From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <root@kvmformation3.odiso.net>
Received: from firstgate.proxmox.com (firstgate.proxmox.com [212.224.123.68])
 (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits)
 key-exchange X25519 server-signature RSA-PSS (2048 bits))
 (No client certificate requested)
 by lists.proxmox.com (Postfix) with ESMTPS id 5E584A25C7
 for <pve-devel@lists.proxmox.com>; Mon, 19 Jun 2023 09:29:27 +0200 (CEST)
Received: from firstgate.proxmox.com (localhost [127.0.0.1])
 by firstgate.proxmox.com (Proxmox) with ESMTP id 2585B25404
 for <pve-devel@lists.proxmox.com>; Mon, 19 Jun 2023 09:28:57 +0200 (CEST)
Received: from bastionodiso.odiso.net (bastionodiso.odiso.net [185.151.191.93])
 (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits)
 key-exchange X25519 server-signature RSA-PSS (2048 bits))
 (No client certificate requested)
 by firstgate.proxmox.com (Proxmox) with ESMTPS
 for <pve-devel@lists.proxmox.com>; Mon, 19 Jun 2023 09:28:54 +0200 (CEST)
Received: from kvmformation3.odiso.net (formationkvm3.odiso.net [10.3.94.12])
 by bastionodiso.odiso.net (Postfix) with ESMTP id 6BE9E7BB8;
 Mon, 19 Jun 2023 09:28:45 +0200 (CEST)
Received: by kvmformation3.odiso.net (Postfix, from userid 0)
 id 6AC3C24149C; Mon, 19 Jun 2023 09:28:45 +0200 (CEST)
From: Alexandre Derumier <aderumier@odiso.com>
To: pve-devel@lists.proxmox.com
Date: Mon, 19 Jun 2023 09:28:40 +0200
Message-Id: <20230619072841.38531-12-aderumier@odiso.com>
X-Mailer: git-send-email 2.39.2
In-Reply-To: <20230619072841.38531-1-aderumier@odiso.com>
References: <20230619072841.38531-1-aderumier@odiso.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
X-SPAM-LEVEL: Spam detection results:  0
 AWL 0.036 Adjusted score from AWL reputation of From: address
 BAYES_00                 -1.9 Bayes spam probability is 0 to 1%
 DMARC_MISSING             0.1 Missing DMARC policy
 HEADER_FROM_DIFFERENT_DOMAINS 0.25 From and EnvelopeFrom 2nd level mail
 domains are different
 KAM_DMARC_STATUS 0.01 Test Rule for DKIM or SPF Failure with Strict Alignment
 KAM_LAZY_DOMAIN_SECURITY 1 Sending domain does not have any anti-forgery
 methods
 SPF_HELO_NONE           0.001 SPF: HELO does not publish an SPF Record
 SPF_NONE                0.001 SPF: sender does not publish an SPF Record
 T_SCC_BODY_TEXT_LINE    -0.01 -
Subject: [pve-devel] [PATCH v6 qemu-server 09/10] memory: virtio-mem :
 implement redispatch retry.
X-BeenThere: pve-devel@lists.proxmox.com
X-Mailman-Version: 2.1.29
Precedence: list
List-Id: Proxmox VE development discussion <pve-devel.lists.proxmox.com>
List-Unsubscribe: <https://lists.proxmox.com/cgi-bin/mailman/options/pve-devel>, 
 <mailto:pve-devel-request@lists.proxmox.com?subject=unsubscribe>
List-Archive: <http://lists.proxmox.com/pipermail/pve-devel/>
List-Post: <mailto:pve-devel@lists.proxmox.com>
List-Help: <mailto:pve-devel-request@lists.proxmox.com?subject=help>
List-Subscribe: <https://lists.proxmox.com/cgi-bin/mailman/listinfo/pve-devel>, 
 <mailto:pve-devel-request@lists.proxmox.com?subject=subscribe>
X-List-Received-Date: Mon, 19 Jun 2023 07:29:27 -0000

If some memory can be removed on a specific node,
we try to rebalance again on other nodes

Signed-off-by: Alexandre Derumier <aderumier@odiso.com>
---
 PVE/QemuServer/Memory.pm | 59 +++++++++++++++++++++++++++++-----------
 1 file changed, 43 insertions(+), 16 deletions(-)

diff --git a/PVE/QemuServer/Memory.pm b/PVE/QemuServer/Memory.pm
index dcdf318..86ab16b 100644
--- a/PVE/QemuServer/Memory.pm
+++ b/PVE/QemuServer/Memory.pm
@@ -203,13 +203,32 @@ my sub get_virtiomem_total_current_size {
     return $size;
 }
 
+my sub get_virtiomem_total_errors_size {
+    my ($mems) = @_;
+
+    my $size = 0;
+    for my $mem (values %$mems) {
+	next if !$mem->{error};
+	$size += $mem->{current};
+    }
+    return $size;
+}
+
 my sub balance_virtiomem {
     my ($vmid, $virtiomems, $blocksize, $target_total) = @_;
 
-    my $nb_virtiomem = scalar(keys %$virtiomems);
+    my $nb_virtiomem = scalar(grep { !$_->{error} } values $virtiomems->%*);
 
     print"try to balance memory on $nb_virtiomem virtiomems\n";
 
+    my $target_total_err = undef;
+    if($target_total < 0) {
+	$target_total = 0;
+	$target_total_err = 1;
+    }
+
+    die "No more virtiomem devices left to try to balance the remaining memory\n" if $nb_virtiomem == 0;
+
     #if we can't share exactly the same amount, we add the remainder on last node
     my $target_aligned = int( $target_total / $nb_virtiomem / $blocksize) * $blocksize;
     my $target_remaining = $target_total - ($target_aligned * ($nb_virtiomem-1));
@@ -217,6 +236,7 @@ my sub balance_virtiomem {
     my $i = 0;
     foreach my $id (sort keys %$virtiomems) {
 	my $virtiomem = $virtiomems->{$id};
+	next if $virtiomem->{error};
 	$i++;
 	my $virtiomem_target = $i == $nb_virtiomem ? $target_remaining : $target_aligned;
 	$virtiomem->{completed} = 0;
@@ -234,7 +254,6 @@ my sub balance_virtiomem {
     }
 
     my $total_finished = 0;
-    my $error = undef;
 
     while ($total_finished != $nb_virtiomem) {
 
@@ -258,6 +277,7 @@ my sub balance_virtiomem {
 	    if($virtiomem->{current} == $virtiomem->{target}) {
 		print"virtiomem$id: completed\n";
 		$virtiomem->{completed} = 1;
+		$virtiomem->{last} = $virtiomem->{current};
 		next;
 	    }
 
@@ -271,7 +291,6 @@ my sub balance_virtiomem {
 	    if($virtiomem->{retry} >= 5) {
 		print "virtiomem$id: target memory still not reached, ignoring device from now on\n";
 		$virtiomem->{error} = 1;
-		$error = 1;
 		#as change is async, we don't want that value change after the api call
 		eval {
 		    mon_cmd(
@@ -286,7 +305,9 @@ my sub balance_virtiomem {
 	    $virtiomem->{retry}++;
 	}
     }
-    die "No more available blocks in virtiomem to balance all requested memory\n" if $error;
+
+    die "No more virtiomem devices left to try to balance the remaining memory\n"
+	if $target_total_err;
 }
 
 sub get_numa_node_list {
@@ -392,18 +413,24 @@ sub qemu_memory_hotplug {
 	    };
 	}
 
-	my $target_total = $value - $static_memory;
-	my $err;
-	eval {
-	    balance_virtiomem($vmid, $virtiomems, $blocksize, $target_total);
-	};
-	$err = $@ if $@;
-
-	my $current_memory = $static_memory + get_virtiomem_total_current_size($virtiomems);
-	$newmem->{current} = $current_memory;
-	$conf->{memory} = print_memory($newmem);
-	PVE::QemuConfig->write_config($vmid, $conf);
-	die $err if $err;
+	while (1) {
+
+	    my $target_total = $value - $static_memory - get_virtiomem_total_errors_size($virtiomems);
+	    my $err;
+	    eval {
+		balance_virtiomem($vmid, $virtiomems, $blocksize, $target_total);
+	    };
+	    $err = $@ if $@;
+
+	    my $current_memory = $static_memory + get_virtiomem_total_current_size($virtiomems);
+	    $newmem->{current} = $current_memory;
+	    $conf->{memory} = print_memory($newmem);
+	    PVE::QemuConfig->write_config($vmid, $conf);
+
+	    die $err if $err;
+	    last if $current_memory == $value;
+	}
+	return $conf->{memory};
 
     } elsif ($value > $memory) {
 
-- 
2.39.2