Many programs open code these functionalities so add it as a generic helper in common/rc Reviewed-by: Darrick J. Wong Reviewed-by: John Garry Signed-off-by: Ojaswin Mujoo --- common/rc | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/common/rc b/common/rc index 81587dad..28fbbcbb 100644 --- a/common/rc +++ b/common/rc @@ -5978,6 +5978,28 @@ _require_inplace_writes() fi } +_min() { + local ret + + for arg in "$@"; do + if [ -z "$ret" ] || (( $arg < $ret )); then + ret="$arg" + fi + done + echo $ret +} + +_max() { + local ret + + for arg in "$@"; do + if [ -z "$ret" ] || (( $arg > $ret )); then + ret="$arg" + fi + done + echo $ret +} + ################################################################################ # make sure this script returns success /bin/true -- 2.49.0 The main motivation of adding this function on top of _require_fio is that there has been a case in fio where atomic= option was added but later it was changed to noop since kernel didn't yet have support for atomic writes. It was then again utilized to do atomic writes in a later version, once kernel got the support. Due to this there is a point in fio where _require_fio w/ atomic=1 will succeed even though it would not be doing atomic writes. Hence, add an internal helper __require_fio_version to require specific versions of fio to work past such issues. Further, add the high level _require_fio_atomic_writes helper which tests can use to ensure fio has the right version for atomic writes. Reviewed-by: Zorro Lang Reviewed-by: John Garry Signed-off-by: Ojaswin Mujoo --- common/rc | 43 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) diff --git a/common/rc b/common/rc index 28fbbcbb..8a023b9d 100644 --- a/common/rc +++ b/common/rc @@ -6000,6 +6000,49 @@ _max() { echo $ret } +# Due to reasons explained in fio commit 40f1fc11d, fio version between +# v3.33 and v3.38 have atomic= feature but it is a no-op and doesn't do +# RWF_ATOMIC write. Hence, use this helper to ensure fio has the +# required support. Currently, the simplest way we have is to ensure +# the version. +_require_fio_atomic_writes() { + __require_fio_version "3.38+" +} + +# Check the required fio version. Examples: +# __require_fio_version 3.38 (matches 3.38 only) +# __require_fio_version 3.38+ (matches 3.38 and above) +# __require_fio_version 3.38- (matches 3.38 and below) +# +# Internal helper, avoid using directly in tests. +__require_fio_version() { + local req_ver="$1" + local fio_ver + + _require_fio + _require_math + + fio_ver=$(fio -v | cut -d"-" -f2) + + case "$req_ver" in + *+) + req_ver=${req_ver%+} + test $(_math "$fio_ver >= $req_ver") -eq 1 || \ + _notrun "need fio >= $req_ver (found $fio_ver)" + ;; + *-) + req_ver=${req_ver%-} + test $(_math "$fio_ver <= $req_ver") -eq 1 || \ + _notrun "need fio <= $req_ver (found $fio_ver)" + ;; + *) + req_ver=${req_ver%-} + test $(_math "$fio_ver == $req_ver") -eq 1 || \ + _notrun "need fio = $req_ver (found $fio_ver)" + ;; + esac +} + ################################################################################ # make sure this script returns success /bin/true -- 2.49.0 Currently run_fsx is hardcoded to run on a file in $TEST_DIR. Add a helper _run_fsx_on_file so that we can run fsx on any given file including in $SCRATCH_MNT. Also, refactor _run_fsx to use this helper. No functional change is intended in this patch. Reviewed-by: Darrick J. Wong Reviewed-by: John Garry Signed-off-by: Ojaswin Mujoo --- common/rc | 23 ++++++++++++++++++++--- 1 file changed, 20 insertions(+), 3 deletions(-) diff --git a/common/rc b/common/rc index 8a023b9d..ac77a650 100644 --- a/common/rc +++ b/common/rc @@ -5203,13 +5203,24 @@ _require_hugepage_fsx() _notrun "fsx binary does not support MADV_COLLAPSE" } -_run_fsx() +_run_fsx_on_file() { + local testfile=$1 + shift + + if ! [ -f $testfile ] + then + echo "_run_fsx_on_file: $testfile doesn't exist. Creating" >> $seqres.full + touch $testfile + fi + echo "fsx $*" local args=`echo $@ | sed -e "s/ BSIZE / $bsize /g" -e "s/ PSIZE / $psize /g"` - set -- $FSX_PROG $args $FSX_AVOID $TEST_DIR/junk + + set -- $FSX_PROG $args $FSX_AVOID $testfile + echo "$@" >>$seqres.full - rm -f $TEST_DIR/junk + rm -f $testfile "$@" 2>&1 | tee -a $seqres.full >$tmp.fsx local res=${PIPESTATUS[0]} if [ $res -ne 0 ]; then @@ -5221,6 +5232,12 @@ _run_fsx() return 0 } +_run_fsx() +{ + _run_fsx_on_file $TEST_DIR/junk $@ + return $? +} + # Run fsx with -h(ugepage buffers). If we can't set up a hugepage then skip # the test, but if any other error occurs then exit the test. _run_hugepage_fsx() { -- 2.49.0 Implement atomic write support to help fuzz atomic writes with fsx. Suggested-by: Ritesh Harjani (IBM) Reviewed-by: Darrick J. Wong Reviewed-by: John Garry Signed-off-by: Ojaswin Mujoo --- ltp/fsx.c | 115 +++++++++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 110 insertions(+), 5 deletions(-) diff --git a/ltp/fsx.c b/ltp/fsx.c index 163b9453..bdb87ca9 100644 --- a/ltp/fsx.c +++ b/ltp/fsx.c @@ -40,6 +40,7 @@ #include #endif #include +#include "statx.h" #ifndef MAP_FILE # define MAP_FILE 0 @@ -49,6 +50,10 @@ #define RWF_DONTCACHE 0x80 #endif +#ifndef RWF_ATOMIC +#define RWF_ATOMIC 0x40 +#endif + #define NUMPRINTCOLUMNS 32 /* # columns of data to print on each line */ /* Operation flags (bitmask) */ @@ -110,6 +115,7 @@ enum { OP_READ_DONTCACHE, OP_WRITE, OP_WRITE_DONTCACHE, + OP_WRITE_ATOMIC, OP_MAPREAD, OP_MAPWRITE, OP_MAX_LITE, @@ -200,6 +206,11 @@ int uring = 0; int mark_nr = 0; int dontcache_io = 1; int hugepages = 0; /* -h flag */ +int do_atomic_writes = 1; /* -a flag disables */ + +/* User for atomic writes */ +int awu_min = 0; +int awu_max = 0; /* Stores info needed to periodically collapse hugepages */ struct hugepages_collapse_info { @@ -288,6 +299,7 @@ static const char *op_names[] = { [OP_READ_DONTCACHE] = "read_dontcache", [OP_WRITE] = "write", [OP_WRITE_DONTCACHE] = "write_dontcache", + [OP_WRITE_ATOMIC] = "write_atomic", [OP_MAPREAD] = "mapread", [OP_MAPWRITE] = "mapwrite", [OP_TRUNCATE] = "truncate", @@ -422,6 +434,7 @@ logdump(void) prt("\t***RRRR***"); break; case OP_WRITE_DONTCACHE: + case OP_WRITE_ATOMIC: case OP_WRITE: prt("WRITE 0x%x thru 0x%x\t(0x%x bytes)", lp->args[0], lp->args[0] + lp->args[1] - 1, @@ -1073,6 +1086,25 @@ update_file_size(unsigned offset, unsigned size) file_size = offset + size; } +static int is_power_of_2(unsigned n) { + return ((n & (n - 1)) == 0); +} + +/* + * Round down n to nearest power of 2. + * If n is already a power of 2, return n; + */ +static int rounddown_pow_of_2(int n) { + int i = 0; + + if (is_power_of_2(n)) + return n; + + for (; (1 << i) < n; i++); + + return 1 << (i - 1); +} + void dowrite(unsigned offset, unsigned size, int flags) { @@ -1081,6 +1113,27 @@ dowrite(unsigned offset, unsigned size, int flags) offset -= offset % writebdy; if (o_direct) size -= size % writebdy; + if (flags & RWF_ATOMIC) { + /* atomic write len must be between awu_min and awu_max */ + if (size < awu_min) + size = awu_min; + if (size > awu_max) + size = awu_max; + + /* atomic writes need power-of-2 sizes */ + size = rounddown_pow_of_2(size); + + /* atomic writes need naturally aligned offsets */ + offset -= offset % size; + + /* Skip the write if we are crossing max filesize */ + if ((offset + size) > maxfilelen) { + if (!quiet && testcalls > simulatedopcount) + prt("skipping atomic write past maxfilelen\n"); + log4(OP_WRITE_ATOMIC, offset, size, FL_SKIPPED); + return; + } + } if (size == 0) { if (!quiet && testcalls > simulatedopcount && !o_direct) prt("skipping zero size write\n"); @@ -1088,7 +1141,10 @@ dowrite(unsigned offset, unsigned size, int flags) return; } - log4(OP_WRITE, offset, size, FL_NONE); + if (flags & RWF_ATOMIC) + log4(OP_WRITE_ATOMIC, offset, size, FL_NONE); + else + log4(OP_WRITE, offset, size, FL_NONE); gendata(original_buf, good_buf, offset, size); if (offset + size > file_size) { @@ -1108,8 +1164,9 @@ dowrite(unsigned offset, unsigned size, int flags) (monitorstart == -1 || (offset + size > monitorstart && (monitorend == -1 || offset <= monitorend)))))) - prt("%lld write\t0x%x thru\t0x%x\t(0x%x bytes)\tdontcache=%d\n", testcalls, - offset, offset + size - 1, size, (flags & RWF_DONTCACHE) != 0); + prt("%lld write\t0x%x thru\t0x%x\t(0x%x bytes)\tdontcache=%d atomic_wr=%d\n", testcalls, + offset, offset + size - 1, size, (flags & RWF_DONTCACHE) != 0, + (flags & RWF_ATOMIC) != 0); iret = fsxwrite(fd, good_buf + offset, size, offset, flags); if (iret != size) { if (iret == -1) @@ -1785,6 +1842,36 @@ do_dedupe_range(unsigned offset, unsigned length, unsigned dest) } #endif +int test_atomic_writes(void) { + int ret; + struct statx stx; + + if (o_direct != O_DIRECT) { + fprintf(stderr, "main: atomic writes need O_DIRECT (-Z), " + "disabling!\n"); + return 0; + } + + ret = xfstests_statx(AT_FDCWD, fname, 0, STATX_WRITE_ATOMIC, &stx); + if (ret < 0) { + fprintf(stderr, "main: Statx failed with %d." + " Failed to determine atomic write limits, " + " disabling!\n", ret); + return 0; + } + + if (stx.stx_attributes & STATX_ATTR_WRITE_ATOMIC && + stx.stx_atomic_write_unit_min > 0) { + awu_min = stx.stx_atomic_write_unit_min; + awu_max = stx.stx_atomic_write_unit_max; + return 1; + } + + fprintf(stderr, "main: IO Stack does not support " + "atomic writes, disabling!\n"); + return 0; +} + #ifdef HAVE_COPY_FILE_RANGE int test_copy_range(void) @@ -2356,6 +2443,12 @@ have_op: goto out; } break; + case OP_WRITE_ATOMIC: + if (!do_atomic_writes) { + log4(OP_WRITE_ATOMIC, offset, size, FL_SKIPPED); + goto out; + } + break; } switch (op) { @@ -2385,6 +2478,11 @@ have_op: dowrite(offset, size, 0); break; + case OP_WRITE_ATOMIC: + TRIM_OFF_LEN(offset, size, maxfilelen); + dowrite(offset, size, RWF_ATOMIC); + break; + case OP_MAPREAD: TRIM_OFF_LEN(offset, size, file_size); domapread(offset, size); @@ -2511,13 +2609,14 @@ void usage(void) { fprintf(stdout, "usage: %s", - "fsx [-dfhknqxyzBEFHIJKLORWXZ0]\n\ + "fsx [-adfhknqxyzBEFHIJKLORWXZ0]\n\ [-b opnum] [-c Prob] [-g filldata] [-i logdev] [-j logid]\n\ [-l flen] [-m start:end] [-o oplen] [-p progressinterval]\n\ [-r readbdy] [-s style] [-t truncbdy] [-w writebdy]\n\ [-A|-U] [-D startingop] [-N numops] [-P dirpath] [-S seed]\n\ [--replay-ops=opsfile] [--record-ops[=opsfile]] [--duration=seconds]\n\ ... fname\n\ + -a: disable atomic writes\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\ @@ -3059,9 +3158,13 @@ main(int argc, char **argv) setvbuf(stdout, (char *)0, _IOLBF, 0); /* line buffered stdout */ while ((ch = getopt_long(argc, argv, - "0b:c:de:fg:hi:j:kl:m:no:p:qr:s:t:uw:xyABD:EFJKHzCILN:OP:RS:UWXZ", + "0ab:c:de:fg:hi:j:kl:m:no:p:qr:s:t:uw:xyABD:EFJKHzCILN:OP:RS:UWXZ", longopts, NULL)) != EOF) switch (ch) { + case 'a': + prt("main(): Atomic writes disabled\n"); + do_atomic_writes = 0; + break; case 'b': simulatedopcount = getnum(optarg, &endp); if (!quiet) @@ -3475,6 +3578,8 @@ main(int argc, char **argv) exchange_range_calls = test_exchange_range(); if (dontcache_io) dontcache_io = test_dontcache_io(); + if (do_atomic_writes) + do_atomic_writes = test_atomic_writes(); while (keep_running()) if (!test()) -- 2.49.0 This adds atomic write test using fio based on it's crc check verifier. fio adds a crc header for each data block, which is verified later to ensure there is no data corruption or torn write. This test essentially does a lot of parallel RWF_ATOMIC IO on a preallocated file to stress the write and end-io unwritten conversion code paths. The idea is to increase code coverage to ensure RWF_ATOMIC hasn't introduced any issues. Avoid doing overlapping parallel atomic writes because it might give unexpected results. Use offset_increment=, size= fio options to achieve this behavior. Co-developed-by: Ritesh Harjani (IBM) Signed-off-by: Ritesh Harjani (IBM) Reviewed-by: Darrick J. Wong Reviewed-by: John Garry Signed-off-by: Ojaswin Mujoo --- tests/generic/1226 | 108 +++++++++++++++++++++++++++++++++++++++++ tests/generic/1226.out | 2 + 2 files changed, 110 insertions(+) create mode 100755 tests/generic/1226 create mode 100644 tests/generic/1226.out diff --git a/tests/generic/1226 b/tests/generic/1226 new file mode 100755 index 00000000..7ad74554 --- /dev/null +++ b/tests/generic/1226 @@ -0,0 +1,108 @@ +#! /bin/bash +# SPDX-License-Identifier: GPL-2.0 +# Copyright (c) 2025 IBM Corporation. All Rights Reserved. +# +# FS QA Test 1226 +# +# Validate FS atomic write using fio crc check verifier. +# +. ./common/preamble +. ./common/atomicwrites + +_begin_fstest auto aio rw atomicwrites + +_require_scratch_write_atomic +_require_odirect +_require_aio +_require_fio_atomic_writes + +_scratch_mkfs >> $seqres.full 2>&1 +_scratch_mount +_require_xfs_io_command "falloc" + +touch "$SCRATCH_MNT/f1" +awu_min_write=$(_get_atomic_write_unit_min "$SCRATCH_MNT/f1") +awu_max_write=$(_get_atomic_write_unit_max "$SCRATCH_MNT/f1") + +blocksize=$(_max "$awu_min_write" "$((awu_max_write/2))") +threads=$(_min "$(($(nproc) * 2 * LOAD_FACTOR))" "100") +filesize=$((blocksize * threads * 100)) +depth=$threads +io_size=$((filesize / threads)) +io_inc=$io_size +testfile=$SCRATCH_MNT/test-file + +fio_config=$tmp.fio +fio_out=$tmp.fio.out + +fio_aw_config=$tmp.aw.fio +fio_verify_config=$tmp.verify.fio + +function create_fio_configs() +{ + create_fio_aw_config + create_fio_verify_config +} + +function create_fio_verify_config() +{ +cat >$fio_verify_config <$fio_aw_config <> $seqres.full +cat $fio_verify_config >> $seqres.full + +$XFS_IO_PROG -fc "falloc 0 $filesize" $testfile >> $seqres.full + +$FIO_PROG $fio_aw_config >> $seqres.full +ret1=$? +$FIO_PROG $fio_verify_config >> $seqres.full +ret2=$? + +[[ $ret1 -eq 0 && $ret2 -eq 0 ]] || _fail "fio with atomic write failed" + +# success, all done +echo Silence is golden +status=0 +exit diff --git a/tests/generic/1226.out b/tests/generic/1226.out new file mode 100644 index 00000000..6dce0ea5 --- /dev/null +++ b/tests/generic/1226.out @@ -0,0 +1,2 @@ +QA output created by 1226 +Silence is golden -- 2.49.0 This test uses fio to first create a file with mixed mappings. Then it does atomic writes using aio dio with parallel jobs to the same file with mixed mappings. Finally, we perform a fio verify step to ensure there is no data corruption or torn write. The aim is to stress the FS block allocation and extent handling logic to ensure it handles mixed mappings with RWF_ATOMIC correctly without tearing or losing data. Avoid doing overlapping parallel atomic writes because it might give unexpected results. Use offset_increment=, size= fio options to achieve this behavior. Co-developed-by: Ritesh Harjani (IBM) Signed-off-by: Ritesh Harjani (IBM) Reviewed-by: Darrick J. Wong Reviewed-by: John Garry Signed-off-by: Ojaswin Mujoo --- tests/generic/1227 | 132 +++++++++++++++++++++++++++++++++++++++++ tests/generic/1227.out | 2 + 2 files changed, 134 insertions(+) create mode 100755 tests/generic/1227 create mode 100644 tests/generic/1227.out diff --git a/tests/generic/1227 b/tests/generic/1227 new file mode 100755 index 00000000..26177508 --- /dev/null +++ b/tests/generic/1227 @@ -0,0 +1,132 @@ +#! /bin/bash +# SPDX-License-Identifier: GPL-2.0 +# Copyright (c) 2025 IBM Corporation. All Rights Reserved. +# +# FS QA Test 1227 +# +# Validate FS atomic write using fio crc check verifier on mixed mappings +# of a file. +# +. ./common/preamble +. ./common/atomicwrites + +_begin_fstest auto aio rw atomicwrites + +_require_scratch_write_atomic_multi_fsblock +_require_odirect +_require_aio +_require_fio_atomic_writes +_require_xfs_io_command "truncate" + +_scratch_mkfs >> $seqres.full 2>&1 +_scratch_mount + +touch "$SCRATCH_MNT/f1" +awu_min_write=$(_get_atomic_write_unit_min "$SCRATCH_MNT/f1") +awu_max_write=$(_get_atomic_write_unit_max "$SCRATCH_MNT/f1") + +aw_bsize=$(_max "$awu_min_write" "$((awu_max_write/4))") +fsbsize=$(_get_block_size $SCRATCH_MNT) + +threads=$(_min "$(($(nproc) * 2 * LOAD_FACTOR))" "100") +filesize=$((aw_bsize * threads * 100)) +depth=$threads +aw_io_size=$((filesize / threads)) +aw_io_inc=$aw_io_size +testfile=$SCRATCH_MNT/test-file + +fio_prep_config=$tmp.prep.fio +fio_aw_config=$tmp.aw.fio +fio_verify_config=$tmp.verify.fio +fio_out=$tmp.fio.out + +cat >$fio_prep_config <$fio_aw_config <$fio_verify_config <> $seqres.full +cat $fio_aw_config >> $seqres.full +cat $fio_verify_config >> $seqres.full + +$XFS_IO_PROG -fc "truncate $filesize" $testfile >> $seqres.full + +#prepare file with mixed mappings +$FIO_PROG $fio_prep_config >> $seqres.full + +# do atomic writes without verifying +$FIO_PROG $fio_aw_config >> $seqres.full + +# verify data is not torn +$FIO_PROG $fio_verify_config >> $seqres.full + +# success, all done +echo Silence is golden +status=0 +exit diff --git a/tests/generic/1227.out b/tests/generic/1227.out new file mode 100644 index 00000000..2605d062 --- /dev/null +++ b/tests/generic/1227.out @@ -0,0 +1,2 @@ +QA output created by 1227 +Silence is golden -- 2.49.0 This adds various atomic write multi-fsblock stress tests with mixed mappings and O_SYNC, to ensure the data and metadata is atomically persisted even if there is a shutdown. Suggested-by: Ritesh Harjani (IBM) Reviewed-by: Darrick J. Wong Reviewed-by: John Garry Signed-off-by: Ojaswin Mujoo --- tests/generic/1228 | 138 +++++++++++++++++++++++++++++++++++++++++ tests/generic/1228.out | 2 + 2 files changed, 140 insertions(+) create mode 100755 tests/generic/1228 create mode 100644 tests/generic/1228.out diff --git a/tests/generic/1228 b/tests/generic/1228 new file mode 100755 index 00000000..730bf91e --- /dev/null +++ b/tests/generic/1228 @@ -0,0 +1,138 @@ +#! /bin/bash +# SPDX-License-Identifier: GPL-2.0 +# Copyright (c) 2025 IBM Corporation. All Rights Reserved. +# +# FS QA Test 1228 +# +# Atomic write multi-fsblock data integrity tests with mixed mappings +# and O_SYNC +# +. ./common/preamble +. ./common/atomicwrites +_begin_fstest auto quick rw atomicwrites + +_require_scratch_write_atomic_multi_fsblock +_require_atomic_write_test_commands +_require_scratch_shutdown +_require_xfs_io_command "truncate" + +_scratch_mkfs >> $seqres.full +_scratch_mount >> $seqres.full + +check_data_integrity() { + actual=$(_hexdump $testfile) + if [[ "$expected" != "$actual" ]] + then + echo "Integrity check failed" + echo "Integrity check failed" >> $seqres.full + echo "# Expected file contents:" >> $seqres.full + echo "$expected" >> $seqres.full + echo "# Actual file contents:" >> $seqres.full + echo "$actual" >> $seqres.full + + _fail "Data integrity check failed. The atomic write was torn." + fi +} + +prep_mixed_mapping() { + $XFS_IO_PROG -c "truncate 0" $testfile >> $seqres.full + local off=0 + local mapping="" + + local operations=("W" "H" "U") + local num_blocks=$((awu_max / blksz)) + for ((i=0; i /dev/null + ;; + "H") + # No operation needed for hole + ;; + "U") + $XFS_IO_PROG -c "falloc $off $blksz" $testfile >> /dev/null + ;; + esac + off=$((off + blksz)) + done + + echo "+ + Mixed mapping prep done. Full mapping pattern: $mapping" >> $seqres.full + + sync $testfile +} + +verify_atomic_write() { + test $bytes_written -eq $awu_max || _fail "atomic write len=$awu_max assertion failed" + check_data_integrity +} + +mixed_mapping_test() { + prep_mixed_mapping + + echo -"+ + Performing O_DSYNC atomic write from 0 to $awu_max" >> $seqres.full + if [[ "$1" == "shutdown" ]] + then + bytes_written=$($XFS_IO_PROG -x -dc \ + "pwrite -DA -V1 -b $awu_max 0 $awu_max" \ + -c "shutdown" $testfile | grep wrote | \ + awk -F'[/ ]' '{print $2}') + _scratch_cycle_mount >>$seqres.full 2>&1 || _fail "remount failed" + else + bytes_written=$($XFS_IO_PROG -dc \ + "pwrite -DA -V1 -b $awu_max 0 $awu_max" $testfile | \ + grep wrote | awk -F'[/ ]' '{print $2}') + fi + + verify_atomic_write +} + +testfile=$SCRATCH_MNT/testfile +touch $testfile + +awu_max=$(_get_atomic_write_unit_max $testfile) +blksz=$(_get_block_size $SCRATCH_MNT) + +# Create an expected pattern to compare with +$XFS_IO_PROG -tc "pwrite -b $awu_max 0 $awu_max" $testfile >> $seqres.full +expected=$(_hexdump $testfile) +echo "# Expected file contents:" >> $seqres.full +echo "$expected" >> $seqres.full +echo >> $seqres.full + +echo "# Test 1: Do O_DSYNC atomic write on random mixed mapping:" >> $seqres.full +echo >> $seqres.full + +iterations=10 +for ((i=1; i<=$iterations; i++)); do + echo "=== Mixed Mapping Test Iteration $i ===" >> $seqres.full + + echo "+ Testing without shutdown..." >> $seqres.full + mixed_mapping_test + echo "Passed!" >> $seqres.full + + echo "+ Testing with sudden shutdown..." >> $seqres.full + mixed_mapping_test "shutdown" + echo "Passed!" >> $seqres.full + + echo "Iteration $i completed: OK" >> $seqres.full + echo >> $seqres.full +done +echo "# Test 1: Do O_SYNC atomic write on random mixed mapping ($iterations iterations): OK" >> $seqres.full + + +echo >> $seqres.full +echo "# Test 2: Do extending O_SYNC atomic writes: " >> $seqres.full +bytes_written=$($XFS_IO_PROG -x -dstc "pwrite -A -V1 -b $awu_max 0 $awu_max" \ + -c "shutdown" $testfile | grep wrote | awk -F'[/ ]' '{print $2}') +_scratch_cycle_mount >>$seqres.full 2>&1 || _fail "remount failed" +verify_atomic_write +echo "# Test 2: Do extending O_SYNC atomic writes: OK" >> $seqres.full + +# success, all done +echo "Silence is golden" +status=0 +exit diff --git a/tests/generic/1228.out b/tests/generic/1228.out new file mode 100644 index 00000000..1baffa91 --- /dev/null +++ b/tests/generic/1228.out @@ -0,0 +1,2 @@ +QA output created by 1228 +Silence is golden -- 2.49.0 Stress file with atomic writes to ensure we exercise codepaths where we are mixing different FS operations with atomic writes Suggested-by: Ritesh Harjani (IBM) Reviewed-by: Darrick J. Wong Reviewed-by: John Garry Signed-off-by: Ojaswin Mujoo --- tests/generic/1229 | 68 ++++++++++++++++++++++++++++++++++++++++++ tests/generic/1229.out | 2 ++ 2 files changed, 70 insertions(+) create mode 100755 tests/generic/1229 create mode 100644 tests/generic/1229.out diff --git a/tests/generic/1229 b/tests/generic/1229 new file mode 100755 index 00000000..6d4dcfed --- /dev/null +++ b/tests/generic/1229 @@ -0,0 +1,68 @@ +#! /bin/bash +# SPDX-License-Identifier: GPL-2.0 +# Copyright (c) 2025 IBM Corporation. All Rights Reserved. +# +# FS QA Test 1229 +# +# fuzz fsx with atomic writes +# +. ./common/preamble +. ./common/atomicwrites +_begin_fstest rw auto quick atomicwrites + +_require_odirect +_require_scratch_write_atomic + +_scratch_mkfs >> $seqres.full 2>&1 +_scratch_mount >> $seqres.full 2>&1 + +testfile=$SCRATCH_MNT/testfile +touch $testfile + +awu_max=$(_get_atomic_write_unit_max $testfile) +blksz=$(_get_block_size $SCRATCH_MNT) +bsize=`$here/src/min_dio_alignment $SCRATCH_MNT $SCRATCH_DEV` + +set_fsx_avoid() { + local file=$1 + + case "$FSTYP" in + "ext4") + local dev=$(findmnt -n -o SOURCE --target $testfile) + + # fsx insert/collapse range support for ext4+bigalloc is + # currently broken, so disable it. Also disable in case we + # can't detect bigalloc to be on safer side. + if [ -z "$DUMPE2FS_PROG" ]; then + echo "dumpe2fs not found, disabling insert/collapse range" >> $seqres.full + FSX_AVOID+=" -I -C" + return + fi + + $DUMPE2FS_PROG -h $dev 2>&1 | grep -q bigalloc && { + echo "fsx insert/collapse range not supported with bigalloc. Disabling.." >> $seqres.full + FSX_AVOID+=" -I -C" + } + ;; + *) + ;; + esac +} + +# fsx usage: +# +# -N numops: total # operations to do +# -l flen: the upper bound on file size +# -o oplen: the upper bound on operation size (64k default) +# -Z: O_DIRECT () + +set_fsx_avoid +_run_fsx_on_file $testfile -N 10000 -o $awu_max -A -l 500000 -r $bsize -w $bsize -Z $FSX_AVOID >> $seqres.full +if [[ "$?" != "0" ]] +then + _fail "fsx returned error: $?" +fi + +echo "Silence is golden" +status=0 +exit diff --git a/tests/generic/1229.out b/tests/generic/1229.out new file mode 100644 index 00000000..737d61c6 --- /dev/null +++ b/tests/generic/1229.out @@ -0,0 +1,2 @@ +QA output created by 1229 +Silence is golden -- 2.49.0 This test is intended to ensure that multi blocks atomic writes maintain atomic guarantees across sudden FS shutdowns. The way we work is that we lay out a file with random mix of written, unwritten and hole extents. Then we start performing atomic writes sequentially on the file while we parallelly shutdown the FS. Then we note the last offset where the atomic write happened just before shut down and then make sure blocks around it either have completely old data or completely new data, ie the write was not torn during shutdown. We repeat the same with completely written, completely unwritten and completely empty file to ensure these cases are not torn either. Finally, we have a similar test for append atomic writes Suggested-by: Ritesh Harjani (IBM) Reviewed-by: Darrick J. Wong Reviewed-by: John Garry Signed-off-by: Ojaswin Mujoo --- tests/generic/1230 | 368 +++++++++++++++++++++++++++++++++++++++++ tests/generic/1230.out | 2 + 2 files changed, 370 insertions(+) create mode 100755 tests/generic/1230 create mode 100644 tests/generic/1230.out diff --git a/tests/generic/1230 b/tests/generic/1230 new file mode 100755 index 00000000..cba75441 --- /dev/null +++ b/tests/generic/1230 @@ -0,0 +1,368 @@ +#! /bin/bash +# SPDX-License-Identifier: GPL-2.0 +# Copyright (c) 2025 IBM Corporation. All Rights Reserved. +# +# FS QA Test No. 1230 +# +# Test multi block atomic writes with sudden FS shutdowns to ensure +# the FS is not tearing the write operation +. ./common/preamble +. ./common/atomicwrites +_begin_fstest auto atomicwrites + +_require_scratch_write_atomic_multi_fsblock +_require_atomic_write_test_commands +_require_scratch_shutdown +_require_xfs_io_command "truncate" + +_scratch_mkfs >> $seqres.full 2>&1 +_scratch_mount >> $seqres.full + +testfile=$SCRATCH_MNT/testfile +touch $testfile + +awu_max=$(_get_atomic_write_unit_max $testfile) +blksz=$(_get_block_size $SCRATCH_MNT) +echo "Awu max: $awu_max" >> $seqres.full + +num_blocks=$((awu_max / blksz)) +# keep initial value high for dry run. This will be +# tweaked in dry_run() based on device write speed. +filesize=$(( 10 * 1024 * 1024 * 1024 )) + +_cleanup() { + [ -n "$awloop_pid" ] && kill $awloop_pid &> /dev/null + wait +} + +atomic_write_loop() { + local off=0 + local size=$awu_max + for ((i=0; i<$((filesize / $size )); i++)); do + # Due to sudden shutdown this can produce errors so just + # redirect them to seqres.full + $XFS_IO_PROG -c "open -fsd $testfile" -c "pwrite -S 0x61 -DA -V1 -b $size $off $size" >> /dev/null 2>>$seqres.full + echo "Written to offset: $off" >> $tmp.aw + off=$((off + $size)) + done +} + +start_atomic_write_and_shutdown() { + atomic_write_loop & + awloop_pid=$! + + local i=0 + # Wait for at least first write to be recorded or 10s + while [ ! -f "$tmp.aw" -a $i -le 50 ]; do i=$((i + 1)); sleep 0.2; done + + if [[ $i -gt 50 ]] + then + _fail "atomic write process took too long to start" + fi + + echo >> $seqres.full + echo "# Shutting down filesystem while write is running" >> $seqres.full + _scratch_shutdown + + kill $awloop_pid 2>/dev/null # the process might have finished already + wait $awloop_pid + unset $awloop_pid +} + +# This test has the following flow: +# 1. Start doing sequential atomic writes in background, upto $filesize +# 2. Sleep for 0.2s and shutdown the FS +# 3. kill the atomic write process +# 4. verify the writes were not torn +# +# We ideally want the shutdown to happen while an atomic write is ongoing +# but this gets tricky since faster devices can actually finish the whole +# atomic write loop before sleep 0.2s completes, resulting in the shutdown +# happening after the write loop which is not what we want. A simple solution +# to this is to increase $filesize so step 1 takes long enough but a big +# $filesize leads to create_mixed_mappings() taking very long, which is not +# ideal. +# +# Hence, use the dry_run function to figure out the rough device speed and set +# $filesize accordingly. +dry_run() { + echo >> $seqres.full + echo "# Estimating ideal filesize..." >> $seqres.full + + start_atomic_write_and_shutdown + + bytes_written=$(tail -n 1 $tmp.aw | cut -d" " -f4) + echo "# Bytes written in 0.2s: $bytes_written" >> $seqres.full + + filesize=$((bytes_written * 3)) + echo "# Setting \$filesize=$filesize" >> $seqres.full + + rm $tmp.aw + sleep 0.5 + + _scratch_cycle_mount + +} + +create_mixed_mappings() { + local file=$1 + local size_bytes=$2 + + echo "# Filling file $file with alternate mappings till size $size_bytes" >> $seqres.full + #Fill the file with alternate written and unwritten blocks + local off=0 + local operations=("W" "U") + + for ((i=0; i<$((size_bytes / blksz )); i++)); do + index=$(($i % ${#operations[@]})) + map="${operations[$index]}" + + case "$map" in + "W") + $XFS_IO_PROG -fc "pwrite -b $blksz $off $blksz" $file >> /dev/null + ;; + "U") + $XFS_IO_PROG -fc "falloc $off $blksz" $file >> /dev/null + ;; + esac + off=$((off + blksz)) + done + + sync $file +} + +populate_expected_data() { + # create a dummy file with expected old data for different cases + create_mixed_mappings $testfile.exp_old_mixed $awu_max + expected_data_old_mixed=$(od -An -t x1 -j 0 -N $awu_max $testfile.exp_old_mixed) + + $XFS_IO_PROG -fc "falloc 0 $awu_max" $testfile.exp_old_zeroes >> $seqres.full + expected_data_old_zeroes=$(od -An -t x1 -j 0 -N $awu_max $testfile.exp_old_zeroes) + + $XFS_IO_PROG -fc "pwrite -b $awu_max 0 $awu_max" $testfile.exp_old_mapped >> $seqres.full + expected_data_old_mapped=$(od -An -t x1 -j 0 -N $awu_max $testfile.exp_old_mapped) + + # create a dummy file with expected new data + $XFS_IO_PROG -fc "pwrite -S 0x61 -b $awu_max 0 $awu_max" $testfile.exp_new >> $seqres.full + expected_data_new=$(od -An -t x1 -j 0 -N $awu_max $testfile.exp_new) +} + +verify_data_blocks() { + local verify_start=$1 + local verify_end=$2 + local expected_data_old="$3" + local expected_data_new="$4" + + echo >> $seqres.full + echo "# Checking for torn write from $verify_start to $verify_end" >> $seqres.full + + # After an atomic write, for every chunk we ensure that the underlying + # data is either the old data or new data as writes shouldn't get torn. + local off=$verify_start + while [[ "$off" -lt "$verify_end" ]] + do + #actual_data=$(xxd -s $off -l $awu_max -p $testfile) + actual_data=$(od -An -t x1 -j $off -N $awu_max $testfile) + if [[ "$actual_data" != "$expected_data_new" ]] && [[ "$actual_data" != "$expected_data_old" ]] + then + echo "Checksum match failed at off: $off size: $awu_max" + echo "Expected contents: (Either of the 2 below):" + echo + echo "Old: " + echo "$expected_data_old" + echo + echo "New: " + echo "$expected_data_new" + echo + echo "Actual contents: " + echo "$actual_data" + + _fail + fi + echo -n "Check at offset $off succeeded! " >> $seqres.full + if [[ "$actual_data" == "$expected_data_new" ]] + then + echo "matched new" >> $seqres.full + elif [[ "$actual_data" == "$expected_data_old" ]] + then + echo "matched old" >> $seqres.full + fi + off=$(( off + awu_max )) + done +} + +# test torn write for file by shutting down in between atomic writes +test_torn_write() { + echo >> $seqres.full + echo "# Writing atomically to file in background" >> $seqres.full + + start_atomic_write_and_shutdown + + last_offset=$(tail -n 1 $tmp.aw | cut -d" " -f4) + if [[ -z $last_offset ]] + then + last_offset=0 + fi + + echo >> $seqres.full + echo "# Last offset of atomic write: $last_offset" >> $seqres.full + + rm $tmp.aw + sleep 0.5 + + _scratch_cycle_mount + + # we want to verify all blocks around which the shutdown happened + verify_start=$(( last_offset - (awu_max * 5))) + if [[ $verify_start < 0 ]] + then + verify_start=0 + fi + + verify_end=$(( last_offset + (awu_max * 5))) + if [[ "$verify_end" -gt "$filesize" ]] + then + verify_end=$filesize + fi +} + +# test torn write for file with written and unwritten mappings +test_torn_write_mixed() { + $XFS_IO_PROG -fc "truncate 0" $testfile >> $seqres.full + + echo >> $seqres.full + echo "# Creating testfile with mixed mappings" >> $seqres.full + create_mixed_mappings $testfile $filesize + + test_torn_write + + verify_data_blocks $verify_start $verify_end "$expected_data_old_mixed" "$expected_data_new" +} + +# test torn write for file with completely written mappings +test_torn_write_written() { + $XFS_IO_PROG -fc "truncate 0" $testfile >> $seqres.full + + echo >> $seqres.full + echo "# Creating testfile with fully written mapping" >> $seqres.full + $XFS_IO_PROG -c "pwrite -b $filesize 0 $filesize" $testfile >> $seqres.full + sync $testfile + + test_torn_write + + verify_data_blocks $verify_start $verify_end "$expected_data_old_mapped" "$expected_data_new" +} + +# test torn write for file with completely unwritten mappings +test_torn_write_unwritten() { + $XFS_IO_PROG -fc "truncate 0" $testfile >> $seqres.full + + echo >> $seqres.full + echo "# Creating testfile with fully unwritten mappings" >> $seqres.full + $XFS_IO_PROG -c "falloc 0 $filesize" $testfile >> $seqres.full + sync $testfile + + test_torn_write + + verify_data_blocks $verify_start $verify_end "$expected_data_old_zeroes" "$expected_data_new" +} + +# test torn write for file with no mappings +test_torn_write_hole() { + $XFS_IO_PROG -fc "truncate 0" $testfile >> $seqres.full + + echo >> $seqres.full + echo "# Creating testfile with no mappings" >> $seqres.full + $XFS_IO_PROG -c "truncate $filesize" $testfile >> $seqres.full + sync $testfile + + test_torn_write + + verify_data_blocks $verify_start $verify_end "$expected_data_old_zeroes" "$expected_data_new" +} + +test_append_torn_write() { + $XFS_IO_PROG -c "truncate 0" $testfile >> $seqres.full + + echo >> $seqres.full + echo "# Performing append atomic writes over file in background" >> $seqres.full + + start_atomic_write_and_shutdown + + local last_offset=$(tail -n 1 $tmp.aw | cut -d" " -f4) + if [[ -z $last_offset ]] + then + last_offset=0 + fi + + echo >> $seqres.full + echo "# Last offset of atomic write: $last_offset" >> $seqres.full + rm $tmp.aw + sleep 0.5 + + _scratch_cycle_mount + local filesize=$(_get_filesize $testfile) + echo >> $seqres.full + echo "# Filesize after shutdown: $filesize" >> $seqres.full + + # To confirm that the write went atomically, we check: + # 1. The last block should be a multiple of awu_max + # 2. The last block should be the completely new data + + if (( $filesize % $awu_max )) + then + echo "Filesize after shutdown ($filesize) not a multiple of atomic write unit ($awu_max)" + fi + + verify_start=$(( filesize - (awu_max * 5))) + if [[ $verify_start < 0 ]] + then + verify_start=0 + fi + + local verify_end=$filesize + + # Here the blocks should always match new data hence, for simplicity of + # code, just corrupt the $expected_data_old buffer so it never matches + local expected_data_old="POISON" + verify_data_blocks $verify_start $verify_end "$expected_data_old" "$expected_data_new" +} + +$XFS_IO_PROG -fc "truncate 0" $testfile >> $seqres.full + +dry_run + +echo >> $seqres.full +echo "# Populating expected data buffers" >> $seqres.full +populate_expected_data + +# Loop 20 times to shake out any races due to shutdown +for ((iter=0; iter<20; iter++)) +do + echo >> $seqres.full + echo "------ Iteration $iter ------" >> $seqres.full + + echo >> $seqres.full + echo "# Starting torn write test for atomic writes over mixed mapping" >> $seqres.full + test_torn_write_mixed + + echo >> $seqres.full + echo "# Starting torn write test for atomic writes over fully written mapping" >> $seqres.full + test_torn_write_written + + echo >> $seqres.full + echo "# Starting torn write test for atomic writes over fully unwritten mapping" >> $seqres.full + test_torn_write_unwritten + + echo >> $seqres.full + echo "# Starting torn write test for atomic writes over holes" >> $seqres.full + test_torn_write_hole + + echo >> $seqres.full + echo "# Starting shutdown torn write test for append atomic writes" >> $seqres.full + test_append_torn_write +done + +echo "Silence is golden" +status=0 +exit diff --git a/tests/generic/1230.out b/tests/generic/1230.out new file mode 100644 index 00000000..d01f54ea --- /dev/null +++ b/tests/generic/1230.out @@ -0,0 +1,2 @@ +QA output created by 1230 +Silence is golden -- 2.49.0 From: "Ritesh Harjani (IBM)" This test does a lot of parallel RWF_ATOMIC IO on a preallocated file to stress the write and end-io unwritten conversion code paths. We brute force this for different blocksize and clustersizes and after each iteration we ensure the data was not torn or corrupted using fio crc verification. Note that in this test we use overlapping atomic writes of same io size. Although serializing racing writes is not guaranteed for RWF_ATOMIC, NVMe and SCSI provide this guarantee as an inseparable feature to power-fail atomicity. Keeping the iosize as same also ensures that ext4 doesn't tear the write due to racing ioend unwritten conversion. The value of this test is that we make sure the RWF_ATOMIC is handled correctly by ext4 as well as test that the block layer doesn't split or only generate multiple bios for an atomic write. Signed-off-by: Ritesh Harjani (IBM) Reviewed-by: Darrick J. Wong Reviewed-by: John Garry Signed-off-by: Ojaswin Mujoo --- tests/ext4/061 | 155 +++++++++++++++++++++++++++++++++++++++++++++ tests/ext4/061.out | 2 + 2 files changed, 157 insertions(+) create mode 100755 tests/ext4/061 create mode 100644 tests/ext4/061.out diff --git a/tests/ext4/061 b/tests/ext4/061 new file mode 100755 index 00000000..1d61c8b0 --- /dev/null +++ b/tests/ext4/061 @@ -0,0 +1,155 @@ +#! /bin/bash +# SPDX-License-Identifier: GPL-2.0 +# Copyright (c) 2025 IBM Corporation. All Rights Reserved. +# +# FS QA Test 061 +# +# This test does a lot of parallel RWF_ATOMIC IO on a preallocated file to +# stress the write and end-io unwritten conversion code paths. We brute force +# this for all possible blocksize and clustersizes and after each iteration we +# ensure the data was not torn or corrupted using fio crc verification. +# +# Note that in this test we use overlapping atomic writes of same io size. +# Although serializing racing writes is not guaranteed for RWF_ATOMIC, NVMe and +# SCSI provide this guarantee as an inseparable feature to power-fail +# atomicity. Keeping the iosize as same also ensures that ext4 doesn't tear the +# write due to racing ioend unwritten conversion. +# +# The value of this test is that we make sure the RWF_ATOMIC is handled +# correctly by ext4 as well as test that the block layer doesn't split or only +# generate multiple bios for an atomic write. + +. ./common/preamble +. ./common/atomicwrites + +_begin_fstest auto rw stress atomicwrites + +_require_scratch_write_atomic +_require_fio_atomic_writes +_require_aiodio + +FIO_LOAD=$(($(nproc) * 2 * LOAD_FACTOR)) +SIZE=$((100*1024*1024)) + +# Calculate fsblocksize as per bdev atomic write units. +bdev_awu_min=$(_get_atomic_write_unit_min $SCRATCH_DEV) +bdev_awu_max=$(_get_atomic_write_unit_max $SCRATCH_DEV) +bs=$(_max 4096 "$bdev_awu_min") + +function create_fio_configs() +{ + local bsize=$1 + create_fio_aw_config $bsize + create_fio_verify_config $bsize +} + +function create_fio_verify_config() +{ + local bsize=$1 +cat >$fio_verify_config <$fio_aw_config <> $seqres.full 2>&1 || return + if _try_scratch_mount >> $seqres.full 2>&1; then + echo "== Testing: bs=$bs cs=$cs iosize=$iosize ==" >> $seqres.full + + touch $SCRATCH_MNT/f1 + create_fio_configs $iosize + + cat $fio_aw_config >> $seqres.full + echo >> $seqres.full + cat $fio_verify_config >> $seqres.full + + $FIO_PROG $fio_aw_config >> $seqres.full + ret1=$? + + $FIO_PROG $fio_verify_config >> $seqres.full + ret2=$? + + _scratch_unmount + + [[ $ret1 -eq 0 && $ret2 -eq 0 ]] || _fail "fio with atomic write failed" + fi +} + +run_test() { + local bs=$1 + + # cluster sizes above 16 x blocksize are experimental so avoid them + # Also, cap cluster size at 128kb to keep it reasonable for large + # blocks size + max_cs=$(_min $((16 * bs)) "$bdev_awu_max" $((128 * 1024))) + + # Fuzz for combinations of blocksize, clustersize and + # iosize that cover most of the cases + run_test_one $bs $bs $bs + run_test_one $bs $max_cs $bs + run_test_one $bs $max_cs $max_cs + run_test_one $bs $max_cs $(_max "$((max_cs/2))" $bs) +} + +# Let's create a sample fio config to check whether fio supports all options. +fio_aw_config=$tmp.aw.fio +fio_verify_config=$tmp.verify.fio +fio_out=$tmp.fio.out + +create_fio_configs $bs +_require_fio $fio_aw_config + +for ((bs=$bs; bs <= $(_get_page_size); bs = $bs << 1)); do + run_test $bs +done + +# success, all done +echo Silence is golden +status=0 +exit diff --git a/tests/ext4/061.out b/tests/ext4/061.out new file mode 100644 index 00000000..273be9e0 --- /dev/null +++ b/tests/ext4/061.out @@ -0,0 +1,2 @@ +QA output created by 061 +Silence is golden -- 2.49.0 In ext4, even if an allocated range is physically and logically contiguous, it can still be split into 2 extents. This is because ext4 does not merge extents across leaf nodes. This is an issue for atomic writes since even for a continuous extent the map block could (in rare cases) return a shorter map, hence tearning the write. This test creates such a file and ensures that the atomic write handles this case correctly Reviewed-by: Darrick J. Wong Signed-off-by: Ojaswin Mujoo --- tests/ext4/063 | 129 +++++++++++++++++++++++++++++++++++++++++++++ tests/ext4/063.out | 2 + 2 files changed, 131 insertions(+) create mode 100755 tests/ext4/063 create mode 100644 tests/ext4/063.out diff --git a/tests/ext4/063 b/tests/ext4/063 new file mode 100755 index 00000000..9d6265a8 --- /dev/null +++ b/tests/ext4/063 @@ -0,0 +1,129 @@ +#! /bin/bash +# SPDX-License-Identifier: GPL-2.0 +# Copyright (c) 2025 IBM Corporation. All Rights Reserved. +# +# In ext4, even if an allocated range is physically and logically contiguous, +# it can still be split into 2 or more extents. This is because ext4 does not +# merge extents across leaf nodes. This is an issue for atomic writes since +# even for a continuous extent the map block could (in rare cases) return a +# shorter map, hence tearing the write. This test creates such a file and +# ensures that the atomic write handles this case correctly +# +. ./common/preamble +. ./common/atomicwrites +_begin_fstest auto atomicwrites + +_require_scratch_write_atomic_multi_fsblock +_require_atomic_write_test_commands +_require_command "$DEBUGFS_PROG" debugfs + +prep() { + local bs=`_get_block_size $SCRATCH_MNT` + local ex_hdr_bytes=12 + local ex_entry_bytes=12 + local entries_per_blk=$(( (bs - ex_hdr_bytes) / ex_entry_bytes )) + + # fill the extent tree leaf with bs len extents at alternate offsets. + # The tree should look as follows + # + # +---------+---------+ + # | index 1 | index 2 | + # +-----+---+-----+---+ + # +------+ +-----------+ + # | | + # +-------+-------+---+---------+ +-----+----+ + # | ex 1 | ex 2 | | ex n | | ex n+1 | + # | off:0 | off:2 |...| off:678 | | off:680 | + # | len:1 | len:1 | | len:1 | | len:1 | + # +-------+-------+---+---------+ +----------+ + # + for i in $(seq 0 $entries_per_blk) + do + $XFS_IO_PROG -fc "pwrite -b $bs $((i * 2 * bs)) $bs" $testfile > /dev/null + done + sync $testfile + + echo >> $seqres.full + echo "Create file with extents spanning 2 leaves. Extents:">> $seqres.full + echo "...">> $seqres.full + $DEBUGFS_PROG -R "ex `basename $testfile`" $SCRATCH_DEV |& tail >> $seqres.full + + # Now try to insert a new extent ex(new) between ex(n) and ex(n+1). + # Since this is a new FS the allocator would find continuous blocks + # such that ex(n) ex(new) ex(n+1) are physically(and logically) + # contiguous. However, since we don't merge extents across leaf we will + # end up with a tree as: + # + # +---------+---------+ + # | index 1 | index 2 | + # +-----+---+-----+---+ + # +------+ +------------+ + # | | + # +-------+-------+---+---------+ +------+-----------+ + # | ex 1 | ex 2 | | ex n | | ex n+1 (merged) | + # | off:0 | off:2 |...| off:678 | | off:679 | + # | len:1 | len:1 | | len:1 | | len:2 | + # +-------+-------+---+---------+ +------------------+ + # + echo >> $seqres.full + torn_ex_offset=$((((entries_per_blk * 2) - 1) * bs)) + $XFS_IO_PROG -c "pwrite $torn_ex_offset $bs" $testfile >> /dev/null + sync $testfile + + echo >> $seqres.full + echo "Perform 1 block write at $torn_ex_offset to create torn extent. Extents:">> $seqres.full + echo "...">> $seqres.full + $DEBUGFS_PROG -R "ex `basename $testfile`" $SCRATCH_DEV |& tail >> $seqres.full + + _scratch_cycle_mount +} + +_scratch_mkfs >> $seqres.full +_scratch_mount >> $seqres.full + +testfile=$SCRATCH_MNT/testfile +touch $testfile +awu_max=$(_get_atomic_write_unit_max $testfile) + +echo >> $seqres.full +echo "# Prepping the file" >> $seqres.full +prep + +torn_aw_offset=$((torn_ex_offset - (torn_ex_offset % awu_max))) + +echo >> $seqres.full +echo "# Performing atomic IO on the torn extent range. Command: " >> $seqres.full +echo $XFS_IO_PROG -c "open -fsd $testfile" -c "pwrite -S 0x61 -DA -V1 -b $awu_max $torn_aw_offset $awu_max" >> $seqres.full +$XFS_IO_PROG -c "open -fsd $testfile" -c "pwrite -S 0x61 -DA -V1 -b $awu_max $torn_aw_offset $awu_max" >> $seqres.full + +echo >> $seqres.full +echo "Extent state after atomic write:">> $seqres.full +echo "...">> $seqres.full +$DEBUGFS_PROG -R "ex `basename $testfile`" $SCRATCH_DEV |& tail >> $seqres.full + +echo >> $seqres.full +echo "# Checking data integrity" >> $seqres.full + +# create a dummy file with expected data +$XFS_IO_PROG -fc "pwrite -S 0x61 -b $awu_max 0 $awu_max" $testfile.exp >> /dev/null +expected_data=$(od -An -t x1 -j 0 -N $awu_max $testfile.exp) + +# We ensure that the data after atomic writes should match the expected data +actual_data=$(od -An -t x1 -j $torn_aw_offset -N $awu_max $testfile) +if [[ "$actual_data" != "$expected_data" ]] +then + echo "Checksum match failed at off: $torn_aw_offset size: $awu_max" + echo + echo "Expected: " + echo "$expected_data" + echo + echo "Actual contents: " + echo "$actual_data" + + _fail +fi + +echo -n "Data verification at offset $torn_aw_offset succeeded!" >> $seqres.full +echo "Silence is golden" +status=0 +exit diff --git a/tests/ext4/063.out b/tests/ext4/063.out new file mode 100644 index 00000000..de35fc52 --- /dev/null +++ b/tests/ext4/063.out @@ -0,0 +1,2 @@ +QA output created by 063 +Silence is golden -- 2.49.0