use PVE::ProcFSTools;
use Data::Dumper;
use Cwd qw(abs_path);
+use Fcntl ':mode';
use PVE::Tools qw(extract_param run_command file_get_contents file_read_firstline dir_glob_regex dir_glob_foreach trim);
my $ZPOOL = "/sbin/zpool";
my $SGDISK = "/sbin/sgdisk";
my $PVS = "/sbin/pvs";
+my $LVS = "/sbin/lvs";
my $UDEVADM = "/bin/udevadm";
sub verify_blockdev_path {
}
sub get_smart_data {
- my ($disk) = @_;
+ my ($disk, $healthonly) = @_;
assert_blockdev($disk);
my $smartdata = {};
- my $datastarted = 0;
+ my $type;
my $returncode = 0;
+
+ if ($disk =~ m!^/dev/(nvme\d+n\d+)$!) {
+ my $info = get_sysdir_info("/sys/block/$1");
+ $disk = "/dev/".($info->{device}
+ or die "failed to get nvme controller device for $disk\n");
+ }
+
+ my $cmd = [$SMARTCTL, '-H'];
+ push @$cmd, '-A', '-f', 'brief' if !$healthonly;
+ push @$cmd, $disk;
+
eval {
- $returncode = run_command([$SMARTCTL, '-H', '-A', '-f', 'brief', $disk], noerr => 1, outfunc => sub{
+ $returncode = run_command($cmd, noerr => 1, outfunc => sub{
my ($line) = @_;
# ATA SMART attributes, e.g.:
# ID# ATTRIBUTE_NAME FLAGS VALUE WORST THRESH FAIL RAW_VALUE
# 1 Raw_Read_Error_Rate POSR-K 100 100 000 - 0
- if ($datastarted && $line =~ m/^([ \d]{2}\d)\s+(\S+)\s+(\S{6})\s+(\d+)\s+(\d+)\s+(\d+)\s+(\S+)\s+(.*)$/) {
+#
+# SAS and NVME disks, e.g.:
+# Data Units Written: 5,584,952 [2.85 TB]
+# Accumulated start-stop cycles: 34
+
+ if (defined($type) && $type eq 'ata' && $line =~ m/^([ \d]{2}\d)\s+(\S+)\s+(\S{6})\s+(\d+)\s+(\d+)\s+(\S+)\s+(\S+)\s+(.*)$/) {
my $entry = {};
+
+
$entry->{name} = $2 if defined $2;
$entry->{flags} = $3 if defined $3;
# the +0 makes a number out of the strings
$entry->{value} = $4+0 if defined $4;
$entry->{worst} = $5+0 if defined $5;
- $entry->{threshold} = $6+0 if defined $6;
+ # some disks report the default threshold as --- instead of 000
+ if (defined($6) && $6 eq '---') {
+ $entry->{threshold} = 0;
+ } else {
+ $entry->{threshold} = $6+0 if defined $6;
+ }
$entry->{fail} = $7 if defined $7;
$entry->{raw} = $8 if defined $8;
$entry->{id} = $1 if defined $1;
push @{$smartdata->{attributes}}, $entry;
- } elsif ($line =~ m/self\-assessment test result: (.*)$/) {
+ } elsif ($line =~ m/(?:Health Status|self\-assessment test result): (.*)$/ ) {
$smartdata->{health} = $1;
} elsif ($line =~ m/Vendor Specific SMART Attributes with Thresholds:/) {
- $datastarted = 1;
+ $type = 'ata';
+ delete $smartdata->{text};
+ } elsif ($line =~ m/=== START OF (READ )?SMART DATA SECTION ===/) {
+ $type = 'text';
+ } elsif (defined($type) && $type eq 'text') {
+ $smartdata->{text} = '' if !defined $smartdata->{text};
+ $smartdata->{text} .= "$line\n";
+ } elsif ($line =~ m/SMART Disabled/) {
+ $smartdata->{health} = "SMART Disabled";
}
});
};
if ((defined($returncode) && ($returncode & 0b00000011)) || $err) {
die "Error getting S.M.A.R.T. data: Exit code: $returncode\n";
}
- return $smartdata;
-}
-
-sub get_smart_health {
- my ($disk) = @_;
-
- return "NOT A DEVICE" if !assert_blockdev($disk, 1);
-
- my $message;
- run_command([$SMARTCTL, '-H', $disk], noerr => 1, outfunc => sub {
- my ($line) = @_;
+ $smartdata->{type} = $type;
- if ($line =~ m/test result: (.*)$/) {
- $message = $1;
- } elsif ($line =~ m/open device: (.*) failed: (.*)$/) {
- $message = "FAILED TO OPEN";
- } elsif ($line =~ m/^SMART Disabled/) {
- $message = "SMART DISABLED";
- }
- });
-
- return $message;
+ return $smartdata;
}
sub get_zfs_devices {
my $list = {};
+ return {} if ! -x $ZPOOL;
+
# use zpool and parttype uuid,
# because log and cache do not have
# zfs type uuid
my $journalhash = {};
my $journal_uuid = '45b0969e-9b03-4f30-b4c6-b4b80ceff106';
+ my $db_uuid = '30cd0809-c2b2-499c-8879-2d6b78529876';
+ my $wal_uuid = '5ce17fce-4087-4169-b7ff-056cc58473f9';
+ my $block_uuid = 'cafecafe-9b03-4f30-b4c6-b4b80ceff106';
- dir_glob_foreach('/dev/disk/by-parttypeuuid', "$journal_uuid\..+", sub {
- my ($entry) = @_;
+ dir_glob_foreach('/dev/disk/by-parttypeuuid', "($journal_uuid|$db_uuid|$wal_uuid|$block_uuid)\..+", sub {
+ my ($entry, $type) = @_;
my $real_dev = abs_path("/dev/disk/by-parttypeuuid/$entry");
- $journalhash->{$real_dev} = 1;
+ if ($type eq $journal_uuid) {
+ $journalhash->{$real_dev} = 1;
+ } elsif ($type eq $db_uuid) {
+ $journalhash->{$real_dev} = 2;
+ } elsif ($type eq $wal_uuid) {
+ $journalhash->{$real_dev} = 3;
+ } elsif ($type eq $block_uuid) {
+ $journalhash->{$real_dev} = 4;
+ }
});
return $journalhash;
}
+# reads the lv_tags and matches them with the devices
+sub get_ceph_volume_infos {
+ my $result = {};
+
+ my $cmd = [ $LVS, '-S', 'lv_name=~^osd-', '-o', 'devices,lv_name,lv_tags',
+ '--noheadings', '--readonly', '--separator', ';' ];
+
+ run_command($cmd, outfunc => sub {
+ my $line = shift;
+ $line =~ s/(?:^\s+)|(?:\s+$)//g; # trim whitespaces
+
+ my $fields = [ split(';', $line) ];
+
+ # lvs syntax is /dev/sdX(Y) where Y is the start (which we do not need)
+ my ($dev) = $fields->[0] =~ m|^(/dev/[a-z]+)|;
+ if ($fields->[1] =~ m|^osd-([^-]+)-|) {
+ my $type = $1;
+ # $result autovivification is wanted, to not creating empty hashes
+ if (($type eq 'block' || $type eq 'data') && $fields->[2] =~ m/ceph.osd_id=([^,])/) {
+ $result->{$dev}->{osdid} = $1;
+ $result->{$dev}->{bluestore} = ($type eq 'block');
+ } else {
+ # undef++ becomes '1' (see `perldoc perlop`: Auto-increment)
+ $result->{$dev}->{$type}++;
+ }
+ }
+ });
+
+ return $result;
+}
+
sub get_udev_info {
my ($dev) = @_;
my $info = "";
my $data = {};
eval {
- run_command([$UDEVADM, 'info', '-n', $dev, '--query', 'all'], outfunc => sub {
+ run_command([$UDEVADM, 'info', '-p', $dev, '--query', 'all'], outfunc => sub {
my ($line) = @_;
$info .= "$line\n";
});
$data->{usb} = 1;
}
+ if ($info =~ m/^E: ID_MODEL=(.+)$/m) {
+ $data->{model} = $1;
+ }
+
$data->{wwn} = 'unknown';
if ($info =~ m/^E: ID_WWN=(.*)$/m) {
$data->{wwn} = $1;
sub get_sysdir_info {
my ($sysdir) = @_;
+ return undef if ! -d "$sysdir/device";
+
my $data = {};
my $size = file_read_firstline("$sysdir/size");
$data->{size} = $size * 512;
# dir/queue/rotational should be 1 for hdd, 0 for ssd
- $data->{rotational} = file_read_firstline("$sysdir/queue/rotational");
+ $data->{rotational} = file_read_firstline("$sysdir/queue/rotational") // -1;
$data->{vendor} = file_read_firstline("$sysdir/device/vendor") || 'unknown';
$data->{model} = file_read_firstline("$sysdir/device/model") || 'unknown';
+ if (defined(my $device = readlink("$sysdir/device"))) {
+ # strip directory and untaint:
+ ($data->{device}) = $device =~ m!([^/]+)$!;
+ }
+
return $data;
}
+sub get_wear_leveling_info {
+ my ($attributes, $model) = @_;
+
+ my $wearout;
+
+ my $vendormap = {
+ 'kingston' => 231,
+ 'samsung' => 177,
+ 'intel' => 233,
+ 'sandisk' => 233,
+ 'crucial' => 202,
+ 'default' => 233,
+ };
+
+ # find target attr id
+
+ my $attrid;
+
+ foreach my $vendor (keys %$vendormap) {
+ if ($model =~ m/$vendor/i) {
+ $attrid = $vendormap->{$vendor};
+ # found the attribute
+ last;
+ }
+ }
+
+ if (!$attrid) {
+ $attrid = $vendormap->{default};
+ }
+
+ foreach my $attr (@$attributes) {
+ next if $attr->{id} != $attrid;
+ $wearout = $attr->{value};
+ last;
+ }
+
+ return $wearout;
+}
+
+sub dir_is_empty {
+ my ($dir) = @_;
+
+ my $dh = IO::Dir->new ($dir);
+ return 1 if !$dh;
+
+ while (defined(my $tmp = $dh->read)) {
+ next if $tmp eq '.' || $tmp eq '..';
+ $dh->close;
+ return 0;
+ }
+ $dh->close;
+ return 1;
+}
+
+sub is_iscsi {
+ my ($sysdir) = @_;
+
+ if (-l $sysdir && readlink($sysdir) =~ m|host[^/]*/session[^/]*|) {
+ return 1;
+ }
+
+ return 0;
+}
+
sub get_disks {
- my ($disk, $nosmart) = @_;
+ my ($disks, $nosmart) = @_;
my $disklist = {};
my $mounted = {};
return $mounted->{$dev};
};
- my $dir_is_empty = sub {
- my ($dir) = @_;
-
- my $dh = IO::Dir->new ($dir);
- return 1 if !$dh;
-
- while (defined(my $tmp = $dh->read)) {
- next if $tmp eq '.' || $tmp eq '..';
- $dh->close;
- return 0;
- }
- $dh->close;
- return 1;
- };
-
my $journalhash = get_ceph_journals();
+ my $ceph_volume_infos = get_ceph_volume_infos();
my $zfslist = get_zfs_devices();
my $lvmlist = get_lvm_devices();
- dir_glob_foreach('/sys/block', '.*', sub {
+ my $disk_regex = ".*";
+ if (defined($disks)) {
+ if (!ref($disks)) {
+ $disks = [ $disks ];
+ } elsif (ref($disks) ne 'ARRAY') {
+ die "disks is not a string or array reference\n";
+ }
+ # we get cciss/c0d0 but need cciss!c0d0
+ map { s|cciss/|cciss!| } @$disks;
+
+ $disk_regex = "(?:" . join('|', @$disks) . ")";
+ }
+
+ dir_glob_foreach('/sys/block', $disk_regex, sub {
my ($dev) = @_;
- return if defined($disk) && $disk ne $dev;
# whitelisting following devices
# hdX: ide block device
# sdX: sd block device
# vdX: virtual block device
# xvdX: xen virtual block device
# nvmeXnY: nvme devices
- # cXnY: cciss devices
+ # cciss!cXnY: cciss devices
return if $dev !~ m/^(h|s|x?v)d[a-z]+$/ &&
$dev !~ m/^nvme\d+n\d+$/ &&
- $dev !~ m/^c\d+d\d+$/;
+ $dev !~ m/^cciss\!c\d+d\d+$/;
- my $data = get_udev_info($dev);
+ my $data = get_udev_info("/sys/block/$dev");
return if !defined($data);
my $devpath = $data->{devpath};
my $sysdir = "/sys/block/$dev";
- return if ! -d "$sysdir/device";
-
# we do not want iscsi devices
- return if readlink($sysdir) =~ m|host[^/]*/session[^/]*|;
+ return if is_iscsi($sysdir);
my $sysdata = get_sysdir_info($sysdir);
return if !defined($sysdata);
}
my $health = 'UNKNOWN';
- my $wearout;
+ my $wearout = 'N/A';
if (!$nosmart) {
eval {
+ my $smartdata = get_smart_data($devpath, ($type ne 'ssd'));
+ $health = $smartdata->{health} if $smartdata->{health};
+
if ($type eq 'ssd') {
# if we have an ssd we try to get the wearout indicator
- $wearout = 'N/A';
- my $smartdata = get_smart_data($devpath);
- $health = $smartdata->{health};
- foreach my $attr (@{$smartdata->{attributes}}) {
- # ID 233 is media wearout indicator on intel and sandisk
- # ID 177 is media wearout indicator on samsung
- next if ($attr->{id} != 233 && $attr->{id} != 177);
- next if ($attr->{name} !~ m/wear/i);
- $wearout = $attr->{value};
-
- # prefer the 233 value
- last if ($attr->{id} == 233);
- }
- } else {
- # else we just get the health
- $health = get_smart_health($devpath);
+ my $wearval = get_wear_leveling_info($smartdata->{attributes}, $data->{model} || $sysdir->{model});
+ $wearout = $wearval if $wearval;
}
};
}
$used = 'ZFS' if $zfslist->{$devpath};
+ # we replaced cciss/ with cciss! above
+ # but in the result we need cciss/ again
+ # because the caller might want to check the
+ # result again with the original parameter
+ if ($dev =~ m|^cciss!|) {
+ $dev =~ s|^cciss!|cciss/|;
+ }
+
$disklist->{$dev} = {
vendor => $sysdata->{vendor},
- model => $sysdata->{model},
+ model => $data->{model} || $sysdata->{model},
size => $sysdata->{size},
serial => $data->{serial},
gpt => $data->{gpt},
};
my $osdid = -1;
+ my $bluestore = 0;
my $journal_count = 0;
+ my $db_count = 0;
+ my $wal_count = 0;
my $found_partitions;
my $found_lvm;
$found_zfs = 1;
}
- $journal_count++ if $journalhash->{"$partpath/$part"};
+ if (my $journal_part = $journalhash->{"$partpath/$part"}) {
+ $journal_count++ if $journal_part == 1;
+ $db_count++ if $journal_part == 2;
+ $wal_count++ if $journal_part == 3;
+ $bluestore = 1 if $journal_part == 4;
+ }
- if (!&$dir_is_empty("$sysdir/$part/holders") && !$found_lvm) {
+ if (!dir_is_empty("$sysdir/$part/holders") && !$found_lvm) {
$found_dm = 1;
}
});
+ if (my $ceph_volume = $ceph_volume_infos->{$devpath}) {
+ $journal_count += $ceph_volume->{journal} // 0;
+ $db_count += $ceph_volume->{db} // 0;
+ $wal_count += $ceph_volume->{wal} // 0;
+ if ($ceph_volume->{osdid}) {
+ $osdid = $ceph_volume->{osdid};
+ $bluestore = 1 if $ceph_volume->{bluestore};
+ }
+ }
+
$used = 'mounted' if $found_mountpoints && !$used;
$used = 'LVM' if $found_lvm && !$used;
$used = 'ZFS' if $found_zfs && !$used;
# multipath, software raid, etc.
# this check comes in last, to show more specific info
# if we have it
- $used = 'Device Mapper' if !$used && !&$dir_is_empty("$sysdir/holders");
+ $used = 'Device Mapper' if !$used && !dir_is_empty("$sysdir/holders");
$disklist->{$dev}->{used} = $used if $used;
$disklist->{$dev}->{osdid} = $osdid;
- $disklist->{$dev}->{journals} = $journal_count;
+ $disklist->{$dev}->{journals} = $journal_count if $journal_count;
+ $disklist->{$dev}->{bluestore} = $bluestore if $osdid != -1;
+ $disklist->{$dev}->{db} = $db_count if $db_count;
+ $disklist->{$dev}->{wal} = $wal_count if $wal_count;
});
return $disklist;
}
+sub get_partnum {
+ my ($part_path) = @_;
+
+ my ($mode, $rdev) = (stat($part_path))[2,6];
+
+ next if !$mode || !S_ISBLK($mode) || !$rdev;
+ my $major = PVE::Tools::dev_t_major($rdev);
+ my $minor = PVE::Tools::dev_t_minor($rdev);
+ my $partnum_path = "/sys/dev/block/$major:$minor/";
+
+ my $partnum;
+
+ $partnum = file_read_firstline("${partnum_path}partition");
+
+ die "Partition does not exists\n" if !defined($partnum);
+
+ #untaint and ensure it is a int
+ if ($partnum =~ m/(\d+)/) {
+ $partnum = $1;
+ die "Partition number $partnum is invalid\n" if $partnum > 128;
+ } else {
+ die "Failed to get partition number\n";
+ }
+
+ return $partnum;
+}
+
+sub get_blockdev {
+ my ($part_path) = @_;
+
+ my $dev = $1 if $part_path =~ m|^/dev/(.*)$|;
+ my $link = readlink "/sys/class/block/$dev";
+ my $block_dev = $1 if $link =~ m|([^/]*)/$dev$|;
+
+ die "Can't parse parent device\n" if !defined($block_dev);
+ die "No valid block device\n" if index($dev, $block_dev) == -1;
+
+ $block_dev = "/dev/$block_dev";
+ die "Block device does not exsists\n" if !(-b $block_dev);
+
+ return $block_dev;
+}
+
+sub locked_disk_action {
+ my ($sub) = @_;
+ my $res = PVE::Tools::lock_file('/run/lock/pve-diskmanage.lck', undef, $sub);
+ die $@ if $@;
+ return $res;
+}
+
+sub assert_disk_unused {
+ my ($dev) = @_;
+
+ die "device '$dev' is already in use\n" if disk_is_used($dev);
+
+ return undef;
+}
+
+sub append_partition {
+ my ($dev, $size) = @_;
+
+ my $devname = $dev;
+ $devname =~ s|^/dev/||;
+
+ my $newpartid = 1;
+ dir_glob_foreach("/sys/block/$devname", qr/\Q$devname\E.*?(\d+)/, sub {
+ my ($part, $partid) = @_;
+
+ if ($partid >= $newpartid) {
+ $newpartid = $partid + 1;
+ }
+ });
+
+ $size = PVE::Tools::convert_size($size, 'b' => 'mb');
+
+ run_command([ $SGDISK, '-n', "$newpartid:0:+${size}M", $dev ],
+ errmsg => "error creating partition '$newpartid' on '$dev'");
+
+ my $partition;
+
+ # loop again to detect the real partiton device which does not always follow
+ # a strict $devname$partition scheme like /dev/nvme0n1 -> /dev/nvme0n1p1
+ dir_glob_foreach("/sys/block/$devname", qr/\Q$devname\E.*$newpartid/, sub {
+ my ($part) = @_;
+
+ $partition = "/dev/$part";
+ });
+
+ return $partition;
+}
+
1;
projects / pve-storage.git / blobdiff