World Community Grid - View Thread - cpu time/real time! What should I expect?

World Community Grid Forums

Category: Support

Forum: BOINC Agent Support

Thread: cpu time/real time! What should I expect?

Quick Go »

No member browsing this thread

Thread Status: Active
Total posts in this thread: 51

[ ]

Author

This topic has been viewed 5346 times and has 50 replies

Falconet
Master Cruncher
Portugal
Joined: Mar 9, 2009
Post Count: 3315
Status: Offline
Project Badges:

14 day badge for Human Proteome Folding - Phase 2

14 day badge for Nutritious Rice for the World

180 day badge for Help Fight Childhood Cancer

90 day badge for Help Cure Muscular Dystrophy - Phase 2

90 day badge for Computing for Clean Water

90 day badge for Drug Search for Leishmaniasis

90 day badge for GO Fight Against Malaria

20 year badge for Mapping Cancer Markers

2 year badge for Uncovering Genome Mysteries

2 year badge for Outsmart Ebola Together

1 year badge for FightAIDS@Home - Phase 2

5 year badge for Microbiome Immunity Project

14 day badge for Africa Rainfall Project

5 year badge for OpenPandemics - COVID-19


Re: cpu time/real time! What should I expect?

There would be no time the computer was using more than 50% of the cpu since I do not use it for anything. One of the other 4 core computers that does not have a ssd and I do use it a lot has 409 results compared to the 291 results it has. I did change that field but that would not explain why the one 6 core computer does more than twice the other one. Would a ssd be that much faster? The one 6 core computer does have 6 Gbytes of ram memory vs the other with one with 3 Gbytes. I would think that 3 Gbytes of memory would be enough to run 6 work units so I would hope there would not be any memory swapping with the hard drive. Just look at the stats for total results and they have more than doubled for some days and are at least 50% more for almost all the the other days before October of last year. That must mean that there is a lot more downloading and uploading now. Since the gpu units are being returned at a much faster pace I would think that wcg would give them priority. I am just looking for an explanation of these results and a lack of bandwidth or server power seems to me to be a valid explanation and if that is true than leaving a computer on 24 hours is a waste of electricity.

AFAIK the only project that benefits from an SSD is CEP2. 3GB of memory should be enough for 6 units(unless you run CEP2). If you really think that the problem is that WCG isn't sending you enough work because of GPU's then increase your buffer. I have a cache of a mere 0.5 days and WCG always keeps 4 tasks aside from the ones that are running.

----------------------------------------

- AMD Ryzen 5 1600AF 6C/12T 3.2 GHz - 85W
- AMD Ryzen 5 2500U 4C/8T 2.0 GHz - 28W
- AMD Ryzen 7 7730U 8C/16T 3.0 GHz

----------------------------------------
[Edit 2 times, last edit by Falconet at Mar 6, 2013 8:53:08 PM]

[Mar 6, 2013 8:44:23 PM]

Falconet
Master Cruncher
Portugal
Joined: Mar 9, 2009
Post Count: 3315
Status: Offline
Project Badges:


Re: cpu time/real time! What should I expect?

Have you checked your device profile?

What do these settings look like?
On multiprocessors, at most use: processors
On multiprocessors, use: % of processors

----------------------------------------

- AMD Ryzen 5 1600AF 6C/12T 3.2 GHz - 85W
- AMD Ryzen 5 2500U 4C/8T 2.0 GHz - 28W
- AMD Ryzen 7 7730U 8C/16T 3.0 GHz

[Mar 6, 2013 8:54:56 PM]

Former Member
Cruncher
Joined: May 22, 2018
Post Count: 0
Status: Offline


Re: cpu time/real time! What should I expect?

Dribbles and drabs of information is useless,

1. you have a 4 core cpu, but are only running 3 wu
2. no information as to what happens when you request more work, is the server not sending? and why, or are you not requesting
3. based on cpu/elasped times 50% setting is not a problem
4. number of wu completed is NOT an indicator of a problem due to varying wu lengths, ie some take 10 min some take 10 hours
5. lack of wu is not the problem, if it is why only you having that problem

I have spent a week trying to work with you on this, please take 15 min of your time and provide all the info I requested in my first post, tyvm

[Mar 6, 2013 10:40:18 PM]

RicktheBrick
Senior Cruncher
Joined: Sep 23, 2005
Post Count: 206
Status: Offline
Project Badges:

180 day badge for Human Proteome Folding

20 year badge for Human Proteome Folding - Phase 2

1 year badge for Discovering Dengue Drugs - Together

2 year badge for Nutritious Rice for the World

10 year badge for Help Fight Childhood Cancer

90 day badge for Influenza Antiviral Drug Search

2 year badge for The Clean Energy Project - Phase 2

180 day badge for Drug Search for Leishmaniasis

45 day badge for GO Fight Against Malaria

100 year badge for Mapping Cancer Markers

5 year badge for Outsmart Ebola Together

5 year badge for FightAIDS@Home - Phase 2

10 year badge for Microbiome Immunity Project

2 year badge for Africa Rainfall Project

10 year badge for OpenPandemics - COVID-19


Re: cpu time/real time! What should I expect?

Once again here is results for last 14 days.
03/06/2013 0:002:08:34:59 7,636 10
03/05/2013 0:002:08:42:18 7,530 10
03/04/2013 0:001:12:08:38 4,797 7
03/03/2013 0:002:03:42:54 6,444 10
03/02/2013 0:001:04:26:04 3,319 4
03/01/2013 0:001:01:37:54 3,319 5
02/28/2013 0:003:14:50:48 11,501 14
02/27/2013 0:000:19:30:38 2,742 4
02/26/2013 0:003:09:43:16 11,015 14
02/25/2013 0:001:16:37:27 5,863 9
02/24/2013 0:002:22:57:51 9,615 13
02/23/2013 0:001:15:32:21 5,668 9
02/22/2013 0:002:12:35:45 8,939 15
02/21/2013 0:002:17:37:01 9,666 14
Do you see on the 27th I got less than a day of cpu time? There are 5 days with less than 2 days of cpu time and 6 days with less than 3 days. I do use all 4 cores with 100% for each core. I have corrected the problems with suspending work and I have increased the cache so I will wait for a week to see if anything changes. Note that the last two days I got 20 results but only 4 days 16 hours of cpu time. I think I should be getting at least 7 days of cpu time.

[Mar 7, 2013 3:12:02 AM]

Former Member
Cruncher
Joined: May 22, 2018
Post Count: 0
Status: Offline


Re: cpu time/real time! What should I expect?

I will leave this for others, my skills to understand your settings via blind guessing are not up to the task.

[Mar 7, 2013 3:32:46 AM]

RicktheBrick
Senior Cruncher
Joined: Sep 23, 2005
Post Count: 206
Status: Offline
Project Badges:


Re: cpu time/real time! What should I expect?

Here is more prove. The same computer for Jan and Feb of this year compared to Jan and Feb of last year. This year 602, Last year 1062. There is something reducing the number of results and it is not the computer. That is a difference of 460 divided by the 59 days or 7.8 results a day. That is a reduction of 43%

[Mar 7, 2013 1:10:15 PM]

Former Member
Cruncher
Joined: May 22, 2018
Post Count: 0
Status: Offline


Re: cpu time/real time! What should I expect?

Result count is absolutely no proof at all, just circumstantial. Most anyone can tell you the reason... project selection and variation in run-times. E.g. Were you running HCC last year and this year on same machine, the run times doubled.

[Mar 7, 2013 1:16:17 PM]

Coleslaw
Veteran Cruncher
USA
Joined: Mar 29, 2007
Post Count: 1343
Status: Offline
Project Badges:

5 year badge for Human Proteome Folding - Phase 2

90 day badge for Discovering Dengue Drugs - Together

180 day badge for The Clean Energy Project

5 year badge for Help Fight Childhood Cancer

1 year badge for Influenza Antiviral Drug Search

5 year badge for Help Cure Muscular Dystrophy - Phase 2

2 year badge for Discovering Dengue Drugs - Together - Phase 2

10 year badge for The Clean Energy Project - Phase 2

5 year badge for Computing for Clean Water

5 year badge for Drug Search for Leishmaniasis

5 year badge for GO Fight Against Malaria

2 year badge for Computing for Sustainable Water

10 year badge for Uncovering Genome Mysteries

20 year badge for Outsmart Ebola Together

10 year badge for FightAIDS@Home - Phase 2

20 year badge for Smash Childhood Cancer

20 year badge for Microbiome Immunity Project

20 year badge for Africa Rainfall Project

20 year badge for OpenPandemics - COVID-19


Re: cpu time/real time! What should I expect?

RicktheBrick...the problems you are running into are self inflicted. When asking for assistance, it is courteous and expected for you to provide the information NECESSARY for troubleshooting the problem that is ONLY happening to YOU. So, you only gave us a partial Event log of what was requested of you. YES there is valuable information in those logs. Don't disregard the request. Second, it is even more helpful when posting on a forum to give all possible information up front. Some common info include not only a description of the problem but the hardware setup, OS, and other software setup (in this case BOINC's settings). You have mentioned a number of results returned which is fine, but that only means YOU are having problems somewhere and not WCG as a whole.

Now, to debunk your statement on how the 50% setting you had was unimportant, it may be more important then you think. Do you have anti-virus? I have seen these scans take large CPU amounts and pause BOINC. If BOINC pauses while running GPU HCC work, it will pause and then start over. This is very bad for GPU work. You also do not mention if "leave applications in memory" aka LAIM is checked. This too can cause you to lose a lot of CPU time. Don't for a moment think that Anti-virus is the only piece of software that from time to time causes a spike either.

Now, to rehash what others have asked.... Start from the beginning and give us the Event Log again only this time do a manual update (the update button on the Projects tab) for WCG only. Then copy the Event log from the very top (not just pieces of it) and copy everything all the way down to wear WCG update request has finished. (and any replies from the WCG servers) Then also took at your preferences (located under Tools) and tell us what you have selected and chosen for each of the categories under the Processor usage tab, Network usage tab Minimum and Max addition work buffer choices, and finally the dsik and memory usage tab Memory usage settings. We also need to know what subprojects you have selected here at WCG. Are you just doing HCC work? Next, we need to know if you are participating at other projects outside WCG. They will compete for CPU/GPU time. Last, we may even ask you to check some additional preference at the WCG website, but I will hold off until you comply with the above requested information.

Edit: Also, pay very close attention to what Sekerob said about run times changing since last year. If you read the many posts in the HCC forum you will find that they doubled up the work in each work unit. Thus, doubling the amount of time to finish and therefore would cut the number of results completed and returned for any given time frame roughly in half. The more important thing to look at is actual run time reported rather then number of results.

----------------------------------------

----------------------------------------
[Edit 1 times, last edit by Coleslaw at Mar 7, 2013 4:32:42 PM]

[Mar 7, 2013 3:33:27 PM]

Hypernova
Master Cruncher
Audaces Fortuna Juvat ! Vaud - Switzerland
Joined: Dec 16, 2008
Post Count: 1908
Status: Offline
Project Badges:

20 year badge for Help Fight Childhood Cancer

14 day badge for Influenza Antiviral Drug Search

20 year badge for Help Cure Muscular Dystrophy - Phase 2

90 day badge for Discovering Dengue Drugs - Together - Phase 2

5 year badge for The Clean Energy Project - Phase 2

20 year badge for Computing for Clean Water

10 year badge for Drug Search for Leishmaniasis

10 year badge for GO Fight Against Malaria

5 year badge for Computing for Sustainable Water


Re: cpu time/real time! What should I expect?

I am looking to find an expert in crystal ball readings. He may solve the issue in a blink wink

----------------------------------------

[Mar 8, 2013 4:31:08 PM]

RicktheBrick
Senior Cruncher
Joined: Sep 23, 2005
Post Count: 206
Status: Offline
Project Badges:


Re: cpu time/real time! What should I expect?

Last October I was advancing in the ranks as I have been doing for the last 5 years. I was just a couple of hundred results from going into page 9 of results returned. Today I am over 15,000 results from doing that and I have fallen into page 11 and it looks like I will soon go back to page 12. I just looked at the task page and found that I had 8 resultls waiting to be reported. I did a manual update and here is the results
Sat 09 Mar 2013 03:14:58 PM EST | World Community Grid | update requested by user
Sat 09 Mar 2013 03:14:58 PM EST | World Community Grid | Sending scheduler request: Requested by user.
Sat 09 Mar 2013 03:14:58 PM EST | World Community Grid | Reporting 8 completed tasks, requesting new tasks for CPU
Sat 09 Mar 2013 03:15:01 PM EST | World Community Grid | Scheduler request completed: got 7 new tasks
Sat 09 Mar 2013 03:15:03 PM EST | World Community Grid | Started download of X0900121330541201006210909_X0900121330541201006210909.zip
Sat 09 Mar 2013 03:15:03 PM EST | World Community Grid | Started download of faah38432_ZINC14169489_xPR_wC6_11_1ref9_02_AD4.1_bound.dat.gzb
Sat 09 Mar 2013 03:15:05 PM EST | World Community Grid | Finished download of X0900121330541201006210909_X0900121330541201006210909.zip
Sat 09 Mar 2013 03:15:05 PM EST | World Community Grid | Finished download of faah38432_ZINC14169489_xPR_wC6_11_1ref9_02_AD4.1_bound.dat.gzb
Sat 09 Mar 2013 03:15:05 PM EST | World Community Grid | Started download of faah38432_ZINC14169489_xPR_wC6_11_1ref9_02_ZINC14169489.pdbqt.gzb
Sat 09 Mar 2013 03:15:05 PM EST | World Community Grid | Started download of 95578ff1a46653e4b02b2492b09cef17.gpf.gzb
Sat 09 Mar 2013 03:15:06 PM EST | World Community Grid | Finished download of faah38432_ZINC14169489_xPR_wC6_11_1ref9_02_ZINC14169489.pdbqt.gzb
Sat 09 Mar 2013 03:15:06 PM EST | World Community Grid | Finished download of 95578ff1a46653e4b02b2492b09cef17.gpf.gzb
Sat 09 Mar 2013 03:15:06 PM EST | World Community Grid | Started download of 229eb0e6be0286a59efaf3e395a4aacd.dpf.gzb
Sat 09 Mar 2013 03:15:06 PM EST | World Community Grid | Started download of qo130-139_qo138.fasta.gz
Sat 09 Mar 2013 03:15:17 PM EST | World Community Grid | Finished download of 229eb0e6be0286a59efaf3e395a4aacd.dpf.gzb
Sat 09 Mar 2013 03:15:17 PM EST | World Community Grid | Finished download of qo130-139_qo138.fasta.gz
Sat 09 Mar 2013 03:15:17 PM EST | World Community Grid | Started download of qo130-139_qo138.psipred.gz
Sat 09 Mar 2013 03:15:17 PM EST | World Community Grid | Started download of qo130-139_qo138.psipred_ss2.gz
Sat 09 Mar 2013 03:15:18 PM EST | World Community Grid | Finished download of qo130-139_qo138.psipred.gz
Sat 09 Mar 2013 03:15:18 PM EST | World Community Grid | Started download of qo130-139_aaqo13803_05.075_v1_3.gz
Sat 09 Mar 2013 03:15:19 PM EST | World Community Grid | Finished download of qo130-139_qo138.psipred_ss2.gz
Sat 09 Mar 2013 03:15:19 PM EST | World Community Grid | Finished download of qo130-139_aaqo13803_05.075_v1_3.gz
Sat 09 Mar 2013 03:15:19 PM EST | World Community Grid | Started download of qo130-139_aaqo13809_05.075_v1_3.gz
Sat 09 Mar 2013 03:15:19 PM EST | World Community Grid | Started download of faah38432_ZINC14184916_xPR_wC6_11_1ref9_02_ZINC14184916.pdbqt.gzb
Sat 09 Mar 2013 03:15:20 PM EST | World Community Grid | Finished download of faah38432_ZINC14184916_xPR_wC6_11_1ref9_02_ZINC14184916.pdbqt.gzb
Sat 09 Mar 2013 03:15:20 PM EST | World Community Grid | Started download of 380de45dd66a9c3f4161750c575b4fac.gpf.gzb
Sat 09 Mar 2013 03:15:21 PM EST | World Community Grid | Finished download of qo130-139_aaqo13809_05.075_v1_3.gz
Sat 09 Mar 2013 03:15:21 PM EST | World Community Grid | Finished download of 380de45dd66a9c3f4161750c575b4fac.gpf.gzb
Sat 09 Mar 2013 03:15:21 PM EST | World Community Grid | Started download of faah38432_ZINC14184916_xPR_wC6_11_1ref9_02_AD4.1_bound.dat.gzb
Sat 09 Mar 2013 03:15:21 PM EST | World Community Grid | Started download of 71b232255db79420d8d41d75c82dc227.dpf.gzb
Sat 09 Mar 2013 03:15:22 PM EST | World Community Grid | Finished download of faah38432_ZINC14184916_xPR_wC6_11_1ref9_02_AD4.1_bound.dat.gzb
Sat 09 Mar 2013 03:15:22 PM EST | World Community Grid | Finished download of 71b232255db79420d8d41d75c82dc227.dpf.gzb
Sat 09 Mar 2013 03:15:22 PM EST | World Community Grid | Started download of faah.base.00019.dat.gzb
Sat 09 Mar 2013 03:15:22 PM EST | World Community Grid | Started download of faah.base1.00019.pdbqt.gzb
Sat 09 Mar 2013 03:15:23 PM EST | World Community Grid | Finished download of faah.base.00019.dat.gzb
Sat 09 Mar 2013 03:15:23 PM EST | World Community Grid | Finished download of faah.base1.00019.pdbqt.gzb
Sat 09 Mar 2013 03:15:23 PM EST | World Community Grid | Started download of faah.base2.00019.pdbqt.gzb
Sat 09 Mar 2013 03:15:23 PM EST | World Community Grid | Started download of faah.wcgrid.00019.gpf.gzb
Sat 09 Mar 2013 03:15:24 PM EST | World Community Grid | Finished download of faah.base2.00019.pdbqt.gzb
Sat 09 Mar 2013 03:15:24 PM EST | World Community Grid | Finished download of faah.wcgrid.00019.gpf.gzb
Sat 09 Mar 2013 03:15:24 PM EST | World Community Grid | Started download of faah.wcgrid.00019.dpf.gzb
Sat 09 Mar 2013 03:15:24 PM EST | World Community Grid | Started download of faah38432_ZINC14202420_xPR_wC6_11_1ref9_02_AD4.1_bound.dat.gzb
Sat 09 Mar 2013 03:15:25 PM EST | World Community Grid | Finished download of faah.wcgrid.00019.dpf.gzb
Sat 09 Mar 2013 03:15:25 PM EST | World Community Grid | Finished download of faah38432_ZINC14202420_xPR_wC6_11_1ref9_02_AD4.1_bound.dat.gzb
Sat 09 Mar 2013 03:15:25 PM EST | World Community Grid | Started download of faah38432_ZINC14202420_xPR_wC6_11_1ref9_02_ZINC14202420.pdbqt.gzb
Sat 09 Mar 2013 03:15:25 PM EST | World Community Grid | Started download of 251a4ed334273a01b237e49084acb178.dpf.gzb
Sat 09 Mar 2013 03:15:27 PM EST | World Community Grid | Finished download of faah38432_ZINC14202420_xPR_wC6_11_1ref9_02_ZINC14202420.pdbqt.gzb
Sat 09 Mar 2013 03:15:27 PM EST | World Community Grid | Finished download of 251a4ed334273a01b237e49084acb178.dpf.gzb
Sat 09 Mar 2013 03:15:27 PM EST | World Community Grid | Started download of 520c9cd08f9cf0149cb51f50d5259800.gpf.gzb
Sat 09 Mar 2013 03:15:27 PM EST | World Community Grid | Started download of faah.base.00036.dat.gzb
Sat 09 Mar 2013 03:15:28 PM EST | World Community Grid | Finished download of 520c9cd08f9cf0149cb51f50d5259800.gpf.gzb
Sat 09 Mar 2013 03:15:28 PM EST | World Community Grid | Finished download of faah.base.00036.dat.gzb
Sat 09 Mar 2013 03:15:28 PM EST | World Community Grid | Started download of faah.base1.00036.pdbqt.gzb
Sat 09 Mar 2013 03:15:28 PM EST | World Community Grid | Started download of faah.base2.00036.pdbqt.gzb
Sat 09 Mar 2013 03:15:29 PM EST | World Community Grid | Finished download of faah.base1.00036.pdbqt.gzb
Sat 09 Mar 2013 03:15:29 PM EST | World Community Grid | Finished download of faah.base2.00036.pdbqt.gzb
Sat 09 Mar 2013 03:15:29 PM EST | World Community Grid | Started download of faah.wcgrid.00036.gpf.gzb
Sat 09 Mar 2013 03:15:29 PM EST | World Community Grid | Started download of faah.wcgrid.00036.dpf.gzb
Sat 09 Mar 2013 03:15:30 PM EST | World Community Grid | Finished download of faah.wcgrid.00036.gpf.gzb
Sat 09 Mar 2013 03:15:30 PM EST | World Community Grid | Finished download of faah.wcgrid.00036.dpf.gzb
Sat 09 Mar 2013 03:15:30 PM EST | World Community Grid | Started download of qo130-139_qo137.fasta.gz
Sat 09 Mar 2013 03:15:30 PM EST | World Community Grid | Started download of qo130-139_qo137.psipred.gz
Sat 09 Mar 2013 03:15:31 PM EST | World Community Grid | Finished download of qo130-139_qo137.fasta.gz
Sat 09 Mar 2013 03:15:31 PM EST | World Community Grid | Finished download of qo130-139_qo137.psipred.gz
Sat 09 Mar 2013 03:15:31 PM EST | World Community Grid | Started download of qo130-139_qo137.psipred_ss2.gz
Sat 09 Mar 2013 03:15:31 PM EST | World Community Grid | Started download of qo130-139_aaqo13703_05.075_v1_3.gz
Sat 09 Mar 2013 03:15:32 PM EST | World Community Grid | Finished download of qo130-139_qo137.psipred_ss2.gz
Sat 09 Mar 2013 03:15:32 PM EST | World Community Grid | Finished download of qo130-139_aaqo13703_05.075_v1_3.gz
Sat 09 Mar 2013 03:15:32 PM EST | World Community Grid | Started download of qo130-139_aaqo13709_05.075_v1_3.gz
Sat 09 Mar 2013 03:15:32 PM EST | World Community Grid | Started download of 9f6d7386c5a41bc4c1ff7407bcf20698.gpf.gzb
Sat 09 Mar 2013 03:15:33 PM EST | World Community Grid | Finished download of 9f6d7386c5a41bc4c1ff7407bcf20698.gpf.gzb
Sat 09 Mar 2013 03:15:33 PM EST | World Community Grid | Started download of faah38432_ZINC14771497_xPR_wC6_11_1ref9_00_AD4.1_bound.dat.gzb
Sat 09 Mar 2013 03:15:34 PM EST | World Community Grid | Finished download of qo130-139_aaqo13709_05.075_v1_3.gz
Sat 09 Mar 2013 03:15:34 PM EST | World Community Grid | Finished download of faah38432_ZINC14771497_xPR_wC6_11_1ref9_00_AD4.1_bound.dat.gzb
Sat 09 Mar 2013 03:15:34 PM EST | World Community Grid | Started download of faah38432_ZINC14771497_xPR_wC6_11_1ref9_00_ZINC14771497.pdbqt.gzb
Sat 09 Mar 2013 03:15:34 PM EST | World Community Grid | Started download of 715f76d5240bf28f1ef3f6947de46f83.dpf.gzb
Sat 09 Mar 2013 03:15:35 PM EST | World Community Grid | Finished download of faah38432_ZINC14771497_xPR_wC6_11_1ref9_00_ZINC14771497.pdbqt.gzb
Sat 09 Mar 2013 03:15:35 PM EST | World Community Grid | Finished download of 715f76d5240bf28f1ef3f6947de46f83.dpf.gzb

I am using all 4 cores without restrictions. I looked at network and found the speed were all zero which I assume means no restrictions. I do only WCG only.
Minimum buffer is .1 and maximum is 1 day. My projects are Help conquer cancer,Human Protome Folding,Fight aids@home, Help cure Muscular Dystrophy, and Help fight childhood cancer. I am running Ubuntu so I do not have any anti virus programs running.

[Mar 9, 2013 9:12:39 PM]

[ ]