+=====================================================
High resolution timers and dynamic ticks design notes
------------------------------------------------------
+=====================================================
Further information can be found in the paper of the OLS 2006 talk "hrtimers
and beyond". The paper is part of the OLS 2006 Proceedings Volume 1, which can
---------------------------
The hrtimer base infrastructure was merged into the 2.6.16 kernel. Details of
-the base implementation are covered in Documentation/timers/hrtimers.txt. See
+the base implementation are covered in Documentation/timers/hrtimers.rst. See
also figure #2 (OLS slides p. 15)
The main differences to the timer wheel, which holds the armed timer_list type
timers are:
+
- time ordered enqueueing into a rb-tree
- independent of ticks (the processing is based on nanoseconds)
Further information about the Generic Time Of Day framework is available in the
OLS 2005 Proceedings Volume 1:
-http://www.linuxsymposium.org/2005/linuxsymposium_procv1.pdf
+
+ http://www.linuxsymposium.org/2005/linuxsymposium_procv1.pdf
The paper "We Are Not Getting Any Younger: A New Approach to Time and
Timers" was written by J. Stultz, D.V. Hart, & N. Aravamudan.
The management layer assigns one or more of the following functions to a clock
event device:
+
- system global periodic tick (jiffies update)
- cpu local update_process_times
- cpu local profiling
available for MIPS and PowerPC.
Thomas, Ingo
-
-
-
- High Precision Event Timer Driver for Linux
+===========================================
+High Precision Event Timer Driver for Linux
+===========================================
The High Precision Event Timer (HPET) hardware follows a specification
by Intel and Microsoft, revision 1.
-
+======================================================
hrtimers - subsystem for high-resolution kernel timers
-----------------------------------------------------
+======================================================
This patch introduces a new subsystem for high-resolution kernel timers.
a given clock has - be it low-res, high-res, or artificially-low-res.
hrtimers - testing and verification
-----------------------------------
+-----------------------------------
We used the high-resolution clock subsystem ontop of hrtimers to verify
the hrtimer implementation details in praxis, and we also ran the posix
--- /dev/null
+:orphan:
+
+======
+timers
+======
+
+.. toctree::
+ :maxdepth: 1
+
+ highres
+ hpet
+ hrtimers
+ no_hz
+ timekeeping
+ timers-howto
+
+.. only:: subproject and html
+
+ Indices
+ =======
+
+ * :ref:`genindex`
- NO_HZ: Reducing Scheduling-Clock Ticks
+======================================
+NO_HZ: Reducing Scheduling-Clock Ticks
+======================================
This document describes Kconfig options and boot parameters that can
discussing testing, and a fifth and final section listing known issues.
-NEVER OMIT SCHEDULING-CLOCK TICKS
+Never Omit Scheduling-Clock Ticks
+=================================
Very old versions of Linux from the 1990s and the very early 2000s
are incapable of omitting scheduling-clock ticks. It turns out that
you should read the following two sections.
-OMIT SCHEDULING-CLOCK TICKS FOR IDLE CPUs
+Omit Scheduling-Clock Ticks For Idle CPUs
+=========================================
If a CPU is idle, there is little point in sending it a scheduling-clock
interrupt. After all, the primary purpose of a scheduling-clock interrupt
dyntick-idle mode.
-OMIT SCHEDULING-CLOCK TICKS FOR CPUs WITH ONLY ONE RUNNABLE TASK
+Omit Scheduling-Clock Ticks For CPUs With Only One Runnable Task
+================================================================
If a CPU has only one runnable task, there is little point in sending it
a scheduling-clock interrupt because there is no other task to switch to.
(yet) be enabled by default.
-RCU IMPLICATIONS
+RCU Implications
+================
There are situations in which idle CPUs cannot be permitted to
enter either dyntick-idle mode or adaptive-tick mode, the most
where you want them to run.
-TESTING
+Testing
+=======
So you enable all the OS-jitter features described in this document,
but do not see any change in your workload's behavior. Is this because
systems.
-KNOWN ISSUES
+Known Issues
+============
-o Dyntick-idle slows transitions to and from idle slightly.
+* Dyntick-idle slows transitions to and from idle slightly.
In practice, this has not been a problem except for the most
aggressive real-time workloads, which have the option of disabling
dyntick-idle mode, an option that most of them take. However,
this parameter effectively disables Turbo Mode on Intel
CPUs, which can significantly reduce maximum performance.
-o Adaptive-ticks slows user/kernel transitions slightly.
+* Adaptive-ticks slows user/kernel transitions slightly.
This is not expected to be a problem for computationally intensive
workloads, which have few such transitions. Careful benchmarking
will be required to determine whether or not other workloads
are significantly affected by this effect.
-o Adaptive-ticks does not do anything unless there is only one
+* Adaptive-ticks does not do anything unless there is only one
runnable task for a given CPU, even though there are a number
of other situations where the scheduling-clock tick is not
needed. To give but one example, consider a CPU that has one
Better handling of these sorts of situations is future work.
-o A reboot is required to reconfigure both adaptive idle and RCU
+* A reboot is required to reconfigure both adaptive idle and RCU
callback offloading. Runtime reconfiguration could be provided
if needed, however, due to the complexity of reconfiguring RCU at
runtime, there would need to be an earthshakingly good reason.
simply offloading RCU callbacks from all CPUs and pinning them
where you want them whenever you want them pinned.
-o Additional configuration is required to deal with other sources
+* Additional configuration is required to deal with other sources
of OS jitter, including interrupts and system-utility tasks
and processes. This configuration normally involves binding
interrupts and tasks to particular CPUs.
-o Some sources of OS jitter can currently be eliminated only by
+* Some sources of OS jitter can currently be eliminated only by
constraining the workload. For example, the only way to eliminate
OS jitter due to global TLB shootdowns is to avoid the unmapping
operations (such as kernel module unload operations) that
helpful, especially when combined with the mlock() and mlockall()
system calls.
-o Unless all CPUs are idle, at least one CPU must keep the
+* Unless all CPUs are idle, at least one CPU must keep the
scheduling-clock interrupt going in order to support accurate
timekeeping.
-o If there might potentially be some adaptive-ticks CPUs, there
+* If there might potentially be some adaptive-ticks CPUs, there
will be at least one CPU keeping the scheduling-clock interrupt
going, even if all CPUs are otherwise idle.
Better handling of this situation is ongoing work.
-o Some process-handling operations still require the occasional
+* Some process-handling operations still require the occasional
scheduling-clock tick. These operations include calculating CPU
load, maintaining sched average, computing CFS entity vruntime,
computing avenrun, and carrying out load balancing. They are
+===========================================================
Clock sources, Clock events, sched_clock() and delay timers
------------------------------------------------------------
+===========================================================
This document tries to briefly explain some basic kernel timekeeping
abstractions. It partly pertains to the drivers usually found in
+===================================================================
delays - Information on the various kernel delay / sleep mechanisms
--------------------------------------------------------------------
+===================================================================
This document seeks to answer the common question: "What is the
RightWay (TM) to insert a delay?"
it really need to delay in atomic context?" If so...
ATOMIC CONTEXT:
- You must use the *delay family of functions. These
+ You must use the `*delay` family of functions. These
functions use the jiffie estimation of clock speed
and will busy wait for enough loop cycles to achieve
the desired delay:
be refactored to allow for the use of msleep.
NON-ATOMIC CONTEXT:
- You should use the *sleep[_range] family of functions.
+ You should use the `*sleep[_range]` family of functions.
There are a few more options here, while any of them may
work correctly, using the "right" sleep function will
help the scheduler, power management, and just make your
driver better :)
-- Backed by busy-wait loop:
+
udelay(unsigned long usecs)
+
-- Backed by hrtimers:
+
usleep_range(unsigned long min, unsigned long max)
+
-- Backed by jiffies / legacy_timers
+
msleep(unsigned long msecs)
msleep_interruptible(unsigned long msecs)
- Unlike the *delay family, the underlying mechanism
+ Unlike the `*delay` family, the underlying mechanism
driving each of these calls varies, thus there are
quirks you should be aware of.
- Why not msleep for (1ms - 20ms)?
Explained originally here:
http://lkml.org/lkml/2007/8/3/250
+
msleep(1~20) may not do what the caller intends, and
will often sleep longer (~20 ms actual sleep for any
value given in the 1~20ms range). In many cases this
HPET: High Precision Event Timers driver
M: Clemens Ladisch <clemens@ladisch.de>
S: Maintained
-F: Documentation/timers/hpet.txt
+F: Documentation/timers/hpet.rst
F: drivers/char/hpet.c
F: include/linux/hpet.h
F: include/uapi/linux/hpet.h
/* TODO FIXME: dvb_usb_generic_rw() fails rarely with error code -32
* (EPIPE, Broken pipe). Function supports currently msleep() as a
* parameter but I would not like to use it, since according to
- * Documentation/timers/timers-howto.txt it should not be used such
+ * Documentation/timers/timers-howto.rst it should not be used such
* short, under < 20ms, sleeps. Repeating failed message would be
* better choice as not to add unwanted delays...
* Fixing that correctly is one of those or both;
*
* Delay for the requested amount of time as per the guidelines in:
*
- * Documentation/timers/timers-howto.txt
+ * Documentation/timers/timers-howto.rst
*
* The assumption here is that regulators will never be enabled in
* atomic context and therefore sleeping functions can be used.
* @cond: Break condition (usually involving @val)
* @sleep_us: Maximum time to sleep between reads in us (0
* tight-loops). Should be less than ~20ms since usleep_range
- * is used (see Documentation/timers/timers-howto.txt).
+ * is used (see Documentation/timers/timers-howto.rst).
* @timeout_us: Timeout in us, 0 means never timeout
*
* Returns 0 on success and -ETIMEDOUT upon a timeout. In either
* @cond: Break condition (usually involving @val)
* @delay_us: Time to udelay between reads in us (0 tight-loops). Should
* be less than ~10us since udelay is used (see
- * Documentation/timers/timers-howto.txt).
+ * Documentation/timers/timers-howto.rst).
* @timeout_us: Timeout in us, 0 means never timeout
*
* Returns 0 on success and -ETIMEDOUT upon a timeout. In either
* @cond: Break condition (usually involving @val)
* @sleep_us: Maximum time to sleep between reads in us (0
* tight-loops). Should be less than ~20ms since usleep_range
- * is used (see Documentation/timers/timers-howto.txt).
+ * is used (see Documentation/timers/timers-howto.rst).
* @timeout_us: Timeout in us, 0 means never timeout
*
* Returns 0 on success and -ETIMEDOUT upon a timeout or the regmap_read
* @cond: Break condition (usually involving @val)
* @sleep_us: Maximum time to sleep between reads in us (0
* tight-loops). Should be less than ~20ms since usleep_range
- * is used (see Documentation/timers/timers-howto.txt).
+ * is used (see Documentation/timers/timers-howto.rst).
* @timeout_us: Timeout in us, 0 means never timeout
*
* Returns 0 on success and -ETIMEDOUT upon a timeout or the regmap_field_read
# ignore udelay's < 10, however
if (! ($delay < 10) ) {
CHK("USLEEP_RANGE",
- "usleep_range is preferred over udelay; see Documentation/timers/timers-howto.txt\n" . $herecurr);
+ "usleep_range is preferred over udelay; see Documentation/timers/timers-howto.rst\n" . $herecurr);
}
if ($delay > 2000) {
WARN("LONG_UDELAY",
if ($line =~ /\bmsleep\s*\((\d+)\);/) {
if ($1 < 20) {
WARN("MSLEEP",
- "msleep < 20ms can sleep for up to 20ms; see Documentation/timers/timers-howto.txt\n" . $herecurr);
+ "msleep < 20ms can sleep for up to 20ms; see Documentation/timers/timers-howto.rst\n" . $herecurr);
}
}
my $max = $7;
if ($min eq $max) {
WARN("USLEEP_RANGE",
- "usleep_range should not use min == max args; see Documentation/timers/timers-howto.txt\n" . "$here\n$stat\n");
+ "usleep_range should not use min == max args; see Documentation/timers/timers-howto.rst\n" . "$here\n$stat\n");
} elsif ($min =~ /^\d+$/ && $max =~ /^\d+$/ &&
$min > $max) {
WARN("USLEEP_RANGE",
- "usleep_range args reversed, use min then max; see Documentation/timers/timers-howto.txt\n" . "$here\n$stat\n");
+ "usleep_range args reversed, use min then max; see Documentation/timers/timers-howto.rst\n" . "$here\n$stat\n");
}
}
* @cond: Break condition (usually involving @val)
* @sleep_us: Maximum time to sleep between reads in us (0
* tight-loops). Should be less than ~20ms since usleep_range
- * is used (see Documentation/timers/timers-howto.txt).
+ * is used (see Documentation/timers/timers-howto.rst).
* @timeout_us: Timeout in us, 0 means never timeout
*
* Returns 0 on success and -ETIMEDOUT upon a timeout. In either