[Qemu-devel] [RFC][PATCH] make sure disk writes actually hit disk

[Rik van Riel]

This is the simple approach to making sure that disk writes actually
hit disk before we tell the guest OS that IO has completed.  Thanks
to DMA_MULTI_THREAD the performance still seems to be adequate.

A fancier solution would be to make the sync/non-sync behaviour of
the qemu disk backing store tunable from the guest OS, by tuning
the IDE disk write cache on/off with hdparm, and having hw/ide.c
call ->fsync functions in the block backends.

I'm willing to code up the fancy solution if people prefer that.

--
"Debugging is twice as hard as writing the code in the first place.
Therefore, if you write the code as cleverly as possible, you are,
by definition, not smart enough to debug it." - Brian W. Kernighan

Make sure disk writes really made it to disk before we report I/O
completion to the guest domain.  The DMA_MULTI_THREAD functionality
from the qemu-dm IDE emulation should make the performance overhead
of synchronous writes bearable, or at least comparable to native
hardware.

Signed-off-by: Rik van Riel <address@hidden>

--- xen-unstable-10712/tools/ioemu/block-bochs.c.osync  2006-07-28 
02:15:56.000000000 -0400
+++ xen-unstable-10712/tools/ioemu/block-bochs.c        2006-07-28 
02:21:08.000000000 -0400
@@ -91,7 +91,7 @@
     int fd, i;
     struct bochs_header bochs;
 
-    fd = open(filename, O_RDWR | O_BINARY | O_LARGEFILE);
+    fd = open(filename, O_RDWR | O_BINARY | O_LARGEFILE | O_SYNC);
     if (fd < 0) {
         fd = open(filename, O_RDONLY | O_BINARY | O_LARGEFILE);
         if (fd < 0)
--- xen-unstable-10712/tools/ioemu/block.c.osync        2006-07-28 
02:15:56.000000000 -0400
+++ xen-unstable-10712/tools/ioemu/block.c      2006-07-28 02:19:27.000000000 
-0400
@@ -677,7 +677,7 @@
     int rv;
 #endif
 
-    fd = open(filename, O_RDWR | O_BINARY | O_LARGEFILE);
+    fd = open(filename, O_RDWR | O_BINARY | O_LARGEFILE | O_SYNC);
     if (fd < 0) {
         fd = open(filename, O_RDONLY | O_BINARY | O_LARGEFILE);
         if (fd < 0)
--- xen-unstable-10712/tools/ioemu/block-cloop.c.osync  2006-07-28 
02:15:56.000000000 -0400
+++ xen-unstable-10712/tools/ioemu/block-cloop.c        2006-07-28 
02:17:13.000000000 -0400
@@ -55,7 +55,7 @@
     BDRVCloopState *s = bs->opaque;
     uint32_t offsets_size,max_compressed_block_size=1,i;
 
-    s->fd = open(filename, O_RDONLY | O_BINARY | O_LARGEFILE);
+    s->fd = open(filename, O_RDONLY | O_BINARY | O_LARGEFILE | O_SYNC);
     if (s->fd < 0)
         return -1;
     bs->read_only = 1;
--- xen-unstable-10712/tools/ioemu/block-cow.c.osync    2006-07-28 
02:15:56.000000000 -0400
+++ xen-unstable-10712/tools/ioemu/block-cow.c  2006-07-28 02:21:34.000000000 
-0400
@@ -69,7 +69,7 @@
     struct cow_header_v2 cow_header;
     int64_t size;
 
-    fd = open(filename, O_RDWR | O_BINARY | O_LARGEFILE);
+    fd = open(filename, O_RDWR | O_BINARY | O_LARGEFILE | O_SYNC);
     if (fd < 0) {
         fd = open(filename, O_RDONLY | O_BINARY | O_LARGEFILE);
         if (fd < 0)
--- xen-unstable-10712/tools/ioemu/block-qcow.c.osync   2006-07-28 
02:15:56.000000000 -0400
+++ xen-unstable-10712/tools/ioemu/block-qcow.c 2006-07-28 02:20:05.000000000 
-0400
@@ -95,7 +95,7 @@
     int fd, len, i, shift;
     QCowHeader header;
     
-    fd = open(filename, O_RDWR | O_BINARY | O_LARGEFILE);
+    fd = open(filename, O_RDWR | O_BINARY | O_LARGEFILE | O_SYNC);
     if (fd < 0) {
         fd = open(filename, O_RDONLY | O_BINARY | O_LARGEFILE);
         if (fd < 0)
--- xen-unstable-10712/tools/ioemu/block-vmdk.c.osync   2006-07-28 
02:15:56.000000000 -0400
+++ xen-unstable-10712/tools/ioemu/block-vmdk.c 2006-07-28 02:20:20.000000000 
-0400
@@ -96,7 +96,7 @@
     uint32_t magic;
     int l1_size;
 
-    fd = open(filename, O_RDWR | O_BINARY | O_LARGEFILE);
+    fd = open(filename, O_RDWR | O_BINARY | O_LARGEFILE | O_SYNC);
     if (fd < 0) {
         fd = open(filename, O_RDONLY | O_BINARY | O_LARGEFILE);
         if (fd < 0)