我们最近购买了一些新服务器,memcpy的性能很差.与笔记本电脑相比,memcpy在服务器上的性能要慢3倍.
Server Specs个
- 底盘和Mobo:SUPER MICRO 1027GR-TRF
- CPU:2个Intel Xeon E5-2680@2.70 GHz
- 内存:8x 16 GB DDR3 1600 MHz
编辑:我还在另一台规格稍高的服务器上进行测试,结果与上述服务器相同
Server 2 Specs个
- 底盘和摩拜:超微10227GR-TRFT
- CPU:2个Intel Xeon E5-2650 v2@2.6 GHz
- 内存:8x 16 GB DDR3 1866 MHz
Laptop Specs个
- 底盘:联想W530
- CPU:1x Intel Core i7 i7-3720QM@2.6Ghz
- 内存:4x 4GB DDR3 1600MHz
Operating System
$ cat /etc/redhat-release
Scientific Linux release 6.5 (Carbon)
$ uname -a
Linux r113 2.6.32-431.1.2.el6.x86_64 #1 SMP Thu Dec 12 13:59:19 CST 2013 x86_64 x86_64 x86_64 GNU/Linux
Compiler (on all systems)个
$ gcc --version
gcc (GCC) 4.6.1
根据@stefan的建议,还使用GCC 4.8.2进行了测试.编译器之间没有性能差异.
Test Code
#include <chrono>
#include <cstring>
#include <iostream>
#include <cstdint>
class Timer
{
public:
Timer()
: mStart(),
mStop()
{
update();
}
void update()
{
mStart = std::chrono::high_resolution_clock::now();
mStop = mStart;
}
double elapsedMs()
{
mStop = std::chrono::high_resolution_clock::now();
std::chrono::milliseconds elapsed_ms =
std::chrono::duration_cast<std::chrono::milliseconds>(mStop - mStart);
return elapsed_ms.count();
}
private:
std::chrono::high_resolution_clock::time_point mStart;
std::chrono::high_resolution_clock::time_point mStop;
};
std::string formatBytes(std::uint64_t bytes)
{
static const int num_suffix = 5;
static const char* suffix[num_suffix] = { "B", "KB", "MB", "GB", "TB" };
double dbl_s_byte = bytes;
int i = 0;
for (; (int)(bytes / 1024.) > 0 && i < num_suffix;
++i, bytes /= 1024.)
{
dbl_s_byte = bytes / 1024.0;
}
const int buf_len = 64;
char buf[buf_len];
// use snprintf so there is no buffer overrun
int res = snprintf(buf, buf_len,"%0.2f%s", dbl_s_byte, suffix[i]);
// snprintf returns number of characters that would have been written if n had
// been sufficiently large, not counting the terminating null character.
// if an encoding error occurs, a negative number is returned.
if (res >= 0)
{
return std::string(buf);
}
return std::string();
}
void doMemmove(void* pDest, const void* pSource, std::size_t sizeBytes)
{
memmove(pDest, pSource, sizeBytes);
}
int main(int argc, char* argv[])
{
std::uint64_t SIZE_BYTES = 1073741824; // 1GB
if (argc > 1)
{
SIZE_BYTES = std::stoull(argv[1]);
std::cout << "Using buffer size from command line: " << formatBytes(SIZE_BYTES)
<< std::endl;
}
else
{
std::cout << "To specify a custom buffer size: big_memcpy_test [SIZE_BYTES] \n"
<< "Using built in buffer size: " << formatBytes(SIZE_BYTES)
<< std::endl;
}
// big array to use for testing
char* p_big_array = NULL;
/////////////
// malloc
{
Timer timer;
p_big_array = (char*)malloc(SIZE_BYTES * sizeof(char));
if (p_big_array == NULL)
{
std::cerr << "ERROR: malloc of " << SIZE_BYTES << " returned NULL!"
<< std::endl;
return 1;
}
std::cout << "malloc for " << formatBytes(SIZE_BYTES) << " took "
<< timer.elapsedMs() << "ms"
<< std::endl;
}
/////////////
// memset
{
Timer timer;
// set all data in p_big_array to 0
memset(p_big_array, 0xF, SIZE_BYTES * sizeof(char));
double elapsed_ms = timer.elapsedMs();
std::cout << "memset for " << formatBytes(SIZE_BYTES) << " took "
<< elapsed_ms << "ms "
<< "(" << formatBytes(SIZE_BYTES / (elapsed_ms / 1.0e3)) << " bytes/sec)"
<< std::endl;
}
/////////////
// memcpy
{
char* p_dest_array = (char*)malloc(SIZE_BYTES);
if (p_dest_array == NULL)
{
std::cerr << "ERROR: malloc of " << SIZE_BYTES << " for memcpy test"
<< " returned NULL!"
<< std::endl;
return 1;
}
memset(p_dest_array, 0xF, SIZE_BYTES * sizeof(char));
// time only the memcpy FROM p_big_array TO p_dest_array
Timer timer;
memcpy(p_dest_array, p_big_array, SIZE_BYTES * sizeof(char));
double elapsed_ms = timer.elapsedMs();
std::cout << "memcpy for " << formatBytes(SIZE_BYTES) << " took "
<< elapsed_ms << "ms "
<< "(" << formatBytes(SIZE_BYTES / (elapsed_ms / 1.0e3)) << " bytes/sec)"
<< std::endl;
// cleanup p_dest_array
free(p_dest_array);
p_dest_array = NULL;
}
/////////////
// memmove
{
char* p_dest_array = (char*)malloc(SIZE_BYTES);
if (p_dest_array == NULL)
{
std::cerr << "ERROR: malloc of " << SIZE_BYTES << " for memmove test"
<< " returned NULL!"
<< std::endl;
return 1;
}
memset(p_dest_array, 0xF, SIZE_BYTES * sizeof(char));
// time only the memmove FROM p_big_array TO p_dest_array
Timer timer;
// memmove(p_dest_array, p_big_array, SIZE_BYTES * sizeof(char));
doMemmove(p_dest_array, p_big_array, SIZE_BYTES * sizeof(char));
double elapsed_ms = timer.elapsedMs();
std::cout << "memmove for " << formatBytes(SIZE_BYTES) << " took "
<< elapsed_ms << "ms "
<< "(" << formatBytes(SIZE_BYTES / (elapsed_ms / 1.0e3)) << " bytes/sec)"
<< std::endl;
// cleanup p_dest_array
free(p_dest_array);
p_dest_array = NULL;
}
// cleanup
free(p_big_array);
p_big_array = NULL;
return 0;
}
CMake File to Build个
project(big_memcpy_test)
cmake_minimum_required(VERSION 2.4.0)
include_directories(${CMAKE_CURRENT_SOURCE_DIR})
# create verbose makefiles that show each command line as it is issued
set( CMAKE_VERBOSE_MAKEFILE ON CACHE BOOL "Verbose" FORCE )
# release mode
set( CMAKE_BUILD_TYPE Release )
# grab in CXXFLAGS environment variable and append C++11 and -Wall options
set( CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -std=c++0x -Wall -march=native -mtune=native" )
message( INFO "CMAKE_CXX_FLAGS = ${CMAKE_CXX_FLAGS}" )
# sources to build
set(big_memcpy_test_SRCS
main.cpp
)
# create an executable file named "big_memcpy_test" from
# the source files in the variable "big_memcpy_test_SRCS".
add_executable(big_memcpy_test ${big_memcpy_test_SRCS})
Test Results
Buffer Size: 1GB | malloc (ms) | memset (ms) | memcpy (ms) | NUMA nodes (numactl --hardware)
---------------------------------------------------------------------------------------------
Laptop 1 | 0 | 127 | 113 | 1
Laptop 2 | 0 | 180 | 120 | 1
Server 1 | 0 | 306 | 301 | 2
Server 2 | 0 | 352 | 325 | 2
正如你所看到的,我们服务器上的memcpys和memset比笔记本电脑上的memcpys和memset慢得多.
Varying buffer sizes
我试过100MB到5 GB的缓冲区,结果都差不多(服务器比笔记本电脑慢)
NUMA Affinity个
我读到有人在使用NUMA时遇到性能问题,所以我try 使用numactl设置CPU和内存关联,但结果仍然相同.
服务器NUMA硬件
$ numactl --hardware
available: 2 nodes (0-1)
node 0 cpus: 0 1 2 3 4 5 6 7 16 17 18 19 20 21 22 23
node 0 size: 65501 MB
node 0 free: 62608 MB
node 1 cpus: 8 9 10 11 12 13 14 15 24 25 26 27 28 29 30 31
node 1 size: 65536 MB
node 1 free: 63837 MB
node distances:
node 0 1
0: 10 21
1: 21 10
笔记本电脑NUMA硬件
$ numactl --hardware
available: 1 nodes (0)
node 0 cpus: 0 1 2 3 4 5 6 7
node 0 size: 16018 MB
node 0 free: 6622 MB
node distances:
node 0
0: 10
设置NUMA关联性
$ numactl --cpunodebind=0 --membind=0 ./big_memcpy_test
非常感谢您对解决此问题的任何帮助.
Edit: GCC Options
根据我try 使用不同GCC选项编译的 comments :
在将-march和-mtune设置为native的情况下编译
g++ -std=c++0x -Wall -march=native -mtune=native -O3 -DNDEBUG -o big_memcpy_test main.cpp
结果:性能完全相同(没有改进)
使用-O2而不是-O3编译
g++ -std=c++0x -Wall -march=native -mtune=native -O2 -DNDEBUG -o big_memcpy_test main.cpp
结果:性能完全相同(没有改进)
Edit: Changed memset to write 0xF instead of 0 to avoid NULL page (@SteveCox)
当memsetting的值不是0(在本例中使用0xF)时,没有任何改进.
Edit: Cachebench results
为了避免我的测试程序过于简单,我下载了一个真正的基准测试程序LLCacheBench(http://icl.cs.utk.edu/projects/llcbench/cachebench.html)
为了避免架构问题,我分别在每台机器上构建了基准测试.下面是我的结果.
请注意,非常大的差异在于缓冲区大小较大时的性能.最后测试的大小(16777216)在笔记本电脑上以18849.29 MB/秒的速度执行,在服务器上以6710.40 MB/秒的速度执行.这大约是性能上的3倍之差.您还可以注意到,服务器的性能下降比笔记本电脑大得多.
Edit: memmove() is 2x FASTER than memcpy() on the server
基于一些实验,我try 在测试用例中使用memmove()而不是memcpy(),并发现服务器性能提高了2倍.笔记本电脑上的Memmove()运行速度比memcpy()慢,但奇怪的是,它与服务器上的Memmove()运行速度相当.这就引出了一个问题:为什么memcpy这么慢?
更新了测试memmove和memcpy的代码.我必须将memmove()封装在一个函数中,因为如果我让它内联,GCC会对它进行优化,并执行与memcpy()完全相同的操作(我假设GCC会将它优化为memcpy,因为它知道位置不会重叠).
更新的结果
Buffer Size: 1GB | malloc (ms) | memset (ms) | memcpy (ms) | memmove() | NUMA nodes (numactl --hardware)
---------------------------------------------------------------------------------------------------------
Laptop 1 | 0 | 127 | 113 | 161 | 1
Laptop 2 | 0 | 180 | 120 | 160 | 1
Server 1 | 0 | 306 | 301 | 159 | 2
Server 2 | 0 | 352 | 325 | 159 | 2
Edit: Naive Memcpy
根据@salgar的建议,我实现了自己的天真memcpy函数并对其进行了测试.
朴素的记忆来源
void naiveMemcpy(void* pDest, const void* pSource, std::size_t sizeBytes)
{
char* p_dest = (char*)pDest;
const char* p_source = (const char*)pSource;
for (std::size_t i = 0; i < sizeBytes; ++i)
{
*p_dest++ = *p_source++;
}
}
简单的memcpy结果与memcpy()的比较
Buffer Size: 1GB | memcpy (ms) | memmove(ms) | naiveMemcpy()
------------------------------------------------------------
Laptop 1 | 113 | 161 | 160
Server 1 | 301 | 159 | 159
Server 2 | 325 | 159 | 159
Edit: Assembly Output
简单memcpy源
#include <cstring>
#include <cstdlib>
int main(int argc, char* argv[])
{
size_t SIZE_BYTES = 1073741824; // 1GB
char* p_big_array = (char*)malloc(SIZE_BYTES * sizeof(char));
char* p_dest_array = (char*)malloc(SIZE_BYTES * sizeof(char));
memset(p_big_array, 0xA, SIZE_BYTES * sizeof(char));
memset(p_dest_array, 0xF, SIZE_BYTES * sizeof(char));
memcpy(p_dest_array, p_big_array, SIZE_BYTES * sizeof(char));
free(p_dest_array);
free(p_big_array);
return 0;
}
汇编输出:这在服务器和笔记本电脑上都是完全相同的.我是在节省空间,而不是两个都粘贴.
.file "main_memcpy.cpp"
.section .text.startup,"ax",@progbits
.p2align 4,,15
.globl main
.type main, @function
main:
.LFB25:
.cfi_startproc
pushq %rbp
.cfi_def_cfa_offset 16
.cfi_offset 6, -16
movl $1073741824, %edi
pushq %rbx
.cfi_def_cfa_offset 24
.cfi_offset 3, -24
subq $8, %rsp
.cfi_def_cfa_offset 32
call malloc
movl $1073741824, %edi
movq %rax, %rbx
call malloc
movl $1073741824, %edx
movq %rax, %rbp
movl $10, %esi
movq %rbx, %rdi
call memset
movl $1073741824, %edx
movl $15, %esi
movq %rbp, %rdi
call memset
movl $1073741824, %edx
movq %rbx, %rsi
movq %rbp, %rdi
call memcpy
movq %rbp, %rdi
call free
movq %rbx, %rdi
call free
addq $8, %rsp
.cfi_def_cfa_offset 24
xorl %eax, %eax
popq %rbx
.cfi_def_cfa_offset 16
popq %rbp
.cfi_def_cfa_offset 8
ret
.cfi_endproc
.LFE25:
.size main, .-main
.ident "GCC: (GNU) 4.6.1"
.section .note.GNU-stack,"",@progbits
PROGRESS!!!! asmlib
根据@tbenson的建议,我试着用asmlib版的memcpy运行.我的结果最初很差,但是在把StEnMcPyCaseLimeId()更改为1GB(我的缓冲区的大小)之后,我的运行速度与我的幼稚循环速度相当.
坏消息是,asmlib版本的memmove比glibc版本慢,它现在的运行速度是300ms(与glibc版本的memcpy持平).奇怪的是,在笔记本电脑上,当我将MemcpyCacheLimit()设置为大量时,会影响性能……
在下面的结果中,标有SetCache的行将SetMemcpyCacheLimit设置为1073741824.没有SetCache的结果不会调用SetMemcpyCacheLimit()
使用asmlib函数的结果:
Buffer Size: 1GB | memcpy (ms) | memmove(ms) | naiveMemcpy()
------------------------------------------------------------
Laptop | 136 | 132 | 161
Laptop SetCache | 182 | 137 | 161
Server 1 | 305 | 302 | 164
Server 1 SetCache | 162 | 303 | 164
Server 2 | 300 | 299 | 166
Server 2 SetCache | 166 | 301 | 166
开始倾向于缓存问题,但这是什么原因呢?