climateprediction.net home page
New work Discussion

New work Discussion

Message boards : Number crunching : New work Discussion
Message board moderation

To post messages, you must log in.

Previous · 1 . . . 43 · 44 · 45 · 46

AuthorMessage
KAMasud

Send message
Joined: 6 Oct 06
Posts: 47
Credit: 2,230,853
RAC: 3,561
Message 62560 - Posted: 8 Jun 2020, 12:02:48 UTC - in response to Message 62461.  

Yes as long as they get "their results".... of course if the 3000 WU's were spread 2 per system across the available Windows systems the researchers would get their 3000 WU's back faster than waiting on fewer systems with huge queued stacks of WU's waiting on long due dates.

IMHO

Bill F



I do not agree with this statement " huge queued stacks of WU's waiting on long due dates". Long due dates besides the point, how many cores a machine has is also not much of a deciding point. Store at least ___days work is set at ten and store additional work is also set at ten days of work maximum. So, how many WU's a machine gets is still a self-limiting factor. I have a twelve thread machine which gets twenty-four WU's max. They report back pretty much at the expected time, within one month.

So, where exactly are these ' huge queued stacks of WU's waiting on long due dates" sitting and sitting they are somewhere. In the old day's we used to squirrel away WU's on floppies or alternative media. Is this still going on?
Then there are crashed hard drives which take WU's with them to the grave but they still get reported.


So you have 12 WUs your working on and 12 queued and the results will be back in a month. How much better if you have 12 WUs and someone else has 12 WUs and the results get back in a fortnight.

I had nothing to do with how many WU"s I have and neither can I put a stop to how much I get. Fight with the server.

The queued stacks of WUs tend to be systems where they have, say, 12 cores, download 24 WUs but then only allow 2 WUs to run concurrently alongside their other projects.
ID: 62560 · Report as offensive     Reply Quote
Jim1348

Send message
Joined: 15 Jan 06
Posts: 509
Credit: 22,294,062
RAC: 0
Message 62561 - Posted: 8 Jun 2020, 12:16:46 UTC - in response to Message 62560.  
Last modified: 8 Jun 2020, 12:17:08 UTC

You can of course control the size of your buffer. Setting it to the default of 0.1+0.5 days will get you fewer work units than setting it to 10 days, for example. But that is rather crude, and sometimes they won't send you anything at all.

Unfortunately, the BOINC scheduler is not aware of the "app_config.xml" file, so if you set it to run only two work units, it will still download as if you were running on all 12 cores. So until BOINC gets smarter (a long process), the best way would be for CPDN to provide you a user-selectable limit of how many work units you want downloaded at a time. Several projects do that now: WCG, LHC and Cosmology that I can think of at the moment.

But CPDN has been going in the direction of fewer options. They need to reverse course.
ID: 62561 · Report as offensive     Reply Quote
KAMasud

Send message
Joined: 6 Oct 06
Posts: 47
Credit: 2,230,853
RAC: 3,561
Message 62562 - Posted: 8 Jun 2020, 12:20:23 UTC - in response to Message 62560.  

"The queued stacks of WUs tend to be systems where they have, say, 12 cores, download 24 WUs but then only allow 2 WUs to run concurrently alongside their other projects."


As to this statement, yes true. It is not about allowing two WU's to run "concurrently" alongside other projects. It is all about how many cores you can run at an ambient temperature of 45c without melting the machine down. In the afternoon I can run only two cores( nothing to do with projects). At night, maybe four. Vector in GPU computing also.
Another factor is the base speed. At all twelve cores running simultaneously, maybe 2.2 MHz. A single core. 4.04 MHz. I am still thinking about the advantages of so many cores. Maybe getting WU's of Climate. Should I get a forty-eight cores machine? Naaa, that is a bit of being silly.
ID: 62562 · Report as offensive     Reply Quote
KAMasud

Send message
Joined: 6 Oct 06
Posts: 47
Credit: 2,230,853
RAC: 3,561
Message 62563 - Posted: 8 Jun 2020, 12:30:20 UTC - in response to Message 62561.  

You can of course control the size of your buffer. Setting it to the default of 0.1+0.5 days will get you fewer work units than setting it to 10 days, for example. But that is rather crude, and sometimes they won't send you anything at all.

Unfortunately, the BOINC scheduler is not aware of the "app_config.xml" file, so if you set it to run only two work units, it will still download as if you were running on all 12 cores. So until BOINC gets smarter (a long process), the best way would be for CPDN to provide you a user-selectable limit of how many work units you want downloaded at a time. Several projects do that now: WCG, LHC and Cosmology that I can think of at the moment.

But CPDN has been going in the direction of fewer options. They need to reverse course.



Better would be CPDN slashing drastically the due back date and then re-issuing the WU"s. The current due back date is from the time of Pentium One. I know, it used to take ages then. Now with faster RAM, SSD drives and modernisation, maybe five days to complete.
As to the buffer size, my GPU is busy on another project whose WU"s it completes in four minutes flat. I earn my credits with my GPU and CPU's are full time dedicated to Climate.
ID: 62563 · Report as offensive     Reply Quote
Profile Dave Jackson
Volunteer moderator

Send message
Joined: 15 May 09
Posts: 2771
Credit: 3,449,240
RAC: 58
Message 62564 - Posted: 8 Jun 2020, 13:01:27 UTC - in response to Message 62563.  

Better would be CPDN slashing drastically the due back date and then re-issuing the WU"s. The current due back date is from the time of Pentium One. I know, it used to take ages then. Now with faster RAM, SSD drives and modernisation, maybe five days to complete.


Yes, even on a slow machine like my current desktop that is going to end up like the axe that has been in my family for generations. (Grandfather gave it a new head, father a new handle) tasks complete in 31/32 days max. (Pentium(R) Dual-Core CPU E5400 @ 2.70GHz) Next upgrade will be new CPU memory and motherboard which with PSU and hard disks having been changed already will only leave the case as original.
ID: 62564 · Report as offensive     Reply Quote
KAMasud

Send message
Joined: 6 Oct 06
Posts: 47
Credit: 2,230,853
RAC: 3,561
Message 62565 - Posted: 8 Jun 2020, 14:00:39 UTC

Another advantage for machines who have dedicated their CPU's to Climate, their machines hammer at the server every one and a half hours or so. Their requests I suppose get lined up, maybe justice. Machines which have not dedicated their CPU's to Boinc and if even there is work available (their work quota might be full of letting us say Collatz WU's) Boinc will not ask the server for work. If you check the server state now and then, there are about 22 or 24 machines dedicated. The rest are busy.
ID: 62565 · Report as offensive     Reply Quote
Profile JIM

Send message
Joined: 31 Dec 07
Posts: 1124
Credit: 20,460,788
RAC: 2
Message 62582 - Posted: 14 Jun 2020, 13:21:25 UTC

Is batch 871 still open? I just received 2 Wu’s (both _2s). They have failed on 2 other machines. They must be 3 or 4 months old. Are they still needed an wanted.
ID: 62582 · Report as offensive     Reply Quote
Profile geophi
Volunteer moderator

Send message
Joined: 7 Aug 04
Posts: 1939
Credit: 41,514,751
RAC: 18
Message 62583 - Posted: 14 Jun 2020, 13:56:00 UTC - in response to Message 62582.  

Is batch 871 still open? I just received 2 Wu’s (both _2s). They have failed on 2 other machines. They must be 3 or 4 months old. Are they still needed an wanted.

Batch 871 is still open. It was issued on May 22nd 2020.
ID: 62583 · Report as offensive     Reply Quote
Profile Dave Jackson
Volunteer moderator

Send message
Joined: 15 May 09
Posts: 2771
Credit: 3,449,240
RAC: 58
Message 62584 - Posted: 14 Jun 2020, 15:22:34 UTC

It is rare for batches to be closed under nine months or even a year except when withdrawn because of a major problem that should have been caught in testing when a new batch is subsequently issued.

I can only remember two or three instances o this happening but might well have missed some.
ID: 62584 · Report as offensive     Reply Quote
Profile JIM

Send message
Joined: 31 Dec 07
Posts: 1124
Credit: 20,460,788
RAC: 2
Message 62585 - Posted: 14 Jun 2020, 15:51:05 UTC - in response to Message 62583.  

Thanks. Hopefully I can shepard these two along and get them completed.
ID: 62585 · Report as offensive     Reply Quote
Profile Dave Jackson
Volunteer moderator

Send message
Joined: 15 May 09
Posts: 2771
Credit: 3,449,240
RAC: 58
Message 62586 - Posted: 18 Jun 2020, 14:09:00 UTC

Oops! Just picked up two retreads when I was trying to clear laptop of work prior to doing a clean install of 20.04 - Thought I had put all projects to no new tasks. - Obviously not!
ID: 62586 · Report as offensive     Reply Quote
WB8ILI

Send message
Joined: 1 Sep 04
Posts: 140
Credit: 55,215,656
RAC: 2,914
Message 62587 - Posted: 18 Jun 2020, 19:54:33 UTC

Dave -

What did you do? Upgrade to 20.04 without a clean install? Your computers show you have 20.04 on both computers and the tasks downloaded today.

I upgraded to 20.04 from 18.04 without any problems on several computers as soon as 20.04 became available (actually before as a beta). without any issues.

.
ID: 62587 · Report as offensive     Reply Quote
Profile Dave Jackson
Volunteer moderator

Send message
Joined: 15 May 09
Posts: 2771
Credit: 3,449,240
RAC: 58
Message 62588 - Posted: 19 Jun 2020, 5:06:35 UTC

What did you do? Upgrade to 20.04 without a clean install? Your computers show you have 20.04 on both computers and the tasks downloaded today.


Yes, did a standard upgrade via the command line. However this stopped the manager from working though not the client due to some wxwidgets conflict. This also causes make command to fall over when I roll my own manager on the laptop though not the desktop. I have found a work around with Jord's self extracting manager and client for the laptop to get it going again. Now I just have a longer wait till I can clean things up.
ID: 62588 · Report as offensive     Reply Quote
lazlo_vii

Send message
Joined: 11 Dec 19
Posts: 78
Credit: 1,998,948
RAC: 0
Message 62589 - Posted: 19 Jun 2020, 11:19:57 UTC - in response to Message 62588.  
Last modified: 19 Jun 2020, 11:20:56 UTC

What did you do? Upgrade to 20.04 without a clean install? Your computers show you have 20.04 on both computers and the tasks downloaded today.


Yes, did a standard upgrade via the command line. However this stopped the manager from working though not the client due to some wxwidgets conflict. This also causes make command to fall over when I roll my own manager on the laptop though not the desktop. I have found a work around with Jord's self extracting manager and client for the laptop to get it going again. Now I just have a longer wait till I can clean things up.


FYI, you can open a terminal and issue commands to start/stop/enable/disable the BIONC client before and after upgrades:

sudo systemctl start boinc-client
sudo systemctl stop boinc-client
sudo systemctl disable boinc-client
sudo systemctl enable boinc-client


You can also use the BOINC command line interface to manage the the client. See:

man boinccmd
ID: 62589 · Report as offensive     Reply Quote
Profile Dave Jackson
Volunteer moderator

Send message
Joined: 15 May 09
Posts: 2771
Credit: 3,449,240
RAC: 58
Message 62590 - Posted: 19 Jun 2020, 11:26:24 UTC - in response to Message 62589.  

You can also use the BOINC command line interface to manage the the client. See:


Yes I was managing BOINC from the command line until I got a work around. However I like to play and often build my own BOINC client and manager from source code using the testing versions and would quite like to get back into being able to do that on the laptop.
ID: 62590 · Report as offensive     Reply Quote
Eirik Redd

Send message
Joined: 31 Aug 04
Posts: 368
Credit: 137,914,252
RAC: 55
Message 62593 - Posted: 20 Jun 2020, 5:15:35 UTC - in response to Message 62590.  

You can also use the BOINC command line interface to manage the the client. See:


Yes I was managing BOINC from the command line until I got a work around. However I like to play and often build my own BOINC client and manager from source code using the testing versions and would quite like to get back into being able to do that on the laptop.


Yes, yes boinccmd has been a great help to me over the years when the gui fails, as it does from time to time.
But I don't think many users even imagine how useful a cli interface can be.
My daughter asked me a few months ago, while taking a coding class --"dad, how do I get out of less?" "q".
How few CPDN volunteers even know what differential equation is?

How to get more crunchers?
Then there will be more work units.
ID: 62593 · Report as offensive     Reply Quote
Previous · 1 . . . 43 · 44 · 45 · 46

Message boards : Number crunching : New work Discussion

©2020 climateprediction.net