On 06/24/2016 09:06 AM, Denis V. Lunev wrote:
From: Evgeny Yakovlev <address@hidden>
Some guests (win2008 server for example) do a lot of unnecessary
flushing when underlying media has not changed. This adds additional
overhead on host when calling fsync/fdatasync.
This change introduces a dirty flag in BlockDriverState which is set
in bdrv_set_dirty and is checked in bdrv_co_flush. This allows us to
avoid unnesessary flushing when storage is clean.
s/unnesessary/unnecessary/ (I pointed this out against v2
https://lists.gnu.org/archive/html/qemu-devel/2016-06/msg05817.html,
which makes me wonder if anything else was missed)
The problem with excessive flushing was found by a performance test
which does parallel directory tree creation (from 2 processes).
Results improved from 0.424 loops/sec to 0.432 loops/sec.
Each loop creates 10^3 directories with 10 files in each.
Signed-off-by: Evgeny Yakovlev <address@hidden>
Signed-off-by: Denis V. Lunev <address@hidden>
CC: Kevin Wolf <address@hidden>
CC: Max Reitz <address@hidden>
CC: Stefan Hajnoczi <address@hidden>
CC: Fam Zheng <address@hidden>
CC: John Snow <address@hidden>
---
+++ b/include/block/block_int.h
@@ -418,6 +418,8 @@ struct BlockDriverState {
int sg; /* if true, the device is a /dev/sg* */
int copy_on_read; /* if true, copy read backing sectors into image
note this is a reference count */
+
+ bool dirty;
bool probed;
Conflicts with the current state of Kevin's block branch (due to my
reordering and conversion of bool parameters); so you'll want to rebase.