ceph: set OSD disk I/O scheduler to none via udev rule
ci/woodpecker/pr/ruby-validate Pipeline was successful
ci/woodpecker/pr/puppet-lint Pipeline was successful
ci/woodpecker/pr/yamllint Pipeline was successful
ci/woodpecker/pr/bolt-validate Pipeline was successful
ci/woodpecker/pr/erb-validate Pipeline was successful
ci/woodpecker/pr/epp-validate Pipeline was successful
ci/woodpecker/pr/puppet-validate Pipeline was successful
ci/woodpecker/pr/ruby-check Pipeline was successful
ci/woodpecker/pr/ruby-validate Pipeline was successful
ci/woodpecker/pr/puppet-lint Pipeline was successful
ci/woodpecker/pr/yamllint Pipeline was successful
ci/woodpecker/pr/bolt-validate Pipeline was successful
ci/woodpecker/pr/erb-validate Pipeline was successful
ci/woodpecker/pr/epp-validate Pipeline was successful
ci/woodpecker/pr/puppet-validate Pipeline was successful
ci/woodpecker/pr/ruby-check Pipeline was successful
Ceph OSDs get no benefit from kernel I/O scheduling; the original intent was to set those disks to the noop scheduler. On the fleet's EL9 blk-mq kernels (AlmaLinux 9, kernel 5.14) the equivalent of noop is none. - add profiles::ceph::osd_scheduler, which renders a udev rule from the ceph_osd_devices fact pinning queue/scheduler to none on each OSD disk - reload udev and trigger the matched block devices so the change applies immediately, while the rule keeps it set across reboots and device re-add - no-op when the fact is absent/empty so VMs and non-OSD hosts are untouched - include the class from profiles::ceph::osd so it lands only on OSD hosts Claude-Session: https://claude.ai/code/session_01JUoARVdmhxKQHyyyp1pxeT
This commit is contained in:
@@ -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:
|
||||
|
||||
@@ -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,
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -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 -%>
|
||||
Reference in New Issue
Block a user