qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
To: qemu-block@nongnu.org
Cc: qemu-devel@nongnu.org, eblake@redhat.com, armbru@redhat.com,
	jsnow@redhat.com, fam@euphon.net, stefanha@redhat.com,
	mreitz@redhat.com, kwolf@redhat.com, den@openvz.org,
	andrey.shinkevich@virtuozzo.com, vsementsov@virtuozzo.com
Subject: [PATCH v14 08/13] copy-on-read: skip non-guest reads if no copy needed
Date: Sat,  5 Dec 2020 01:07:53 +0300	[thread overview]
Message-ID: <20201204220758.2879-9-vsementsov@virtuozzo.com> (raw)
In-Reply-To: <20201204220758.2879-1-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>
---
 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 81a3894129..3499554d9c 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 67f61983c0..8b64e55e22 100644
--- a/block/copy-on-read.c
+++ b/block/copy-on-read.c
@@ -49,6 +49,8 @@ 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);
 
@@ -150,10 +152,14 @@ 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;
-- 
2.21.3



  parent reply	other threads:[~2020-12-04 22:21 UTC|newest]

Thread overview: 37+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-12-04 22:07 [PATCH v14 00/13] Apply COR-filter to the block-stream permanently Vladimir Sementsov-Ogievskiy
2020-12-04 22:07 ` [PATCH v14 01/13] copy-on-read: support preadv/pwritev_part functions Vladimir Sementsov-Ogievskiy
2020-12-04 22:07 ` [PATCH v14 02/13] block: add API function to insert a node Vladimir Sementsov-Ogievskiy
2020-12-10 17:33   ` Max Reitz
2020-12-04 22:07 ` [PATCH v14 03/13] copy-on-read: add filter drop function Vladimir Sementsov-Ogievskiy
2020-12-10 17:34   ` Max Reitz
2020-12-04 22:07 ` [PATCH v14 04/13] qapi: add filter-node-name to block-stream Vladimir Sementsov-Ogievskiy
2020-12-10 17:37   ` Max Reitz
2020-12-04 22:07 ` [PATCH v14 05/13] qapi: create BlockdevOptionsCor structure for COR driver Vladimir Sementsov-Ogievskiy
2020-12-10 17:43   ` Max Reitz
2020-12-10 18:30     ` Vladimir Sementsov-Ogievskiy
2020-12-11  8:54       ` Max Reitz
2020-12-11 12:32         ` Vladimir Sementsov-Ogievskiy
2020-12-04 22:07 ` [PATCH v14 06/13] iotests: add #310 to test bottom node in " Vladimir Sementsov-Ogievskiy
2020-12-11 12:49   ` Max Reitz
2020-12-11 13:10     ` Vladimir Sementsov-Ogievskiy
2020-12-11 13:24       ` Max Reitz
2020-12-04 22:07 ` [PATCH v14 07/13] block: include supported_read_flags into BDS structure Vladimir Sementsov-Ogievskiy
2020-12-11 13:20   ` Max Reitz
2020-12-11 13:31     ` Vladimir Sementsov-Ogievskiy
2020-12-04 22:07 ` Vladimir Sementsov-Ogievskiy [this message]
2020-12-11 14:29   ` [PATCH v14 08/13] copy-on-read: skip non-guest reads if no copy needed Max Reitz
2020-12-04 22:07 ` [PATCH v14 09/13] stream: skip filters when writing backing file name to QCOW2 header Vladimir Sementsov-Ogievskiy
2020-12-11 15:15   ` Max Reitz
2020-12-04 22:07 ` [PATCH v14 10/13] qapi: block-stream: add "bottom" argument Vladimir Sementsov-Ogievskiy
2020-12-11 16:05   ` Max Reitz
2020-12-11 16:50     ` Vladimir Sementsov-Ogievskiy
2020-12-11 17:24       ` Max Reitz
2020-12-11 17:42         ` Vladimir Sementsov-Ogievskiy
2020-12-11 17:52           ` Max Reitz
2020-12-04 22:07 ` [PATCH v14 11/13] iotests: 30: prepare to COR filter insertion by stream job Vladimir Sementsov-Ogievskiy
2020-12-11 16:09   ` Max Reitz
2020-12-04 22:07 ` [PATCH v14 12/13] block/stream: add s->target_bs Vladimir Sementsov-Ogievskiy
2020-12-11 16:33   ` Max Reitz
2020-12-04 22:07 ` [PATCH v14 13/13] block: apply COR-filter to block-stream jobs Vladimir Sementsov-Ogievskiy
2020-12-11 17:21   ` Max Reitz
2020-12-11 17:48     ` 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=20201204220758.2879-9-vsementsov@virtuozzo.com \
    --to=vsementsov@virtuozzo.com \
    --cc=andrey.shinkevich@virtuozzo.com \
    --cc=armbru@redhat.com \
    --cc=den@openvz.org \
    --cc=eblake@redhat.com \
    --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).