Re: [PATCH 1/6] fsx: add clone range

["Darrick J. Wong" <darrick.wong@oracle.com>]

On Tue, Nov 13, 2018 at 03:39:43PM -0800, Darrick J. Wong wrote:
> From: Darrick J. Wong <darrick.wong@oracle.com>
> 
> Add support for FICLONERANGE to fsx.
> 
> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
> ---
>  ltp/fsx.c |  182 +++++++++++++++++++++++++++++++++++++++++++++++++++++--------
>  1 file changed, 158 insertions(+), 24 deletions(-)
> 
> 
> diff --git a/ltp/fsx.c b/ltp/fsx.c
> index b0157ba3..2b0a2b28 100644
> --- a/ltp/fsx.c
> +++ b/ltp/fsx.c
> @@ -88,25 +88,28 @@ int			logcount = 0;	/* total ops */
>   * mode being run.
>   */
>  
> -/* common operations */
> -#define	OP_READ		0
> -#define OP_WRITE	1
> -#define OP_MAPREAD	2
> -#define OP_MAPWRITE	3
> -#define OP_MAX_LITE	4
> -
> -/* !lite operations */
> -#define OP_TRUNCATE		4
> -#define OP_FALLOCATE		5
> -#define OP_PUNCH_HOLE		6
> -#define OP_ZERO_RANGE		7
> -#define OP_COLLAPSE_RANGE	8
> -#define OP_INSERT_RANGE	9
> -#define OP_MAX_FULL		10
> -
> -/* integrity operations */
> -#define OP_FSYNC		10
> -#define OP_MAX_INTEGRITY	11
> +enum {
> +	/* common operations */
> +	OP_READ = 0,
> +	OP_WRITE,
> +	OP_MAPREAD,
> +	OP_MAPWRITE,
> +	OP_MAX_LITE,
> +
> +	/* !lite operations */
> +	OP_TRUNCATE = OP_MAX_LITE,
> +	OP_FALLOCATE,
> +	OP_PUNCH_HOLE,
> +	OP_ZERO_RANGE,
> +	OP_COLLAPSE_RANGE,
> +	OP_INSERT_RANGE,
> +	OP_CLONE_RANGE,
> +	OP_MAX_FULL,
> +
> +	/* integrity operations */
> +	OP_FSYNC = OP_MAX_FULL,
> +	OP_MAX_INTEGRITY,
> +};
>  
>  #undef PAGE_SIZE
>  #define PAGE_SIZE       getpagesize()
> @@ -160,6 +163,7 @@ int     punch_hole_calls = 1;           /* -H flag disables */
>  int     zero_range_calls = 1;           /* -z flag disables */
>  int	collapse_range_calls = 1;	/* -C flag disables */
>  int	insert_range_calls = 1;		/* -I flag disables */
> +int	remap_calls = 1;		/* -J flag disables */
>  int 	mapped_reads = 1;		/* -R flag disables it */
>  int	integrity = 0;			/* -i flag */
>  int	fsxgoodfd = 0;
> @@ -254,6 +258,7 @@ static const char *op_names[] = {
>  	[OP_ZERO_RANGE] = "zero_range",
>  	[OP_COLLAPSE_RANGE] = "collapse_range",
>  	[OP_INSERT_RANGE] = "insert_range",
> +	[OP_CLONE_RANGE] = "clone_range",
>  	[OP_FSYNC] = "fsync",
>  };
>  
> @@ -275,6 +280,25 @@ static int op_code(const char *name)
>  	return -1;
>  }
>  
> +void
> +log5(int operation, int arg0, int arg1, int arg2, enum opflags flags)
> +{
> +	struct log_entry *le;
> +
> +	le = &oplog[logptr];
> +	le->operation = operation;
> +	if (closeopen)
> +		flags |= FL_CLOSE_OPEN;
> +	le->args[0] = arg0;
> +	le->args[1] = arg1;
> +	le->args[2] = arg2;

I would like to withdraw this patch so that I can add a fourth args[]
slot so that we can maintain the convention of printing the
pre-operation file size after the other operation arguments.  This will
make tracking the location of EOF through an fsxops file easier.

--D

> +	le->flags = flags;
> +	logptr++;
> +	logcount++;
> +	if (logptr >= LOGSIZE)
> +		logptr = 0;
> +}
> +
>  void
>  log4(int operation, int arg0, int arg1, enum opflags flags)
>  {
> @@ -294,7 +318,6 @@ log4(int operation, int arg0, int arg1, enum opflags flags)
>  		logptr = 0;
>  }
>  
> -
>  void
>  logdump(void)
>  {
> @@ -418,6 +441,13 @@ logdump(void)
>  			if (overlap)
>  				prt("\t******IIII");
>  			break;
> +		case OP_CLONE_RANGE:
> +			prt("CLONE 0x%x thru 0x%x\t(0x%x bytes) to 0x%x",
> +			    lp->args[0], lp->args[0] + lp->args[1] - 1,
> +			    lp->args[1], lp->args[2]);
> +			if (overlap)
> +				prt("\t******IIII");
> +			break;
>  		case OP_FSYNC:
>  			prt("FSYNC");
>  			break;
> @@ -1218,6 +1248,73 @@ do_insert_range(unsigned offset, unsigned length)
>  }
>  #endif
>  
> +#ifdef FICLONERANGE
> +void
> +do_clone_range(unsigned offset, unsigned length, unsigned dest)
> +{
> +	struct file_clone_range	fcr;
> +
> +	if (length == 0) {
> +		if (!quiet && testcalls > simulatedopcount)
> +			prt("skipping zero length clone range\n");
> +		log5(OP_CLONE_RANGE, offset, length, dest, FL_SKIPPED);
> +		return;
> +	}
> +
> +	if ((loff_t)offset >= file_size) {
> +		if (!quiet && testcalls > simulatedopcount)
> +			prt("skipping clone range behind EOF\n");
> +		log5(OP_CLONE_RANGE, offset, length, dest, FL_SKIPPED);
> +		return;
> +	}
> +
> +	log5(OP_CLONE_RANGE, offset, length, dest, FL_NONE);
> +
> +	if (testcalls <= simulatedopcount)
> +		return;
> +
> +	if ((progressinterval && testcalls % progressinterval == 0) ||
> +	    (debug && (monitorstart == -1 || monitorend == -1 ||
> +		       dest <= monitorstart || dest + length <= monitorend))) {
> +		prt("%lu clone\tfrom 0x%x to 0x%x, (0x%x bytes) at 0x%x\n",
> +			testcalls, offset, offset+length, length, dest);
> +	}
> +
> +	fcr.src_fd = fd;
> +	fcr.src_offset = offset;
> +	fcr.src_length = length;
> +	fcr.dest_offset = dest;
> +
> +	if (ioctl(fd, FICLONERANGE, &fcr) == -1) {
> +		if (errno == EOPNOTSUPP || errno == ENOTTY) {
> +			if (!quiet && testcalls > simulatedopcount)
> +				prt("skipping unsupported clone range\n");
> +			logptr--;
> +			log5(OP_CLONE_RANGE, offset, length, dest, FL_SKIPPED);
> +			return;
> +		}
> +
> +		prt("clone range: 0x%x to 0x%x at 0x%x\n", offset,
> +				offset + length, dest);
> +		prterr("do_clone_range: FICLONERANGE");
> +		report_failure(161);
> +	}
> +
> +	memcpy(good_buf + dest, good_buf + offset, length);
> +	if (dest > file_size)
> +		memset(good_buf + file_size, '\0', dest - file_size);
> +	if (dest + length > file_size)
> +		file_size = dest + length;
> +}
> +
> +#else
> +void
> +do_clone_range(unsigned offset, unsigned length, unsigned dest)
> +{
> +	return;
> +}
> +#endif
> +
>  #ifdef HAVE_LINUX_FALLOC_H
>  /* fallocate is basically a no-op unless extending, then a lot like a truncate */
>  void
> @@ -1374,6 +1471,7 @@ cleanup(int sig)
>  static int
>  read_op(struct log_entry *log_entry)
>  {
> +	char *end;
>  	char line[256];
>  
>  	memset(log_entry, 0, sizeof(*log_entry));
> @@ -1404,8 +1502,6 @@ read_op(struct log_entry *log_entry)
>  		if (log_entry->operation == -1)
>  			goto fail;
>  		for (i = 0; i < 3; i++) {
> -			char *end;
> -
>  			str = strtok(NULL, " \t\n");
>  			if (!str)
>  				goto fail;
> @@ -1438,7 +1534,7 @@ read_op(struct log_entry *log_entry)
>  int
>  test(void)
>  {
> -	unsigned long	offset;
> +	unsigned long	offset, offset2;
>  	unsigned long	size;
>  	unsigned long	rv;
>  	unsigned long	op;
> @@ -1469,6 +1565,7 @@ test(void)
>  			op = log_entry.operation;
>  			offset = log_entry.args[0];
>  			size = log_entry.args[1];
> +			offset2 = log_entry.args[2];
>  			closeopen = !!(log_entry.flags & FL_CLOSE_OPEN);
>  			keep_size = !!(log_entry.flags & FL_KEEP_SIZE);
>  			goto have_op;
> @@ -1481,6 +1578,7 @@ test(void)
>  		closeopen = (rv >> 3) < (1 << 28) / closeprob;
>  
>  	offset = random();
> +	offset2 = 0;
>  	size = maxoplen;
>  	if (randomoplen)
>  		size = random() % (maxoplen + 1);
> @@ -1506,6 +1604,17 @@ test(void)
>  		if (zero_range_calls && size && keep_size_calls)
>  			keep_size = random() % 2;
>  		break;
> +	case OP_CLONE_RANGE:
> +		TRIM_OFF_LEN(offset, size, file_size);
> +		offset = offset & ~(block_size - 1);
> +		size = size & ~(block_size - 1);
> +		do {
> +			offset2 = random();
> +			TRIM_OFF(offset2, maxfilelen);
> +			offset2 = offset2 & ~(block_size - 1);
> +		} while (llabs(offset2 - offset) < size ||
> +			 offset2 + size > maxfilelen);
> +		break;
>  	}
>  
>  have_op:
> @@ -1549,6 +1658,12 @@ test(void)
>  			goto out;
>  		}
>  		break;
> +	case OP_CLONE_RANGE:
> +		if (!remap_calls) {
> +			log5(op, offset, size, offset2, FL_SKIPPED);
> +			goto out;
> +		}
> +		break;
>  	}
>  
>  	switch (op) {
> @@ -1615,6 +1730,18 @@ test(void)
>  
>  		do_insert_range(offset, size);
>  		break;
> +	case OP_CLONE_RANGE:
> +		if (size == 0) {
> +			log5(OP_CLONE_RANGE, offset, size, offset2, FL_SKIPPED);
> +			goto out;
> +		}
> +		if (offset2 + size > maxfilelen) {
> +			log5(OP_CLONE_RANGE, offset, size, offset2, FL_SKIPPED);
> +			goto out;
> +		}
> +
> +		do_clone_range(offset, size, offset2);
> +		break;
>  	case OP_FSYNC:
>  		dofsync();
>  		break;
> @@ -1637,7 +1764,7 @@ void
>  usage(void)
>  {
>  	fprintf(stdout, "usage: %s",
> -		"fsx [-dknqxAFLOWZ] [-b opnum] [-c Prob] [-g filldata] [-i logdev] [-j logid] [-l flen] [-m start:end] [-o oplen] [-p progressinterval] [-r readbdy] [-s style] [-t truncbdy] [-w writebdy] [-D startingop] [-N numops] [-P dirpath] [-S seed] fname\n\
> +		"fsx [-dknqxAFJLOWZ] [-b opnum] [-c Prob] [-g filldata] [-i logdev] [-j logid] [-l flen] [-m start:end] [-o oplen] [-p progressinterval] [-r readbdy] [-s style] [-t truncbdy] [-w writebdy] [-D startingop] [-N numops] [-P dirpath] [-S seed] fname\n\
>  	-b opnum: beginning operation number (default 1)\n\
>  	-c P: 1 in P chance of file close+open at each op (default infinity)\n\
>  	-d: debug output for all operations\n\
> @@ -1678,6 +1805,10 @@ usage(void)
>  #ifdef FALLOC_FL_INSERT_RANGE
>  "	-I: Do not use insert range calls\n"
>  #endif
> +#if defined(FICLONERANGE) || defined(FIDEDUPERANGE) || \
> +    defined(HAVE_COPY_FILE_RANGE)
> +"	-J: Do not use clone/dedupe/copy range calls\n"
> +#endif
>  "	-L: fsxLite - no file creations & no file size changes\n\
>  	-N numops: total # operations to do (default infinity)\n\
>  	-O: use oplen (see -o flag) for every op (default random)\n\
> @@ -2010,6 +2141,9 @@ main(int argc, char **argv)
>  		case 'I':
>  			insert_range_calls = 0;
>  			break;
> +		case 'J':
> +			remap_calls = 0;
> +			break;
>  		case 'L':
>  		        lite = 1;
>  			o_flags &= ~(O_CREAT|O_TRUNC);
>