From 728d8f39925d2c694ee49c79d65c2156f2553a9a Mon Sep 17 00:00:00 2001 From: Alexandre Derumier via pve-devel Date: Thu, 23 Oct 2025 14:23:30 +0200 Subject: [PATCH] lvmplugin: use blkdiscard when supported instead cstream to saferemove drive Current cstream implementation is pretty slow, even without throttling. use blkdiscard --zeroout instead when storage support it, which is a few magnitudes faster. Another benefit is that blkdiscard is skipping already zeroed block, so for empty temp images like snapshot, is pretty fast. blkdiscard don't have throttling like cstream, but we can tune the step size of zeroes pushed to the storage. I'm using 32MB stepsize by default , like ovirt, where it seem to be the best balance between speed and load. https://github.com/oVirt/vdsm/commit/79f1d79058aad863ca4b6672d4a5ce2be8e48986 but it can be reduce with "saferemove_stepsize" option. stepsize is also autoreduce to sysfs write_zeroes_max_bytes, which is the maximum zeroing batch supported by the storage test with a 100G volume (empty): time /usr/bin/cstream -i /dev/zero -o /dev/test/vm-100-disk-0.qcow2 -T 10 -v 1 -b 1048576 13561233408 B 12.6 GB 10.00 s 1356062979 B/s 1.26 GB/s 26021462016 B 24.2 GB 20.00 s 1301029969 B/s 1.21 GB/s 38585499648 B 35.9 GB 30.00 s 1286135343 B/s 1.20 GB/s 50998542336 B 47.5 GB 40.00 s 1274925312 B/s 1.19 GB/s 63702765568 B 59.3 GB 50.00 s 1274009877 B/s 1.19 GB/s 76721885184 B 71.5 GB 60.00 s 1278640698 B/s 1.19 GB/s 89126539264 B 83.0 GB 70.00 s 1273178488 B/s 1.19 GB/s 101666459648 B 94.7 GB 80.00 s 1270779024 B/s 1.18 GB/s 107390959616 B 100.0 GB 84.39 s 1272531142 B/s 1.19 GB/s write: No space left on device real 1m24.394s user 0m0.171s sys 1m24.052s time blkdiscard --zeroout /dev/test/vm-100-disk-0.qcow2 -v /dev/test/vm-100-disk-0.qcow2: Zero-filled 107390959616 bytes from the offset 0 real 0m3.641s user 0m0.001s sys 0m3.433s test with a 100G volume with random data: time blkdiscard --zeroout /dev/test/vm-100-disk-0.qcow2 -v /dev/test/vm-112-disk-1: Zero-filled 4764729344 bytes from the offset 0 /dev/test/vm-112-disk-1: Zero-filled 4664066048 bytes from the offset 4764729344 /dev/test/vm-112-disk-1: Zero-filled 4831838208 bytes from the offset 9428795392 /dev/test/vm-112-disk-1: Zero-filled 4831838208 bytes from the offset 14260633600 /dev/test/vm-112-disk-1: Zero-filled 4831838208 bytes from the offset 19092471808 /dev/test/vm-112-disk-1: Zero-filled 4865392640 bytes from the offset 23924310016 /dev/test/vm-112-disk-1: Zero-filled 4596957184 bytes from the offset 28789702656 /dev/test/vm-112-disk-1: Zero-filled 4731174912 bytes from the offset 33386659840 /dev/test/vm-112-disk-1: Zero-filled 4294967296 bytes from the offset 38117834752 /dev/test/vm-112-disk-1: Zero-filled 4664066048 bytes from the offset 42412802048 /dev/test/vm-112-disk-1: Zero-filled 4697620480 bytes from the offset 47076868096 /dev/test/vm-112-disk-1: Zero-filled 4664066048 bytes from the offset 51774488576 /dev/test/vm-112-disk-1: Zero-filled 4261412864 bytes from the offset 56438554624 /dev/test/vm-112-disk-1: Zero-filled 4362076160 bytes from the offset 60699967488 /dev/test/vm-112-disk-1: Zero-filled 4127195136 bytes from the offset 65062043648 /dev/test/vm-112-disk-1: Zero-filled 4328521728 bytes from the offset 69189238784 /dev/test/vm-112-disk-1: Zero-filled 4731174912 bytes from the offset 73517760512 /dev/test/vm-112-disk-1: Zero-filled 4026531840 bytes from the offset 78248935424 /dev/test/vm-112-disk-1: Zero-filled 4194304000 bytes from the offset 82275467264 /dev/test/vm-112-disk-1: Zero-filled 4664066048 bytes from the offset 86469771264 /dev/test/vm-112-disk-1: Zero-filled 4395630592 bytes from the offset 91133837312 /dev/test/vm-112-disk-1: Zero-filled 3623878656 bytes from the offset 95529467904 /dev/test/vm-112-disk-1: Zero-filled 4462739456 bytes from the offset 99153346560 /dev/test/vm-112-disk-1: Zero-filled 3758096384 bytes from the offset 103616086016 real 0m23.969s user 0m0.030s sys 0m0.144s Signed-off-by: Alexandre Derumier Link: https://lore.proxmox.com/mailman.253.1761222252.362.pve-devel@lists.proxmox.com [FE: Minor language improvements Use more common style for importing with qw() Don't specify full path to blkdiscard binary for run_command()] Signed-off-by: Fiona Ebner --- src/PVE/Storage/LVMPlugin.pm | 72 ++++++++++++++++++++++++++++++------ 1 file changed, 61 insertions(+), 11 deletions(-) diff --git a/src/PVE/Storage/LVMPlugin.pm b/src/PVE/Storage/LVMPlugin.pm index 0416c9e..80f6aba 100644 --- a/src/PVE/Storage/LVMPlugin.pm +++ b/src/PVE/Storage/LVMPlugin.pm @@ -3,10 +3,11 @@ package PVE::Storage::LVMPlugin; use strict; use warnings; +use Cwd qw(abs_path); use File::Basename; use IO::File; -use PVE::Tools qw(run_command trim); +use PVE::Tools qw(run_command file_read_firstline trim); use PVE::Storage::Plugin; use PVE::JSONSchema qw(get_standard_option); @@ -284,23 +285,40 @@ my sub free_lvm_volumes { my $vg = $scfg->{vgname}; - # we need to zero out LVM data for security reasons - # and to allow thin provisioning - my $zero_out_worker = sub { - # 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}; + my $secure_delete_cmd = sub { + my ($lvmpath) = @_; + + my $stepsize = $scfg->{'saferemove-stepsize'} // 32; + $stepsize = $stepsize * 1024 * 1024; + + my $bdev = abs_path($lvmpath); + + my $sysdir = undef; + if ($bdev && $bdev =~ m|^/dev/(dm-\d+)|) { + $sysdir = "/sys/block/$1"; + } else { + warn "skip zero-out for volume '$lvmpath' - no device mapper link\n"; + return; } - for my $name (@$volnames) { - print "zero-out data on image $name (/dev/$vg/del-$name)\n"; + + my $write_zeroes_max_bytes = + file_read_firstline("$sysdir/queue/write_zeroes_max_bytes") // 0; + ($write_zeroes_max_bytes) = $write_zeroes_max_bytes =~ m/^(\d+)$/; #untaint + + 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}; + } my $cmd = [ '/usr/bin/cstream', '-i', '/dev/zero', '-o', - "/dev/$vg/del-$name", + $lvmpath, '-T', '10', '-v', @@ -317,6 +335,30 @@ my sub free_lvm_volumes { ); }; warn $@ if $@; + } else { + # If the storage supports write_zeroes but stepsize is too big, reduce the stepsize to + # the maximum supported by the storage. + if ($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"; + + $stepsize = $write_zeroes_max_bytes; + } + + my $cmd = ['blkdiscard', $lvmpath, '-v', '--zeroout', '--step', "${stepsize}"]; + eval { run_command($cmd); }; + warn $@ if $@; + } + }; + + # we need to zero out LVM data for security reasons + # and to allow thin provisioning + my $zero_out_worker = sub { + for my $name (@$volnames) { + my $lvmpath = "/dev/$vg/del-$name"; + print "zero-out data on image $name ($lvmpath)\n"; + + $secure_delete_cmd->($lvmpath); $class->cluster_lock_storage( $storeid, @@ -376,6 +418,13 @@ sub properties { description => "Zero-out data when removing LVs.", type => 'boolean', }, + 'saferemove-stepsize' => { + description => "Wipe step size in MiB." + . " It will be capped to the maximum supported by the storage.", + default => 32, + enum => [qw(1 2 4 8 16 32)], + type => 'integer', + }, saferemove_throughput => { description => "Wipe throughput (cstream -t parameter value).", type => 'string', @@ -394,6 +443,7 @@ sub options { shared => { optional => 1 }, disable => { optional => 1 }, saferemove => { optional => 1 }, + 'saferemove-stepsize' => { optional => 1 }, saferemove_throughput => { optional => 1 }, content => { optional => 1 }, base => { fixed => 1, optional => 1 },