Right now we punt any buffered request that ends up triggering an
-EAGAIN to an async workqueue. This works fine in terms of providing
async execution of them, but it also can create quite a lot of work
queue items. For sequentially buffered IO, it's advantageous to
serialize the issue of them. For reads, the first one will trigger a
read-ahead, and subsequent request merely end up waiting on later pages
to complete. For writes, devices usually respond better to streamed
sequential writes.
Add state to track the last buffered request we punted to a work queue,
and if the next one is sequential to the previous, attempt to get the
previous work item to handle it. We limit the number of sequential
add-ons to the a multiple (8) of the max read-ahead size of the file.
This should be a good number for both reads and wries, as it defines the
max IO size the device can do directly.
This drastically cuts down on the number of context switches we need to
handle buffered sequential IO, and a basic test case of copying a big
file with io_uring sees a 5x speedup.
Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>
---
fs/io_uring.c | 231 ++++++++++++++++++++++++++++++++++++++++++--------
1 file changed, 194 insertions(+), 37 deletions(-)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index fe75931d7df5..aa903fa902d5 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -68,6 +68,16 @@ struct io_mapped_ubuf {
unsigned int nr_bvecs;
};
+struct async_list {
+ spinlock_t lock;
+ atomic_t cnt;
+ struct list_head list;
+
+ struct file *file;
+ off_t io_end;
+ size_t io_pages;
+};
+
struct io_ring_ctx {
struct {
struct percpu_ref refs;
@@ -126,6 +136,8 @@ struct io_ring_ctx {
struct list_head poll_list;
struct list_head cancel_list;
} ____cacheline_aligned_in_smp;
+
+ struct async_list pending_async[2];
};
struct sqe_submit {
@@ -157,6 +169,7 @@ struct io_kiocb {
#define REQ_F_IOPOLL_COMPLETED 2 /* polled IO has completed */
#define REQ_F_IOPOLL_EAGAIN 4 /* submission got EAGAIN */
#define REQ_F_FIXED_FILE 8 /* ctx owns file */
+#define REQ_F_SEQ_PREV 16 /* sequential with previous */
u64 user_data;
u64 res;
@@ -200,6 +213,7 @@ static void io_ring_ctx_ref_free(struct percpu_ref *ref)
static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
{
struct io_ring_ctx *ctx;
+ int i;
ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
if (!ctx)
@@ -215,6 +229,11 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
init_completion(&ctx->ctx_done);
mutex_init(&ctx->uring_lock);
init_waitqueue_head(&ctx->wait);
+ for (i = 0; i < ARRAY_SIZE(ctx->pending_async); i++) {
+ spin_lock_init(&ctx->pending_async[i].lock);
+ INIT_LIST_HEAD(&ctx->pending_async[i].list);
+ atomic_set(&ctx->pending_async[i].cnt, 0);
+ }
spin_lock_init(&ctx->completion_lock);
INIT_LIST_HEAD(&ctx->poll_list);
INIT_LIST_HEAD(&ctx->cancel_list);
@@ -774,6 +793,39 @@ static int io_import_iovec(struct io_ring_ctx *ctx, int rw,
return import_iovec(rw, buf, sqe->len, UIO_FASTIOV, iovec, iter);
}
+static void io_async_list_note(int rw, struct io_kiocb *req, size_t len)
+{
+ struct async_list *async_list = &req->ctx->pending_async[rw];
+ struct kiocb *kiocb = &req->rw;
+ struct file *filp = kiocb->ki_filp;
+ off_t io_end = kiocb->ki_pos + len;
+
+ if (filp == async_list->file && kiocb->ki_pos == async_list->io_end) {
+ unsigned long max_pages;
+
+ /* Use 8x RA size as a decent limiter for both reads/writes */
+ max_pages = filp->f_ra.ra_pages;
+ if (!max_pages)
+ max_pages = VM_MAX_READAHEAD >> (PAGE_SHIFT - 10);
+ max_pages *= 8;
+
+ len >>= PAGE_SHIFT;
+ if (async_list->io_pages + len <= max_pages) {
+ req->flags |= REQ_F_SEQ_PREV;
+ async_list->io_pages += len;
+ } else {
+ io_end = 0;
+ async_list->io_pages = 0;
+ }
+ }
+
+ if (async_list->file != filp) {
+ async_list->io_pages = 0;
+ async_list->file = filp;
+ }
+ async_list->io_end = io_end;
+}
+
static ssize_t io_read(struct io_kiocb *req, const struct io_uring_sqe *sqe,
bool force_nonblock, struct io_submit_state *state)
{
@@ -781,6 +833,7 @@ static ssize_t io_read(struct io_kiocb *req, const struct io_uring_sqe *sqe,
struct kiocb *kiocb = &req->rw;
struct iov_iter iter;
struct file *file;
+ size_t iov_count;
ssize_t ret;
ret = io_prep_rw(req, sqe, force_nonblock, state);
@@ -799,16 +852,19 @@ static ssize_t io_read(struct io_kiocb *req, const struct io_uring_sqe *sqe,
if (ret)
goto out_fput;
- ret = rw_verify_area(READ, file, &kiocb->ki_pos, iov_iter_count(&iter));
+ iov_count = iov_iter_count(&iter);
+ ret = rw_verify_area(READ, file, &kiocb->ki_pos, iov_count);
if (!ret) {
ssize_t ret2;
/* Catch -EAGAIN return for forced non-blocking submission */
ret2 = call_read_iter(file, kiocb, &iter);
- if (!force_nonblock || ret2 != -EAGAIN)
+ if (!force_nonblock || ret2 != -EAGAIN) {
io_rw_done(kiocb, ret2);
- else
+ } else {
+ io_async_list_note(READ, req, iov_count);
ret = -EAGAIN;
+ }
}
kfree(iovec);
out_fput:
@@ -824,6 +880,7 @@ static ssize_t io_write(struct io_kiocb *req, const struct io_uring_sqe *sqe,
struct kiocb *kiocb = &req->rw;
struct iov_iter iter;
struct file *file;
+ size_t iov_count;
ssize_t ret;
ret = io_prep_rw(req, sqe, force_nonblock, state);
@@ -831,10 +888,6 @@ static ssize_t io_write(struct io_kiocb *req, const struct io_uring_sqe *sqe,
return ret;
file = kiocb->ki_filp;
- ret = -EAGAIN;
- if (force_nonblock && !(kiocb->ki_flags & IOCB_DIRECT))
- goto out_fput;
-
ret = -EBADF;
if (unlikely(!(file->f_mode & FMODE_WRITE)))
goto out_fput;
@@ -846,8 +899,15 @@ static ssize_t io_write(struct io_kiocb *req, const struct io_uring_sqe *sqe,
if (ret)
goto out_fput;
- ret = rw_verify_area(WRITE, file, &kiocb->ki_pos,
- iov_iter_count(&iter));
+ iov_count = iov_iter_count(&iter);
+
+ ret = -EAGAIN;
+ if (force_nonblock && !(kiocb->ki_flags & IOCB_DIRECT)) {
+ io_async_list_note(WRITE, req, iov_count);
+ goto out_free;
+ }
+
+ ret = rw_verify_area(WRITE, file, &kiocb->ki_pos, iov_count);
if (!ret) {
/*
* Open-code file_start_write here to grab freeze protection,
@@ -865,6 +925,7 @@ static ssize_t io_write(struct io_kiocb *req, const struct io_uring_sqe *sqe,
kiocb->ki_flags |= IOCB_WRITE;
io_rw_done(kiocb, call_write_iter(file, kiocb, &iter));
}
+out_free:
kfree(iovec);
out_fput:
if (unlikely(ret))
@@ -1212,6 +1273,21 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
return 0;
}
+static struct async_list *io_async_list_from_sqe(struct io_ring_ctx *ctx,
+ const struct io_uring_sqe *sqe)
+{
+ switch (sqe->opcode) {
+ case IORING_OP_READV:
+ case IORING_OP_READ_FIXED:
+ return &ctx->pending_async[READ];
+ case IORING_OP_WRITEV:
+ case IORING_OP_WRITE_FIXED:
+ return &ctx->pending_async[WRITE];
+ default:
+ return NULL;
+ }
+}
+
static inline bool io_sqe_needs_user(const struct io_uring_sqe *sqe)
{
return !(sqe->opcode == IORING_OP_READ_FIXED ||
@@ -1221,50 +1297,124 @@ static inline bool io_sqe_needs_user(const struct io_uring_sqe *sqe)
static void io_sq_wq_submit_work(struct work_struct *work)
{
struct io_kiocb *req = container_of(work, struct io_kiocb, work);
- struct sqe_submit *s = &req->submit;
- u64 user_data = s->sqe->user_data;
struct io_ring_ctx *ctx = req->ctx;
+ struct mm_struct *cur_mm = NULL;
struct files_struct *old_files;
+ struct async_list *async_list;
+ LIST_HEAD(req_list);
mm_segment_t old_fs;
- bool needs_user;
int ret;
- /* Ensure we clear previously set forced non-block flag */
- req->flags &= ~REQ_F_FORCE_NONBLOCK;
-
old_files = current->files;
current->files = ctx->sqo_files;
+ async_list = io_async_list_from_sqe(ctx, req->submit.sqe);
+restart:
+ do {
+ struct sqe_submit *s = &req->submit;
+ u64 user_data = s->sqe->user_data;
+
+ /* Ensure we clear previously set forced non-block flag */
+ req->flags &= ~REQ_F_FORCE_NONBLOCK;
+
+ ret = 0;
+ if (io_sqe_needs_user(s->sqe) && !cur_mm) {
+ if (!mmget_not_zero(ctx->sqo_mm)) {
+ ret = -EFAULT;
+ } else {
+ cur_mm = ctx->sqo_mm;;
+ use_mm(ctx->sqo_mm);
+ old_fs = get_fs();
+ set_fs(USER_DS);
+ }
+ }
+
+ if (!ret)
+ ret = __io_submit_sqe(ctx, req, s, false, NULL);
+ if (ret) {
+ io_cqring_add_event(ctx, user_data, ret, 0);
+ io_free_req(req);
+ }
+ if (!async_list)
+ break;
+ if (!list_empty(&req_list)) {
+ req = list_first_entry(&req_list, struct io_kiocb,
+ list);
+ list_del(&req->list);
+ continue;
+ }
+ if (list_empty(&async_list->list))
+ break;
+
+ req = NULL;
+ spin_lock(&async_list->lock);
+ if (list_empty(&async_list->list)) {
+ spin_unlock(&async_list->lock);
+ break;
+ }
+ list_splice_init(&async_list->list, &req_list);
+ spin_unlock(&async_list->lock);
+
+ req = list_first_entry(&req_list, struct io_kiocb, list);
+ list_del(&req->list);
+ } while (req);
+
/*
- * If we're doing IO to fixed buffers, we don't need to get/set
- * user context
+ * Rare case of racing with a submitter. If we find the count has
+ * dropped to zero AND we have pending work items, then restart
+ * the processing. This is a tiny race window.
*/
- needs_user = io_sqe_needs_user(s->sqe);
- if (needs_user) {
- if (!mmget_not_zero(ctx->sqo_mm)) {
- ret = -EFAULT;
- goto err;
+ ret = atomic_dec_return(&async_list->cnt);
+ while (!ret && !list_empty(&async_list->list)) {
+ spin_lock(&async_list->lock);
+ atomic_inc(&async_list->cnt);
+ list_splice_init(&async_list->list, &req_list);
+ spin_unlock(&async_list->lock);
+
+ if (!list_empty(&req_list)) {
+ req = list_first_entry(&req_list, struct io_kiocb,
+ list);
+ list_del(&req->list);
+ goto restart;
}
- use_mm(ctx->sqo_mm);
- old_fs = get_fs();
- set_fs(USER_DS);
+ ret = atomic_dec_return(&async_list->cnt);
}
- ret = __io_submit_sqe(ctx, req, s, false, NULL);
-
- if (needs_user) {
+ if (cur_mm) {
set_fs(old_fs);
- unuse_mm(ctx->sqo_mm);
- mmput(ctx->sqo_mm);
- }
-err:
- if (ret) {
- io_cqring_add_event(ctx, user_data, ret, 0);
- io_free_req(req);
+ unuse_mm(cur_mm);
+ mmput(cur_mm);
}
current->files = old_files;
}
+/*
+ * See if we can piggy back onto previously submitted work, that is still
+ * running. We currently only allow this if the new request is sequential
+ * to the previous one we punted.
+ */
+static bool io_add_to_prev_work(struct async_list *list, struct io_kiocb *req)
+{
+ bool ret = false;
+
+ if (!list)
+ return false;
+ if (!(req->flags & REQ_F_SEQ_PREV))
+ return false;
+ if (!atomic_read(&list->cnt))
+ return false;
+
+ ret = true;
+ spin_lock(&list->lock);
+ list_add_tail(&req->list, &list->list);
+ if (!atomic_read(&list->cnt)) {
+ list_del_init(&req->list);
+ ret = false;
+ }
+ spin_unlock(&list->lock);
+ return ret;
+}
+
static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s,
struct io_submit_state *state)
{
@@ -1281,9 +1431,16 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s,
ret = __io_submit_sqe(ctx, req, s, true, state);
if (ret == -EAGAIN) {
+ struct async_list *list;
+
+ list = io_async_list_from_sqe(ctx, s->sqe);
memcpy(&req->submit, s, sizeof(*s));
- INIT_WORK(&req->work, io_sq_wq_submit_work);
- queue_work(ctx->sqo_wq, &req->work);
+ if (!io_add_to_prev_work(list, req)) {
+ if (list)
+ atomic_inc(&list->cnt);
+ INIT_WORK(&req->work, io_sq_wq_submit_work);
+ queue_work(ctx->sqo_wq, &req->work);
+ }
ret = 0;
}
if (ret)
--
2.17.1
