block: Preallocated truncation for gluster and sheepdog
cover block: Preallocated truncation for gluster and sheepdog
As far as I can see, these are the only protocols beside file-posix that support preallocated creation. In contrast to file-posix, however, they have not supported preallocated truncation so far. This series brings their truncation code to feature parity with their creation code in this regard.
Note that I do not have a test setup for either of the two drivers, so I do not actually know whether this works. Anyone with a setup is more than welcome to test this series.
Max Reitz (7):
gluster: Move glfs_close() to create's clean-up
gluster: Pull truncation from qemu_gluster_create
gluster: Query current size in do_truncate()
gluster: Add preallocated truncation
sheepdog: Make sd_prealloc() take a BDS
sheepdog: Pass old and new size to sd_prealloc()
sheepdog: Allow fully preallocated truncation
block/gluster.c | 116 ++++++++++++++++++++++++++++++------------------------- block/sheepdog.c | 56 +++++++++++++++++---------- 2 files changed, 99 insertions(+), 73 deletions(-)
Signature · 1 line
2.14.3
PATCH 1/7 gluster: Move glfs_close() to create's clean-up
glfs_close() is a classical clean-up operation, as can be seen by the fact that it is executed even if the truncation before it failed. Also, moving it to clean-up makes it more clear that if it fails, we do not want it to overwrite the current ret value if that signifies an error already.
--- block/gluster.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)
block/gluster.c +6 -4
@@ -970,7 +970,7 @@ static int qemu_gluster_create(const char *filename, {BlockdevOptionsGluster *gconf;struct glfs *glfs; -struct glfs_fd *fd; +struct glfs_fd *fd =NULL ;int ret =0 ;PreallocMode prealloc;int64_t total_size =0 ;
@@ -1054,10 +1054,12 @@ static int qemu_gluster_create(const char *filename,break ; } -if (glfs_close (fd) !=0 ) { - ret = -errno; - } out: +if (fd) { +if (glfs_close (fd) !=0 && ret ==0 ) { + ret = -errno; + } + }qapi_free_BlockdevOptionsGluster (gconf);glfs_clear_preopened (glfs);return ret;
Signature · 1 line
2.14.3
Re: [Qemu-devel] [PATCH 1/7] gluster: Move glfs_close() to create's clean-up
Quoted 11 lines · Max Reitz
glfs_close()is a classical clean-up operation, as can be seen by the fact that it is executed even if the truncation before it failed. Also, moving it to clean-up makes it more clear that if it fails, we do not want it to overwrite the current ret value if that signifies an error already.Signed-off-by Max Reitz <[email protected]>--- block/gluster.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)
Signature · 3 lines
Eric Blake, Principal Software Engineer Red Hat, Inc. +1-919-301-3266 Virtualization: qemu.org | libvirt.org
PATCH 2/7 gluster: Pull truncation from qemu_gluster_create
In reply to Max ReitzPull out the truncation code from the qemu_cluster_create() function so we can later reuse it in qemu_gluster_truncate().
--- block/gluster.c | 74 +++++++++++++++++++++++++++++++-------------------------- 1 file changed, 40 insertions(+), 34 deletions(-)
block/gluster.c +40 -34
@@ -965,6 +965,45 @@ static coroutine_fn int qemu_gluster_co_pwrite_zeroes(BlockDriverState *bs, }#endif +static int qemu_gluster_do_truncate (struct glfs_fd *fd,int64_t offset, +PreallocMode prealloc,Error **errp) +{ +switch (prealloc) { +#ifdef CONFIG_GLUSTERFS_FALLOCATE +case PREALLOC_MODE_FALLOC : +if (glfs_fallocate (fd,0 ,0 , offset)) { +error_setg_errno (errp, errno,"Could not preallocate data" ); +return -errno; + } +break ; +#endif /* CONFIG_GLUSTERFS_FALLOCATE */ +#ifdef CONFIG_GLUSTERFS_ZEROFILL +case PREALLOC_MODE_FULL : +if (glfs_ftruncate (fd, offset)) { +error_setg_errno (errp, errno,"Could not resize file" ); +return -errno; + } +if (glfs_zerofill (fd,0 , offset)) { +error_setg_errno (errp, errno,"Could not zerofill the new area" ); +return -errno; + } +break ; +#endif /* CONFIG_GLUSTERFS_ZEROFILL */ +case PREALLOC_MODE_OFF : +if (glfs_ftruncate (fd, offset)) { +error_setg_errno (errp, errno,"Could not resize file" ); +return -errno; + } +break ; +default : +error_setg (errp,"Unsupported preallocation mode: %s" , +PreallocMode_str (prealloc)); +return -EINVAL ; + } + +return 0 ; +} +static int qemu_gluster_create (const char *filename,QemuOpts *opts,Error **errp) {
@@ -1019,40 +1058,7 @@ static int qemu_gluster_create(const char *filename, goto out; } -switch (prealloc) { -#ifdef CONFIG_GLUSTERFS_FALLOCATE -case PREALLOC_MODE_FALLOC : -if (glfs_fallocate (fd,0 ,0 , total_size)) { -error_setg (errp,"Could not preallocate data for the new file" ); - ret = -errno; - } -break ; -#endif /* CONFIG_GLUSTERFS_FALLOCATE */ -#ifdef CONFIG_GLUSTERFS_ZEROFILL -case PREALLOC_MODE_FULL : -if (!glfs_ftruncate (fd, total_size)) { -if (glfs_zerofill (fd,0 , total_size)) { -error_setg (errp,"Could not zerofill the new file" ); - ret = -errno; - } - }else { -error_setg (errp,"Could not resize file" ); - ret = -errno; - } -break ; -#endif /* CONFIG_GLUSTERFS_ZEROFILL */ -case PREALLOC_MODE_OFF : -if (glfs_ftruncate (fd, total_size) !=0 ) { - ret = -errno; -error_setg (errp,"Could not resize file" ); - } -break ; -default : - ret = -EINVAL ; -error_setg (errp,"Unsupported preallocation mode: %s" , -PreallocMode_str (prealloc)); -break ; - } + ret =qemu_gluster_do_truncate (fd, total_size, prealloc, errp); out:if (fd) {
Signature · 1 line
2.14.3
Re: [Qemu-devel] [PATCH 2/7] gluster: Pull truncation from qemu_gluster_create
Quoted 8 lines · Max Reitz
Pull out the truncation code from the
qemu_cluster_create()function so we can later reuse it inqemu_gluster_truncate().Signed-off-by Max Reitz <[email protected]>--- block/gluster.c | 74 +++++++++++++++++++++++++++++++-------------------------- 1 file changed, 40 insertions(+), 34 deletions(-)
Signature · 3 lines
Eric Blake, Principal Software Engineer Red Hat, Inc. +1-919-301-3266 Virtualization: qemu.org | libvirt.org
PATCH 3/7 gluster: Query current size in do_truncate()
In reply to Max ReitzInstead of expecting the current size to be 0, query it and allocate only the area [current_size, offset) if preallocation is requested.
--- block/gluster.c | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-)
block/gluster.c +19 -2
@@ -968,10 +968,27 @@ static coroutine_fn int qemu_gluster_co_pwrite_zeroes(BlockDriverState *bs,static int qemu_gluster_do_truncate (struct glfs_fd *fd,int64_t offset,PreallocMode prealloc,Error **errp) { +int64_t current_length; + + current_length =glfs_lseek (fd,0 ,SEEK_END ); +if (current_length <0 ) { +error_setg_errno (errp, errno,"Failed to determine current size" ); +return -errno; + } + +if (current_length > offset && prealloc !=PREALLOC_MODE_OFF ) { +error_setg (errp,"Cannot use preallocation for shrinking files" ); +return -ENOTSUP ; + } + +if (current_length == offset) { +return 0 ; + } +switch (prealloc) {#ifdef CONFIG_GLUSTERFS_FALLOCATE case PREALLOC_MODE_FALLOC : -if (glfs_fallocate (fd,0 ,0 , offset)) { +if (glfs_fallocate (fd,0 , current_length, offset - current_length)) {error_setg_errno (errp, errno,"Could not preallocate data" );return -errno; }
@@ -983,7 +1000,7 @@ static int qemu_gluster_do_truncate(struct glfs_fd *fd, int64_t offset,error_setg_errno (errp, errno,"Could not resize file" );return -errno; } -if (glfs_zerofill (fd,0 , offset)) { +if (glfs_zerofill (fd, current_length, offset - current_length)) {error_setg_errno (errp, errno,"Could not zerofill the new area" );return -errno; }
Signature · 1 line
2.14.3
Re: [Qemu-devel] [PATCH 3/7] gluster: Query current size in do_truncate()
Quoted 8 lines · Max Reitz
Instead of expecting the current size to be 0, query it and allocate only the area [
current_size, offset) if preallocation is requested.Signed-off-by Max Reitz <[email protected]>--- block/gluster.c | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-)
I don't have a gluster setup handy to test this, but the concept matches file-posix and the change looks reasonable.
Signature · 3 lines
Eric Blake, Principal Software Engineer Red Hat, Inc. +1-919-301-3266 Virtualization: qemu.org | libvirt.org
PATCH 4/7 gluster: Add preallocated truncation
In reply to Max ReitzBy using qemu_do_cluster_truncate() in qemu_cluster_truncate(), we now automatically have preallocated truncation.
--- block/gluster.c | 17 +---------------- 1 file changed, 1 insertion(+), 16 deletions(-)
block/gluster.c +1 -16
@@ -1122,23 +1122,8 @@ static coroutine_fn int qemu_gluster_co_rw(BlockDriverState *bs,static int qemu_gluster_truncate (BlockDriverState *bs,int64_t offset,PreallocMode prealloc,Error **errp) { -int ret;BDRVGlusterState *s = bs->opaque; - -if (prealloc !=PREALLOC_MODE_OFF ) { -error_setg (errp,"Unsupported preallocation mode '%s'" , -PreallocMode_str (prealloc)); -return -ENOTSUP ; - } - - ret =glfs_ftruncate (s->fd, offset); -if (ret <0 ) { - ret = -errno; -error_setg_errno (errp, -ret,"Failed to truncate file" ); -return ret; - } - -return 0 ; +return qemu_gluster_do_truncate (s->fd, offset, prealloc, errp); } static coroutine_fn int qemu_gluster_co_readv(BlockDriverState *bs,
Signature · 1 line
2.14.3
Re: [Qemu-devel] [PATCH 4/7] gluster: Add preallocated truncation
Quoted 8 lines · Max Reitz
By using
qemu_do_cluster_truncate()inqemu_cluster_truncate(), we now automatically have preallocated truncation.Signed-off-by Max Reitz <[email protected]>--- block/gluster.c | 17 +---------------- 1 file changed, 1 insertion(+), 16 deletions(-)
Signature · 3 lines
Eric Blake, Principal Software Engineer Red Hat, Inc. +1-919-301-3266 Virtualization: qemu.org | libvirt.org
PATCH 5/7 sheepdog: Make sd_prealloc() take a BDS
In reply to Max ReitzWe want to use this function in sd_truncate() later on, so taking a filename is not exactly ideal.
--- block/sheepdog.c | 29 +++++++++++++++++++++-------- 1 file changed, 21 insertions(+), 8 deletions(-)
block/sheepdog.c +21 -8
@@ -1826,10 +1826,10 @@ static int do_sd_create(BDRVSheepdogState *s, uint32_t *vdi_id, int snapshot,return 0 ; } -static int sd_prealloc (const char *filename,Error **errp) +static int sd_prealloc (BlockDriverState *bs,Error **errp) {BlockBackend *blk =NULL ; -BDRVSheepdogState *base =NULL ; +BDRVSheepdogState *base = bs->opaque;unsigned long buf_size;uint32_t idx, max_idx;uint32_t object_size;
@@ -1837,10 +1837,11 @@ static int sd_prealloc(const char *filename, Error **errp)void *buf =NULL ;int ret; - blk =blk_new_open (filename,NULL ,NULL , -BDRV_O_RDWR |BDRV_O_RESIZE |BDRV_O_PROTOCOL , errp); -if (blk ==NULL ) { - ret = -EIO ; + blk =blk_new (BLK_PERM_CONSISTENT_READ |BLK_PERM_WRITE |BLK_PERM_RESIZE , +BLK_PERM_ALL ); + + ret =blk_insert_bs (blk, bs, errp); +if (ret <0 ) { goto out_with_err_set; }
@@ -1852,7 +1853,6 @@ static int sd_prealloc(const char *filename, Error **errp) goto out; } - base =blk_bs (blk)->opaque; object_size = (UINT32_C (1 ) << base->inode.block_size_shift); buf_size =MIN (object_size,SD_DATA_OBJ_SIZE ); buf =g_malloc0 (buf_size);
@@ -2108,7 +2108,20 @@ static int sd_create(const char *filename, QemuOpts *opts, }if (prealloc) { - ret =sd_prealloc (filename, errp); +BlockDriverState *bs; +QDict *opts; + + opts =qdict_new (); +qdict_put_str (opts,"driver" ,"sheepdog" ); + bs =bdrv_open (filename,NULL , opts,BDRV_O_PROTOCOL |BDRV_O_RDWR , + errp); +if (!bs) { + goto out; + } + + ret =sd_prealloc (bs, errp); + +bdrv_unref (bs); } out:g_free (backing_file);
Signature · 1 line
2.14.3
Re: [Qemu-devel] [PATCH 5/7] sheepdog: Make sd_prealloc() take a BDS
Quoted 23 lines · Max Reitz
We want to use this function in
sd_truncate()later on, so taking a filename is not exactly ideal.Signed-off-by Max Reitz <[email protected]>--- block/sheepdog.c | 29 +++++++++++++++++++++-------- 1 file changed, 21 insertions(+), 8 deletions(-)block/sheepdog.c +5
-4@@ -1837,10 +1837,11 @@ static int sd_prealloc(const char *filename, Error **errp)void *buf =NULL ;int ret; - blk =blk_new_open (filename,NULL ,NULL , -BDRV_O_RDWR |BDRV_O_RESIZE |BDRV_O_PROTOCOL , errp); -if (blk ==NULL ) { - ret = -EIO ; + blk =blk_new (BLK_PERM_CONSISTENT_READ |BLK_PERM_WRITE |BLK_PERM_RESIZE , +BLK_PERM_ALL ); + + ret =blk_insert_bs (blk, bs, errp); +if (ret <0 ) {
block/sheepdog.c static int sd_prealloc(const char *filename, Error **errp)
Quoted 10 lines
block/sheepdog.c +7
-1if (prealloc) { - ret =sd_prealloc (filename, errp); +BlockDriverState *bs; +QDict *opts; + + opts =qdict_new (); +qdict_put_str (opts,"driver" ,"sheepdog" ); + bs =bdrv_open (filename,NULL , opts,BDRV_O_PROTOCOL |BDRV_O_RDWR , + errp);
I'm a bit weak on ensuring the same ending flags result after the new bdrv_open()/blk_new() as what you used to get on blk_new_open(), so someone that can actually test this is appreciated.
Signature · 3 lines
Eric Blake, Principal Software Engineer Red Hat, Inc. +1-919-301-3266 Virtualization: qemu.org | libvirt.org
PATCH 6/7 sheepdog: Pass old and new size to sd_prealloc()
In reply to Max Reitzsd_prealloc() will now preallocate the area [old_size, new_size). As before, it rounds to buf_size and may thus overshoot and preallocate areas that were not requested to be preallocated. For image creation, this is no change in behavior. For truncation, this is in accordance with the documentation for preallocated truncation.
--- block/sheepdog.c | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-)
block/sheepdog.c +5 -11
@@ -1826,14 +1826,14 @@ static int do_sd_create(BDRVSheepdogState *s, uint32_t *vdi_id, int snapshot,return 0 ; } -static int sd_prealloc (BlockDriverState *bs,Error **errp) +static int sd_prealloc (BlockDriverState *bs,int64_t old_size,int64_t new_size, +Error **errp) {BlockBackend *blk =NULL ;BDRVSheepdogState *base = bs->opaque;unsigned long buf_size;uint32_t idx, max_idx;uint32_t object_size; -int64_t vdi_size;void *buf =NULL ;int ret;
@@ -1847,19 +1847,13 @@ static int sd_prealloc(BlockDriverState *bs, Error **errp)blk_set_allow_write_beyond_eof (blk, true); - vdi_size =blk_getlength (blk); -if (vdi_size <0 ) { - ret = vdi_size; - goto out; - } - object_size = (UINT32_C (1 ) << base->inode.block_size_shift); buf_size =MIN (object_size,SD_DATA_OBJ_SIZE ); buf =g_malloc0 (buf_size); - max_idx =DIV_ROUND_UP (vdi_size, buf_size); + max_idx =DIV_ROUND_UP (new_size, buf_size); -for (idx =0 ; idx < max_idx; idx++) { +for (idx = old_size / buf_size; idx < max_idx; idx++) {/* * The created image can be a cloned image, so we need to read * a data from the source image.
@@ -2119,7 +2113,7 @@ static int sd_create(const char *filename, QemuOpts *opts, goto out; } - ret =sd_prealloc (bs, errp); + ret =sd_prealloc (bs,0 , s->inode.vdi_size, errp);bdrv_unref (bs); }
Signature · 1 line
2.14.3
Re: [Qemu-devel] [PATCH 6/7] sheepdog: Pass old and new size to sd_prealloc()
Quoted 24 lines · Max Reitz
sd_prealloc()will now preallocate the area [old_size,new_size). As before, it rounds tobuf_sizeand may thus overshoot and preallocate areas that were not requested to be preallocated. For image creation, this is no change in behavior. For truncation, this is in accordance with the documentation for preallocated truncation.Signed-off-by Max Reitz <[email protected]>--- block/sheepdog.c | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-)block/sheepdog.c +0
-6@@ -1847,19 +1847,13 @@ static int sd_prealloc(BlockDriverState *bs, Error **errp)blk_set_allow_write_beyond_eof (blk, true); - vdi_size =blk_getlength (blk); -if (vdi_size <0 ) { - ret = vdi_size; - goto out; - } -
block/sheepdog.c static int sd_create(const char *filename, QemuOpts *opts, · line 2116
Quoted 5 lines
block/sheepdog.c +1
-1@@ -2119,7 +2113,7 @@ static int sd_create(const char *filename, QemuOpts *opts, goto out; } - ret =sd_prealloc (bs, errp); + ret =sd_prealloc (bs,0 , s->inode.vdi_size, errp);
Nice - you also got rid of a potential failure in blk_getlength().
Signature · 3 lines
Eric Blake, Principal Software Engineer Red Hat, Inc. +1-919-301-3266 Virtualization: qemu.org | libvirt.org
PATCH 7/7 sheepdog: Allow fully preallocated truncation
In reply to Max Reitz--- block/sheepdog.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-)
block/sheepdog.c +12 -3
@@ -2180,15 +2180,16 @@ static int sd_truncate(BlockDriverState *bs, int64_t offset,int ret, fd;unsigned int datalen;uint64_t max_vdi_size; +int64_t old_size = s->inode.vdi_size; -if (prealloc !=PREALLOC_MODE_OFF ) { +if (prealloc !=PREALLOC_MODE_OFF && prealloc !=PREALLOC_MODE_FULL ) {error_setg (errp,"Unsupported preallocation mode '%s'" ,PreallocMode_str (prealloc));return -ENOTSUP ; } max_vdi_size = (UINT64_C (1 ) << s->inode.block_size_shift) *MAX_DATA_OBJS ; -if (offset < s->inode.vdi_size) { +if (offset < old_size) {error_setg (errp,"shrinking is not supported" );return -EINVAL ; }else if (offset > max_vdi_size) {
@@ -2211,9 +2212,17 @@ static int sd_truncate(BlockDriverState *bs, int64_t offset,if (ret <0 ) {error_setg_errno (errp, -ret,"failed to update an inode" ); +return ret; } -return ret; +if (prealloc ==PREALLOC_MODE_FULL ) { + ret =sd_prealloc (bs, old_size, offset, errp); +if (ret <0 ) { +return ret; + } + } + +return 0 ; }/*
Signature · 1 line
2.14.3
Re: [Qemu-devel] [PATCH 7/7] sheepdog: Allow fully preallocated truncation
Quoted 5 lines · Max Reitz
Signed-off-by Max Reitz <[email protected]>--- block/sheepdog.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-)
Signature · 3 lines
Eric Blake, Principal Software Engineer Red Hat, Inc. +1-919-301-3266 Virtualization: qemu.org | libvirt.org
Kevin Wolf
AppliedAm 13.02.2018 um 14:03 hat Max Reitz geschrieben:
Quoted 9 lines
As far as I can see, these are the only protocols beside file-posix that support preallocated creation. In contrast to file-posix, however, they have not supported preallocated truncation so far. This series brings their truncation code to feature parity with their creation code in this regard.
Note that I do not have a test setup for either of the two drivers, so I do not actually know whether this works. Anyone with a setup is more than welcome to test this series.
Thanks, applied to the block branch.
We'll see if someone screams once this hits master.
Kevin