fix #1135: refactor wear level parsing

[pve-storage.git] / PVE / Diskmanage.pm

diff --git a/PVE/Diskmanage.pm b/PVE/Diskmanage.pm
index bcd38837e5b9e6dfc06cbc1335f610b43bc52557..1befd9e89214955b81a805976de42881fe91922c 100644 (file)
--- a/PVE/Diskmanage.pm
+++ b/PVE/Diskmanage.pm
@@ -61,7 +61,7 @@ sub disk_is_used {
     my $dev = $disk;
     $dev =~ s|^/dev/||;
 
-    my $disklist = get_disks($dev);
+    my $disklist = get_disks($dev, 1);
 
     die "'$disk' is not a valid local disk\n" if !defined($disklist->{$dev});
     return 1 if $disklist->{$dev}->{used};
@@ -70,21 +70,34 @@ sub disk_is_used {
 }
 
 sub get_smart_data {
-    my ($disk) = @_;
+    my ($disk, $healthonly) = @_;
 
     assert_blockdev($disk);
     my $smartdata = {};
-    my $datastarted = 0;
+    my $type;
 
     my $returncode = 0;
+
+    $disk =~ s/n\d+$//
+        if $disk =~ m!^/dev/nvme\d+n\d+$!;
+
+    my $cmd = [$SMARTCTL, '-H'];
+    push @$cmd, '-A', '-f', 'brief' if !$healthonly;
+    push @$cmd, $disk;
+
     eval {
-       $returncode = run_command([$SMARTCTL, '-H', '-A', '-f', 'brief', $disk], noerr => 1, outfunc => sub{
+       $returncode = run_command($cmd, noerr => 1, outfunc => sub{
            my ($line) = @_;
 
 # ATA SMART attributes, e.g.:
 # ID# ATTRIBUTE_NAME          FLAGS    VALUE WORST THRESH FAIL RAW_VALUE
 #   1 Raw_Read_Error_Rate     POSR-K   100   100   000    -    0
-           if ($datastarted && $line =~ m/^([ \d]{2}\d)\s+(\S+)\s+(\S{6})\s+(\d+)\s+(\d+)\s+(\d+)\s+(\S+)\s+(.*)$/) {
+#
+# SAS and NVME disks, e.g.:
+# Data Units Written:                 5,584,952 [2.85 TB]
+# Accumulated start-stop cycles:  34
+
+           if (defined($type) && $type eq 'ata' && $line =~ m/^([ \d]{2}\d)\s+(\S+)\s+(\S{6})\s+(\d+)\s+(\d+)\s+(\d+)\s+(\S+)\s+(.*)$/) {
                my $entry = {};
                $entry->{name} = $2 if defined $2;
                $entry->{flags} = $3 if defined $3;
@@ -96,10 +109,18 @@ sub get_smart_data {
                $entry->{raw} = $8 if defined $8;
                $entry->{id} = $1 if defined $1;
                push @{$smartdata->{attributes}}, $entry;
-           } elsif ($line =~ m/self\-assessment test result: (.*)$/) {
+           } elsif ($line =~ m/(?:Health Status|self\-assessment test result): (.*)$/ ) {
                $smartdata->{health} = $1;
            } elsif ($line =~ m/Vendor Specific SMART Attributes with Thresholds:/) {
-               $datastarted = 1;
+               $type = 'ata';
+               delete $smartdata->{text};
+           } elsif ($line =~ m/=== START OF (READ )?SMART DATA SECTION ===/) {
+               $type = 'text';
+           } elsif (defined($type) && $type eq 'text') {
+               $smartdata->{text} = '' if !defined $smartdata->{text};
+               $smartdata->{text} .= "$line\n";
+           } elsif ($line =~ m/SMART Disabled/) {
+               $smartdata->{health} = "SMART Disabled";
            }
        });
     };
@@ -111,29 +132,10 @@ sub get_smart_data {
     if ((defined($returncode) && ($returncode & 0b00000011)) || $err) {
        die "Error getting S.M.A.R.T. data: Exit code: $returncode\n";
     }
-    return $smartdata;
-}
-
-sub get_smart_health {
-    my ($disk) = @_;
 
-    return "NOT A DEVICE" if !assert_blockdev($disk, 1);
+    $smartdata->{type} = $type;
 
-    my $message;
-
-    run_command([$SMARTCTL, '-H', $disk], noerr => 1, outfunc => sub {
-       my ($line) = @_;
-
-       if ($line =~ m/test result: (.*)$/) {
-           $message = $1;
-       } elsif ($line =~ m/open device: (.*) failed: (.*)$/) {
-           $message = "FAILED TO OPEN";
-       } elsif ($line =~ m/^SMART Disabled/) {
-           $message = "SMART DISABLED";
-       }
-    });
-
-    return $message;
+    return $smartdata;
 }
 
 sub get_zfs_devices {
@@ -282,8 +284,46 @@ sub get_sysdir_info {
     return $data;
 }
 
+sub get_wear_leveling_info {
+    my ($attributes, $model) = @_;
+
+    my $wearout;
+
+    my $vendormap = {
+       'kingston' => 231,
+       'samsung' => 177,
+       'intel' => 233,
+       'sandisk' => 233,
+       'default' => 233,
+    };
+
+    # find target attr id
+
+    my $attrid;
+
+    foreach my $vendor (keys $vendormap) {
+       if ($model =~ m/$vendor/i) {
+           $attrid = $vendormap->{$vendor};
+           # found the attribute
+           last;
+       }
+    }
+
+    if (!$attrid) {
+       $attrid = $vendormap->{default};
+    }
+
+    foreach my $attr (@$attributes) {
+       next if $attr->{id} != $attrid;
+       $wearout = $attr->{value};
+       last;
+    }
+
+    return $wearout;
+}
+
 sub get_disks {
-    my ($disk) = @_;
+    my ($disk, $nosmart) = @_;
     my $disklist = {};
 
     my $mounted = {};
@@ -364,29 +404,20 @@ sub get_disks {
        }
 
        my $health = 'UNKNOWN';
-       my $wearout;
-       eval {
-           if ($type eq 'ssd' && !defined($disk)) {
-               # if we have an ssd we try to get the wearout indicator
-               $wearout = 'N/A';
-               my $smartdata = get_smart_data($devpath);
-               $health = $smartdata->{health};
-               foreach my $attr (@{$smartdata->{attributes}}) {
-                   # ID 233 is media wearout indicator on intel and sandisk
-                   # ID 177 is media wearout indicator on samsung
-                   next if ($attr->{id} != 233 && $attr->{id} != 177);
-                   next if ($attr->{name} !~ m/wear/i);
-                   $wearout = $attr->{value};
-
-                   # prefer the 233 value
-                   last if ($attr->{id} == 233);
+       my $wearout = 'N/A';
+
+       if (!$nosmart) {
+           eval {
+               my $smartdata = get_smart_data($devpath, ($type ne 'ssd'));
+               $health = $smartdata->{health} if $smartdata->{health};
+
+               if ($type eq 'ssd') {
+                   # if we have an ssd we try to get the wearout indicator
+                   my $wearval = get_wear_leveling_info($smartdata->{attributes}, $sysdata->{model});
+                   $wearout = $wearval if $wearval;
                }
-           } elsif (!defined($disk)) {
-               # we do not need smart data if we check a single disk
-               # because this functionality is only for disk_is_used
-               $health = get_smart_health($devpath) if !defined($disk);
-           }
-       };
+           };
+       }
 
        my $used;