qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Fam Zheng <fam@euphon.net>
To: Aarushi Mehta <mehta.aaru20@gmail.com>
Cc: Kevin Wolf <kwolf@redhat.com>, Sergio Lopez <slp@redhat.com>,
	qemu-block@nongnu.org, qemu-devel@nongnu.org,
	Max Reitz <mreitz@redhat.com>,
	saket.sinha89@gmail.com, Stefan Hajnoczi <stefanha@redhat.com>,
	Paolo Bonzini <pbonzini@redhat.com>,
	Maxim Levitsky <mlevitsk@redhat.com>,
	Julia Suvorova <jusual@mail.ru>,
	Markus Armbruster <armbru@redhat.com>
Subject: Re: [Qemu-devel] [PATCH v5 09/12] block: add trace events for io_uring
Date: Tue, 11 Jun 2019 19:34:52 +0800	[thread overview]
Message-ID: <20190611113452.v6frbexgoyfjzjh7@debian> (raw)
In-Reply-To: <20190610134905.22294-10-mehta.aaru20@gmail.com>

On Mon, 06/10 19:19, Aarushi Mehta wrote:
> Signed-off-by: Aarushi Mehta <mehta.aaru20@gmail.com>
> ---
>  block/io_uring.c   | 14 ++++++++++++--
>  block/trace-events |  8 ++++++++
>  2 files changed, 20 insertions(+), 2 deletions(-)
> 
> diff --git a/block/io_uring.c b/block/io_uring.c
> index f327c7ef96..47e027364a 100644
> --- a/block/io_uring.c
> +++ b/block/io_uring.c
> @@ -17,6 +17,7 @@
>  #include "block/raw-aio.h"
>  #include "qemu/coroutine.h"
>  #include "qapi/error.h"
> +#include "trace.h"
>  
>  #define MAX_EVENTS 128
>  
> @@ -191,12 +192,15 @@ static int ioq_submit(LuringState *s)
>  
>  void luring_io_plug(BlockDriverState *bs, LuringState *s)
>  {
> +    trace_luring_io_plug();
>      s->io_q.plugged++;
>  }
>  
>  void luring_io_unplug(BlockDriverState *bs, LuringState *s)
>  {
>      assert(s->io_q.plugged);
> +    trace_luring_io_unplug(s->io_q.blocked, s->io_q.plugged,
> +                                 s->io_q.in_queue, s->io_q.in_flight);
>      if (--s->io_q.plugged == 0 &&
>          !s->io_q.blocked && s->io_q.in_queue > 0) {
>          ioq_submit(s);
> @@ -217,6 +221,7 @@ void luring_io_unplug(BlockDriverState *bs, LuringState *s)
>  static int luring_do_submit(int fd, LuringAIOCB *luringcb, LuringState *s,
>                              uint64_t offset, int type)
>  {
> +    int ret;
>      struct io_uring_sqe *sqes = io_uring_get_sqe(&s->ring);
>      if (!sqes) {
>          sqes = &luringcb->sqeq;
> @@ -242,11 +247,14 @@ static int luring_do_submit(int fd, LuringAIOCB *luringcb, LuringState *s,
>      }
>      io_uring_sqe_set_data(sqes, luringcb);
>      s->io_q.in_queue++;
> -
> +    trace_luring_do_submit(s->io_q.blocked, s->io_q.plugged,
> +                           s->io_q.in_queue, s->io_q.in_flight);
>      if (!s->io_q.blocked &&
>          (!s->io_q.plugged ||
>           s->io_q.in_flight + s->io_q.in_queue >= MAX_EVENTS)) {
> -        return ioq_submit(s);
> +        ret = ioq_submit(s);
> +        trace_luring_do_submit_done(ret);
> +        return ret;
>      }
>      return 0;
>  }
> @@ -294,6 +302,7 @@ LuringState *luring_init(Error **errp)
>      int rc;
>      LuringState *s;
>      s = g_malloc0(sizeof(*s));
> +    trace_luring_init_state((void *)s, sizeof(*s));

The pointer type cast is unnecessary.

>      struct io_uring *ring = &s->ring;
>      rc =  io_uring_queue_init(MAX_EVENTS, ring, 0);
>      if (rc < 0) {
> @@ -311,4 +320,5 @@ void luring_cleanup(LuringState *s)
>  {
>      io_uring_queue_exit(&s->ring);
>      g_free(s);
> +    trace_luring_cleanup_state();

Pass @s?

>  }
> diff --git a/block/trace-events b/block/trace-events
> index eab51497fc..c4564dcd96 100644
> --- a/block/trace-events
> +++ b/block/trace-events
> @@ -60,6 +60,14 @@ qmp_block_stream(void *bs, void *job) "bs %p job %p"
>  file_paio_submit(void *acb, void *opaque, int64_t offset, int count, int type) "acb %p opaque %p offset %"PRId64" count %d type %d"
>  file_copy_file_range(void *bs, int src, int64_t src_off, int dst, int64_t dst_off, int64_t bytes, int flags, int64_t ret) "bs %p src_fd %d offset %"PRIu64" dst_fd %d offset %"PRIu64" bytes %"PRIu64" flags %d ret %"PRId64
>  
> +#io_uring.c
> +luring_init_state(void *s, size_t size) "s %p size %zu"
> +luring_cleanup_state(void) "s freed"
> +disable luring_io_plug(void) "plug"
> +disable luring_io_unplug(int blocked, int plugged, int queued, int inflight) "blocked %d plugged %d queued %d inflight %d"
> +disable luring_do_submit(int blocked, int plugged, int queued, int inflight) "blocked %d plugged %d queued %d inflight %d"
> +disable luring_do_submit_done(int ret) "submitted to kernel %d"
> +
>  # qcow2.c
>  qcow2_writev_start_req(void *co, int64_t offset, int bytes) "co %p offset 0x%" PRIx64 " bytes %d"
>  qcow2_writev_done_req(void *co, int ret) "co %p ret %d"
> -- 
> 2.17.1
> 

Fam



  parent reply	other threads:[~2019-06-11 12:38 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-06-10 13:48 [Qemu-devel] [PATCH v5 00/12] Add support for io_uring Aarushi Mehta
2019-06-10 13:48 ` [Qemu-devel] [PATCH v5 01/12] configure: permit use of io_uring Aarushi Mehta
2019-06-10 13:48 ` [Qemu-devel] [PATCH v5 02/12] qapi/block-core: add option for io_uring Aarushi Mehta
2019-06-11  7:36   ` Fam Zheng
2019-06-11  9:32     ` Stefan Hajnoczi
2019-07-03  6:26       ` Markus Armbruster
2019-06-10 13:48 ` [Qemu-devel] [PATCH v5 03/12] block/block: add BDRV flag " Aarushi Mehta
2019-06-10 13:48 ` [Qemu-devel] [PATCH v5 04/12] block/io_uring: implements interfaces " Aarushi Mehta
2019-06-11 11:17   ` Fam Zheng
2019-06-12 14:43     ` Stefan Hajnoczi
2019-06-17 12:26   ` Maxim Levitsky
2019-06-19 10:14     ` Stefan Hajnoczi
2019-06-19 10:47       ` Maxim Levitsky
2019-06-22 15:10     ` [Qemu-devel] [Qemu-block] " Stefan Hajnoczi
2019-06-10 13:48 ` [Qemu-devel] [PATCH v5 05/12] stubs: add stubs for io_uring interface Aarushi Mehta
2019-06-17 12:33   ` Maxim Levitsky
2019-06-19 10:21     ` Stefan Hajnoczi
2019-06-10 13:48 ` [Qemu-devel] [PATCH v5 06/12] util/async: add aio interfaces for io_uring Aarushi Mehta
2019-06-17 12:56   ` Maxim Levitsky
2019-06-10 13:49 ` [Qemu-devel] [PATCH v5 07/12] blockdev: accept io_uring as option Aarushi Mehta
2019-06-17 13:01   ` Maxim Levitsky
2019-06-19 10:24     ` Stefan Hajnoczi
2019-06-19 10:48       ` Maxim Levitsky
2019-06-10 13:49 ` [Qemu-devel] [PATCH v5 08/12] block/file-posix.c: extend to use io_uring Aarushi Mehta
2019-06-17 14:12   ` Maxim Levitsky
2019-06-10 13:49 ` [Qemu-devel] [PATCH v5 09/12] block: add trace events for io_uring Aarushi Mehta
2019-06-11  9:47   ` Stefan Hajnoczi
2019-06-11 11:34   ` Fam Zheng [this message]
2019-06-10 13:49 ` [Qemu-devel] [PATCH v5 10/12] block/io_uring: adds userspace completion polling Aarushi Mehta
2019-06-11  9:51   ` Stefan Hajnoczi
2019-06-17 14:14     ` Maxim Levitsky
2019-06-10 13:49 ` [Qemu-devel] [PATCH v5 11/12] qemu-io: adds support for io_uring Aarushi Mehta
2019-06-11  9:54   ` Stefan Hajnoczi
2019-06-11 12:26   ` Fam Zheng
2019-06-10 13:49 ` [Qemu-devel] [PATCH v5 12/12] qemu-iotests/087: checks " Aarushi Mehta
2019-06-11  9:58   ` Stefan Hajnoczi
2019-06-17 14:21   ` Maxim Levitsky
2019-06-11  9:56 ` [Qemu-devel] [PATCH v5 00/12] Add support " Stefan Hajnoczi
2019-06-22 15:13   ` [Qemu-devel] [Qemu-block] " Stefan Hajnoczi
2019-06-23 14:03     ` Stefan Hajnoczi

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=20190611113452.v6frbexgoyfjzjh7@debian \
    --to=fam@euphon.net \
    --cc=armbru@redhat.com \
    --cc=jusual@mail.ru \
    --cc=kwolf@redhat.com \
    --cc=mehta.aaru20@gmail.com \
    --cc=mlevitsk@redhat.com \
    --cc=mreitz@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=qemu-block@nongnu.org \
    --cc=qemu-devel@nongnu.org \
    --cc=saket.sinha89@gmail.com \
    --cc=slp@redhat.com \
    --cc=stefanha@redhat.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;
as well as URLs for NNTP newsgroup(s).