/linux-5.10/Documentation/networking/ |
D | tcp-thin.rst | 14 the service quality. Extreme latencies are caused by TCP's 23 streams provoke high latencies when using TCP is unfortunate. 37 to experience high retransmission latencies.
|
/linux-5.10/Documentation/block/ |
D | kyber-iosched.rst | 5 The only two tunables for the Kyber scheduler are the target latencies for 7 these target latencies.
|
/linux-5.10/Documentation/trace/ |
D | hwlat_detector.rst | 9 detect large system latencies induced by the behavior of certain underlying 22 you are trying to keep event service latencies down in the microsecond range. 57 change to a default of 10 usecs. If any latencies that exceed the threshold is
|
/linux-5.10/drivers/gpu/drm/i915/display/ |
D | intel_display_debugfs.c | 1457 * - latencies are in us on gen9/vlv/chv in wm_latency_show() 1477 const u16 *latencies; in pri_wm_latency_show() local 1480 latencies = dev_priv->wm.skl_latency; in pri_wm_latency_show() 1482 latencies = dev_priv->wm.pri_latency; in pri_wm_latency_show() 1484 wm_latency_show(m, latencies); in pri_wm_latency_show() 1492 const u16 *latencies; in spr_wm_latency_show() local 1495 latencies = dev_priv->wm.skl_latency; in spr_wm_latency_show() 1497 latencies = dev_priv->wm.spr_latency; in spr_wm_latency_show() 1499 wm_latency_show(m, latencies); in spr_wm_latency_show() 1507 const u16 *latencies; in cur_wm_latency_show() local [all …]
|
/linux-5.10/kernel/ |
D | Kconfig.preempt | 11 throughput. It will still provide good latencies most of the 18 latencies.
|
/linux-5.10/drivers/pci/pcie/ |
D | aspm.c | 69 /* Exit latencies */ 73 * Endpoint acceptable latencies. A pcie downstream port only 408 * The exit latencies for L1 substates are not advertised in pcie_aspm_check_latency() 410 * to determine max latencies introduced by enabling L1 in pcie_aspm_check_latency() 413 * L1 exit latencies advertised by a device include L1 in pcie_aspm_check_latency() 414 * substate latencies (and hence do not do any check). in pcie_aspm_check_latency() 568 /* Configure common clock before checking latencies */ in pcie_aspm_cap_init() 573 * clock configuration. L0s & L1 exit latencies in the otherwise in pcie_aspm_cap_init() 661 /* Get and check endpoint acceptable latencies */ in pcie_aspm_cap_init() 961 /* Recheck latencies and update aspm_capable for links under the root */ [all …]
|
/linux-5.10/include/trace/events/ |
D | irq.h | 51 * out irq handler latencies. 81 * conjunction with the irq_handler_entry to understand irq handler latencies.
|
/linux-5.10/kernel/trace/ |
D | trace_hwlat.c | 5 * Use this tracer to detect large system latencies induced by the behavior of 20 * Although certain hardware-inducing latencies are necessary (for example, 29 * WARNING: This implementation necessarily introduces latencies. Therefore, 163 * get_sample - sample the CPU TSC and look for likely hardware latencies 363 * counter (TSC or similar) and look for potential hardware latencies.
|
/linux-5.10/drivers/s390/scsi/ |
D | zfcp_scsi.c | 151 zfcp_sdev->latencies.write.channel.min = 0xFFFFFFFF; in zfcp_scsi_slave_alloc() 152 zfcp_sdev->latencies.write.fabric.min = 0xFFFFFFFF; in zfcp_scsi_slave_alloc() 153 zfcp_sdev->latencies.read.channel.min = 0xFFFFFFFF; in zfcp_scsi_slave_alloc() 154 zfcp_sdev->latencies.read.fabric.min = 0xFFFFFFFF; in zfcp_scsi_slave_alloc() 155 zfcp_sdev->latencies.cmd.channel.min = 0xFFFFFFFF; in zfcp_scsi_slave_alloc() 156 zfcp_sdev->latencies.cmd.fabric.min = 0xFFFFFFFF; in zfcp_scsi_slave_alloc() 157 spin_lock_init(&zfcp_sdev->latencies.lock); in zfcp_scsi_slave_alloc()
|
D | zfcp_def.h | 277 * @latencies: FSF channel and fabric latencies 285 struct zfcp_latencies latencies; member
|
/linux-5.10/tools/perf/Documentation/ |
D | perf-sched.txt | 6 perf-sched - Tool to trace/measure scheduler properties (latencies) 20 'perf sched latency' to report the per task scheduling latencies
|
/linux-5.10/Documentation/devicetree/bindings/powerpc/opal/ |
D | power-mgt.txt | 60 - ibm,cpu-idle-state-latencies-ns: 62 exit-latencies (in ns) for the idle states in
|
/linux-5.10/arch/alpha/lib/ |
D | memcpy.c | 70 * Note the ordering to try to avoid load (and address generation) latencies. 116 * Note the ordering to try to avoid load (and address generation) latencies.
|
/linux-5.10/block/ |
D | Kconfig.iosched | 17 multiqueue and other fast devices. Given target latencies for reads and
|
D | blk-wbt.c | 6 * - Monitor latencies in a defined window of time. 10 * - For any window where we don't have solid data on what the latencies 12 * - If latencies look good, decrement scaling step. 243 * flag the latency as exceeded. wbt works off completion latencies, in latency_exceeded()
|
/linux-5.10/Documentation/admin-guide/device-mapper/ |
D | statistics.rst | 19 histogram of latencies. All these counters may be accessed by sending 74 collect histogram of latencies. The
|
/linux-5.10/Documentation/devicetree/bindings/arm/ |
D | l2c2x0.yaml | 71 read, write and setup latencies. Minimum valid values are 1. Controllers 82 read, write and setup latencies. Controllers without setup latency control
|
/linux-5.10/tools/power/cpupower/man/ |
D | cpupower-frequency-info.1 | 54 Output frequencies and latencies without rounding off values.
|
/linux-5.10/Documentation/devicetree/bindings/memory-controllers/ |
D | baikal,bt1-l2-ctl.yaml | 16 to change the Tag, Data and Way-select RAM access latencies. Baikal-T1
|
/linux-5.10/Documentation/devicetree/bindings/interconnect/ |
D | qcom,bcm-voter.yaml | 37 overridden to reduce latencies.
|
/linux-5.10/Documentation/timers/ |
D | no_hz.rst | 92 in order to avoid degrading from-idle transition latencies. 238 eliminate scheduling-clock interrupt latencies. Here are some 252 to degrade your latencies -- and that this degradation can
|
/linux-5.10/drivers/base/power/ |
D | domain_governor.c | 32 * suspend/resume latencies, so assume them to be negligible and in dev_update_qos_constraint() 115 * their suspend latencies into account here. in default_suspend_ok()
|
/linux-5.10/Documentation/driver-api/ |
D | pps.rst | 75 you should take into account the latencies and jitter introduced by 240 latencies. But if it is too small slave won't be able to capture clear edge
|
/linux-5.10/arch/sh/kernel/cpu/shmobile/ |
D | cpuidle.c | 42 * - requested_state: best mode allowed by software (latencies) in cpuidle_sleep_enter()
|
/linux-5.10/Documentation/staging/ |
D | speculation.rst | 10 To improve performance and minimize average latencies, many contemporary CPUs
|