LTT Folding Team's Emergency Response to Covid-19

[J1mjam]

8 minutes ago, Macaw2000 said:

Nice! Folding is an embarrassingly good application for this. You have a non-mission critical workload that is compute intensive. AWS calls it spot, Google calls it preemptible, and Azure calls it Low-priority but all essentially the same thing. Yeah it can be a pain to manage if you don't build some automation but you are on the right track.

My only worry with these instance types is losing the WU.  Not so much that I lose the points, but of the lost time on the WU to the overall science effort. 

 

I suspect the overall impact to points is probably negligible, as you could twice as many instances for the same cost.

[Zando_]

40 minutes ago, TVwazhere said:

EVGA X58 chipset Dual CPU motherboards

5520, but they allow for OCing which no other 5520 boards do so functionally they're *almost* the same. Some slight differences, but the SR-2 does also use the same PCIe lane setup and placement that the X58 Classified SLI 4-Way does so it blurs the line even more lol. 

Basically stupidly large badass board that lets you overclock 2 Xeons. 

46 minutes ago, The King of the Undead said:

what are these?

See above for the SR-2. The SR-X was eeeeh. It has similar funkiness to the SR-2, but dual socket capable Xeons on the 2011 platform are not overclockable AFAIK so it basically flopped. 

[Gustavehomme01]

41 minutes ago, LAR_Systems said:

Yeah it's really messed up, the admin system is buggered.

As long as i can close my instances on time? 

[NetoriusNick]

6 minutes ago, Zando Bob said:

5520, but they allow for OCing which no other 5520 boards do so functionally they're *almost* the same. Some slight differences, but the SR-2 does also use the same PCIe lane setup and placement that the X58 Classified SLI 4-Way does so it blurs the line even more lol. 

Basically stupidly large badass board that lets you overclock 2 Xeons. 

See above for the SR-2. The SR-X was eeeeh. It has similar funkiness to the SR-2, but dual socket capable Xeons on the 2011 platform are not overclockable AFAIK so it basically flopped. 

the SR-X is clocking 300K ppd just on CPUs ( 2off 2680V2) so to me not bad.

[Atreiumontoya]

Final credit estimate, 128867.00 points --- That was a big one!

[HaRdLy007]

Okay, finally got my instance, but now I can't install the nVidia drivers...

 It won't allow me to add the nVidia repository

 

Help?

[jctappel67]

6 minutes ago, Gustavehomme01 said:

As long as i can close my instances on time? 

It seems to have been fixed now.

[Zando_]

2 minutes ago, NetoriusNick said:

the SR-X is clocking 300K ppd just on CPUs ( 2off 2680V2) so to me not bad.

Oh yeah they still run stock CPUs fine, they just aren't XOC boards, which was kind of the point of the Super Record boards. 

[TVwazhere]

13 minutes ago, Zando Bob said:

5520, but they allow for OCing which no other 5520 boards do so functionally they're *almost* the same. Some slight differences, but the SR-2 does also use the same PCIe lane setup and placement that the X58 Classified SLI 4-Way does so it blurs the line even more lol.

Ah, thought they were x58's. Interesting.

[Gustavehomme01]

 

 

 

 

Spoiler

2 minutes ago, HaRdLy007 said:

Okay, finally got my instance, but now I can't install the nvidia drivers...

 

Help?

 

Are you following this guide? it the same steps just change the GPU to the needed one, i also whent with a v4core15Gb Ram to make sure I'm not starving the GPUs.

 

[bafo_ah]

5 minutes ago, HaRdLy007 said:

Okay, finally got my instance, but now I can't install the nvidia drivers...

 

Help?

Hope you using centos, paste line by line, its all setup, or you can use this https://cloud.google.com/compute/docs/gpus/install-drivers-gpu

 

Spoiler

sudo dnf install -y epel-release
sudo dnf install -y nano wget telnet fail2ban fail2ban-systemd
# install fail2ban for security? ddos prevention? just to lazy to change ssh port?
sudo systemctl enable fail2ban
sudo nano /etc/fail2ban/jail.local
# paste this line :
[DEFAULT]
# Ban hosts for one day!:
bantime = 86400

# Override /etc/fail2ban/jail.d/00-firewalld.conf:
banaction = iptables-multiport

[sshd]
enabled = true

# ctrl+x for exit and then y then enter

sudo systemctl restart fail2ban
sudo fail2ban-client status sshd

sudo dnf install -y kernel
sudo dnf install -y kernel-devel-$(uname -r) kernel-headers-$(uname -r)
sudo dnf install -y http://developer.download.nvidia.com/compute/cuda/repos/rhel8/x86_64/cuda-repo-rhel8-10.1.243-1.x86_64.rpm
sudo dnf install -y https://dl.fedoraproject.org/pub/epel/epel-release-latest-8.noarch.rpm
sudo dnf clean all
sudo dnf install -y cuda
nvidia-smi # you should see your GPU here, if not, you screwed

wget https://download.foldingathome.org/releases/public/release/fahclient/centos-5.3-64bit/v7.4/fahclient-7.4.4-1.x86_64.rpm
sudo rpm -i --nodeps fahclient-7.4.4-1.x86_64.rpm

telnet localhost 36330
slot-info
options user=usernamehere passkey=yourpasskeyhere team=223518 client-type=beta max-packet-size=big power=full gpu=true
exit

sudo /etc/init.d/FAHClient stop
# wait a moment, cross your finger... then proceed
sudo /etc/init.d/FAHClient start

telnet localhost 36330
slot-info
# you should see your GPU here, and we can delete CPU slot
slot-delete 0
always_on
unpause
exit

tail -f /var/lib/fahclient/log.txt

 

 

[HaRdLy007]

2 minutes ago, bafo_ah said:

Hope you using centos, paste line by line, its all setup, or you can use this https://cloud.google.com/compute/docs/gpus/install-drivers-gpu

 

  Hide contents

sudo dnf install -y epel-release
sudo dnf install -y nano wget telnet fail2ban fail2ban-systemd
# install fail2ban for security? ddos prevention? just to lazy to change ssh port?
sudo systemctl enable fail2ban
sudo nano /etc/fail2ban/jail.local
# paste this line :
[DEFAULT]
# Ban hosts for one day!:
bantime = 86400

# Override /etc/fail2ban/jail.d/00-firewalld.conf:
banaction = iptables-multiport

[sshd]
enabled = true

# ctrl+x for exit and then y then enter

sudo systemctl restart fail2ban
sudo fail2ban-client status sshd

sudo dnf install -y kernel
sudo dnf install -y kernel-devel-$(uname -r) kernel-headers-$(uname -r)
sudo dnf install -y http://developer.download.nvidia.com/compute/cuda/repos/rhel8/x86_64/cuda-repo-rhel8-10.1.243-1.x86_64.rpm
sudo dnf install -y https://dl.fedoraproject.org/pub/epel/epel-release-latest-8.noarch.rpm
sudo dnf clean all
sudo dnf install -y cuda
nvidia-smi # you should see your GPU here, if not, you screwed

wget https://download.foldingathome.org/releases/public/release/fahclient/centos-5.3-64bit/v7.4/fahclient-7.4.4-1.x86_64.rpm
sudo rpm -i --nodeps fahclient-7.4.4-1.x86_64.rpm

telnet localhost 36330
slot-info
options user=usernamehere passkey=yourpasskeyhere team=223518 client-type=beta max-packet-size=big power=full gpu=true
exit

sudo /etc/init.d/FAHClient stop
# wait a moment, cross your finger... then proceed
sudo /etc/init.d/FAHClient start

telnet localhost 36330
slot-info
# you should see your GPU here, and we can delete CPU slot
slot-delete 0
always_on
unpause
exit

tail -f /var/lib/fahclient/log.txt

 

 

Ubuntu 18.04 not Centos

[Gustavehomme01]

 

 

 

 

Spoiler

26 minutes ago, Macaw2000 said:

Nice! Folding is an embarrassingly good application for this. You have a non-mission critical workload that is compute intensive. AWS calls it spot, Google calls it preemptible, and Azure calls it Low-priority but all essentially the same thing. Yeah it can be a pain to manage if you don't build some automation but you are on the right track.

 

I was trying to figure out how to start a preemptible instance this morning at 3am , but i was just hitting a wall so i opened a on-demand instance instead. Is there any guides on opening a preemptible instance? is it just a check box that i missed?

[Xaiux]

7 minutes ago, Zando Bob said:

Oh yeah they still run stock CPUs fine, they just aren't XOC boards, which was kind of the point of the Super Record boards.

What would be the top end CPUs you could run in a board like this, and what sort of prices would I be looking at? Sounding super interesting for a server build

[jctappel67]

3 minutes ago, Gustavehomme01 said:

Spoiler

 

 

 

 

  Reveal hidden contents

 

I was trying to figure out how to start a preemptible instance this morning at 3am , but i was just hitting a wall so i opened a on-demand instance instead. Is there any guides on opening a preemptible instance? is it just a check box that i missed?

In the setup menu, under  "Management, security, disks, networking, sole tenancy" there is an option for preemptibility

[NetoriusNick]

2 minutes ago, Xaiux said:

What would be the top end CPUs you could run in a board like this, and what sort of prices would I be looking at? Sounding super interesting for a server build

E5-2690 or E5-2687W

[Zando_]

Just now, Xaiux said:

What would be the top end CPUs you could run in a board like this, and what sort of prices would I be looking at? Sounding super interesting for a server build

They're terrible for a lot of server use, they're XOC boards. The SR-2 can run up to the X5690, 6c/12t Westmere-EP chips from mid 2011. There's much better boards (usually SuperMicro) ones for server use, that are also more usable form factors too. You can ask @bimmerman about the woes of trying to get virtualization and such going on the SR-2. 

SR-X is eh. It's got some issues with RAM but it'd be fine for a server board. But you do have to deal with the HPTX form factor, very few cases currently sold actually support it well. 

[NetoriusNick]

4 minutes ago, Xaiux said:

What would be the top end CPUs you could run in a board like this, and what sort of prices would I be looking at? Sounding super interesting for a server build

http://www.cpu-upgrade.com/mb-EVGA/Classified_SR-X.html

[Xaiux]

5 minutes ago, Zando Bob said:

They're terrible for a lot of server use, they're XOC boards. The SR-2 can run up to the X5690, 6c/12t Westmere-EP chips from mid 2011. There's much better boards (usually SuperMicro) ones for server use, that are also more usable form factors too. You can ask @bimmerman about the woes of trying to get virtualization and such going on the SR-2.

SR-X is eh. It's got some issues with RAM but it'd be fine for a server board. But you do have to deal with the HPTX form factor, very few cases currently sold actually support it well.

I'm not sure what XOC means honestly. I suppose it would be very power inefficient as well

[snorlaxgangs]

Speaking of SR-2, found one on debauer shelf.

[Zando_]

2 minutes ago, Xaiux said:

I'm not sure what XOC means honestly. I suppose it would be very power inefficient as well

eXtreme OverClocking. They're focused on bench numbers and over to top gaming rigs, not really server use. EVGA used the server chipset (5520 on the SR-2) only because that's needed to run dual CPUs. 

[bafo_ah]

7 minutes ago, HaRdLy007 said:

Ubuntu 18.04 not Centos

I havent try it on ubuntu yet... Sorry... But you can follow google guide

https://cloud.google.com/compute/docs/gpus/install-drivers-gpu

 

If you can see your GPU with nvidia-smi then you can download and install fahclient

 

https://foldingathome.org/faqs/installation-guides/linux/manual-installation-optional-advanced/terminal-installation-for-debian-mint-ubuntu/

 

Only need fahclient

 

Setting option (username, team, passkey)... Restart FAHClient service if necessary, and youre good to go... I think...

[Gustavehomme01]

Spoiler

 

That's some savings...  it's just to manage it that's all. 

[jctappel67]

Just now, Gustavehomme01 said:

  Reveal hidden contents

 

That's some savings...  it's just to manage it that's all. 

Your picture seems to be missing, but yeah. $300/month vs $700

[Metallus97]

I am the guy who wrote the guide about GCE folding. I did not know about this instance type back then. Sadly I don’t have free credit left and am pretty financially constrained right now (due to friggin corona).

 

Therefore I cant test this instance type and modify the guide.

Annyone wanna help with that?

Shoot me a PM