Re: [PATCH v3 08/15] block/file-posix.c: extend to use io_uring

[Stefano Garzarella]

On Wed, Dec 18, 2019 at 04:32:21PM +0000, Stefan Hajnoczi wrote:
> From: Aarushi Mehta <address@hidden>
> 
> Signed-off-by: Aarushi Mehta <address@hidden>
> Reviewed-by: Maxim Levitsky <address@hidden>
> Signed-off-by: Stefan Hajnoczi <address@hidden>
> ---
>  block/file-posix.c | 95 ++++++++++++++++++++++++++++++++++++----------
>  1 file changed, 75 insertions(+), 20 deletions(-)
> 
> diff --git a/block/file-posix.c b/block/file-posix.c
> index 1b805bd938..a42a90e59d 100644
> --- a/block/file-posix.c
> +++ b/block/file-posix.c
> @@ -156,6 +156,7 @@ typedef struct BDRVRawState {
>      bool has_write_zeroes:1;
>      bool discard_zeroes:1;
>      bool use_linux_aio:1;
> +    bool use_linux_io_uring:1;
>      bool page_cache_inconsistent:1;
>      bool has_fallocate;
>      bool needs_alignment;
> @@ -444,7 +445,7 @@ static QemuOptsList raw_runtime_opts = {
>          {
>              .name = "aio",
>              .type = QEMU_OPT_STRING,
> -            .help = "host AIO implementation (threads, native)",
> +            .help = "host AIO implementation (threads, native, io_uring)",
>          },
>          {
>              .name = "locking",
> @@ -503,9 +504,11 @@ static int raw_open_common(BlockDriverState *bs, QDict 
> *options,
>          goto fail;
>      }
>  
> -    aio_default = (bdrv_flags & BDRV_O_NATIVE_AIO)
> -                  ? BLOCKDEV_AIO_OPTIONS_NATIVE
> -                  : BLOCKDEV_AIO_OPTIONS_THREADS;
> +    if (bdrv_flags & BDRV_O_NATIVE_AIO) {
> +        aio_default = BLOCKDEV_AIO_OPTIONS_NATIVE;
> +    } else {
> +        aio_default = BLOCKDEV_AIO_OPTIONS_THREADS;
> +    }

This is only a cosmetic change?

>      aio = qapi_enum_parse(&BlockdevAioOptions_lookup,
>                            qemu_opt_get(opts, "aio"),
>                            aio_default, &local_err);
> @@ -514,7 +517,11 @@ static int raw_open_common(BlockDriverState *bs, QDict 
> *options,
>          ret = -EINVAL;
>          goto fail;
>      }
> +
>      s->use_linux_aio = (aio == BLOCKDEV_AIO_OPTIONS_NATIVE);
> +#ifdef CONFIG_LINUX_IO_URING
> +    s->use_linux_io_uring = (aio == BLOCKDEV_AIO_OPTIONS_IO_URING);
> +#endif
>  
>      locking = qapi_enum_parse(&OnOffAuto_lookup,
>                                qemu_opt_get(opts, "locking"),
> @@ -578,7 +585,7 @@ static int raw_open_common(BlockDriverState *bs, QDict 
> *options,
>      s->shared_perm = BLK_PERM_ALL;
>  
>  #ifdef CONFIG_LINUX_AIO
> -     /* Currently Linux does AIO only for files opened with O_DIRECT */
> +    /* Currently Linux does AIO only for files opened with O_DIRECT */

Also this is a not related fix, if you respin maybe we should split in a
new patch or say something in the commit message.

>      if (s->use_linux_aio) {
>          if (!(s->open_flags & O_DIRECT)) {
>              error_setg(errp, "aio=native was specified, but it requires "
> @@ -600,6 +607,22 @@ static int raw_open_common(BlockDriverState *bs, QDict 
> *options,
>      }
>  #endif /* !defined(CONFIG_LINUX_AIO) */
>  
> +#ifdef CONFIG_LINUX_IO_URING
> +    if (s->use_linux_io_uring) {
> +        if (!aio_setup_linux_io_uring(bdrv_get_aio_context(bs), errp)) {
> +            error_prepend(errp, "Unable to use io_uring: ");
> +            goto fail;
> +        }
> +    }
> +#else
> +    if (s->use_linux_io_uring) {
> +        error_setg(errp, "aio=io_uring was specified, but is not supported "
> +                         "in this build.");
> +        ret = -EINVAL;
> +        goto fail;
> +    }
> +#endif /* !defined(CONFIG_LINUX_IO_URING) */
> +
>      s->has_discard = true;
>      s->has_write_zeroes = true;
>      if ((bs->open_flags & BDRV_O_NOCACHE) != 0) {
> @@ -1877,21 +1900,25 @@ static int coroutine_fn raw_co_prw(BlockDriverState 
> *bs, uint64_t offset,
>          return -EIO;
>  
>      /*
> -     * Check if the underlying device requires requests to be aligned,
> -     * and if the request we are trying to submit is aligned or not.
> -     * If this is the case tell the low-level driver that it needs
> -     * to copy the buffer.
> +     * When using O_DIRECT, the request must be aligned to be able to use
> +     * either libaio or io_uring interface. If not fail back to regular 
> thread
> +     * pool read/write code which emulates this for us if we
> +     * set QEMU_AIO_MISALIGNED.
>       */
> -    if (s->needs_alignment) {
> -        if (!bdrv_qiov_is_aligned(bs, qiov)) {
> -            type |= QEMU_AIO_MISALIGNED;
> +    if (s->needs_alignment && !bdrv_qiov_is_aligned(bs, qiov)) {
> +        type |= QEMU_AIO_MISALIGNED;
> +#ifdef CONFIG_LINUX_IO_URING
> +    } else if (s->use_linux_io_uring) {
> +        LuringState *aio = aio_get_linux_io_uring(bdrv_get_aio_context(bs));
> +        assert(qiov->size == bytes);
> +        return luring_co_submit(bs, aio, s->fd, offset, qiov, type);
> +#endif
>  #ifdef CONFIG_LINUX_AIO
> -        } else if (s->use_linux_aio) {
> -            LinuxAioState *aio = aio_get_linux_aio(bdrv_get_aio_context(bs));
> -            assert(qiov->size == bytes);
> -            return laio_co_submit(bs, aio, s->fd, offset, qiov, type);
> +    } else if (s->use_linux_aio) {

This code block was executed if "s->needs_alignment" was true, now we don't
check it. Could this be a problem?

> +        LinuxAioState *aio = aio_get_linux_aio(bdrv_get_aio_context(bs));
> +        assert(qiov->size == bytes);
> +        return laio_co_submit(bs, aio, s->fd, offset, qiov, type);
>  #endif
> -        }
>      }
>  
>      acb = (RawPosixAIOData) {
> @@ -1927,24 +1954,36 @@ static int coroutine_fn 
> raw_co_pwritev(BlockDriverState *bs, uint64_t offset,
>  
>  static void raw_aio_plug(BlockDriverState *bs)
>  {
> +    BDRVRawState __attribute__((unused)) *s = bs->opaque;
>  #ifdef CONFIG_LINUX_AIO
> -    BDRVRawState *s = bs->opaque;
>      if (s->use_linux_aio) {
>          LinuxAioState *aio = aio_get_linux_aio(bdrv_get_aio_context(bs));
>          laio_io_plug(bs, aio);
>      }
>  #endif
> +#ifdef CONFIG_LINUX_IO_URING
> +    if (s->use_linux_io_uring) {
> +        LuringState *aio = aio_get_linux_io_uring(bdrv_get_aio_context(bs));
> +        luring_io_plug(bs, aio);
> +    }
> +#endif
>  }
>  
>  static void raw_aio_unplug(BlockDriverState *bs)
>  {
> +    BDRVRawState __attribute__((unused)) *s = bs->opaque;
>  #ifdef CONFIG_LINUX_AIO
> -    BDRVRawState *s = bs->opaque;
>      if (s->use_linux_aio) {
>          LinuxAioState *aio = aio_get_linux_aio(bdrv_get_aio_context(bs));
>          laio_io_unplug(bs, aio);
>      }
>  #endif
> +#ifdef CONFIG_LINUX_IO_URING
> +    if (s->use_linux_io_uring) {
> +        LuringState *aio = aio_get_linux_io_uring(bdrv_get_aio_context(bs));
> +        luring_io_unplug(bs, aio);
> +    }
> +#endif
>  }
>  
>  static int raw_co_flush_to_disk(BlockDriverState *bs)
> @@ -1964,14 +2003,20 @@ static int raw_co_flush_to_disk(BlockDriverState *bs)
>          .aio_type       = QEMU_AIO_FLUSH,
>      };
>  
> +#ifdef CONFIG_LINUX_IO_URING
> +    if (s->use_linux_io_uring) {
> +        LuringState *aio = aio_get_linux_io_uring(bdrv_get_aio_context(bs));
> +        return luring_co_submit(bs, aio, s->fd, 0, NULL, QEMU_AIO_FLUSH);
> +    }
> +#endif
>      return raw_thread_pool_submit(bs, handle_aiocb_flush, &acb);
>  }
>  
>  static void raw_aio_attach_aio_context(BlockDriverState *bs,
>                                         AioContext *new_context)
>  {
> +    BDRVRawState __attribute__((unused)) *s = bs->opaque;
>  #ifdef CONFIG_LINUX_AIO
> -    BDRVRawState *s = bs->opaque;
>      if (s->use_linux_aio) {
>          Error *local_err = NULL;
>          if (!aio_setup_linux_aio(new_context, &local_err)) {
> @@ -1981,6 +2026,16 @@ static void 
> raw_aio_attach_aio_context(BlockDriverState *bs,
>          }
>      }
>  #endif
> +#ifdef CONFIG_LINUX_IO_URING
> +    if (s->use_linux_io_uring) {
> +        Error *local_err;
> +        if (!aio_setup_linux_io_uring(new_context, &local_err)) {
> +            error_reportf_err(local_err, "Unable to use linux io_uring, "
> +                                         "falling back to thread pool: ");
> +            s->use_linux_io_uring = false;
> +        }
> +    }
> +#endif
>  }
>  
>  static void raw_close(BlockDriverState *bs)
> -- 
> 2.23.0
> 
>