polyphony 1.0.1 → 1.0.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/CHANGELOG.md +4 -0
- data/TODO.md +4 -0
- data/examples/core/debug.rb +12 -0
- data/examples/core/rpc_benchmark.rb +136 -0
- data/lib/polyphony/extensions/fiber.rb +1 -0
- data/lib/polyphony/extensions/socket.rb +42 -42
- data/lib/polyphony/version.rb +1 -1
- data/polyphony.gemspec +3 -1
- data/test/test_socket.rb +1 -1
- metadata +32 -149
- data/vendor/liburing/man/IO_URING_CHECK_VERSION.3 +0 -1
- data/vendor/liburing/man/IO_URING_VERSION_MAJOR.3 +0 -1
- data/vendor/liburing/man/IO_URING_VERSION_MINOR.3 +0 -1
- data/vendor/liburing/man/io_uring.7 +0 -781
- data/vendor/liburing/man/io_uring_buf_ring_add.3 +0 -53
- data/vendor/liburing/man/io_uring_buf_ring_advance.3 +0 -31
- data/vendor/liburing/man/io_uring_buf_ring_cq_advance.3 +0 -41
- data/vendor/liburing/man/io_uring_buf_ring_init.3 +0 -30
- data/vendor/liburing/man/io_uring_buf_ring_mask.3 +0 -27
- data/vendor/liburing/man/io_uring_check_version.3 +0 -72
- data/vendor/liburing/man/io_uring_close_ring_fd.3 +0 -43
- data/vendor/liburing/man/io_uring_cq_advance.3 +0 -49
- data/vendor/liburing/man/io_uring_cq_has_overflow.3 +0 -25
- data/vendor/liburing/man/io_uring_cq_ready.3 +0 -26
- data/vendor/liburing/man/io_uring_cqe_get_data.3 +0 -53
- data/vendor/liburing/man/io_uring_cqe_get_data64.3 +0 -1
- data/vendor/liburing/man/io_uring_cqe_seen.3 +0 -42
- data/vendor/liburing/man/io_uring_enter.2 +0 -1700
- data/vendor/liburing/man/io_uring_enter2.2 +0 -1
- data/vendor/liburing/man/io_uring_free_probe.3 +0 -27
- data/vendor/liburing/man/io_uring_get_events.3 +0 -33
- data/vendor/liburing/man/io_uring_get_probe.3 +0 -30
- data/vendor/liburing/man/io_uring_get_sqe.3 +0 -57
- data/vendor/liburing/man/io_uring_major_version.3 +0 -1
- data/vendor/liburing/man/io_uring_minor_version.3 +0 -1
- data/vendor/liburing/man/io_uring_opcode_supported.3 +0 -30
- data/vendor/liburing/man/io_uring_peek_cqe.3 +0 -38
- data/vendor/liburing/man/io_uring_prep_accept.3 +0 -197
- data/vendor/liburing/man/io_uring_prep_accept_direct.3 +0 -1
- data/vendor/liburing/man/io_uring_prep_cancel.3 +0 -118
- data/vendor/liburing/man/io_uring_prep_cancel64.3 +0 -1
- data/vendor/liburing/man/io_uring_prep_close.3 +0 -59
- data/vendor/liburing/man/io_uring_prep_close_direct.3 +0 -1
- data/vendor/liburing/man/io_uring_prep_connect.3 +0 -66
- data/vendor/liburing/man/io_uring_prep_fadvise.3 +0 -59
- data/vendor/liburing/man/io_uring_prep_fallocate.3 +0 -59
- data/vendor/liburing/man/io_uring_prep_fgetxattr.3 +0 -1
- data/vendor/liburing/man/io_uring_prep_files_update.3 +0 -92
- data/vendor/liburing/man/io_uring_prep_fsetxattr.3 +0 -1
- data/vendor/liburing/man/io_uring_prep_fsync.3 +0 -70
- data/vendor/liburing/man/io_uring_prep_getxattr.3 +0 -61
- data/vendor/liburing/man/io_uring_prep_link.3 +0 -1
- data/vendor/liburing/man/io_uring_prep_link_timeout.3 +0 -94
- data/vendor/liburing/man/io_uring_prep_linkat.3 +0 -91
- data/vendor/liburing/man/io_uring_prep_madvise.3 +0 -56
- data/vendor/liburing/man/io_uring_prep_mkdir.3 +0 -1
- data/vendor/liburing/man/io_uring_prep_mkdirat.3 +0 -83
- data/vendor/liburing/man/io_uring_prep_msg_ring.3 +0 -92
- data/vendor/liburing/man/io_uring_prep_msg_ring_cqe_flags.3 +0 -1
- data/vendor/liburing/man/io_uring_prep_multishot_accept.3 +0 -1
- data/vendor/liburing/man/io_uring_prep_multishot_accept_direct.3 +0 -1
- data/vendor/liburing/man/io_uring_prep_nop.3 +0 -28
- data/vendor/liburing/man/io_uring_prep_openat.3 +0 -117
- data/vendor/liburing/man/io_uring_prep_openat2.3 +0 -117
- data/vendor/liburing/man/io_uring_prep_openat2_direct.3 +0 -1
- data/vendor/liburing/man/io_uring_prep_openat_direct.3 +0 -1
- data/vendor/liburing/man/io_uring_prep_poll_add.3 +0 -72
- data/vendor/liburing/man/io_uring_prep_poll_multishot.3 +0 -1
- data/vendor/liburing/man/io_uring_prep_poll_remove.3 +0 -55
- data/vendor/liburing/man/io_uring_prep_poll_update.3 +0 -89
- data/vendor/liburing/man/io_uring_prep_provide_buffers.3 +0 -140
- data/vendor/liburing/man/io_uring_prep_read.3 +0 -69
- data/vendor/liburing/man/io_uring_prep_read_fixed.3 +0 -72
- data/vendor/liburing/man/io_uring_prep_readv.3 +0 -85
- data/vendor/liburing/man/io_uring_prep_readv2.3 +0 -111
- data/vendor/liburing/man/io_uring_prep_recv.3 +0 -105
- data/vendor/liburing/man/io_uring_prep_recv_multishot.3 +0 -1
- data/vendor/liburing/man/io_uring_prep_recvmsg.3 +0 -124
- data/vendor/liburing/man/io_uring_prep_recvmsg_multishot.3 +0 -1
- data/vendor/liburing/man/io_uring_prep_remove_buffers.3 +0 -52
- data/vendor/liburing/man/io_uring_prep_rename.3 +0 -1
- data/vendor/liburing/man/io_uring_prep_renameat.3 +0 -96
- data/vendor/liburing/man/io_uring_prep_send.3 +0 -66
- data/vendor/liburing/man/io_uring_prep_send_set_addr.3 +0 -38
- data/vendor/liburing/man/io_uring_prep_send_zc.3 +0 -96
- data/vendor/liburing/man/io_uring_prep_send_zc_fixed.3 +0 -1
- data/vendor/liburing/man/io_uring_prep_sendmsg.3 +0 -89
- data/vendor/liburing/man/io_uring_prep_sendmsg_zc.3 +0 -1
- data/vendor/liburing/man/io_uring_prep_setxattr.3 +0 -64
- data/vendor/liburing/man/io_uring_prep_shutdown.3 +0 -53
- data/vendor/liburing/man/io_uring_prep_socket.3 +0 -118
- data/vendor/liburing/man/io_uring_prep_socket_direct.3 +0 -1
- data/vendor/liburing/man/io_uring_prep_socket_direct_alloc.3 +0 -1
- data/vendor/liburing/man/io_uring_prep_splice.3 +0 -120
- data/vendor/liburing/man/io_uring_prep_statx.3 +0 -74
- data/vendor/liburing/man/io_uring_prep_symlink.3 +0 -1
- data/vendor/liburing/man/io_uring_prep_symlinkat.3 +0 -85
- data/vendor/liburing/man/io_uring_prep_sync_file_range.3 +0 -59
- data/vendor/liburing/man/io_uring_prep_tee.3 +0 -74
- data/vendor/liburing/man/io_uring_prep_timeout.3 +0 -95
- data/vendor/liburing/man/io_uring_prep_timeout_remove.3 +0 -1
- data/vendor/liburing/man/io_uring_prep_timeout_update.3 +0 -98
- data/vendor/liburing/man/io_uring_prep_unlink.3 +0 -1
- data/vendor/liburing/man/io_uring_prep_unlinkat.3 +0 -82
- data/vendor/liburing/man/io_uring_prep_write.3 +0 -67
- data/vendor/liburing/man/io_uring_prep_write_fixed.3 +0 -72
- data/vendor/liburing/man/io_uring_prep_writev.3 +0 -85
- data/vendor/liburing/man/io_uring_prep_writev2.3 +0 -111
- data/vendor/liburing/man/io_uring_queue_exit.3 +0 -26
- data/vendor/liburing/man/io_uring_queue_init.3 +0 -89
- data/vendor/liburing/man/io_uring_queue_init_params.3 +0 -1
- data/vendor/liburing/man/io_uring_recvmsg_cmsg_firsthdr.3 +0 -1
- data/vendor/liburing/man/io_uring_recvmsg_cmsg_nexthdr.3 +0 -1
- data/vendor/liburing/man/io_uring_recvmsg_name.3 +0 -1
- data/vendor/liburing/man/io_uring_recvmsg_out.3 +0 -82
- data/vendor/liburing/man/io_uring_recvmsg_payload.3 +0 -1
- data/vendor/liburing/man/io_uring_recvmsg_payload_length.3 +0 -1
- data/vendor/liburing/man/io_uring_recvmsg_validate.3 +0 -1
- data/vendor/liburing/man/io_uring_register.2 +0 -834
- data/vendor/liburing/man/io_uring_register_buf_ring.3 +0 -140
- data/vendor/liburing/man/io_uring_register_buffers.3 +0 -104
- data/vendor/liburing/man/io_uring_register_buffers_sparse.3 +0 -1
- data/vendor/liburing/man/io_uring_register_buffers_tags.3 +0 -1
- data/vendor/liburing/man/io_uring_register_buffers_update_tag.3 +0 -1
- data/vendor/liburing/man/io_uring_register_eventfd.3 +0 -51
- data/vendor/liburing/man/io_uring_register_eventfd_async.3 +0 -1
- data/vendor/liburing/man/io_uring_register_file_alloc_range.3 +0 -52
- data/vendor/liburing/man/io_uring_register_files.3 +0 -112
- data/vendor/liburing/man/io_uring_register_files_sparse.3 +0 -1
- data/vendor/liburing/man/io_uring_register_files_tags.3 +0 -1
- data/vendor/liburing/man/io_uring_register_files_update.3 +0 -1
- data/vendor/liburing/man/io_uring_register_files_update_tag.3 +0 -1
- data/vendor/liburing/man/io_uring_register_iowq_aff.3 +0 -61
- data/vendor/liburing/man/io_uring_register_iowq_max_workers.3 +0 -71
- data/vendor/liburing/man/io_uring_register_ring_fd.3 +0 -49
- data/vendor/liburing/man/io_uring_register_sync_cancel.3 +0 -71
- data/vendor/liburing/man/io_uring_setup.2 +0 -669
- data/vendor/liburing/man/io_uring_sq_ready.3 +0 -31
- data/vendor/liburing/man/io_uring_sq_space_left.3 +0 -25
- data/vendor/liburing/man/io_uring_sqe_set_data.3 +0 -48
- data/vendor/liburing/man/io_uring_sqe_set_data64.3 +0 -1
- data/vendor/liburing/man/io_uring_sqe_set_flags.3 +0 -87
- data/vendor/liburing/man/io_uring_sqring_wait.3 +0 -34
- data/vendor/liburing/man/io_uring_submit.3 +0 -46
- data/vendor/liburing/man/io_uring_submit_and_get_events.3 +0 -31
- data/vendor/liburing/man/io_uring_submit_and_wait.3 +0 -38
- data/vendor/liburing/man/io_uring_submit_and_wait_timeout.3 +0 -56
- data/vendor/liburing/man/io_uring_unregister_buf_ring.3 +0 -30
- data/vendor/liburing/man/io_uring_unregister_buffers.3 +0 -27
- data/vendor/liburing/man/io_uring_unregister_eventfd.3 +0 -1
- data/vendor/liburing/man/io_uring_unregister_files.3 +0 -27
- data/vendor/liburing/man/io_uring_unregister_iowq_aff.3 +0 -1
- data/vendor/liburing/man/io_uring_unregister_ring_fd.3 +0 -32
- data/vendor/liburing/man/io_uring_wait_cqe.3 +0 -40
- data/vendor/liburing/man/io_uring_wait_cqe_nr.3 +0 -43
- data/vendor/liburing/man/io_uring_wait_cqe_timeout.3 +0 -53
- data/vendor/liburing/man/io_uring_wait_cqes.3 +0 -56
@@ -1,140 +0,0 @@
|
|
1
|
-
.\" Copyright (C) 2022 Jens Axboe <axboe@kernel.dk>
|
2
|
-
.\"
|
3
|
-
.\" SPDX-License-Identifier: LGPL-2.0-or-later
|
4
|
-
.\"
|
5
|
-
.TH io_uring_register_buf_ring 3 "May 18, 2022" "liburing-2.2" "liburing Manual"
|
6
|
-
.SH NAME
|
7
|
-
io_uring_register_buf_ring \- register buffer ring for provided buffers
|
8
|
-
.SH SYNOPSIS
|
9
|
-
.nf
|
10
|
-
.B #include <liburing.h>
|
11
|
-
.PP
|
12
|
-
.BI "int io_uring_register_buf_ring(struct io_uring *" ring ",
|
13
|
-
.BI " struct io_uring_buf_reg *" reg ",
|
14
|
-
.BI " unsigned int " flags ");"
|
15
|
-
.BI "
|
16
|
-
.fi
|
17
|
-
.SH DESCRIPTION
|
18
|
-
.PP
|
19
|
-
The
|
20
|
-
.BR io_uring_register_buf_ring (3)
|
21
|
-
function registers a shared buffer ring to be used with provided buffers. For
|
22
|
-
the request types that support it, provided buffers are given to the ring and
|
23
|
-
one is selected by a request if it has
|
24
|
-
.B IOSQE_BUFFER_SELECT
|
25
|
-
set in the SQE
|
26
|
-
.IR flags ,
|
27
|
-
when the request is ready to receive data. This allows both clear ownership
|
28
|
-
of the buffer lifetime, and a way to have more read/receive type of operations
|
29
|
-
in flight than buffers available.
|
30
|
-
|
31
|
-
The
|
32
|
-
.I reg
|
33
|
-
argument must be filled in with the appropriate information. It looks as
|
34
|
-
follows:
|
35
|
-
.PP
|
36
|
-
.in +4n
|
37
|
-
.EX
|
38
|
-
struct io_uring_buf_reg {
|
39
|
-
__u64 ring_addr;
|
40
|
-
__u32 ring_entries;
|
41
|
-
__u16 bgid;
|
42
|
-
__u16 pad;
|
43
|
-
__u64 resv[3];
|
44
|
-
};
|
45
|
-
.EE
|
46
|
-
.in
|
47
|
-
.PP
|
48
|
-
The
|
49
|
-
.I ring_addr
|
50
|
-
field must contain the address to the memory allocated to fit this ring.
|
51
|
-
The memory must be page aligned and hence allocated appropriately using eg
|
52
|
-
.BR posix_memalign (3)
|
53
|
-
or similar. The size of the ring is the product of
|
54
|
-
.I ring_entries
|
55
|
-
and the size of
|
56
|
-
.IR "struct io_uring_buf" .
|
57
|
-
.I ring_entries
|
58
|
-
is the desired size of the ring, and must be a power-of-2 in size. The maximum
|
59
|
-
size allowed is 2^15 (32768).
|
60
|
-
.I bgid
|
61
|
-
is the buffer group ID associated with this ring. SQEs that select a buffer
|
62
|
-
have a buffer group associated with them in their
|
63
|
-
.I buf_group
|
64
|
-
field, and the associated CQEs will have
|
65
|
-
.B IORING_CQE_F_BUFFER
|
66
|
-
set in their
|
67
|
-
.I flags
|
68
|
-
member, which will also contain the specific ID of the buffer selected. The rest
|
69
|
-
of the fields are reserved and must be cleared to zero.
|
70
|
-
|
71
|
-
The
|
72
|
-
.I flags
|
73
|
-
argument is currently unused and must be set to zero.
|
74
|
-
|
75
|
-
A shared buffer ring looks as follows:
|
76
|
-
.PP
|
77
|
-
.in +4n
|
78
|
-
.EX
|
79
|
-
struct io_uring_buf_ring {
|
80
|
-
union {
|
81
|
-
struct {
|
82
|
-
__u64 resv1;
|
83
|
-
__u32 resv2;
|
84
|
-
__u16 resv3;
|
85
|
-
__u16 tail;
|
86
|
-
};
|
87
|
-
struct io_uring_buf bufs[0];
|
88
|
-
};
|
89
|
-
};
|
90
|
-
.EE
|
91
|
-
.in
|
92
|
-
.PP
|
93
|
-
where
|
94
|
-
.I tail
|
95
|
-
is the index at which the application can insert new buffers for consumption
|
96
|
-
by requests, and
|
97
|
-
.I struct io_uring_buf
|
98
|
-
is buffer definition:
|
99
|
-
.PP
|
100
|
-
.in +4n
|
101
|
-
.EX
|
102
|
-
struct io_uring_buf {
|
103
|
-
__u64 addr;
|
104
|
-
__u32 len;
|
105
|
-
__u16 bid;
|
106
|
-
__u16 resv;
|
107
|
-
};
|
108
|
-
.EE
|
109
|
-
.in
|
110
|
-
.PP
|
111
|
-
where
|
112
|
-
.I addr
|
113
|
-
is the address for the buffer,
|
114
|
-
.I len
|
115
|
-
is the length of the buffer in bytes, and
|
116
|
-
.I bid
|
117
|
-
is the buffer ID that will be returned in the CQE once consumed.
|
118
|
-
|
119
|
-
Reserved fields must not be touched. Applications must use
|
120
|
-
.BR io_uring_buf_ring_init (3)
|
121
|
-
to initialise the buffer ring before use. Applications may use
|
122
|
-
.BR io_uring_buf_ring_add (3)
|
123
|
-
and
|
124
|
-
.BR io_uring_buf_ring_advance (3)
|
125
|
-
or
|
126
|
-
.BR io_uring_buf_ring_cq_advance (3)
|
127
|
-
to provide buffers, which will set these fields and update the tail.
|
128
|
-
|
129
|
-
Available since 5.19.
|
130
|
-
|
131
|
-
.SH RETURN VALUE
|
132
|
-
On success
|
133
|
-
.BR io_uring_register_buf_ring (3)
|
134
|
-
returns 0. On failure it returns
|
135
|
-
.BR -errno .
|
136
|
-
.SH SEE ALSO
|
137
|
-
.BR io_uring_buf_ring_init (3),
|
138
|
-
.BR io_uring_buf_ring_add (3),
|
139
|
-
.BR io_uring_buf_ring_advance (3),
|
140
|
-
.BR io_uring_buf_ring_cq_advance (3)
|
@@ -1,104 +0,0 @@
|
|
1
|
-
.\" Copyright (C) 2021 Stefan Roesch <shr@fb.com>
|
2
|
-
.\"
|
3
|
-
.\" SPDX-License-Identifier: LGPL-2.0-or-later
|
4
|
-
.\"
|
5
|
-
.TH io_uring_register_buffers 3 "November 15, 2021" "liburing-2.1" "liburing Manual"
|
6
|
-
.SH NAME
|
7
|
-
io_uring_register_buffers \- register buffers for fixed buffer operations
|
8
|
-
.SH SYNOPSIS
|
9
|
-
.nf
|
10
|
-
.B #include <liburing.h>
|
11
|
-
.PP
|
12
|
-
.BI "int io_uring_register_buffers(struct io_uring *" ring ","
|
13
|
-
.BI " const struct iovec *" iovecs ","
|
14
|
-
.BI " unsigned " nr_iovecs ");"
|
15
|
-
.PP
|
16
|
-
.BI "int io_uring_register_buffers_tags(struct io_uring *" ring ","
|
17
|
-
.BI " const struct iovec *" iovecs ","
|
18
|
-
.BI " const __u64 *" tags ","
|
19
|
-
.BI " unsigned " nr ");"
|
20
|
-
.PP
|
21
|
-
.BI "int io_uring_register_buffers_sparse(struct io_uring *" ring ","
|
22
|
-
.BI " unsigned " nr_iovecs ");"
|
23
|
-
.PP
|
24
|
-
.BI "int io_uring_register_buffers_update_tag(struct io_uring *" ring ","
|
25
|
-
.BI " unsigned " off ","
|
26
|
-
.BI " const struct iovec *" iovecs ","
|
27
|
-
.BI " const __u64 *" tags ","
|
28
|
-
.BI " unsigned " nr ");"
|
29
|
-
.fi
|
30
|
-
.SH DESCRIPTION
|
31
|
-
.PP
|
32
|
-
The
|
33
|
-
.BR io_uring_register_buffers (3)
|
34
|
-
function registers
|
35
|
-
.I nr_iovecs
|
36
|
-
number of buffers defined by the array
|
37
|
-
.I iovecs
|
38
|
-
belonging to the
|
39
|
-
.IR ring .
|
40
|
-
|
41
|
-
The
|
42
|
-
.BR io_uring_register_buffers_tags (3)
|
43
|
-
function behaves the same as
|
44
|
-
.BR io_uring_register_buffers (3)
|
45
|
-
function but additionally takes
|
46
|
-
.I tags
|
47
|
-
parameter. See
|
48
|
-
.B IORING_REGISTER_BUFFERS2
|
49
|
-
for the resource tagging description.
|
50
|
-
|
51
|
-
The
|
52
|
-
.BR io_uring_register_buffers_sparse (3)
|
53
|
-
function registers
|
54
|
-
.I nr_iovecs
|
55
|
-
empty buffers belonging to the
|
56
|
-
.IR ring .
|
57
|
-
These buffers must be updated before use, using eg
|
58
|
-
.BR io_uring_register_buffers_update_tag (3).
|
59
|
-
|
60
|
-
After the caller has registered the buffers, they can be used with one of the
|
61
|
-
fixed buffers functions.
|
62
|
-
|
63
|
-
Registered buffers is an optimization that is useful in conjunction with
|
64
|
-
.B O_DIRECT
|
65
|
-
reads and writes, where it maps the specified range into the kernel once when
|
66
|
-
the buffer is registered rather than doing a map and unmap for each IO
|
67
|
-
every time IO is performed to that region. Additionally, it also avoids
|
68
|
-
manipulating the page reference counts for each IO.
|
69
|
-
|
70
|
-
The
|
71
|
-
.BR io_uring_register_buffers_update_tag (3)
|
72
|
-
function updates registered buffers with new ones, either turning a sparse
|
73
|
-
entry into a real one, or replacing an existing entry. The
|
74
|
-
.I off
|
75
|
-
is offset on which to start the update
|
76
|
-
.I nr
|
77
|
-
number of buffers defined by the array
|
78
|
-
.I iovecs
|
79
|
-
belonging to the
|
80
|
-
.IR ring .
|
81
|
-
The
|
82
|
-
.I tags
|
83
|
-
points to an array of tags. See
|
84
|
-
.B IORING_REGISTER_BUFFERS2
|
85
|
-
for the resource tagging description.
|
86
|
-
|
87
|
-
.SH RETURN VALUE
|
88
|
-
On success
|
89
|
-
.BR io_uring_register_buffers (3),
|
90
|
-
.BR io_uring_register_buffers_tags (3)
|
91
|
-
and
|
92
|
-
.BR io_uring_register_buffers_sparse (3)
|
93
|
-
return 0.
|
94
|
-
.BR io_uring_register_buffers_update_tag (3)
|
95
|
-
return number of buffers updated.
|
96
|
-
On failure they return
|
97
|
-
.BR -errno .
|
98
|
-
.SH SEE ALSO
|
99
|
-
.BR io_uring_register (2),
|
100
|
-
.BR io_uring_get_sqe (3),
|
101
|
-
.BR io_uring_unregister_buffers (3),
|
102
|
-
.BR io_uring_register_buf_ring (3),
|
103
|
-
.BR io_uring_prep_read_fixed (3),
|
104
|
-
.BR io_uring_prep_write_fixed (3)
|
@@ -1 +0,0 @@
|
|
1
|
-
io_uring_register_buffers.3
|
@@ -1 +0,0 @@
|
|
1
|
-
io_uring_register_buffers.3
|
@@ -1 +0,0 @@
|
|
1
|
-
io_uring_register_buffers.3
|
@@ -1,51 +0,0 @@
|
|
1
|
-
.\" Copyright (C) 2022 Jens Axboe <axboe@kernel.dk>
|
2
|
-
.\"
|
3
|
-
.\" SPDX-License-Identifier: LGPL-2.0-or-later
|
4
|
-
.\"
|
5
|
-
.TH io_uring_register_eventfd 3 "April 16, 2022" "liburing-2.2" "liburing Manual"
|
6
|
-
.SH NAME
|
7
|
-
io_uring_register_eventfd \- register an eventfd with a ring
|
8
|
-
.SH SYNOPSIS
|
9
|
-
.nf
|
10
|
-
.B #include <liburing.h>
|
11
|
-
.PP
|
12
|
-
.BI "int io_uring_register_eventfd(struct io_uring *" ring ","
|
13
|
-
.BI " int " fd ");"
|
14
|
-
.PP
|
15
|
-
.BI "int io_uring_register_eventfd_async(struct io_uring *" ring ","
|
16
|
-
.BI " int " fd ");"
|
17
|
-
.PP
|
18
|
-
.BI "int io_uring_unregister_eventfd(struct io_uring *" ring ");"
|
19
|
-
.fi
|
20
|
-
.SH DESCRIPTION
|
21
|
-
.PP
|
22
|
-
.BR io_uring_register_eventfd (3)
|
23
|
-
registers the eventfd file descriptor
|
24
|
-
.I fd
|
25
|
-
with the ring identified by
|
26
|
-
.IR ring .
|
27
|
-
|
28
|
-
Whenever completions are posted to the CQ ring, an eventfd notification
|
29
|
-
is generated with the registered eventfd descriptor. If
|
30
|
-
.BR io_uring_register_eventfd_async (3)
|
31
|
-
is used, only events that completed out-of-line will trigger a notification.
|
32
|
-
|
33
|
-
It notifications are no longer desired,
|
34
|
-
.BR io_uring_unregister_eventfd (3)
|
35
|
-
may be called to remove the eventfd registration. No eventfd argument is
|
36
|
-
needed, as a ring can only have a single eventfd registered.
|
37
|
-
|
38
|
-
.SH NOTES
|
39
|
-
While io_uring generally takes care to avoid spurious events, they can occur.
|
40
|
-
Similarly, batched completions of CQEs may only trigger a single eventfd
|
41
|
-
notification even if multiple CQEs are posted. The application should make no
|
42
|
-
assumptions on number of events being available having a direct correlation to
|
43
|
-
eventfd notifications posted. An eventfd notification must thus only be treated
|
44
|
-
as a hint to check the CQ ring for completions.
|
45
|
-
.SH RETURN VALUE
|
46
|
-
Returns 0 on success, or
|
47
|
-
or
|
48
|
-
.BR -errno
|
49
|
-
on error.
|
50
|
-
.SH SEE ALSO
|
51
|
-
.BR eventfd (2)
|
@@ -1 +0,0 @@
|
|
1
|
-
io_uring_register_eventfd.3
|
@@ -1,52 +0,0 @@
|
|
1
|
-
.\" Copyright (C) 2022 Jens Axboe <axboe@kernel.dk>
|
2
|
-
.\"
|
3
|
-
.\" SPDX-License-Identifier: LGPL-2.0-or-later
|
4
|
-
.\"
|
5
|
-
.TH io_uring_register_file_alloc_range 3 "Oct 21, 2022" "liburing-2.3" "liburing Manual"
|
6
|
-
.SH NAME
|
7
|
-
io_uring_register_file_alloc_range \- set range for fixed file allocations
|
8
|
-
.SH SYNOPSIS
|
9
|
-
.nf
|
10
|
-
.B #include <liburing.h>
|
11
|
-
.PP
|
12
|
-
.BI "int io_uring_register_file_alloc_range(struct io_uring *" ring ",
|
13
|
-
.BI " unsigned " off ","
|
14
|
-
.BI " unsigned " len ");"
|
15
|
-
.BI "
|
16
|
-
.fi
|
17
|
-
.SH DESCRIPTION
|
18
|
-
.PP
|
19
|
-
The
|
20
|
-
.BR io_uring_register_file_alloc_range (3)
|
21
|
-
function sets the allowable range for fixed file index allocations within the
|
22
|
-
kernel. When requests that can instantiate a new fixed file are used with
|
23
|
-
.B IORING_FILE_INDEX_ALLOC ,
|
24
|
-
the application is asking the kernel to allocate a new fixed file descriptor
|
25
|
-
rather than pass in a specific value for one. By default, the kernel will
|
26
|
-
pick any available fixed file descriptor within the range available. Calling
|
27
|
-
this function with
|
28
|
-
.I off
|
29
|
-
set to the starting offset and
|
30
|
-
.I len
|
31
|
-
set to the number of descriptors, the application can limit the allocated
|
32
|
-
descriptors to that particular range. This effectively allows the application
|
33
|
-
to set aside a range just for dynamic allocations, with the remainder being
|
34
|
-
used for specific values.
|
35
|
-
|
36
|
-
The application must have registered a fixed file table upfront, eg through
|
37
|
-
.BR io_uring_register_files (3)
|
38
|
-
or
|
39
|
-
.BR io_uring_register_files_sparse (3) .
|
40
|
-
|
41
|
-
Available since 6.0.
|
42
|
-
|
43
|
-
.SH RETURN VALUE
|
44
|
-
On success
|
45
|
-
.BR io_uring_register_buf_ring (3)
|
46
|
-
returns 0. On failure it returns
|
47
|
-
.BR -errno .
|
48
|
-
.SH SEE ALSO
|
49
|
-
.BR io_uring_register_files (3)
|
50
|
-
.BR io_uring_prep_accept_direct (3)
|
51
|
-
.BR io_uring_prep_openat_direct (3)
|
52
|
-
.BR io_uring_prep_socket_direct (3)
|
@@ -1,112 +0,0 @@
|
|
1
|
-
.\" Copyright (C) 2021 Stefan Roesch <shr@fb.com>
|
2
|
-
.\"
|
3
|
-
.\" SPDX-License-Identifier: LGPL-2.0-or-later
|
4
|
-
.\"
|
5
|
-
.TH io_uring_register_files 3 "November 15, 2021" "liburing-2.1" "liburing Manual"
|
6
|
-
.SH NAME
|
7
|
-
io_uring_register_files \- register file descriptors
|
8
|
-
.SH SYNOPSIS
|
9
|
-
.nf
|
10
|
-
.B #include <liburing.h>
|
11
|
-
.PP
|
12
|
-
.BI "int io_uring_register_files(struct io_uring *" ring ","
|
13
|
-
.BI " const int *" files ","
|
14
|
-
.BI " unsigned " nr_files ");"
|
15
|
-
.PP
|
16
|
-
.BI "int io_uring_register_files_tags(struct io_uring *" ring ","
|
17
|
-
.BI " const int *" files ","
|
18
|
-
.BI " const __u64 *" tags ","
|
19
|
-
.BI " unsigned " nr ");"
|
20
|
-
.PP
|
21
|
-
.BI "int io_uring_register_files_sparse(struct io_uring *" ring ","
|
22
|
-
.BI " unsigned " nr_files ");"
|
23
|
-
.PP
|
24
|
-
.BI "int io_uring_register_files_update(struct io_uring *" ring ","
|
25
|
-
.BI " unsigned " off ","
|
26
|
-
.BI " const int *" files ","
|
27
|
-
.BI " unsigned " nr_files ");"
|
28
|
-
.PP
|
29
|
-
.BI "int io_uring_register_files_update_tag(struct io_uring *" ring ","
|
30
|
-
.BI " unsigned " off ","
|
31
|
-
.BI " const int *" files ","
|
32
|
-
.BI " const __u64 *" tags ","
|
33
|
-
.BI " unsigned " nr_files ");"
|
34
|
-
.fi
|
35
|
-
.SH DESCRIPTION
|
36
|
-
.PP
|
37
|
-
The
|
38
|
-
.BR io_uring_register_files (3)
|
39
|
-
function registers
|
40
|
-
.I nr_files
|
41
|
-
number of file descriptors defined by the array
|
42
|
-
.I files
|
43
|
-
belonging to the
|
44
|
-
.I ring
|
45
|
-
for subsequent operations.
|
46
|
-
|
47
|
-
The
|
48
|
-
.BR io_uring_register_files_tags (3)
|
49
|
-
function behaves the same as
|
50
|
-
.BR io_uring_register_files (3)
|
51
|
-
function but additionally takes
|
52
|
-
.I tags
|
53
|
-
parameter. See
|
54
|
-
.B IORING_REGISTER_BUFFERS2
|
55
|
-
for the resource tagging description.
|
56
|
-
|
57
|
-
The
|
58
|
-
.BR io_uring_register_files_sparse (3)
|
59
|
-
function registers an empty file table of
|
60
|
-
.I nr_files
|
61
|
-
number of file descriptors. These files must be updated before use, using eg
|
62
|
-
.BR io_uring_register_files_update_tag (3).
|
63
|
-
The sparse variant is available in kernels 5.19 and later.
|
64
|
-
|
65
|
-
Registering a file table is a prerequisite for using any request that uses
|
66
|
-
direct descriptors.
|
67
|
-
|
68
|
-
Registered files have less overhead per operation than normal files. This
|
69
|
-
is due to the kernel grabbing a reference count on a file when an operation
|
70
|
-
begins, and dropping it when it's done. When the process file table is
|
71
|
-
shared, for example if the process has ever created any threads, then this
|
72
|
-
cost goes up even more. Using registered files reduces the overhead of
|
73
|
-
file reference management across requests that operate on a file.
|
74
|
-
|
75
|
-
The
|
76
|
-
.BR io_uring_register_files_update (3)
|
77
|
-
function updates existing registered files. The
|
78
|
-
.I off
|
79
|
-
is offset on which to start the update
|
80
|
-
.I nr_files
|
81
|
-
number of files defined by the array
|
82
|
-
.I files
|
83
|
-
belonging to the
|
84
|
-
.IR ring .
|
85
|
-
|
86
|
-
The
|
87
|
-
.BR io_uring_register_files_update_tag (3)
|
88
|
-
function behaves the same as
|
89
|
-
.BR io_uring_register_files_update (3)
|
90
|
-
function but additionally takes
|
91
|
-
.I tags
|
92
|
-
parameter. See
|
93
|
-
.B IORING_REGISTER_BUFFERS2
|
94
|
-
for the resource tagging description.
|
95
|
-
|
96
|
-
.SH RETURN VALUE
|
97
|
-
On success
|
98
|
-
.BR io_uring_register_files (3),
|
99
|
-
.BR io_uring_register_files_tags (3)
|
100
|
-
and
|
101
|
-
.BR io_uring_register_files_sparse (3)
|
102
|
-
return 0.
|
103
|
-
.BR io_uring_register_files_update (3)
|
104
|
-
and
|
105
|
-
.BR io_uring_register_files_update_tag (3)
|
106
|
-
return number of files updated.
|
107
|
-
On failure they return
|
108
|
-
.BR -errno .
|
109
|
-
.SH SEE ALSO
|
110
|
-
.BR io_uring_register (2),
|
111
|
-
.BR io_uring_get_sqe (3),
|
112
|
-
.BR io_uring_unregister_files (3)
|
@@ -1 +0,0 @@
|
|
1
|
-
io_uring_register_files.3
|
@@ -1 +0,0 @@
|
|
1
|
-
io_uring_register_files.3
|
@@ -1 +0,0 @@
|
|
1
|
-
io_uring_register_files.3
|
@@ -1 +0,0 @@
|
|
1
|
-
io_uring_register_files.3
|
@@ -1,61 +0,0 @@
|
|
1
|
-
.\" Copyright (C) 2022 Jens Axboe <axboe@kernel.dk>
|
2
|
-
.\"
|
3
|
-
.\" SPDX-License-Identifier: LGPL-2.0-or-later
|
4
|
-
.\"
|
5
|
-
.TH io_uring_register_iowq_aff 3 "March 13, 2022" "liburing-2.2" "liburing Manual"
|
6
|
-
.SH NAME
|
7
|
-
io_uring_register_iowq_aff \- register async worker CPU affinities
|
8
|
-
.SH SYNOPSIS
|
9
|
-
.nf
|
10
|
-
.B #include <sched.h>
|
11
|
-
.B #include <liburing.h>
|
12
|
-
.PP
|
13
|
-
.BI "int io_uring_register_iowq_aff(struct io_uring *" ring ","
|
14
|
-
.BI " size_t " cpusz ","
|
15
|
-
.BI " const cpu_set_t *" mask ");
|
16
|
-
.PP
|
17
|
-
.BI "void io_uring_unregister_iowq_aff(struct io_uring *" ring ");"
|
18
|
-
.fi
|
19
|
-
.SH DESCRIPTION
|
20
|
-
.PP
|
21
|
-
The
|
22
|
-
.BR io_uring_prep_register_iowq_aff (3)
|
23
|
-
function registers a set of CPU affinities to be used by the io_uring async
|
24
|
-
workers. By default, io_uring async workers are allowed to run on any CPU in
|
25
|
-
the system. If this function is called with
|
26
|
-
.I ring
|
27
|
-
set to the ring in question and
|
28
|
-
.I mask
|
29
|
-
set to a pointer to a
|
30
|
-
.B cpu_set_t
|
31
|
-
value and
|
32
|
-
.I cpusz
|
33
|
-
set to the size of the CPU set, then async workers will only be allowed to run
|
34
|
-
on the CPUs specified in the mask. Existing workers may need to hit a schedule
|
35
|
-
point before they are migrated.
|
36
|
-
|
37
|
-
For unregistration,
|
38
|
-
.BR io_uring_unregister_iowq_aff (3)
|
39
|
-
may be called to restore CPU affinities to the default.
|
40
|
-
|
41
|
-
.SH RETURN VALUE
|
42
|
-
Returns
|
43
|
-
.B 0
|
44
|
-
on success, or any of the following values in case of error.
|
45
|
-
.TP
|
46
|
-
.B -EFAULT
|
47
|
-
The kernel was unable to copy the memory pointer to by
|
48
|
-
.I mask
|
49
|
-
as it was invalid.
|
50
|
-
.TP
|
51
|
-
.B -ENOMEM
|
52
|
-
The kernel was unable to allocate memory for the new CPU mask.
|
53
|
-
.TP
|
54
|
-
.B -EINVAL
|
55
|
-
.I cpusz
|
56
|
-
or
|
57
|
-
.I mask
|
58
|
-
was NULL/0, or any other value specified was invalid.
|
59
|
-
.SH SEE ALSO
|
60
|
-
.BR io_uring_queue_init (3),
|
61
|
-
.BR io_uring_register (2)
|
@@ -1,71 +0,0 @@
|
|
1
|
-
.\" Copyright (C) 2022 Jens Axboe <axboe@kernel.dk>
|
2
|
-
.\"
|
3
|
-
.\" SPDX-License-Identifier: LGPL-2.0-or-later
|
4
|
-
.\"
|
5
|
-
.TH io_uring_register_iowq_max_workers 3 "March 13, 2022" "liburing-2.2" "liburing Manual"
|
6
|
-
.SH NAME
|
7
|
-
io_uring_register_iowq_max_workers \- modify the maximum allowed async workers
|
8
|
-
.SH SYNOPSIS
|
9
|
-
.nf
|
10
|
-
.B #include <liburing.h>
|
11
|
-
.PP
|
12
|
-
.BI "int io_uring_register_iowq_max_workers(struct io_uring *" ring ","
|
13
|
-
.BI " unsigned int *" values ");"
|
14
|
-
.fi
|
15
|
-
.SH DESCRIPTION
|
16
|
-
.PP
|
17
|
-
io_uring async workers are split into two types:
|
18
|
-
.TP
|
19
|
-
.B Bounded
|
20
|
-
These workers have a bounded execution time. Examples of that are filesystem
|
21
|
-
reads, which normally complete in a relatively short amount of time. In case
|
22
|
-
of disk failures, they are still bounded by a timeout operation that will
|
23
|
-
abort them if exceeded.
|
24
|
-
.TP
|
25
|
-
.B Unbounded
|
26
|
-
Work items here may take an indefinite amount of time to complete. Examples
|
27
|
-
include doing IO to sockets, pipes, or any other non-regular type of file.
|
28
|
-
|
29
|
-
.PP
|
30
|
-
By default, the amount of bounded IO workers is limited to how many SQ entries
|
31
|
-
the ring was setup with, or 4 times the number of online CPUs in the system,
|
32
|
-
whichever is smaller. Unbounded workers are only limited by the process task
|
33
|
-
limit, as indicated by the rlimit
|
34
|
-
.B RLIMIT_NPROC
|
35
|
-
limit.
|
36
|
-
|
37
|
-
This can be modified by calling
|
38
|
-
.B io_uring_register_iowq_max_workers
|
39
|
-
with
|
40
|
-
.I ring
|
41
|
-
set to the ring in question, and
|
42
|
-
.I values
|
43
|
-
pointing to an array of two values. The first element should contain the number
|
44
|
-
of desired bounded workers, and the second element should contain the number
|
45
|
-
of desired unbounded workers. These are both maximum values, io_uring will
|
46
|
-
not maintain a high count of idle workers, they are reaped when they are not
|
47
|
-
necessary anymore.
|
48
|
-
|
49
|
-
If called with both values set to 0, the existing values are returned.
|
50
|
-
|
51
|
-
.SH RETURN VALUE
|
52
|
-
Returns
|
53
|
-
.B 0
|
54
|
-
on success, with
|
55
|
-
.I values
|
56
|
-
containing the previous values for the settings. On error, any of the following
|
57
|
-
may be returned.
|
58
|
-
.TP
|
59
|
-
.B -EFAULT
|
60
|
-
The kernel was unable to copy the memory pointer to by
|
61
|
-
.I values
|
62
|
-
as it was invalid.
|
63
|
-
.TP
|
64
|
-
.B -EINVAL
|
65
|
-
.I values
|
66
|
-
was
|
67
|
-
.B NULL
|
68
|
-
or the new values exceeded the maximum allowed value.
|
69
|
-
.SH SEE ALSO
|
70
|
-
.BR io_uring_queue_init (3),
|
71
|
-
.BR io_uring_register (2)
|
@@ -1,49 +0,0 @@
|
|
1
|
-
.\" Copyright (C) 2022 Jens Axboe <axboe@kernel.dk>
|
2
|
-
.\"
|
3
|
-
.\" SPDX-License-Identifier: LGPL-2.0-or-later
|
4
|
-
.\"
|
5
|
-
.TH io_uring_register_ring_fd 3 "March 11, 2022" "liburing-2.2" "liburing Manual"
|
6
|
-
.SH NAME
|
7
|
-
io_uring_register_ring_fd \- register a ring file descriptor
|
8
|
-
.SH SYNOPSIS
|
9
|
-
.nf
|
10
|
-
.B #include <liburing.h>
|
11
|
-
.PP
|
12
|
-
.BI "int io_uring_register_ring_fd(struct io_uring *" ring ");"
|
13
|
-
.fi
|
14
|
-
.SH DESCRIPTION
|
15
|
-
.PP
|
16
|
-
.BR io_uring_register_ring_fd (3)
|
17
|
-
registers the file descriptor of the ring.
|
18
|
-
|
19
|
-
Whenever
|
20
|
-
.BR io_uring_enter (2)
|
21
|
-
is called to submit request or wait for completions, the kernel must grab a
|
22
|
-
reference to the file descriptor. If the application using io_uring is threaded,
|
23
|
-
the file table is marked as shared, and the reference grab and put of the file
|
24
|
-
descriptor count is more expensive than it is for a non-threaded application.
|
25
|
-
|
26
|
-
Similarly to how io_uring allows registration of files, this allow registration
|
27
|
-
of the ring file descriptor itself. This reduces the overhead of the
|
28
|
-
.BR io_uring_enter (2)
|
29
|
-
system call.
|
30
|
-
|
31
|
-
If an application using liburing is threaded, then an application should call
|
32
|
-
this function to register the ring descriptor when a ring is set up. See NOTES
|
33
|
-
for restrictions when a ring is shared.
|
34
|
-
|
35
|
-
.SH NOTES
|
36
|
-
When the ring descriptor is registered, it is stored internally in the
|
37
|
-
.I struct io_uring
|
38
|
-
structure. For applications that share a ring between threads, for example
|
39
|
-
having one thread do submits and another reap events, then this optimization
|
40
|
-
cannot be used as each thread may have a different index for the registered
|
41
|
-
ring fd.
|
42
|
-
.SH RETURN VALUE
|
43
|
-
Returns 1 on success, indicating that one file descriptor was registered,
|
44
|
-
or
|
45
|
-
.BR -errno
|
46
|
-
on error.
|
47
|
-
.SH SEE ALSO
|
48
|
-
.BR io_uring_unregister_ring_fd (3),
|
49
|
-
.BR io_uring_register_files (3)
|