Bagaimana Unix pipeline diimplementasikan

Apa yang kita bicarakan?

$ echo hello | wc -c
6

Konveyor menyediakan saluran komunikasi antar proses searah. Pipeline memiliki input (akhir penulisan) dan output (akhir baca). Data yang ditulis ke input dari pipa dapat dibacakan.

Pipeline dibuat menggunakan panggilan pipe(2)yang mengembalikan dua deskriptor file: satu merujuk pada input dari pipeline, yang kedua ke output.

$ strace -qf -e execve,pipe,dup2,read,write \
    sh -c 'echo hello | wc -c'

execve("/bin/sh", ["sh", "-c", "echo hello | wc -c"], …)
pipe([3, 4])                            = 0
[pid 2604795] dup2(4, 1)                = 1
[pid 2604795] write(1, "hello\n", 6)    = 6
[pid 2604796] dup2(3, 0)                = 0
[pid 2604796] execve("/usr/bin/wc", ["wc", "-c"], …)
[pid 2604796] read(0, "hello\n", 16384) = 6
[pid 2604796] write(1, "6\n", 2)        = 2

, read(2) , . , write(2) , .

Apa yang kita cari

Di mana kita mencari?

Kernel Unix Tradisional (1970–1974)

Edisi ketiga Unix adalah versi terbaru dengan kernel yang ditulis dalam bahasa assembly, tetapi versi pertama dengan saluran pipa. Selama tahun 1973, pekerjaan dilakukan untuk memperbaiki edisi ketiga, intinya ditulis ulang dalam bahasa C, sehingga muncullah edisi keempat Unix.

Unix, , , , - , , . , . , , , . ? «» , , -, : « !».

. , , ( ), . . . API , .

Panggilan sistem pipa menciptakan mekanisme input output yang disebut pipeline. Deskriptor file yang dikembalikan dapat digunakan untuk operasi baca dan tulis. Ketika sesuatu ditulis ke saluran pipa, hingga 504 byte data buffer, setelah itu proses penulisan dijeda. Saat membaca dari saluran pipa, data buffer diambil.

pipe , . . - , , r1 (. fildes[1]), 4096 , . , r0 (. fildes[0]), .

, ( ) ( fork) read write.

Shell memiliki sintaks untuk mendefinisikan array linier dari proses yang terhubung melalui pipa.

Baca panggilan dari saluran pipa kosong (tidak mengandung data buffered) yang hanya memiliki satu ujung (semua deskriptor file penulisan ditutup) mengembalikan "akhir file". Merekam panggilan dalam situasi yang sama diabaikan.

Edisi Keenam Unix (1975)

Selama bertahun-tahun, Lions telah menjadi satu-satunya dokumen inti Unix yang tersedia di luar dinding Bell Labs. Meskipun lisensi edisi keenam memungkinkan guru untuk menggunakan kode sumbernya, lisensi edisi ketujuh mengecualikan kemungkinan ini, sehingga buku itu didistribusikan dalam bentuk salinan tulisan tangan yang tidak sah.

15 , Lions, . TUHS , . 1988- 9 , PDP11. , , /usr/src/, 1979- , . PWB, .

. , , += =+. - , - , .

/*
 * Max allowable buffering per pipe.
 * This is also the max size of the
 * file created to implement the pipe.
 * If this size is bigger than 4096,
 * pipes will be implemented in LARG
 * files, which is probably not good.
 */
#define    PIPSIZ    4096

/*
 * The sys-pipe entry.
 * Allocate an inode on the root device.
 * Allocate 2 file structures.
 * Put it all together with flags.
 */
pipe()
{
    register *ip, *rf, *wf;
    int r;

    ip = ialloc(rootdev);
    if(ip == NULL)
        return;
    rf = falloc();
    if(rf == NULL) {
        iput(ip);
        return;
    }
    r = u.u_ar0[R0];
    wf = falloc();
    if(wf == NULL) {
        rf->f_count = 0;
        u.u_ofile[r] = NULL;
        iput(ip);
        return;
    }
    u.u_ar0[R1] = u.u_ar0[R0]; /* wf's fd */
    u.u_ar0[R0] = r;           /* rf's fd */
    wf->f_flag = FWRITE|FPIPE;
    wf->f_inode = ip;
    rf->f_flag = FREAD|FPIPE;
    rf->f_inode = ip;
    ip->i_count = 2;
    ip->i_flag = IACC|IUPD;
    ip->i_mode = IALLOC;
}

/*
 * common code for read and write calls:
 * check permissions, set base, count, and offset,
 * and switch out to readi, writei, or pipe code.
 */
rdwr(mode)
{
    register *fp, m;

    m = mode;
    fp = getf(u.u_ar0[R0]);
        /* … */

    if(fp->f_flag&FPIPE) {
        if(m==FREAD)
            readp(fp); else
            writep(fp);
    }
        /* … */
}

writep(fp)
{
    register *rp, *ip, c;

    rp = fp;
    ip = rp->f_inode;
    c = u.u_count;

loop:
    /* If all done, return. */

    plock(ip);
    if(c == 0) {
        prele(ip);
        u.u_count = 0;
        return;
    }

    /*
     * If there are not both read and write sides of the
     * pipe active, return error and signal too.
     */

    if(ip->i_count < 2) {
        prele(ip);
        u.u_error = EPIPE;
        psignal(u.u_procp, SIGPIPE);
        return;
    }

    /*
     * If the pipe is full, wait for reads to deplete
     * and truncate it.
     */

    if(ip->i_size1 == PIPSIZ) {
        ip->i_mode =| IWRITE;
        prele(ip);
        sleep(ip+1, PPIPE);
        goto loop;
    }

    /* Write what is possible and loop back. */

    u.u_offset[0] = 0;
    u.u_offset[1] = ip->i_size1;
    u.u_count = min(c, PIPSIZ-u.u_offset[1]);
    c =- u.u_count;
    writei(ip);
    prele(ip);
    if(ip->i_mode&IREAD) {
        ip->i_mode =& ~IREAD;
        wakeup(ip+2);
    }
    goto loop;
}

/*
 * Give up the processor till a wakeup occurs
 * on chan, at which time the process
 * enters the scheduling queue at priority pri.
 * The most important effect of pri is that when
 * pri<0 a signal cannot disturb the sleep;
 * if pri>=0 signals will be processed.
 * Callers of this routine must be prepared for
 * premature return, and check that the reason for
 * sleeping has gone away.
 */
sleep(chan, pri) /* … */

/*
 * Wake up all processes sleeping on chan.
 */
wakeup(chan) /* … */

readp(fp)
int *fp;
{
    register *rp, *ip;

    rp = fp;
    ip = rp->f_inode;

loop:
    /* Very conservative locking. */

    plock(ip);

    /*
     * If the head (read) has caught up with
     * the tail (write), reset both to 0.
     */

    if(rp->f_offset[1] == ip->i_size1) {
        if(rp->f_offset[1] != 0) {
            rp->f_offset[1] = 0;
            ip->i_size1 = 0;
            if(ip->i_mode&IWRITE) {
                ip->i_mode =& ~IWRITE;
                wakeup(ip+1);
            }
        }

        /*
         * If there are not both reader and
         * writer active, return without
         * satisfying read.
         */

        prele(ip);
        if(ip->i_count < 2)
            return;
        ip->i_mode =| IREAD;
        sleep(ip+2, PPIPE);
        goto loop;
    }

    /* Read and return */

    u.u_offset[0] = 0;
    u.u_offset[1] = rp->f_offset[1];
    readi(ip);
    rp->f_offset[1] = u.u_offset[1];
    prele(ip);
}

/*
 * Read the file corresponding to
 * the inode pointed at by the argument.
 * The actual read arguments are found
 * in the variables:
 *    u_base        core address for destination
 *    u_offset    byte offset in file
 *    u_count        number of bytes to read
 *    u_segflg    read to kernel/user
 */
readi(aip)
struct inode *aip;
/* … */

/*
 * Write the file corresponding to
 * the inode pointed at by the argument.
 * The actual write arguments are found
 * in the variables:
 *    u_base        core address for source
 *    u_offset    byte offset in file
 *    u_count        number of bytes to write
 *    u_segflg    write to kernel/user
 */
writei(aip)
struct inode *aip;
/* … */

/*
 * Lock a pipe.
 * If its already locked, set the WANT bit and sleep.
 */
plock(ip)
int *ip;
{
    register *rp;

    rp = ip;
    while(rp->i_flag&ILOCK) {
        rp->i_flag =| IWANT;
        sleep(rp, PPIPE);
    }
    rp->i_flag =| ILOCK;
}

/*
 * Unlock a pipe.
 * If WANT bit is on, wakeup.
 * This routine is also used to unlock inodes in general.
 */
prele(ip)
int *ip;
{
    register *rp;

    rp = ip;
    rp->i_flag =& ~ILOCK;
    if(rp->i_flag&IWANT) {
        rp->i_flag =& ~IWANT;
        wakeup(rp);
    }
}

Xv6, kernel berbentuk Unix yang sederhana

#define PIPESIZE 512

struct pipe {
  struct spinlock lock;
  char data[PIPESIZE];
  uint nread;     // number of bytes read
  uint nwrite;    // number of bytes written
  int readopen;   // read fd is still open
  int writeopen;  // write fd is still open
};

int
pipealloc(struct file **f0, struct file **f1)
{
  struct pipe *p;

  p = 0;
  *f0 = *f1 = 0;
  if((*f0 = filealloc()) == 0 || (*f1 = filealloc()) == 0)
    goto bad;
  if((p = (struct pipe*)kalloc()) == 0)
    goto bad;
  p->readopen = 1;
  p->writeopen = 1;
  p->nwrite = 0;
  p->nread = 0;
  initlock(&p->lock, "pipe");
  (*f0)->type = FD_PIPE;
  (*f0)->readable = 1;
  (*f0)->writable = 0;
  (*f0)->pipe = p;
  (*f1)->type = FD_PIPE;
  (*f1)->readable = 0;
  (*f1)->writable = 1;
  (*f1)->pipe = p;
  return 0;

 bad:
  if(p)
    kfree((char*)p);
  if(*f0)
    fileclose(*f0);
  if(*f1)
    fileclose(*f1);
  return -1;
}

Linux 0,01

int write_pipe(struct m_inode * inode, char * buf, int count)
{
    char * b=buf;

    wake_up(&inode->i_wait);
    if (inode->i_count != 2) { /* no readers */
        current->signal |= (1<<(SIGPIPE-1));
        return -1;
    }
    while (count-->0) {
        while (PIPE_FULL(*inode)) {
            wake_up(&inode->i_wait);
            if (inode->i_count != 2) {
                current->signal |= (1<<(SIGPIPE-1));
                return b-buf;
            }
            sleep_on(&inode->i_wait);
        }
        ((char *)inode->i_size)[PIPE_HEAD(*inode)] =
            get_fs_byte(b++);
        INC_PIPE( PIPE_HEAD(*inode) );
        wake_up(&inode->i_wait);
    }
    wake_up(&inode->i_wait);
    return b-buf;
}

Linux modern, FreeBSD, NetBSD, kernel OpenBSD