apfstests/common/filter

##/bin/bash
#
# Copyright (c) 2000-2001 Silicon Graphics, Inc.  All Rights Reserved.
#
# This program is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License as
# published by the Free Software Foundation.
#
# This program is distributed in the hope that it would be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write the Free Software Foundation,
# Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
#
#
# standard filters
#

# Checks that given_value is in range of correct_value +/- tolerance.
# Tolerance can be an absolute value or a percentage of the correct value
# (see examples with tolerances below).
# Outputs suitable message to stdout if it's not in range.
#
# A verbose option, -v, may be used as the LAST argument
# 
# e.g. 
# foo: 0.0298 = 0.03 +/- 5%
# _within_tolerance "foo" 0.0298 0.03 5%  
# 
# foo: 0.0298 = 0.03 +/- 0.01
# _within_tolerance "foo" 0.0298 0.03 0.01
#
# foo: 0.0298 = 0.03 -0.01 +0.002
# _within_tolerance "foo" 0.0298 0.03 0.01 0.002
#
# foo: verbose output of 0.0298 = 0.03 +/- 5% 
# _within_tolerance "foo" 0.0298 0.03 5% -v 
_within_tolerance()
{
  _name=$1
  _given_val=$2
  _correct_val=$3
  _mintol=$4
  _maxtol=$_mintol
  _verbose=0
  _debug=false

  # maxtol arg is optional
  # verbose arg is optional
  if [ $# -ge 5 ]
  then 
     if [ "$5" = "-v" ]
     then
	_verbose=1
     else
        _maxtol=$5
     fi
  fi
  if [ $# -ge 6 ]
  then
     [ "$6" = "-v" ] && _verbose=1
  fi

  # find min with or without %
  _mintolerance=`echo $_mintol | sed -e 's/%//'` 
  if [ $_mintol = $_mintolerance ]
  then 
      _min=`echo "scale=5; $_correct_val-$_mintolerance" | bc`
  else
      _min=`echo "scale=5; $_correct_val-$_mintolerance*0.01*$_correct_val" | bc`
  fi

  # find max with or without %
  _maxtolerance=`echo $_maxtol | sed -e 's/%//'` 
  if [ $_maxtol = $_maxtolerance ]
  then 
      _max=`echo "scale=5; $_correct_val+$_maxtolerance" | bc`
  else
      _max=`echo "scale=5; $_correct_val+$_maxtolerance*0.01*$_correct_val" | bc`
  fi

  $_debug && echo "min = $_min"
  $_debug && echo "max = $_max"

  cat <<EOF >$tmp.bc.1
scale=5;
if ($_min <= $_given_val) 1;
if ($_min > $_given_val) 0; 
EOF

  cat <<EOF >$tmp.bc.2
scale=5;
if ($_given_val <= $_max) 1;
if ($_given_val > $_max) 0;
EOF

  _above_min=`bc <$tmp.bc.1`
  _below_max=`bc <$tmp.bc.2`

  rm -f $tmp.bc.[12]

  _in_range=`expr $_above_min \& $_below_max` 

  # fix up min, max precision for output
  # can vary for 5.3, 6.2

  # remove any trailing zeroes from min, max if they have fractional parts
  _min=`echo $_min | sed -e '/\./s/0*$//' -e 's/\.$//'`
  _max=`echo $_max | sed -e '/\./s/0*$//' -e 's/\.$//'`

  if [ $_in_range -eq 1 ] 
  then
	[ $_verbose -eq 1 ] && echo $_name is in range
	return 0
  else
	[ $_verbose -eq 1 ] && echo $_name has value of $_given_val
	[ $_verbose -eq 1 ] && echo $_name is NOT in range $_min .. $_max	
	return 1
  fi
}

# ctime(3) dates
#
_filter_date()
{
    sed \
	-e 's/[A-Z][a-z][a-z] [A-z][a-z][a-z]  *[0-9][0-9]* [0-9][0-9]:[0-9][0-9]:[0-9][0-9] [0-9][0-9][0-9][0-9]$/DATE/'
}

# prints filtered output on stdout, values (use eval) on stderr
# Non XFS filesystems always return a 4k block size and a 256 byte inode.
_filter_mkfs()
{
    case $FSTYP in
    xfs)
	;;
    *)
	cat - >/dev/null
	perl -e 'print STDERR "dbsize=4096\nisize=256\n"'
	return ;;
    esac

    echo "_fs_has_crcs=0" >&2
    set -
    perl -ne '
    if (/^meta-data=([\w,|\/.-]+)\s+isize=(\d+)\s+agcount=(\d+), agsize=(\d+) blks/) {
	print STDERR "ddev=$1\nisize=$2\nagcount=$3\nagsize=$4\n";
	print STDOUT "meta-data=DDEV isize=XXX agcount=N, agsize=XXX blks\n";
    }
    if (/^\s+=\s+sectsz=(\d+)\s+attr=(\d+)/) {
        print STDERR "sectsz=$1\nattr=$2\n";
    }
    if (/^\s+=\s+crc=(\d)/) {
        print STDERR "_fs_has_crcs=$1\n";
    }
    if (/^data\s+=\s+bsize=(\d+)\s+blocks=(\d+), imaxpct=(\d+)/) {
	print STDERR "dbsize=$1\ndblocks=$2\nimaxpct=$3\n";
	print STDOUT "data     = bsize=XXX blocks=XXX, imaxpct=PCT\n";
    }
    if (/^\s+=\s+sunit=(\d+)\s+swidth=(\d+) blks/) {
        print STDERR "sunit=$1\nswidth=$2\nunwritten=1\n";
	print STDOUT "         = sunit=XXX swidth=XXX, unwritten=X\n";
    }
    if (/^naming\s+=version\s+(\d+)\s+bsize=(\d+)/) {
	print STDERR "dirversion=$1\ndirbsize=$2\n";
	print STDOUT "naming   =VERN bsize=XXX\n";
    }
    if (/^log\s+=(internal log|[\w|\/.-]+)\s+bsize=(\d+)\s+blocks=(\d+),\s+version=(\d+)/ ||
	/^log\s+=(internal log|[\w|\/.-]+)\s+bsize=(\d+)\s+blocks=(\d+)/) {
	print STDERR "ldev=\"$1\"\nlbsize=$2\nlblocks=$3\nlversion=$4\n";
	print STDOUT "log      =LDEV bsize=XXX blocks=XXX\n";
    }
    if (/^\s+=\s+sectsz=(\d+)\s+sunit=(\d+) blks/) {
	print STDERR "logsectsz=$1\nlogsunit=$2\n\n";
    }
    if (/^realtime\s+=([\w|\/.-]+)\s+extsz=(\d+)\s+blocks=(\d+), rtextents=(\d+)/) {
	print STDERR "rtdev=$1\nrtextsz=$2\nrtblocks=$3\nrtextents=$4\n";
	print STDOUT "realtime =RDEV extsz=XXX blocks=XXX, rtextents=XXX\n";
    }'
}


# prints the bits we care about in growfs
# 
_filter_growfs()
{
    perl -ne '
    if (/^data\s+=\s+bsize=(\d+)\s+blocks=(\d+), imaxpct=(\d+)/) {
        print "xfs_growfs --BlockSize=$1 --Blocks=$2\n";
    }
    elsif (/^data/) {
        print;
    }'
}

_filter_dd()
{
    $AWK_PROG '
        /records in/                { next }
        /records out/               { next }
        /No space left on device/   { print "   !!! disk full (expected)" 
                                      next }
                                    { print "   *** " $0 }
    '
}

common_line_filter()
{
    perl -ne 'if (/.*:(.*)/) {
        if ( "$last_line" ne "$1" ) { print "$_"; $first_match=1; }
        elsif ( $first_match==1 ) { print "*\n"; $first_match=0; }
        $last_line="$1";
    }
    else {
        print $_; $last_line=$_;
    }'
}

_filter_xfs_io()
{
    sed -e "s/[0-9/.]* [GMKiBbytes]*, [0-9]* ops\; [0-9/:. sec]* ([inf0-9/.]* [EPGMKiBbytes]*\/sec and [inf0-9/.]* ops\/sec)/XXX Bytes, X ops\; XX:XX:XX.X (XXX YYY\/sec and XXX ops\/sec)/"
}

_filter_xfs_io_unique()
{
    common_line_filter | _filter_xfs_io
}

_filter_xfs_io_units_modified()
{
	UNIT=$1
	UNIT_SIZE=$2

	$AWK_PROG -v unit="$UNIT" -v unit_size=$UNIT_SIZE '
		/wrote/ {
			split($2, bytes, "/")

			bytes_written = strtonum(bytes[1])

			offset = strtonum($NF)

			unit_start = offset / unit_size
			unit_start = int(unit_start)
			unit_end = (offset + bytes_written - 1) / unit_size
			unit_end = int(unit_end)

			printf("%ss modified: [%d - %d]\n", unit, unit_start, unit_end)

			next
		}
	'
}

_filter_xfs_io_blocks_modified()
{
	BLOCK_SIZE=$(get_block_size $SCRATCH_MNT)

	_filter_xfs_io_units_modified "Block" $BLOCK_SIZE
}

_filter_xfs_io_pages_modified()
{
	PAGE_SIZE=$(get_page_size)

	_filter_xfs_io_units_modified "Page" $PAGE_SIZE
}


_filter_test_dir()
{
	sed -e "s,$TEST_DEV,TEST_DEV,g" -e "s,$TEST_DIR,TEST_DIR,g"
}

_filter_scratch()
{
	sed -e "s,$SCRATCH_DEV,SCRATCH_DEV,g" \
	    -e "s,$SCRATCH_MNT,SCRATCH_MNT,g" \
	    -e "/.use_space/d"
}

# Turn any device in the scratch pool into SCRATCH_DEV
_filter_scratch_pool()
{
	FILTER_STRINGS=`echo $SCRATCH_DEV_POOL | sed -e 's/\s\+/\\\|/g'`
	sed -e "s,$FILTER_STRINGS,SCRATCH_DEV,g"
}

_filter_spaces()
{
       sed -e 's/ [ ]*/ /g'
}

_filter_quota()
{
	# Long dev name might be split onto its own line; last
	# seds remove that newline if present
	_filter_scratch | _filter_test_dir | _filter_spaces | \
	sed -e 'N;s/SCRATCH_DEV\n/SCRATCH_DEV/g' | \
	sed -e 'N;s/TEST_DEV\n/TEST_DEV/g'
}

_filter_project_quota()
{
	# Project ID 0 is always present on disk but was not reported
	# until the GETNEXTQUOTA ioctl came into use.  Filter it out.
	# But if you specify a name for ID 0, that means you want to
	# deal with it by yourself, this function won't filter it out.
	_filter_quota | grep -v "^\#0 \|^(null) "
}

# Account for different "ln" failure messages
_filter_ln()
{
	sed -e "s,\(creating symbolic link .*\) to .*: ,\1: ," \
	    -e "s,failed to create,creating,"
}

# If given an arg, filter *that* UUID string
# Otherwise look for something that looks like a generic UUID
_filter_uuid()
{
	if [ ! -z $1 ]; then
		UUID=$1
		sed -e "s/\(uuid[ :=]\+\) $UUID/\1 <EXACTUUID>/i"
	else
		sed -e "s/\(uuid[ :=]\+\) [0-9a-f-][0-9a-f-]*/\1 <UUID>/ig"
	fi
}

# In mixed group the added disks may have zero used size
_filter_zero_size()
{
	sed -e "s/0\.00/<SIZE>/g"
}

# Filter out sizes like 6.14MB etc
_filter_size()
{
	sed -e "s/[0-9\.]\+\s\?[b|k|m|g|t][i]\?[b]\?/<SIZE>/ig"
}

# Convert string read from stdin like 128K to bytes and print it to stdout
_filter_size_to_bytes()
{
	read size
	suffix=${size:${#size}-1}
	mul=1
	case $suffix in
		k|K) mul=1024 ;;
		m|M) mul=$((1024*1024)) ;;
		g|G) mul=$((1024*1024*1024)) ;;
		t|T) mul=$((1024*1024*1024*1024)) ;;
	esac
	echo $((${size:0:${#size}-1}*$mul))
}

# Print trimmed bytes of fstrim
# Starting from util-linux v2.23 fstrim usees human readable sizes in
# verbose output
_filter_fstrim()
{
	egrep -o "[0-9]+ bytes" | $AWK_PROG '{print $1}'
}

# Older mount output referred to "block device" when mounting RO devices
# It's gone in newer versions
_filter_ro_mount() {
	sed -e "s/mount: block device/mount:/g" \
	    -e "s/mount: cannot mount block device/mount: cannot mount/g"
}

_filter_od()
{
	BLOCK_SIZE=$(get_block_size $SCRATCH_MNT)
	$AWK_PROG -v block_size=$BLOCK_SIZE '
		/^[0-9]+/ {
			offset = strtonum("0"$1);
			$1 = sprintf("%o", offset / block_size);
			print $0;
		}
		/\*/
	'
}

# make sure this script returns success
/bin/true