This is not necessary on our systems and according to the documentation
will reduce code size of the allocator which will result in better
performance.
Signed-off-by: Michael Tremer <michael.tremer@ipfire.org>
Acked-by: Peter Müller <peter.mueller@ipfire.org>
Signed-off-by: Arne Fitzenreiter <arne_f@ipfire.org>
This is a new type of metric to find out what resource is currently a
bottleneck for the whole system. We might use this for graphs.
Signed-off-by: Michael Tremer <michael.tremer@ipfire.org>
Acked-by: Peter Müller <peter.mueller@ipfire.org>
Signed-off-by: Arne Fitzenreiter <arne_f@ipfire.org>
This feature is now disabled (was disabled on ARM before) as we do not
need it:
"Select this option to enable fine granularity task irq time accounting.
This is done by reading a timestamp on each transitions between softirq
and hardirq state, so there can be a small performance impact."
Signed-off-by: Michael Tremer <michael.tremer@ipfire.org>
Acked-by: Peter Müller <peter.mueller@ipfire.org>
Signed-off-by: Arne Fitzenreiter <arne_f@ipfire.org>
This change is required to make the system respond faster to any
realtime events (sending or receiving data packets).
It will wake up at least one core 1000 times a second which will result
in finer timer granularity and make scheduling smoother. HTB for
example sends large packet bursts on each timer even to keep up data
rates which is not helpful for most applications.
The change might increase resource consumption and overhead slightly on
some systems, but since we are running in an idle-dyntick configuration,
we should not keep awake any cores that have not been awake before.
Signed-off-by: Michael Tremer <michael.tremer@ipfire.org>
Acked-by: Peter Müller <peter.mueller@ipfire.org>
Signed-off-by: Arne Fitzenreiter <arne_f@ipfire.org>
the application layer gateway modules can used to bypass the nat
via nat slipstreaming. I had disabled all of them. If one is really needed
we can reenable it later.
Signed-off-by: Arne Fitzenreiter <arne_f@ipfire.org>
This will increase throughput since BBR is more modern and adjusted to
the nowadays version of the Internet whereas Cubic is more conservative
and might not always fully saturate the downlink.
Signed-off-by: Michael Tremer <michael.tremer@ipfire.org>
This will allow the kernel to seed its CRNG using RDSEED or RDRAND.
During the boot process, it is required that the CRNG is being
initialised, but it may take some long time on systems that do not have
a random number generator.
This is the default for various other distributions like Debian.
Signed-off-by: Arne Fitzenreiter <arne.fitzenreiter@ipfire.org>
Signed-off-by: Michael Tremer <michael.tremer@ipfire.org>
The kernel will try to gather entropy really early in the boot process
where those device drivers might not have been loaded yet. They are
small and can therefore be compiled into the kernel like we already do
on ARM.
Signed-off-by: Michael Tremer <michael.tremer@ipfire.org>
