- Accueil
- Forums
- OsLand
- Optimisation Windows
- Réduire la latence sous W10
Réduire la latence sous W10
Posté le: 10 août 2019 à 15:05 
Bonjour,
je m'intéresse depuis récemment sur les différentes façons d'agir sur la latence Windows.
Je suis passé entre autre par LatencyMon pour faire un audit de la chose, dont voici la capture d'écran :
et voici le détails des "stats" :
_________________________________________________________________________________________________________
CONCLUSION
_________________________________________________________________________________________________________
Your system appears to be suitable for handling real-time audio and other tasks without dropouts.
LatencyMon has been analyzing your system for 0:02:45 (h:mm:ss) on all processors.
_________________________________________________________________________________________________________
SYSTEM INFORMATION
_________________________________________________________________________________________________________
Computer name: DESKTOP-JOE95SV
OS version: Windows 10 , 10.0, version 1809, build: 17763 (x64)
Hardware: Z370P D3, Gigabyte Technology Co., Ltd., Z370P D3-CF
CPU: GenuineIntel Intel(R) Core(TM) i5-8400 CPU @ 2.80GHz
Logical processors: 6
Processor groups: 1
RAM: 8136 MB total
_________________________________________________________________________________________________________
CPU SPEED
_________________________________________________________________________________________________________
Reported CPU speed: 2808 MHz
Note: reported execution times may be calculated based on a fixed reported CPU speed. Disable variable speed settings like Intel Speed Step and AMD Cool N Quiet in the BIOS setup for more accurate results.
WARNING: the CPU speed that was measured is only a fraction of the CPU speed reported. Your CPUs may be throttled back due to variable speed settings and thermal issues. It is suggested that you run a utility which reports your actual CPU frequency and temperature.
_________________________________________________________________________________________________________
MEASURED INTERRUPT TO USER PROCESS LATENCIES
_________________________________________________________________________________________________________
The interrupt to process latency reflects the measured interval that a usermode process needed to respond to a hardware request from the moment the interrupt service routine started execution. This includes the scheduling and execution of a DPC routine, the signaling of an event and the waking up of a usermode thread from an idle wait state in response to that event.
Highest measured interrupt to process latency (µs): 109,0
Average measured interrupt to process latency (µs): 2,222493
Highest measured interrupt to DPC latency (µs): 84,40
Average measured interrupt to DPC latency (µs): 0,639904
_________________________________________________________________________________________________________
REPORTED ISRs
_________________________________________________________________________________________________________
Interrupt service routines are routines installed by the OS and device drivers that execute in response to a hardware interrupt signal.
Highest ISR routine execution time (µs): 45,748575
Driver with highest ISR routine execution time: Wdf01000.sys - Runtime de l’infrastructure de pilotes en mode noyau, Microsoft Corporation
Highest reported total ISR routine time (%): 0,000461
Driver with highest ISR total time: Wdf01000.sys - Runtime de l’infrastructure de pilotes en mode noyau, Microsoft Corporation
Total time spent in ISRs (%) 0,000508
ISR count (execution time <250 µs): 4470
ISR count (execution time 250-500 µs): 0
ISR count (execution time 500-999 µs): 0
ISR count (execution time 1000-1999 µs): 0
ISR count (execution time 2000-3999 µs): 0
ISR count (execution time >=4000 µs): 0
_________________________________________________________________________________________________________
REPORTED DPCs
_________________________________________________________________________________________________________
DPC routines are part of the interrupt servicing dispatch mechanism and disable the possibility for a process to utilize the CPU while it is interrupted until the DPC has finished execution.
Highest DPC routine execution time (µs): 102,409544
Driver with highest DPC routine execution time: dxgkrnl.sys - DirectX Graphics Kernel, Microsoft Corporation
Highest reported total DPC routine time (%): 0,021276
Driver with highest DPC total execution time: rspLLL64.sys - Resplendence Latency Monitoring and Auxiliary Kernel Library, Resplendence Software Projects Sp.
Total time spent in DPCs (%) 0,042187
DPC count (execution time <250 µs): 353955
DPC count (execution time 250-500 µs): 0
DPC count (execution time 500-999 µs): 0
DPC count (execution time 1000-1999 µs): 0
DPC count (execution time 2000-3999 µs): 0
DPC count (execution time >=4000 µs): 0
_________________________________________________________________________________________________________
REPORTED HARD PAGEFAULTS
_________________________________________________________________________________________________________
Hard pagefaults are events that get triggered by making use of virtual memory that is not resident in RAM but backed by a memory mapped file on disk. The process of resolving the hard pagefault requires reading in the memory from disk while the process is interrupted and blocked from execution.
NOTE: some processes were hit by hard pagefaults. If these were programs producing audio, they are likely to interrupt the audio stream resulting in dropouts, clicks and pops. Check the Processes tab to see which programs were hit.
Process with highest pagefault count: mspaint.exe
Total number of hard pagefaults 103
Hard pagefault count of hardest hit process: 66
Number of processes hit: 6
_________________________________________________________________________________________________________
PER CPU DATA
_________________________________________________________________________________________________________
CPU 0 Interrupt cycle time (s): 4,605918
CPU 0 ISR highest execution time (µs): 45,748575
CPU 0 ISR total execution time (s): 0,005025
CPU 0 ISR count: 4470
CPU 0 DPC highest execution time (µs): 102,409544
CPU 0 DPC total execution time (s): 0,407902
CPU 0 DPC count: 351747
_________________________________________________________________________________________________________
CPU 1 Interrupt cycle time (s): 2,914411
CPU 1 ISR highest execution time (µs): 0,0
CPU 1 ISR total execution time (s): 0,0
CPU 1 ISR count: 0
CPU 1 DPC highest execution time (µs): 49,090456
CPU 1 DPC total execution time (s): 0,003130
CPU 1 DPC count: 734
[b]_________________________________________________________________________________________________________
CPU 2 Interrupt cycle time (s): 2,274612
CPU 2 ISR highest execution time (µs): 0,0
CPU 2 ISR total execution time (s): 0,0
CPU 2 ISR count: 0
CPU 2 DPC highest execution time (µs): 58,637821
CPU 2 DPC total execution time (s): 0,002169
CPU 2 DPC count: 429
_________________________________________________________________________________________________________
CPU 3 Interrupt cycle time (s): 2,132740
CPU 3 ISR highest execution time (µs): 0,0
CPU 3 ISR total execution time (s): 0,0
CPU 3 ISR count: 0
CPU 3 DPC highest execution time (µs): 48,405983
CPU 3 DPC total execution time (s): 0,001221
CPU 3 DPC count: 267
_________________________________________________________________________________________________________
CPU 4 Interrupt cycle time (s): 1,979494
CPU 4 ISR highest execution time (µs): 0,0
CPU 4 ISR total execution time (s): 0,0
CPU 4 ISR count: 0
CPU 4 DPC highest execution time (µs): 49,173077
CPU 4 DPC total execution time (s): 0,001890
CPU 4 DPC count: 439
_________________________________________________________________________________________________________
CPU 5 Interrupt cycle time (s): 1,728682
CPU 5 ISR highest execution time (µs): 0,0
CPU 5 ISR total execution time (s): 0,0
CPU 5 ISR count: 0
CPU 5 DPC highest execution time (µs): 42,064459
CPU 5 DPC total execution time (s): 0,001423
CPU 5 DPC count: 339
_________________________________________________________________________________________________________
[/b]
Qu'en pensez-vous ? J'ai beaucoup de latence ? Par quel biais je peux encore la réduire selon vous ?
merci.
je m'intéresse depuis récemment sur les différentes façons d'agir sur la latence Windows.
Je suis passé entre autre par LatencyMon pour faire un audit de la chose, dont voici la capture d'écran :
et voici le détails des "stats" :
_________________________________________________________________________________________________________
CONCLUSION
_________________________________________________________________________________________________________
Your system appears to be suitable for handling real-time audio and other tasks without dropouts.
LatencyMon has been analyzing your system for 0:02:45 (h:mm:ss) on all processors.
_________________________________________________________________________________________________________
SYSTEM INFORMATION
_________________________________________________________________________________________________________
Computer name: DESKTOP-JOE95SV
OS version: Windows 10 , 10.0, version 1809, build: 17763 (x64)
Hardware: Z370P D3, Gigabyte Technology Co., Ltd., Z370P D3-CF
CPU: GenuineIntel Intel(R) Core(TM) i5-8400 CPU @ 2.80GHz
Logical processors: 6
Processor groups: 1
RAM: 8136 MB total
_________________________________________________________________________________________________________
CPU SPEED
_________________________________________________________________________________________________________
Reported CPU speed: 2808 MHz
Note: reported execution times may be calculated based on a fixed reported CPU speed. Disable variable speed settings like Intel Speed Step and AMD Cool N Quiet in the BIOS setup for more accurate results.
WARNING: the CPU speed that was measured is only a fraction of the CPU speed reported. Your CPUs may be throttled back due to variable speed settings and thermal issues. It is suggested that you run a utility which reports your actual CPU frequency and temperature.
_________________________________________________________________________________________________________
MEASURED INTERRUPT TO USER PROCESS LATENCIES
_________________________________________________________________________________________________________
The interrupt to process latency reflects the measured interval that a usermode process needed to respond to a hardware request from the moment the interrupt service routine started execution. This includes the scheduling and execution of a DPC routine, the signaling of an event and the waking up of a usermode thread from an idle wait state in response to that event.
Highest measured interrupt to process latency (µs): 109,0
Average measured interrupt to process latency (µs): 2,222493
Highest measured interrupt to DPC latency (µs): 84,40
Average measured interrupt to DPC latency (µs): 0,639904
_________________________________________________________________________________________________________
REPORTED ISRs
_________________________________________________________________________________________________________
Interrupt service routines are routines installed by the OS and device drivers that execute in response to a hardware interrupt signal.
Highest ISR routine execution time (µs): 45,748575
Driver with highest ISR routine execution time: Wdf01000.sys - Runtime de l’infrastructure de pilotes en mode noyau, Microsoft Corporation
Highest reported total ISR routine time (%): 0,000461
Driver with highest ISR total time: Wdf01000.sys - Runtime de l’infrastructure de pilotes en mode noyau, Microsoft Corporation
Total time spent in ISRs (%) 0,000508
ISR count (execution time <250 µs): 4470
ISR count (execution time 250-500 µs): 0
ISR count (execution time 500-999 µs): 0
ISR count (execution time 1000-1999 µs): 0
ISR count (execution time 2000-3999 µs): 0
ISR count (execution time >=4000 µs): 0
_________________________________________________________________________________________________________
REPORTED DPCs
_________________________________________________________________________________________________________
DPC routines are part of the interrupt servicing dispatch mechanism and disable the possibility for a process to utilize the CPU while it is interrupted until the DPC has finished execution.
Highest DPC routine execution time (µs): 102,409544
Driver with highest DPC routine execution time: dxgkrnl.sys - DirectX Graphics Kernel, Microsoft Corporation
Highest reported total DPC routine time (%): 0,021276
Driver with highest DPC total execution time: rspLLL64.sys - Resplendence Latency Monitoring and Auxiliary Kernel Library, Resplendence Software Projects Sp.
Total time spent in DPCs (%) 0,042187
DPC count (execution time <250 µs): 353955
DPC count (execution time 250-500 µs): 0
DPC count (execution time 500-999 µs): 0
DPC count (execution time 1000-1999 µs): 0
DPC count (execution time 2000-3999 µs): 0
DPC count (execution time >=4000 µs): 0
_________________________________________________________________________________________________________
REPORTED HARD PAGEFAULTS
_________________________________________________________________________________________________________
Hard pagefaults are events that get triggered by making use of virtual memory that is not resident in RAM but backed by a memory mapped file on disk. The process of resolving the hard pagefault requires reading in the memory from disk while the process is interrupted and blocked from execution.
NOTE: some processes were hit by hard pagefaults. If these were programs producing audio, they are likely to interrupt the audio stream resulting in dropouts, clicks and pops. Check the Processes tab to see which programs were hit.
Process with highest pagefault count: mspaint.exe
Total number of hard pagefaults 103
Hard pagefault count of hardest hit process: 66
Number of processes hit: 6
_________________________________________________________________________________________________________
PER CPU DATA
_________________________________________________________________________________________________________
CPU 0 Interrupt cycle time (s): 4,605918
CPU 0 ISR highest execution time (µs): 45,748575
CPU 0 ISR total execution time (s): 0,005025
CPU 0 ISR count: 4470
CPU 0 DPC highest execution time (µs): 102,409544
CPU 0 DPC total execution time (s): 0,407902
CPU 0 DPC count: 351747
_________________________________________________________________________________________________________
CPU 1 Interrupt cycle time (s): 2,914411
CPU 1 ISR highest execution time (µs): 0,0
CPU 1 ISR total execution time (s): 0,0
CPU 1 ISR count: 0
CPU 1 DPC highest execution time (µs): 49,090456
CPU 1 DPC total execution time (s): 0,003130
CPU 1 DPC count: 734
[b]_________________________________________________________________________________________________________
CPU 2 Interrupt cycle time (s): 2,274612
CPU 2 ISR highest execution time (µs): 0,0
CPU 2 ISR total execution time (s): 0,0
CPU 2 ISR count: 0
CPU 2 DPC highest execution time (µs): 58,637821
CPU 2 DPC total execution time (s): 0,002169
CPU 2 DPC count: 429
_________________________________________________________________________________________________________
CPU 3 Interrupt cycle time (s): 2,132740
CPU 3 ISR highest execution time (µs): 0,0
CPU 3 ISR total execution time (s): 0,0
CPU 3 ISR count: 0
CPU 3 DPC highest execution time (µs): 48,405983
CPU 3 DPC total execution time (s): 0,001221
CPU 3 DPC count: 267
_________________________________________________________________________________________________________
CPU 4 Interrupt cycle time (s): 1,979494
CPU 4 ISR highest execution time (µs): 0,0
CPU 4 ISR total execution time (s): 0,0
CPU 4 ISR count: 0
CPU 4 DPC highest execution time (µs): 49,173077
CPU 4 DPC total execution time (s): 0,001890
CPU 4 DPC count: 439
_________________________________________________________________________________________________________
CPU 5 Interrupt cycle time (s): 1,728682
CPU 5 ISR highest execution time (µs): 0,0
CPU 5 ISR total execution time (s): 0,0
CPU 5 ISR count: 0
CPU 5 DPC highest execution time (µs): 42,064459
CPU 5 DPC total execution time (s): 0,001423
CPU 5 DPC count: 339
_________________________________________________________________________________________________________
[/b]
Qu'en pensez-vous ? J'ai beaucoup de latence ? Par quel biais je peux encore la réduire selon vous ?
merci.
0 pour,0
girok @
Agriculteur
2444pts
Inscrit le: 30 janvier 2011
Age: 37
Messages: 743
Navigateur : n.c.
Hors ligne
Agriculteur
2444pts
Inscrit le: 30 janvier 2011
Age: 37
Messages: 743
Navigateur : n.c.
Hors ligne
Posté le: 10 août 2019 à 15:23
salut j'utilise timertool.exe pour reduire la latence
trolled by girok
trolled by girok
0 pour,0
Posté le: 10 août 2019 à 15:38
| girok a écrit: |
| salut j'utilise timertool.exe pour reduire la latence |
Salut, moi il est à 15 le current. Je dois le mettre à 0.5 et valider ?
0 pour,0
Posté le: 10 août 2019 à 15:39
perso j'ai mis à 0.5 et ça a immédiatement réduit sensiblement la latence de l'ISR routine,
et un peu le DPC routine
et un peu le DPC routine
0 pour,0
rimaille @
Cultivateur
1141pts
Inscrit le: 16 septembre 2011
Age: 45
Messages: 782
Localisation: Sisteron
Navigateur : n.c.
Hors ligne
Cultivateur
1141pts
Inscrit le: 16 septembre 2011
Age: 45
Messages: 782
Localisation: Sisteron
Navigateur : n.c.
Hors ligne
Posté le: 10 août 2019 à 16:07
Salut, par curiosité, pour quelle raison veux-tu réduire la latence du kernel windows ?
Parceque sous Linux, la seule raison valable pour jouer avec un kernel basse latence (aka real time kernel) c'est la création musicale, et encore, seulement si on veut faire de l'acquisition/traitement temps réel.
Parceque sous Linux, la seule raison valable pour jouer avec un kernel basse latence (aka real time kernel) c'est la création musicale, et encore, seulement si on veut faire de l'acquisition/traitement temps réel.
0 pour,0
Posté le: 10 août 2019 à 16:09
salut
pour avoir un système globalement plus réactif et ce quelque soit l'occupation du moment
pour avoir un système globalement plus réactif et ce quelque soit l'occupation du moment
0 pour,0
rimaille @
Cultivateur
1141pts
Inscrit le: 16 septembre 2011
Age: 45
Messages: 782
Localisation: Sisteron
Navigateur : n.c.
Hors ligne
Cultivateur
1141pts
Inscrit le: 16 septembre 2011
Age: 45
Messages: 782
Localisation: Sisteron
Navigateur : n.c.
Hors ligne
Posté le: 10 août 2019 à 16:16
Sous windows, je ne sais pas... mais sous Linux le temps réel implique moins de sécurité (on chuite certains mécanisme pour gagner en temps de réaction), moins de fiabilité sur le scheduler, et paradoxalement par rapport à ton objectif une baisse globale des performances, vérifiable en bench.
0 pour,0
Posté le: 10 août 2019 à 16:20
probablement.
je n'en suis qu'au début de mes explorations.
et pour le moment j'observe un système un peu plus réactif, car avant même d'avoir testé Timertool j'avais déjà désactivé pas mal de choses visiblement inutiles dans windows et depuis j'avais constaté une meilleure réactivité.
quand à TimerTool là pour le moment je ne saurais dire si ça apporte un vrai plus ou pas de "perceptible".
je n'en suis qu'au début de mes explorations.
et pour le moment j'observe un système un peu plus réactif, car avant même d'avoir testé Timertool j'avais déjà désactivé pas mal de choses visiblement inutiles dans windows et depuis j'avais constaté une meilleure réactivité.
quand à TimerTool là pour le moment je ne saurais dire si ça apporte un vrai plus ou pas de "perceptible".
0 pour,0
- Accueil
- Forums
- OsLand
- Optimisation Windows
- Réduire la latence sous W10
Vous ne pouvez pas poster de nouveaux sujets dans ce forum
Vous ne pouvez pas répondre aux sujets dans ce forum
Vous ne pouvez pas éditer vos messages dans ce forum
Vous ne pouvez pas supprimer vos messages dans ce forum
Vous ne pouvez pas voter dans les sondages de ce forum
Sujets similaires |
|||||
| Sujet | Auteur | Forum | Réponses | Posté le | |
|---|---|---|---|---|---|
 |
J'ose pas sous-titrer | Alfie | Blagues | 1 | 12 mars 2024 à 14:32 |
 |
Wifi dans parking sous sol en copropriété | Jess | Périphériques | 7 | 22 février 2024 à 19:59 |
|
[WB] Virtu du Ghetto sous OMV et FM2 | mini-pouce | Virtualisation | 2 | 12 octobre 2023 à 19:01 |
|
Enormes ralentissements sous Chrome et dans les vidéos | Tonton_Sodomax | Questions diverses... | 7 | 09 octobre 2023 à 17:55 |
|
Test clavier Sin65 de Wind Studio, un bonheur sous les do... | SebastienD | Claviers et souris | 0 | 18 septembre 2023 à 14:27 |
- 10:15 Test alimentation Enermax PlatiGemini 1200 : L'excellence ?
- 10:06 AMD propose les drivers Adrenalin Edition 24.4.1 WHQL
- 09:06 X Silent Edge : Du bloc ATX 3.1 100 % passif en 850 et 1100 watts par Cooler Master
- 08:50 ATTENTION, plus que deux jours pour gagner une RTX 4080 SUPER AMP EXTREME AIRO avec ZOTAC, NVIDIA et Cowcotland
- 08:49 Ressens toute la puissance d'Anakin avec la sauce TRUFF
- 08:42 Cooler Master libère ses alimentation V Platinum V2
- 08:13 ASTRIA 200 et ASTRIA 400, Thermaltake à fond dans le RGB
- 08:03 Le futur arrive chez Cooler Master avec le MasterBox 600
- 07:53 [Maj] ASUS NUC 14 ROG, les premiers tarifs tombent : RTX 4070 et Core Ultra 9 pour 2499 €
- 07:43 Surprise, Thermalright passe désormais au kit AIO sans ventilateur
Insatisfaction du jour 2024 [ Le poulailler ]
Kaptain_K7 il y a 6 minutes.
Enermax PlatiGemini 1200 : Le retour en grâce !!! [ Alimentations ]
mantidor il y a 22 minutes.
Topic Cinema [ Le poulailler ]
YoNeL il y a 17 minutes.
Flight Simulator 2020 (Performance in-game) [ Jeux pc ]
Mick996 il y a 22 minutes.
Le Gros LOL du jour 2024 [ Le poulailler ]
Gaek_Shao il y a 33 minutes.- Satisfaction du jour 2024 [ Le poulailler ]
Kaptain_K7 il y a 3 heures. 
Conseils de pro pour un 1er watercooling rigide [ Watercooling ]
hakoss il y a 10 heures.
Vos jeux du moment [ GameLand ]
Bibi09 il y a 10 heures.
[Workblog] Funky et la PAO [ Graphisme ]
funkydata il y a 20 heures.
Le truc intéressant du jour - 2024 [ Le poulailler ]
eldran64 il y a 20 heures.- Tous les forums