linux - 如果在小区域发出请求，NVME SSD 上的随机读取 IOPS 会减少

Question

(TL;DR) 在 NVME SSD(Intel p3600 和 Avant)上，如果我对磁盘的一小部分而不是整个磁盘发出随机读取，我会看到 IOPS 降低。

虽然一遍又一遍地读取相同的偏移量，但对于 4k block 大小，IOPS 约为 36-40K。随着发出随机读取的区域的扩大，IOPS 逐渐增加。该程序(如下所示)在 Linux 上使用异步 IO 来提交读取请求。

Disk Range(in 4k blocks), IOPS 
0, 38833 
1, 68596 
10, 76100 
30, 80381 
40, 113647 
50, 148205 
100, 170374 
200, 239798 
400, 270197 
800, 334767

操作系统:Linux 4.2.0-35-generic

固态硬盘:英特尔 P3600 NVME 闪存

是什么导致了这个问题？

程序可以运行如下

$ for i in 0 1 10 30 40 50 100 200 400 800
do 
<program_name> /dev/nvme0n1 10 $i 
done

并验证您是否也看到上面看到的 IOPS 的增加模式

   /**
 * $ g++ <progname.cpp> -o progname -std=c++11 -lpthread -laio -O3
 * $ progname /dev/nvme0n1 10 100
 */
#include <random>
#include <libaio.h>
#include <stdlib.h>//malloc, exit
#include <future> //async
#include <unistd.h> //usleep
#include <iostream>
#include <sys/time.h> // gettimeofday
#include <vector>
#include <fcntl.h> // open
#include <errno.h>
#include <sys/types.h> // open
#include <sys/stat.h> // open
#include <cassert>
#include <semaphore.h>

io_context_t ioctx;
std::vector<char*> buffers;
int fd = -1;
sem_t sem;

constexpr int numPerRound = 20;
constexpr int numRounds  = 100000;

constexpr int MAXEVENT = 10;
constexpr size_t BLKSIZE = 4096;
constexpr int QDEPTH = 200;

off_t startBlock = 0;
off_t numBlocks = 100;

const int numSubmitted = numRounds * numPerRound;

void DoGet()
{
  io_event eventsArray[MAXEVENT];
  int numCompleted = 0;
  while (numCompleted != numSubmitted)
  {
    bzero(eventsArray, MAXEVENT * sizeof(io_event));
    int numEvents;
    do {
      numEvents = io_getevents(ioctx, 1, MAXEVENT, eventsArray, nullptr);
    } while (numEvents == -EINTR);

    for (int i = 0; i < numEvents; i++)
    {
      io_event* ev = &eventsArray[i];
      iocb* cb = (iocb*)(ev->data);
      assert(ev->res2 == 0);
      assert(ev->res == BLKSIZE);
      sem_post(&sem); // free ioctx
    }
    numCompleted += numEvents;
  }
  std::cout << "completed=" << numCompleted << std::endl;
}


int main(int argc, char* argv[])
{
  if (argc == 1) {
    std::cout << "usage <nvme_device_name> <start_4k_block> <num_4k_blocks>" << std::endl;
    exit(1);
  }

  char* deviceName = argv[1];
  startBlock = atoll(argv[2]);
  numBlocks = atoll(argv[3]);

  int ret = 0;
  ret = io_queue_init(QDEPTH, &ioctx);
  assert(ret == 0);
  ret = sem_init(&sem, 0, QDEPTH);
 assert(ret == 0);

  auto DoGetFut = std::async(std::launch::async, DoGet);

  // preallocate buffers
  for (int i = 0; i < QDEPTH; i++)
  {
    char* buf ;
    ret = posix_memalign((void**)&buf, 4096, BLKSIZE);
    assert(ret == 0);
    buffers.push_back(buf);
  }

  fd = open("/dev/nvme0n1", O_DIRECT | O_RDONLY);
  assert(fd >= 0);

  off_t offset = 0;

  struct timeval start;
  gettimeofday(&start, 0);

  std::mt19937 generator (getpid());
  // generate random offsets within [startBlock, startBlock + numBlocks]
  std::uniform_int_distribution<off_t> offsetgen(startBlock, startBlock + numBlocks);

  for (int j = 0; j < numRounds; j++)
  {
    iocb mycb[numPerRound];
    iocb* posted[numPerRound];

    bzero(mycb, sizeof(iocb) * numPerRound);

    for (int i = 0; i < numPerRound; i++)
    {
      // same buffer may get used in 2 different async read
      // thats ok - not validating content in this program
      char* iobuf = buffers[i];
      iocb* cb = &mycb[i];

       offset = offsetgen(generator) * BLKSIZE;

      io_prep_pread(cb, fd, iobuf, BLKSIZE, offset);
      cb->data = iobuf;
      posted[i] = cb;
      sem_wait(&sem); // wait for ioctx to be free
    }

    int ret = 0;
    do {
      ret = io_submit(ioctx, numPerRound, posted);
    } while (ret == -EINTR);

    assert(ret == numPerRound);
  }

  DoGetFut.wait();

  struct timeval end;
  gettimeofday(&end, 0);

  uint64_t diff = ((end.tv_sec - start.tv_sec) * 1000000) + (end.tv_usec - start.tv_usec);

  io_queue_release(ioctx);

  std::cout
    << "ops=" << numRounds * numPerRound
    << " iops=" << (numRounds * numPerRound *(uint64_t)1000000)/diff
    << " region-size=" << (numBlocks * BLKSIZE)
    << std::endl;
}

Answer 1

肯定是跟内存的结构有关。在内部，此驱动器由许多内存芯片构成，内部可能有多个内存总线。如果您在小范围内发出请求，所有请求都将解析为一个或几个筹码，并且必须排队。如果您访问整个设备，那么多个请求将跨越许多内部芯片和总线，并且可以异步运行，因此将提供更高的吞吐量。