NV 36 hour tdr bug resolved in linux
Moderators: Site Moderators, FAHC Science Team
-
- Posts: 533
- Joined: Tue May 27, 2008 11:56 pm
- Hardware configuration: Parts:
Asus H370 Mining Master motherboard (X2)
Patriot Viper DDR4 memory 16gb stick (X4)
Nvidia GeForce GTX 1080 gpu (X16)
Intel Core i7 8700 cpu (X2)
Silverstone 1000 watt psu (X4)
Veddha 8 gpu miner case (X2)
Thermaltake hsf (X2)
Ubit riser card (X16) - Location: ames, iowa
NV 36 hour tdr bug resolved in linux
i am happy to report that the 36 hour tdr bug is resolved in linux with the release of nvidia-331. if you are on ubuntu its available through the xorg-edgers ppa.
-
- Posts: 1576
- Joined: Tue May 28, 2013 12:14 pm
- Location: Tokyo
Re: 36 hour tdr bug resolved in linux
Your make my day !!
Thanks for sharing. Happy to get rid of daily reboot.
Any visible impact on performance/PPD as reported on earlier versions ? On GTX 780 or 660Ti ?
Thanks for sharing. Happy to get rid of daily reboot.
Any visible impact on performance/PPD as reported on earlier versions ? On GTX 780 or 660Ti ?
Please contribute your logs to http://ppd.fahmm.net
-
- Posts: 533
- Joined: Tue May 27, 2008 11:56 pm
- Hardware configuration: Parts:
Asus H370 Mining Master motherboard (X2)
Patriot Viper DDR4 memory 16gb stick (X4)
Nvidia GeForce GTX 1080 gpu (X16)
Intel Core i7 8700 cpu (X2)
Silverstone 1000 watt psu (X4)
Veddha 8 gpu miner case (X2)
Thermaltake hsf (X2)
Ubit riser card (X16) - Location: ames, iowa
Re: 36 hour tdr bug resolved in linux
i am on gtx 780's. though i have gotten higher ppd since installing it i attribute that to the run of work units i have had (no p8900). will know more by the end of the week after it has run awhile.
-
- Posts: 10179
- Joined: Thu Nov 29, 2007 4:30 pm
- Hardware configuration: Intel i7-4770K @ 4.5 GHz, 16 GB DDR3-2133 Corsair Vengence (black/red), EVGA GTX 760 @ 1200 MHz, on an Asus Maximus VI Hero MB (black/red), in a blacked out Antec P280 Tower, with a Xigmatek Night Hawk (black) HSF, Seasonic 760w Platinum (black case, sleeves, wires), 4 SilenX 120mm Case fans with silicon fan gaskets and silicon mounts (all black), a 512GB Samsung SSD (black), and a 2TB Black Western Digital HD (silver/black).
- Location: Arizona
- Contact:
Re: 36 hour tdr bug resolved in linux
Others have reported a 10% drop in performance for non-780/Titan cards. That may improve in future releases, but some people are sticking with the older drivers, and still rebooting once a day. Time will tell.
How to provide enough information to get helpful support
Tell me and I forget. Teach me and I remember. Involve me and I learn.
Tell me and I forget. Teach me and I remember. Involve me and I learn.
-
- Posts: 823
- Joined: Tue Mar 25, 2008 12:45 am
- Hardware configuration: Core i7 3770K @3.5 GHz (not folding), 8 GB DDR3 @2133 MHz, 2xGTX 780 @1215 MHz, Windows 7 Pro 64-bit running 7.3.6 w/ 1xSMP, 2xGPU
4P E5-4650 @3.1 GHz, 64 GB DDR3 @1333MHz, Ubuntu Desktop 13.10 64-bit
Re: 36 hour tdr bug resolved in linux
I think those seeing a 10% drop were running Fermis or rather low-end Keplers. People running 770s, 760s, and 680s were seeing over 60% drops.7im wrote:Others have reported a 10% drop in performance for non-780/Titan cards. That may improve in future releases, but some people are sticking with the older drivers, and still rebooting once a day. Time will tell.
-
- Posts: 10179
- Joined: Thu Nov 29, 2007 4:30 pm
- Hardware configuration: Intel i7-4770K @ 4.5 GHz, 16 GB DDR3-2133 Corsair Vengence (black/red), EVGA GTX 760 @ 1200 MHz, on an Asus Maximus VI Hero MB (black/red), in a blacked out Antec P280 Tower, with a Xigmatek Night Hawk (black) HSF, Seasonic 760w Platinum (black case, sleeves, wires), 4 SilenX 120mm Case fans with silicon fan gaskets and silicon mounts (all black), a 512GB Samsung SSD (black), and a 2TB Black Western Digital HD (silver/black).
- Location: Arizona
- Contact:
Re: 36 hour tdr bug resolved in linux
Whatever the case, it's still not a good option.
How to provide enough information to get helpful support
Tell me and I forget. Teach me and I remember. Involve me and I learn.
Tell me and I forget. Teach me and I remember. Involve me and I learn.
-
- Posts: 1576
- Joined: Tue May 28, 2013 12:14 pm
- Location: Tokyo
Re: 36 hour tdr bug resolved in linux
Its weekend, nothing better to do so I decided to reinstall my Ubuntu box to mainly switch to EXT3 instead of EXT4 and get a ramdisk in. Sidestory.
I also installed the new nvidia driver 331. Not yet even close run to full 36 hours but some data points I can confirm with the setup
MB: Asus P8Z77 V-PRO
CPU i7 2600S
Memory: 8GB
GPU0: 780 GTX
GPU1: 660 TI
just the first frames
on my 780 it looks very good: 8900 with TPF 3:20 and ~137kPPD; very much normal.
on my 660 Ti it looks ... awful ! 8900 with TPF 10:20 (!) instead 5:47; 17 hours total time instead of 9 hours
So I think after the 660 TI is done I will downgrade to 319 again until some revised driver will be around. Just don't want to loose those points.
(My wife would say: I told you )
Update: I couldn't watch any longer my 660TI suffering;
1) stop the FAHclient
2) ppa-purge
3) reinstalled 319 from ppa:ubuntu-x-swat/x-updates
4) reboot box
5) start FAHclient
Now seems I get the original TPF values back with 5:30 for the 660TI and 3:20 (still) for 780; based on the log file. The PPD estimation and TPF value from client are still off; some more frame to align.
and so end the little experiment with nv-331 ... maybe next time ...
I also installed the new nvidia driver 331. Not yet even close run to full 36 hours but some data points I can confirm with the setup
MB: Asus P8Z77 V-PRO
CPU i7 2600S
Memory: 8GB
GPU0: 780 GTX
GPU1: 660 TI
just the first frames
on my 780 it looks very good: 8900 with TPF 3:20 and ~137kPPD; very much normal.
on my 660 Ti it looks ... awful ! 8900 with TPF 10:20 (!) instead 5:47; 17 hours total time instead of 9 hours
So I think after the 660 TI is done I will downgrade to 319 again until some revised driver will be around. Just don't want to loose those points.
(My wife would say: I told you )
Update: I couldn't watch any longer my 660TI suffering;
1) stop the FAHclient
2) ppa-purge
3) reinstalled 319 from ppa:ubuntu-x-swat/x-updates
4) reboot box
5) start FAHclient
Now seems I get the original TPF values back with 5:30 for the 660TI and 3:20 (still) for 780; based on the log file. The PPD estimation and TPF value from client are still off; some more frame to align.
and so end the little experiment with nv-331 ... maybe next time ...
Please contribute your logs to http://ppd.fahmm.net
-
- Posts: 1576
- Joined: Tue May 28, 2013 12:14 pm
- Location: Tokyo
Re: 36 hour tdr bug resolved in linux
... there was only one good thing I saw with the 331 driver: the 660TI run 5C cooler ; which didn't surprised with the reduced speed
Please contribute your logs to http://ppd.fahmm.net
-
- Posts: 10179
- Joined: Thu Nov 29, 2007 4:30 pm
- Hardware configuration: Intel i7-4770K @ 4.5 GHz, 16 GB DDR3-2133 Corsair Vengence (black/red), EVGA GTX 760 @ 1200 MHz, on an Asus Maximus VI Hero MB (black/red), in a blacked out Antec P280 Tower, with a Xigmatek Night Hawk (black) HSF, Seasonic 760w Platinum (black case, sleeves, wires), 4 SilenX 120mm Case fans with silicon fan gaskets and silicon mounts (all black), a 512GB Samsung SSD (black), and a 2TB Black Western Digital HD (silver/black).
- Location: Arizona
- Contact:
Re: 36 hour tdr bug resolved in linux
v331.58 for Windows posted today.
How to provide enough information to get helpful support
Tell me and I forget. Teach me and I remember. Involve me and I learn.
Tell me and I forget. Teach me and I remember. Involve me and I learn.