Searched +full:run +full:- +full:time (Results 1 – 25 of 502) sorted by relevance
12345678910>>...21
| /Documentation/scheduler/ |
| D | sched-rt-group.rst | 2 Real-Time group scheduling
12 2.1 System-wide settings
28 resolution, or the time it takes to handle the budget refresh itself.
33 are real-time processes).
40 ---------------
42 Real-time scheduling is all about determinism, a group has to be able to rely on
43 the amount of bandwidth (eg. CPU time) being constant. In order to schedule
44 multiple groups of real-time tasks, each group must be assigned a fixed portion
45 of the CPU time available. Without a minimum guarantee a real-time group can
50 ----------------
[all …]
|
| D | sched-eevdf.rst | 9 of EEVDF proposed by Peter Zijlstra in 2023 [2-4]. More information
11 Documentation/scheduler/sched-design-CFS.rst.
13 Similarly to CFS, EEVDF aims to distribute CPU time equally among all
14 runnable tasks with the same priority. To do so, it assigns a virtual run
15 time to each task, creating a "lag" value that can be used to determine
16 whether a task has received its fair share of CPU time. In this way, a task
17 with a positive lag is owed CPU time, while a negative lag means the task
21 allows latency-sensitive tasks with shorter time slices to be prioritized,
25 tasks; but at the time of writing EEVDF uses a "decaying" mechanism based
26 on virtual run time (VRT). This prevents tasks from exploiting the system
[all …]
|
| D | sched-bwc.rst | 7 The SCHED_RT case is covered in Documentation/scheduler/sched-rt-group.rst
14 microseconds of CPU time. That quota is assigned to per-cpu run queues in
17 throttled. Throttled threads will not be able to run again until the next
22 is transferred to cpu-local "silos" on a demand basis. The amount transferred
26 -------------
27 This feature borrows time now against our future underrun, at the cost of
30 Traditional (UP-EDF) bandwidth control is something like:
36 we'd have to run more than a second of program time, and obviously miss
38 never time to catch up, unbounded fail.
52 everything is good. At the same time we have a p(5)p(5) = 0.25% chance
[all …]
|
| D | sched-util-clamp.rst | 1 .. SPDX-License-Identifier: GPL-2.0
23 system run at a certain performance point.
57 foreground, top-app, etc. Util clamp can be used to constrain how much
59 can run at. This constraint helps reserve resources for important tasks, like
60 the ones belonging to the currently active app (top-app group). Beside this
65 1. The big cores are free to run top-app tasks immediately. top-app
68 2. They don't run on a power hungry core and drain battery even if they
85 On the other hand, a busy task for instance that requires to run at maximum
88 mobile devices where frames will drop due to slow response time to select the
89 higher frequency required for the tasks to finish their work in time. Setting
[all …]
|
| D | sched-design-CFS.rst | 16 Documentation/scheduler/sched-eevdf.rst.
19 an "ideal, precise multi-tasking CPU" on real hardware.
21 "Ideal multi-tasking CPU" is a (non-existent :-)) CPU that has 100% physical
22 power and which can run each task at precise equal speed, in parallel, each at
24 each at 50% physical power --- i.e., actually in parallel.
26 On real hardware, we can run only a single task at once, so we have to
29 multi-tasking CPU described above. In practice, the virtual runtime of a task
37 In CFS the virtual runtime is expressed and tracked via the per-task
38 p->se.vruntime (nanosec-unit) value. This way, it's possible to accurately
39 timestamp and measure the "expected CPU time" a task should have gotten.
[all …]
|
| /Documentation/RCU/ |
| D | torture.rst | 1 .. SPDX-License-Identifier: GPL-2.0
13 be loaded to run a torture test. The test periodically outputs
19 Documentation/admin-guide/kernel-parameters.txt.
26 …rcu-torture:--- Start of test: nreaders=16 nfakewriters=4 stat_interval=30 verbose=0 test_no_idle_…
27 …rcu-torture: rtc: (null) ver: 155441 tfle: 0 rta: 155441 rtaf: 8884 rtf: 155440 rtmbe: 0…
28 rcu-torture: Reader Pipe: 727860534 34213 0 0 0 0 0 0 0 0 0
29 rcu-torture: Reader Batch: 727877838 17003 0 0 0 0 0 0 0 0 0
30 …rcu-torture: Free-Block Circulation: 155440 155440 155440 155440 155440 155440 155440 155440 1554…
31 …rcu-torture:--- End of test: SUCCESS: nreaders=16 nfakewriters=4 stat_interval=30 verbose=0 test_n…
37 be evident. ;-)
[all …]
|
| /Documentation/admin-guide/ |
| D | lockup-watchdogs.rst | 10 details), without giving other tasks a chance to run. The current
14 "softlockup_panic" (see "Documentation/admin-guide/kernel-parameters.rst" for
20 details), without letting other interrupts have a chance to run.
24 'hardlockup_panic', a compile time knob, "BOOTPARAM_HARDLOCKUP_PANIC",
26 (see "Documentation/admin-guide/kernel-parameters.rst" for details).
31 of time.
43 (compile-time initialized to 10 and configurable through sysctl of the
45 does not receive any hrtimer interrupt during that time the
51 timestamp every time it is scheduled. If that timestamp is not updated
64 event. The right value for a particular environment is a trade-off
[all …]
|
| /Documentation/leds/ |
| D | ledtrig-transient.rst | 8 to be off. The delay_on value specifies the time period an LED should stay
11 gets deactivated. There is no provision for one time activation to implement
36 that are active at the time driver gets suspended, continue to run, without
56 non-transient state. When driver gets suspended, irrespective of the transient
71 - duration allows setting timer value in msecs. The initial value is 0.
72 - activate allows activating and deactivating the timer specified by
75 - state allows user to specify a transient state to be held for the specified
79 - one shot timer activate mechanism.
90 - one shot timer value. When activate is set, duration value
96 - transient state to be held. It has two values 0 or 1. 0 maps
[all …]
|
| D | leds-qcom-lpg.rst | 1 .. SPDX-License-Identifier: GPL-2.0
8 -----------
31 --------------------------------
35 The pattern is a series of brightness and hold-time pairs, with the hold-time
36 expressed in milliseconds. The hold time is a property of the pattern and must
39 transitions expected by the leds-trigger-pattern format, each entry in the
40 pattern must be followed a zero-length entry of the same brightness.
48 255 +----+ +----+
50 0 | +----+ +----
51 +---------------------->
[all …]
|
| /Documentation/virt/ |
| D | paravirt_ops.rst | 1 .. SPDX-License-Identifier: GPL-2.0
12 allows a single kernel binary to run on all supported execution environments
13 including native machine -- without any hypervisors.
16 corresponding to low-level critical instructions and high-level
17 functionalities in various areas. pv_ops allows for optimizations at run
18 time by enabling binary patching of the low-level critical operations
19 at boot time.
23 - simple indirect call
24 These operations correspond to high-level functionality where it is
27 - indirect call which allows optimization with binary patch
[all …]
|
| /Documentation/driver-api/dmaengine/ |
| D | dmatest.rst | 16 test multiple channels at the same time, and it can start multiple threads
21 capability of the following: DMA_MEMCPY (memory-to-memory), DMA_MEMSET
22 (const-to-memory or memory-to-memory, when emulated), DMA_XOR, DMA_PQ.
28 Part 1 - How to build the test module
33 Device Drivers -> DMA Engine support -> DMA Test client
38 Part 2 - When dmatest is built as a module
43 % modprobe dmatest timeout=2000 iterations=1 channel=dma0chan0 run=1
51 % echo 1 > /sys/module/dmatest/parameters/run
55 dmatest.timeout=2000 dmatest.iterations=1 dmatest.channel=dma0chan0 dmatest.run=1
57 Example of multi-channel test usage (new in the 5.0 kernel)::
[all …]
|
| /Documentation/dev-tools/kunit/ |
| D | start.rst | 1 .. SPDX-License-Identifier: GPL-2.0
8 teaching how to run existing tests and then how to write a simple test case,
9 and covers common problems users face when using KUnit for the first time.
14 build the kernel, you can run KUnit.
20 can run kunit_tool:
22 .. code-block:: bash
24 ./tools/testing/kunit/kunit.py run
28 "The source tree is not clean, please run 'make ARCH=um mrproper'"
32 through the argument ``--build_dir``. Hence, before starting an
33 out-of-tree build, the source tree must be clean.
[all …]
|
| D | run_manual.rst | 1 .. SPDX-License-Identifier: GPL-2.0
4 Run Tests without kunit_tool
8 with other systems, or run tests on real hardware), we can
18 KUnit tests can run without kunit_tool. This can be useful, if:
20 - We have an existing kernel configuration to test.
21 - Need to run on real hardware (or using an emulator/VM kunit_tool
23 - Wish to integrate with some existing testing systems.
38 Once we have built our kernel (and/or modules), it is simple to run
39 the tests. If the tests are built-in, they will run automatically on the
43 If the tests are built as modules, they will run when the module is
[all …]
|
| D | run_wrapper.rst | 1 .. SPDX-License-Identifier: GPL-2.0
7 We can either run KUnit tests using kunit_tool or can run tests
8 manually, and then use kunit_tool to parse the results. To run tests
9 manually, see: Documentation/dev-tools/kunit/run_manual.rst.
10 As long as we can build the kernel, we can run KUnit.
15 Run command:
17 .. code-block::
19 ./tools/testing/kunit/kunit.py run
23 .. code-block::
31 .. code-block::
[all …]
|
| /Documentation/locking/ |
| D | locktorture.rst | 18 acquire the lock and hold it for specific amount of time, thus simulating
20 can be simulated by either enlarging this critical region hold time and/or
30 Locktorture-specific
31 --------------------
49 - "lock_busted":
52 - "spin_lock":
55 - "spin_lock_irq":
58 - "rw_lock":
61 - "rw_lock_irq":
65 - "mutex_lock":
[all …]
|
| /Documentation/driver-api/thermal/ |
| D | cpu-cooling-api.rst | 22 --------------------------------------------
30 "thermal-cpufreq-%x". This api can support multiple instances of cpufreq
42 the name "thermal-cpufreq-%x" linking it with a device tree node, in
54 This interface function unregisters the "thermal-cpufreq-%x" cooling device.
63 supported currently). This power model requires that the operating-points of
73 - The time the processor spends running, consuming dynamic power, as
74 compared to the time in idle states where dynamic consumption is
76 - The voltage and frequency levels as a result of DVFS. The DVFS
78 - In running time the 'execution' behaviour (instruction types, memory
85 Pdyn = f(run) * Voltage^2 * Frequency * Utilisation
[all …]
|
| /Documentation/power/ |
| D | runtime_pm.rst | 5 (C) 2009-2011 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
18 put their PM-related work items. It is strongly recommended that pm_wq be
20 them to be synchronized with system-wide power transitions (suspend to RAM,
53 The ->runtime_suspend(), ->runtime_resume() and ->runtime_idle() callbacks
57 1. PM domain of the device, if the device's PM domain object, dev->pm_domain,
60 2. Device type of the device, if both dev->type and dev->type->pm are present.
62 3. Device class of the device, if both dev->class and dev->class->pm are
65 4. Bus type of the device, if both dev->bus and dev->bus->pm are present.
69 dev->driver->pm directly (if present).
73 and bus type. Moreover, the high-priority one will always take precedence over
[all …]
|
| /Documentation/trace/coresight/ |
| D | coresight-perf.rst | 1 .. SPDX-License-Identifier: GPL-2.0
4 CoreSight - Perf
15 perf record -e cs_etm//u testbinary
17 This would run some test binary (testbinary) until it exits and record
22 perf report --stdio --dump -i perf.data
26 …ERF_RECORD_AUXTRACE size: 0x11dd0 offset: 0 ref: 0x1b614fc1061b0ad1 idx: 0 tid: 531230 cpu: -1
48 for the support such as libopencsd and libopencsd-dev or download it
60 ------------------------
81 Perf test - Verify kernel and userspace perf CoreSight work
82 -----------------------------------------------------------
[all …]
|
| /Documentation/admin-guide/pm/ |
| D | cpuidle.rst | 1 .. SPDX-License-Identifier: GPL-2.0
8 CPU Idle Time Management
27 CPU idle time management is an energy-efficiency feature concerned about using
31 ------------
33 CPU idle time management operates on CPUs as seen by the *CPU scheduler* (that
37 software as individual single-core processors. In other words, a CPU is an
43 program) at a time, it is a CPU. In that case, if the hardware is asked to
46 Second, if the processor is multi-core, each core in it is able to follow at
47 least one program at a time. The cores need not be entirely independent of each
48 other (for example, they may share caches), but still most of the time they
[all …]
|
| /Documentation/mm/damon/ |
| D | maintainer-profile.rst | 1 .. SPDX-License-Identifier: GPL-2.0
10 linux-mm@kvack.org. Patches should be made against the `mm-unstable tree
11 <https://git.kernel.org/akpm/mm/h/mm-unstable>`_ whenever possible and posted
15 ---------
20 Sufficiently reviewed patches will be queued in `mm-unstable
21 <https://git.kernel.org/akpm/mm/h/mm-unstable>`_ by the memory management
23 in `mm-stable <https://git.kernel.org/akpm/mm/h/mm-stable>`_, and finally
24 pull-requested to the mainline by the memory management subsystem maintainer.
26 Note again the patches for `mm-unstable tree
27 <https://git.kernel.org/akpm/mm/h/mm-unstable>`_ are queued by the memory
[all …]
|
| /Documentation/virt/kvm/ |
| D | halt-polling.rst | 1 .. SPDX-License-Identifier: GPL-2.0
9 for some time period after the guest has elected to no longer run by cedeing.
12 before giving up the cpu to the scheduler in order to let something else run.
14 Polling provides a latency advantage in cases where the guest can be run again
16 the order of a few micro-seconds, although performance benefits are workload
20 wakeup periods where the time spent halt polling is minimised and the time
27 The powerpc kvm-hv specific case is implemented in:
34 The maximum time for which to poll before invoking the scheduler, referred to
39 kvm_vcpu->halt_poll_ns
41 or in the case of powerpc kvm-hv, in the vcore struct:
[all …]
|
| /Documentation/ABI/testing/ |
| D | sysfs-devices-power | 40 space to control the run-time power management of the device.
45 + "auto\n" to allow the device to be power managed at run time;
51 from power managing the device at run time. Doing that while
61 with the main suspend/resume thread) during system-wide power
86 attribute is read-only. If the device is not capable to wake up
98 is read-only. If the device is not capable to wake up the
110 state in progress. This attribute is read-only. If the device
122 read-only. If the device is not capable to wake up the system
133 the device is being processed (1). This attribute is read-only.
144 the total time of processing wakeup events associated with the
[all …]
|
| /Documentation/sound/designs/ |
| D | seq-oss.rst | 15 What this does - it provides the emulation of the OSS sequencer, access
17 The most of applications using OSS can run if the appropriate ALSA
51 You can run two or more applications simultaneously (even for OSS
53 However, each MIDI device is exclusive - that is, if a MIDI device
57 * Real-time event processing:
59 The events can be processed in real time without using out of bound
60 ioctl. To switch to real-time mode, send ABSTIME 0 event. The followed
61 events will be processed in real-time without queued. To switch off the
62 real-time mode, send RELTIME 0 event.
67 ``/proc/asound/seq/oss`` at any time. In the later version,
[all …]
|
| /Documentation/admin-guide/mm/ |
| D | ksm.rst | 8 KSM is a memory-saving de-duplication feature, enabled by CONFIG_KSM=y,
19 content which can be replaced by a single write-protected page (which
22 and the time between the passes are configured using :ref:`sysfs
47 may suddenly require more memory than is available - possibly failing
48 with EAGAIN, but more probably arousing the Out-Of-Memory killer.
60 will exceed ``vm.max_map_count`` (see Documentation/admin-guide/sysctl/vm.rst).
84 been set to scan-time.
105 when there are no ksm shared pages in the system: set run 2 to
111 run
113 * set to 1 to run ksmd e.g. ``echo 1 > /sys/kernel/mm/ksm/run``,
[all …]
|
| /Documentation/driver-api/mmc/ |
| D | mmc-async-req.rst | 11 pre-fetch makes the cache overhead relatively significant. If the DMA
15 The intention of non-blocking (asynchronous) MMC requests is to minimize the
16 time between when an MMC request ends and another MMC request begins.
19 dma_unmap_sg are processing. Using non-blocking MMC requests makes it
26 The mmc_blk_issue_rw_rq() in the MMC block driver is made non-blocking.
28 The increase in throughput is proportional to the time it takes to
31 more significant the prepare request time becomes. Roughly the expected
33 platform. In power save mode, when clocks run on a lower frequency, the DMA
34 preparation may cost even more. As long as these slower preparations are run
40 https://wiki.linaro.org/WorkingGroups/Kernel/Specs/StoragePerfMMC-async-req
[all …]
|
12345678910>>...21