[PATCH qemu-server 3/3] Fix #5708: Add CPU raw counters

[Sascha Westermann]

Add a map containing raw values from /proc/<pid>/stat (utime, stime and
guest_time), "uptime_ticks" and "user_hz" (from cpuinfo) to calcuate
physical CPU usage from two samples. In addition, virtual CPU statistics
based on /proc/<pid>/task/<tid>/schedstat (<tid> for virtual cores) are
added - based on this data, the CPU usage can be calculated from the
perspective of the virtual machine.

The total usage corresponds to "cpu_ns + runqueue_ns", "cpu_ns" should
roughly reflect the physical CPU usage (without I/O-threads and
emulators) and "runqueue_ns" corresponds to the value of %steal, i.e.
the same as "CPU ready" for VMware or "Wait for dispatch" for Hyper-V.

To calculate the difference value, uptime_ticks and user_hz would be
converted to nanoseconds - the value was determined immediately after
utime, stime and guest_time were determined from /proc/<pid>/stat, i.e.
before /proc/<pid>/task/<tid>/schedstat was determined. The time value
is therefore not exact, but should be sufficiently close to the time of
determination so that the values determined should be relatively
accurate.

Signed-off-by: Sascha Westermann <sascha.westermann at hl-services.de>
---
 PVE/QemuServer.pm | 55 +++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 53 insertions(+), 2 deletions(-)

diff --git a/PVE/QemuServer.pm b/PVE/QemuServer.pm
index b26da505..39830709 100644
--- a/PVE/QemuServer.pm
+++ b/PVE/QemuServer.pm
@@ -2814,6 +2814,40 @@ our $vmstatus_return_properties = {
 
 my $last_proc_pid_stat;
 
+sub get_vcpu_to_thread_id {
+    my ($pid) = @_;
+    my @cpu_to_thread_id;
+    my $task_dir = "/proc/$pid/task";
+
+    if (! -d $task_dir) {
+	return @cpu_to_thread_id;
+    }
+
+    opendir(my $dh, $task_dir);
+    if (!$dh) {
+	return @cpu_to_thread_id;
+    }
+    while (my $tid = readdir($dh)) {
+	next if $tid =~ /^\./;
+	my $comm_file = "$task_dir/$tid/comm";
+	next unless -f $comm_file;
+
+	open(my $fh, '<', $comm_file) or next;
+	my $comm = <$fh>;
+	close($fh);
+
+	chomp $comm;
+
+	if ($comm =~ /^CPU\s+(\d+)\/KVM$/) {
+	    my $vcpu = $1;
+	    push @cpu_to_thread_id, { tid => $tid, vcpu => $vcpu };
+	}
+    }
+    closedir($dh);
+
+    return @cpu_to_thread_id;
+}
+
 # get VM status information
 # This must be fast and should not block ($full == false)
 # We only query KVM using QMP if $full == true (this can be slow)
@@ -2827,8 +2861,6 @@ sub vmstatus {
     my $list = vzlist();
     my $defaults = load_defaults();
 
-    my ($uptime) = PVE::ProcFSTools::read_proc_uptime(1);
-
     my $cpucount = $cpuinfo->{cpus} || 1;
 
     foreach my $vmid (keys %$list) {
@@ -2911,6 +2943,25 @@ sub vmstatus {
 
 	my $pstat = PVE::ProcFSTools::read_proc_pid_stat($pid);
 	next if !$pstat; # not running
+	my ($uptime) = PVE::ProcFSTools::read_proc_uptime(1);
+	my $process_uptime_ticks = $uptime - $pstat->{starttime};
+
+	$d->{cpustat}->{guest_time} = int($pstat->{guest_time});
+	$d->{cpustat}->{process_uptime_ticks} = $process_uptime_ticks;
+	$d->{cpustat}->{stime} = int($pstat->{stime});
+	$d->{cpustat}->{user_hz} = $cpuinfo->{user_hz};
+	$d->{cpustat}->{utime} = int($pstat->{utime});
+
+	my @vcpu_to_thread_id = get_vcpu_to_thread_id($pid);
+	if (@vcpu_to_thread_id) {
+	    foreach my $entry (@vcpu_to_thread_id) {
+		my $statstr = PVE::Tools::file_read_firstline("/proc/$pid/task/$entry->{tid}/schedstat") or next;
+		if ($statstr && $statstr =~ m/^(\d+) (\d+) \d/) {
+		    $d->{cpustat}->{"vcpu" . $entry->{vcpu}}->{cpu_ns} = int($1);
+		    $d->{cpustat}->{"vcpu" . $entry->{vcpu}}->{runqueue_ns} = int($2);
+		};
+	    }
+	}
 
 	my $used = $pstat->{utime} + $pstat->{stime};
 
-- 
2.46.0