Login to Account Create an Account
How to get the cause of high CPU usage by DPC / Interrupt
Posted 27 April 2013 - 02:57 PM
Posted 27 April 2013 - 02:57 PM
Edited by Malphas, 27 April 2013 - 03:31 PM.
Posted 28 April 2013 - 12:39 AM
nvidia_DPC.png 110.37KB 6 downloads
Total = 2962 for module nvlddmkm.sys
Elapsed Time, > 0 usecs AND <= 1 usecs, 26, or 0.88%
Elapsed Time, > 1 usecs AND <= 2 usecs, 20, or 0.68%
Elapsed Time, > 2 usecs AND <= 4 usecs, 137, or 4.63%
Elapsed Time, > 4 usecs AND <= 8 usecs, 257, or 8.68%
Elapsed Time, > 8 usecs AND <= 16 usecs, 492, or 16.61%
Elapsed Time, > 16 usecs AND <= 32 usecs, 1645, or 55.54%
Elapsed Time, > 32 usecs AND <= 64 usecs, 324, or 10.94%
Elapsed Time, > 524288 usecs AND <= 1048576 usecs, 0, or 0.00%
Elapsed Time, > 1048576 usecs AND <= 2097152 usecs, 9, or 0.30%
Elapsed Time, > 2097152 usecs , 9, or 0.30%
tr the latest Beta driver:
and put the GPU into a different PCIe x16 slot if you have more of them.
Posted 28 April 2013 - 01:06 AM
Posted 03 May 2013 - 08:51 AM
i want your help. i am encountering the same problem but i have windows xp and i dont know how to run the compand promt steps.
i am waiting for your reply.
Posted 03 May 2013 - 09:37 AM
Copy the WPT folder from a 32Bit Windows to XP and run the commands I posted.
Posted 09 May 2013 - 03:29 AM
- Intel Core i3-3225 3.30GHz (Ivybridge) Socket LGA1155 Processor (55W) - Retail **High Performance IGP**
- Sapphire HD 7750 Low Profile Edition 1024MB GDDR5 PCI-Express Graphics Card
- Asus P8H77-I Intel H77 (Socket 1155) DDR3 MiniITX Motherboard
- Corsair Force Series 3 120GB SATA 2.5" 6Gb/s Solid State Drive
- Streacom Nano 150w HTPC Power Supply/Adapter
- Streacom ST-F7CB EVO HTPC Aluminium Case - Black
- Corsair XMS3 8GB (2x4GB) DDR3 PC3-10666C9 1333MHz Dual Channel Kit
I'm sure the low wattage of the PSU jumps out to people but I do not believe it to be the issue. I can run fairly demanding games no issue for upto an hour or more then what seems to be audio or usb keyboard lockups cause the pc to freeze. I have also ran prime95 (cpu and ram stress test) and furmark (gpu stress test) at the same time for 15 minutes both pushing their respective components at 100% all the way through with no mouse lockups, no freezes and no BSOD's. I also ran memtest on my RAM no issues showed up. So I feel I can rule out processor, gpu and RAM as issues.
Yet as I mentioned I had these lockups while gaming, randomly occurring when browsing or when playing music. I run Windows 8, yet had these issues occur on Windows 7. The issues actually occurred so frequently on Windows 7 it prompted me to move to Windows 8.
The pc is hooked upto my TV through HDMI, the keyboard and mouse is a wireless logitech k400 combi connected with a logitech unifying usb dongle, network connectivity is generally through an Edimax wifi dongle. After much searching I found the issues to be related to DPC latency where I tested it with LatencyMon it pointed to USBPORT.SYS - USB 1.1 & 2.0 Port Driver being the culprit for highest IRC and DRC. And steam.exe for pagefaults. LatencyMon would only run for a few seconds before locking up sometimes it would unlock intermittently so I could stop the test. Othertimes I would BSOD with DPC watchdog timeout. I updated my BIOS and SSD firmware to the latest versions and the issues persisted.
So to troubleshoot issues I carried out the Windows 8 reset where it reinstalls itself but doesn't need the key reactivating. It gave me a clean slate to test from. I installed initially only drivers listed on the asus website for my motherboard. Then tried newer updates directly from Intel, ATI etc. as the crashes and BSOD's still persisted when running LatencyMon.
Issues persisted with USBPORT.SYS - USB 1.1 & 2.0 Port Driver so I moved my usb devices to my USB 3.0 ports and the IRC reported issues with storport.sys - Microsoft Storage Port Driver, Microsoft Corporation
and DRC Wdf01000.sys - Kernel Mode Driver Framework Runtime, Microsoft Corporation. The SSD is set to AHCI mode in windows and bios, I installed the latest Intel Rapid Storage Technology drivers. This got rid of storport.sys as highest IRC and Wdf01000.sys took up that title.
I kept the system lean with little programs installed and tried out different hardware settings and combinations.
- Turned windows defender on demand scanning off as it showed up in LatencyMon.
- The audio was running through my ATI graphics card and using ATI audio drivers, I disabled the onboard sound in device manager. Issues persisted with BSOD'ing (DPC watchdog timeout) and freezing in latencymon.
- Removed the ATI audio drivers, still BSOD'ing and freezing in latencymon.
- Turned pagefiles and indexing off.
- HPET was activated in BIOS but not windows, so I switched it on in windows: bcdedit /set useplatformclock true restarted the computer confirmed it was working and still BSOD'ing and freezing in latencymon.
- Turned Intel Speedstep and Thermal Throttling off in BIOS, no change.
- Turned HPET off in BIOS and windows, no change.
- Removed the GPU and its drivers and catalyst control centre and ran through the onboard graphics firstly without the Intel HD4000 drivers with BSOD'ing and freezing in latencymon.
- With the Intel HD4000 drivers, no change.
- The system actually seems less stable and more prone to random freezes and BSOD's without the dedicated graphics.
- The usb devices were in the USB 3.0 ports at this time, when I moved the usb devices one at and time and both onto usb 2 ports the USBPORT.SYS started to show up in latencymon again whenever a usb device was in these ports with freezes and BSOD's.
- I removed the usb wifi dongle and used ethernet, no change.
- Removed the logitech unifying dongle and used TeamViewer to control the PC so no usb devices present, no change.
- Tried with no network connectivity and using my Logitech k400, no change.
After finding this thread I tried to record xperf but the system freezes requiring a hard reset or BSOD's so nothing is saved. Attached my latest latencymon results, as you can see I could only run it for 1 second as it would consistently freezes after 3 seconds, sometimes unfreeze for a split second to update the clock but not long enough to click stop. But mostly it would just BSOD with DPC watchdog timeout.
I am almost certain its an RMA of the motherboard to ASUS but would like some second opinions before I do.
Posted 09 May 2013 - 11:19 AM
Which issues do you have?
Posted 09 May 2013 - 12:42 PM
according to the latencymon report your PC has no DPC/ISR issues.
Which issues do you have?
I know what I posted was a wall of text sorry. But when I run latencymon I can only run it a few seconds until the whole pc locks up and usually bsod saying DPC watchdog timeout.
Posted 09 May 2013 - 03:50 PM
Tried a trace although not sure if i kept it going long enough, near the end my system began to become jerky: DCP_Interupt
Also attached minidump. Also have a memory dump here: memory.dmp (from last night with Intel thermal throttling and speedstep off)
EDIT another trace (i did open event viewer while running the trace): DPC_interupt 2
The annoying thing is I have arranged a RMA on the mobo today but i will hold off sending it for now!!
EDIT 2 Got a BSOD and minidump attached. 050913-5625-01.dmp
Edited by niko1986, 09 May 2013 - 05:01 PM.
Posted 09 May 2013 - 10:29 PM
the first trace is fine. In the second the usbport.sys causes 1 larger spike. Connect your logitech devices to different uSB ports.
Also make sure that the RAM is compatible to the board, the ram is fine itself (test with memtest86+) and the memory timings match to the SPD data on the RAM modules. Use CPU-Z to verify this. If nothing helps, RAM the board and hope the new one is better.
Posted 10 May 2013 - 02:34 AM
My specific RAM Corsair CMX8GX3M2A1333C9 is not listed in the qualified vendor list supplied by ASUS but the 1600MHz version is listed as compatible, I'm running the RAM to the tested values on the corsair page not XMP profile in the BIOS.
I'll run memtest86+ again for a few hours and do as you say and verify with CPU-Z.
RMA might be the best option in the end, but thank you very much MagicAndre I've not found any other thread linked to this subject with someone so helpful
Posted 10 May 2013 - 09:59 AM
DO you have other RAM which you can test?
Posted 10 May 2013 - 01:41 PM
Unfortunately I don't have any other RAM to try, but I will see if I can borrow some from another computer if it is compatible.
Corsair with ASUS can cause issues if it is not listed as compatible.
DO you have other RAM which you can test?
Posted 11 May 2013 - 12:13 PM
Don't use DiagEasy run the exact command I posted.
Posted 11 May 2013 - 01:51 PM
I've been having issues with audio playback skipping on this PC I've recently built, and I can't seem to solve it on my own so I'd like to ask for your help.
I've Googled and tried pretty much every common solution, such as:
Drivers: Have all the latest Chipset, audio and LAN drivers from the motherboard manufacturer's website. GPU is Radeon 68xx, and I've updated the drivers for that recently.
BIOS: C-states, Speedstep and Turbo Boost are turned off. Everything else I don't use (integrated audio, USB 3.0 controller, serial port, etc.) are turned off as well. All power-saving options are disabled if possible.
Windows: All power-saving options are disabled, the power scheme is set to High Performance. System sounds are off, processor scheduling is set to "background services". Most unnecessary Windows services and Aero are disabled, and the only non-Windows program I have on startup is Daemon Tools Lite.
Other programs: No anti-virus running in the background, Windows Firewall is off as well.
Some other things to note:
-I'm running a USB audio DAC and the dropouts/skips only seem to occur with this device, the integrated audio chip seems to be working without problems. But the same DAC/setup works without problems on my laptop, so it doesn't seem to be a hardware problem.
I've tried all the other USB ports on the motherboard, but they all have the same issue. I've read USB 3.0 ports could potentially have issues with audio playback, so I turned those off as I have no USB 3.0 devices anyway.
-Disabling the (wired) network device in the Windows Device Manager temporarily doesn't solve the issue.
-The problem seems to be with the "INTERRUPT TO USER PROCESS LATENCIES", which spikes to 1500-4000 sometimes, the ISR/DPC latency seems to be relatively low (below 200 µs), so I'm not sure how to interpret that, as from reading this thread, most people have an issue with high DPC.
-The "hard page fault count" also builds up over time.
Please let me know if you need more info, I've attached a screenshot and the log from LatencyMon below.
Your system appears to be having trouble handling real-time audio and other tasks. You are likely to experience buffer underruns appearing as drop outs, clicks or pops. One problem may be related to power management, disable CPU throttling settings in Control Panel and BIOS setup. Check for BIOS updates.
LatencyMon has been analyzing your system for 0:02:29 (h:mm:ss) on all processors.
Computer name: 123
OS version: Windows 7 Service Pack 1, 6.1, build: 7601 (x64)
Hardware: P67A-UD3-B3, Gigabyte Technology Co., Ltd.
CPU: GenuineIntel Intel® Core i5-2500 CPU @ 3.30GHz
Logical processors: 4
Processor groups: 1
RAM: 4079 MB total
Reported CPU speed: 3309,0 MHz
Measured CPU speed: 2158,0 MHz (approx.)
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.
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): 4088,857662
Average measured interrupt to process latency (µs): 4,655696
Highest measured interrupt to DPC latency (µs): 169,365101
Average measured interrupt to DPC latency (µs): 2,644106
MEASURED SMI, IPI AND CPU STALLS
The SMI, IPI and CPU stalls value represents the highest measured interval that a CPU did not respond while having its maskable interrupts disabled.
Highest measured SMI or CPU stall (µs) 3,561905
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): 45,421578
Driver with highest ISR routine execution time: ataport.SYS - ATAPI Driver Extension, Microsoft Corporation
Highest reported total ISR routine time (%): 0,112664
Driver with highest ISR total time: USBPORT.SYS - Poortstuurprogramma voor USB 1.1 en 2.0, Microsoft Corporation
Total time spent in ISRs (%) 0,193451
ISR count (execution time <250 µs): 499048
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
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): 115,249320
Driver with highest DPC routine execution time: USBPORT.SYS - Poortstuurprogramma voor USB 1.1 en 2.0, Microsoft Corporation
Highest reported total DPC routine time (%): 0,439076
Driver with highest DPC total execution time: USBPORT.SYS - Poortstuurprogramma voor USB 1.1 en 2.0, Microsoft Corporation
Total time spent in DPCs (%) 1,008420
DPC count (execution time <250 µs): 1562516
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: latmon.exe
Total number of hard pagefaults 285
Hard pagefault count of hardest hit process: 250
Highest hard pagefault resolution time (µs): 89612,281656
Total time spent in hard pagefaults (%): 0,143697
Number of processes hit: 6
PER CPU DATA
CPU 0 Interrupt cycle time (s): 8,952294
CPU 0 ISR highest execution time (µs): 45,421578
CPU 0 ISR total execution time (s): 1,154993
CPU 0 ISR count: 499048
CPU 0 DPC highest execution time (µs): 115,249320
CPU 0 DPC total execution time (s): 5,666736
CPU 0 DPC count: 1529534
CPU 1 Interrupt cycle time (s): 1,264642
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): 61,477183
CPU 1 DPC total execution time (s): 0,038436
CPU 1 DPC count: 3482
CPU 2 Interrupt cycle time (s): 1,457896
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): 102,457540
CPU 2 DPC total execution time (s): 0,258378
CPU 2 DPC count: 24770
CPU 3 Interrupt cycle time (s): 0,852683
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): 80,678150
CPU 3 DPC total execution time (s): 0,057198
CPU 3 DPC count: 4730
Posted 11 May 2013 - 02:18 PM
run the xperf command and give me the file.
Posted 12 May 2013 - 11:19 AM
I had the bright idea to check the components' manufacturers' websites for drivers rather than the latest ones my motherboard's manufacturer put up for download.
So this might be worth a try for others who have tried "everything", try to find the model number of the component(s) that is giving you problems, and manually update the drivers.
In my case I updated all the chipset drivers related to PCI bus and USB controllers, and also the drivers for my NIC.
This seems to have fixed my issues; I occasionally still get a spike, but these are so rare I can live with it.
Thanks anyway though, it's really rare to see someone so selflessly helpful nowadays!
Posted 15 May 2013 - 09:41 AM
Posted 15 May 2013 - 11:44 AM
Posted 18 May 2013 - 10:10 PM
I also ran xperf while running Battlefield 3, but the file is huge and i'm having trouble interpreting the results.
The tests seem to point to USBPORT.sys as the main culprit; i tried updating my drivers, re installing windows etc., but nothing worked.
Any help would be greatly appreciated, thanks in advance!
Edited by 3Seven, 22 May 2013 - 05:18 PM.
Posted 19 May 2013 - 11:20 AM
Posted 19 May 2013 - 01:09 PM
look for IRQ sharing. Which other devices share the IRQ of the USB controller?
I only have 2 USB devices (mouse / keyboard) and they seem to be on: Intel 7 Series/C216 Chipset Family USB Enhanced Host Controller 1E26 - IRQ = 23
Where i do see USB sharing is on IRQ 16. The devices sharing IRQ 16 are:
1. Intel USB Enhanced Host Controller 1E2D
2. Intel PCI Express Root Port 1 1E10
3. Intel PCI Express Root Port 5 1E18
4. Intel Management Engine Interface
5. Xeon Processor PCI Express Root Port 0151
PC's a new build ~ 3 months old, worked fine for a month or so.
Asrock z77 Extreme4
Intel 330 SSD
WD Blue HDD
ATI HD 5850
8 Gig's GSKILL 1600
Edited by 3Seven, 21 May 2013 - 11:13 PM.
2 user(s) are reading this topic
0 members, 2 guests, 0 anonymous users