Just explain what isolated_cores= is for and recommend to only have one
isolated_cores= line to avoid wrong system configuration.
Signed-off-by: Luiz Capitulino <lcapitulino@redhat.com>
Resolves: RHEL-16469
Since intel_pstate and amd-pstate use the same per-CPU interface
for setting EPP hints, the current cpu plugin supports amd-pstate
out of the box.
This commit modifies current P-state related logs and variable
names to be explicit about the support for amd-pstate.
Note that while intel_pstate supports global attributes such as
`max_perf_pct`, amd-pstate does not.
Python 3.12 is more strict about correct escaping and
outputs SyntaxWarning for invalid escape sequences that
were previously silently corrected.
Signed-off-by: Jaroslav Škarvada <jskarvad@redhat.com>
Resolves: RHEL-15137
Appropriate commands are added to tuned-adm as well.
`get_instances`: Retrieves a list of active instances of a given
plugin or all active instances.
`instance_get_devices`: Retrieves a list of devices assigned
to a given instance.
Resolves: RHEL-3707
The logic for converting sysctl names to paths did not work for
sysctls like "net.ipv4.conf.bond0/355.forwarding" because it
contains a slash. According to the sysctl.d manpage, the dots
and slashed must be interchanged if the first separator is a
dot, which we assume.
Improve error log by printing all arguments passed to command.
This helps in troubleshooting issues where just knowing the command is
not enough, we need more details on which settings, devices and options
has caused this error.
Signed-off-by: Kenneth D'souza <kennethdsouza94@gmail.com>
When ksm or ksmtuned services do not exist, return 0 so that we do not
generate ERRORs in TuneD logs.
Resolves: OCPBUGS-19656
Signed-off-by: Jiri Mencak <jmencak@users.noreply.github.com>
Show no errors when the physical_package_id file does not exist -- the
CPUs may be offline.
Resolves: rhbz#2217015
Signed-off-by: Jiri Mencak <jmencak@users.noreply.github.com>
The rcu_normal_after_boot=1 kernel parameter (which is enabled by
default on CONFIG_PREEMPT_RT kernels) avoids the use of IPIs
to expedite the runtime of synchronize_rcu_expedited() callers.
Enable this in tuned to avoid such IPIs on !CONFIG_PREEMPT_RT kernels
as well.
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
The ktimer_lockless_check interface was removed from Red Hat kernels.
Drop the tuned configuration as well.
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
The interruptions avoided by the rtentsk logic:
"Add plugin to open a socket with SOF_TIMESTAMPING_OPT_TX_SWHW.
This is for avoiding interruptions due to static key IPIs due
to opening socket with timestamping enabled (by opening a
socket ourselves the static key is kept enabled)."
Are also desired on systems that use cpu-partitioning.
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Commit 49cc817871
("realtime: Set tsc as 'reliable'") reads:
"We already disable the clocksource watchdog, it's there to double-check
whether clock results are coherent between reads. But a new reliability
test was introduced in recent kernels[1], tracking tsc drift between
CPUs[2]. It works by programming timers on all CPUs, including isolated
ones, and checks whether the tsc was adjusted in between runs. This
introduces unwarranted latency on real time systems. So let's promote
tsc to 'reliable', which disables both checks."
The timer is also undesired interruption to systems that use cpu-partitioning.
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
The following sysctl settings are the same between cpu-partitioning and
realtime profiles:
kernel.hung_task_timeout_secs = 600
kernel.nmi_watchdog = 0
vm.stat_interval = 10
kernel.timer_migration = 0
Unify them in the network-latency profile, parent of both profiles.
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Add rollback option to tuned-main.conf file. The option specifies how
TuneD should perform rollbacks. By default, the old behaviour is
preserved (rollback=auto) and settings are rolled back on TuneD daemon
exit and profile switches. Using rollback=not_on_exit will result in
TuneD not performing any rollbacks on the daemon exit, however, on
profile switches, settings rollbacks will still be performed.
Resolves: rhbz#2203142
Signed-off-by: Jiri Mencak <jmencak@users.noreply.github.com>
