From: "Darrick J. Wong" <darrick.wong@oracle.com>
To: tytso@mit.edu
Cc: linux-ext4@vger.kernel.org
Subject: Re: [PATCH 15/34] libext2fs: support BLKZEROOUT/FALLOC_FL_ZERO_RANGE in ext2fs_zero_blocks
Date: Mon, 13 Oct 2014 19:58:53 -0700 [thread overview]
Message-ID: <20141014025853.GI12009@birch.djwong.org> (raw)
In-Reply-To: <20140913221253.13646.7723.stgit@birch.djwong.org>
On Sat, Sep 13, 2014 at 03:12:53PM -0700, Darrick J. Wong wrote:
> Plumb a new call into the IO manager to support translating
> ext2fs_zero_blocks calls into the equivalent kernel-level BLKZEROOUT
> ioctl or FALLOC_FL_ZERO_RANGE fallocate flag primitives when possible.
>
> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
> ---
> contrib/fallocate.c | 14 +++++++++
> lib/ext2fs/ext2_io.h | 7 ++++-
> lib/ext2fs/io_manager.c | 11 +++++++
> lib/ext2fs/mkjournal.c | 6 ++++
> lib/ext2fs/test_io.c | 21 ++++++++++++++
> lib/ext2fs/unix_io.c | 71 +++++++++++++++++++++++++++++++++++++++++++++++
> 6 files changed, 128 insertions(+), 2 deletions(-)
>
>
> diff --git a/contrib/fallocate.c b/contrib/fallocate.c
> index 1f9b59a..01d4af7 100644
> --- a/contrib/fallocate.c
> +++ b/contrib/fallocate.c
> @@ -36,6 +36,8 @@
> // #include <linux/falloc.h>
> #define FALLOC_FL_KEEP_SIZE 0x01
> #define FALLOC_FL_PUNCH_HOLE 0x02 /* de-allocates range */
> +#define FALLOC_FL_COLLAPSE_RANGE 0x08
> +#define FALLOC_FL_ZERO_RANGE 0x10
>
> void usage(void)
> {
> @@ -95,7 +97,7 @@ int main(int argc, char **argv)
> int error;
> int tflag = 0;
>
> - while ((opt = getopt(argc, argv, "npl:o:t")) != -1) {
> + while ((opt = getopt(argc, argv, "npl:o:tzc")) != -1) {
> switch(opt) {
> case 'n':
> /* do not change filesize */
> @@ -106,6 +108,16 @@ int main(int argc, char **argv)
> falloc_mode = (FALLOC_FL_PUNCH_HOLE |
> FALLOC_FL_KEEP_SIZE);
> break;
> + case 'c':
> + /* collapse range mode */
> + falloc_mode = (FALLOC_FL_COLLAPSE_RANGE |
> + FALLOC_FL_KEEP_SIZE);
> + break;
> + case 'z':
> + /* zero range mode */
> + falloc_mode = (FALLOC_FL_ZERO_RANGE |
> + FALLOC_FL_KEEP_SIZE);
> + break;
> case 'l':
> length = cvtnum(optarg);
> break;
> diff --git a/lib/ext2fs/ext2_io.h b/lib/ext2fs/ext2_io.h
> index 4c5a5c5..1faa720 100644
> --- a/lib/ext2fs/ext2_io.h
> +++ b/lib/ext2fs/ext2_io.h
> @@ -93,7 +93,9 @@ struct struct_io_manager {
> errcode_t (*cache_readahead)(io_channel channel,
> unsigned long long block,
> unsigned long long count);
> - long reserved[15];
> + errcode_t (*zeroout)(io_channel channel, unsigned long long block,
> + unsigned long long count);
> + long reserved[14];
> };
>
> #define IO_FLAG_RW 0x0001
> @@ -125,6 +127,9 @@ extern errcode_t io_channel_write_blk64(io_channel channel,
> extern errcode_t io_channel_discard(io_channel channel,
> unsigned long long block,
> unsigned long long count);
> +extern errcode_t io_channel_zeroout(io_channel channel,
> + unsigned long long block,
> + unsigned long long count);
> extern errcode_t io_channel_alloc_buf(io_channel channel,
> int count, void *ptr);
> extern errcode_t io_channel_cache_readahead(io_channel io,
> diff --git a/lib/ext2fs/io_manager.c b/lib/ext2fs/io_manager.c
> index dc5888d..c395d61 100644
> --- a/lib/ext2fs/io_manager.c
> +++ b/lib/ext2fs/io_manager.c
> @@ -112,6 +112,17 @@ errcode_t io_channel_discard(io_channel channel, unsigned long long block,
> return EXT2_ET_UNIMPLEMENTED;
> }
>
> +errcode_t io_channel_zeroout(io_channel channel, unsigned long long block,
> + unsigned long long count)
> +{
> + EXT2_CHECK_MAGIC(channel, EXT2_ET_MAGIC_IO_CHANNEL);
> +
> + if (channel->manager->zeroout)
> + return (channel->manager->zeroout)(channel, block, count);
> +
> + return EXT2_ET_UNIMPLEMENTED;
> +}
> +
> errcode_t io_channel_alloc_buf(io_channel io, int count, void *ptr)
> {
> size_t size;
> diff --git a/lib/ext2fs/mkjournal.c b/lib/ext2fs/mkjournal.c
> index 6f3a862..5be425c 100644
> --- a/lib/ext2fs/mkjournal.c
> +++ b/lib/ext2fs/mkjournal.c
> @@ -164,6 +164,12 @@ errcode_t ext2fs_zero_blocks2(ext2_filsys fs, blk64_t blk, int num,
> }
> return 0;
> }
> +
> + /* Try a zero out command, if supported */
> + retval = io_channel_zeroout(fs->io, blk, num);
> + if (retval == 0)
> + return 0;
> +
> /* Allocate the zeroizing buffer if necessary */
> if (!buf) {
> buf = malloc(fs->blocksize * STRIDE_LENGTH);
> diff --git a/lib/ext2fs/test_io.c b/lib/ext2fs/test_io.c
> index b03a939..f7c50d1 100644
> --- a/lib/ext2fs/test_io.c
> +++ b/lib/ext2fs/test_io.c
> @@ -86,6 +86,7 @@ void (*test_io_cb_write_byte)
> #define TEST_FLAG_SET_OPTION 0x20
> #define TEST_FLAG_DISCARD 0x40
> #define TEST_FLAG_READAHEAD 0x80
> +#define TEST_FLAG_ZEROOUT 0x100
>
> static void test_dump_block(io_channel channel,
> struct test_private_data *data,
> @@ -507,6 +508,25 @@ static errcode_t test_cache_readahead(io_channel channel,
> return retval;
> }
>
> +static errcode_t test_zeroout(io_channel channel, unsigned long long block,
> + unsigned long long count)
> +{
> + struct test_private_data *data;
> + errcode_t retval = 0;
> +
> + EXT2_CHECK_MAGIC(channel, EXT2_ET_MAGIC_IO_CHANNEL);
> + data = (struct test_private_data *) channel->private_data;
> + EXT2_CHECK_MAGIC(data, EXT2_ET_MAGIC_TEST_IO_CHANNEL);
> +
> + if (data->real)
> + retval = io_channel_zeroout(data->real, block, count);
> + if (data->flags & TEST_FLAG_ZEROOUT)
> + fprintf(data->outfile,
> + "Test_io: zeroout(%llu, %llu) returned %s\n",
> + block, count, retval ? error_message(retval) : "OK");
> + return retval;
> +}
> +
> static struct struct_io_manager struct_test_manager = {
> .magic = EXT2_ET_MAGIC_IO_MANAGER,
> .name = "Test I/O Manager",
> @@ -523,6 +543,7 @@ static struct struct_io_manager struct_test_manager = {
> .write_blk64 = test_write_blk64,
> .discard = test_discard,
> .cache_readahead = test_cache_readahead,
> + .zeroout = test_zeroout,
> };
>
> io_manager test_io_manager = &struct_test_manager;
> diff --git a/lib/ext2fs/unix_io.c b/lib/ext2fs/unix_io.c
> index 189adce..20e5b64 100644
> --- a/lib/ext2fs/unix_io.c
> +++ b/lib/ext2fs/unix_io.c
> @@ -986,6 +986,76 @@ unimplemented:
> return EXT2_ET_UNIMPLEMENTED;
> }
>
> +#if defined(__linux__) && !defined(BLKZEROOUT)
> +#define BLKZEROOUT _IO(0x12, 127)
> +#endif
> +
> +#if defined(__linux__) && !defined(FALLOC_FL_ZERO_RANGE)
> +#define FALLOC_FL_ZERO_RANGE 0x10
> +#endif
> +
> +static errcode_t unix_zeroout(io_channel channel, unsigned long long block,
> + unsigned long long count)
> +{
> + struct unix_private_data *data;
> + int ret;
> +
> + EXT2_CHECK_MAGIC(channel, EXT2_ET_MAGIC_IO_CHANNEL);
> + data = (struct unix_private_data *) channel->private_data;
> + EXT2_CHECK_MAGIC(data, EXT2_ET_MAGIC_UNIX_IO_CHANNEL);
> +
> + if (getenv("UNIX_IO_NOZEROOUT"))
> + goto unimplemented;
> +
> + if (channel->flags & CHANNEL_FLAGS_BLOCK_DEVICE) {
> +#ifdef BLKZEROOUT
> + __u64 range[2];
> +
> + range[0] = (__u64)(block) * channel->block_size;
> + range[1] = (__u64)(count) * channel->block_size;
> +
> + ret = ioctl(data->dev, BLKZEROOUT, &range);
NAK this line for now. I think I've uncovered a race condition where
pwrite+blkzeroout+pread returns the pwritten contents instead of zeroes as I
was expecting.
--D
> +#else
> + goto unimplemented;
> +#endif
> + } else {
> +#if defined(HAVE_FALLOCATE) && defined(FALLOC_FL_ZERO_RANGE)
> + int flag = FALLOC_FL_ZERO_RANGE;
> + struct stat statbuf;
> +
> + /*
> + * If we're trying to zero a range past the end of the file,
> + * just use regular fallocate to get there, because zeroing
> + * a range past EOF does not extend the file.
> + */
> + ret = fstat(data->dev, &statbuf);
> + if (ret)
> + goto err;
> + if (statbuf.st_size < (block + count) * channel->block_size)
> + flag = 0;
> + /*
> + * If we are not on block device, try to use the zero out
> + * primitive.
> + */
> + ret = fallocate(data->dev,
> + flag,
> + (off_t)(block) * channel->block_size,
> + (off_t)(count) * channel->block_size);
> +#else
> + goto unimplemented;
> +#endif
> + }
> +err:
> + if (ret < 0) {
> + if (errno == EOPNOTSUPP)
> + goto unimplemented;
> + return errno;
> + }
> + return 0;
> +unimplemented:
> + return EXT2_ET_UNIMPLEMENTED;
> +}
> +
> static struct struct_io_manager struct_unix_manager = {
> .magic = EXT2_ET_MAGIC_IO_MANAGER,
> .name = "Unix I/O Manager",
> @@ -1002,6 +1072,7 @@ static struct struct_io_manager struct_unix_manager = {
> .write_blk64 = unix_write_blk64,
> .discard = unix_discard,
> .cache_readahead = unix_cache_readahead,
> + .zeroout = unix_zeroout,
> };
>
> io_manager unix_io_manager = &struct_unix_manager;
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
next prev parent reply other threads:[~2014-10-14 2:58 UTC|newest]
Thread overview: 67+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-09-13 22:11 [PATCH 00/34] e2fsprogs Summer 2014 patchbomb, part 6 Darrick J. Wong
2014-09-13 22:11 ` [PATCH 01/34] e2fsck: offer to clear overlapping extents Darrick J. Wong
2014-09-19 1:45 ` Theodore Ts'o
2014-09-13 22:11 ` [PATCH 02/34] e2fsck: fix sliding the directory block down on bigalloc Darrick J. Wong
2014-09-19 1:45 ` Theodore Ts'o
2014-09-13 22:11 ` [PATCH 03/34] misc: zero s_jnl_blocks when adding journal online or removing external journal Darrick J. Wong
2014-09-19 1:45 ` Theodore Ts'o
2014-09-13 22:11 ` [PATCH 04/34] libext2fs: ext2fs_new_block2() should call alloc_block hook Darrick J. Wong
2014-09-13 22:11 ` [PATCH 05/34] debugfs: manage needs_recover feature when messing with the journal Darrick J. Wong
2014-09-19 6:01 ` Theodore Ts'o
2014-09-13 22:11 ` [PATCH 06/34] debugfs: add LIBINTL to debugfs link command Darrick J. Wong
2014-09-19 4:46 ` Theodore Ts'o
2014-10-17 21:07 ` Darrick J. Wong
2014-10-18 16:10 ` Theodore Ts'o
2014-09-13 22:11 ` [PATCH 07/34] ext2fs: add readahead method to improve scanning Darrick J. Wong
2014-09-19 16:15 ` Theodore Ts'o
2014-09-13 22:12 ` [PATCH 08/34] libext2fs/e2fsck: provide routines to read-ahead metadata Darrick J. Wong
2014-09-13 22:12 ` [PATCH 09/34] e2fsck: read-ahead metadata during passes 1, 2, and 4 Darrick J. Wong
2014-09-13 22:12 ` [PATCH 10/34] dumpe2fs: provide a machine-readable group-only mode Darrick J. Wong
2014-09-19 16:17 ` Theodore Ts'o
2014-09-13 22:12 ` [PATCH 11/34] dumpe2fs: output cleanup Darrick J. Wong
2014-09-19 16:22 ` Theodore Ts'o
2014-09-19 20:00 ` Darrick J. Wong
2014-10-13 18:04 ` Darrick J. Wong
2014-09-13 22:12 ` [PATCH 12/34] misc: move check_plausibility into a separate file Darrick J. Wong
2014-09-19 22:16 ` Theodore Ts'o
2014-09-13 22:12 ` [PATCH 13/34] misc: add plausibility checks to debugfs/tune2fs/dumpe2fs/e2fsck Darrick J. Wong
2014-09-19 23:00 ` Theodore Ts'o
2014-09-13 22:12 ` [PATCH 14/34] misc: use libmagic when libblkid can't identify something Darrick J. Wong
2014-09-21 5:29 ` Theodore Ts'o
2014-09-13 22:12 ` [PATCH 15/34] libext2fs: support BLKZEROOUT/FALLOC_FL_ZERO_RANGE in ext2fs_zero_blocks Darrick J. Wong
2014-09-22 2:51 ` Theodore Ts'o
2014-09-29 18:58 ` Darrick J. Wong
2014-10-14 2:58 ` Darrick J. Wong [this message]
2014-10-18 16:32 ` Theodore Ts'o
2014-10-20 23:37 ` Darrick J. Wong
2014-09-13 22:12 ` [PATCH 16/34] libext2fs/e2fsck: refactor everyone who writes zero blocks to disk Darrick J. Wong
2014-10-13 10:09 ` Theodore Ts'o
2014-10-13 17:09 ` Darrick J. Wong
2014-09-13 22:13 ` [PATCH 17/34] libext2fs: support allocating uninit blocks in bmap2() Darrick J. Wong
2014-10-13 14:35 ` Theodore Ts'o
2014-10-13 16:56 ` Darrick J. Wong
2014-10-13 18:34 ` Darrick J. Wong
2014-09-13 22:13 ` [PATCH 18/34] libext2fs: file IO routines should handle uninit blocks Darrick J. Wong
2014-09-13 22:13 ` [PATCH 19/34] resize2fs: convert fs to and from 64bit mode Darrick J. Wong
2014-09-14 17:34 ` TR Reardon
2014-09-14 17:50 ` Darrick J. Wong
2014-09-13 22:13 ` [PATCH 20/34] resize2fs: adjust reserved_gdt_blocks when changing group descriptor size Darrick J. Wong
2014-09-13 22:13 ` [PATCH 21/34] tests: test resize2fs 32->64 and 64->32bit conversion code Darrick J. Wong
2014-09-13 22:13 ` [PATCH 22/34] libext2fs: find inode goal when allocating blocks Darrick J. Wong
2014-09-13 22:13 ` [PATCH 23/34] libext2fs: find/alloc a range of empty blocks Darrick J. Wong
2014-09-13 22:13 ` [PATCH 24/34] libext2fs: add new hooks to support large allocations Darrick J. Wong
2014-09-13 22:14 ` [PATCH 25/34] libext2fs: implement fallocate Darrick J. Wong
2014-09-13 22:14 ` [PATCH 26/34] libext2fs: use fallocate for creating journals and hugefiles Darrick J. Wong
2014-09-13 22:14 ` [PATCH 27/34] debugfs: implement fallocate Darrick J. Wong
2014-09-13 22:14 ` [PATCH 28/34] tests: test debugfs punch command Darrick J. Wong
2014-09-19 16:26 ` Theodore Ts'o
2014-09-19 20:01 ` Darrick J. Wong
2014-09-13 22:14 ` [PATCH 30/34] fuse2fs: translate ACL structures Darrick J. Wong
2014-09-13 22:14 ` [PATCH 31/34] fuse2fs: handle 64-bit dates correctly Darrick J. Wong
2014-09-13 22:14 ` [PATCH 32/34] fuse2fs: implement fallocate Darrick J. Wong
2014-09-13 22:15 ` [PATCH 34/34] tests: enable using fuse2fs with metadata checksum test Darrick J. Wong
2014-09-14 17:19 ` [PATCH 35/34] e2fsck: free bh when descriptor block checksum fails Darrick J. Wong
2014-09-14 19:11 ` Eric Sandeen
2014-09-19 1:46 ` Theodore Ts'o
2014-09-18 19:09 ` [PATCH 36/34] misc: fix Coverity complaints Darrick J. Wong
2014-09-19 1:47 ` Theodore Ts'o
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20141014025853.GI12009@birch.djwong.org \
--to=darrick.wong@oracle.com \
--cc=linux-ext4@vger.kernel.org \
--cc=tytso@mit.edu \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).