site/profiles/manifests/ceph/osd.pp

@@ -2,6 +2,9 @@ class profiles::ceph::osd (
   Boolean $ensure_running = true,
 ) {
 
+  # tune the I/O scheduler on the disks backing ceph OSDs
+  include profiles::ceph::osd_scheduler
+
   if $ensure_running and $facts['is_ceph_osd'] {
     $facts['ceph_services']['osd'].each |String $svc| {
       service { $svc:

site/profiles/manifests/ceph/osd_scheduler.pp

@@ -0,0 +1,32 @@
+class profiles::ceph::osd_scheduler (
+  String[1] $scheduler = 'none',
+) {
+
+  $devices = $facts['ceph_osd_devices']
+
+  # no-op where the fact is absent/empty (VMs, non-OSD hosts have no ceph PVs)
+  if $devices =~ Array[String[1], 1] {
+
+    # strip /dev/ so the rule matches the udev KERNEL sysname (e.g. sda)
+    $kernel_names    = $devices.map |$dev| { regsubst($dev, '^.*/', '') }
+    $sysname_matches = $kernel_names.map |$name| { "--sysname-match=${name}" }
+
+    file { '/etc/udev/rules.d/60-ceph-osd-scheduler.rules':
+      ensure  => file,
+      owner   => 'root',
+      group   => 'root',
+      mode    => '0644',
+      content => template('profiles/ceph/osd-scheduler.rules.erb'),
+      notify  => Exec['ceph-osd-scheduler-reload'],
+    }
+
+    # apply immediately; udev re-applies on reboot and device re-add
+    $trigger = "udevadm trigger --subsystem-match=block --action=change ${join($sysname_matches, ' ')}"
+
+    exec { 'ceph-osd-scheduler-reload':
+      command     => "udevadm control --reload-rules && ${trigger}",
+      path        => ['/usr/bin', '/bin', '/usr/sbin', '/sbin'],
+      refreshonly => true,
+    }
+  }
+}

site/profiles/templates/ceph/osd-scheduler.rules.erb

@@ -0,0 +1,5 @@
+# Managed by puppet (profiles::ceph::osd_scheduler).
+# Set the I/O scheduler to <%= @scheduler %> on ceph OSD block devices.
+<% @kernel_names.sort.each do |dev| -%>
+ACTION=="add|change", SUBSYSTEM=="block", KERNEL=="<%= dev %>", ATTR{queue/scheduler}="<%= @scheduler %>"
+<% end -%>