aio_write比ext4上的普通写入花费更多时间？(aio_write takes more time than plain write on ext4?)

 我有一个C程序，它编写32768个块，每个块大小为16K（总大小为512MB），运行3.18.1内核的系统上的ext4文件系统。 该程序的常规写入系统调用版本需要5.35秒来完成写入（由for循环之前和之后的gettimeofday测量）。 然而，该程序的async io版本需要以下时间： 
 
 
 
 排队所有aio_writes（32768 aio_writes）：7.43秒 
 
 
 轮询完成每个IO请求：额外4.93秒 
 
 
 使用以下标志打开输出文件：O_WRONLY，O_CREAT，O_NONBLOCK 
 
 为什么异步io占用write（）时间的两倍以上？ 甚至时间到队列 - 异步 - 请求/时间 - 写 - 同步 - io是1.4。 
 
 由于有些人将其标记为偏离主题，我查看了定义并决定粘贴代码 - 这似乎是它应该被标记为主题的唯一原因。 我不是在问为什么代码不起作用，只是为什么aio比常规写入慢得多，特别是因为所有并行写入都是针对不同的块。 这是aio代码，后跟非aio代码： 
 
 AIO计划 
 
#define MAX_AIO        (16384*2)
#define BUFSIZE        16384

struct mys {
    int status;
    struct aiocb aio;
};

void set_aiocb(struct mys *aio, int num, int fd)
{
    int i;

    for (i = 0; i < num; i++) {
        aio[i].aio.aio_fildes = fd;
        aio[i].aio.aio_offset = BUFSIZE * i;
        aio[i].aio.aio_buf = malloc(BUFSIZE);
        set_buf(aio[i].aio.aio_buf, BUFSIZE, i);
        aio[i].aio.aio_nbytes = BUFSIZE;
        aio[i].aio.aio_reqprio = fd;
        aio[i].aio.aio_sigevent.sigev_notify = SIGEV_NONE;
        aio[i].aio.aio_sigevent.sigev_signo = SIGUSR1;
        aio[i].aio.aio_sigevent.sigev_value.sival_ptr = &aio[i];
        aio[i].aio.aio_lio_opcode = 0;
        aio[i].status = EINPROGRESS;
    }
}

void main(void)
{
    int fd = open("/tmp/AIO", O_WRONLY | O_CREAT, 0666);
    int i, open_reqs = MAX_AIO;
    struct mys aio[MAX_AIO];
    struct timeval start, end, diff;

    set_aiocb(aio, MAX_AIO, fd);

    gettimeofday(&start, NULL);
    for (i = 0; i < MAX_AIO; i++)
        aio_write(&aio[i].aio);

    while (open_reqs > 0) {
        for (i = 0; i < MAX_AIO; i++) {
            if (aio[i].status == EINPROGRESS) {
                aio[i].status = aio_error(&(aio[i].aio));
                if (aio[i].status != EINPROGRESS)
                    open_reqs--;
            }
        }
    }
    gettimeofday(&end, NULL);
    timersub(&end, &start, &diff);
    printf("%d.%d\n", (int)diff.tv_sec, (int)diff.tv_usec);
}
 
 常规IO程序 
 
#define MAX_AIO        (16384*2)
#define BUFSIZE        16384

char buf[MAX_AIO][BUFSIZE];
void main(void)
{
    int i, fd = open("/tmp/NON_AIO", O_WRONLY | O_CREAT, 0666);
    struct timeval start, end, diff;

    gettimeofday(&start, NULL);
    for (i = 0; i < MAX_AIO; i++)
        write(fd, buf[i], BUFSIZE);
    gettimeofday(&end, NULL);
    timersub(&end, &start, &diff);
    printf("%d.%d\n", (int)diff.tv_sec, (int)diff.tv_usec);
}

I have a C program that writes 32768 blocks, each block is 16K size (total size of 512MB), to an ext4 filesystem on a system running 3.18.1 kernel. The regular write system call version of this program takes 5.35 seconds to finish the writes (as measured by gettimeofday before and after the for loop). The async io version of this program however takes the following times:
 
 
 
to queue all the aio_writes (32768 aio_writes): 7.43 seconds
 
 
poll to finish each IO request: additional 4.93 seconds
 
 
The output files are opened with these flags:O_WRONLY, O_CREAT, O_NONBLOCK
 
Why does async io take more than double the write() time? Even the Time-to-queue-async-io-request/time-to-write-sync-io is 1.4.
 
Since some people marked it off-topic, I looked at the definition and decided to paste the code - that seems to be the only reason why it should be marked off-topic. I am not asking why the code is not working, only why aio is much slower than regular writes, especially since all parallel writes are to different blocks. Here's the aio code, followed by the non-aio code:
 
AIO program
 
#define MAX_AIO        (16384*2)
#define BUFSIZE        16384

struct mys {
    int status;
    struct aiocb aio;
};

void set_aiocb(struct mys *aio, int num, int fd)
{
    int i;

    for (i = 0; i < num; i++) {
        aio[i].aio.aio_fildes = fd;
        aio[i].aio.aio_offset = BUFSIZE * i;
        aio[i].aio.aio_buf = malloc(BUFSIZE);
        set_buf(aio[i].aio.aio_buf, BUFSIZE, i);
        aio[i].aio.aio_nbytes = BUFSIZE;
        aio[i].aio.aio_reqprio = fd;
        aio[i].aio.aio_sigevent.sigev_notify = SIGEV_NONE;
        aio[i].aio.aio_sigevent.sigev_signo = SIGUSR1;
        aio[i].aio.aio_sigevent.sigev_value.sival_ptr = &aio[i];
        aio[i].aio.aio_lio_opcode = 0;
        aio[i].status = EINPROGRESS;
    }
}

void main(void)
{
    int fd = open("/tmp/AIO", O_WRONLY | O_CREAT, 0666);
    int i, open_reqs = MAX_AIO;
    struct mys aio[MAX_AIO];
    struct timeval start, end, diff;

    set_aiocb(aio, MAX_AIO, fd);

    gettimeofday(&start, NULL);
    for (i = 0; i < MAX_AIO; i++)
        aio_write(&aio[i].aio);

    while (open_reqs > 0) {
        for (i = 0; i < MAX_AIO; i++) {
            if (aio[i].status == EINPROGRESS) {
                aio[i].status = aio_error(&(aio[i].aio));
                if (aio[i].status != EINPROGRESS)
                    open_reqs--;
            }
        }
    }
    gettimeofday(&end, NULL);
    timersub(&end, &start, &diff);
    printf("%d.%d\n", (int)diff.tv_sec, (int)diff.tv_usec);
}
 
Regular IO program
 
#define MAX_AIO        (16384*2)
#define BUFSIZE        16384

char buf[MAX_AIO][BUFSIZE];
void main(void)
{
    int i, fd = open("/tmp/NON_AIO", O_WRONLY | O_CREAT, 0666);
    struct timeval start, end, diff;

    gettimeofday(&start, NULL);
    for (i = 0; i < MAX_AIO; i++)
        write(fd, buf[i], BUFSIZE);
    gettimeofday(&end, NULL);
    timersub(&end, &start, &diff);
    printf("%d.%d\n", (int)diff.tv_sec, (int)diff.tv_usec);
}

原文：https://stackoverflow.com/questions/28170110