x0000800000400801 140737492551681
- .Reserved[1]: //0x0000000000000001 1
- .Cache.Level: 1
- .Cache.Associativity: 0x08 //8
- .Cache.LineSize: 0x0040 //64
- .Cache.Size: 0x00008000 //32768
- .Cache.Type: 1 //CacheInstruction
- SYSTEM_LOGICAL_PROCESSOR_INFORMATION[8]
- .ProcessorMask: 0x000000000000000A //10
- .Relationship: 2 //RelationCache
- .Reserved[0]: //0x0004000000400802 1125899911038978
- .Reserved[1]: //0x0000000000000000 0
- .Cache.Level: 2
- .Cache.Associativity: 0x08 //8
- .Cache.LineSize: 0x0040 //64
- .Cache.Size: 0x00040000 //262144
- .Cache.Type: 0 //CacheUnified
- SYSTEM_LOGICAL_PROCESSOR_INFORMATION[9]
- .ProcessorMask: 0x000000000000000F //15
- .Relationship: 2 //RelationCache
- .Reserved[0]: //0x0030000000400C03 13510798886308867
- .Reserved[1]: //0x0000000000000000 0
- .Cache.Level: 3
- .Cache.Associativity: 0x0C //12
- .Cache.LineSize: 0x0040 //64
- .Cache.Size: 0x00300000 //3145728
- .Cache.Type: 0 //CacheUnified
- SYSTEM_LOGICAL_PROCESSOR_INFORMATION[10]
- .ProcessorMask: 0x000000000000000F //15
- .Relationship: 1 //RelationNumaNode
- .Reserved[0]: //0x0000000000000000 0
- .Reserved[1]: //0x0000000000000000 0
-
- GetLogicalProcessorInformation results:
- Number of NUMA nodes: 1
- Number of physical processor packages: 1
- Number of processor cores: 2
- Number of logical processors: 4
- Number of processor L1/L2/L3 caches: 4/2/1