From 808eb12f8cc61480457e836f9d97e94373f3a644 Mon Sep 17 00:00:00 2001
From: Stefan Hanreich <s.hanreich@proxmox.com>
Date: Mon, 4 Sep 2023 11:18:07 +0200
Subject: [PATCH] api: ceph: improve reporting of ceph OSD memory usage

Currently we are using the MemoryCurrent property of the OSD service
to determine the used memory of a Ceph OSD. This includes, among other
things, the memory used by buffers [1]. Since BlueFS uses buffered
I/O, this can lead to extremely high values shown in the UI.

Instead we are now reading the PSS value from the proc filesystem,
which should more accurately reflect the amount of memory currently
used by the Ceph OSD.

Aaron and I decided on PSS over RSS, since this should give a better
idea of used memory - particularly when using a large amount of OSDs
on one host, since the OSDs share some of the pages.

[1] https://www.kernel.org/doc/Documentation/cgroup-v1/memory.txt

Signed-off-by: Stefan Hanreich <s.hanreich@proxmox.com>
Tested-by: Aaron Lauterer <a.lauterer@proxmox.com>
---
 PVE/API2/Ceph/OSD.pm            | 21 ++++++++++++++++-----
 www/manager6/ceph/OSDDetails.js |  2 +-
 2 files changed, 17 insertions(+), 6 deletions(-)

diff --git a/PVE/API2/Ceph/OSD.pm b/PVE/API2/Ceph/OSD.pm
index ded35990..38980297 100644
--- a/PVE/API2/Ceph/OSD.pm
+++ b/PVE/API2/Ceph/OSD.pm
@@ -687,13 +687,10 @@ __PACKAGE__->register_method ({
 
 	my $raw = '';
 	my $pid;
-	my $memory;
 	my $parser = sub {
 	    my $line = shift;
 	    if ($line =~ m/^MainPID=([0-9]*)$/) {
 		$pid = $1;
-	    } elsif ($line =~ m/^MemoryCurrent=([0-9]*|\[not set\])$/) {
-		$memory = $1 eq "[not set]" ? 0 : $1;
 	    }
 	};
 
@@ -702,12 +699,26 @@ __PACKAGE__->register_method ({
 	    'show',
 	    "ceph-osd\@${osdid}.service",
 	    '--property',
-	    'MainPID,MemoryCurrent',
+	    'MainPID',
 	];
 	run_command($cmd, errmsg => 'fetching OSD PID and memory usage failed', outfunc => $parser);
 
 	$pid = defined($pid) ? int($pid) : undef;
-	$memory = defined($memory) ? int($memory) : undef;
+
+	my $memory = 0;
+	if ($pid && $pid > 0) {
+	    open (my $SMAPS, '<', "/proc/$pid/smaps_rollup")
+		or die "failed to read PSS memory-stat from process - $!\n";
+
+	    while (my $line = <$SMAPS>) {
+		if ($line =~ m/^Pss:\s+([0-9]+) kB$/) {
+		    $memory = $1 * 1024;
+		    last;
+		}
+	    }
+
+	    close $SMAPS;
+	}
 
 	my $data = {
 	    osd => {
diff --git a/www/manager6/ceph/OSDDetails.js b/www/manager6/ceph/OSDDetails.js
index f0765d4f..3b1c1d9c 100644
--- a/www/manager6/ceph/OSDDetails.js
+++ b/www/manager6/ceph/OSDDetails.js
@@ -148,7 +148,7 @@ Ext.define('PVE.CephOsdDetails', {
 				{
 				    xtype: 'text',
 				    name: 'mem_usage',
-				    text: gettext('Memory usage'),
+				    text: gettext('Memory usage (PSS)'),
 				    renderer: Proxmox.Utils.render_size,
 				},
 				{