4:35 a.m.
Btrfs has terrible performance when hosting VM images, even more when the guest
in those VM are also using btrfs as file system. One way to mitigate this bad
performance is to turn off COW attributes on VM files (since having copy on
write for this kind of data is not useful).
According to 'chattr' manpage, NOCOW could be set to new or empty file only on
btrfs, so this patch tries to add a --nocow option to vol-create functions and
vol-clone function, so that users could have a chance to set NOCOW to a new
volume if that happens to create on a btrfs like file system.
Signed-off-by: Chunyan Liu <cyliu(a)suse.com>
---
include/libvirt/libvirt.h.in | 1 +
src/storage/storage_backend.c | 2 +-
src/storage/storage_backend_fs.c | 49 ++++++++++++++++++++++++++++++++++++-
src/storage/storage_driver.c | 6 +++-
tools/virsh-volume.c | 26 ++++++++++++++++++-
5 files changed, 77 insertions(+), 7 deletions(-)
diff --git a/include/libvirt/libvirt.h.in b/include/libvirt/libvirt.h.in
index 5aad75c..0761ba6 100644
--- a/include/libvirt/libvirt.h.in
+++ b/include/libvirt/libvirt.h.in
@@ -3151,6 +3151,7 @@ const char* virStorageVolGetKey
(virStorageVolPtr vol);
typedef enum {
VIR_STORAGE_VOL_CREATE_PREALLOC_METADATA = 1 << 0,
+ VIR_STORAGE_VOL_CREATE_NOCOW = 1 << 1,
} virStorageVolCreateFlags;
virStorageVolPtr virStorageVolCreateXML (virStoragePoolPtr pool,
diff --git a/src/storage/storage_backend.c b/src/storage/storage_backend.c
index 57c1728..8ce7e99 100644
--- a/src/storage/storage_backend.c
+++ b/src/storage/storage_backend.c
@@ -423,7 +423,7 @@ virStorageBackendCreateRaw(virConnectPtr conn ATTRIBUTE_UNUSED,
operation_flags |= VIR_FILE_OPEN_FORK;
if ((fd = virFileOpenAs(vol->target.path,
- O_RDWR | O_CREAT | O_EXCL,
+ O_RDWR | O_CREAT,
vol->target.perms.mode,
vol->target.perms.uid,
vol->target.perms.gid,
diff --git a/src/storage/storage_backend_fs.c b/src/storage/storage_backend_fs.c
index 11cf2df..d60b64c 100644
--- a/src/storage/storage_backend_fs.c
+++ b/src/storage/storage_backend_fs.c
@@ -51,6 +51,13 @@
#include "virfile.h"
#include "virlog.h"
#include "virstring.h"
+#ifdef __linux__
+# include <sys/ioctl.h>
+# include <linux/fs.h>
+#ifndef FS_NOCOW_FL
+#define FS_NOCOW_FL 0x00800000 /* Do not cow file */
+#endif
+#endif
#define VIR_FROM_THIS VIR_FROM_STORAGE
@@ -1090,6 +1097,42 @@ _virStorageBackendFileSystemVolBuild(virConnectPtr conn,
return -1;
}
+ if (flags & VIR_STORAGE_VOL_CREATE_NOCOW) {
+#ifdef __linux__
+ /* create an empty file and set nocow flag.
+ * This could optimize performance on file system like btrfs.
+ */
+ int attr, fd;
+ int operation_flags = VIR_FILE_OPEN_FORCE_MODE | VIR_FILE_OPEN_FORCE_OWNER;
+ if (pool->def->type == VIR_STORAGE_POOL_NETFS)
+ operation_flags |= VIR_FILE_OPEN_FORK;
+
+ if ((fd = virFileOpenAs(vol->target.path,
+ O_RDWR | O_CREAT | O_EXCL | O_LARGEFILE,
+ vol->target.perms.mode,
+ vol->target.perms.uid,
+ vol->target.perms.gid,
+ operation_flags)) < 0) {
+ virReportSystemError(-fd,
+ _("Failed to create file '%s'"),
+ vol->target.path);
+ return -1;
+ }
+
+ /* This is an optimisation. The FS_IOC_SETFLAGS ioctl return value will
+ * be ignored since any failure of this operation should not block the
+ * left work.
+ */
+ if (ioctl(fd, FS_IOC_GETFLAGS, &attr) == 0) {
+ attr |= FS_NOCOW_FL;
+ ioctl(fd, FS_IOC_SETFLAGS, &attr);
+ }
+
+ VIR_FORCE_CLOSE(fd);
+#endif
+ flags &= ~VIR_STORAGE_VOL_CREATE_NOCOW;
+ }
+
if (create_func(conn, pool, vol, inputvol, flags) < 0)
return -1;
return 0;
@@ -1106,7 +1149,8 @@ virStorageBackendFileSystemVolBuild(virConnectPtr conn,
virStorageVolDefPtr vol,
unsigned int flags)
{
- virCheckFlags(VIR_STORAGE_VOL_CREATE_PREALLOC_METADATA, -1);
+ virCheckFlags(VIR_STORAGE_VOL_CREATE_PREALLOC_METADATA |
+ VIR_STORAGE_VOL_CREATE_NOCOW, -1);
return _virStorageBackendFileSystemVolBuild(conn, pool, vol, NULL, flags);
}
@@ -1121,7 +1165,8 @@ virStorageBackendFileSystemVolBuildFrom(virConnectPtr conn,
virStorageVolDefPtr inputvol,
unsigned int flags)
{
- virCheckFlags(VIR_STORAGE_VOL_CREATE_PREALLOC_METADATA, -1);
+ virCheckFlags(VIR_STORAGE_VOL_CREATE_PREALLOC_METADATA |
+ VIR_STORAGE_VOL_CREATE_NOCOW, -1);
return _virStorageBackendFileSystemVolBuild(conn, pool, vol, inputvol, flags);
}
diff --git a/src/storage/storage_driver.c b/src/storage/storage_driver.c
index 3b4715a..2aef1a7 100644
--- a/src/storage/storage_driver.c
+++ b/src/storage/storage_driver.c
@@ -1509,7 +1509,8 @@ storageVolCreateXML(virStoragePoolPtr obj,
virStorageVolPtr ret = NULL, volobj = NULL;
virStorageVolDefPtr buildvoldef = NULL;
- virCheckFlags(VIR_STORAGE_VOL_CREATE_PREALLOC_METADATA, NULL);
+ virCheckFlags(VIR_STORAGE_VOL_CREATE_PREALLOC_METADATA |
+ VIR_STORAGE_VOL_CREATE_NOCOW, NULL);
storageDriverLock(driver);
pool = virStoragePoolObjFindByUUID(&driver->pools, obj->uuid);
@@ -1641,7 +1642,8 @@ storageVolCreateXMLFrom(virStoragePoolPtr obj,
unsigned long long allocation;
int buildret;
- virCheckFlags(VIR_STORAGE_VOL_CREATE_PREALLOC_METADATA, NULL);
+ virCheckFlags(VIR_STORAGE_VOL_CREATE_PREALLOC_METADATA |
+ VIR_STORAGE_VOL_CREATE_NOCOW, NULL);
storageDriverLock(driver);
pool = virStoragePoolObjFindByUUID(&driver->pools, obj->uuid);
diff --git a/tools/virsh-volume.c b/tools/virsh-volume.c
index 22b10d5..bfbcc1f 100644
--- a/tools/virsh-volume.c
+++ b/tools/virsh-volume.c
@@ -151,6 +151,10 @@ static const vshCmdOptDef opts_vol_create_as[] = {
.type = VSH_OT_BOOL,
.help = N_("preallocate metadata (for qcow2 instead of full allocation)")
},
+ {.name = "nocow",
+ .type = VSH_OT_BOOL,
+ .help = N_("turn off copy-on-write (for file on fs like btrfs)")
+ },
{.name = NULL}
};
@@ -177,6 +181,8 @@ cmdVolCreateAs(vshControl *ctl, const vshCmd *cmd)
if (vshCommandOptBool(cmd, "prealloc-metadata"))
flags |= VIR_STORAGE_VOL_CREATE_PREALLOC_METADATA;
+ if (vshCommandOptBool(cmd, "nocow"))
+ flags |= VIR_STORAGE_VOL_CREATE_NOCOW;
if (!(pool = vshCommandOptPool(ctl, cmd, "pool", NULL)))
return false;
@@ -330,6 +336,10 @@ static const vshCmdOptDef opts_vol_create[] = {
.type = VSH_OT_BOOL,
.help = N_("preallocate metadata (for qcow2 instead of full allocation)")
},
+ {.name = "nocow",
+ .type = VSH_OT_BOOL,
+ .help = N_("turn off copy-on-write (for file on fs like btrfs)")
+ },
{.name = NULL}
};
@@ -345,6 +355,8 @@ cmdVolCreate(vshControl *ctl, const vshCmd *cmd)
if (vshCommandOptBool(cmd, "prealloc-metadata"))
flags |= VIR_STORAGE_VOL_CREATE_PREALLOC_METADATA;
+ if (vshCommandOptBool(cmd, "nocow"))
+ flags |= VIR_STORAGE_VOL_CREATE_NOCOW;
if (!(pool = vshCommandOptPool(ctl, cmd, "pool", NULL)))
return false;
@@ -408,6 +420,10 @@ static const vshCmdOptDef opts_vol_create_from[] = {
.type = VSH_OT_BOOL,
.help = N_("preallocate metadata (for qcow2 instead of full allocation)")
},
+ {.name = "nocow",
+ .type = VSH_OT_BOOL,
+ .help = N_("turn off copy-on-write (for file on fs like btrfs)")
+ },
{.name = NULL}
};
@@ -426,7 +442,8 @@ cmdVolCreateFrom(vshControl *ctl, const vshCmd *cmd)
if (vshCommandOptBool(cmd, "prealloc-metadata"))
flags |= VIR_STORAGE_VOL_CREATE_PREALLOC_METADATA;
-
+ if (vshCommandOptBool(cmd, "nocow"))
+ flags |= VIR_STORAGE_VOL_CREATE_NOCOW;
if (vshCommandOptStringReq(ctl, cmd, "file", &from) < 0)
goto cleanup;
@@ -521,6 +538,10 @@ static const vshCmdOptDef opts_vol_clone[] = {
.type = VSH_OT_BOOL,
.help = N_("preallocate metadata (for qcow2 instead of full allocation)")
},
+ {.name = "nocow",
+ .type = VSH_OT_BOOL,
+ .help = N_("turn off copy-on-write (for file on fs like btrfs)")
+ },
{.name = NULL}
};
@@ -540,7 +561,8 @@ cmdVolClone(vshControl *ctl, const vshCmd *cmd)
if (vshCommandOptBool(cmd, "prealloc-metadata"))
flags |= VIR_STORAGE_VOL_CREATE_PREALLOC_METADATA;
-
+ if (vshCommandOptBool(cmd, "nocow"))
+ flags |= VIR_STORAGE_VOL_CREATE_NOCOW;
origpool = virStoragePoolLookupByVolume(origvol);
if (!origpool) {
vshError(ctl, "%s", _("failed to get parent pool"));
--
1.6.0.2