From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from gate001.proxmox.com (gate001.proxmox.com [45.144.208.40]) by lore.proxmox.com (Postfix) with ESMTPS id C18FF1FF146 for ; Tue, 07 Jul 2026 16:33:40 +0200 (CEST) Received: from gate001.proxmox.com (localhost.localdomain [127.0.0.1]) by gate001.proxmox.com (Proxmox) with ESMTP id 123DC21495; Tue, 07 Jul 2026 16:33:34 +0200 (CEST) From: Lukas Sichert To: pve-devel@lists.proxmox.com Subject: [PATCH storage v8 2/5] lvm: saferemove: zero out volumes range by range Date: Tue, 7 Jul 2026 16:32:45 +0200 Message-ID: <20260707143252.101757-3-l.sichert@proxmox.com> X-Mailer: git-send-email 2.47.3 In-Reply-To: <20260707143252.101757-1-l.sichert@proxmox.com> References: <20260707143252.101757-1-l.sichert@proxmox.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Bm-Milter-Handled: 55990f41-d878-4baa-be0a-ee34c49e34d2 X-Bm-Transport-Timestamp: 1783434771993 X-SPAM-LEVEL: Spam detection results: 0 AWL 0.000 Adjusted score from AWL reputation of From: address DMARC_MISSING 0.1 Missing DMARC policy KAM_DMARC_STATUS 0.01 Test Rule for DKIM or SPF Failure with Strict Alignment (newer systems) SPF_HELO_NONE 0.001 SPF: HELO does not publish an SPF Record SPF_PASS -0.001 SPF: sender matches SPF record Message-ID-Hash: 7UNURZL2U5BZIHIXZKYOR7JV2FASYYJO X-Message-ID-Hash: 7UNURZL2U5BZIHIXZKYOR7JV2FASYYJO X-MailFrom: l.sichert@proxmox.com X-Mailman-Rule-Misses: dmarc-mitigation; no-senders; approved; loop; banned-address; emergency; member-moderation; nonmember-moderation; administrivia; implicit-dest; max-recipients; max-size; news-moderation; no-subject; digests; suspicious-header CC: Lukas Sichert X-Mailman-Version: 3.3.10 Precedence: list List-Id: Proxmox VE development discussion List-Help: List-Owner: List-Post: List-Subscribe: List-Unsubscribe: 'saferemove' currently uses different full-volume zero-out paths: `blkdiscard --zeroout` for devices with write-zeroes support and `cstream` otherwise. This makes consistent progress reporting and throttling difficult and prevents interleaving future discard cleanup with zeroing. On thin-provisioned backing storage, zeroing the whole LV first can force unnecessary allocation. Move zeroing into an explicit range loop. Use BLKZEROOUT when supported, cap to the device limit, and fall back to manually writing zeroes via syswrite otherwise. Add progress reporting in the shared loop, and apply a configured saferemove throughput limit there as well. Without an explicit limit, keep BLKZEROOUT unthrottled and throttle only manual writes to 10 MiB/s. Signed-off-by: Lukas Sichert --- src/PVE/Storage/LVMPlugin.pm | 146 +++++++++++++++++++++++++++-------- 1 file changed, 112 insertions(+), 34 deletions(-) diff --git a/src/PVE/Storage/LVMPlugin.pm b/src/PVE/Storage/LVMPlugin.pm index a0feb5c..a3adeef 100644 --- a/src/PVE/Storage/LVMPlugin.pm +++ b/src/PVE/Storage/LVMPlugin.pm @@ -8,9 +8,12 @@ use File::Basename; use IO::File; use JSON; use List::Util qw(max); +use Fcntl qw(SEEK_SET); use PVE::JSONSchema qw(get_standard_option); use PVE::Tools qw(run_command file_read_firstline trim); +use PVE::SafeSyslog; +use PVE::Format qw(render_bytes render_duration); use PVE::Storage::Common; use PVE::Storage::Plugin; @@ -19,6 +22,10 @@ use base qw(PVE::Storage::Plugin); # lvm helper functions +use constant { + BLKZEROOUT => 0x127f, +}; + my $ignore_no_medium_warnings = sub { my $line = shift; # ignore those, most of the time they're from (virtual) IPMI/iKVM devices @@ -280,6 +287,13 @@ sub lvm_list_volumes { return $lvs; } +my sub blockdev_ioctl_range { + my ($fh, $ioctl, $offset, $length) = @_; + + my $range = pack('QQ', $offset, $length); + ioctl($fh, $ioctl, $range) or die "$!\n"; +} + my sub free_lvm_volumes_locked { my ($class, $scfg, $storeid, $volnames) = @_; @@ -305,48 +319,112 @@ my sub free_lvm_volumes_locked { file_read_firstline("$sysdir/queue/write_zeroes_max_bytes") // 0; ($write_zeroes_max_bytes) = $write_zeroes_max_bytes =~ m/^(\d+)$/; #untaint + my $size = file_read_firstline("$sysdir/size") or die "size of $sysdir cannot be read"; + ($size) = $size =~ m/^(\d+)$/; # untaint + $size *= 512; # sysfs size is in 512-byte sectors + + my $zeroout_variant = 'blkzeroout'; + my $throughput = -1; + if ($scfg->{saferemove_throughput}) { + # use abs as legacy cstream accepted negative values + $throughput = abs($scfg->{saferemove_throughput}); + my $throughput_in_mibs = render_bytes($throughput); + print "using saferemove throughput limit: $throughput_in_mibs/s\n"; + } + + # If the storage does not support write_zeroes fall back to writing zeroes manually using + # syswrite. Otherwise if the storage supports write_zeroes but stepsize is too big, + # reduce the stepsize to the maximum supported by the storage. + my $zeroes; if ($write_zeroes_max_bytes == 0) { - # If the storage does not support 'write zeroes', we fallback to cstream. - # wipe throughput up to 10MB/s by default; may be overwritten with saferemove_throughput - my $throughput = '-10485760'; - if ($scfg->{saferemove_throughput}) { - $throughput = $scfg->{saferemove_throughput}; + print + "WRITE_ZEROES operation not supported, falling back to syswrite to zero-out '$lvmpath'\n"; + $zeroout_variant = 'syswrite'; + $stepsize = 1024 * 1024; # 1 MiB + print "reduce stepsize to 1 MiB for syswrite\n"; + $zeroes = "\0" x $stepsize; + # limit throughput to 10MiB/s for syswrite, if throughput was not set + if ($throughput <= 0) { + # FIXME: increase to 100 MiB/s with 10.0 + $throughput = 10485760; + print "using default syswrite-saferemove throughput limit: 10 MiB/s\n"; } + } elsif ($stepsize > $write_zeroes_max_bytes) { + print "reduce stepsize to the maximum supported by the storage:" + . " $write_zeroes_max_bytes bytes\n"; + $stepsize = $write_zeroes_max_bytes; + } + open(my $fh, '+<', $lvmpath) or die "can't open '$lvmpath' - $!\n"; - my $cmd = [ - '/usr/bin/cstream', - '-i', - '/dev/zero', - '-o', - $lvmpath, - '-T', - '10', - '-v', - '1', - '-b', - '1048576', - '-t', - "$throughput", - ]; - run_command( - $cmd, - errmsg => "zero out finished (note: 'No space left on device' is ok here)", - ); - } else { - # If the storage supports write_zeroes but stepsize is too big, reduce the stepsize to - # the maximum supported by the storage. - if ($write_zeroes_max_bytes > 0 && $stepsize > $write_zeroes_max_bytes) { - print "reduce stepsize to the maximum supported by the storage:" - . " $write_zeroes_max_bytes bytes\n"; + # eval block, so filehandle is closed even if something fails below + eval { + my $start = time(); + my $written_total = 0; + my $lastprint = -1; + my $written; + + for (my $offset = 0; $offset < $size; $offset += $written) { - $stepsize = $write_zeroes_max_bytes; + if ($offset + $stepsize > $size) { + $stepsize = $size - $offset; + } + + if ($zeroout_variant eq 'blkzeroout') { + eval { blockdev_ioctl_range($fh, BLKZEROOUT, $offset, $stepsize); }; + if ($@) { + die "blkzeroout for $stepsize bytes at offset $offset failed: $@"; + } + $written = $stepsize; + } elsif ($zeroout_variant eq 'syswrite') { + # if the $offset is 0, sysseek can return 0, therefore use // to only + # throw an error, if it returns undef + sysseek($fh, $offset, SEEK_SET) // die "sysseek failed: $!\n"; + + # use or as we also want to die if no progress was made, i.e. if $written is 0 + $written = syswrite($fh, $zeroes, $stepsize) + or die "syswrite failed: $!\n"; + + if ($written != $stepsize) { + warn "short syswrite: wrote $written of $stepsize bytes\n"; + } + + } + $written_total += $written; + + my $curr_time = time(); + if (($curr_time - $lastprint) >= 3) { + my $percent_finished = 100 * $written_total / $size; + my $curr_seconds = $curr_time - $start; + + printf( + "zeroed out %s of %s (%.2f%%) using %s in %s seconds\n", + render_bytes($written_total), + render_bytes($size), + $percent_finished, + $zeroout_variant, + render_duration($curr_seconds), + ); + $lastprint = $curr_time; + } + + if ($throughput > 0) { + my $expected_elapsed = $written_total / $throughput; + my $actual_elapsed = $curr_time - $start; + my $delay = $expected_elapsed - $actual_elapsed; + if ($delay > 0) { + sleep($delay); + } + } } - my $cmd = ['blkdiscard', $lvmpath, '-v', '--zeroout', '--step', "${stepsize}"]; - run_command($cmd); + }; + # close filehandle before throwing an error + my $err = $@; + close($fh); + if ($err) { + die "$err"; } }; - # we need to zero out LVM data for security reasons # and to allow thin provisioning my $zero_out_worker = sub { -- 2.47.3