qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
To: qemu-block@nongnu.org
Cc: fam@euphon.net, kwolf@redhat.com, vsementsov@virtuozzo.com,
	qemu-devel@nongnu.org, armbru@redhat.com, stefanha@redhat.com,
	den@openvz.org, andrey.shinkevich@virtuozzo.com,
	mreitz@redhat.com, jsnow@redhat.com
Subject: [PATCH v15 08/13] copy-on-read: skip non-guest reads if no copy needed
Date: Wed, 16 Dec 2020 09:16:58 +0300	[thread overview]
Message-ID: <20201216061703.70908-9-vsementsov@virtuozzo.com> (raw)
In-Reply-To: <20201216061703.70908-1-vsementsov@virtuozzo.com>

From: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com>

If the flag BDRV_REQ_PREFETCH was set, skip idling read/write
operations in COR-driver. It can be taken into account for the
COR-algorithms optimization. That check is being made during the
block stream job by the moment.

Add the BDRV_REQ_PREFETCH flag to the supported_read_flags of the
COR-filter.

block: Modify the comment for the flag BDRV_REQ_PREFETCH as we are
going to use it alone and pass it to the COR-filter driver for further
processing.

Signed-off-by: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
---
 include/block/block.h |  8 +++++---
 block/copy-on-read.c  | 14 ++++++++++----
 2 files changed, 15 insertions(+), 7 deletions(-)

diff --git a/include/block/block.h b/include/block/block.h
index 8ea794959b..f652f31406 100644
--- a/include/block/block.h
+++ b/include/block/block.h
@@ -81,9 +81,11 @@ typedef enum {
     BDRV_REQ_NO_FALLBACK        = 0x100,
 
     /*
-     * BDRV_REQ_PREFETCH may be used only together with BDRV_REQ_COPY_ON_READ
-     * on read request and means that caller doesn't really need data to be
-     * written to qiov parameter which may be NULL.
+     * BDRV_REQ_PREFETCH makes sense only in the context of copy-on-read
+     * (i.e., together with the BDRV_REQ_COPY_ON_READ flag or when a COR
+     * filter is involved), in which case it signals that the COR operation
+     * need not read the data into memory (qiov) but only ensure they are
+     * copied to the top layer (i.e., that COR operation is done).
      */
     BDRV_REQ_PREFETCH  = 0x200,
     /* Mask of valid flags */
diff --git a/block/copy-on-read.c b/block/copy-on-read.c
index 71560984f6..9cad9e1b8c 100644
--- a/block/copy-on-read.c
+++ b/block/copy-on-read.c
@@ -50,6 +50,8 @@ static int cor_open(BlockDriverState *bs, QDict *options, int flags,
         return -EINVAL;
     }
 
+    bs->supported_read_flags = BDRV_REQ_PREFETCH;
+
     bs->supported_write_flags = BDRV_REQ_WRITE_UNCHANGED |
         (BDRV_REQ_FUA & bs->file->bs->supported_write_flags);
 
@@ -172,10 +174,14 @@ static int coroutine_fn cor_co_preadv_part(BlockDriverState *bs,
             }
         }
 
-        ret = bdrv_co_preadv_part(bs->file, offset, n, qiov, qiov_offset,
-                                  local_flags);
-        if (ret < 0) {
-            return ret;
+        /* Skip if neither read nor write are needed */
+        if ((local_flags & (BDRV_REQ_PREFETCH | BDRV_REQ_COPY_ON_READ)) !=
+            BDRV_REQ_PREFETCH) {
+            ret = bdrv_co_preadv_part(bs->file, offset, n, qiov, qiov_offset,
+                                      local_flags);
+            if (ret < 0) {
+                return ret;
+            }
         }
 
         offset += n;
-- 
2.25.4



  parent reply	other threads:[~2020-12-16  6:29 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-12-16  6:16 [PATCH v15 00/13] Apply COR-filter to the block-stream permanently Vladimir Sementsov-Ogievskiy
2020-12-16  6:16 ` [PATCH v15 01/13] copy-on-read: support preadv/pwritev_part functions Vladimir Sementsov-Ogievskiy
2020-12-16  6:16 ` [PATCH v15 02/13] block: add API function to insert a node Vladimir Sementsov-Ogievskiy
2020-12-16  6:16 ` [PATCH v15 03/13] copy-on-read: add filter drop function Vladimir Sementsov-Ogievskiy
2020-12-16  6:16 ` [PATCH v15 04/13] qapi: add filter-node-name to block-stream Vladimir Sementsov-Ogievskiy
2020-12-22 15:24   ` Max Reitz
2020-12-16  6:16 ` [PATCH v15 05/13] qapi: copy-on-read filter: add 'bottom' option Vladimir Sementsov-Ogievskiy
2020-12-16  6:16 ` [PATCH v15 06/13] iotests: add #310 to test bottom node in COR driver Vladimir Sementsov-Ogievskiy
2020-12-16  6:16 ` [PATCH v15 07/13] block: include supported_read_flags into BDS structure Vladimir Sementsov-Ogievskiy
2020-12-16  6:16 ` Vladimir Sementsov-Ogievskiy [this message]
2020-12-16  6:16 ` [PATCH v15 09/13] stream: rework backing-file changing Vladimir Sementsov-Ogievskiy
2020-12-22 15:59   ` Max Reitz
2020-12-22 17:53     ` Vladimir Sementsov-Ogievskiy
2021-01-05 12:51       ` Max Reitz
2020-12-16  6:17 ` [PATCH v15 10/13] qapi: block-stream: add "bottom" argument Vladimir Sementsov-Ogievskiy
2020-12-22 16:07   ` Max Reitz
2020-12-22 18:00     ` Vladimir Sementsov-Ogievskiy
2020-12-22 18:11       ` Vladimir Sementsov-Ogievskiy
2021-01-05 12:51       ` Max Reitz
2020-12-16  6:17 ` [PATCH v15 11/13] iotests: 30: prepare to COR filter insertion by stream job Vladimir Sementsov-Ogievskiy
2020-12-16  6:17 ` [PATCH v15 12/13] block/stream: add s->target_bs Vladimir Sementsov-Ogievskiy
2020-12-16  6:17 ` [PATCH v15 13/13] block: apply COR-filter to block-stream jobs Vladimir Sementsov-Ogievskiy
2020-12-22 16:20   ` Max Reitz
2020-12-22 18:07     ` Vladimir Sementsov-Ogievskiy
2021-01-05 12:52       ` Max Reitz
2021-01-05 15:30   ` Max Reitz
2021-01-05 16:08 ` [PATCH v15 00/13] Apply COR-filter to the block-stream permanently Max Reitz
2021-01-08 10:24   ` Vladimir Sementsov-Ogievskiy

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=20201216061703.70908-9-vsementsov@virtuozzo.com \
    --to=vsementsov@virtuozzo.com \
    --cc=andrey.shinkevich@virtuozzo.com \
    --cc=armbru@redhat.com \
    --cc=den@openvz.org \
    --cc=fam@euphon.net \
    --cc=jsnow@redhat.com \
    --cc=kwolf@redhat.com \
    --cc=mreitz@redhat.com \
    --cc=qemu-block@nongnu.org \
    --cc=qemu-devel@nongnu.org \
    --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).