From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 3738D1865FA for ; Wed, 11 Jun 2025 14:35:54 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1749652555; cv=none; b=WCHNhKY29hP9lzWEzt82ihjUvFH7WRX8g4lfCMi/sENz0SY/Sor8ddH6AFF08AwRUq5sgnXPSEY/CeQJASJYel3WIxg5Fngn3RqKuN2YnoqT/+JW1LICgAAlz4gJRQm8GA+8GLA7wYaM9+gFjSmF4ReHMLywZgVGHqyk/0SRmlQ= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1749652555; c=relaxed/simple; bh=HbBi0E3AaJvfJ5RjY933mJJF4tIESA6x0RhtVxrNvYc=; h=Date:From:To:Cc:Subject:Message-ID:References:MIME-Version: Content-Type:Content-Disposition:In-Reply-To; b=uUzJyTR+2nDNL/+ne6S58i9Esdf1hhuhGg2vAM5DdyeAbLeti3WBnQ6DeLjM+bEfBa/JZRwaOC61MgKWAtI/Q5pJfr0pZcb2yZDrGijctyH6IH/khGs4XpjNYFZmqaZWA3gTgOl7TbN1/ka8KoIK7n03IOir+GTEkUHxvKGZ9ws= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=YUf25rV2; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="YUf25rV2" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 9723EC4CEE3; Wed, 11 Jun 2025 14:35:54 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1749652554; bh=HbBi0E3AaJvfJ5RjY933mJJF4tIESA6x0RhtVxrNvYc=; h=Date:From:To:Cc:Subject:References:In-Reply-To:From; b=YUf25rV2+64AXk0oJx5v5ELPzD/MKWiNTf9QJwHotBBwNEQzpw4ZE0NrqBd/fAnhd zQdspjicXVgvkB9pUUZmn5iQT0DiNhHHdQ78CBbdIn7W+Joe5kQEhB5XvUHTTP8m8b jD/VGuN+c+654lUqF6ZA2sMNfMKGjNGWJpUDslbOWPuShTEDnAzK8QEAKUrYGEDu62 T0F2D+x83595vcMTviAVv/0TMaErGMXxnZOkimWcGKgjZ5JhHccKBz8+cloksOD3a7 iokFlw04+QqSHqz5lZnYGM54emDRNsZIhNnrP+iM7w2ADISsJCEGuZA9Bis58P/7Ji sMoLRxv+qb1vw== Date: Wed, 11 Jun 2025 07:35:54 -0700 From: "Darrick J. Wong" To: Ojaswin Mujoo Cc: fstests@vger.kernel.org, Ritesh Harjani , john.g.garry@oracle.com Subject: Re: [RFC 03/12] ltp/fsx.c: Add atomic writes support to fsx Message-ID: <20250611143554.GH6143@frogsfrogsfrogs> References: <07d5d00e4ebc24b4dd4c718b29dd14867fefdd70.1749629233.git.ojaswin@linux.ibm.com> Precedence: bulk X-Mailing-List: fstests@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <07d5d00e4ebc24b4dd4c718b29dd14867fefdd70.1749629233.git.ojaswin@linux.ibm.com> On Wed, Jun 11, 2025 at 03:04:46PM +0530, Ojaswin Mujoo wrote: > Implement atomic write support to help fuzz atomic writes > with fsx. > > Suggested-by: Ritesh Harjani (IBM) > Signed-off-by: Ojaswin Mujoo > --- > ltp/fsx.c | 105 +++++++++++++++++++++++++++++++++++++++++++++++++++--- > 1 file changed, 100 insertions(+), 5 deletions(-) > > diff --git a/ltp/fsx.c b/ltp/fsx.c > index 163b9453..9353fe6f 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 = 0; /* -a flag */ > + > +/* 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 inbetween 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 +1842,30 @@ do_dedupe_range(unsigned offset, unsigned length, unsigned dest) > } > #endif > > +int test_atomic_writes(void) { > + int ret; > + struct statx stx; > + > + 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) > @@ -2385,6 +2466,14 @@ have_op: > dowrite(offset, size, 0); > break; > > + case OP_WRITE_ATOMIC: > + TRIM_OFF_LEN(offset, size, maxfilelen); > + if (do_atomic_writes) > + dowrite(offset, size, RWF_ATOMIC); > + else > + dowrite(offset, size, 0); Er.... shouldn't we skip OP_ATOMIC_WRITE if !do_atomic_writes? There's a whole switch statement further up in test() that does things like: case OP_COPY_RANGE: if (!copy_range_calls) { log5(op, offset, size, offset2, FL_SKIPPED); goto out; } break; to break out early. --D > + break; > + > case OP_MAPREAD: > TRIM_OFF_LEN(offset, size, file_size); > domapread(offset, size); > @@ -2511,13 +2600,14 @@ 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: enable atomic writes if IO stack supports it\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 +3149,12 @@ 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': > + do_atomic_writes = 1; > + break; > case 'b': > simulatedopcount = getnum(optarg, &endp); > if (!quiet) > @@ -3475,6 +3568,8 @@ 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 > >