qemu-patch-raspberry4/util/trace-events
Stefan Hajnoczi d37d0e365a aio-posix: remove idle poll handlers to improve scalability
When there are many poll handlers it's likely that some of them are idle
most of the time.  Remove handlers that haven't had activity recently so
that the polling loop scales better for guests with a large number of
devices.

This feature only takes effect for the Linux io_uring fd monitoring
implementation because it is capable of combining fd monitoring with
userspace polling.  The other implementations can't do that and risk
starving fds in favor of poll handlers, so don't try this optimization
when they are in use.

IOPS improves from 10k to 105k when the guest has 100
virtio-blk-pci,num-queues=32 devices and 1 virtio-blk-pci,num-queues=1
device for rw=randread,iodepth=1,bs=4k,ioengine=libaio on NVMe.

[Clarified aio_poll_handlers locking discipline explanation in comment
after discussion with Paolo Bonzini <pbonzini@redhat.com>.
--Stefan]

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Link: https://lore.kernel.org/r/20200305170806.1313245-8-stefanha@redhat.com
Message-Id: <20200305170806.1313245-8-stefanha@redhat.com>
2020-03-09 16:45:16 +00:00

86 lines
5.4 KiB
Plaintext

# See docs/devel/tracing.txt for syntax documentation.
# aio-posix.c
run_poll_handlers_begin(void *ctx, int64_t max_ns, int64_t timeout) "ctx %p max_ns %"PRId64 " timeout %"PRId64
run_poll_handlers_end(void *ctx, bool progress, int64_t timeout) "ctx %p progress %d new timeout %"PRId64
poll_shrink(void *ctx, int64_t old, int64_t new) "ctx %p old %"PRId64" new %"PRId64
poll_grow(void *ctx, int64_t old, int64_t new) "ctx %p old %"PRId64" new %"PRId64
poll_add(void *ctx, void *node, int fd, unsigned revents) "ctx %p node %p fd %d revents 0x%x"
poll_remove(void *ctx, void *node, int fd) "ctx %p node %p fd %d"
# async.c
aio_co_schedule(void *ctx, void *co) "ctx %p co %p"
aio_co_schedule_bh_cb(void *ctx, void *co) "ctx %p co %p"
# thread-pool.c
thread_pool_submit(void *pool, void *req, void *opaque) "pool %p req %p opaque %p"
thread_pool_complete(void *pool, void *req, void *opaque, int ret) "pool %p req %p opaque %p ret %d"
thread_pool_cancel(void *req, void *opaque) "req %p opaque %p"
# buffer.c
buffer_resize(const char *buf, size_t olen, size_t len) "%s: old %zd, new %zd"
buffer_move_empty(const char *buf, size_t len, const char *from) "%s: %zd bytes from %s"
buffer_move(const char *buf, size_t len, const char *from) "%s: %zd bytes from %s"
buffer_free(const char *buf, size_t len) "%s: capacity %zd"
# filemonitor-inotify.c
qemu_file_monitor_add_watch(void *mon, const char *dirpath, const char *filename, void *cb, void *opaque, int64_t id) "File monitor %p add watch dir='%s' file='%s' cb=%p opaque=%p id=%" PRId64
qemu_file_monitor_remove_watch(void *mon, const char *dirpath, int64_t id) "File monitor %p remove watch dir='%s' id=%" PRId64
qemu_file_monitor_new(void *mon, int fd) "File monitor %p created fd=%d"
qemu_file_monitor_enable_watch(void *mon, const char *dirpath, int id) "File monitor %p enable watch dir='%s' id=%u"
qemu_file_monitor_disable_watch(void *mon, const char *dirpath, int id) "Fle monitor %p disable watch dir='%s' id=%u"
qemu_file_monitor_event(void *mon, const char *dirpath, const char *filename, int mask, unsigned int id) "File monitor %p event dir='%s' file='%s' mask=0x%x id=%u"
qemu_file_monitor_dispatch(void *mon, const char *dirpath, const char *filename, int ev, void *cb, void *opaque, int64_t id) "File monitor %p dispatch dir='%s' file='%s' ev=%d cb=%p opaque=%p id=%" PRId64
# qemu-coroutine.c
qemu_aio_coroutine_enter(void *ctx, void *from, void *to, void *opaque) "ctx %p from %p to %p opaque %p"
qemu_coroutine_yield(void *from, void *to) "from %p to %p"
qemu_coroutine_terminate(void *co) "self %p"
# qemu-coroutine-lock.c
qemu_co_mutex_lock_uncontended(void *mutex, void *self) "mutex %p self %p"
qemu_co_mutex_lock_entry(void *mutex, void *self) "mutex %p self %p"
qemu_co_mutex_lock_return(void *mutex, void *self) "mutex %p self %p"
qemu_co_mutex_unlock_entry(void *mutex, void *self) "mutex %p self %p"
qemu_co_mutex_unlock_return(void *mutex, void *self) "mutex %p self %p"
# oslib-win32.c
# oslib-posix.c
qemu_memalign(size_t alignment, size_t size, void *ptr) "alignment %zu size %zu ptr %p"
qemu_anon_ram_alloc(size_t size, void *ptr) "size %zu ptr %p"
qemu_vfree(void *ptr) "ptr %p"
qemu_anon_ram_free(void *ptr, size_t size) "ptr %p size %zu"
# hbitmap.c
hbitmap_iter_skip_words(const void *hb, void *hbi, uint64_t pos, unsigned long cur) "hb %p hbi %p pos %"PRId64" cur 0x%lx"
hbitmap_reset(void *hb, uint64_t start, uint64_t count, uint64_t sbit, uint64_t ebit) "hb %p items %"PRIu64",%"PRIu64" bits %"PRIu64"..%"PRIu64
hbitmap_set(void *hb, uint64_t start, uint64_t count, uint64_t sbit, uint64_t ebit) "hb %p items %"PRIu64",%"PRIu64" bits %"PRIu64"..%"PRIu64
# lockcnt.c
lockcnt_fast_path_attempt(const void *lockcnt, int expected, int new) "lockcnt %p fast path %d->%d"
lockcnt_fast_path_success(const void *lockcnt, int expected, int new) "lockcnt %p fast path %d->%d succeeded"
lockcnt_unlock_attempt(const void *lockcnt, int expected, int new) "lockcnt %p unlock %d->%d"
lockcnt_unlock_success(const void *lockcnt, int expected, int new) "lockcnt %p unlock %d->%d succeeded"
lockcnt_futex_wait_prepare(const void *lockcnt, int expected, int new) "lockcnt %p preparing slow path %d->%d"
lockcnt_futex_wait(const void *lockcnt, int val) "lockcnt %p waiting on %d"
lockcnt_futex_wait_resume(const void *lockcnt, int new) "lockcnt %p after wait: %d"
lockcnt_futex_wake(const void *lockcnt) "lockcnt %p waking up one waiter"
# qemu-sockets.c
socket_listen(int num) "backlog: %d"
# qemu-thread-common.h
qemu_mutex_lock(void *mutex, const char *file, const int line) "waiting on mutex %p (%s:%d)"
qemu_mutex_locked(void *mutex, const char *file, const int line) "taken mutex %p (%s:%d)"
qemu_mutex_unlock(void *mutex, const char *file, const int line) "released mutex %p (%s:%d)"
# vfio-helpers.c
qemu_vfio_dma_reset_temporary(void *s) "s %p"
qemu_vfio_ram_block_added(void *s, void *p, size_t size) "s %p host %p size 0x%zx"
qemu_vfio_ram_block_removed(void *s, void *p, size_t size) "s %p host %p size 0x%zx"
qemu_vfio_find_mapping(void *s, void *p) "s %p host %p"
qemu_vfio_new_mapping(void *s, void *host, size_t size, int index, uint64_t iova) "s %p host %p size %zu index %d iova 0x%"PRIx64
qemu_vfio_do_mapping(void *s, void *host, size_t size, uint64_t iova) "s %p host %p size %zu iova 0x%"PRIx64
qemu_vfio_dma_map(void *s, void *host, size_t size, bool temporary, uint64_t *iova) "s %p host %p size %zu temporary %d iova %p"
qemu_vfio_dma_unmap(void *s, void *host) "s %p host %p"