Panic Mode On (94) Server Problems?

Message boards : Number crunching : Panic Mode On (94) Server Problems?
Message board moderation

To post messages, you must log in.

Previous · 1 . . . 4 · 5 · 6 · 7 · 8 · 9 · 10 . . . 22 · Next

AuthorMessage
Profile Jimbocous Project Donor
Volunteer tester
Avatar

Send message
Joined: 1 Apr 13
Posts: 1849
Credit: 268,616,081
RAC: 1,349
United States
Message 1625246 - Posted: 8 Jan 2015, 2:51:27 UTC - in response to Message 1625228.  

... monetary donation is nothing compared to the costs of the electrical power my two crunchers accumulate over a year ...


A good point, one that perhaps some folks should keep in mind.
ID: 1625246 · Report as offensive
Profile betreger Project Donor
Avatar

Send message
Joined: 29 Jun 99
Posts: 11360
Credit: 29,581,041
RAC: 66
United States
Message 1625249 - Posted: 8 Jan 2015, 3:00:51 UTC - in response to Message 1625247.  

Ten Dollar donation?

Thar was the minimum the last time I looked since I give a bit more I did not look last week,
ID: 1625249 · Report as offensive
Profile Keith Myers Special Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 29 Apr 01
Posts: 13161
Credit: 1,160,866,277
RAC: 1,873
United States
Message 1625250 - Posted: 8 Jan 2015, 3:14:12 UTC - in response to Message 1625243.  

You are getting much more than what you paid for.


The message boards alone are worth the price of a donation, great forum for exchanging info and ideas, not to mention humor.

And unlike Twitter, Facebook etc. ad nauseum, you are actually contributing to scientific research instead of vacuous self admiration.

Just one old man's opinion....

:D


+100

You have that right!! The forums are one of the best aspects of the project. I can always depend on the SETI forums to cut to the chase about hardware or software issues with the BOINC platform. The signal to noise ratio is SO MUCH higher here at SETI compared to Einstein or MilkyWay.

Cheers, Keith
Seti@Home classic workunits:20,676 CPU time:74,226 hours

A proud member of the OFA (Old Farts Association)
ID: 1625250 · Report as offensive
Profile Keith Myers Special Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 29 Apr 01
Posts: 13161
Credit: 1,160,866,277
RAC: 1,873
United States
Message 1625251 - Posted: 8 Jan 2015, 3:21:57 UTC - in response to Message 1625247.  

... monetary donation is nothing compared to the costs of the electrical power my two crunchers accumulate over a year ...


A good point, one that perhaps some folks should keep in mind.

Ten Dollar donation?



Not in California with its $0.35/kWhr tier and 24/7 computing. Even with solar power, the costs are significant over the year. I try to build up a buffer over the summer to allow for the resistive heating the two crunchers provide over the winter. Still cheaper than the natural gas heating. I will always consider my distributed computing efforts a great benefits to cost relationship no matter the ultimate cost to my pocketbook. No, in fact a $100 dollar donation again this year. From a fixed income retiree.

Cheers, Keith
Seti@Home classic workunits:20,676 CPU time:74,226 hours

A proud member of the OFA (Old Farts Association)
ID: 1625251 · Report as offensive
Cosmic_Ocean
Avatar

Send message
Joined: 23 Dec 00
Posts: 3027
Credit: 13,516,867
RAC: 13
United States
Message 1625259 - Posted: 8 Jan 2015, 4:21:55 UTC
Last modified: 8 Jan 2015, 4:31:04 UTC

Just wanted to point out and put into perspective for anyone who was wondering..

The fact that there are ~519,000 AP WUs waiting for assimilation.. 519000*8MB = 3.96 TiB that are sitting on-disk presently. That doesn't factor in "out in the field," "waiting for validation," nor does it factor in anything on the MB-side of things. So just from that alone is 4TB.

Looking at the other values now.. specifically "returned, awaiting validation" bearing in mind that is results, not WUs.. probably assume an average of 3 results per WU, so ~1.2M/3 = 400k * 8 MB = 3.05 TiB, so that brings us up to 7TB.

"out in the field" is again results, not WUs, so that rough-estimates out to 375 GB, making 7.4 TB. Then we add all the MB stuff in. "out in the field" is about 320 GB, same for "returned, awaiting validation", so that brings us up to 8TB.. roughly.

I think it's safe to reasonably assume that the WU storage area was 8TB before more had to be added to it.

And I think that extra space got added, because you can see the surge on the cricket and the creation rate is over 1/sec now when it was like 0.1/sec earlier in the day. No idea how much more space got added though. Hopefully assimilation can begin sooner rather than later though.
Linux laptop:
record uptime: 1511d 20h 19m (ended due to the power brick giving-up)
ID: 1625259 · Report as offensive
Profile Zombu2
Volunteer tester

Send message
Joined: 24 Feb 01
Posts: 1615
Credit: 49,315,423
RAC: 0
United States
Message 1625261 - Posted: 8 Jan 2015, 4:25:17 UTC

Either way

I'm out of GPU tasks since monday and my cpu tasks on my main cruncher is diminishing fast
I came down with a bad case of i don't give a crap
ID: 1625261 · Report as offensive
Profile JaundicedEye
Avatar

Send message
Joined: 14 Mar 12
Posts: 5375
Credit: 30,870,693
RAC: 1
United States
Message 1625263 - Posted: 8 Jan 2015, 4:30:09 UTC - in response to Message 1625251.  

That Ritchey-Chretien next to you is pretty impressive for 'fixed income retiree'..........I'm jealous.

:DD

"Sour Grapes make a bitter Whine." <(0)>
ID: 1625263 · Report as offensive
Profile Zombu2
Volunteer tester

Send message
Joined: 24 Feb 01
Posts: 1615
Credit: 49,315,423
RAC: 0
United States
Message 1625272 - Posted: 8 Jan 2015, 4:48:59 UTC - in response to Message 1625263.  
Last modified: 8 Jan 2015, 4:49:09 UTC

That Ritchey-Chretien next to you is pretty impressive for 'fixed income retiree'..........I'm jealous.

:DD


yeah i was looking at that too and thought ... man that must be one hell of a fixed income hahaha
I came down with a bad case of i don't give a crap
ID: 1625272 · Report as offensive
Profile JaundicedEye
Avatar

Send message
Joined: 14 Mar 12
Posts: 5375
Credit: 30,870,693
RAC: 1
United States
Message 1625278 - Posted: 8 Jan 2015, 4:57:10 UTC

In case anyone hasn't seen it.........

NASA Science News for Jan. 7, 2015

Recently, Hubble revisited the famous "Pillars of Creation," providing astronomers with a sharper and wider view of the iconic star forming region. The image hints that the Pillars of Creation might also be "pillars of destruction."

FULL STORY: http://science.nasa.gov/science-news/science-at-nasa/2015/07jan_pillarsofcreation/

Unbelievably beautiful, how insignificant we all are..........

"Sour Grapes make a bitter Whine." <(0)>
ID: 1625278 · Report as offensive
Profile Keith Myers Special Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 29 Apr 01
Posts: 13161
Credit: 1,160,866,277
RAC: 1,873
United States
Message 1625288 - Posted: 8 Jan 2015, 5:17:29 UTC - in response to Message 1625263.  

I consider myself fortunate to get in on the ground floor for the first offerings of a new manufacturer. I was working at the time and had the cash at hand and I definitely hit the jackpot on this purchase. Best bang for the buck so far in my astrophotography hobby. When I made the purchase, I was figuring this was going to be my retirement scope; same with the mount. I didn't even consider that I would be stuck on the upgrade treadmill after this. I made a conscious decision to only consider products I could be happy with for the future with no upgrades after with limited resources. I think I hit it out of the park with the Deep Sky Instruments RC10C. Same with the Mountain Instruments MI-250 mount. I also have the Stellarvue SV-152 refractor to mount on it for large subjects at medium focal length. These two scopes cover just about everything I want to photograph. I figured I had to make purchases I could be happy with for the future in my retirement. Never again going to have the resources I had when employed so had better make the most of it.

Sure there are larger available, but the scopes I have are the best fit I have for the mount. Doesn't mean I wouldn't want the newest AstroPhysics AP-1600 mount. At the time, I couldn't stomach the 2 year waiting list for the AP-1200 and the equivalent MI-250 was available in 4 months. So the MI-250 it was. Never been happier even though the MI-250 is no longer made. The combination so far has given me plenty of room to grow my skills. It isn't the hardware holding me back.

Cheers, and thanks for noticing the hardware.

Keith
Seti@Home classic workunits:20,676 CPU time:74,226 hours

A proud member of the OFA (Old Farts Association)
ID: 1625288 · Report as offensive
Profile JaundicedEye
Avatar

Send message
Joined: 14 Mar 12
Posts: 5375
Credit: 30,870,693
RAC: 1
United States
Message 1625297 - Posted: 8 Jan 2015, 5:38:13 UTC - in response to Message 1625288.  



Cheers, and thanks for noticing the hardware.

Keith


I've been considering an upgrade to my 'observatory' equipment(HaHaHa a camper on a Dodge PU to get away from the lights of Denver). I have been using a 1964 Dynamax 8" for 35 years. It no longer has a working clock drive and no parts are available. Time to bite the bullet and devote some of my fixed income to the cause. Unfortunately for me JMI Telescopes is only 3 miles away and beckons to my Credit Card on a regular basis.

Retirement is hell........

"Sour Grapes make a bitter Whine." <(0)>
ID: 1625297 · Report as offensive
Profile Keith Myers Special Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 29 Apr 01
Posts: 13161
Credit: 1,160,866,277
RAC: 1,873
United States
Message 1625304 - Posted: 8 Jan 2015, 6:10:28 UTC - in response to Message 1625297.  



I've been considering an upgrade to my 'observatory' equipment(HaHaHa a camper on a Dodge PU to get away from the lights of Denver). I have been using a 1964 Dynamax 8" for 35 years. It no longer has a working clock drive and no parts are available. Time to bite the bullet and devote some of my fixed income to the cause. Unfortunately for me JMI Telescopes is only 3 miles away and beckons to my Credit Card on a regular basis.

Retirement is hell........



A lot of the times, it is the location and not the equipment that defines your experience. The photo in my profile was taken at the Central Nevada Star Party. Best dark sky site I've experienced in North America so far. Doesn't hold a candle to the middle of the Pacific on a ship nor Western Australia east of the Coast Range. Restarted my childhood hobby with a Celestron 8" SCT. Still have it. Easiest clock drive scope I have to setup. Great for elementary school outreach programs and forgiving to clumsy and sticky little fingers. Ahh! Bino scopes. Now that is hard to resist the call of the credit card. Stay strong. Last temptation was the views from a home-brew 17" binocular scope at the Black Butte Lake Star Party. Mmmmm. good.

Keith
Seti@Home classic workunits:20,676 CPU time:74,226 hours

A proud member of the OFA (Old Farts Association)
ID: 1625304 · Report as offensive
Speedy
Volunteer tester
Avatar

Send message
Joined: 26 Jun 04
Posts: 1639
Credit: 12,921,799
RAC: 89
New Zealand
Message 1625306 - Posted: 8 Jan 2015, 6:23:03 UTC
Last modified: 8 Jan 2015, 6:26:36 UTC

To bring this thread the back on topic it would appear that extra space created has increased the splitting speed. MB tasks are being split at over 23 a second and it is struggling to make a ready to send buffer, as always APs are going out as fast as they can be split
ID: 1625306 · Report as offensive
Dena Wiltsie
Volunteer tester

Send message
Joined: 19 Apr 01
Posts: 1628
Credit: 24,230,968
RAC: 26
United States
Message 1625311 - Posted: 8 Jan 2015, 6:44:33 UTC - in response to Message 1625306.  

To bring this thread the back on topic it would appear that extra space created has increased the splitting speed. MB tasks are being split at over 23 a second and it is struggling to make a ready to send buffer, as always APs are going out as fast as they can be split

Yes, but in the last few hours there are 10,000 more AP work units in the field. The split rate is slow but making progress filling all those empty queues.
ID: 1625311 · Report as offensive
Speedy
Volunteer tester
Avatar

Send message
Joined: 26 Jun 04
Posts: 1639
Credit: 12,921,799
RAC: 89
New Zealand
Message 1625317 - Posted: 8 Jan 2015, 7:39:26 UTC - in response to Message 1625311.  

To bring this thread the back on topic it would appear that extra space created has increased the splitting speed. MB tasks are being split at over 23 a second and it is struggling to make a ready to send buffer, as always APs are going out as fast as they can be split

Yes, but in the last few hours there are 10,000 more AP work units in the field. The split rate is slow but making progress filling all those empty queues.

This is good news
ID: 1625317 · Report as offensive
W-K 666 Project Donor
Volunteer tester

Send message
Joined: 18 May 99
Posts: 19012
Credit: 40,757,560
RAC: 67
United Kingdom
Message 1625339 - Posted: 8 Jan 2015, 8:45:23 UTC - in response to Message 1625317.  
Last modified: 8 Jan 2015, 8:49:47 UTC

To bring this thread the back on topic it would appear that extra space created has increased the splitting speed. MB tasks are being split at over 23 a second and it is struggling to make a ready to send buffer, as always APs are going out as fast as they can be split

Yes, but in the last few hours there are 10,000 more AP work units in the field. The split rate is slow but making progress filling all those empty queues.

This is good news

Would be, if true.

I've received 25 AP tasks in total on my primary machine since 00:00 today. But only 4 in the last 3 hours, in that time it would have completed at least 6 AP tasks. Therefore it has slowed down, despite several pushes on the project update button, and now the cache is getting smaller.

edit] whinging works just got another AP task at 08:47 LOL
ID: 1625339 · Report as offensive
Profile Jord
Volunteer tester
Avatar

Send message
Joined: 9 Jun 99
Posts: 15184
Credit: 4,362,181
RAC: 3
Netherlands
Message 1625343 - Posted: 8 Jan 2015, 9:24:03 UTC - in response to Message 1625190.  

No, It's constantly getting tasks abandoned, that happens if an earlier scheduler contact gets through after a later one, ie out of sequence,
It's eithier got a very poor ISP, or some sort of backup software that restores Boinc,
But it restores a client_state.xml with an earlier <rpc_seqno>, The scheduler will mark all those tasks abandoned,
If you were able to see the result from those abandoned tasks, you'll probably find that host is still crunching them.

Still, a couple more weird ones:

3897406272 	1670136558 	8 Jan 2015, 6:12:21 UTC 	8 Jan 2015, 6:12:31 UTC 	Timed out - no response
3897406279 	1670136559 	8 Jan 2015, 6:12:21 UTC 	8 Jan 2015, 6:12:31 UTC 	Timed out - no response

A deadline of 10 seconds?

Created	8 Jan 2015, 6:12:19 UTC
Sent	8 Jan 2015, 6:12:21 UTC
Report deadline	8 Jan 2015, 6:12:31 UTC

Created	8 Jan 2015, 6:12:19 UTC
Sent	8 Jan 2015, 6:12:21 UTC
Report deadline	8 Jan 2015, 6:12:31 UTC

Although, last night I saw him have several of these timed out tasks with 4 minute 27 second deadlines.
ID: 1625343 · Report as offensive
Profile Julie
Volunteer moderator
Volunteer tester
Avatar

Send message
Joined: 28 Oct 09
Posts: 34041
Credit: 18,883,157
RAC: 18
Belgium
Message 1625362 - Posted: 8 Jan 2015, 10:53:58 UTC - in response to Message 1625205.  

Good to here Julie getting rid of your dust bunnys has helped . Annoying little critters clogging everything up hehehehe


I did what you told me Glenn and it's working like a charm again, thanx:)
rOZZ
Music
Pictures
ID: 1625362 · Report as offensive
Profile Keith Myers Special Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 29 Apr 01
Posts: 13161
Credit: 1,160,866,277
RAC: 1,873
United States
Message 1625511 - Posted: 8 Jan 2015, 19:53:33 UTC - in response to Message 1625343.  


Still, a couple more weird ones:


Yes, just noticed 3 invalids that finished through computation with normal exit status and a normal stderr output. Even has the same computed result as my wingmen. Why invalid? Weird indeed.

http://setiathome.berkeley.edu/workunit.php?wuid=1669825487
http://setiathome.berkeley.edu/workunit.php?wuid=1669825535
http://setiathome.berkeley.edu/workunit.php?wuid=1669825541


Keith
Seti@Home classic workunits:20,676 CPU time:74,226 hours

A proud member of the OFA (Old Farts Association)
ID: 1625511 · Report as offensive
Dena Wiltsie
Volunteer tester

Send message
Joined: 19 Apr 01
Posts: 1628
Credit: 24,230,968
RAC: 26
United States
Message 1625514 - Posted: 8 Jan 2015, 20:00:42 UTC

I see what is happening with the AP units. I am picking up SSE units while my GPU is getting close to running dry. I don't think it would happen if they had MB units to keep the queues full but lacking MB work has caused the few AP units that are being created to be converted into SSE units. We now have around 30,000 more AP units in the field but most are in somebodies CPU queues where they will take a long time to process. AARRRGGGGGGGGGG.
ID: 1625514 · Report as offensive
Previous · 1 . . . 4 · 5 · 6 · 7 · 8 · 9 · 10 . . . 22 · Next

Message boards : Number crunching : Panic Mode On (94) Server Problems?


 
©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.