Seems like many if not most of the KASHIF_HIVPR_auto_spawn WUs are failing :-(

Seems like many if not most of the KASHIF_HIVPR_auto_spawn WUs are failing :-(

Seems like many if not most of the KASHIF_HIVPR_auto_spawn WUs are failing :-(

Would you like to point to a few to back up that statement?

Thanks for that, they all appear to have failed within a few seconds and I've got one on one of my machines that has been running over 3 hours now so we'll see what happens. it had been to someone else and failed within a few seconds there as well.

Here
____________
Radio Caroline, the world's most famous offshore pirate radio station.
Great music since April 1964. Support Radio Caroline Team -
Radio Caroline

Could be that it's a big coincidence but thought I'd report it since pretty much all I was finding was failed ones.

Just had a quick look at 6 of those units you posted and the machines that errored are not great examples of anything other than they produce a lot of errored WU's of all types.
Couldn't be bothered to look through the whole list.



____________
Radio Caroline, the world's most famous offshore pirate radio station.
Great music since April 1964. Support Radio Caroline Team -
Radio Caroline

The reason I noticed it at all was that the one that failed for me was on a GPU that seldom ever fails, so started looking at the results from the top RAC machines. BTW, the above comment about "defensiveness" was not aimed at you :-)

It's okay, It didn't bother me as I'm the last person to defend a project if they've got it wrong. :)

I'll let you know if I have any problems with these WU's.



____________
Radio Caroline, the world's most famous offshore pirate radio station.
Great music since April 1964. Support Radio Caroline Team -
Radio Caroline

I for one have had a nightmare when it comes to 6.72 WU failures.
We eventually got it sorted, well sort of - the 197.xx drivers were to blame on my Vista x64 machine with four GTX240's, but I tried so many different drivers on my GTX260sp216, that in the end I just gave up.
It is on Win7 x64 - the same as your two GTX275's!
My GTX260 is a good card, and kept failing immediately, even when natively clocked and temps under 60 deg C. I see you dripped your clocks as well, just in case.

I guess you are having a similar problem.

My 2 GT240's are working fine with that setup SK but my 2 remote machines (core2 E4300 and Dual Core E6300) are giving me problems. Why is it always remote machines you have problems with?

You started OK with your 4 GT240's don't know what the problem could be. I have mine clocked at Core 640, Memory 2000, and Shaders 1580 for my 2 GT240 GDDR5 on my Quad and Core 630, Memory 840, and Shaders 1580 on my GDDR3 machines. All clocks are as GPUZ shows them.


____________
Radio Caroline, the world's most famous offshore pirate radio station.
Great music since April 1964. Support Radio Caroline Team -
Radio Caroline

1 success and 1 failure to date for these units "KASHIF_HIVPR_auto_spawn"

Fail

Success



____________
Radio Caroline, the world's most famous offshore pirate radio station.
Great music since April 1964. Support Radio Caroline Team -
Radio Caroline

My really stable 295 failed 12 of these with the following error:

ERROR: file ntnbrlist.cpp line 63: Insufficent memory available for pairlists. Set pairlistdist to match the cutoff


It also failed 2 TONI (alos 6.72) with a error:
SWAN: FATAL : swanMalloc failed

I am now working on 2 more TONIs which are OK after 2+ hours so I think they will be fine.


____________
Thanks - Steve

Task 2347063 OK with gtx470.
____________
Ton (ftpd) Netherlands

Beyond, I meant GTX260. On which we were/are both having problems with 6.72 tasks under Win7.
I tried several drivers and clients but the 6.72 WUs still failed (running native).

KASHIF_HIVPR WU are also failing for me on my GT240s. This is after going back to the 19621 driver (which is still working for all TONI_HERG 6.72 WUs).

What's the temps on these failed WU's? I know that there is a need for speed & it's always nicer to get these WU's done faster. But it's "my personal opinion" that GPUGRID is becoming more & more elitist. It's Enthusiast friendly, Consumer unfriendly when WU's become so aggressive that even stock clocked GPU's are failing due to overheating. Not everybody has water cooled systems. I've moved around just about every cable to enhance the airflow of my PC's, but now that Linux is so good & Windows is so slow, I'm almost forced to stop using Linux because my GPU's are running at 80-90 degrees on Linux no matter how they're clocked or how great the airflow is. I've got 2 PC's in enclosures that aren't meant for this, & the only way to improve airflow there, is to get new enclosures.

If GPUGRID keeps on improving their WU's for Windows, I soon won't be able to use Windows either. But that's no reason not to. I'm just itching for an option to throttle down the use of GPU, as is possible to set a max CPU use of x%.
____________

Heat is not a problem for me ... the 295 that has recieved lots of errors is running a cool 75 degrees c.

The errors as I posted above appear to be memory allocation issues ... with
1896 MB shared between both cards I doubt it really is "insufficient".

Perhaps CUDA or the driver is reporting incorrectly or a bug at some internal condition? That will not be easy for the GPUGrid devs to identify buit because the errors are always the same that might point in a particular direction for investigation.

When HERG WUs fail (some do pass) it is always the same error =
"SWAN: FATAL : swanMalloc failed"

When KAHIF WUs fail (I havbe not had any success yet with them) it is always the same error =
"ERROR: file ntnbrlist.cpp line 63: Insufficent memory available for pairlists. Set pairlistdist to match the cutoff."

This is a dedicated cruncher so the only other thing going on is WCG which should not matter.
____________
Thanks - Steve

What's the temps on these failed WU's? I know that there is a need for speed & it's always nicer to get these WU's done faster. But it's "my personal opinion" that GPUGRID is becoming more & more elitist. It's Enthusiast friendly, Consumer unfriendly when WU's become so aggressive that even stock clocked GPU's are failing due to overheating. Not everybody has water cooled systems. I've moved around just about every cable to enhance the airflow of my PC's, but now that Linux is so good & Windows is so slow, I'm almost forced to stop using Linux because my GPU's are running at 80-90 degrees on Linux no matter how they're clocked or how great the airflow is. I've got 2 PC's in enclosures that aren't meant for this, & the only way to improve airflow there, is to get new enclosures.

If GPUGRID keeps on improving their WU's for Windows, I soon won't be able to use Windows either. But that's no reason not to. I'm just itching for an option to throttle down the use of GPU, as is possible to set a max CPU use of x%.

They have all failed an my system within 10 seconds. I am running BOINC 6.10.43 and 197.13 driver on 3 GT 240s.
-Matt

Just finished one of these on a Fermi (470) - 285-KASHIF_HIVPR_auto_spawn_2_90_ba1-0-100-RND3939_2.

Two errors before mine, on a GT 240M and a GTX 295, which possibly suggests that they're tough. Also, I saw a lot more screen freezing while it was running, for up to 10 seconds at a time: made the computer almost unusable. I'm running with Swan_Sync=0, and BOINC restricted to 7 out of 8 cores.

BTW, although this is a "stock Dell", I don't think cooling is going to be the issue. It's a Precision 490 workstation, with two factory-fitted front case fans, and even a separate dinky little fan angled onto the RAM. Eeven though it's three and a half years old, it took Windows 7 and the Fermi with no problems at all.

skgiven,

BOINC 6.10.51 will randomly stop running tasks on your GPUs, it also has a memory leak... move up to 6.10.56 which has neither of these problems ... don't know if it will cure any of the issues you are having for sure, but it cannot hurt to use the better version ... all the versions between 6.10.45 and 6.10.55 have these two issues at the very least ... I know, I tried most of them ...

KASHIF_HIVPR WU are also failing for me on my GT240s. This is after going back to the 19621 driver (which is still working for all TONI_HERG 6.72 WUs).

I notice that most of the KASHIF_HIVPR_auto_spawn WUs that I listed above are now validating with subsequent machines so I probably jumped the gun by posting this thread. Like I said before, trying to be proactive. Seems they run fine on some machines, not so fine on others.

This is what I'm getting on every KASHIF_HIVPR_auto_spawn on any GT 240, doesn't matter what driver or OS:


<core_client_version>6.10.56</core_client_version>
<![CDATA[
<message>
- exit code 98 (0x62)
</message>
<stderr_txt>
# Using device 0
# There is 1 device supporting CUDA
# Device 0: "GeForce GT 240"
# Clock rate: 1.55 GHz
# Total amount of global memory: 536870912 bytes
# Number of multiprocessors: 12
# Number of cores: 96
ERROR: file ntnbrlist.cpp line 63: Insufficent memory available for pairlists. Set pairlistdist to match the cutoff.
called boinc_finish

</stderr_txt>
]]>

Seems the KASHIF_HIVPR_auto_spawn WUs are asking for more memory than 512k?

Those units succeed on all my gt240 1 gig gddr3 cards but fail on my gt240's with 512mb gddr5 cards.
____________
Radio Caroline, the world's most famous offshore pirate radio station.
Great music since April 1964. Support Radio Caroline Team -
Radio Caroline

WU 1496749 looks like a bad job, by any standard and on any card. Just failed on my Fermi.

Hopefully they fail immediately and don't cause credit loss.

Unfortunately all the HIV WUs still seem to fail after about 13sec for me on systems with a GT240 and only 512MB RAM. This Vista System for example.
Fortunately the other WUs run fine and I am picking up enough of them.

KASHIF_HIVPR does not run on these systems,
19621 drivers, 4xGT240 (512MB GDDR5), Vista x64, Phenom II 940, 4GB RAM, 1TB Drive.
19562 drivers also fail on Microsoft Windows Server 2008 R2 x64 with a GT240 (512MB GDDR5).
19621 drivers also fail on Win 7 x64, again with a GT240 (512MB).

Upgrade to the 257.21 drivers and they will work OK



____________
Radio Caroline, the world's most famous offshore pirate radio station.
Great music since April 1964. Support Radio Caroline Team -
Radio Caroline