From: Jens Axboe <axboe@kernel.dk>
To: linux-block@vger.kernel.org, linux-aio@kvack.org,
linux-fsdevel@vger.kernel.org
Cc: Jens Axboe <axboe@kernel.dk>
Subject: [PATCH 18/20] aio: add submission side request cache
Date: Mon, 26 Nov 2018 09:45:42 -0700 [thread overview]
Message-ID: <20181126164544.5699-19-axboe@kernel.dk> (raw)
In-Reply-To: <20181126164544.5699-1-axboe@kernel.dk>
We have to add each submitted polled request to the io_context
poll_submitted list, which means we have to grab the poll_lock. We
already use the block plug to batch submissions if we're doing a batch
of IO submissions, extend that to cover the poll requests internally as
well.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
fs/aio.c | 136 +++++++++++++++++++++++++++++++++++++++++++++----------
1 file changed, 113 insertions(+), 23 deletions(-)
diff --git a/fs/aio.c b/fs/aio.c
index db73c8af1a0a..74afd1ff7fc9 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -247,6 +247,15 @@ static const struct address_space_operations aio_ctx_aops;
static const unsigned int iocb_page_shift =
ilog2(PAGE_SIZE / sizeof(struct iocb));
+/*
+ * We rely on block level unplugs to flush pending requests, if we schedule
+ */
+#ifdef CONFIG_BLOCK
+static const bool aio_use_state_req_list = true;
+#else
+static const bool aio_use_state_req_list = false;
+#endif
+
static void aio_useriocb_free(struct kioctx *);
static void aio_iopoll_reap_events(struct kioctx *);
@@ -1724,6 +1733,21 @@ static void aio_complete_rw_poll(struct kiocb *kiocb, long res, long res2)
}
}
+struct aio_submit_state {
+ struct kioctx *ctx;
+
+ struct blk_plug plug;
+#ifdef CONFIG_BLOCK
+ struct blk_plug_cb plug_cb;
+#endif
+
+ /*
+ * Polled iocbs that have been submitted, but not added to the ctx yet
+ */
+ struct list_head req_list;
+ unsigned int req_count;
+};
+
static int aio_prep_rw(struct aio_kiocb *kiocb, const struct iocb *iocb)
{
struct kioctx *ctx = kiocb->ki_ctx;
@@ -1832,13 +1856,28 @@ static inline void aio_rw_done(struct kiocb *req, ssize_t ret)
}
+/*
+ * Called either at the end of IO submission, or through a plug callback
+ * because we're going to schedule. Moves out local batch of requests to
+ * the ctx poll list, so they can be found for polling + reaping.
+ */
+static void aio_flush_state_reqs(struct kioctx *ctx,
+ struct aio_submit_state *state)
+{
+ spin_lock(&ctx->poll_lock);
+ list_splice_tail_init(&state->req_list, &ctx->poll_submitted);
+ spin_unlock(&ctx->poll_lock);
+ state->req_count = 0;
+}
+
/*
* After the iocb has been issued, it's safe to be found on the poll list.
* Adding the kiocb to the list AFTER submission ensures that we don't
* find it from a io_getevents() thread before the issuer is done accessing
* the kiocb cookie.
*/
-static void aio_iopoll_iocb_issued(struct aio_kiocb *kiocb)
+static void aio_iopoll_iocb_issued(struct aio_submit_state *state,
+ struct aio_kiocb *kiocb)
{
/*
* For fast devices, IO may have already completed. If it has, add
@@ -1848,12 +1887,21 @@ static void aio_iopoll_iocb_issued(struct aio_kiocb *kiocb)
const int front_add = test_bit(IOCB_POLL_COMPLETED, &kiocb->ki_flags);
struct kioctx *ctx = kiocb->ki_ctx;
- spin_lock(&ctx->poll_lock);
- if (front_add)
- list_add(&kiocb->ki_list, &ctx->poll_submitted);
- else
- list_add_tail(&kiocb->ki_list, &ctx->poll_submitted);
- spin_unlock(&ctx->poll_lock);
+ if (!state || !aio_use_state_req_list) {
+ spin_lock(&ctx->poll_lock);
+ if (front_add)
+ list_add(&kiocb->ki_list, &ctx->poll_submitted);
+ else
+ list_add_tail(&kiocb->ki_list, &ctx->poll_submitted);
+ spin_unlock(&ctx->poll_lock);
+ } else {
+ if (front_add)
+ list_add(&kiocb->ki_list, &state->req_list);
+ else
+ list_add_tail(&kiocb->ki_list, &state->req_list);
+ if (++state->req_count >= AIO_IOPOLL_BATCH)
+ aio_flush_state_reqs(ctx, state);
+ }
}
static ssize_t aio_read(struct aio_kiocb *kiocb, const struct iocb *iocb,
@@ -2149,7 +2197,8 @@ static ssize_t aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb)
}
static int __io_submit_one(struct kioctx *ctx, const struct iocb *iocb,
- struct iocb __user *user_iocb, bool compat)
+ struct iocb __user *user_iocb,
+ struct aio_submit_state *state, bool compat)
{
struct aio_kiocb *req;
ssize_t ret;
@@ -2253,7 +2302,7 @@ static int __io_submit_one(struct kioctx *ctx, const struct iocb *iocb,
ret = -EAGAIN;
goto out_put_req;
}
- aio_iopoll_iocb_issued(req);
+ aio_iopoll_iocb_issued(state, req);
}
return 0;
out_put_req:
@@ -2267,7 +2316,7 @@ static int __io_submit_one(struct kioctx *ctx, const struct iocb *iocb,
}
static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
- bool compat)
+ struct aio_submit_state *state, bool compat)
{
struct iocb iocb, *iocbp;
@@ -2288,7 +2337,44 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
iocbp = &iocb;
}
- return __io_submit_one(ctx, iocbp, user_iocb, compat);
+ return __io_submit_one(ctx, iocbp, user_iocb, state, compat);
+}
+
+#ifdef CONFIG_BLOCK
+static void aio_state_unplug(struct blk_plug_cb *cb, bool from_schedule)
+{
+ struct aio_submit_state *state;
+
+ state = container_of(cb, struct aio_submit_state, plug_cb);
+ if (!list_empty(&state->req_list))
+ aio_flush_state_reqs(state->ctx, state);
+}
+#endif
+
+/*
+ * Batched submission is done, ensure local IO is flushed out.
+ */
+static void aio_submit_state_end(struct aio_submit_state *state)
+{
+ blk_finish_plug(&state->plug);
+ if (!list_empty(&state->req_list))
+ aio_flush_state_reqs(state->ctx, state);
+}
+
+/*
+ * Start submission side cache.
+ */
+static void aio_submit_state_start(struct aio_submit_state *state,
+ struct kioctx *ctx)
+{
+ state->ctx = ctx;
+ INIT_LIST_HEAD(&state->req_list);
+ state->req_count = 0;
+#ifdef CONFIG_BLOCK
+ state->plug_cb.callback = aio_state_unplug;
+ blk_start_plug(&state->plug);
+ list_add(&state->plug_cb.list, &state->plug.cb_list);
+#endif
}
/*
@@ -2312,10 +2398,10 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr,
struct iocb __user * __user *, iocbpp)
{
+ struct aio_submit_state state, *statep = NULL;
struct kioctx *ctx;
long ret = 0;
int i = 0;
- struct blk_plug plug;
if (unlikely(nr < 0))
return -EINVAL;
@@ -2329,8 +2415,10 @@ SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr,
if (nr > ctx->nr_events)
nr = ctx->nr_events;
- if (nr > AIO_PLUG_THRESHOLD)
- blk_start_plug(&plug);
+ if (nr > AIO_PLUG_THRESHOLD) {
+ aio_submit_state_start(&state, ctx);
+ statep = &state;
+ }
for (i = 0; i < nr; i++) {
struct iocb __user *user_iocb;
@@ -2339,12 +2427,12 @@ SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr,
break;
}
- ret = io_submit_one(ctx, user_iocb, false);
+ ret = io_submit_one(ctx, user_iocb, statep, false);
if (ret)
break;
}
- if (nr > AIO_PLUG_THRESHOLD)
- blk_finish_plug(&plug);
+ if (statep)
+ aio_submit_state_end(statep);
percpu_ref_put(&ctx->users);
return i ? i : ret;
@@ -2354,10 +2442,10 @@ SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr,
COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id,
int, nr, compat_uptr_t __user *, iocbpp)
{
+ struct aio_submit_state state, *statep = NULL;
struct kioctx *ctx;
long ret = 0;
int i = 0;
- struct blk_plug plug;
if (unlikely(nr < 0))
return -EINVAL;
@@ -2371,8 +2459,10 @@ COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id,
if (nr > ctx->nr_events)
nr = ctx->nr_events;
- if (nr > AIO_PLUG_THRESHOLD)
- blk_start_plug(&plug);
+ if (nr > AIO_PLUG_THRESHOLD) {
+ aio_submit_state_start(&state, ctx);
+ statep = &state;
+ }
for (i = 0; i < nr; i++) {
compat_uptr_t user_iocb;
@@ -2381,12 +2471,12 @@ COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id,
break;
}
- ret = io_submit_one(ctx, compat_ptr(user_iocb), true);
+ ret = io_submit_one(ctx, compat_ptr(user_iocb), statep, true);
if (ret)
break;
}
- if (nr > AIO_PLUG_THRESHOLD)
- blk_finish_plug(&plug);
+ if (statep)
+ aio_submit_state_end(statep);
percpu_ref_put(&ctx->users);
return i ? i : ret;
--
2.17.1
next prev parent reply other threads:[~2018-11-27 3:41 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-11-26 16:45 [PATCHSET v3 0/18] Support for polled aio Jens Axboe
2018-11-26 16:45 ` [PATCH 01/20] aio: fix failure to put the file pointer Jens Axboe
2018-11-27 8:16 ` Johannes Thumshirn
2018-11-26 16:45 ` [PATCH 02/20] aio: clear IOCB_HIPRI Jens Axboe
2018-11-27 8:18 ` Johannes Thumshirn
2018-11-26 16:45 ` [PATCH 03/20] fs: add an iopoll method to struct file_operations Jens Axboe
2018-11-27 8:24 ` Johannes Thumshirn
2018-11-26 16:45 ` [PATCH 04/20] block: wire up block device iopoll method Jens Axboe
2018-11-27 8:29 ` Johannes Thumshirn
2018-11-26 16:45 ` [PATCH 05/20] block: ensure that async polled IO is marked REQ_NOWAIT Jens Axboe
2018-11-26 16:45 ` [PATCH 06/20] iomap: wire up the iopoll method Jens Axboe
2018-11-26 16:45 ` [PATCH 07/20] iomap: ensure that async polled IO is marked REQ_NOWAIT Jens Axboe
2018-11-26 16:45 ` [PATCH 08/20] aio: use assigned completion handler Jens Axboe
2018-11-26 16:45 ` [PATCH 09/20] aio: separate out ring reservation from req allocation Jens Axboe
2018-11-26 16:45 ` [PATCH 10/20] aio: don't zero entire aio_kiocb aio_get_req() Jens Axboe
2018-11-26 16:45 ` [PATCH 11/20] aio: only use blk plugs for > 2 depth submissions Jens Axboe
2018-11-26 16:45 ` [PATCH 12/20] aio: use iocb_put() instead of open coding it Jens Axboe
2018-11-26 16:45 ` [PATCH 13/20] aio: split out iocb copy from io_submit_one() Jens Axboe
2018-11-26 16:45 ` [PATCH 14/20] aio: abstract out io_event filler helper Jens Axboe
2018-11-26 16:45 ` [PATCH 15/20] aio: add io_setup2() system call Jens Axboe
2018-11-26 16:45 ` [PATCH 16/20] aio: add support for having user mapped iocbs Jens Axboe
2018-11-26 16:45 ` [PATCH 17/20] aio: support for IO polling Jens Axboe
2018-11-27 9:53 ` Benny Halevy
2018-11-27 15:24 ` Jens Axboe
2018-11-28 9:33 ` Benny Halevy
2018-11-28 18:50 ` Jens Axboe
2018-11-29 14:10 ` Benny Halevy
2018-11-26 16:45 ` Jens Axboe [this message]
2018-11-26 16:45 ` [PATCH 19/20] fs: add fget_many() and fput_many() Jens Axboe
2018-11-26 16:45 ` [PATCH 20/20] aio: use fget/fput_many() for file references Jens Axboe
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20181126164544.5699-19-axboe@kernel.dk \
--to=axboe@kernel.dk \
--cc=linux-aio@kvack.org \
--cc=linux-block@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).