Posts by popandbob

1) Message boards : SETI@home Staff Blog : This hurts me as much as it hurts you. (Message 2037238)
Posted 11 Mar 2020 by Profile popandbob
Post:
In the downtime, perhaps its time to consider how funds are asked for from volunteers.

Instead of asking for a general donation why not ask for specific budget items?
Allow donors to select exactly where their money goes.
If not enough is coming in to pay the power bills - ask for donations for the power! People will respond.

Look at how well the disk drive went as a prime example.

Just my 2 cents worth.
2) Message boards : Number crunching : Suggestions/Comments for a SETI@home v3 (Message 2036181)
Posted 6 Mar 2020 by Profile popandbob
Post:
I think a big suggestion would be to have a non-university group take over to unlock lots of new funding sources - the biggest of which is advertising!

We have the source code - we have plenty of volunteers who are expert coders - whats to stop us from creating our own project(s) ?

Do we have enough support to carry on?
I think its worth considering.
3) Message boards : News : SETI@home hibernation (Message 2035708)
Posted 4 Mar 2020 by Profile popandbob
Post:
Well I am disappointed. This feels very much like the team is giving up because of the recent database issues. There are plenty of cures out there, but the team is out of energy, out of drive to continue.

Perhaps its time to re-think the design of Boinc to make it vastly easier to manage. Create a ‘self-healing’ Boinc that will operate with very little oversight. I’m sure some volunteer coders could step up to the plate and help with that.

Alternately - why not open up the full Seti@home code to public so others could take the project and create a new start?
4) Message boards : Number crunching : The Server Issues / Outages Thread - Panic Mode On! (118) (Message 2030894)
Posted 5 Feb 2020 by Profile popandbob
Post:
I haven`t noticed anyone comment on this yet but the reason for the growing assimilation number is quite a simple one.... They have less spindles on the storage drive. Less spindles means lower read and write rates.
5) Message boards : Number crunching : How to Fix the current Issues - One man's opinion (Message 2029568)
Posted 27 Jan 2020 by Profile popandbob
Post:
Define "Power Users".


Everyone would be free to sign up for the separate project. Its up to the user to make sure their computer is able to meet the deadlines no different than any other short deadline project.
6) Message boards : Number crunching : How to Fix the current Issues - One man's opinion (Message 2029566)
Posted 27 Jan 2020 by Profile popandbob
Post:
You would be running an extra database on the same server. Same amount of data, same type of data, but in more tables.
More tables is good when normalising a database (up to a point), but when you are creating more tables to effectively double up on some of the data, and keeping it on the same hardware, you're increasing the load that hardware has to deal with..


No it would not be an extra database on the same server - my plan was to stop using the replica boinc database and use that server to host the separate project.

As to your other comment, yes hardware will continue to improve so do you A) tell participants with older hardware not to bother or b) set up a separate project for those with faster hardware. It could be done under this project as well but it adds user complexity.
7) Message boards : Number crunching : How to Fix the current Issues - One man's opinion (Message 2029482)
Posted 27 Jan 2020 by Profile popandbob
Post:
I'm not sure how you figure it would increase the server work Grant.
Creating a separate project with greatly increased unit sizes would vastly decrease server loading because it would have at least 10x less tasks/work units to handle!
8) Message boards : Number crunching : How to Fix the current Issues - One man's opinion (Message 2029472)
Posted 27 Jan 2020 by Profile popandbob
Post:
I've been a long term SETI cruncher and I would like to put forward my thoughts on a fix for the current issues.

I propose that the current replica server be used to create a separate project for the "Power Users" - those who have high speed computers with lots of GPU's or CPU's
This separate project would have vastly increased task sizes - 10x larger at least, with greatly reduced deadlines (1-2 weeks maximum)
There should be a credit bonus (say 10%?) for the increased task sizes and reduced deadlines. This would encourage those power users to switch to this lower overhead project.
I would estimate half of the current servers here at main could be shifted over to this "Power Users" Project.
As an added benefit, the projects efficiency would increase due to the reduced overlap present in the larger tasks.

Power users here create a massive workload for the servers currently. The top 10 computers alone (as of when I checked last night) had over 280,000 tasks in the database with zero in progress. If things were running well they would easily have another 40,0000 + tasks in the database.

I understand this would cause an increased workload on the team running 2 projects instead of 1, however the reduced workload on the servers would also help alleviate some of the workload from issues such as those we are currently facing. As an added benefit, when one project has issues, the other can take some of the load which would allow the team to not have to prioritize repairs to keep things running to the same degree they do now.
I also understand this would require the main servers to handle all of the task viewing and read only tasks, however several years ago when the number of tasks was vastly less, it used to handle it just fine and I do believe with the above changes it could handle it again since most set and forget users which will remain on this project will not be checking up on tasks anywhere near as often. Those "Power Users" who do check up on tasks would create less workload on the "Power Users" Project due to the increased task sizes.

These changes will allow the project to still have those older, part time contributors able to do their bit while allowing the "Power Users" to use their ever increasing hardware capabilities to contribute also.
9) Message boards : Number crunching : The Server Issues / Outages Thread - Panic Mode On! (118) (Message 2027830)
Posted 16 Jan 2020 by Profile popandbob
Post:
the feeder only holds 200 tasks at a time.

And of those 200 a portion of them are reserved for astropulse so I`d guess between 150-180 tasks for v8 and the feeder is refilled every 20 seconds when things are running good. When the responses take longer, the refilling time takes longer also.
10) Message boards : News : Unexplained database slowness (Message 1931448)
Posted 22 Apr 2018 by Profile popandbob
Post:
Could be. Next we need to catch that process in the act of being enabled and then go look at the Haveland graphs for synchronicity.

Process currently running - only 3 Green Bank splitters running - remaining splitters are not running.
11) Message boards : News : Unexplained database slowness (Message 1931105)
Posted 20 Apr 2018 by Profile popandbob
Post:
i've just seen it , splitters speed limit ?

No, I think it is the process that knocks the splitters offline when the RTS buffer hits its max limit trip-point of around 620-640K. I've caught the splitters offline several times when the RTS buffer gets full. When the splitters go offline, it frees up resources for the file deleters and purgers to get caught up. You can see the behavior in the Haveland graphs.


The Splitters have that function build in. I suspect the function of this new process is to reduce the number of splitters running when under heavy db load to allow for other processes to take priority.
12) Message boards : News : Unexplained database slowness (Message 1927724)
Posted 1 Apr 2018 by Profile popandbob
Post:
The flaw still lies in the majority of the workload is in the workunit section. The forums/users add very little workload relatively.

If one was to separate the workunit database into separate sections (a lot of work no denying that) it would create the following situations:

Increased per CPU/GPU task numbers (we were told they were limited because of DB size)
Reduced weekly downtime ( instead of dealing with 1 large db you deal with only 2 smaller ones as only 2 would be fragmented, the others would be linear in function)
Possibility of still issuing work during weekly downtime (if ready to send were on a separate DB it could be done)
Reduced DB load (Instead of querying the full db to find tasks/wu's to delete/purge it could be done by a simple return first/last 20 results of my suggested waiting for purge db)

Dealing with a single large DB is only going to get worse as hardware continues to get better and more users join. It won't get any smaller.
13) Message boards : News : Unexplained database slowness (Message 1927626)
Posted 1 Apr 2018 by Profile popandbob
Post:
My 2cents worth...
I think perhaps its time for this project to rethink the 1 master, 1 slave database setup.
I do not see any reason preventing a multi-master database or several databases.
I think the best move would be splitting the database into several smaller databases. 1 ready to send, 1 in-progress, 1 waiting-validation, 1 awaiting purge.

For those wondering about finances/fundraising... ever look how many times this project has managed to raise the full value of its budget? I haven't seen it happen once in the 12+ years I've been here. The simple fact that this project is still here after falling that short on the budget continuously for that many years is a testament to the time and effort put forward by the crew here to keep the doors open.
14) Message boards : Number crunching : Panic Mode On (110) Server Problems? (Message 1920387)
Posted 22 Feb 2018 by Profile popandbob
Post:
From the info provided on the SSP down at the bottom of the page "(each file contains data for 14 channels)" but that doesn't answer your question.

I don't know the exact number of tasks per file other than guessing that 52.45GB ÷ 703KB per task = 74608 tasks. But how much overhead is involved with each task generation is unknown.


Don't forget the overlap and the file info adds a few bytes per wu...
15) Message boards : Number crunching : Intel and Gforce cards running together (Message 1904624)
Posted 3 Dec 2017 by Profile popandbob
Post:
Grant, I don't know if its just a SETI issue but when I was testing a new app over at folding@home the iGPU actually improved CPU output by 50%
16) Message boards : News : Breakthrough Listen data now flowing. (Message 1779177)
Posted 14 Apr 2016 by Profile popandbob
Post:
It looks like there isn't any astropulse for the breakthrough data? Is that due to the data itself or is there another reason?
17) Message boards : Number crunching : Panic Mode On (84) Server Problems? (Message 1373405)
Posted 30 May 2013 by Profile popandbob
Post:
Got 52 Tasks first try... All downloaded just fine.
Saw a funny message in BOINC a couple min ago though...

30/05/2013 3:52:34 AM | SETI@home | Sending scheduler request: To fetch work.
30/05/2013 3:52:34 AM | SETI@home | Not requesting tasks
30/05/2013 3:52:36 AM | SETI@home | Scheduler request completed

18) Message boards : Number crunching : Coming towards the end of an era in the top 100 machines (Message 1370185)
Posted 21 May 2013 by Profile popandbob
Post:


Not progress. Good Marketing. GTX295 versus GTX690.


The 690 is probably running 2 or 3 wu per gpu... judging by that computers RAC I would say it is.
19) Message boards : Technical News : Labyrinth of Light (Oct 06 2011) (Message 1159646)
Posted 7 Oct 2011 by Profile popandbob
Post:
Perhaps it would be a good idea to put the goodsearch/goodshop link on the donation page (since it wasn't mentioned in the email)
Bob
20) Message boards : SETI@home Science : SETI Brainstorm (Message 1156477)
Posted 27 Sep 2011 by Profile popandbob
Post:
I think that someone creative could turn this idea into something special...

What I'm thinking of is something along the lines of fold.it

Basically you make a program to visualize the data in 3D (in much smaller chunks of course!) and have users scan through it using a few built in tools but have the option available for users to write scripts to do what ever they want with the data (without being able to edit it)
It could be turned into a fun game I think... highest scoring signal wins!

Bob


Next 20


 
©2024 University of California
 
SETI@home and Astropulse are funded by grants from the National Science Foundation, NASA, and donations from SETI@home volunteers. AstroPulse is funded in part by the NSF through grant AST-0307956.