Support changing the 'power_dpm_state' parameter of Radeon
GPUs. It only works if the 'dpm' power method is enabled.
Note that the 'dpm' power method cannot be enabled through
the video plugin, but it can be set using the bootloader plugin
using 'cmdline = radeon.dpm=1'.
The video plugin now recognizes a new 'radeon_dpm_state' option
which changes the dpm state. Possible values are 'battery',
'balanced' and 'performance' [1].
[video]
radeon_dpm_state=balanced
[1] https://wiki.archlinux.org/index.php/ATI#Dynamic_power_management
Resolves: rhbz#1417659
Signed-off-by: Ondřej Lysoněk <olysonek@redhat.com>
E.g.:
[myprofile]
process=myprocess1
process2=myprocess2.*
The myprofile will be recommended if there are 'myprocess1' and
'myprocess2.*' (e.g. myprocess2, myprocess21, myprocess2_whatever)
running.
Resolves: rhbz#1461838
Signed-off-by: Jaroslav Škarvada <jskarvad@redhat.com>
From 63e5ebfe0c71c5e6d0613c4d8327b2a6f3fba7ba Mon Sep 17 00:00:00 2001
From: Luiz Capitulino <lcapitulino@redhat.com>
Date: Fri, 19 May 2017 14:42:06 -0400
Subject:
The realtime guest profile uses the RT kernel default priority
assignment for the ksoftird, rcuc, and ktimersoftd kernel threads,
which is:
17 FF 2 [rcuc/1] *
19 FF 1 [ktimersoftd/1] *
20 TS - [ksoftirqd/1] *
This doesn't allow running a PMD thread with fifo:1 in the
guest, since this will starve ktimersoftd and ksoftirqd if
those threads ever become runnable.
The solution is to use the same priority assigment we use
in the host where we've been running PMD threads with
fifo:1 priorities without problems. This assignment is:
151 FF 4 [rcuc/15] *
153 FF 3 [ktimersoftd/15] *
154 FF 2 [ksoftirqd/15] *
This patch just copies the [scheduler] section from the
host profile.
Resolves: rhbz#1452357
Signed-off-by: Luiz Capitulino <lcapitulino@redhat.com>
By default the timer tick will fire at the same time on all
CPUs. This causes the jiffies_lock to get contended in the
real-time kernel, as it's a raw spinlock. skew_tick=1 causes
the timer tick to fire at different times on all CPUs,
fixing the contention.
Note skew_tick=1 usage is going to be propagated to the
NFV profiles as well.
Resolves: rhbz#1447938
Signed-off-by: Luiz Capitulino <lcapitulino@redhat.com>
the macros are called .nf and .fi, not .NF and .FI
Test:
% LC_ALL=en_US.UTF-8 MANROFFSEQ='' MANWIDTH=80 man --warnings \
-E UTF-8 -l -Tutf8 -Z <file> >/dev/null
<standard input>:53: warning: macro `NF' not defined
<standard input>:74: warning: macro `FI' not defined
Spotted by rpmlint and lintian.
List available profiles when 'tuned-adm profile' is run
without a profile name.
Resolves: rhbz#988433
Signed-off-by: Ondřej Lysoněk <olysonek@redhat.com>
Plugin_net instances can now be given a new 'ring' option with
the following values (see ethtool(8) for their meaning):
rx N
rx-mini N
rx-jumbo N
tx N
The syntax is the same as the syntax for 'coalesce' and 'features'
parameters introduced in commit bc5d7acca8.
Example:
[net]
ring=rx 1024 tx 512
Resolves: https://github.com/redhat-performance/tuned/issues/2
Signed-off-by: Ondřej Lysoněk <olysonek@redhat.com>
Plugin_net instances can now be given a new 'pause' option with
the following values (see ethtool(8) for their meaning):
autoneg on|off
rx on|off
tx on|off
The syntax is the same as the syntax for 'coalesce' and 'features'
parameters introduced in commit bc5d7acca8.
Example:
[net]
pause=autoneg off rx off
Resolves: https://github.com/redhat-performance/tuned/issues/2
Signed-off-by: Ondřej Lysoněk <olysonek@redhat.com>
pkg-config is the most reliable and cross-distro way to get
information about the systemd folders on a system.
only rely on RPM macros when pkg-config is not installed or
systemd.pc is not available.
This will add tuned_initrd to newly installed kernels upon Tuned
restart. It's workaround for rhbz#1442117.
Resolves: rhbz#1441797
Signed-off-by: Jaroslav Škarvada <jskarvad@redhat.com>
