| /linux/net/netfilter/ipvs/ |
| H A D | Kconfig | 14 single IP address and scheduling them to real servers.
18 server via direct routing. The several scheduling algorithms can
116 tristate "round-robin scheduling"
118 The robin-robin scheduling algorithm simply directs network
125 tristate "weighted round-robin scheduling"
127 The weighted robin-robin scheduling algorithm directs network
138 tristate "least-connection scheduling"
140 The least-connection scheduling algorithm directs network
148 tristate "weighted least-connection scheduling"
150 The weighted least-connection scheduling algorithm directs network
[all …]
|
| H A D | ip_vs_wlc.c | 3 * IPVS: Weighted Least-Connection Scheduling module
10 * Wensong Zhang : changed to use the inactconns in scheduling
26 * Weighted Least Connection scheduling
35 IP_VS_DBG(6, "ip_vs_wlc_schedule(): Scheduling...\n"); in ip_vs_wlc_schedule()
|
| H A D | ip_vs_nq.c | 3 * IPVS: Never Queue scheduling module
15 * Expected Delay scheduling algorithm).
50 * Weighted Least Connection scheduling
59 IP_VS_DBG(6, "%s(): Scheduling...\n", __func__); in ip_vs_nq_schedule()
|
| H A D | ip_vs_sed.c | 3 * IPVS: Shortest Expected Delay scheduling module
28 * WLC, while scheduling big jobs under larger heterogeneous systems
54 * Weighted Least Connection scheduling
63 IP_VS_DBG(6, "%s(): Scheduling...\n", __func__); in ip_vs_sed_schedule()
|
| H A D | ip_vs_lc.c | 3 * IPVS: Least-Connection Scheduling module
21 * Least Connection scheduling
30 IP_VS_DBG(6, "%s(): Scheduling...\n", __func__); in ip_vs_lc_schedule()
|
| H A D | ip_vs_ovf.c | 3 * IPVS: Overflow-Connection Scheduling module
23 /* OVF Connection scheduling */
31 IP_VS_DBG(6, "ip_vs_ovf_schedule(): Scheduling...\n"); in ip_vs_ovf_schedule()
|
| /linux/Documentation/timers/ |
| H A D | no_hz.rst | 2 NO_HZ: Reducing Scheduling-Clock Ticks
7 reduce the number of scheduling-clock interrupts, thereby improving energy
12 There are three main ways of managing scheduling-clock interrupts
13 (also known as "scheduling-clock ticks" or simply "ticks"):
15 1. Never omit scheduling-clock ticks (CONFIG_HZ_PERIODIC=y or
19 2. Omit scheduling-clock ticks on idle CPUs (CONFIG_NO_HZ_IDLE=y or
23 3. Omit scheduling-clock ticks on CPUs that are either idle or that
33 Never Omit Scheduling-Clock Ticks
37 are incapable of omitting scheduling-clock ticks. It turns out that
42 hundreds of microseconds). For these types of workloads, scheduling
[all …]
|
| /linux/Documentation/admin-guide/hw-vuln/ |
| H A D | core-scheduling.rst | 4 Core Scheduling
6 Core scheduling support allows userspace to define groups of tasks that can
19 scheduling is a scheduler feature that can mitigate some (not all) cross-HT
24 world workloads. In theory, core scheduling aims to perform at least as good as
26 not always: as synchronizing scheduling decisions across 2 or more CPUs in a
29 scheduling to perform more poorly compared to SMT-disabled, where N_CPUS is the
34 Core scheduling support is enabled via the ``CONFIG_SCHED_CORE`` config option.
38 doing its best to satisfy the system's scheduling requirements.
40 Core scheduling can be enabled via the ``PR_SCHED_CORE`` prctl interface.
41 This interface provides support for the creation of core scheduling groups, as
[all …]
|
| /linux/Documentation/scheduler/ |
| H A D | sched-deadline.rst | 2 Deadline Task Scheduling
9 2. Scheduling algorithm
12 3. Scheduling Real-Time Tasks
33 system behavior. As for -rt (group) scheduling, it is assumed that root users
40 The SCHED_DEADLINE policy contained inside the sched_dl scheduling class is
41 basically an implementation of the Earliest Deadline First (EDF) scheduling
46 2. Scheduling algorithm
57 every time the task wakes up, the scheduler computes a "scheduling deadline"
59 scheduled using EDF[1] on these scheduling deadlines (the task with the
60 earliest scheduling deadline is selected for execution). Notice that the
[all …]
|
| H A D | sched-rt-group.rst | 2 Real-Time group scheduling
42 Real-time scheduling is all about determinism, a group has to be able to rely on
90 The scheduling period that is equivalent to 100% CPU bandwidth.
93 A global limit on how much time real-time scheduling may use. This is always
121 Real-time group scheduling means you have to assign a portion of total CPU
153 There is work in progress to make the scheduling period for each group
158 as its prone to starvation without deadline scheduling.
175 The next project will be SCHED_EDF (Earliest Deadline First scheduling) to bring
176 full deadline scheduling to the linux kernel. Deadline scheduling the above
182 the limited static priority levels 0-99. With deadline scheduling you need to
|
| H A D | sched-design-CFS.rst | 121 scheduling modules are used. The balancing code got quite a bit simpler as a
126 5. Scheduling policies
129 CFS implements three scheduling policies:
131 - SCHED_NORMAL (traditionally called SCHED_OTHER): The scheduling
151 6. SCHEDULING CLASSES
154 The new CFS scheduler has been designed in such a way to introduce "Scheduling
156 encapsulate scheduling policy details and are handled by the scheduler core
166 Scheduling classes are implemented through the sched_class structure, which
175 It puts the scheduling entity (task) into the red-black tree and
181 corresponding scheduling entity out of the red-black tree. It decrements
[all …]
|
| H A D | sched-capacity.rst | 2 Capacity Aware Scheduling
133 Capacity aware scheduling requires an expression of a task's requirements with
248 This means that while the capacity aware scheduling criteria will be written
252 3. Capacity aware scheduling requirements
269 As stated in 2.2, capacity-aware scheduling requires a frequency-invariant task
331 5. Capacity aware scheduling implementation
340 The main capacity scheduling criterion of CFS is::
370 Wakeup CPU selection in CFS can be eclipsed by Energy Aware Scheduling
406 the CPU capacity scheduling criterion is violated, and there may not be any more
427 CPUs can satisfy this capacity criterion, then strict priority based scheduling
|
| H A D | sched-domains.rst | 5 Each CPU has a "base" scheduling domain (struct sched_domain). The domain
10 Each scheduling domain spans a number of CPUs (stored in the ->span field).
19 Each scheduling domain must have one or more CPU groups (struct sched_group)
26 flag is set on the corresponding scheduling domain and its groups may not be
|
| H A D | sched-energy.rst | 2 Energy Aware Scheduling
8 Energy Aware Scheduling (or EAS) gives the scheduler the ability to predict
20 because this is where the potential for saving energy through scheduling is
88 scheduling domains are built, or re-built. For each root domain (rd), the
312 (than CFS) scheduling classes (as well as IRQ) must be taken into account. As
314 by CFS tasks, but also by the other scheduling classes and IRQ.
320 Energy Aware Scheduling depends on the CPUs of the system having specific
331 looking for the presence of the SD_ASYM_CPUCAPACITY_FULL flag when the scheduling
345 EAS uses the EM of a platform to estimate the impact of scheduling decisions on
350 Please also note that the scheduling domains need to be re-built after the
|
| /linux/include/uapi/linux/sched/ |
| H A D | types.h | 11 * Extended scheduling parameters data structure.
24 * Scheduling Class Attributes
28 * scheduling policy and relative POSIX attributes:
32 * @sched_policy task's scheduling policy
36 * Certain more advanced scheduling features can be controlled by a
49 * - the maximum (or average, depending on the actual scheduling
65 * Given this task model, there are a multiplicity of scheduling algorithms
69 * As of now, the SCHED_DEADLINE policy (sched_dl scheduling class) is the
71 * available in the scheduling class file or in Documentation/.
|
| /linux/kernel/ |
| H A D | Kconfig.preempt | 29 raw processing power of the kernel, irrespective of scheduling
119 bool "Core Scheduling for SMT"
122 This option permits Core Scheduling, a means of coordinated task
137 bool "Extensible Scheduling Class"
142 allows scheduling policies to be implemented as BPF programs to
146 iteration of new scheduling policies.
151 scheduling policies in production environments.
155 wish to implement scheduling policies. The struct_ops structure
|
| /linux/Documentation/block/ |
| H A D | ioprio.rst | 10 similar to what has been possible with cpu scheduling for ages. Support for io
14 Scheduling classes
17 Three generic scheduling classes are implemented for io priorities that
20 IOPRIO_CLASS_RT: This is the realtime io class. This scheduling class is given
29 IOPRIO_CLASS_BE: This is the best-effort scheduling class, which is the default
36 IOPRIO_CLASS_IDLE: This is the idle scheduling class, processes running at this
53 will run ls at the best-effort scheduling class at the highest priority.
58 will change pid 100 to run at the realtime scheduling class, at priority 2.
|
| /linux/net/sched/ |
| H A D | Kconfig | 46 comment "Queueing/Scheduling"
52 packet scheduling algorithm. See
66 (HFSC) packet scheduling algorithm.
93 packet scheduling algorithm.
104 packet scheduling algorithm.
115 packet scheduling algorithm.
126 scheduling algorithm. This queueing discipline allows the combination
138 scheduling algorithm.
149 scheduling algorithm.
160 scheduling algorithm.
[all …]
|
| /linux/tools/perf/pmu-events/arch/arm64/arm/cortex-a65-e1/ |
| H A D | ifu.json | 69 "PublicDescription": "This thread and the other thread both ready for scheduling in if0",
72 "BriefDescription": "This thread and the other thread both ready for scheduling in if0"
75 …blicDescription": "This thread was arbitrated when the other thread was also ready for scheduling",
78 …BriefDescription": "This thread was arbitrated when the other thread was also ready for scheduling"
87 …ription": "This thread was not arbitrated because it was not ready for scheduling. For example, du…
90 …"BriefDescription": "This thread was not arbitrated because it was not ready for scheduling. For e…
|
| /linux/drivers/gpu/drm/amd/include/ |
| H A D | kgd_kfd_interface.h | 82 * @KFD_SCHED_POLICY_HWS: H/W scheduling policy known as command processor (cp)
83 * scheduling. In this scheduling mode we're using the firmware code to
89 * in this scheduling mode user mode queues over subscription feature is
95 * @KFD_SCHED_POLICY_NO_HWS: no H/W scheduling policy is a mode which directly
168 * This function is used only for no cp scheduling mode.
171 * scheduling mode. Only used for no cp scheduling mode.
195 * Only used for no cp scheduling mode
|
| /linux/drivers/net/ethernet/chelsio/cxgb4/ |
| H A D | sched.c | 87 * value (TX Scheduling Class in this case). in t4_sched_bind_unbind_op()
387 * cxgb4_sched_class_bind - Bind an entity to a scheduling class
392 * Binds an entity (queue) to a scheduling class. If the entity
436 * cxgb4_sched_class_unbind - Unbind an entity from a scheduling class
441 * Unbinds an entity (queue) from a scheduling class.
496 /* Look for a class with matching scheduling parameters */ in t4_sched_class_lookup()
573 * cxgb4_sched_class_alloc - allocate a scheduling class
575 * @p: new scheduling class to create.
577 * Returns pointer to the scheduling class created. If @p is NULL, then
578 * it allocates and returns any available unused scheduling class. If a
[all …]
|
| /linux/drivers/accel/ivpu/ |
| H A D | vpu_jsm_api.h | 38 * Number of Priority Bands for Hardware Scheduling
117 * For HWS command queue scheduling, we can prioritise command queues inside the
125 * For HWS priority scheduling, we can have multiple realtime priority bands.
266 * aborted and removed from internal scheduling queues. All doorbells assigned
302 /** Control command: Set context scheduling properties */
404 /** Response to control command: Set context scheduling properties */
458 * This structure supports doorbell registration for only OS scheduling.
476 * Request structure to unregister a doorbell for both HW and OS scheduling.
655 * and HW scheduling.
668 * and HW scheduling.
[all …]
|
| /linux/tools/sched_ext/ |
| H A D | scx_simple.bpf.c | 6 * be switched to FIFO scheduling. It also demonstrates the following niceties.
13 * the scheduling queue is shared across all CPUs means that whatever is at the
15 * number of CPUs. The FIFO scheduling mode may be beneficial to some workloads
16 * but comes with the usual problems with FIFO scheduling where saturating
36 * from. If scx_simple only supported global FIFO scheduling, then we could
|
| H A D | scx_central.bpf.c | 5 * a. Making all scheduling decisions from one CPU:
7 * The central CPU is the only one making scheduling decisions. All other
37 * SCX_KICK_PREEMPT is used to trigger scheduling and CPUs to move to the
41 * more practical implementation would likely put the scheduling loop outside
236 * Force dispatch on the scheduling CPU so that it finds a task in BPF_STRUCT_OPS()
348 * We are offloading all scheduling decisions to the central CPU
|
| /linux/tools/perf/Documentation/ |
| H A D | perf-sched.txt | 17 'perf sched record <command>' to record the scheduling events
20 'perf sched latency' to report the per task scheduling latencies
21 and other scheduling properties of the workload.
59 'perf sched timehist' provides an analysis of scheduling events.
67 task scheduling delay (time between runnable and actually running) and
173 Show only a summary of scheduling by thread with min, max, and average
178 Show all scheduling events followed by a summary by thread with min,
|