search for: file_zero

..., uint32_t count, uint64_t offset) offset += r; } + if ((flags & NBDKIT_FLAG_FUA) && file_flush (handle, 0) == -1) + return -1; + return 0; } @@ -323,20 +350,20 @@ do_fallocate(int fd, int mode, off_t offset, off_t len) /* Write zeroes to the file. */ static int -file_zero (void *handle, uint32_t count, uint64_t offset, int may_trim) +file_zero (void *handle, uint32_t count, uint64_t offset, uint32_t flags) { struct handle *h = handle; int r; #ifdef FALLOC_FL_PUNCH_HOLE - if (h->can_punch_hole && may_trim) { + if (h->can_punch_hole &&amp...

...ad data from the file. */ static int file_pread (void *handle, void *buf, uint32_t count, uint64_t offset) @@ -219,7 +231,7 @@ file_pwrite (void *handle, const void *buf, uint32_t count, uint64_t offset) return 0; } -/* Write data to the file. */ +/* Write zeroes to the file. */ static int file_zero (void *handle, uint32_t count, uint64_t offset, int may_trim) { @@ -268,6 +280,33 @@ file_flush (void *handle) return 0; } +/* Punch a hole in the file. */ +static int +file_trim (void *handle, uint32_t count, uint64_t offset) +{ + int r = -1; +#ifdef FALLOC_FL_PUNCH_HOLE + struct handle *h...

...uild nbdkit on RHEL, but the change is pretty trivial. --- plugins/file/file.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/plugins/file/file.c b/plugins/file/file.c index b6e33de..a7c07fb 100644 --- a/plugins/file/file.c +++ b/plugins/file/file.c @@ -243,7 +243,7 @@ file_zero (void *handle, uint32_t count, uint64_t offset, int may_trim) if (may_trim) { r = fallocate (h->fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, offset, count); - if (r == -1 && errno != EOPNOTSUPP) { + if (r == -1 && errno != EOPNOTSUPP && errno != ENO...

...ins/file/file.c | 8 ++++---- > > 1 file changed, 4 insertions(+), 4 deletions(-) > > > >diff --git a/plugins/file/file.c b/plugins/file/file.c > >index b6e33de..a7c07fb 100644 > >--- a/plugins/file/file.c > >+++ b/plugins/file/file.c > >@@ -243,7 +243,7 @@ file_zero (void *handle, uint32_t count, uint64_t offset, int may_trim) > > if (may_trim) { > > r = fallocate (h->fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, > > offset, count); > >- if (r == -1 && errno != EOPNOTSUPP) { > >+ if (r == -1 &&...

...el 3.10 fails with ENODEV for block device. Kernel >= 4.9 fails + with EOPNOTSUPP in this case. Normalize errno to simplify callers. */ + if (r == -1 && errno == ENODEV) { + errno = EOPNOTSUPP; + } + return r; +} +#endif + static void file_unload (void) { @@ -241,9 +256,9 @@ file_zero (void *handle, uint32_t count, uint64_t offset, int may_trim) #ifdef FALLOC_FL_PUNCH_HOLE if (may_trim) { - r = fallocate (h->fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, - offset, count); - if (r == -1 && errno != EOPNOTSUPP && errno != ENODEV) { + r = do_f...

...nel 3.10 fails with ENODEV for block device. Kernel >= 4.9 fails + with EOPNOTSUPP in this case. Normlize errno to simplify callers. */ + if (r == -1 && errno == ENODEV) { + errno = EOPNOTSUPP; + } + return r; +} +#endif + static void file_unload (void) { @@ -241,9 +256,9 @@ file_zero (void *handle, uint32_t count, uint64_t offset, int may_trim) #ifdef FALLOC_FL_PUNCH_HOLE if (may_trim) { - r = fallocate (h->fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, - offset, count); - if (r == -1 && errno != EOPNOTSUPP && errno != ENODEV) { + r = do_f...

FYI I added a few enhancements to allow easier tracing inside the file plugin: https://github.com/libguestfs/nbdkit/commit/10d4dcfb30cb0ba626a2ec503c7c96f72c6ca88e https://github.com/libguestfs/nbdkit/commit/96a41cd798ec0dce07d97c2a4a04ee6284e1552f I learned from this that the file_zero function does successfully use fallocate to zero ranges, at least on my very recent Linux system. Rich. -- Richard Jones, Virtualization Group, Red Hat http://people.redhat.com/~rjones Read my programming and virtualization blog: http://rwmj.wordpress.com virt-p2v converts physical machines to v...

...ile/file.c @@ -73,6 +73,12 @@ static pthread_mutex_t lseek_lock = PTHREAD_MUTEX_INITIALIZER; /* to enable: -D file.zero=1 */ int file_debug_zero; +static bool +file_is_enotsup (int err) +{ + return err == ENOTSUP || err == EOPNOTSUPP; +} + static void file_unload (void) { @@ -399,7 +405,7 @@ file_zero (void *handle, uint32_t count, uint64_t offset, uint32_t flags) goto out; } - if (errno != EOPNOTSUPP) { + if (!file_is_enotsup (errno)) { nbdkit_error ("zero: %m"); return -1; } @@ -418,7 +424,7 @@ file_zero (void *handle, uint32_t count, uint64_t of...

...rivial. > --- > plugins/file/file.c | 8 ++++---- > 1 file changed, 4 insertions(+), 4 deletions(-) > > diff --git a/plugins/file/file.c b/plugins/file/file.c > index b6e33de..a7c07fb 100644 > --- a/plugins/file/file.c > +++ b/plugins/file/file.c > @@ -243,7 +243,7 @@ file_zero (void *handle, uint32_t count, uint64_t offset, int may_trim) > if (may_trim) { > r = fallocate (h->fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, > offset, count); > - if (r == -1 && errno != EOPNOTSUPP) { > + if (r == -1 && errno != EOPNOT...

I ran into these while trying to prepare patches to add NBD_CMD_FLAG_FAST_ZERO, which will expose a new NBD_ENOTSUP wire value. Eric Blake (2): plugins: Don't lose original error when emulating FUA plugins: Permit ENOTSUP as synonym for EOPNOTSUPP docs/nbdkit-filter.pod | 11 ++++++----- docs/nbdkit-plugin.pod | 12 +++++++----- plugins/file/file.c | 16 +++++++++++-----

...fall back... > + } > + } > +#else > + h->sector_size = 4096; /* Safe guess */ ...to the safe guess, instead of giving up entirely? (Might matter on a system with newer headers that have the macro, but where the kernel does not support the ioctl). > @@ -329,6 +361,20 @@ file_zero (void *handle, uint32_t count, uint64_t offset, int may_trim) > } > #endif > > +#ifdef BLKZEROOUT > + /* For aligned range and block devices, we can use BLKZEROOUT. */ > + if (h->is_block_device && is_aligned (h, offset) && is_aligned (h, count)) { S...

First thing to say is that I need to do a *lot* more testing on this, so this is just an early peek. In particular, although it passed ‘make check && make check-valgrind’ I have *not* tested it against a multi-conn-aware client such as the Linux kernel >= 4.9. This implements NBD_FLAG_CAN_MULTI_CONN, described in the protocol doc as: "NBD_FLAG_CAN_MULTI_CONN: Indicates that

This version addresses some of the comments on v2. Changes since v2: - file_zero: Add missing space in function call - is_aligned: Assert that align is indeed a power of 2 - Spelling in commit message Not changed: - Eric commented that spacing was off: https://www.redhat.com/archives/libguestfs/2018-August/msg00113.html but I could not find anything wrong. - Eric asked if...

This version addresses comments on v3. Changes since v3: - Finally got spacing right (Eric) - Reorder includes (Richard) - Return 0 or -1 instead of r (Richard) - Add common/include/isaligned.h to Makefile.am (Richard) v3 was here: https://www.redhat.com/archives/libguestfs/2018-August/msg00177.html Nir Soffer (4): file: Avoid unsupported fallocate() calls file: Support zero without

This is the second version to support efficient zero for block devices on older kernels (e.g. RHEL 7.5), and file systems that do not support yet FALLOC_FS_ZERO_RANGE (e.g. NFS 4.2). Changes since v1: - Split to smaller patches - Skip linux only includes on other systems - Skip code using BLKZEROOUT if the macro is not defined - Try BLKZEROOUT only if the offset and count are aligned to device

For existing commits, this is almost identical to v1, except that I updated some commit messages and reordered the commits in a somewhat more logical sequence. The main changes are the extra commits: [06/11] plugins: Return NBD_FLAG_CAN_MULTI_CONN from some readonly plugins. - Readonly plugins that can set the flag unconditionally. [09/11] partitioning: Return NBD_FLAG_CAN_MULTI_CONN. [10/11]

...assert (is_power_of_2 ((align))); \ + !((size) & ((align) - 1)); \ +}) #endif /* NBDKIT_ISALIGNED_H */ diff --git a/plugins/file/file.c b/plugins/file/file.c index 9d03f18..1391f62 100644 --- a/plugins/file/file.c +++ b/plugins/file/file.c @@ -397,13 +397,13 @@ file_zero (void *handle, uint32_t count, uint64_t offset, int may_trim) #ifdef BLKZEROOUT /* For aligned range and block device, we can use BLKZEROOUT. */ - if (h->can_zeroout && is_aligned (offset | count, h->sector_size)) { + if (h->can_zeroout && IS_ALIGNED (offset | count...

This is the third version to support efficient zero for block devices on older kernels (e.g. RHEL 7.5), and file systems that do not support yet FALLOC_FS_ZERO_RANGE (e.g. NFS 4.2). Changes since v2: - Revert file_can_trim change, since it is too late to change the value after negotiation. Changing the capability dinamically may be useful internally, but it should be done via other means. -

...assert (is_power_of_2 ((align))); \ + !((size) & ((align) - 1)); \ +}) #endif /* NBDKIT_ISALIGNED_H */ diff --git a/plugins/file/file.c b/plugins/file/file.c index 9d03f18..1391f62 100644 --- a/plugins/file/file.c +++ b/plugins/file/file.c @@ -397,13 +397,13 @@ file_zero (void *handle, uint32_t count, uint64_t offset, int may_trim) #ifdef BLKZEROOUT /* For aligned range and block device, we can use BLKZEROOUT. */ - if (h->can_zeroout && is_aligned (offset | count, h->sector_size)) { + if (h->can_zeroout && IS_ALIGNED (offset | count...

...t handle { int fd; bool can_punch_hole; bool can_zero_range; + bool can_fallocate; }; /* Create the per-connection handle. */ @@ -161,6 +162,8 @@ file_open (int readonly) h->can_zero_range = false; #endif + h->can_fallocate = true; + return h; } @@ -297,6 +300,35 @@ file_zero (void *handle, uint32_t count, uint64_t offset, int may_trim) } #endif +#ifdef FALLOC_FL_PUNCH_HOLE + /* If we can punch hole but may not trim, we can combine punching hole and + fallocate to zero a range. This is expected to be more efficient than + writing zeros manually. */ + i...