[pve-devel] [PATCH v5 qemu-server 11/12] memory: virtio-mem : implement redispatch retry.

[Alexandre Derumier <aderumier@odiso.com>]

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 3bcdd7c..271c55f 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) {
 
-- 
2.30.2