Skylake hard locks seeminly when IDLE / CStates ON

[GGlyn]

Myself and others have been struggling with a different hard lock problem with Skylake and we have ran out of options but to assume it is a CPU fault/issue. Does anyone have any comments or feedback?

The long thread is over here, but I will summarise. http://www.tomshardware.co.uk/forum/id-2830772/skylake-build-randomly-freezing-crashing/page-7.html New Skylake Build Randomly Freezing/Crashing - Page 7 - windows 10 - Windows 10

Our systems hard lock randomly but appears on the most part to be when IDLE or next to IDLE. The hardlock can come when playing video, browsing (reading) or mostly when not interacting at all. Some (like myself) noted that they seem to occur more often if you are doing a large amount of disk IO (partition move for example or copying 40+ GB of data disk to disk).

Hard locks happen in either Windows (7,8,10) or Linux.

With CStates on, the crashes are often and usually within 10 minutes of IDLE. With CStates disabled completely most find that the system remains "mainly" stable for days. Generally, no one has reported locks when gaming or under high CPU load (so I do not think this is the Prime95 example but then, since compilers / drivers use the latest instructions (according to CPUID) I cant be sure).

The symptoms happen on many different manufacturers motherboards, RAM types and setups. We have successfully removed or replaced all components and the only change that seems to make a difference is CPU for a few. CStates off in the BIOS is absolutely a guarenteed way to stabilize significantly but not fix.

I changed CPU (after trying everything else) and find it now mostly stable with CStates ON. I must be clear that my system is 100% identical, CPU # 1 crashes all the time and must have CStates off, CPU # 2 does not crash so often even with CStates ON. One may argue this is a problem with my PC, a fault, but with so many people having the exact same issues I cant believe it is a defect. And with Cstates/SpeedStep so specifically (a known new part of Skylakes architecture), I remain convinced that this is something real.

Others were not so lucky, a replacement CPU did not make the situation better. Batches from different factories as well etc etc

My new CPU has hard locked but not when IDLE like the last one (not yet anyway). Mine can lock when under full load, video transcoding, but not more than 1 in 10 sessions. Cstates ON seems equally stable on this CPU as OFF.

Thanks for any suggestions you can give.

[WSkow]

I have a similar issue - complete freezes (even reset button doesnt response) with no error reports in windows.

6600k with microcode 55

hyperX Savage 2x8GB DDR4-2400 CL12 running at dual

MSI Z170A gaming M3 with leatest bios

SSD ADATA Premier Pro SP920 256GB

WD Caviar Blue 1TB

PSU Chieftec 750W ctg-750c

windows 10, clean installation

What i have noticed is that when RAM is running on XMP Profile # 1: DDR4-2400 CL12-13-13 @1.35V it usually freezes within an hour. On XMP Profile # 2: DDR4-2133 CL13-13-13 @1.2V or JEDEC its a bit more stable - it takes about 3 hours, but eventually it freezes too.

Processor has passed all the tests in Intel Processor Diagnostic Tool, and memory was checked with memtest - no errors either.

It has never happened on any of the stress tests in Extreme Tuning Utility, or while gaming (although i dont play much and didnt put in on stress test for more than hour, so its not objective). About 90% of freezes happened while browsing internet (on Chrome,Firefox and Edge - on all of them), once while copying files, and few times while completely idle.

Can this be related to this Prime95 issue, or are we experiencing something different?

[DThif]

Details about me:

- CStates are enabled

- CPU is i5-6500

- Microcode is 506E3 49

My build:

http://ca.pcpartpicker.com/p/6rP86h http://ca.pcpartpicker.com/p/6rP86h

[WSkow]

After some more testing i thing that memory setting has no impact on stability - it just pure random - it can freeze while loading windows or can work for 4-6h on both settings.

But i have found something diffrent that i have no idea what to think:

After about 40min of gaming (on integrated intel 530) i looked at Extreme Tuning Utility monitors and noticed some abnormal reading:

Processor Graphics Frequency:

Recent minimum: 0 Mhz

Recent maximum: 16076652 Mhz

Processor Cache Frequency:

Recent minimum: 0 Mhz

Recent maximum: 52520,82 Ghz

Memory Frequency:

Recent minimum: 1Mhz

Recent maximum: 33467396 Mhz

Temeprature was 43C max, and the only thing i have noticed was 3 about 1-2 seconds long graphic freezes, one of them ended in Windows "Display driver stopped responding and has recovered" error, but this error also happenes without this strange readings.

Computer didnt freeze, but again it has never freezed for me under load (except two times when it frezzed while loading Windows).

[GGlyn]

New BIOSes for the Prime95 fixes are starting to appear. The initial (early) feedback is that it does not help in the CStates/IDLE hard locks.

[MRuni]

Hello. I am having the same freezing issue when idle

My PC Specs

Intel Core i7-6700K 8M Skylake Quad-Core 4.0 GHz.

GIGABYTE GA-Z170X-UD5.

GIGABYTE G1 Gaming GTX 980.

Corsair H100i GTX Water Cooling.

CORSAIR Vengeance LPX 16GB DDR4 2666.

XFX Pro 750 Watt.

Samsung 840 EVO 250GB(OS).

1 TB Sata HDD @ 7200rpm. (Storage).

500GB Sata HDD@ 7200rpm. (Storage).

I have tried a variety of stuff, which I had listed on another site, Toms Hardware. Got off the support line with intel, and was asked to post here.

I was told intel is aware of the issue and no eta for a fix is given. Just to be clear, my issue is not the Prime 95 issue. I can game fine, its when idle that I lock up

[DThif]

@GeekForceOne

Good to know Intel is aware of the issue! At least something is being investigated. Hope they resolve this quickly...

Thanks for the info!

[TLund3]

I also have freezing issues when idle:

System Information

------------------

Processor Name: Intel(R) Core(TM) i5-6600K CPU @ 3.50GHz

Processor Information: Intel64 Family 6 Model 94 Stepping 3

Number of Physical Cores: 4

Number of Logical Cores: 4

Installed System Memory: 8 GB

Operating System: Microsoft Windows 7 Ultimate 64-bit

Graphics Information: NVIDIA GeForce GT 630

System Product: Z170-HD3 DDR3-CF

System BIOS: F2

System Serial Number: To be filled by O.E.M.

But I also get FAIL when running Intel Processor Diagnostic Tool:

--- IPDT64 - Revision: 3.0.0.23.W.MP

--- IPDT64 - Start Time: 26-02-2016 20:39:51

--------------------------------------------------------------------

Processor 1

--------------------------------------------------------------------

Intel(R) spbc Module Test

Module Version: 1.0.7.64b.W

Start Time: Fri Feb 26 20:39:51 2016

Test Result - PASS

..!!..Processor under test is verified as 'PRODUCTION'..!!..

Processor Manufacturer: GenuineIntel

Processor Brand String: Intel(R) Core(TM) i5-6600K CPU @ 3.50GHz

End Time: Fri Feb 26 20:39:51 2016

Total Time: seconds: 0

--------------------------------------------------------------------

Genuine Intel CPU Test

Module Version: 1.0.12.64b.W

Start Time: Fri Feb 26 20:39:51 2016

Test Result - PASS

Expected: GenuineIntel

Detected: GenuineIntel

End Time: Fri Feb 26 20:39:51 2016

Total Time: seconds: 0

--------------------------------------------------------------------

Temperature Test

Module Version: 1.0.12.64b.W

Start Time: Fri Feb 26 20:39:51 2016

Test Result - PASS

Expected: Greater than 1 degrees below max

Received: 76 degrees below max

End Time: Fri Feb 26 20:39:51 2016

Total Time: seconds: 0

--------------------------------------------------------------------

CPU Brand String Test

Module Version: 1.0.12.64b.W

Start Time: Fri Feb 26 20:39:51 2016

Test Result - PASS

Expected String Parts: As Defined in BrandString_LocalConfig.xml

Detected: Intel(R) Core(TM) i5-6600K CPU @ 3.50GHz

End Time: Fri Feb 26 20:39:51 2016

Total Time: seconds: 0

--------------------------------------------------------------------

Module - CPUFreq.exe did not create a results file.

--------------------------------------------------------------------

--- IPDT64 - Temperature Monitor Results

Temperature Monitor will begin when CPULoad Test starts

Temperature Monitor Stopped

--------------------------------------------------------------------

System Information

------------------

Processor Name: Intel(R) Core(TM) i5-6600K CPU @ 3.50GHz

Processor Information: Intel64 Family 6 Model 94 Stepping 3

Number of Physical Cores: 4

Number of Logical Cores: 4

Installed System Memory: 8 GB

Operating System: Microsoft Windows 7 Ultimate 64-bit

Graphics Information: NVIDIA GeForce GT 630

System Product: Z170-HD3 DDR3-CF

System BIOS: F2

System Serial Number: To be filled by O.E.M.

--------------------------------------------------------------------

--- IPDT64 - End Time: 26-02-2016 20:39:51

--- IPDT64 - Result: Fail

--------------------------------------------------------------------

FAIL

Any suggestions?

[MScri2]

Might as well chime in so I can get notifications about this thread. I've had this problem since day 1 of my 6700k build back in Sept.

[JBigg1]

I have been posting and tracking the same forum on Tom's Hardware that the OP referred to, and decided to post here to get myself on the notification list. I built my Skylake system in the first week of December, and have had freezes when idle since the beginning, until I turned off C8, (or disabled C-states entirely). For some other posters, C8 did not help, but for me, disabling just that one has stabilized my system.

i7-6700k @ 4.0Ghz Air cooled

G.Skill 16GB DDR4 3200MHz (XMP)

Samsung 850 EVO 500GB SSD

MSI Armor 2x GTX 980 Ti

Thermaltake Toughpower 750W Gold-certified PS

[AMohr1]

But i have found something diffrent that i have no idea what to think:

After about 40min of gaming (on integrated intel 530) i looked at Extreme Tuning Utility monitors and noticed some abnormal reading:

Processor Graphics Frequency:

Recent minimum: 0 Mhz

Recent maximum: 16076652 Mhz

Processor Cache Frequency:

Recent minimum: 0 Mhz

Recent maximum: 52520,82 Ghz

Memory Frequency:

Recent minimum: 1Mhz

Recent maximum: 33467396 Mhz

Now your processor was sent to heaven....

[EPrig]

Hi! I am having the same freezing issue when idle

My system

Intel Core i5-6600 3,3 ГГц

Gigabyte GA-h170n-WiFi

Crucial 2133mhz 2 * 8GB

Seasonic SS-300tgw

Western Digital 1Tb WD10EZEX

[dmone2]

kinda glad i found this thread. stupid new skylake build randomly hangs for 5-30sec at a time...all the time. after the hang it will right itself and i never get BSOD and i have not had to hard reboot. ram is good, ram voltage is good, cpu (i7-6700k) oc'd to 4.4 can run marathon circles around prime for days on end, but the moment i start dragging and dropping files on desktop, opening Word, Word Perfect, Adobe Pro, VideoPad Video Editor and ImageEditor, copying and pasting...i get frequent random hangs. it sucks. this is a NEW pc build. like, literally 3 days new and a fresh Windows 10 install, not upgrade. playing with C-states did not increase stability, it happens whether i run with oc or stock, happens whether XMP is on or not, slight adjustments to voltage do not help. please someone tell me that Intel is all over this problem and that a fix is coming. i will RMA if not resolved in the next week or so. i have things that need to get done. thank you to those here who provide technical assistance to us noobs. you are appreciated.

i7-6700k

AMD R9-390 8GB GDDR5

Corsair H55 w/ Fractal high performance fans

Gigabyte Z170XP-SLI (running latest bios update)

ADATA XPG Z1 16GB DDR4 2800

Sandisk 400S SSD

WD Caviar Blue 1TB HDD

Thermaltake Smart 750w PCBUS

[OTrau]

This seems to be something different. What you describes is typical HDD signature. It might be faulty. If it encounters a read error, it tries to recover for like 30 s (in case of a typical desktop drive). If your OS tries to access then at some point, it might hang for the rest of these 30 s. What you can do to check this:

- take out your WD HDD for a while, see if the thing stops

- install SpeedFan e.g. (easy under Windows) and issue an extended SMART test; in case you reliably discover a read error (irrespective of bad blocks), just RMA your drive; you could also start with a short test, it might save you time (but it might also overlook the problem)

- you can also look into the Windows event logs; you might or might not see something drive related here (on one machine I got no drive errors though, but switching the drive helped anyway)

[dmone2]

I found an answer to my problem. turns out intel sata stuff is not compatible with all SSDs as of yet (mine is Sandisk). many people are having the hang/freeze problem. need to go to advance power options and turn this stuff off. i found a link that actually walked me through it and worked like a charm. sorry didnt post here and cant remember where it was. i am back to blazing fast with zero hiccups!!! for at least some reference i posted the key words below.

under power options/hard disk:

AHCI Link Power Management - HIPM/DIPM and AHCI Link Power Management - Adaptive

i remember i had to get into registry and change values on the link power keys from 1s to 2s and then go back to power management options and change HIPM/DIPM and AHCI to off. system 100% stable and running on jet fuel.

this should be probably be spread around, i am seeing more and more people with this issue 

[AMohr1]

AHCI enables NCQ.

If you use a SSD, then AHCI should be enabled. If this does work, either the SATA controller does not work correctly or the SSD.

If you want to know which part, then try another SSD from a different manufacturer.

[AMohr1]

I have bought a Samsung 850 Pro SSD 512GB.

It works correctly with the X99-Deluxe chipset.

I use Suse Leap 42.1.

AHCI is on.

[WSkow]

I was send a new beta bios from MSI (with microcode 74). And for 2 days my computer hasnt freezed yet.

Btw. I have noticed that CPU its a bit hotter under load that it was before (it went from about 50 to 58deg)

[FParr]

Really ?, what motherboard you're using?, are you using the same application or the same game, which is?, when you skipped the update?.

It is good news, I'm from Asus, I hope also investigate how to fix it.

Regards

[dmone2]

https://en.wikipedia.org/wiki/Native_Command_Queuing Native Command Queuing - Wikipedia, the free encyclopedia

I do not typically accept wikipedia as an authority.

"Many newer chipsets support the Advanced Host Controller Interface (AHCI), which allows operating systems to universally control them and enable NCQ. Newer mainstream Linux kernels support AHCI natively, and FreeBSD fully supports AHCI since version 8.0. Windows Vista and Windows 7 also natively support AHCI, but their AHCI support (via the msahci service) must be manually enabled via registry editing if controller support was not present during their initial install. Windows 7's AHCI enables not only NCQ but also TRIM support on SSD drives (with their supporting firmware). Older operating systems such as Windows XP require the installation of a vendor-specific driver (similar to installing a RAID or SCSI controller) even if AHCI is present on the host bus adapter, which makes initial setup more tedious and conversions of existing installations relatively difficult as most controllers cannot operate their ports in mixed AHCI–SATA/IDE/legacy mode."

I suspect that the instances where this is happening are because controller support on install wasn't present. Windows 10 is where this is happening most recently.

[dmone2]

I use Z170 chipset on Gigabyte board. I just found this Driver on the product support page under downloads:

Intel SATA Preinstall driver for Windows 10 64bit

(For AHCI / RAID Mode) version 14.6.0.1029 released on 10/16/2015.

Just download the zip file, cut and paste the files only, not the folder, onto a flash drive, and then in Bios tell system to boot from USB drive with the driver files. I just did it and apparently after the SATA controllers/drivers are updated, it automatically activated all my AHCI Power Management settings and the original hangs that were present before are still nowhere to be found!!! hallelujah!!! and that's why i am the smartest man in America.

For all experiencing this problem PLEASE CHECK YOUR BOARD's SUPPORT PAGE FOR UPDATED DRIVER/BIOS downloads. The end.

[OTrau]

Please don't discuss sata/drive issues here in this thread. This undermines our attempt do get a clearer picture of c-state related issues with these new CPUs. Thank you.