use PVE::API2::LXC;
use PVE::API2::Qemu;
use PVE::API2::Certificates;
+use PVE::API2::Cluster::Ceph;
use PVE::AccessControl;
use PVE::Ceph::Tools;
use PVE::QemuConfig;
use PVE::QemuServer;
use PVE::VZDump::Common;
+use PVE::LXC;
+use PVE::LXC::Config;
+use PVE::LXC::Setup;
use Term::ANSIColor;
my $min_pve_minor = 4;
my $min_pve_pkgrel = 1;
+my $forced_legacy_cgroup = 0;
+
my $counters = {
pass => 0,
skip => 0,
my $info = PVE::Storage::storage_info($cfg);
- foreach my $storeid (keys %$info) {
+ foreach my $storeid (sort keys %$info) {
my $d = $info->{$storeid};
if ($d->{enabled}) {
if ($d->{type} eq 'sheepdog') {
log_info("getting Ceph status/health information..");
my $ceph_status = eval { PVE::API2::Ceph->status({ node => $nodename }); };
- my $osd_flags = eval { PVE::API2::Ceph->get_flags({ node => $nodename }); };
+ my $noout = eval { PVE::API2::Cluster::Ceph->get_flag({ flag => "noout" }); };
+ if ($@) {
+ log_fail("failed to get 'noout' flag status - $@");
+ }
+
my $noout_wanted = 1;
- my $noout = $osd_flags && $osd_flags =~ m/noout/;
if (!$ceph_status || !$ceph_status->{health}) {
log_fail("unable to determine Ceph status!");
}
}
- log_info("getting Ceph OSD flags..");
- eval {
- if (!$osd_flags) {
- log_fail("unable to get Ceph OSD flags!");
- } else {
- if (!($osd_flags =~ m/recovery_deletes/ && $osd_flags =~ m/purged_snapdirs/)) {
- log_fail("missing 'recovery_deletes' and/or 'purged_snapdirs' flag, scrub of all PGs required before upgrading to Nautilus!");
- }
- }
- };
-
# TODO: check OSD min-required version, if to low it breaks stuff!
log_info("getting Ceph daemon versions..");
log_warn("unable to determine overall Ceph daemon versions!");
} elsif (keys %$overall_versions == 1) {
log_pass("single running overall version detected for all Ceph daemon types.");
- if ((keys %$overall_versions)[0] =~ /^ceph version 15\./) {
- $noout_wanted = 0;
- }
+ $noout_wanted = 1; # off post-upgrade, on pre-upgrade
} else {
log_warn("overall version mismatch detected, check 'ceph versions' output for details!");
}
log_warn("'noout' flag set, Ceph cluster upgrade seems finished.");
}
} elsif ($noout_wanted) {
- log_warn("'noout' flag not set - recommended to prevent rebalancing during upgrades.");
+ log_warn("'noout' flag not set - recommended to prevent rebalancing during cluster-wide upgrades.");
}
log_info("checking Ceph config..");
my $global_monhost = $global->{mon_host} // $global->{"mon host"} // $global->{"mon-host"};
if (!defined($global_monhost)) {
log_warn("No 'mon_host' entry found in ceph config.\n It's recommended to add mon_host with all monitor addresses (without ports) to the global section.");
- } else {
- log_pass("Found 'mon_host' entry.");
}
my $ipv6 = $global->{ms_bind_ipv6} // $global->{"ms bind ipv6"} // $global->{"ms-bind-ipv6"};
my $ipv4 = $global->{ms_bind_ipv4} // $global->{"ms bind ipv4"} // $global->{"ms-bind-ipv4"};
if ($ipv6 eq 'true' && (!defined($ipv4) || $ipv4 ne 'false')) {
log_warn("'ms_bind_ipv6' is enabled but 'ms_bind_ipv4' is not disabled.\n Make sure to disable 'ms_bind_ipv4' for ipv6 only clusters, or add an ipv4 network to public/cluster network.");
- } else {
- log_pass("'ms_bind_ipv6' is enabled and 'ms_bind_ipv4' disabled");
}
- } else {
- log_pass("'ms_bind_ipv6' not enabled");
}
if (defined($global->{keyring})) {
log_warn("[global] config section contains 'keyring' option, which will prevent services from starting with Nautilus.\n Move 'keyring' option to [client] section instead.");
- } else {
- log_pass("no 'keyring' option in [global] section found.");
}
} else {
my $local_ceph_ver = PVE::Ceph::Tools::get_local_version(1);
if (defined($local_ceph_ver)) {
- if ($local_ceph_ver == 14) {
- my $ceph_volume_osds = PVE::Ceph::Tools::ceph_volume_list();
- my $scanned_osds = PVE::Tools::dir_glob_regex('/etc/ceph/osd', '^.*\.json$');
- if (-e '/var/lib/ceph/osd/' && !defined($scanned_osds) && !(keys %$ceph_volume_osds)) {
- log_warn("local Ceph version is Nautilus, local OSDs detected, but no conversion from ceph-disk to ceph-volume done (yet).");
- }
+ if ($local_ceph_ver <= 14) {
+ log_fail("local Ceph version too low, at least Octopus required..");
}
} else {
log_fail("unable to determine local Ceph version.");
log_warn($warning) if defined($raw) && length($raw) > $max_length;
}
-sub check_description_lengths {
+sub check_node_and_guest_configurations {
log_info("Checking node and guest description/note legnth..");
my @affected_nodes = grep {
log_pass("All node config descriptions fit in the new limit of 64 KiB");
}
- my $affected_guests = [];
+ my $affected_guests_long_desc = [];
+ my $affected_cts_cgroup_keys = [];
my $cts = PVE::LXC::config_list();
for my $vmid (sort { $a <=> $b } keys %$cts) {
- my $desc = PVE::LXC::Config->load_config($vmid)->{description};
- push @$affected_guests, "CT $vmid" if defined($desc) && length($desc) > 8 * 1024;
+ my $conf = PVE::LXC::Config->load_config($vmid);
+
+ my $desc = $conf->{description};
+ push @$affected_guests_long_desc, "CT $vmid" if defined($desc) && length($desc) > 8 * 1024;
+
+ my $lxc_raw_conf = $conf->{lxc};
+ push @$affected_cts_cgroup_keys, "CT $vmid" if (grep (@$_[0] =~ /^lxc\.cgroup\./, @$lxc_raw_conf));
}
my $vms = PVE::QemuServer::config_list();
for my $vmid (sort { $a <=> $b } keys %$vms) {
my $desc = PVE::QemuConfig->load_config($vmid)->{description};
- push @$affected_guests, "VM $vmid" if defined($desc) && length($desc) > 8 * 1024;
+ push @$affected_guests_long_desc, "VM $vmid" if defined($desc) && length($desc) > 8 * 1024;
}
- if (scalar($affected_guests->@*) > 0) {
+ if (scalar($affected_guests_long_desc->@*) > 0) {
log_warn("Guest config description of the following virtual-guests too long for new limit of 64 KiB:\n"
- ." * " . join("\n * ", $affected_guests->@*));
+ ." " . join(", ", $affected_guests_long_desc->@*));
} else {
log_pass("All guest config descriptions fit in the new limit of 8 KiB");
}
+
+ log_info("Checking container configs for deprecated lxc.cgroup entries");
+
+ if (scalar($affected_cts_cgroup_keys->@*) > 0) {
+ if ($forced_legacy_cgroup) {
+ log_pass("Found legacy 'lxc.cgroup' keys, but system explicitly configured for legacy hybrid cgroup hierarchy.");
+ } else {
+ log_warn("The following CTs have 'lxc.cgroup' keys configured, which will be ignored in the new default unified cgroupv2:\n"
+ ." " . join(", ", $affected_cts_cgroup_keys->@*) ."\n"
+ ." Often it can be enough to change to the new 'lxc.cgroup2' prefix after the upgrade to Proxmox VE 7.x");
+ }
+ } else {
+ log_pass("No legacy 'lxc.cgroup' keys found.");
+ }
}
sub check_storage_content {
log_info("Checking storage content type configuration..");
- my $found_referenced;
- my $found_unreferenced;
+ my $found;
my $pass = 1;
my $storage_cfg = PVE::Storage::config();
- my $potentially_affected = {};
- my $referenced_volids = {};
-
- for my $storeid (keys $storage_cfg->{ids}->%*) {
+ for my $storeid (sort keys $storage_cfg->{ids}->%*) {
my $scfg = $storage_cfg->{ids}->{$storeid};
+ next if $scfg->{shared};
next if !PVE::Storage::storage_check_enabled($storage_cfg, $storeid, undef, 1);
my $valid_content = PVE::Storage::Plugin::valid_content_types($scfg->{type});
delete $scfg->{content}->{none}; # scan for guest images below
}
- next if $scfg->{content}->{images} && $scfg->{content}->{rootdir};
+ next if $scfg->{content}->{images};
+ next if $scfg->{content}->{rootdir};
# Skip 'iscsi(direct)' (and foreign plugins with potentially similiar behavior) with 'none',
# because that means "use LUNs directly" and vdisk_list() in PVE 6.x still lists those.
}
my @volids = map { $_->{volid} } $res->{$storeid}->@*;
- for my $volid (@volids) {
- $potentially_affected->{$volid} = 1;
- }
-
my $number = scalar(@volids);
- if ($number > 0 && !$scfg->{content}->{images} && !$scfg->{content}->{rootdir}) {
+ if ($number > 0) {
log_info("storage '$storeid' - neither content type 'images' nor 'rootdir' configured"
.", but found $number guest volume(s)");
}
my $check_volid = sub {
my ($volid, $vmid, $vmtype, $reference) = @_;
- $referenced_volids->{$volid} = 1 if $reference ne 'unreferenced';
-
my $guesttext = $vmtype eq 'qemu' ? 'VM' : 'CT';
my $prefix = "$guesttext $vmid - volume '$volid' ($reference)";
}
if (!$scfg->{content}->{$vtype}) {
- $found_referenced = 1 if $reference ne 'unreferenced';
- $found_unreferenced = 1 if $reference eq 'unreferenced';
+ $found = 1;
$pass = 0;
log_warn("$prefix - storage does not have content type '$vtype' configured.");
}
};
- my $guests = {};
-
my $cts = PVE::LXC::config_list();
for my $vmid (sort { $a <=> $b } keys %$cts) {
- $guests->{$vmid} = 'lxc';
-
my $conf = PVE::LXC::Config->load_config($vmid);
my $volhash = {};
my $vms = PVE::QemuServer::config_list();
for my $vmid (sort { $a <=> $b } keys %$vms) {
- $guests->{$vmid} = 'qemu';
-
my $conf = PVE::QemuConfig->load_config($vmid);
my $volhash = {};
}
}
- if ($found_referenced) {
+ if ($found) {
log_warn("Proxmox VE 7.0 enforces stricter content type checks. The guests above " .
"might not work until the storage configuration is fixed.");
}
- for my $volid (sort keys $potentially_affected->%*) {
- next if $referenced_volids->{$volid}; # already checked
+ if ($pass) {
+ log_pass("no problems found");
+ }
+}
- my (undef, undef, $vmid) = PVE::Storage::parse_volname($storage_cfg, $volid);
- my $vmtype = $guests->{$vmid};
- next if !$vmtype;
+sub check_containers_cgroup_compat {
+ if ($forced_legacy_cgroup) {
+ log_skip("System explicitly configured for legacy hybrid cgroup hierarchy.");
+ return;
+ }
+
+ my $supports_cgroupv2 = sub {
+ my ($conf, $rootdir, $ctid) = @_;
+
+ my $get_systemd_version = sub {
+ my ($self) = @_;
+
+ my $sd_lib_dir = -d "/lib/systemd" ? "/lib/systemd" : "/usr/lib/systemd";
+ my $libsd = PVE::Tools::dir_glob_regex($sd_lib_dir, "libsystemd-shared-.+\.so");
+ if (defined($libsd) && $libsd =~ /libsystemd-shared-(\d+)\.so/) {
+ return $1;
+ }
+
+ return undef;
+ };
+
+ my $unified_cgroupv2_support = sub {
+ my ($self) = @_;
+
+ # https://www.freedesktop.org/software/systemd/man/systemd.html
+ # systemd is installed as symlink to /sbin/init
+ my $systemd = CORE::readlink('/sbin/init');
+
+ # assume non-systemd init will run with unified cgroupv2
+ if (!defined($systemd) || $systemd !~ m@/systemd$@) {
+ return 1;
+ }
+
+ # systemd version 232 (e.g. debian stretch) supports the unified hierarchy
+ my $sdver = $get_systemd_version->();
+ if (!defined($sdver) || $sdver < 232) {
+ return 0;
+ }
+
+ return 1;
+ };
+
+ my $ostype = $conf->{ostype};
+ if (!defined($ostype)) {
+ log_warn("Found CT ($ctid) without 'ostype' set!");
+ } elsif ($ostype eq 'devuan' || $ostype eq 'alpine') {
+ return 1; # no systemd, no cgroup problems
+ }
+
+ my $lxc_setup = PVE::LXC::Setup->new($conf, $rootdir);
+ return $lxc_setup->protected_call($unified_cgroupv2_support);
+ };
+
+ my $log_problem = sub {
+ my ($ctid) = @_;
+ log_warn("Found at least one CT ($ctid) which does not support running in a unified cgroup v2" .
+ " layout.\n Either upgrade the Container distro or set systemd.unified_cgroup_hierarchy=0 " .
+ "in the Proxmox VE hosts' kernel cmdline! Skipping further CT compat checks."
+ );
+ };
- $check_volid->($volid, $vmid, $vmtype, 'unreferenced');
+ my $cts = eval { PVE::API2::LXC->vmlist({ node => $nodename }) };
+ if ($@) {
+ log_warn("Failed to retrieve information about this node's CTs - $@");
+ return;
}
- if ($found_unreferenced) {
- log_warn("When migrating, Proxmox VE 7.0 only scans storages with the appropriate " .
- "content types for unreferenced guest volumes.");
+ if (!defined($cts) || !scalar(@$cts)) {
+ log_skip("No containers on node detected.");
+ return;
}
- if ($pass) {
- log_pass("no problems found");
+ my @running_cts = sort { $a <=> $b } grep { $_->{status} eq 'running' } @$cts;
+ my @offline_cts = sort { $a <=> $b } grep { $_->{status} ne 'running' } @$cts;
+
+ for my $ct (@running_cts) {
+ my $ctid = $ct->{vmid};
+ my $pid = eval { PVE::LXC::find_lxc_pid($ctid) };
+ if (my $err = $@) {
+ log_warn("Failed to get PID for running CT $ctid - $err");
+ next;
+ }
+ my $rootdir = "/proc/$pid/root";
+ my $conf = PVE::LXC::Config->load_config($ctid);
+
+ my $ret = eval { $supports_cgroupv2->($conf, $rootdir, $ctid) };
+ if (my $err = $@) {
+ log_warn("Failed to get cgroup support status for CT $ctid - $err");
+ next;
+ }
+ if (!$ret) {
+ $log_problem->($ctid);
+ return;
+ }
+ }
+
+ my $storage_cfg = PVE::Storage::config();
+ for my $ct (@offline_cts) {
+ my $ctid = $ct->{vmid};
+ my ($conf, $rootdir, $ret);
+ eval {
+ $conf = PVE::LXC::Config->load_config($ctid);
+ $rootdir = PVE::LXC::mount_all($ctid, $storage_cfg, $conf);
+ $ret = $supports_cgroupv2->($conf, $rootdir, $ctid);
+ };
+ if (my $err = $@) {
+ log_warn("Failed to load config and mount CT $ctid - $err");
+ eval { PVE::LXC::umount_all($ctid, $storage_cfg, $conf) };
+ next;
+ }
+ if (!$ret) {
+ $log_problem->($ctid);
+ eval { PVE::LXC::umount_all($ctid, $storage_cfg, $conf) };
+ last;
+ }
+
+ eval { PVE::LXC::umount_all($ctid, $storage_cfg, $conf) };
+ }
+};
+
+sub check_security_repo {
+ log_info("Checking if the suite for the Debian security repository is correct..");
+
+ my $found = 0;
+
+ my $dir = '/etc/apt/sources.list.d';
+ my $in_dir = 0;
+
+ my $check_file = sub {
+ my ($file) = @_;
+
+ $file = "${dir}/${file}" if $in_dir;
+
+ my $raw = eval { PVE::Tools::file_get_contents($file) };
+ return if !defined($raw);
+ my @lines = split(/\n/, $raw);
+
+ my $number = 0;
+ for my $line (@lines) {
+ $number++;
+
+ next if length($line) == 0; # split would result in undef then...
+
+ ($line) = split(/#/, $line);
+
+ next if $line !~ m/^deb[[:space:]]/; # is case sensitive
+
+ my $suite;
+
+ # catch any of
+ # https://deb.debian.org/debian-security
+ # http://security.debian.org/debian-security
+ # http://security.debian.org/
+ if ($line =~ m|https?://deb\.debian\.org/debian-security/?\s+(\S*)|i) {
+ $suite = $1;
+ } elsif ($line =~ m|https?://security\.debian\.org(?:.*?)\s+(\S*)|i) {
+ $suite = $1;
+ } else {
+ next;
+ }
+
+ $found = 1;
+
+ my $where = "in ${file}:${number}";
+
+ if ($suite eq 'buster/updates') {
+ log_info("Make sure to change the suite of the Debian security repository " .
+ "from 'buster/updates' to 'bullseye-security' - $where");
+ } elsif ($suite eq 'bullseye-security') {
+ log_pass("already using 'bullseye-security'");
+ } else {
+ log_fail("The new suite of the Debian security repository should be " .
+ "'bullseye-security' - $where");
+ }
+ }
+ };
+
+ $check_file->("/etc/apt/sources.list");
+
+ $in_dir = 1;
+
+ PVE::Tools::dir_glob_foreach($dir, '^.*\.list$', $check_file);
+
+ if (!$found) {
+ # only warn, it might be defined in a .sources file or in a way not catched above
+ log_warn("No Debian security repository detected in /etc/apt/sources.list and " .
+ "/etc/apt/sources.list.d/*.list");
}
}
check_backup_retention_settings();
check_cifs_credential_location();
check_custom_pool_roles();
- check_description_lengths();
+ check_node_and_guest_configurations();
check_storage_content();
+ check_security_repo();
}
__PACKAGE__->register_method ({
parameters => {
additionalProperties => 0,
properties => {
+ full => {
+ description => 'perform additional, expensive checks.',
+ type => 'boolean',
+ optional => 1,
+ default => 0,
+ },
},
},
returns => { type => 'null' },
code => sub {
my ($param) = @_;
+ my $kernel_cli = PVE::Tools::file_get_contents('/proc/cmdline');
+ if ($kernel_cli =~ /systemd.unified_cgroup_hierarchy=0/){
+ $forced_legacy_cgroup = 1;
+ }
+
check_pve_packages();
check_cluster_corosync();
check_ceph();
check_storage_health();
check_misc();
+ if ($param->{full}) {
+ check_containers_cgroup_compat();
+ } else {
+ log_skip("NOTE: Expensive checks, like CT cgroupv2 compat, not performed without '--full' parameter");
+ }
+
print_header("SUMMARY");
my $total = 0;
our $cmddef = [ __PACKAGE__, 'checklist', [], {}];
-# for now drop all unknown params and just check
-@ARGV = ();
-
1;