block: optimize zero writes with bdrv_write_zeroes

this patch tries to optimize zero write requests
by automatically using bdrv_write_zeroes if it is
supported by the format.

This significantly speeds up file system initialization and
should speed zero write test used to test backend storage
performance.

I ran the following 2 tests on my internal SSD with a
50G QCOW2 container and on an attached iSCSI storage.

a) mkfs.ext4 -E lazy_itable_init=0,lazy_journal_init=0 /dev/vdX

QCOW2         [off]     [on]     [unmap]
-----
runtime:       14secs    1.1secs  1.1secs
filesize:      937M      18M      18M

iSCSI         [off]     [on]     [unmap]
----
runtime:       9.3s      0.9s     0.9s

b) dd if=/dev/zero of=/dev/vdX bs=1M oflag=direct

QCOW2         [off]     [on]     [unmap]
-----
runtime:       246secs   18secs   18secs
filesize:      51G       192K     192K
throughput:    203M/s    2.3G/s   2.3G/s

iSCSI*        [off]     [on]     [unmap]
----
runtime:       8mins     45secs   33secs
throughput:    106M/s    1.2G/s   1.6G/s
allocated:     100%      100%     0%

* The storage was connected via an 1Gbit interface.
  It seems to internally handle writing zeroes
  via WRITESAME16 very fast.

Signed-off-by: Peter Lieven <pl@kamp.de>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>

1 files changed, 24 insertions, 0 deletions

diff --git a/blockdev.c b/blockdev.c
index 78b927f..1cbcc1c 100644
--- a/blockdev.c
+++ b/blockdev.c
@@ -343,6 +343,7 @@ static DriveInfo *blockdev_init(const char *file, QDict *bs_opts,
     QemuOpts *opts;
     const char *id;
     bool has_driver_specific_opts;
+    BlockdevDetectZeroesOptions detect_zeroes;
     BlockDriver *drv = NULL;
 
     /* Check common options by copying from bs_opts to opts, all other options
@@ -471,6 +472,24 @@ static DriveInfo *blockdev_init(const char *file, QDict *bs_opts,
         }
     }
 
+    detect_zeroes =
+        parse_enum_option(BlockdevDetectZeroesOptions_lookup,
+                          qemu_opt_get(opts, "detect-zeroes"),
+                          BLOCKDEV_DETECT_ZEROES_OPTIONS_MAX,
+                          BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF,
+                          &error);
+    if (error) {
+        error_propagate(errp, error);
+        goto early_err;
+    }
+
+    if (detect_zeroes == BLOCKDEV_DETECT_ZEROES_OPTIONS_UNMAP &&
+        !(bdrv_flags & BDRV_O_UNMAP)) {
+        error_setg(errp, "setting detect-zeroes to unmap is not allowed "
+                         "without setting discard operation to unmap");
+        goto early_err;
+    }
+
     /* init */
     dinfo = g_malloc0(sizeof(*dinfo));
     dinfo->id = g_strdup(qemu_opts_id(opts));
@@ -481,6 +500,7 @@ static DriveInfo *blockdev_init(const char *file, QDict *bs_opts,
     }
     dinfo->bdrv->open_flags = snapshot ? BDRV_O_SNAPSHOT : 0;
     dinfo->bdrv->read_only = ro;
+    dinfo->bdrv->detect_zeroes = detect_zeroes;
     dinfo->refcount = 1;
     if (serial != NULL) {
         dinfo->serial = g_strdup(serial);
@@ -2474,6 +2494,10 @@ QemuOptsList qemu_common_drive_opts = {
             .name = "copy-on-read",
             .type = QEMU_OPT_BOOL,
             .help = "copy read data from backing file into image file",
+        },{
+            .name = "detect-zeroes",
+            .type = QEMU_OPT_STRING,
+            .help = "try to optimize zero writes (off, on, unmap)",
         },
         { /* end of list */ }
     },