[pve-devel] [PATCH manager 2/5] api ceph osd: add OSD details endpoint

[Aaron Lauterer]

Adding a GET endpoint to .../ceph/osd/<osdid> that returns various
metadata regarding the OSD.

Such as
* process id
* memory usage
* info about devices used (bdev/block, db, wal)
    * size
    * disks used (sdX)
    ...
* network addresses and ports used
...

Memory usage and PID are retrieved from systemd while the rest can be
retrieved from the metadata provided by Ceph.

Signed-off-by: Aaron Lauterer <a.lauterer at proxmox.com>
---
 PVE/API2/Ceph/OSD.pm | 181 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 181 insertions(+)

diff --git a/PVE/API2/Ceph/OSD.pm b/PVE/API2/Ceph/OSD.pm
index 93433b3a..33b3fdb6 100644
--- a/PVE/API2/Ceph/OSD.pm
+++ b/PVE/API2/Ceph/OSD.pm
@@ -516,6 +516,187 @@ __PACKAGE__->register_method ({
 	return $rpcenv->fork_worker('cephcreateosd', $devs->{dev}->{name},  $authuser, $worker);
     }});
 
+my $OSD_DEV_RETURN_PROPS = {
+    dev_node => {
+	type => 'string',
+	description => 'Device node',
+    },
+    devices => {
+	type => 'string',
+	description => 'Physical disks used',
+    },
+    size => {
+	type => 'integer',
+	description => 'Size in bytes',
+    },
+    support_discard => {
+	type => 'boolean',
+	description => 'Discard support of the physical device',
+    },
+    type => {
+	type => 'string',
+	description => 'Type of device. For example, hdd or ssd',
+    },
+};
+
+__PACKAGE__->register_method ({
+    name => 'osddetails',
+    path => '{osdid}',
+    method => 'GET',
+    description => "Get OSD details",
+    proxyto => 'node',
+    protected => 1,
+    permissions => {
+	check => ['perm', '/', [ 'Sys.Audit', 'Datastore.Audit' ], any => 1],
+    },
+    parameters => {
+	additionalProperties => 0,
+	properties => {
+	    node => get_standard_option('pve-node'),
+	    osdid => {
+		description => 'OSD ID',
+		type => 'integer',
+	    },
+	},
+    },
+    returns => {
+	type => 'object',
+	properties => {
+	    osd => {
+		type => 'object',
+		description => 'General information about the OSD',
+		properties => {
+		    hostname => {
+			type => 'string',
+			description => 'Name of the host containing the OSD.',
+		    },
+		    id => {
+			type => 'integer',
+			description => 'ID of the OSD.',
+		    },
+		    mem_usage => {
+			type => 'integer',
+			description => 'Memory usage of the OSD service.',
+		    },
+		    osd_data => {
+			type => 'string',
+			description => "Path to the OSD's data directory.",
+		    },
+		    osd_objectstore => {
+			type => 'string',
+			description => 'The type of object store used.',
+		    },
+		    pid => {
+			type => 'integer',
+			description => 'OSD process ID.',
+		    },
+		    version => {
+			type => 'string',
+			description => 'Ceph version of the OSD service.',
+		    },
+		    front_addr => {
+			type => 'string',
+			description => 'Address and port used to talk to clients and monitors.',
+		    },
+		    back_addr => {
+			type => 'string',
+			description => 'Address and port used to talk to other OSDs.',
+		    },
+		    hb_front_addr => {
+			type => 'string',
+			description => 'Heartbeat address and port for clients and monitors.',
+		    },
+		    hb_back_addr => {
+			type => 'string',
+			description => 'Heartbeat address and port for other OSDs.',
+		    },
+		},
+	    },
+	    bdev => {
+		type => 'object',
+		description => 'Data about the OSD block device',
+		properties => $OSD_DEV_RETURN_PROPS,
+	    },
+	    db => {
+		type => 'object',
+		description => 'Data about the DB device (optional)',
+		properties => $OSD_DEV_RETURN_PROPS,
+		optional => 1,
+	    },
+	    wal => {
+		type => 'object',
+		description => 'Data about the WAL device (optional)',
+		properties => $OSD_DEV_RETURN_PROPS,
+		optional => 1,
+	    },
+	}
+    },
+    code => sub {
+	my ($param) = @_;
+
+	PVE::Ceph::Tools::check_ceph_inited();
+
+	my $osdid = $param->{osdid};
+	my $rados = PVE::RADOS->new();
+	my $metadata = $rados->mon_command({ prefix => 'osd metadata', id => int($osdid) });
+
+	die "OSD '${osdid}' does not exists on host '${nodename}'\n"
+	    if $nodename ne $metadata->{hostname};
+
+	my $raw = '';
+	my $pid;
+	my $memory;
+	my $parser = sub { $raw .= shift };
+	my $cmd = [
+	    '/bin/systemctl',
+	    'show',
+	    "ceph-osd\@${osdid}.service",
+	    '--property=MainPID,MemoryCurrent'
+	];
+	eval { run_command($cmd, errmsg => 'systemctl show error', outfunc => $parser) };
+	die $@ if $@;
+
+	if ($raw =~ m/^MainPID=([0-9]*)MemoryCurrent=([0-9]*|\[not set\])$/s) { #untaint
+	    $pid = $1;
+	    $memory = $2 eq "[not set]" ? 0 : $2;
+	} else {
+	    die "got unexpected data from systemctl: '${raw}'\n";
+	}
+
+	my $data = {
+	    osd => {
+		hostname => $metadata->{hostname},
+		id => $metadata->{id},
+		mem_usage => int($memory),
+		osd_data => $metadata->{osd_data},
+		osd_objectstore => $metadata->{osd_objectstore},
+		pid => int($pid),
+		version => "$metadata->{ceph_version_short} ($metadata->{ceph_release})",
+		front_addr => $metadata->{front_addr},
+		back_addr => $metadata->{back_addr},
+		hb_front_addr => $metadata->{hb_front_addr},
+		hb_back_addr => $metadata->{hb_back_addr},
+	    },
+	};
+
+	my $get_data = sub {
+	    my ($dev, $prefix) = @_;
+	    $data->{$dev} = {
+		dev_node => $metadata->{"${prefix}_${dev}_dev_node"},
+		devices => $metadata->{"${prefix}_${dev}_devices"},
+		size => int($metadata->{"${prefix}_${dev}_size"}),
+		support_discard => int($metadata->{"${prefix}_${dev}_support_discard"}),
+		type => $metadata->{"${prefix}_${dev}_type"},
+	    };
+	};
+
+	$get_data->("bdev", "bluestore");
+	$get_data->("db", "bluefs") if $metadata->{bluefs_dedicated_db};
+	$get_data->("wal", "bluefs") if $metadata->{bluefs_dedicated_wal};
+
+	return $data;
+    }});
+
 # Check if $osdid belongs to $nodename
 # $tree ... rados osd tree (passing the tree makes it easy to test)
 sub osd_belongs_to_node {
-- 
2.30.2