xref: /freebsd-12.1/lib/libc/sys/sendfile.2 (revision dfd1ff19)
1.\" Copyright (c) 2003, David G. Lawrence
2.\" All rights reserved.
3.\"
4.\" Redistribution and use in source and binary forms, with or without
5.\" modification, are permitted provided that the following conditions
6.\" are met:
7.\" 1. Redistributions of source code must retain the above copyright
8.\"    notice unmodified, this list of conditions, and the following
9.\"    disclaimer.
10.\" 2. Redistributions in binary form must reproduce the above copyright
11.\"    notice, this list of conditions and the following disclaimer in the
12.\"    documentation and/or other materials provided with the distribution.
13.\"
14.\" THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
15.\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
16.\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
17.\" ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
18.\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
19.\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
20.\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
21.\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
22.\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
23.\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
24.\" SUCH DAMAGE.
25.\"
26.\" $FreeBSD$
27.\"
28.Dd October 31, 2005
29.Dt SENDFILE 2
30.Os
31.Sh NAME
32.Nm sendfile
33.Nd send a file to a socket
34.Sh LIBRARY
35.Lb libc
36.Sh SYNOPSIS
37.In sys/types.h
38.In sys/socket.h
39.In sys/uio.h
40.Ft int
41.Fo sendfile
42.Fa "int fd" "int s" "off_t offset" "size_t nbytes"
43.Fa "struct sf_hdtr *hdtr" "off_t *sbytes" "int flags"
44.Fc
45.Sh DESCRIPTION
46The
47.Fn sendfile
48system call
49sends a regular file specified by descriptor
50.Fa fd
51out a stream socket specified by descriptor
52.Fa s .
53.Pp
54The
55.Fa offset
56argument specifies where to begin in the file.
57Should
58.Fa offset
59fall beyond the end of file, the system will return
60success and report 0 bytes sent as described below.
61The
62.Fa nbytes
63argument specifies how many bytes of the file should be sent, with 0 having the special
64meaning of send until the end of file has been reached.
65.Pp
66An optional header and/or trailer can be sent before and after the file data by specifying
67a pointer to a
68.Vt "struct sf_hdtr" ,
69which has the following structure:
70.Pp
71.Bd -literal -offset indent -compact
72struct sf_hdtr {
73	struct iovec *headers;	/* pointer to header iovecs */
74	int hdr_cnt;		/* number of header iovecs */
75	struct iovec *trailers;	/* pointer to trailer iovecs */
76	int trl_cnt;		/* number of trailer iovecs */
77};
78.Ed
79.Pp
80The
81.Fa headers
82and
83.Fa trailers
84pointers, if
85.Pf non- Dv NULL ,
86point to arrays of
87.Vt "struct iovec"
88structures.
89See the
90.Fn writev
91system call for information on the iovec structure.
92The number of iovecs in these
93arrays is specified by
94.Fa hdr_cnt
95and
96.Fa trl_cnt .
97.Pp
98If
99.Pf non- Dv NULL ,
100the system will write the total number of bytes sent on the socket to the
101variable pointed to by
102.Fa sbytes .
103.Pp
104The
105.Fa flags
106argument has one possible value:
107.Dv SF_NODISKIO .
108This flag causes any
109.Fn sendfile
110call which would block on disk I/O to instead
111return
112.Er EBUSY .
113Busy servers may benefit by transferring requests that would
114block to a separate I/O worker thread.
115.Pp
116When using a socket marked for non-blocking I/O,
117.Fn sendfile
118may send fewer bytes than requested.
119In this case, the number of bytes successfully
120written is returned in
121.Fa *sbytes
122(if specified),
123and the error
124.Er EAGAIN
125is returned.
126.Sh IMPLEMENTATION NOTES
127The
128.Fx
129implementation of
130.Fn sendfile
131is "zero-copy", meaning that it has been optimized so that copying of the file data is avoided.
132.Sh TUNING
133Internally, this system call uses a special
134.Fn sendfile
135buffer
136.Pq Vt "struct sf_buf"
137to handle sending file data to the client.
138If the sending socket is
139blocking, and there are not enough
140.Fn sendfile
141buffers available,
142.Fn sendfile
143will block and report a state of
144.Dq Li sfbufa .
145If the sending socket is non-blocking and there are not enough
146.Fn sendfile
147buffers available, the call will block and wait for the
148necessary buffers to become available before finishing the call.
149.Pp
150The number of
151.Vt sf_buf Ns 's
152allocated should be proportional to the number of nmbclusters used to
153send data to a client via
154.Fn sendfile .
155Tune accordingly to avoid blocking!
156Busy installations that make extensive use of
157.Fn sendfile
158may want to increase these values to be inline with their
159.Va kern.ipc.nmbclusters
160(see
161.Xr tuning 7
162for details).
163.Pp
164The number of
165.Fn sendfile
166buffers available is determined at boot time by either the
167.Va kern.ipc.nsfbufs
168.Xr loader.conf 5
169variable or the
170.Dv NSFBUFS
171kernel configuration tunable.
172The number of
173.Fn sendfile
174buffers scales with
175.Va kern.maxusers .
176The
177.Va kern.ipc.nsfbufsused
178and
179.Va kern.ipc.nsfbufspeak
180read-only
181.Xr sysctl 8
182variables show current and peak
183.Fn sendfile
184buffers usage respectively.
185These values may also be viewed through
186.Nm netstat Fl m .
187.Sh RETURN VALUES
188.Rv -std sendfile
189.Sh ERRORS
190.Bl -tag -width Er
191.It Bq Er EAGAIN
192The socket is marked for non-blocking I/O and not all data was sent due to
193the socket buffer being filled.
194If specified, the number of bytes successfully sent will be returned in
195.Fa *sbytes .
196.It Bq Er EBADF
197The
198.Fa fd
199argument
200is not a valid file descriptor.
201.It Bq Er EBADF
202The
203.Fa s
204argument
205is not a valid socket descriptor.
206.It Bq Er EBUSY
207Completing the entire transfer would have required disk I/O, so
208it was aborted.
209Partial data may have been sent.
210(This error can only occur when
211.Dv SF_NODISKIO
212is specified.)
213.It Bq Er EFAULT
214An invalid address was specified for an argument.
215.It Bq Er EINTR
216A signal interrupted
217.Fn sendfile
218before it could be completed.
219If specified, the number
220of bytes successfully sent will be returned in
221.Fa *sbytes .
222.It Bq Er EINVAL
223The
224.Fa fd
225argument
226is not a regular file.
227.It Bq Er EINVAL
228The
229.Fa s
230argument
231is not a SOCK_STREAM type socket.
232.It Bq Er EINVAL
233The
234.Fa offset
235argument
236is negative.
237.It Bq Er EIO
238An error occurred while reading from
239.Fa fd .
240.It Bq Er ENOTCONN
241The
242.Fa s
243argument
244points to an unconnected socket.
245.It Bq Er ENOTSOCK
246The
247.Fa s
248argument
249is not a socket.
250.It Bq Er EOPNOTSUPP
251The file system for descriptor
252.Fa fd
253does not support
254.Fn sendfile .
255.It Bq Er EPIPE
256The socket peer has closed the connection.
257.El
258.Sh SEE ALSO
259.Xr netstat 1 ,
260.Xr open 2 ,
261.Xr send 2 ,
262.Xr socket 2 ,
263.Xr writev 2 ,
264.Xr tuning 7
265.Sh HISTORY
266The
267.Fn sendfile
268system call
269first appeared in
270.Fx 3.0 .
271This manual page first appeared in
272.Fx 3.1 .
273.Sh AUTHORS
274The
275.Fn sendfile
276system call
277and this manual page were written by
278.An David G. Lawrence Aq [email protected] .
279