P35 Motherboards and DPC Latency Spiking

[theearbox]

Re: P35 Motherboards and DPC Latency Spiking

I have spoken with them, and it is fixed in the all the P35 latest BIOS's. So if you are having issues still it is either hardware/software or conflicting drivers.

Have you tested this on a clean install? No other drivers loaded?

Is your latest BIOS version Before April 08? I see it is 7/08 so it is the fixed BIOS.

Here is Gigabyte's answer to me about this and why it is fixed for sure already on their end, and why you may still be affected by other issues and not the BIOS >>>

Hi again, after a lot of days I have now a replaced MB, my model is now GA-EP35c-ds3r. I had the same configuration in a cheap asrock without any dpc spikes, same memory, graphic card, audio card, etc. For me is a shame that in my mails to gigabyte they told me "And for your information, because we did not find the DPC problem as you mentioned in our side"
I hope that gigabyte will solve the problem soon,otherwise I will never buy another gigabyte product.
If anyone can tell me any solution, please tell me, surely If I dont solve the problem I will kick my MB very far away.

[theearbox]

Re: P35 Motherboards and DPC Latency Spiking

PD
I tried a lot of bios without success, (beta included)

Hi again, after a lot of days I have now a replaced MB, my model is now GA-EP35c-ds3r. I had the same configuration in a cheap asrock without any dpc spikes, same memory, graphic card, audio card, etc. For me is a shame that in my mails to gigabyte they told me "And for your information, because we did not find the DPC problem as you mentioned in our side"
I hope that gigabyte will solve the problem soon,otherwise I will never buy another gigabyte product.
If anyone can tell me any solution, please tell me, surely If I dont solve the problem I will kick my MB very far away.

[Lsdmeasap]

Re: P35 Motherboards and DPC Latency Spiking

Are you flashing properly? Loading optimized defaults and saving and applying after you flash? F3 and F4a are fixed as they are newer then April 08

As noted above, ANY Driver or other hardware can cause this. The BIOS for that board is fixed so maybe the software or sound drivers, Network drivers, USB drivers, ect you are using cause it? I am not sure really, sorry but the BIOS is not to blame.

Maybe you could return that board and get a P45 instead, DDR3 is kinda a waste of $$ right now. I Just wonder why you bought a DDR3 P35 board when you knew of this possible issue???

P45 boards are fully working without a BIOS fix needed >>>



More P45 discussion with images so you can see it is fine >>>>
DPC issues still present in Gigabyte EP45 boards? - XtremeSystems Forums


Sorry I cannot offer you more real help or suggestions, but I can assure you the BIOS is fixed and it has to be a hardware or driver issue on your end. Unless you are not properly flashing the BIOS

DPC checker is extremely overrated.

but lets go to the source shall we, as in RTFM from the DPC manual.


1) DPC:Processing of streaming data in real-time is a very challenging task for Windows based applications and device drivers. This is because by design Windows is not a real-time operating system. There is no guarantee that certain (periodic) actions can be executed in a timely manner.

scott: so as we near real time buffer setting IE 64 and 32 buffers we are pretty much maxing out the OS and i would add the physical limitations of hardware communication.

2) DPC: Audio or video data streams transferred from or to an external device are typically handled by a kernel-mode device driver. Data processing in such device drivers is interrupt-driven. Typically, the external hardware periodically issues interrupts to request the driver to transfer the next block of data. In Windows NT based systems (Windows 2000 and better) there is a specific interrupt handling mechanism. A device driver cannot process data immediately in its interrupt routine.
It has to schedule a Deferred Procedure Call (DPC) which basically is a callback routine that will be called by the operating system as soon as possible. Any data transfer performed by the device driver takes place in the context of this callback routine, named DPC for short.

Scott: so take a poorly written driver for an audio interface and right off you can have DPC issues. this is why some interfaces can handle 64 or 32 buffer and others cant go below 512.

so the only way to compare motherboards as a suspect issue is to have the identical setup, interface and windows install. this is called the scientific method in case you were asleep in college.
this is excatly the method we use prior to ever posting a system on our site for sale.
which by the way may or may not have Gigabyte boards (depending on the system)


3) DPC: The operating system maintains DPCs scheduled by device drivers in a queue. There is one DPC queue per CPU available in the system. At certain points the kernel checks the DPC queue and if no interrupt is to be processed and no DPC is currently running the first DPC will be un-queued and executed. DPC queue processing happens before the dispatcher selects a thread and assigns the CPU to it. So, a Deferred Procedure Call has a higher priority than any thread in the system.

again this can relate to A drivers or B software used.
it can also be caused by a motherboard bios, how it address' resource allocation and upper memory range (beyond standard 32 bit OS) so even if you are using a 32bit the mobo can effect you with these upper reagions
not used as now all new hardware is Vista certified.
this can appear on ANY mobo as alot are more concerned with Vista approval than worrying over legacy support.

4) DPC: While there is a pre-emptive multitasking for threads, DPCs are executed
sequentially according to the first in, first out nature of a DPC queue.
Thus, a sort of cooperative multitasking scheme exists for Deferred
Procedure Calls. If any DPC runs for an excessive amount of time then
other DPCs will be delayed by that amount of time. Consequently, the
latency of a particular DPC is defined as the sum of the execution time
of all DPCs queued in front of that DPC. In order to achieve reasonable
DPC latencies, in the Windows Device Driver Kit (DDK) documentation
Microsoft recommends to return from a DPC routine as quick as possible.
Any lengthy operation and specifically loops that wait for a hardware
state change (polling) are strongly discouraged.



Unfortunately, many existing device drivers do not conform to this
advice. Such drivers spend an excessive amount of time in their DPC
routines, causing an exceptional large latency for any other driver's
DPCs. For a device driver that handles data streams in real-time it is
crucial that a DPC scheduled from its interrupt routine is executed
before the hardware issues the next interrupt. If the DPC is delayed and
runs after the next interrupt occurred, typically a hardware buffer
overrun occurs and the flow of data is interrupted. A drop-out occurs.

Scott:
there are numerous causes for high DPC, aside from lousy drivers.
the netwarok card is most noted for this, and a wireless NIC is 10 times worse.

enabling AHCI for your drives will most definately cause this as well

what IRQs are shared is again another issue.

DPC checker is useless run a audio test. a real one like here

D.A.W Bench : D.A.W Performance Benchmarking

Source >>>
Cubase.net .:::. View topic - The DPC latency thread... and Gigabyte P35/X38 issue

http://www.thesycon.de/deu/latency_check.shtml#background

Here, and several of the linkbacks below you can go and read towards the end P35 Boards BIOS's are all fixed >>>
RE: I'm shattered:( - my new useless super computer - GIGABYTE IS CRAP!

[theearbox]

Re: P35 Motherboards and DPC Latency Spiking

I have tested with the same configuration with a cheap asrock mb and it did not had any dpc issues.

I did not knew the dpc problem before I bought it.
I bought my MB in april.
Thanks anyways again.

[Lsdmeasap]

Re: P35 Motherboards and DPC Latency Spiking

Sorry to be of no help I guess. You never said, are you Properly Flashing the BIOS when you update it? If you do not the problems will remain until you do a proper flash as noted above

[theearbox]

Re: P35 Motherboards and DPC Latency Spiking

I solved partially the problem. I changed the graphic card for an old x800 and the dpc has disappeared. It seems that 8800gt and p35 by gigabyte is a bad c o c ktail.

[badonkadonk]

Re: P35 Motherboards and DPC Latency Spiking

I solved partially the problem. I changed the graphic card for an old x800 and the dpc has disappeared. It seems that 8800gt and p35 by gigabyte is a bad c o c ktail.

Ya PCI-E 2.0 video card in any Gigabyte board before P45 is problematic(P35/x38/48). I abandon this thread many months ago when i gave up on the X38DQ6 to get another brand and i have no problems since then with the SAME components. (PSU/RAM ETC).

They say its fixed in P45 but i lost faith in Gigabyte so i cant confirm.

I just wanted to add this issue has been very bad for Gigabyte. Yes DPC issues can be caused by many things but bad/slow/stuttering performance can not easily be ignored what ever the cause.

I was a fan of Gigabyte back in P965 days but my experience cost me several hundreds of dollars and many hours problem solving and a new board from another brand solve the problem so now i dont recommend or use Gigabyte. Even though maybe the problem is solved with P45 i cant afford to gamble on it.

[Lsdmeasap]

Re: P35 Motherboards and DPC Latency Spiking

See that just goes to show you that ANYTHING can cause DPC issues, driver and hardware for sure included.

Glad you can now use your system to make your music!

[zjiejun]

Re: P35 Motherboards and DPC Latency Spiking

I had the same problem of DPC latency with my old EP35-DS3L.

Fixed by uninstalling DES. Apparently DES caused latency spikes for me. Without DES, my system latency was <30 nanosecs.

[DavidDavisLeeSomething]

Re: P35 Motherboards and DPC Latency Spiking

I gots some really horrible spikes turning on my T.V. app with a HDTV broadcast



The worst one I have yet to experience.

[Lsdmeasap]

Re: P35 Motherboards and DPC Latency Spiking

Not too bad really, and since you do not have a job as a music maker or similar I would please ask you to not bump this thread again. Please and Thanks

Not mad at you or anything, but many users who this does not really affect see things like this and think their board is broke.

[Alicantino32]

Re: P35 Motherboards and DPC Latency Spiking

Edit: Oh umm even that is not great. They should Ideally be the same as the smallest ones without any spikes..

Also if you look in Vista performance logs there are many critical errors complaining of system degradation, windows components taking too long to start up, slow boot degradation...wtf is going on?? There is one common component, Gigabyte boards. Asus doesnt have this issue.

This is good:

[theearbox]

Re: P35 Motherboards and DPC Latency Spiking

possible solution!
I have ga-ep35c-ds3r 2.1 bios f4a and geforce 8800gt (bad couple :D)
I have tested latest nvidia video drivers (geforce beta 180.439 and now my system have no serious latency issues.

[ryan200]

Re: P35 Motherboards and DPC Latency Spiking

this is what worked the best for my board ds3l ep43 (note: different bios versions didn't matter) with a 9800gt (9800gt bascially is a 8800gt)

one disable cpu eist function in the bios
two uninstall gigabyte energy saver (specifically the gsvr.exe process was slowing me down even with power saving disabled in the program)

hopefully what works for me will work for you, give it a try.

[kpo6969]

Re: P35 Motherboards and DPC Latency Spiking

GA-P35-DS3L F9b BIOS Question. - Overclock.net - Overclocking.net