[PATCH manager 3/5] ceph: add require_osd_release upgrade check

[Kefu Chai <k.chai@proxmox.com>]

Add a get_osd_dump() helper in PVE::Ceph::Tools that wraps the
'osd dump' mon command, and use it to implement a new advisory check
in PVE::Ceph::UpgradeCheck: require_osd_release.

The check warns if require_osd_release is unset or older than the
currently installed Ceph release on the node, and suggests running
'ceph osd require-osd-release <codename>' once all OSDs are upgraded.
Not setting this flag blocks a number of features that the OSDs would
otherwise support.

See
https://docs.ceph.com/en/latest/rados/operations/require-osd-release/

Signed-off-by: Kefu Chai <k.chai@proxmox.com>
---
 PVE/Ceph/Releases.pm     | 14 ++++++++++
 PVE/Ceph/Tools.pm        |  6 +++++
 PVE/Ceph/UpgradeCheck.pm | 57 +++++++++++++++++++++++++++++++++++++++-
 3 files changed, 76 insertions(+), 1 deletion(-)

diff --git a/PVE/Ceph/Releases.pm b/PVE/Ceph/Releases.pm
index 324fcfaf..7eabda60 100644
--- a/PVE/Ceph/Releases.pm
+++ b/PVE/Ceph/Releases.pm
@@ -131,6 +131,20 @@ sub get_available_ceph_release_codenames($include_unstable_releases = 0) {
 
 my $_default_ceph_release_codename;
 
+# Return the codename (e.g. 'squid') whose major release matches $major,
+# searching all Ceph releases tracked in this module (i.e., not restricted
+# to releases available on the current PVE version). Returns undef if no
+# release matches. The inverse of looking up the major from
+# get_ceph_release_info($codename).
+sub get_codename_for_major_release($major) {
+    my $releases = get_ceph_release_def();
+    for my $codename (keys $releases->%*) {
+        my ($release_major) = split(/\./, $releases->{$codename}->{release});
+        return $codename if $release_major == $major;
+    }
+    return undef;
+}
+
 sub get_default_ceph_release_codename {
     if (!defined($_default_ceph_release_codename)) {
         my $ceph_releases = get_all_available_ceph_releases();
diff --git a/PVE/Ceph/Tools.pm b/PVE/Ceph/Tools.pm
index c731ac14..4edc967b 100644
--- a/PVE/Ceph/Tools.pm
+++ b/PVE/Ceph/Tools.pm
@@ -112,6 +112,12 @@ sub get_cluster_versions {
     return $rados->mon_command({ prefix => $cmd });
 }
 
+sub get_osd_dump {
+    my ($rados) = @_;
+    $rados = PVE::RADOS->new() if !$rados;
+    return $rados->mon_command({ prefix => 'osd dump', format => 'json' });
+}
+
 sub get_config {
     my $key = shift;
 
diff --git a/PVE/Ceph/UpgradeCheck.pm b/PVE/Ceph/UpgradeCheck.pm
index 6998caf2..5c454fd1 100644
--- a/PVE/Ceph/UpgradeCheck.pm
+++ b/PVE/Ceph/UpgradeCheck.pm
@@ -13,6 +13,7 @@ use warnings;
 
 use PVE::API2::Ceph;
 use PVE::API2::Cluster::Ceph;
+use PVE::Ceph::Releases;
 use PVE::Ceph::Tools;
 use PVE::Cluster;
 
@@ -50,7 +51,7 @@ sub run_checks {
     my ($health_msgs, $noout) = check_health($nodename);
     push @messages, $health_msgs->@*;
 
-    # TODO: check OSD min-required version, if to low it breaks stuff!
+    push @messages, check_require_osd_release($supported_release)->@*;
 
     my ($version_msgs, $noout_wanted) = check_versions($supported_release, $upgraded);
     push @messages, $version_msgs->@*;
@@ -339,4 +340,58 @@ sub check_local_version_minimum {
     return \@out;
 }
 
+# returns the numeric release value (e.g. 19.2) for a given codename, or undef
+# if the codename is not known to PVE::Ceph::Releases.
+my sub release_number {
+    my ($codename) = @_;
+    return undef if !$codename;
+    my $info = PVE::Ceph::Releases::get_ceph_release_info($codename);
+    return $info ? $info->{release} : undef;
+}
+
+sub check_require_osd_release {
+    my ($supported_release) = @_;
+
+    my @out;
+
+    my $osdmap = eval { PVE::Ceph::Tools::get_osd_dump() };
+    if ($@ || !$osdmap) {
+        my $err = $@ || 'empty osd dump';
+        push @out, { level => 'warn', msg => "could not query osd dump: $err" };
+        return \@out;
+    }
+
+    my $current = $osdmap->{require_osd_release} // '';
+    if (!$current) {
+        push @out,
+            {
+                level => 'warn',
+                msg => "require_osd_release is not set. Run"
+                . " 'ceph osd require-osd-release <codename>' after all OSDs are upgraded to"
+                . " the new release.",
+            };
+        return \@out;
+    }
+
+    my $expected_codename = PVE::Ceph::Releases::get_codename_for_major_release($supported_release)
+        // PVE::Ceph::Releases::get_default_ceph_release_codename();
+    my $expected_release = release_number($expected_codename);
+    my $current_release = release_number($current);
+
+    if (!defined($current_release) || $current_release < $expected_release) {
+        push @out,
+            {
+                level => 'warn',
+                msg => "require_osd_release is '$current', older than '$expected_codename'."
+                . " Once all OSDs are upgraded, run"
+                . " 'ceph osd require-osd-release $expected_codename' to unlock features"
+                . " that depend on the newer release.",
+            };
+    } else {
+        push @out, { level => 'pass', msg => "require_osd_release is at '$current'." };
+    }
+
+    return \@out;
+}
+
 1;
-- 
2.47.3