| /linux/net/netfilter/ipvs/ |
| H A D | ip_vs_sched.c | 28 * IPVS scheduler list
37 * Bind a service with a scheduler
40 struct ip_vs_scheduler *scheduler) in ip_vs_bind_scheduler() argument
44 if (scheduler->init_service) { in ip_vs_bind_scheduler()
45 ret = scheduler->init_service(svc); in ip_vs_bind_scheduler()
51 rcu_assign_pointer(svc->scheduler, scheduler); in ip_vs_bind_scheduler()
57 * Unbind a service with its scheduler
63 sched = rcu_dereference_protected(svc->scheduler, 1); in ip_vs_unbind_scheduler()
67 /* Reset the scheduler before initiating any RCU callbacks */ in ip_vs_unbind_scheduler()
68 rcu_assign_pointer(svc->scheduler, NULL); in ip_vs_unbind_scheduler()
[all …]
|
| /linux/drivers/gpu/drm/i915/gvt/ |
| H A D | sched_policy.c | 135 struct intel_gvt_workload_scheduler *scheduler = &gvt->scheduler; in try_to_schedule_next_vgpu() local
142 * let scheduler chose next_vgpu again by setting it to NULL. in try_to_schedule_next_vgpu()
144 if (scheduler->next_vgpu == scheduler->current_vgpu) { in try_to_schedule_next_vgpu()
145 scheduler->next_vgpu = NULL; in try_to_schedule_next_vgpu()
153 scheduler->need_reschedule = true; in try_to_schedule_next_vgpu()
157 if (scheduler->current_workload[engine->id]) in try_to_schedule_next_vgpu()
162 vgpu_update_timeslice(scheduler->current_vgpu, cur_time); in try_to_schedule_next_vgpu()
163 vgpu_data = scheduler->next_vgpu->sched_data; in try_to_schedule_next_vgpu()
167 scheduler->current_vgpu = scheduler->next_vgpu; in try_to_schedule_next_vgpu()
168 scheduler->next_vgpu = NULL; in try_to_schedule_next_vgpu()
[all …]
|
| /linux/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/ |
| H A D | core-imp-def.json | 219 "PublicDescription": "Dispatch stall due to IXU scheduler entries",
222 "BriefDescription": "Dispatch stall due to IXU scheduler entries"
225 "PublicDescription": "Dispatch stall due to FSU scheduler entries",
228 "BriefDescription": "Dispatch stall due to FSU scheduler entries"
285 "PublicDescription": "Instructions issued by the scheduler",
288 "BriefDescription": "Instructions issued by the scheduler"
297 "PublicDescription": "A load wakeup to the scheduler has been canceled",
300 "BriefDescription": "A load wakeup to the scheduler has been canceled"
303 "PublicDescription": "The scheduler had to cancel one slow Uop due to resource conflict",
306 "BriefDescription": "The scheduler had to cancel one slow Uop due to resource conflict"
[all …]
|
| /linux/Documentation/scheduler/ |
| H A D | sched-ext.rst | 4 Extensible Scheduler Class
7 sched_ext is a scheduler class whose behavior can be defined by a set of BPF
8 programs - the BPF scheduler.
13 * The BPF scheduler can group CPUs however it sees fit and schedule them
16 * The BPF scheduler can be turned on and off dynamically anytime.
18 * The system integrity is maintained no matter what the BPF scheduler does.
23 * When the BPF scheduler triggers an error, debug information is dumped to
25 scheduler binary. The debug dump can also be accessed through the
27 triggers a debug dump. This doesn't terminate the BPF scheduler and can
47 sched_ext is used only when the BPF scheduler is loaded and running.
[all …]
|
| H A D | sched-nice-design.rst | 2 Scheduler Nice Design
6 nice-levels implementation in the new Linux scheduler.
12 scheduler, (otherwise we'd have done it long ago) because nice level
16 In the O(1) scheduler (in 2003) we changed negative nice levels to be
77 With the old scheduler, if you for example started a niced task with +1
88 The new scheduler in v2.6.23 addresses all three types of complaints:
91 enough), the scheduler was decoupled from 'time slice' and HZ concepts
94 support: with the new scheduler nice +19 tasks get a HZ-independent
96 scheduler.
99 the new scheduler makes nice(1) have the same CPU utilization effect on
[all …]
|
| H A D | sched-energy.rst | 8 Energy Aware Scheduling (or EAS) gives the scheduler the ability to predict
23 The actual EM used by EAS is _not_ maintained by the scheduler, but by a
50 scheduler. This alternative considers two objectives: energy-efficiency and
53 The idea behind introducing an EM is to allow the scheduler to evaluate the
56 time, the EM must be as simple as possible to minimize the scheduler latency
60 for the scheduler to decide where a task should run (during wake-up), the EM
71 EAS (as well as the rest of the scheduler) uses the notion of 'capacity' to
87 The scheduler manages references to the EM objects in the topology code when the
89 scheduler maintains a singly linked list of all performance domains intersecting
115 Please note that the scheduler will create two duplicate list nodes for
[all …]
|
| /linux/tools/perf/pmu-events/arch/arm64/ampere/ampereone/ |
| H A D | core-imp-def.json | 219 "PublicDescription": "Dispatch stall due to IXU scheduler entries",
222 "BriefDescription": "Dispatch stall due to IXU scheduler entries"
225 "PublicDescription": "Dispatch stall due to FSU scheduler entries",
228 "BriefDescription": "Dispatch stall due to FSU scheduler entries"
297 "PublicDescription": "Instructions issued by the scheduler",
300 "BriefDescription": "Instructions issued by the scheduler"
309 "PublicDescription": "A load wakeup to the scheduler has been cancelled",
312 "BriefDescription": "A load wakeup to the scheduler has been cancelled"
315 "PublicDescription": "The scheduler had to cancel one slow Uop due to resource conflict",
318 "BriefDescription": "The scheduler had to cancel one slow Uop due to resource conflict"
[all …]
|
| /linux/Documentation/block/ |
| H A D | switching-sched.rst | 2 Switching Scheduler
5 Each io queue has a set of io scheduler tunables associated with it. These
6 tunables control how the io scheduler works. You can find these entries
16 It is possible to change the IO scheduler for a given block device on
20 To set a specific scheduler, simply do this::
22 echo SCHEDNAME > /sys/block/DEV/queue/scheduler
24 where SCHEDNAME is the name of a defined IO scheduler, and DEV is the
28 a "cat /sys/block/DEV/queue/scheduler" - the list of valid names
29 will be displayed, with the currently selected scheduler in brackets::
31 # cat /sys/block/sda/queue/scheduler
[all …]
|
| H A D | deadline-iosched.rst | 2 Deadline IO scheduler tunables
5 This little file attempts to document how the deadline io scheduler works.
12 selecting an io scheduler on a per-device basis.
19 The goal of the deadline io scheduler is to attempt to guarantee a start
21 tunable. When a read request first enters the io scheduler, it is assigned
49 When we have to move requests from the io scheduler queue to the block
60 Sometimes it happens that a request enters the io scheduler that is contiguous
69 rbtree front sector lookup when the io scheduler merge function is called.
|
| /linux/Documentation/gpu/rfc/ |
| H A D | i915_scheduler.rst | 2 I915 GuC Submission/DRM Scheduler Section
8 i915 with the DRM scheduler is:
14 * Lots of rework will need to be done to integrate with DRM scheduler so
32 * Convert the i915 to use the DRM scheduler
33 * GuC submission backend fully integrated with DRM scheduler
35 handled in DRM scheduler)
36 * Resets / cancels hook in DRM scheduler
37 * Watchdog hooks into DRM scheduler
39 integrated with DRM scheduler (e.g. state machine gets
41 * Execlists backend will minimum required to hook in the DRM scheduler
[all …]
|
| /linux/kernel/sched/ext/ |
| H A D | internal.h | 3 * BPF extensible scheduler class: Documentation/scheduler/sched-ext.rst
54 SCX_EXIT_PARENT_KILL, /* killed by parent scheduler */
98 * scx_exit_info is passed to ops.exit() to describe why the BPF scheduler is
149 * scheduler depends on pid lookup for dispatching, the task will be
153 * dispatched to the local DSQ on enqueue. If the BPF scheduler doesn't
185 * As the BPF scheduler may depend on ops.select_cpu() being invoked
189 * the BPF scheduler must be able to handle ops.enqueue() invoked on the
209 * scheduler can recover task pointers from stored tids via
212 * Only the root scheduler turns this on. A sub-sched may set the flag
213 * to declare a dependency on the lookup; if the root scheduler hasn't
[all …]
|
| /linux/tools/sched_ext/ |
| H A D | README.md | 51 In order to run a sched_ext scheduler, you'll have to run a kernel compiled
86 example, using vmlinux.h allows a scheduler to access fields defined directly
101 bpf_printk("Task %s enabled in example scheduler", p->comm);
112 The scheduler build system will generate this vmlinux.h file as part of the
113 scheduler build pipeline. It looks for a vmlinux file in the following
156 For more scheduler implementations, tools and documentation, visit
161 A simple scheduler that provides an example of a minimal sched_ext scheduler.
164 Though very simple, in limited scenarios, this scheduler can perform reasonably
169 Another simple, yet slightly more complex scheduler tha
[all...] |
| H A D | scx_userland.c | 3 * A demo sched_ext user space scheduler which provides vruntime semantics
7 * the need to do any load balancing between domains. The scheduler could
35 "A minimal userland sched_ext scheduler.\n"
94 * deadlock. A more substantive user space scheduler could e.g. provide a hook
95 * for newly enabled tasks that are passed to the scheduler from the
96 * .prep_enable() callback to allows the scheduler to allocate on safe paths.
214 * user space scheduler could look like. in vruntime_enqueue()
344 * Enforce that the user scheduler task is managed by sched_ext. The in pre_bootstrap()
346 * loop, and then yields the CPU. The BPF scheduler only schedules the in pre_bootstrap()
347 * user space scheduler task when at least one other task in the system in pre_bootstrap()
[all …]
|
| H A D | scx_pair.bpf.c | 3 * A demo sched_ext core-scheduler which always makes every sibling CPU pair
6 * This scheduler is a minimal implementation and would need some form of
11 * "stride" value that can be specified when the BPF scheduler program is first
12 * loaded. Throughout the runtime of the scheduler, these CPU pairs guarantee
15 * Scheduler Initialization
18 * The scheduler BPF program is first initialized from user space, before it is
37 * loads the scheduler. By default, the stride is 1/2 the total number of CPUs.
42 * Every cgroup in the system is registered with the scheduler using the
44 * exactly one cgroup. At a high level, the idea with the pair scheduler is to
50 * If you look through the implementation of the scheduler, you'll notice that
[all …]
|
| /linux/block/ |
| H A D | Kconfig.iosched | 5 tristate "MQ deadline I/O scheduler"
8 MQ version of the deadline IO scheduler.
11 tristate "Kyber I/O scheduler"
14 The Kyber I/O scheduler is a low-overhead scheduler suitable for
20 tristate "BFQ I/O scheduler"
23 BFQ I/O scheduler for BLK-MQ. BFQ distributes the bandwidth of
|
| /linux/drivers/net/wireless/intel/iwlegacy/ |
| H A D | prph.h | 236 /* 3945 Tx scheduler registers */
247 * Tx Scheduler
249 * The Tx Scheduler selects the next frame to be transmitted, choosing TFDs
275 * 1) Scheduler-Ack, in which the scheduler automatically supports a
281 * In scheduler-ack mode, the scheduler keeps track of the Tx status of
292 * 2) FIFO (a.k.a. non-Scheduler-ACK), in which each TFD is processed in order.
300 * Driver controls scheduler operation via 3 means:
301 * 1) Scheduler registers
302 * 2) Shared scheduler data base in internal 4956 SRAM
313 * the scheduler (especially for queue #4/#9, the command queue, otherwise
[all …]
|
| /linux/kernel/trace/rv/monitors/sts/ |
| H A D | Kconfig | 11 Monitor to ensure relationships between scheduler and task switches
12 * the scheduler is called and returns with interrupts disabled
13 * each call to the scheduler has up to one switch
14 * switches only happen inside the scheduler
15 * each call to the scheduler disables interrupts to switch
|
| /linux/drivers/gpu/drm/panthor/ |
| H A D | panthor_sched.c | 40 * DOC: Scheduler
67 * FW-scheduler, we use the 1:1 entity:scheduler mode, such that each
68 * entity has its own job scheduler. When a job is ready to be executed
143 * struct panthor_scheduler - Object used to manage the scheduler
150 * @wq: Workqueue used by our internal scheduler logic and
153 * Used for the scheduler tick, group update or other kind of FW
164 * blocking the rest of the scheduler if the allocation tries to
188 * FW event processing to the scheduler workqueue.
215 * @lock: Lock protecting access to all the scheduler fields.
287 /** @pm.has_ref: True if the scheduler owns a runtime PM reference. */
[all …]
|
| /linux/tools/perf/pmu-events/arch/x86/amdzen3/ |
| H A D | other.json | 28 …have been stalled due to a Token Stall. FP scheduler resource stall. Applies to ops that use the F…
46 …roup is valid but does not get dispatched due to a token stall. Integer Scheduler miscellaneous re…
82 …but does not get dispatched due to a token stall. No tokens for Integer Scheduler Queue 3 availabl…
88 …but does not get dispatched due to a token stall. No tokens for Integer Scheduler Queue 2 availabl…
94 …but does not get dispatched due to a token stall. No tokens for Integer Scheduler Queue 1 availabl…
100 …but does not get dispatched due to a token stall. No tokens for Integer Scheduler Queue 0 availabl…
|
| /linux/kernel/ |
| H A D | Kconfig.preempt | 79 bool "Scheduler controlled preemption model"
84 This option provides a scheduler driven preemption model that
102 low level and critical code paths (entry code, scheduler, low
104 execution contexts under scheduler control.
179 This option enables a new scheduler class sched_ext (SCX), which
188 - Rapid scheduler deployments: Non-disruptive swap outs of
198 Documentation/scheduler/sched-ext.rst
|
| /linux/tools/perf/pmu-events/arch/x86/amdzen6/ |
| H A D | decode.json | 70 …h group is valid but does not get dispatched due to unavailability of integer scheduler 0 tokens.",
76 …h group is valid but does not get dispatched due to unavailability of integer scheduler 1 tokens.",
82 …h group is valid but does not get dispatched due to unavailability of integer scheduler 2 tokens.",
88 …h group is valid but does not get dispatched due to unavailability of integer scheduler 3 tokens.",
94 …h group is valid but does not get dispatched due to unavailability of integer scheduler 4 tokens.",
100 …h group is valid but does not get dispatched due to unavailability of integer scheduler 5 tokens.",
|
| /linux/drivers/net/ethernet/qualcomm/ppe/ |
| H A D | ppe_config.c | 7 * QM(queue management) and scheduler configs.
73 * enum ppe_scheduler_direction - PPE scheduler direction for packet.
74 * @PPE_SCH_INGRESS: Scheduler for the packet on ingress,
75 * @PPE_SCH_EGRESS: Scheduler for the packet on egress,
90 * Configure the scheduler settings for accessing and releasing the PPE buffers.
101 * struct ppe_scheduler_qm_config - PPE arbitration for scheduler config.
102 * @ensch_port_bmp: Port bit map for enqueue scheduler.
103 * @ensch_port: Port ID to enqueue scheduler.
104 * @desch_port: Port ID to dequeue scheduler.
106 * @desch_backup_port: Backup port ID to dequeue scheduler.
[all …]
|
| /linux/include/linux/sched/ |
| H A D | ext.h | 3 * BPF extensible scheduler class: Documentation/scheduler/sched-ext.rst
21 * %SCX_SLICE_DFL is used to refill slices when the BPF scheduler misses
80 * buffer between the scheduler core and the BPF scheduler. See the
228 /* BPF scheduler modifiable fields */
232 * by the task's scheduler. Set it when enqueuing via
247 * BPF scheduler. Modifying it while a task is queued on a dsq may
272 * Can be set from ops.init_task() while the BPF scheduler is being
277 * ops.init_task() invocation, such as during fork, fails the scheduler.
|
| /linux/net/sched/ |
| H A D | Kconfig | 16 If you say N here, you will get the standard packet scheduler, which
75 scheduler.
83 Say Y here if you want to use an n-band queue packet scheduler
173 tristate "Time Aware Priority (taprio) Scheduler"
208 tristate "Deficit Round Robin scheduler (DRR)"
219 tristate "Multi-queue priority scheduler (MQPRIO)"
222 Say Y here if you want to use the Multi-queue Priority scheduler.
223 This scheduler allows QOS to be offloaded on NICs that have support
232 tristate "SKB priority queue scheduler (SKBPRIO)"
235 scheduler. This schedules packets according to skb->priority,
[all …]
|
| /linux/tools/perf/pmu-events/arch/x86/amdzen4/ |
| H A D | other.json | 81 "BriefDescription": "Number of cycles dispatch is stalled for floating-point scheduler tokens.",
93 … "BriefDescription": "Number of cycles dispatch is stalled for integer scheduler queue 0 tokens.",
99 … "BriefDescription": "Number of cycles dispatch is stalled for integer scheduler queue 1 tokens.",
105 … "BriefDescription": "Number of cycles dispatch is stalled for integer scheduler queue 2 tokens.",
111 … "BriefDescription": "Number of cycles dispatch is stalled for integer scheduler queue 3 tokens.",
|