[pve-devel] [PATCH v5 qemu-server 1/3] migration: move livemigration code in a dedicated sub
Alexandre Derumier
aderumier at odiso.com
Thu Oct 26 10:57:08 CEST 2023
Signed-off-by: Alexandre Derumier <aderumier at odiso.com>
---
PVE/QemuMigrate.pm | 420 +++++++++++++++++++++++----------------------
1 file changed, 214 insertions(+), 206 deletions(-)
diff --git a/PVE/QemuMigrate.pm b/PVE/QemuMigrate.pm
index 111eeb0..7dd3455 100644
--- a/PVE/QemuMigrate.pm
+++ b/PVE/QemuMigrate.pm
@@ -728,6 +728,219 @@ sub cleanup_bitmaps {
}
}
+sub live_migration {
+ my ($self, $vmid, $migrate_uri, $spice_port) = @_;
+
+ my $conf = $self->{vmconf};
+
+ $self->log('info', "starting online/live migration on $migrate_uri");
+ $self->{livemigration} = 1;
+
+ # load_defaults
+ my $defaults = PVE::QemuServer::load_defaults();
+
+ $self->log('info', "set migration capabilities");
+ eval { PVE::QemuServer::set_migration_caps($vmid) };
+ warn $@ if $@;
+
+ my $qemu_migrate_params = {};
+
+ # migrate speed can be set via bwlimit (datacenter.cfg and API) and via the
+ # migrate_speed parameter in qm.conf - take the lower of the two.
+ my $bwlimit = $self->get_bwlimit();
+
+ my $migrate_speed = $conf->{migrate_speed} // 0;
+ $migrate_speed *= 1024; # migrate_speed is in MB/s, bwlimit in KB/s
+
+ if ($bwlimit && $migrate_speed) {
+ $migrate_speed = ($bwlimit < $migrate_speed) ? $bwlimit : $migrate_speed;
+ } else {
+ $migrate_speed ||= $bwlimit;
+ }
+ $migrate_speed ||= ($defaults->{migrate_speed} || 0) * 1024;
+
+ if ($migrate_speed) {
+ $migrate_speed *= 1024; # qmp takes migrate_speed in B/s.
+ $self->log('info', "migration speed limit: ". render_bytes($migrate_speed, 1) ."/s");
+ } else {
+ # always set migrate speed as QEMU default to 128 MiBps == 1 Gbps, use 16 GiBps == 128 Gbps
+ $migrate_speed = (16 << 30);
+ }
+ $qemu_migrate_params->{'max-bandwidth'} = int($migrate_speed);
+
+ my $migrate_downtime = $defaults->{migrate_downtime};
+ $migrate_downtime = $conf->{migrate_downtime} if defined($conf->{migrate_downtime});
+ # migrate-set-parameters expects limit in ms
+ $migrate_downtime *= 1000;
+ $self->log('info', "migration downtime limit: $migrate_downtime ms");
+ $qemu_migrate_params->{'downtime-limit'} = int($migrate_downtime);
+
+ # set cachesize to 10% of the total memory
+ my $memory = get_current_memory($conf->{memory});
+ my $cachesize = int($memory * 1048576 / 10);
+ $cachesize = round_powerof2($cachesize);
+
+ $self->log('info', "migration cachesize: " . render_bytes($cachesize, 1));
+ $qemu_migrate_params->{'xbzrle-cache-size'} = int($cachesize);
+
+ $self->log('info', "set migration parameters");
+ eval {
+ mon_cmd($vmid, "migrate-set-parameters", %{$qemu_migrate_params});
+ };
+ $self->log('info', "migrate-set-parameters error: $@") if $@;
+
+ if (PVE::QemuServer::vga_conf_has_spice($conf->{vga}) && !$self->{opts}->{remote}) {
+ my $rpcenv = PVE::RPCEnvironment::get();
+ my $authuser = $rpcenv->get_user();
+
+ my (undef, $proxyticket) = PVE::AccessControl::assemble_spice_ticket($authuser, $vmid, $self->{node});
+
+ my $filename = "/etc/pve/nodes/$self->{node}/pve-ssl.pem";
+ my $subject = PVE::AccessControl::read_x509_subject_spice($filename);
+
+ $self->log('info', "spice client_migrate_info");
+
+ eval {
+ mon_cmd($vmid, "client_migrate_info", protocol => 'spice',
+ hostname => $proxyticket, 'port' => 0, 'tls-port' => $spice_port,
+ 'cert-subject' => $subject);
+ };
+ $self->log('info', "client_migrate_info error: $@") if $@;
+
+ }
+
+ my $start = time();
+
+ $self->log('info', "start migrate command to $migrate_uri");
+ eval {
+ mon_cmd($vmid, "migrate", uri => $migrate_uri);
+ };
+ my $merr = $@;
+ $self->log('info', "migrate uri => $migrate_uri failed: $merr") if $merr;
+
+ my $last_mem_transferred = 0;
+ my $usleep = 1000000;
+ my $i = 0;
+ my $err_count = 0;
+ my $lastrem = undef;
+ my $downtimecounter = 0;
+ while (1) {
+ $i++;
+ my $avglstat = $last_mem_transferred ? $last_mem_transferred / $i : 0;
+
+ usleep($usleep);
+
+ my $stat = eval { mon_cmd($vmid, "query-migrate") };
+ if (my $err = $@) {
+ $err_count++;
+ warn "query migrate failed: $err\n";
+ $self->log('info', "query migrate failed: $err");
+ if ($err_count <= 5) {
+ usleep(1_000_000);
+ next;
+ }
+ die "too many query migrate failures - aborting\n";
+ }
+
+ my $status = $stat->{status};
+ if (defined($status) && $status =~ m/^(setup)$/im) {
+ sleep(1);
+ next;
+ }
+
+ if (!defined($status) || $status !~ m/^(active|completed|failed|cancelled)$/im) {
+ die $merr if $merr;
+ die "unable to parse migration status '$status' - aborting\n";
+ }
+ $merr = undef;
+ $err_count = 0;
+
+ my $memstat = $stat->{ram};
+
+ if ($status eq 'completed') {
+ my $delay = time() - $start;
+ if ($delay > 0) {
+ my $total = $memstat->{total} || 0;
+ my $avg_speed = render_bytes($total / $delay, 1);
+ my $downtime = $stat->{downtime} || 0;
+ $self->log('info', "average migration speed: $avg_speed/s - downtime $downtime ms");
+ }
+ }
+
+ if ($status eq 'failed' || $status eq 'cancelled') {
+ my $message = $stat->{'error-desc'} ? "$status - $stat->{'error-desc'}" : $status;
+ $self->log('info', "migration status error: $message");
+ die "aborting\n"
+ }
+
+ if ($status ne 'active') {
+ $self->log('info', "migration status: $status");
+ last;
+ }
+
+ if ($memstat->{transferred} ne $last_mem_transferred) {
+ my $trans = $memstat->{transferred} || 0;
+ my $rem = $memstat->{remaining} || 0;
+ my $total = $memstat->{total} || 0;
+ my $speed = ($memstat->{'pages-per-second'} // 0) * ($memstat->{'page-size'} // 0);
+ my $dirty_rate = ($memstat->{'dirty-pages-rate'} // 0) * ($memstat->{'page-size'} // 0);
+
+ # reduce sleep if remainig memory is lower than the average transfer speed
+ $usleep = 100_000 if $avglstat && $rem < $avglstat;
+
+ # also reduce loggin if we poll more frequent
+ my $should_log = $usleep > 100_000 ? 1 : ($i % 10) == 0;
+
+ my $total_h = render_bytes($total, 1);
+ my $transferred_h = render_bytes($trans, 1);
+ my $speed_h = render_bytes($speed, 1);
+
+ my $progress = "transferred $transferred_h of $total_h VM-state, ${speed_h}/s";
+
+ if ($dirty_rate > $speed) {
+ my $dirty_rate_h = render_bytes($dirty_rate, 1);
+ $progress .= ", VM dirties lots of memory: $dirty_rate_h/s";
+ }
+
+ $self->log('info', "migration $status, $progress") if $should_log;
+
+ my $xbzrle = $stat->{"xbzrle-cache"} || {};
+ my ($xbzrlebytes, $xbzrlepages) = $xbzrle->@{'bytes', 'pages'};
+ if ($xbzrlebytes || $xbzrlepages) {
+ my $bytes_h = render_bytes($xbzrlebytes, 1);
+
+ my $msg = "send updates to $xbzrlepages pages in $bytes_h encoded memory";
+
+ $msg .= sprintf(", cache-miss %.2f%%", $xbzrle->{'cache-miss-rate'} * 100)
+ if $xbzrle->{'cache-miss-rate'};
+
+ $msg .= ", overflow $xbzrle->{overflow}" if $xbzrle->{overflow};
+
+ $self->log('info', "xbzrle: $msg") if $should_log;
+ }
+
+ if (($lastrem && $rem > $lastrem) || ($rem == 0)) {
+ $downtimecounter++;
+ }
+ $lastrem = $rem;
+
+ if ($downtimecounter > 5) {
+ $downtimecounter = 0;
+ $migrate_downtime *= 2;
+ $self->log('info', "auto-increased downtime to continue migration: $migrate_downtime ms");
+ eval {
+ # migrate-set-parameters does not touch values not
+ # specified, so this only changes downtime-limit
+ mon_cmd($vmid, "migrate-set-parameters", 'downtime-limit' => int($migrate_downtime));
+ };
+ $self->log('info', "migrate-set-parameters error: $@") if $@;
+ }
+ }
+
+ $last_mem_transferred = $memstat->{transferred};
+ }
+}
+
sub phase1 {
my ($self, $vmid) = @_;
@@ -1139,212 +1352,7 @@ sub phase2 {
}
}
- $self->log('info', "starting online/live migration on $migrate_uri");
- $self->{livemigration} = 1;
-
- # load_defaults
- my $defaults = PVE::QemuServer::load_defaults();
-
- $self->log('info', "set migration capabilities");
- eval { PVE::QemuServer::set_migration_caps($vmid) };
- warn $@ if $@;
-
- my $qemu_migrate_params = {};
-
- # migrate speed can be set via bwlimit (datacenter.cfg and API) and via the
- # migrate_speed parameter in qm.conf - take the lower of the two.
- my $bwlimit = $self->get_bwlimit();
-
- my $migrate_speed = $conf->{migrate_speed} // 0;
- $migrate_speed *= 1024; # migrate_speed is in MB/s, bwlimit in KB/s
-
- if ($bwlimit && $migrate_speed) {
- $migrate_speed = ($bwlimit < $migrate_speed) ? $bwlimit : $migrate_speed;
- } else {
- $migrate_speed ||= $bwlimit;
- }
- $migrate_speed ||= ($defaults->{migrate_speed} || 0) * 1024;
-
- if ($migrate_speed) {
- $migrate_speed *= 1024; # qmp takes migrate_speed in B/s.
- $self->log('info', "migration speed limit: ". render_bytes($migrate_speed, 1) ."/s");
- } else {
- # always set migrate speed as QEMU default to 128 MiBps == 1 Gbps, use 16 GiBps == 128 Gbps
- $migrate_speed = (16 << 30);
- }
- $qemu_migrate_params->{'max-bandwidth'} = int($migrate_speed);
-
- my $migrate_downtime = $defaults->{migrate_downtime};
- $migrate_downtime = $conf->{migrate_downtime} if defined($conf->{migrate_downtime});
- # migrate-set-parameters expects limit in ms
- $migrate_downtime *= 1000;
- $self->log('info', "migration downtime limit: $migrate_downtime ms");
- $qemu_migrate_params->{'downtime-limit'} = int($migrate_downtime);
-
- # set cachesize to 10% of the total memory
- my $memory = get_current_memory($conf->{memory});
- my $cachesize = int($memory * 1048576 / 10);
- $cachesize = round_powerof2($cachesize);
-
- $self->log('info', "migration cachesize: " . render_bytes($cachesize, 1));
- $qemu_migrate_params->{'xbzrle-cache-size'} = int($cachesize);
-
- $self->log('info', "set migration parameters");
- eval {
- mon_cmd($vmid, "migrate-set-parameters", %{$qemu_migrate_params});
- };
- $self->log('info', "migrate-set-parameters error: $@") if $@;
-
- if (PVE::QemuServer::vga_conf_has_spice($conf->{vga}) && !$self->{opts}->{remote}) {
- my $rpcenv = PVE::RPCEnvironment::get();
- my $authuser = $rpcenv->get_user();
-
- my (undef, $proxyticket) = PVE::AccessControl::assemble_spice_ticket($authuser, $vmid, $self->{node});
-
- my $filename = "/etc/pve/nodes/$self->{node}/pve-ssl.pem";
- my $subject = PVE::AccessControl::read_x509_subject_spice($filename);
-
- $self->log('info', "spice client_migrate_info");
-
- eval {
- mon_cmd($vmid, "client_migrate_info", protocol => 'spice',
- hostname => $proxyticket, 'port' => 0, 'tls-port' => $spice_port,
- 'cert-subject' => $subject);
- };
- $self->log('info', "client_migrate_info error: $@") if $@;
-
- }
-
- my $start = time();
-
- $self->log('info', "start migrate command to $migrate_uri");
- eval {
- mon_cmd($vmid, "migrate", uri => $migrate_uri);
- };
- my $merr = $@;
- $self->log('info', "migrate uri => $migrate_uri failed: $merr") if $merr;
-
- my $last_mem_transferred = 0;
- my $usleep = 1000000;
- my $i = 0;
- my $err_count = 0;
- my $lastrem = undef;
- my $downtimecounter = 0;
- while (1) {
- $i++;
- my $avglstat = $last_mem_transferred ? $last_mem_transferred / $i : 0;
-
- usleep($usleep);
-
- my $stat = eval { mon_cmd($vmid, "query-migrate") };
- if (my $err = $@) {
- $err_count++;
- warn "query migrate failed: $err\n";
- $self->log('info', "query migrate failed: $err");
- if ($err_count <= 5) {
- usleep(1_000_000);
- next;
- }
- die "too many query migrate failures - aborting\n";
- }
-
- my $status = $stat->{status};
- if (defined($status) && $status =~ m/^(setup)$/im) {
- sleep(1);
- next;
- }
-
- if (!defined($status) || $status !~ m/^(active|completed|failed|cancelled)$/im) {
- die $merr if $merr;
- die "unable to parse migration status '$status' - aborting\n";
- }
- $merr = undef;
- $err_count = 0;
-
- my $memstat = $stat->{ram};
-
- if ($status eq 'completed') {
- my $delay = time() - $start;
- if ($delay > 0) {
- my $total = $memstat->{total} || 0;
- my $avg_speed = render_bytes($total / $delay, 1);
- my $downtime = $stat->{downtime} || 0;
- $self->log('info', "average migration speed: $avg_speed/s - downtime $downtime ms");
- }
- }
-
- if ($status eq 'failed' || $status eq 'cancelled') {
- my $message = $stat->{'error-desc'} ? "$status - $stat->{'error-desc'}" : $status;
- $self->log('info', "migration status error: $message");
- die "aborting\n"
- }
-
- if ($status ne 'active') {
- $self->log('info', "migration status: $status");
- last;
- }
-
- if ($memstat->{transferred} ne $last_mem_transferred) {
- my $trans = $memstat->{transferred} || 0;
- my $rem = $memstat->{remaining} || 0;
- my $total = $memstat->{total} || 0;
- my $speed = ($memstat->{'pages-per-second'} // 0) * ($memstat->{'page-size'} // 0);
- my $dirty_rate = ($memstat->{'dirty-pages-rate'} // 0) * ($memstat->{'page-size'} // 0);
-
- # reduce sleep if remainig memory is lower than the average transfer speed
- $usleep = 100_000 if $avglstat && $rem < $avglstat;
-
- # also reduce loggin if we poll more frequent
- my $should_log = $usleep > 100_000 ? 1 : ($i % 10) == 0;
-
- my $total_h = render_bytes($total, 1);
- my $transferred_h = render_bytes($trans, 1);
- my $speed_h = render_bytes($speed, 1);
-
- my $progress = "transferred $transferred_h of $total_h VM-state, ${speed_h}/s";
-
- if ($dirty_rate > $speed) {
- my $dirty_rate_h = render_bytes($dirty_rate, 1);
- $progress .= ", VM dirties lots of memory: $dirty_rate_h/s";
- }
-
- $self->log('info', "migration $status, $progress") if $should_log;
-
- my $xbzrle = $stat->{"xbzrle-cache"} || {};
- my ($xbzrlebytes, $xbzrlepages) = $xbzrle->@{'bytes', 'pages'};
- if ($xbzrlebytes || $xbzrlepages) {
- my $bytes_h = render_bytes($xbzrlebytes, 1);
-
- my $msg = "send updates to $xbzrlepages pages in $bytes_h encoded memory";
-
- $msg .= sprintf(", cache-miss %.2f%%", $xbzrle->{'cache-miss-rate'} * 100)
- if $xbzrle->{'cache-miss-rate'};
-
- $msg .= ", overflow $xbzrle->{overflow}" if $xbzrle->{overflow};
-
- $self->log('info', "xbzrle: $msg") if $should_log;
- }
-
- if (($lastrem && $rem > $lastrem) || ($rem == 0)) {
- $downtimecounter++;
- }
- $lastrem = $rem;
-
- if ($downtimecounter > 5) {
- $downtimecounter = 0;
- $migrate_downtime *= 2;
- $self->log('info', "auto-increased downtime to continue migration: $migrate_downtime ms");
- eval {
- # migrate-set-parameters does not touch values not
- # specified, so this only changes downtime-limit
- mon_cmd($vmid, "migrate-set-parameters", 'downtime-limit' => int($migrate_downtime));
- };
- $self->log('info', "migrate-set-parameters error: $@") if $@;
- }
- }
-
- $last_mem_transferred = $memstat->{transferred};
- }
+ live_migration($self, $vmid, $migrate_uri, $spice_port);
if ($self->{storage_migration}) {
# finish block-job with block-job-cancel, to disconnect source VM from NBD
--
2.39.2
More information about the pve-devel
mailing list