Linux performance optimization using Tuned configuration optimization solution

Among them, the /etc/tuned/ directory has higher priority!

Default tuning configuration files are in the directory below. Each tuning method has its own configuration file.

┌──[[email protected]]-[/usr/lib/tuned]
└─$ls
accelerator-performance desktop hpc-compute latency-performance network-throughput recommend.d virtual-guest
balanced functions intel-sst network-latency powersave throughput-performance virtual-host
┌──[[email protected]]-[/usr/lib/tuned]
└─$

You can see that the default tuning file is divided into two parts, the main and sysctl parts

┌──[[email protected]]-[/usr/lib/tuned]
└─$cat ./network-throughput/tuned.conf
#
# tuned configuration
#

[main]
summary=Optimize for streaming network throughput, generally only necessary on older CPUs or 40G + networks
include=throughput-performance

[sysctl]
# Increase kernel buffer size maximums. Currently this seems only necessary at 40Gb speeds.
#
# The buffer tuning values below do not account for any potential hugepage allocation.
# Ensure that you do not oversubscribe system memory.
net.ipv4.tcp_rmem="4096 87380 16777216"
net.ipv4.tcp_wmem="4096 16384 16777216"
net.ipv4.udp_mem="3145728 4194304 16777216"
┌──[[email protected]]-[/usr/lib/tuned]
└─$

• The mail section describes the role of this configuration file, and it references the "throughput-performance" configuration file include=throughput-performance
• The sysctl section describes the kernel parameters it modified. The main changes here are the network buffer sizes related to TCP and UDP.

Let’s take a look at the adjustments made to the referenced configuration files.

┌──[[email protected]]-[/usr/lib/tuned]
└─$cat ./throughput-performance/tuned.conf | grep -v ^#

[main]
summary=Broadly applicable tuning that provides excellent performance across a variety of common server workloads

[cpu]
governor=performance
energy_perf_bias=performance
min_perf_pct=100

[disk]
readahead=>4096

[sysctl]
kernel.sched_min_granularity_ns = 10000000
kernel.sched_wakeup_granularity_ns = 15000000
vm.dirty_ratio = 40
vm.dirty_background_ratio = 10
vm.swappiness=10
┌──[[email protected]]-[/usr/lib/tuned]
└─$

There are more configuration blocks such as cpu, disk and so on.

• The [cpu] section contains CPU-related parameter settings. governor=performance sets the CPU frequency regulation policy to performance mode, energy_perf_bias=performance sets the CPU energy consumption performance preference to performance mode, min_perf_pct=100 sets the CPU Minimum performance percentage is 100%.
• The [disk] section contains settings related to disk-related parameters. readahead=>4096 Set the disk readahead size to 4096.
• The [sysctl] section contains some kernel parameter settings. For example, kernel.sched_min_granularity_ns sets the scheduling minimum granularity interval to 10,000,000 nanoseconds, and kernel.sched_wakeup_granularity_ns sets the scheduling wakeup granularity interval to 15,000,000 nanoseconds. In addition, there are parameter settings related to memory management, such as vm.dirty_ratio, vm.dirty_background_ratio and vm.swappiness.

The configuration block will be introduced in detail below. In addition to the configuration files corresponding to the different tuning strategies above, tuned also provides a global configuration file. This configuration file mainly configures tuned Service related configuration

┌──[[email protected]]-[/usr/lib/tuned]
└─$cat /etc/tuned/tuned-main.conf | grep -v ^#

daemon = 1 #Specify whether to use daemon mode
dynamic_tuning = 0 #Specify whether to enable dynamic adjustment. If set to 1, dynamic scaling will be enabled, otherwise only static scaling will be used.
sleep_interval = 1
update_interval = 10
recommend_command = 1
reapply_sysctl = 1
default_instance_priority = 0
udev_buffer_size = 1MB
log_file_count = 2
log_file_max_size = 1MB
┌──[[email protected]]-[/usr/lib/tuned]
└─$

Of course, we can also define our own configuration files for optimization

Customized tuning plan

You can customize the tuning plan, and tuned tuning methods are generally divided into two types: dynamic and static

• Static tuning: Apply the preset kernel parameters at one time (the kernel parameters here mainly refer to the kernel parameters in /sys or /proc )
• Dynamic tuning: tunde monitors system behavior and dynamically tunes and optimizes kernel parameters based on the behavior. For example: there is a video transcoding job. When the video is transcoded, no network connection is required. At this time, it can be reduced Network interface speed to reduce energy consumption. When the video transcoding is completed and the network interface data increases for a long time, set the interface to the maximum speed.

The /etc/tuned/ directory contains the tuned-main.conf file (global configuration file), which is mainly used for dynamic tuning, generally automatically The defined tuning plan is also placed in this location

A custom tuning plan generally copies an existing tuning plan and makes changes.

┌──[[email protected]]-[/usr/lib/tuned]
└─$cp -r /usr/lib/tuned/throughput-performance/ /etc/tuned/liruilong-performance
┌──[[email protected]]-[/usr/lib/tuned]
└─$cat /etc/tuned/liruilong-performance/tuned.conf
#
# tuned configuration
#

[main]
summary=Broadly applicable tuning that provides excellent performance across a variety of common server workloads

[cpu]
governor=performance
energy_perf_bias=performance
min_perf_pct=100

[disk]
# The default unit for readahead is KiB. This can be adjusted to sectors
# by specifying the relevant suffix, eg. (readahead => 8192 s). There must
# be at least one space between the number and suffix (if suffix is specified).
readahead=>4096

[sysctl]
# ktune sysctl settings for rhel6 servers, maximizing i/o throughput
#
# Minimal preemption granularity for CPU-bound tasks:
# (default: 1 msec# (1 + ilog(ncpus)), units: nanoseconds)
kernel.sched_min_granularity_ns = 10000000

# SCHED_OTHER wake-up granularity.
# (default: 1 msec# (1 + ilog(ncpus)), units: nanoseconds)
#
# This option delays the preemption effects of decoupled workloads
# and reduces their over-scheduling. Synchronous workloads will still
# have immediate wakeup/sleep latencies.
kernel.sched_wakeup_granularity_ns = 15000000

# If a workload mostly uses anonymous memory and it hits this limit, the entire
# working set is buffered for I/O, and any more write buffering would require
# swapping, so it's time to throttle writes until I/O can catch up. Workloads
# that mostly use file mappings may be able to use even higher values.
#
# The generator of dirty data starts writeback at this percentage (system default
# is 20%)
vm.dirty_ratio = 40

# Start background writeback (via writeback threads) at this percentage (system
# default is 10%)
vm.dirty_background_ratio = 10

# PID allocation wrap value. When the kernel's next PID value
# reaches this value, it wraps back to a minimum PID value.
# PIDs of value pid_max or larger are not allocated.
#
# A suggested value for pid_max is 1024 * <# of cpu cores/threads in system>
# e.g., a box with 32 cpus, the default of 32768 is reasonable, for 64 cpus,
# 65536, for 4096 cpus, 4194304 (which is the upper limit possible).
#kernel.pid_max = 65536

# The swappiness parameter controls the tendency of the kernel to move
# processes out of physical memory and onto the swap disk.
# 0 tells the kernel to avoid swapping processes out of physical memory
# for as long as possible
# 100 tells the kernel to aggressively swap processes out of physical memory
# and move them to swap cache
vm.swappiness=10
┌──[[email protected]]-[/usr/lib/tuned]
└─$

Regarding the tuned.conf configuration file, here is a brief explanation. You can view the corresponding information in the man manual.

┌──[[email protected]]-[/usr/lib/tuned]
└─$man tuned.conf

main

[main] is the main configuration. In main, you can include the include= statement. You can load a specific profile through the include statement. You can create a new profile based on the existing profile. If two profiles are defined If there are conflicting tuning parameters, the newly defined parameters shall prevail.

Plugins

Other configuration sections are defined as plug-ins. Each configuration section has a name. The name is the unique identifier of the plug-in. It can be arbitrary and cannot be repeated. type= Plugin type. Plug-in type, common types cpu, disk, mount, net, vm, sysctl, script, sysfs, scheduler, systemd.

If you use the plug-in name is consistent with [NAME], then type can be ignored,

View currently supported plugins:

┌──[root@hp-ProLiant-SL270s-Gen8-SE]-[~]
└─$ dpkg -L tuned | grep plugin_
/usr/lib/python3/dist-packages/tuned/plugins/plugin_audio.py
/usr/lib/python3/dist-packages/tuned/plugins/plugin_bootloader.py
/usr/lib/python3/dist-packages/tuned/plugins/plugin_cpu.py
/usr/lib/python3/dist-packages/tuned/plugins/plugin_disk.py
/usr/lib/python3/dist-packages/tuned/plugins/plugin_eeepc_she.py
/usr/lib/python3/dist-packages/tuned/plugins/plugin_irqbalance.py
/usr/lib/python3/dist-packages/tuned/plugins/plugin_modules.py
/usr/lib/python3/dist-packages/tuned/plugins/plugin_mounts.py
/usr/lib/python3/dist-packages/tuned/plugins/plugin_net.py
/usr/lib/python3/dist-packages/tuned/plugins/plugin_rtentsk.py
/usr/lib/python3/dist-packages/tuned/plugins/plugin_scheduler.py
/usr/lib/python3/dist-packages/tuned/plugins/plugin_script.py
/usr/lib/python3/dist-packages/tuned/plugins/plugin_scsi_host.py
/usr/lib/python3/dist-packages/tuned/plugins/plugin_selinux.py
/usr/lib/python3/dist-packages/tuned/plugins/plugin_service.py
/usr/lib/python3/dist-packages/tuned/plugins/plugin_sysctl.py
/usr/lib/python3/dist-packages/tuned/plugins/plugin_sysfs.py
/usr/lib/python3/dist-packages/tuned/plugins/plugin_systemd.py
/usr/lib/python3/dist-packages/tuned/plugins/plugin_usb.py
/usr/lib/python3/dist-packages/tuned/plugins/plugin_video.py
/usr/lib/python3/dist-packages/tuned/plugins/plugin_vm.py
/usr/lib/python3/dist-packages/tuned/utils/plugin_loader.py
┌──[root@hp-ProLiant-SL270s-Gen8-SE]-[~]
└─$

Check the parameters supported by the plug-in:

┌──[root@hp-ProLiant-SL270s-Gen8-SE]-[~]
└─$ cat /usr/lib/python3/dist-packages/tuned/plugins/plugin_cpu.py | grep -A 10 config_options
        def _get_config_options(self):
                return {<!-- -->
                        "load_threshold" : 0.2,
                        "latency_low" : 100,
                        "latency_high" : 1000,
                        "force_latency" : None,
                        "governor" : None,
                        "sampling_down_factor" : None,
                        "energy_perf_bias" : None,
                        "min_perf_pct" : None,
                        "max_perf_pct" : None,
┌──[root@hp-ProLiant-SL270s-Gen8-SE]-[~]
└─$ cat /usr/lib/python3/dist-packages/tuned/plugins/plugin_disk.py | grep -A 10 config_options
        def _get_config_options(cls):
                return {<!-- -->
                        "dynamic" : True, # FIXME: do we want this default?
                        "elevator" : None,
                        "apm" : None,
                        "spindown" : None,
                        "readahead" : None,
                        "readahead_multiply" : None,
                        "scheduler_quantum" : None,
                }

--
        def _get_config_options_used_by_dynamic(cls):
                return [
                        "apm",
                        "spindown",
                ]

        def _instance_init(self, instance):
                instance._has_static_tuning = True

                self._apm_errcnt = 0
                self._spindown_errcnt = 0
┌──[root@hp-ProLiant-SL270s-Gen8-SE]-[~]
└─$

Specific parameter configuration needs to be handled based on the actual situation. Here, the sysctl plug-in can directly set the kernel adjustable parameters, and the script plug-in can introduce a custom tuning script. But it needs to be used in combination with library functions. script is more used for dynamic tuning.

Watch a Demo

vim tuned.conf

[main]
# Includes plugins defined in "included" profile.
include=included
# Define my_sysctl plugin
[my_sysctl]
type=sysctl
# 256 KB default performs well experimentally.
net.core.rmem_default = 262144
net.core.wmem_default = 262144
[my_script]
type=script
script=${i:PROFILE_DIR}/profile.sh

The script plug-in supports the execution of specific scripts. The shell script is located in the /etc/tuned/profile-name directory and the script library /usr /lib/tuned/functions can be used to export commonly used functions.