view src/os/unix/ngx_recv.c @ 7668:0a04e5e4c40b

Large block sizes on Linux are now ignored (ticket #1168). NFS on Linux is known to report wsize as a block size (in both f_bsize and f_frsize, both in statfs() and statvfs()). On the other hand, typical file system block sizes on Linux (ext2/ext3/ext4, XFS) are limited to pagesize. (With FAT, block sizes can be at least up to 512k in extreme cases, but this doesn't really matter, see below.) To avoid too aggressive cache clearing on NFS volumes on Linux, block sizes larger than pagesize are now ignored. Note that it is safe to ignore large block sizes. Since 3899:e7cd13b7f759 (1.0.1) cache size is calculated based on fstat() st_blocks, and rounding to file system block size is preserved mostly for Windows. Note well that on other OSes valid block sizes seen are at least up to 65536. In particular, UFS on FreeBSD is known to work well with block and fragment sizes set to 65536.
author Maxim Dounin <mdounin@mdounin.ru>
date Mon, 22 Jun 2020 18:02:58 +0300
parents efd71d49bde0
children 5119c8150478
line wrap: on
line source


/*
 * Copyright (C) Igor Sysoev
 * Copyright (C) Nginx, Inc.
 */


#include <ngx_config.h>
#include <ngx_core.h>
#include <ngx_event.h>


ssize_t
ngx_unix_recv(ngx_connection_t *c, u_char *buf, size_t size)
{
    ssize_t       n;
    ngx_err_t     err;
    ngx_event_t  *rev;

    rev = c->read;

#if (NGX_HAVE_KQUEUE)

    if (ngx_event_flags & NGX_USE_KQUEUE_EVENT) {
        ngx_log_debug3(NGX_LOG_DEBUG_EVENT, c->log, 0,
                       "recv: eof:%d, avail:%d, err:%d",
                       rev->pending_eof, rev->available, rev->kq_errno);

        if (rev->available == 0) {
            if (rev->pending_eof) {
                rev->ready = 0;
                rev->eof = 1;

                if (rev->kq_errno) {
                    rev->error = 1;
                    ngx_set_socket_errno(rev->kq_errno);

                    return ngx_connection_error(c, rev->kq_errno,
                               "kevent() reported about an closed connection");
                }

                return 0;

            } else {
                rev->ready = 0;
                return NGX_AGAIN;
            }
        }
    }

#endif

#if (NGX_HAVE_EPOLLRDHUP)

    if (ngx_event_flags & NGX_USE_EPOLL_EVENT) {
        ngx_log_debug2(NGX_LOG_DEBUG_EVENT, c->log, 0,
                       "recv: eof:%d, avail:%d",
                       rev->pending_eof, rev->available);

        if (rev->available == 0 && !rev->pending_eof) {
            rev->ready = 0;
            return NGX_AGAIN;
        }
    }

#endif

    do {
        n = recv(c->fd, buf, size, 0);

        ngx_log_debug3(NGX_LOG_DEBUG_EVENT, c->log, 0,
                       "recv: fd:%d %z of %uz", c->fd, n, size);

        if (n == 0) {
            rev->ready = 0;
            rev->eof = 1;

#if (NGX_HAVE_KQUEUE)

            /*
             * on FreeBSD recv() may return 0 on closed socket
             * even if kqueue reported about available data
             */

            if (ngx_event_flags & NGX_USE_KQUEUE_EVENT) {
                rev->available = 0;
            }

#endif

            return 0;
        }

        if (n > 0) {

#if (NGX_HAVE_KQUEUE)

            if (ngx_event_flags & NGX_USE_KQUEUE_EVENT) {
                rev->available -= n;

                /*
                 * rev->available may be negative here because some additional
                 * bytes may be received between kevent() and recv()
                 */

                if (rev->available <= 0) {
                    if (!rev->pending_eof) {
                        rev->ready = 0;
                    }

                    rev->available = 0;
                }

                return n;
            }

#endif

#if (NGX_HAVE_FIONREAD)

            if (rev->available >= 0) {
                rev->available -= n;

                /*
                 * negative rev->available means some additional bytes
                 * were received between kernel notification and recv(),
                 * and therefore ev->ready can be safely reset even for
                 * edge-triggered event methods
                 */

                if (rev->available < 0) {
                    rev->available = 0;
                    rev->ready = 0;
                }

                ngx_log_debug1(NGX_LOG_DEBUG_EVENT, c->log, 0,
                               "recv: avail:%d", rev->available);

            } else if ((size_t) n == size) {

                if (ngx_socket_nread(c->fd, &rev->available) == -1) {
                    n = ngx_connection_error(c, ngx_socket_errno,
                                             ngx_socket_nread_n " failed");
                    break;
                }

                ngx_log_debug1(NGX_LOG_DEBUG_EVENT, c->log, 0,
                               "recv: avail:%d", rev->available);
            }

#endif

#if (NGX_HAVE_EPOLLRDHUP)

            if ((ngx_event_flags & NGX_USE_EPOLL_EVENT)
                && ngx_use_epoll_rdhup)
            {
                if ((size_t) n < size) {
                    if (!rev->pending_eof) {
                        rev->ready = 0;
                    }

                    rev->available = 0;
                }

                return n;
            }

#endif

            if ((size_t) n < size
                && !(ngx_event_flags & NGX_USE_GREEDY_EVENT))
            {
                rev->ready = 0;
            }

            return n;
        }

        err = ngx_socket_errno;

        if (err == NGX_EAGAIN || err == NGX_EINTR) {
            ngx_log_debug0(NGX_LOG_DEBUG_EVENT, c->log, err,
                           "recv() not ready");
            n = NGX_AGAIN;

        } else {
            n = ngx_connection_error(c, err, "recv() failed");
            break;
        }

    } while (err == NGX_EINTR);

    rev->ready = 0;

    if (n == NGX_ERROR) {
        rev->error = 1;
    }

    return n;
}