[Xen-devel] [PATCH][RFC] open HVM backing storage with O_SYNC

[Rik van Riel <riel@xxxxxxxxxx>]

I noticed that the new qemu-dm code has DMA_MULTI_THREAD defined, so
I/O already overlaps with CPU run time of the guest domain.  This
means that we might as well open the backing storage with O_SYNC, so
writes done by the guest hit the disk when the guest expects them to,
and in the other the guest expects them to.

I am now running my postgresql HVM test domain (which has had its
database eaten a number of times by the async write behaviour) with
this patch, and will try to abuse it heavily over the next few days.

Any comments on this patch?

--
"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 <riel@xxxxxxxxxx>

--- 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)

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel