From: Jens Axboe <axboe@kernel.dk>
To: Ketor D <d.ketor@gmail.com>,
Mark Kirkwood <mark.kirkwood@catalyst.net.nz>
Cc: Mark Nelson <mark.nelson@inktank.com>,
Mark Nelson <mark.a.nelson@gmail.com>,
fio@vger.kernel.org, "xan.peng" <xanpeng@gmail.com>,
"ceph-devel@vger.kernel.org" <ceph-devel@vger.kernel.org>
Subject: Re: fio rbd completions (Was: fio rbd hang for block sizes > 1M)
Date: Mon, 27 Oct 2014 08:19:04 -0600 [thread overview]
Message-ID: <544E5458.3070506@kernel.dk> (raw)
In-Reply-To: <CAM9_UU8X7xVst+OR0__POkaXY6eG=D4_uiWK1T_iTFNJkRo3Gg@mail.gmail.com>
[-- Attachment #1: Type: text/plain, Size: 1425 bytes --]
On 10/27/2014 04:25 AM, Ketor D wrote:
> Hi Jens:
> After debug the v3 patch, I found there is a bug in the patch.
> On the first fio_rbd_getevents loop, the fri->io_seen is set to
> 1, and this variable never set to 0 again. So the program get into
> endless loop in such code:
>
> do {
> this_events = rbd_iter_events(td, &events, min, wait);
>
> if (events >= min)
> break;
> if (this_events)
> continue;
>
> wait = 1;
> } while (1);
>
> this_events and events always be 0, because the fri->io_seen is always
> 1, so no events can be getted.
>
> The Bug fix is:
> in the function _fio_rbd_finish_read_aiocb,
> _fio_rbd_finish_write_aiocb and _fio_rbd_finish_sync_aiocb add
> "fio_rbd_iou->io_seen = 0;" after "fio_rbd_iou->io_complete = 1;".
So there are two issues. One is that ->io_seen should be reset in the
->queue() ops, before issuing the IO. The second is that the comp is
released in a racy way, so we can't use it in getevents() reliably.
The new patch moves the comp release to when we reap the event, and
cleans up the ->io_seen setting as well. As far as I can tell, this
should fix all cases.
Additionally, it now actually checks for IO errors and handles those
correctly. They were just ignored before. Gets rid of some useless
casting as well, and lots of duplicated IO comp functions.
If everybody involved (Mark, you) could try this one out, then I'd
appreciate it.
--
Jens Axboe
[-- Attachment #2: rbd-comp-v5.patch --]
[-- Type: text/x-patch, Size: 7347 bytes --]
diff --git a/engines/rbd.c b/engines/rbd.c
index 6fe87b8d010c..89344033f894 100644
--- a/engines/rbd.c
+++ b/engines/rbd.c
@@ -11,7 +11,9 @@
struct fio_rbd_iou {
struct io_u *io_u;
+ rbd_completion_t completion;
int io_complete;
+ int io_seen;
};
struct rbd_data {
@@ -163,92 +165,102 @@ static void _fio_rbd_disconnect(struct rbd_data *rbd_data)
}
}
-static void _fio_rbd_finish_write_aiocb(rbd_completion_t comp, void *data)
+static void _fio_rbd_io_finish(struct io_u *io_u)
{
- struct io_u *io_u = (struct io_u *)data;
- struct fio_rbd_iou *fio_rbd_iou =
- (struct fio_rbd_iou *)io_u->engine_data;
+ struct fio_rbd_iou *fri = io_u->engine_data;
+ ssize_t ret;
+
+ fri->io_complete = 1;
+
+ ret = rbd_aio_get_return_value(&fri->completion);
+ if (ret != (int) io_u->xfer_buflen) {
+ if (ret >= 0) {
+ io_u->resid = io_u->xfer_buflen - ret;
+ io_u->error = 0;
+ } else
+ io_u->error = ret;
+ }
+}
- fio_rbd_iou->io_complete = 1;
+static void _fio_rbd_finish_aiocb(rbd_completion_t comp, void *data)
+{
+ struct io_u *io_u = data;
- /* if write needs to be verified - we should not release comp here
- without fetching the result */
+ _fio_rbd_io_finish(io_u);
+}
- rbd_aio_release(comp);
- /* TODO handle error */
+static struct io_u *fio_rbd_event(struct thread_data *td, int event)
+{
+ struct rbd_data *rbd_data = td->io_ops->data;
- return;
+ return rbd_data->aio_events[event];
}
-static void _fio_rbd_finish_read_aiocb(rbd_completion_t comp, void *data)
+static inline int fri_check_complete(struct rbd_data *rbd_data,
+ struct io_u *io_u,
+ unsigned int *events)
{
- struct io_u *io_u = (struct io_u *)data;
- struct fio_rbd_iou *fio_rbd_iou =
- (struct fio_rbd_iou *)io_u->engine_data;
+ struct fio_rbd_iou *fri = io_u->engine_data;
- fio_rbd_iou->io_complete = 1;
+ if (fri->io_complete) {
+ fri->io_complete = 0;
+ fri->io_seen = 1;
+ rbd_data->aio_events[*events] = io_u;
+ (*events)++;
- /* if read needs to be verified - we should not release comp here
- without fetching the result */
- rbd_aio_release(comp);
-
- /* TODO handle error */
+ rbd_aio_release(&fri->completion);
+ return 1;
+ }
- return;
+ return 0;
}
-static void _fio_rbd_finish_sync_aiocb(rbd_completion_t comp, void *data)
+static int rbd_iter_events(struct thread_data *td, unsigned int *events,
+ unsigned int min_evts, int wait)
{
- struct io_u *io_u = (struct io_u *)data;
- struct fio_rbd_iou *fio_rbd_iou =
- (struct fio_rbd_iou *)io_u->engine_data;
-
- fio_rbd_iou->io_complete = 1;
+ struct rbd_data *rbd_data = td->io_ops->data;
+ unsigned int this_events = 0;
+ struct io_u *io_u;
+ int i;
- /* if sync needs to be verified - we should not release comp here
- without fetching the result */
- rbd_aio_release(comp);
+ io_u_qiter(&td->io_u_all, io_u, i) {
+ struct fio_rbd_iou *fri = io_u->engine_data;
- /* TODO handle error */
+ if (!(io_u->flags & IO_U_F_FLIGHT))
+ continue;
+ if (fri->io_seen)
+ continue;
- return;
-}
+ if (fri_check_complete(rbd_data, io_u, events))
+ this_events++;
+ else if (wait) {
+ rbd_aio_wait_for_complete(fri->completion);
-static struct io_u *fio_rbd_event(struct thread_data *td, int event)
-{
- struct rbd_data *rbd_data = td->io_ops->data;
+ if (fri_check_complete(rbd_data, io_u, events))
+ this_events++;
+ }
+ if (*events >= min_evts)
+ break;
+ }
- return rbd_data->aio_events[event];
+ return this_events;
}
static int fio_rbd_getevents(struct thread_data *td, unsigned int min,
unsigned int max, const struct timespec *t)
{
- struct rbd_data *rbd_data = td->io_ops->data;
- unsigned int events = 0;
- struct io_u *io_u;
- int i;
- struct fio_rbd_iou *fov;
+ unsigned int this_events, events = 0;
+ int wait = 0;
do {
- io_u_qiter(&td->io_u_all, io_u, i) {
- if (!(io_u->flags & IO_U_F_FLIGHT))
- continue;
-
- fov = (struct fio_rbd_iou *)io_u->engine_data;
-
- if (fov->io_complete) {
- fov->io_complete = 0;
- rbd_data->aio_events[events] = io_u;
- events++;
- }
+ this_events = rbd_iter_events(td, &events, min, wait);
- }
- if (events < min)
- usleep(100);
- else
+ if (events >= min)
break;
+ if (this_events)
+ continue;
+ wait = 1;
} while (1);
return events;
@@ -256,17 +268,18 @@ static int fio_rbd_getevents(struct thread_data *td, unsigned int min,
static int fio_rbd_queue(struct thread_data *td, struct io_u *io_u)
{
- int r = -1;
struct rbd_data *rbd_data = td->io_ops->data;
- rbd_completion_t comp;
+ struct fio_rbd_iou *fri = io_u->engine_data;
+ int r = -1;
fio_ro_check(td, io_u);
+ fri->io_complete = 0;
+ fri->io_seen = 0;
+
if (io_u->ddir == DDIR_WRITE) {
- r = rbd_aio_create_completion(io_u,
- (rbd_callback_t)
- _fio_rbd_finish_write_aiocb,
- &comp);
+ r = rbd_aio_create_completion(io_u, _fio_rbd_finish_aiocb,
+ &fri->completion);
if (r < 0) {
log_err
("rbd_aio_create_completion for DDIR_WRITE failed.\n");
@@ -274,17 +287,16 @@ static int fio_rbd_queue(struct thread_data *td, struct io_u *io_u)
}
r = rbd_aio_write(rbd_data->image, io_u->offset,
- io_u->xfer_buflen, io_u->xfer_buf, comp);
+ io_u->xfer_buflen, io_u->xfer_buf,
+ fri->completion);
if (r < 0) {
log_err("rbd_aio_write failed.\n");
goto failed;
}
} else if (io_u->ddir == DDIR_READ) {
- r = rbd_aio_create_completion(io_u,
- (rbd_callback_t)
- _fio_rbd_finish_read_aiocb,
- &comp);
+ r = rbd_aio_create_completion(io_u, _fio_rbd_finish_aiocb,
+ &fri->completion);
if (r < 0) {
log_err
("rbd_aio_create_completion for DDIR_READ failed.\n");
@@ -292,7 +304,8 @@ static int fio_rbd_queue(struct thread_data *td, struct io_u *io_u)
}
r = rbd_aio_read(rbd_data->image, io_u->offset,
- io_u->xfer_buflen, io_u->xfer_buf, comp);
+ io_u->xfer_buflen, io_u->xfer_buf,
+ fri->completion);
if (r < 0) {
log_err("rbd_aio_read failed.\n");
@@ -300,17 +313,15 @@ static int fio_rbd_queue(struct thread_data *td, struct io_u *io_u)
}
} else if (io_u->ddir == DDIR_SYNC) {
- r = rbd_aio_create_completion(io_u,
- (rbd_callback_t)
- _fio_rbd_finish_sync_aiocb,
- &comp);
+ r = rbd_aio_create_completion(io_u, _fio_rbd_finish_aiocb,
+ &fri->completion);
if (r < 0) {
log_err
("rbd_aio_create_completion for DDIR_SYNC failed.\n");
goto failed;
}
- r = rbd_aio_flush(rbd_data->image, comp);
+ r = rbd_aio_flush(rbd_data->image, fri->completion);
if (r < 0) {
log_err("rbd_flush failed.\n");
goto failed;
@@ -439,22 +450,21 @@ static int fio_rbd_invalidate(struct thread_data *td, struct fio_file *f)
static void fio_rbd_io_u_free(struct thread_data *td, struct io_u *io_u)
{
- struct fio_rbd_iou *o = io_u->engine_data;
+ struct fio_rbd_iou *fri = io_u->engine_data;
- if (o) {
+ if (fri) {
io_u->engine_data = NULL;
- free(o);
+ free(fri);
}
}
static int fio_rbd_io_u_init(struct thread_data *td, struct io_u *io_u)
{
- struct fio_rbd_iou *o;
+ struct fio_rbd_iou *fri;
- o = malloc(sizeof(*o));
- o->io_complete = 0;
- o->io_u = io_u;
- io_u->engine_data = o;
+ fri = calloc(1, sizeof(*fri));
+ fri->io_u = io_u;
+ io_u->engine_data = fri;
return 0;
}
next prev parent reply other threads:[~2014-10-27 14:19 UTC|newest]
Thread overview: 52+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-10-24 2:38 fio rbd hang for block sizes > 1M Mark Kirkwood
2014-10-24 5:35 ` Jens Axboe
2014-10-24 6:17 ` Mark Kirkwood
2014-10-24 13:19 ` Mark Nelson
2014-10-24 14:09 ` Mark Nelson
2014-10-24 14:30 ` Jens Axboe
2014-10-24 22:45 ` Mark Kirkwood
2014-10-25 0:12 ` Mark Nelson
2014-10-25 0:37 ` Mark Kirkwood
2014-10-25 2:35 ` Mark Kirkwood
2014-10-25 3:47 ` Jens Axboe
2014-10-25 4:50 ` fio rbd completions (Was: fio rbd hang for block sizes > 1M) Mark Kirkwood
2014-10-25 19:20 ` Jens Axboe
2014-10-25 22:25 ` Mark Kirkwood
2014-10-27 9:27 ` Ketor D
2014-10-27 10:25 ` Ketor D
2014-10-27 14:19 ` Jens Axboe [this message]
2014-10-27 14:15 ` Jens Axboe
2014-10-27 14:19 ` Jens Axboe
2014-10-27 15:12 ` Ketor D
2014-10-27 15:22 ` Jens Axboe
2014-10-27 15:25 ` Jens Axboe
2014-10-27 15:29 ` Ketor D
2014-10-27 15:36 ` Jens Axboe
2014-10-27 15:45 ` Ketor D
2014-10-27 15:53 ` Jens Axboe
2014-10-27 16:20 ` Ketor D
2014-10-27 16:55 ` Jens Axboe
2014-10-27 21:59 ` Mark Kirkwood
2014-10-27 22:32 ` Jens Axboe
2014-10-27 23:21 ` Mark Kirkwood
2014-10-28 3:23 ` Ketor D
2014-10-28 4:01 ` Mark Kirkwood
2014-10-28 4:05 ` Jens Axboe
2014-10-28 4:49 ` Ketor D
2014-10-28 15:14 ` Jens Axboe
2014-10-28 15:49 ` Ketor D
2014-10-28 15:53 ` Jens Axboe
2014-10-28 17:09 ` Jens Axboe
2014-10-28 18:43 ` Ketor D
2014-10-29 7:15 ` Ketor D
2014-10-29 14:31 ` Jens Axboe
2014-10-30 2:50 ` Ketor D
2014-10-30 2:55 ` Jens Axboe
2014-10-30 5:29 ` Ketor D
2014-10-30 7:44 ` Mark Kirkwood
2014-10-30 8:04 ` Ketor D
2014-10-31 8:54 ` Mark Kirkwood
2014-10-24 22:30 ` fio rbd hang for block sizes > 1M Mark Kirkwood
2014-10-24 22:38 ` Mark Nelson
2014-10-24 14:11 ` Danny Al-Gaaf
2014-10-24 14:31 ` 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=544E5458.3070506@kernel.dk \
--to=axboe@kernel.dk \
--cc=ceph-devel@vger.kernel.org \
--cc=d.ketor@gmail.com \
--cc=fio@vger.kernel.org \
--cc=mark.a.nelson@gmail.com \
--cc=mark.kirkwood@catalyst.net.nz \
--cc=mark.nelson@inktank.com \
--cc=xanpeng@gmail.com \
/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