qemu/util/aio-posix.h

83 lines
2.0 KiB
C
Raw Normal View History

/*
* AioContext POSIX event loop implementation internal APIs
*
* Copyright IBM, Corp. 2008
* Copyright Red Hat, Inc. 2020
*
* Authors:
* Anthony Liguori <aliguori@us.ibm.com>
*
* This work is licensed under the terms of the GNU GPL, version 2. See
* the COPYING file in the top-level directory.
*
* Contributions after 2012-01-13 are licensed under the terms of the
* GNU GPL, version 2 or (at your option) any later version.
*/
#ifndef AIO_POSIX_H
#define AIO_POSIX_H
#include "block/aio.h"
struct AioHandler {
GPollFD pfd;
IOHandler *io_read;
IOHandler *io_write;
AioPollFn *io_poll;
aio-posix: split poll check from ready handler Adaptive polling measures the execution time of the polling check plus handlers called when a polled event becomes ready. Handlers can take a significant amount of time, making it look like polling was running for a long time when in fact the event handler was running for a long time. For example, on Linux the io_submit(2) syscall invoked when a virtio-blk device's virtqueue becomes ready can take 10s of microseconds. This can exceed the default polling interval (32 microseconds) and cause adaptive polling to stop polling. By excluding the handler's execution time from the polling check we make the adaptive polling calculation more accurate. As a result, the event loop now stays in polling mode where previously it would have fallen back to file descriptor monitoring. The following data was collected with virtio-blk num-queues=2 event_idx=off using an IOThread. Before: 168k IOPS, IOThread syscalls: 9837.115 ( 0.020 ms): IO iothread1/620155 io_submit(ctx_id: 140512552468480, nr: 16, iocbpp: 0x7fcb9f937db0) = 16 9837.158 ( 0.002 ms): IO iothread1/620155 write(fd: 103, buf: 0x556a2ef71b88, count: 8) = 8 9837.161 ( 0.001 ms): IO iothread1/620155 write(fd: 104, buf: 0x556a2ef71b88, count: 8) = 8 9837.163 ( 0.001 ms): IO iothread1/620155 ppoll(ufds: 0x7fcb90002800, nfds: 4, tsp: 0x7fcb9f1342d0, sigsetsize: 8) = 3 9837.164 ( 0.001 ms): IO iothread1/620155 read(fd: 107, buf: 0x7fcb9f939cc0, count: 512) = 8 9837.174 ( 0.001 ms): IO iothread1/620155 read(fd: 105, buf: 0x7fcb9f939cc0, count: 512) = 8 9837.176 ( 0.001 ms): IO iothread1/620155 read(fd: 106, buf: 0x7fcb9f939cc0, count: 512) = 8 9837.209 ( 0.035 ms): IO iothread1/620155 io_submit(ctx_id: 140512552468480, nr: 32, iocbpp: 0x7fca7d0cebe0) = 32 174k IOPS (+3.6%), IOThread syscalls: 9809.566 ( 0.036 ms): IO iothread1/623061 io_submit(ctx_id: 140539805028352, nr: 32, iocbpp: 0x7fd0cdd62be0) = 32 9809.625 ( 0.001 ms): IO iothread1/623061 write(fd: 103, buf: 0x5647cfba5f58, count: 8) = 8 9809.627 ( 0.002 ms): IO iothread1/623061 write(fd: 104, buf: 0x5647cfba5f58, count: 8) = 8 9809.663 ( 0.036 ms): IO iothread1/623061 io_submit(ctx_id: 140539805028352, nr: 32, iocbpp: 0x7fd0d0388b50) = 32 Notice that ppoll(2) and eventfd read(2) syscalls are eliminated because the IOThread stays in polling mode instead of falling back to file descriptor monitoring. As usual, polling is not implemented on Windows so this patch ignores the new io_poll_read() callback in aio-win32.c. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Stefano Garzarella <sgarzare@redhat.com> Message-id: 20211207132336.36627-2-stefanha@redhat.com [Fixed up aio_set_event_notifier() calls in tests/unit/test-fdmon-epoll.c added after this series was queued. --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2021-12-07 21:23:31 +08:00
IOHandler *io_poll_ready;
IOHandler *io_poll_begin;
IOHandler *io_poll_end;
void *opaque;
QLIST_ENTRY(AioHandler) node;
QLIST_ENTRY(AioHandler) node_ready; /* only used during aio_poll() */
QLIST_ENTRY(AioHandler) node_deleted;
QLIST_ENTRY(AioHandler) node_poll;
#ifdef CONFIG_LINUX_IO_URING
QSLIST_ENTRY(AioHandler) node_submitted;
unsigned flags; /* see fdmon-io_uring.c */
#endif
int64_t poll_idle_timeout; /* when to stop userspace polling */
bool is_external;
};
/* Add a handler to a ready list */
void aio_add_ready_handler(AioHandlerList *ready_list, AioHandler *node,
int revents);
extern const FDMonOps fdmon_poll_ops;
#ifdef CONFIG_EPOLL_CREATE1
bool fdmon_epoll_try_upgrade(AioContext *ctx, unsigned npfd);
void fdmon_epoll_setup(AioContext *ctx);
void fdmon_epoll_disable(AioContext *ctx);
#else
static inline bool fdmon_epoll_try_upgrade(AioContext *ctx, unsigned npfd)
{
return false;
}
static inline void fdmon_epoll_setup(AioContext *ctx)
{
}
static inline void fdmon_epoll_disable(AioContext *ctx)
{
}
#endif /* !CONFIG_EPOLL_CREATE1 */
#ifdef CONFIG_LINUX_IO_URING
bool fdmon_io_uring_setup(AioContext *ctx);
void fdmon_io_uring_destroy(AioContext *ctx);
#else
static inline bool fdmon_io_uring_setup(AioContext *ctx)
{
return false;
}
static inline void fdmon_io_uring_destroy(AioContext *ctx)
{
}
#endif /* !CONFIG_LINUX_IO_URING */
#endif /* AIO_POSIX_H */