[V4] libxfs: use FALLOC_FL_ZERO_RANGE in libxfs_device_zero
diff mbox series

Message ID 1c7c39f7-91a7-be85-5906-e55180a91a5f@sandeen.net
State Accepted
Headers show
Series
  • [V4] libxfs: use FALLOC_FL_ZERO_RANGE in libxfs_device_zero
Related show

Commit Message

Eric Sandeen Feb. 25, 2020, 6:13 p.m. UTC
I had a request from someone who cared about mkfs speed over
a slower network block device to look into using faster zeroing
methods, particularly for the log, during mkfs.

Using FALLOC_FL_ZERO_RANGE is faster in this case than writing
a bunch of zeros across a wire.

Signed-off-by: Eric Sandeen <sandeen@redhat.com>
---

V2: Clean up all the nasty stuff I'd flung out there as a wild first
cut, thanks Dave.

V3: make len_bytes a size_t; leave "end_offset" where it is for the loop
use.  It's a bit odd but ... just don't mess with it for now, one patch
one change.

V4: Use EOPNOTSUPP not EOPNOTSUP (same on linux anyway but meh)
I ignored(tm) darrick's suggestion to make libxfs_device_zero accept
a longer length, for now - no callers need anything bigger at this time.

Comments

Christoph Hellwig Feb. 25, 2020, 6:46 p.m. UTC | #1
On Tue, Feb 25, 2020 at 10:13:55AM -0800, Eric Sandeen wrote:
> I had a request from someone who cared about mkfs speed over
> a slower network block device to look into using faster zeroing
> methods, particularly for the log, during mkfs.
> 
> Using FALLOC_FL_ZERO_RANGE is faster in this case than writing
> a bunch of zeros across a wire.
> 
> Signed-off-by: Eric Sandeen <sandeen@redhat.com>

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>
Darrick J. Wong Feb. 25, 2020, 7:16 p.m. UTC | #2
On Tue, Feb 25, 2020 at 10:13:55AM -0800, Eric Sandeen wrote:
> I had a request from someone who cared about mkfs speed over
> a slower network block device to look into using faster zeroing
> methods, particularly for the log, during mkfs.
> 
> Using FALLOC_FL_ZERO_RANGE is faster in this case than writing
> a bunch of zeros across a wire.
> 
> Signed-off-by: Eric Sandeen <sandeen@redhat.com>
> ---
> 
> V2: Clean up all the nasty stuff I'd flung out there as a wild first
> cut, thanks Dave.
> 
> V3: make len_bytes a size_t; leave "end_offset" where it is for the loop
> use.  It's a bit odd but ... just don't mess with it for now, one patch
> one change.
> 
> V4: Use EOPNOTSUPP not EOPNOTSUP (same on linux anyway but meh)
> I ignored(tm) darrick's suggestion to make libxfs_device_zero accept
> a longer length, for now - no callers need anything bigger at this time.

But... 

> diff --git a/include/builddefs.in b/include/builddefs.in
> index 4700b527..1dd27f76 100644
> --- a/include/builddefs.in
> +++ b/include/builddefs.in
> @@ -144,6 +144,9 @@ endif
>  ifeq ($(HAVE_GETFSMAP),yes)
>  PCFLAGS+= -DHAVE_GETFSMAP
>  endif
> +ifeq ($(HAVE_FALLOCATE),yes)
> +PCFLAGS += -DHAVE_FALLOCATE
> +endif
>  
>  LIBICU_LIBS = @libicu_LIBS@
>  LIBICU_CFLAGS = @libicu_CFLAGS@
> diff --git a/include/linux.h b/include/linux.h
> index 8f3c32b0..8d5c4584 100644
> --- a/include/linux.h
> +++ b/include/linux.h
> @@ -20,6 +20,10 @@
>  #include <stdio.h>
>  #include <asm/types.h>
>  #include <mntent.h>
> +#include <fcntl.h>
> +#if defined(HAVE_FALLOCATE)
> +#include <linux/falloc.h>
> +#endif
>  #ifdef OVERRIDE_SYSTEM_FSXATTR
>  # define fsxattr sys_fsxattr
>  #endif
> @@ -164,6 +168,24 @@ static inline void platform_mntent_close(struct mntent_cursor * cursor)
>  	endmntent(cursor->mtabp);
>  }
>  
> +#if defined(FALLOC_FL_ZERO_RANGE)
> +static inline int
> +platform_zero_range(
> +	int		fd,
> +	xfs_off_t	start,
> +	size_t		len)
> +{
> +	int ret;
> +
> +	ret = fallocate(fd, FALLOC_FL_ZERO_RANGE, start, len);
> +	if (!ret)
> +		return 0;
> +	return -errno;
> +}
> +#else
> +#define platform_zero_range(fd, s, l)	(-EOPNOTSUPP)
> +#endif
> +
>  /*
>   * Check whether we have to define FS_IOC_FS[GS]ETXATTR ourselves. These
>   * are a copy of the definitions moved to linux/uapi/fs.h in the 4.5 kernel,
> diff --git a/libxfs/rdwr.c b/libxfs/rdwr.c
> index 0d9d7202..e2d9d790 100644
> --- a/libxfs/rdwr.c
> +++ b/libxfs/rdwr.c
> @@ -61,8 +61,18 @@ libxfs_device_zero(struct xfs_buftarg *btp, xfs_daddr_t start, uint len)
>  {
>  	xfs_off_t	start_offset, end_offset, offset;
>  	ssize_t		zsize, bytes;
> +	size_t		len_bytes;
>  	char		*z;
> -	int		fd;
> +	int		error, fd;
> +
> +	fd = libxfs_device_to_fd(btp->dev);
> +	start_offset = LIBXFS_BBTOOFF64(start);
> +
> +	/* try to use special zeroing methods, fall back to writes if needed */
> +	len_bytes = LIBXFS_BBTOOFF64(len);

...but if the caller passes in (say) 2^23 daddrs on a 32-bit system,
this conversion will try to stuff 2^32 into a size_t (which is 32-bit),
causing an integer overflow.  I grok that no callers currently try this,
but this seems like leaving a logic bomb that could go off on what are
becoming difficult-to-test architectures.

Granted the added overflow checking and whatnot required to convert that
last parameter of libxfs_device_zero to unsigned long long could very
well justify a separate patch for fixing the 64-bitness of the whole
api.

--D 

> +	error = platform_zero_range(fd, start_offset, len_bytes);
> +	if (!error)
> +		return 0;
>  
>  	zsize = min(BDSTRAT_SIZE, BBTOB(len));
>  	if ((z = memalign(libxfs_device_alignment(), zsize)) == NULL) {
> @@ -73,9 +83,6 @@ libxfs_device_zero(struct xfs_buftarg *btp, xfs_daddr_t start, uint len)
>  	}
>  	memset(z, 0, zsize);
>  
> -	fd = libxfs_device_to_fd(btp->dev);
> -	start_offset = LIBXFS_BBTOOFF64(start);
> -
>  	if ((lseek(fd, start_offset, SEEK_SET)) < 0) {
>  		fprintf(stderr, _("%s: %s seek to offset %llu failed: %s\n"),
>  			progname, __FUNCTION__,
> 
>
Eric Sandeen Feb. 25, 2020, 11:33 p.m. UTC | #3
On 2/25/20 11:16 AM, Darrick J. Wong wrote:
> On Tue, Feb 25, 2020 at 10:13:55AM -0800, Eric Sandeen wrote:
>> I had a request from someone who cared about mkfs speed over
>> a slower network block device to look into using faster zeroing
>> methods, particularly for the log, during mkfs.
>>
>> Using FALLOC_FL_ZERO_RANGE is faster in this case than writing
>> a bunch of zeros across a wire.
>>
>> Signed-off-by: Eric Sandeen <sandeen@redhat.com>
>> ---
>>
>> V2: Clean up all the nasty stuff I'd flung out there as a wild first
>> cut, thanks Dave.
>>
>> V3: make len_bytes a size_t; leave "end_offset" where it is for the loop
>> use.  It's a bit odd but ... just don't mess with it for now, one patch
>> one change.
>>
>> V4: Use EOPNOTSUPP not EOPNOTSUP (same on linux anyway but meh)
>> I ignored(tm) darrick's suggestion to make libxfs_device_zero accept
>> a longer length, for now - no callers need anything bigger at this time.
> 
> But... 
> 

...

>> diff --git a/libxfs/rdwr.c b/libxfs/rdwr.c
>> index 0d9d7202..e2d9d790 100644
>> --- a/libxfs/rdwr.c
>> +++ b/libxfs/rdwr.c
>> @@ -61,8 +61,18 @@ libxfs_device_zero(struct xfs_buftarg *btp, xfs_daddr_t start, uint len)
>>  {
>>  	xfs_off_t	start_offset, end_offset, offset;
>>  	ssize_t		zsize, bytes;
>> +	size_t		len_bytes;
>>  	char		*z;
>> -	int		fd;
>> +	int		error, fd;
>> +
>> +	fd = libxfs_device_to_fd(btp->dev);
>> +	start_offset = LIBXFS_BBTOOFF64(start);
>> +
>> +	/* try to use special zeroing methods, fall back to writes if needed */
>> +	len_bytes = LIBXFS_BBTOOFF64(len);
> 
> ...but if the caller passes in (say) 2^23 daddrs on a 32-bit system,
> this conversion will try to stuff 2^32 into a size_t (which is 32-bit),
> causing an integer overflow.  I grok that no callers currently try this,
> but this seems like leaving a logic bomb that could go off on what are
> becoming difficult-to-test architectures.

That's true, but ....

> Granted the added overflow checking and whatnot required to convert that
> last parameter of libxfs_device_zero to unsigned long long could very
> well justify a separate patch for fixing the 64-bitness of the whole
> api.
> 
> --D 
> 
>> +	error = platform_zero_range(fd, start_offset, len_bytes);
>> +	if (!error)
>> +		return 0;
>>  
>>  	zsize = min(BDSTRAT_SIZE, BBTOB(len));

it's an existing problem, right?  One which this patch doesn't address.  :)

-Eric

Patch
diff mbox series

diff --git a/include/builddefs.in b/include/builddefs.in
index 4700b527..1dd27f76 100644
--- a/include/builddefs.in
+++ b/include/builddefs.in
@@ -144,6 +144,9 @@  endif
 ifeq ($(HAVE_GETFSMAP),yes)
 PCFLAGS+= -DHAVE_GETFSMAP
 endif
+ifeq ($(HAVE_FALLOCATE),yes)
+PCFLAGS += -DHAVE_FALLOCATE
+endif
 
 LIBICU_LIBS = @libicu_LIBS@
 LIBICU_CFLAGS = @libicu_CFLAGS@
diff --git a/include/linux.h b/include/linux.h
index 8f3c32b0..8d5c4584 100644
--- a/include/linux.h
+++ b/include/linux.h
@@ -20,6 +20,10 @@ 
 #include <stdio.h>
 #include <asm/types.h>
 #include <mntent.h>
+#include <fcntl.h>
+#if defined(HAVE_FALLOCATE)
+#include <linux/falloc.h>
+#endif
 #ifdef OVERRIDE_SYSTEM_FSXATTR
 # define fsxattr sys_fsxattr
 #endif
@@ -164,6 +168,24 @@  static inline void platform_mntent_close(struct mntent_cursor * cursor)
 	endmntent(cursor->mtabp);
 }
 
+#if defined(FALLOC_FL_ZERO_RANGE)
+static inline int
+platform_zero_range(
+	int		fd,
+	xfs_off_t	start,
+	size_t		len)
+{
+	int ret;
+
+	ret = fallocate(fd, FALLOC_FL_ZERO_RANGE, start, len);
+	if (!ret)
+		return 0;
+	return -errno;
+}
+#else
+#define platform_zero_range(fd, s, l)	(-EOPNOTSUPP)
+#endif
+
 /*
  * Check whether we have to define FS_IOC_FS[GS]ETXATTR ourselves. These
  * are a copy of the definitions moved to linux/uapi/fs.h in the 4.5 kernel,
diff --git a/libxfs/rdwr.c b/libxfs/rdwr.c
index 0d9d7202..e2d9d790 100644
--- a/libxfs/rdwr.c
+++ b/libxfs/rdwr.c
@@ -61,8 +61,18 @@  libxfs_device_zero(struct xfs_buftarg *btp, xfs_daddr_t start, uint len)
 {
 	xfs_off_t	start_offset, end_offset, offset;
 	ssize_t		zsize, bytes;
+	size_t		len_bytes;
 	char		*z;
-	int		fd;
+	int		error, fd;
+
+	fd = libxfs_device_to_fd(btp->dev);
+	start_offset = LIBXFS_BBTOOFF64(start);
+
+	/* try to use special zeroing methods, fall back to writes if needed */
+	len_bytes = LIBXFS_BBTOOFF64(len);
+	error = platform_zero_range(fd, start_offset, len_bytes);
+	if (!error)
+		return 0;
 
 	zsize = min(BDSTRAT_SIZE, BBTOB(len));
 	if ((z = memalign(libxfs_device_alignment(), zsize)) == NULL) {
@@ -73,9 +83,6 @@  libxfs_device_zero(struct xfs_buftarg *btp, xfs_daddr_t start, uint len)
 	}
 	memset(z, 0, zsize);
 
-	fd = libxfs_device_to_fd(btp->dev);
-	start_offset = LIBXFS_BBTOOFF64(start);
-
 	if ((lseek(fd, start_offset, SEEK_SET)) < 0) {
 		fprintf(stderr, _("%s: %s seek to offset %llu failed: %s\n"),
 			progname, __FUNCTION__,