Message boards : Server and website : Why are Downloads So Slow
Author | Message |
---|---|
It seems that for a 2.5MB taking 20 minutes do download is a little odd. | |
ID: 44368 | Rating: 0 | rate: / Reply Quote | |
This has happened a few times over the past few days and is not a normal thing for the year or for the servers. If this has been happening to you all year it may be on your end. Tasks take about 3 minutes at most to normally download for me and about 8-10 minutes to upload at most. Only the past few days since the ADRIA OPEN and CLOSED tasks were on high failure rate did the servers start to stutter for up and downloads. In the case where they do that stutter, they need to time out and restart. None have been slow and stuttering the way you describe moving 2% at a time or not needing a timeout to restart. | |
ID: 44371 | Rating: 0 | rate: / Reply Quote | |
It seems that for a 2.5MB taking 20 minutes do download is a little odd. It downloads at 138KBps for 2% Stops and waits then another 2%. This pausing while downloading has also been happening here for a long long time. I have to start BOINC from the command line to manage this phenomenon: boinc.exe" --pers_retry_delay_max 60 Also in the cc_config I have to have the line: <http_transfer_timeout>60</http_transfer_timeout> Only then will downloads complete in around 10 minutes. This "stuttering" happens with no other projects and never happens with any other downloads of any kind. The ever increasing in size uploads are also slow but do not "stutter". The UL slowness is due to low bandwidth caused by the predatory monopoly ISP that's the only choice in this area (centurylink). Predatory monopolies run by the tax avoiding billionaire bunch that control them, the corrupt politicians that they own and the sheeple via the media. Gotta love it. Where's a new Teddy Roosevelt when you need him? Oh yeah, Bernie got blindsided (by the above)... The whole DL/UL slowness is kind of frustrating as for instance I've had many WUs in the last day complete in under 24 hours yet by the time the DL/UL time is added in they miss the 1 day bonus deadline. | |
ID: 44374 | Rating: 0 | rate: / Reply Quote | |
Oups, | |
ID: 44577 | Rating: 0 | rate: / Reply Quote | |
It seems that for a 2.5MB taking 20 minutes do download is a little odd. It downloads at 138KBps for 2% Stops and waits then another 2%. I understand this but what I do not understand is when at download stops a new task starts and even delay the first one even longer and now a 3rd starting to download as yet the first is still not completed. It is a great Project to run as to Folding@Home but is starting to be a real frustrating Project to run. Either we no projects or we get projects that download but you only give us half the download and are at a stand still. ____________ Crunching@EVGA The Number One Team in the BOINC Community. Folding@EVGA The Number One Team in the Folding@Home Community. | |
ID: 44978 | Rating: 0 | rate: / Reply Quote | |
It seems that for a 2.5MB taking 20 minutes do download is a little odd. It downloads at 138KBps for 2% Stops and waits then another 2%. Invalid command --pers_retry_delay_max 60 ____________ Crunching@EVGA The Number One Team in the BOINC Community. Folding@EVGA The Number One Team in the Folding@Home Community. | |
ID: 44995 | Rating: 0 | rate: / Reply Quote | |
boinc.exe --pers_retry_delay_max 60 | |
ID: 44997 | Rating: 0 | rate: / Reply Quote | |
Invalid command --pers_retry_delay_max 60 As stated it's command line BOINC. For Windows (depending on your BOINC location): "C:\Program Files\BOINC\boinc.exe" --pers_retry_delay_max 60 | |
ID: 45001 | Rating: 0 | rate: / Reply Quote | |
Invalid command --pers_retry_delay_max 60 What is this command doing? --pers_retry_delay_max 60 No Biggie and I might be dropping this project because I spend more time downloading then running tasks. It is causing WCG CPU issues with starting and stopping over and over because I cannot keep the this project running. boinc.exe --pers_retry_delay_max 60 D:\Program Files\BOINC>boinc.exe --pers_retry_delay_max 60 29-Oct-2016 08:08:49 Another instance of BOINC is running. GLE: Cannot create a file when that file already exists. (0xb7) Have to exit and start over. the command does not work a shortcut. So this means I would be running without a client tool. No Client Interface no point for me, But thanks anyway I cannot take it out of " Suspending computation - user request " the client never comes up and the command never ends D:\Program Files\BOINC>boinc.exe --pers_retry_delay_max 60 29-Oct-2016 08:12:02 [---] Starting BOINC client version 7.6.22 for windows_x86_64 29-Oct-2016 08:12:02 [---] log flags: file_xfer, sched_ops, task 29-Oct-2016 08:12:02 [---] Libraries: libcurl/7.45.0 OpenSSL/1.0.2d zlib/1.2.8 29-Oct-2016 08:12:02 [---] Data directory: D:\ProgramData\BOINC 29-Oct-2016 08:12:02 [---] Running under account User 29-Oct-2016 08:12:03 [---] CUDA: NVIDIA GPU 0: GeForce GTX 1080 (driver version 373.06, CUDA version 8.0, compute capabi lity 6.1, 4096MB, 3044MB available, 8876 GFLOPS peak) 29-Oct-2016 08:12:03 [---] CUDA: NVIDIA GPU 1: GeForce GTX 1080 (driver version 373.06, CUDA version 8.0, compute capabi lity 6.1, 4096MB, 3044MB available, 8876 GFLOPS peak) 29-Oct-2016 08:12:03 [---] OpenCL: NVIDIA GPU 0: GeForce GTX 1080 (driver version 373.06, device version OpenCL 1.2 CUDA , 8192MB, 3044MB available, 8876 GFLOPS peak) 29-Oct-2016 08:12:03 [---] OpenCL: NVIDIA GPU 1: GeForce GTX 1080 (driver version 373.06, device version OpenCL 1.2 CUDA , 8192MB, 3044MB available, 8876 GFLOPS peak) 29-Oct-2016 08:12:03 [---] Host name: BoincFolder 29-Oct-2016 08:12:03 [---] Processor: 56 GenuineIntel Intel(R) Xeon(R) CPU E5-2680 v4 @ 2.40GHz [Family 6 Model 79 Stepp ing 1] 29-Oct-2016 08:12:03 [---] Processor features: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 c lflush dts acpi mmx fxsr sse sse2 ss htt tm pni ssse3 fma cx16 sse4_1 sse4_2 movebe popcnt aes f16c rdrandsyscall nx lm avx avx2 vmx smx tm2 dca pbe fsgsbase bmi1 hle smep bmi2 29-Oct-2016 08:12:03 [---] OS: Microsoft Windows Server 2012 R2: Standard x64 Edition, (06.03.9600.00) 29-Oct-2016 08:12:03 [---] Memory: 95.78 GB physical, 111.41 GB virtual 29-Oct-2016 08:12:03 [---] Disk: 217.08 GB total, 192.21 GB free 29-Oct-2016 08:12:03 [---] Local time is UTC -6 hours 29-Oct-2016 08:12:03 [---] VirtualBox version: 5.0.26 29-Oct-2016 08:12:03 [ATLAS@home] Found app_config.xml 29-Oct-2016 08:12:03 [Collatz Conjecture] Found app_config.xml 29-Oct-2016 08:12:03 [Einstein@Home] Found app_config.xml 29-Oct-2016 08:12:03 [GPUGRID] Found app_config.xml 29-Oct-2016 08:12:03 [Milkyway@Home] Found app_config.xml 29-Oct-2016 08:12:03 [Moo! Wrapper] Found app_config.xml 29-Oct-2016 08:12:03 [Poem@Home] Found app_config.xml 29-Oct-2016 08:12:03 [PrimeGrid] Found app_config.xml 29-Oct-2016 08:12:03 [SETI@home] Found app_config.xml 29-Oct-2016 08:12:03 [---] Config: report completed tasks immediately 29-Oct-2016 08:12:03 [ATLAS@home] URL http://atlasathome.cern.ch/; Computer ID 58530; resource share 100 29-Oct-2016 08:12:03 [Citizen Science Grid] URL http://csgrid.org/csg/; Computer ID 41771; resource share 100 29-Oct-2016 08:12:03 [Collatz Conjecture] URL https://boinc.thesonntags.com/collatz/; Computer ID 804980; resource share 100 29-Oct-2016 08:12:03 [Cosmology@Home] URL http://www.cosmologyathome.org/; Computer ID 292623; resource share 100 29-Oct-2016 08:12:03 [Einstein@Home] URL http://einstein.phys.uwm.edu/; Computer ID 12437501; resource share 100 29-Oct-2016 08:12:03 [Enigma@Home] URL http://www.enigmaathome.net/; Computer ID 196959; resource share 100 29-Oct-2016 08:12:03 [GoofyxGrid@Home] URL http://goofyxgridathome.net/; Computer ID 62406; resource share 100 29-Oct-2016 08:12:03 [GPUGRID] URL http://www.gpugrid.net/; Computer ID 379625; resource share 100 29-Oct-2016 08:12:03 [Leiden Classical] URL http://boinc.gorlaeus.net/; Computer ID 143583; resource share 100 29-Oct-2016 08:12:03 [LHC@home 1.0] URL https://lhcathome.cern.ch/lhcathome/; Computer ID 10403113; resource share 100 29-Oct-2016 08:12:03 [Milkyway@Home] URL http://milkyway.cs.rpi.edu/milkyway/; Computer ID 705518; resource share 100 29-Oct-2016 08:12:03 [Moo! Wrapper] URL http://moowrap.net/; Computer ID 651416; resource share 100 29-Oct-2016 08:12:03 [NumberFields@home] URL http://numberfields.asu.edu/NumberFields/; Computer ID 33087; resource shar e 100 29-Oct-2016 08:12:03 [Poem@Home] URL http://boinc.fzk.de/poem/; Computer ID 1793658; resource share 100 29-Oct-2016 08:12:03 [pogs] URL http://pogs.theskynet.org/pogs/; Computer ID 743647; resource share 100 29-Oct-2016 08:12:03 [PrimeGrid] URL http://www.primegrid.com/; Computer ID 524550; resource share 100 29-Oct-2016 08:12:03 [rosetta@home] URL http://boinc.bakerlab.org/rosetta/; Computer ID 3112116; resource share 100 29-Oct-2016 08:12:03 [SETI@home] URL http://setiathome.berkeley.edu/; Computer ID 8105972; resource share 100 29-Oct-2016 08:12:03 [SRBase] URL http://srbase.my-firewall.org/sr5/; Computer ID 6978; resource share 100 29-Oct-2016 08:12:03 [vdwnumbers.org: Van Der Waerden Numbers] URL http://www.vdwnumbers.org/; Computer ID 4366; resourc e share 100 29-Oct-2016 08:12:03 [VGTU project@Home] URL http://boinc.vgtu.lt/vtuathome/; Computer ID 12442; resource share 100 29-Oct-2016 08:12:03 [VirtualLHC@home] URL http://lhcathome2.cern.ch/vLHCathome/; Computer ID 98681; resource share 100 29-Oct-2016 08:12:03 [World Community Grid] URL http://www.worldcommunitygrid.org/; Computer ID 3660300; resource share 100 29-Oct-2016 08:12:03 [WUProp@Home] URL http://wuprop.boinc-af.org/; Computer ID 122164; resource share 100 29-Oct-2016 08:12:03 [World Community Grid] General prefs: from World Community Grid (last modified 26-Oct-2016 08:38:16 ) 29-Oct-2016 08:12:03 [World Community Grid] Computer location: work 29-Oct-2016 08:12:03 [---] General prefs: using separate prefs for work 29-Oct-2016 08:12:03 [---] Reading preferences override file 29-Oct-2016 08:12:03 [---] Preferences: 29-Oct-2016 08:12:03 [---] max memory usage when active: 88274.08MB 29-Oct-2016 08:12:03 [---] max memory usage when idle: 93178.19MB 29-Oct-2016 08:12:03 [---] max disk usage: 187.60GB 29-Oct-2016 08:12:04 [---] max CPUs used: 46 29-Oct-2016 08:12:04 [---] (to change preferences, visit a project web site or select Preferences in the Manager) 29-Oct-2016 08:12:04 Initialization completed 29-Oct-2016 08:12:04 [---] Suspending computation - user request 29-Oct-2016 08:13:09 [GoofyxGrid@Home] Sending scheduler request: Requested by project. 29-Oct-2016 08:13:09 [GoofyxGrid@Home] Not requesting tasks 29-Oct-2016 08:13:11 [GoofyxGrid@Home] Scheduler request completed ____________ Crunching@EVGA The Number One Team in the BOINC Community. Folding@EVGA The Number One Team in the Folding@Home Community. | |
ID: 45002 | Rating: 0 | rate: / Reply Quote | |
Retrying now it sits on This computer has reached a limit on tasks in progress | |
ID: 45004 | Rating: 0 | rate: / Reply Quote | |
Thanks for tying to help me out but it seem to still have download issues and I cannot manage any other BOINC projects in this mode nor can I make changes and so on without a Client Interface. If I had a system that ONLY ran this Project then maybe it would be worth looking more in to the Command Line way of Running BOINC but that for me is not an easy task to learn. | |
ID: 45005 | Rating: 0 | rate: / Reply Quote | |
Perhaps this download issue will be less frustrating when the Pascal app will be assigned to the long queue also, as the long tasks take 4-8-12 hours to finish. This is probably long enough to complete the download of the next task, even if it gets halted a couple of times. | |
ID: 45011 | Rating: 0 | rate: / Reply Quote | |
Perhaps this download issue will be less frustrating when the Pascal app will be assigned to the long queue also, as the long tasks take 4-8-12 hours to finish. This is probably long enough to complete the download of the next task, even if it gets halted a couple of times. The tasks were even shorter when they errored out immediately ;-) I've seen fewer stalled downloads since we got the Pascal app running. | |
ID: 45015 | Rating: 0 | rate: / Reply Quote | |
Perhaps this download issue will be less frustrating when the Pascal app will be assigned to the long queue also, as the long tasks take 4-8-12 hours to finish. This is probably long enough to complete the download of the next task, even if it gets halted a couple of times. Well I think it would be even longer as it will not download a new task until the old task is completed and uploaded from what I have been watching the few days. Because the File Size are Larger than the Short Runs I see it being even worse. The bad part is when it stop other projects from running and playing the Waiting to run game. I do prefer the long tasks over the short one, I only ran the Short for this Beta Testing on the Pascal Cards. ____________ Crunching@EVGA The Number One Team in the BOINC Community. Folding@EVGA The Number One Team in the Folding@Home Community. | |
ID: 45017 | Rating: 0 | rate: / Reply Quote | |
As stated it's command line BOINC. For Windows (depending on your BOINC location): It's telling the client to only back off a maximum of 60 seconds on the stalled DL, otherwise sometimes it will not retry for hours. Going less than 60 seconds gave me erratic results. As far as the GUI, you can make a shortcut to start the commandline client, THEN start the GUI. Better yet use BoincTasks and you'll really be able to see and control your clients. | |
ID: 45020 | Rating: 0 | rate: / Reply Quote | |
As stated it's command line BOINC. For Windows (depending on your BOINC location): Cool, It gave my MacAfee erratic results as well. ____________ Crunching@EVGA The Number One Team in the BOINC Community. Folding@EVGA The Number One Team in the Folding@Home Community. | |
ID: 45022 | Rating: 0 | rate: / Reply Quote | |
The tasks were even shorter when they errored out immediately ;-) Yes, but those hosts got their daily quota reduced, and it (hopefully) made the BOINC manager to try less often. I've seen fewer stalled downloads since we got the Pascal app running. Me too, and the error rate on the server status page is also shows significantly more green (=lower, below 25%) numbers. | |
ID: 45023 | Rating: 0 | rate: / Reply Quote | |
As I said in the other thread we are trying to look into the downloading problem. Once I have some news I'll update you. Sorry for the inconvenience. | |
ID: 45061 | Rating: 0 | rate: / Reply Quote | |
As I said in the other thread we are trying to look into the downloading problem. Once I have some news I'll update you. Sorry for the inconvenience. Stefan thank you for looking into this. It has been 30 days now and still no change. ____________ Crunching@EVGA The Number One Team in the BOINC Community. Folding@EVGA The Number One Team in the Folding@Home Community. | |
ID: 45418 | Rating: 0 | rate: / Reply Quote | |
What is the situation with the downloads? Please keep reporting if you have problems and better if you can quantify them. | |
ID: 45427 | Rating: 0 | rate: / Reply Quote | |
The server status page is still loads halfway, then stops for a while, then completes. | |
ID: 45465 | Rating: 0 | rate: / Reply Quote | |
We tweaked some web and db parameters, let's see if anything improves. | |
ID: 45522 | Rating: 0 | rate: / Reply Quote | |
The server status page is still loads halfway, then stops for a while, then completes. Toni (re: Zoltan's post), the tweaks didn't help (sadly). Also, downloading WUs is the worst it's ever been. | |
ID: 45557 | Rating: 0 | rate: / Reply Quote | |
Yes, those download speeds are hard to explain. It has become a long thread in the news. I am inclined to think that they are suffering from the same problem as before, probably not related to the server itself, now aggravated by the increased traffic due to 1 day of stop. | |
ID: 45574 | Rating: 0 | rate: / Reply Quote | |
The server status page is still loads halfway, then stops for a while, then completes. any solution for this to be expected soon? | |
ID: 45578 | Rating: 0 | rate: / Reply Quote | |
I've read many posts on this issue but I'm sure I've missed a lot, so my apologies in advance if this is a dumb or repeat question. | |
ID: 45587 | Rating: 0 | rate: / Reply Quote | |
Is the slow download issue experienced from within the GPUGRID local area network? The problem is not seen within Spain, but appears to be with their connections to the outside world, as Richard Haselgrove reports see #45570). http://www.gpugrid.net/forum_thread.php?id=4442&nowrap=true#45570 | |
ID: 45589 | Rating: 0 | rate: / Reply Quote | |
Just like to inform, the problem with stalled downloads still exists for me after the server up-grade. | |
ID: 45597 | Rating: 0 | rate: / Reply Quote | |
Yes, those download speeds are hard to explain. It has become a long thread in the news. I am inclined to think that they are suffering from the same problem as before, probably not related to the server itself, now aggravated by the increased traffic due to 1 day of stop. Toni, did you upgrade the NAS storage as well, or just the server? ____________ FAQ's HOW TO: - Opt out of Beta Tests - Ask for Help | |
ID: 45606 | Rating: 0 | rate: / Reply Quote | |
Yes, those download speeds are hard to explain. It has become a long thread in the news. I am inclined to think that they are suffering from the same problem as before, probably not related to the server itself, now aggravated by the increased traffic due to 1 day of stop. Now there's hardly any work moving up or down and the DL stalling is worse than its ever been. | |
ID: 45609 | Rating: 0 | rate: / Reply Quote | |
I haven't had any problems uploading the results to the server but downloads are the worst I have ever seen. Almost everyone is stalling, like the packet has been lost and it sits there waiting to time out. Most of the time it takes 3 or more retries before completing it. While trying to disable and then re-enable the network communications it took over a dozen times before one file was downloaded. Then the next file the same thing. I understand not having work units to process but the downloading problem, well that is another story. | |
ID: 45623 | Rating: 0 | rate: / Reply Quote | |
I think there is value looking into the "inside Spain vs outside Spain" angle. Many of these traceroutes have an increase in ping time starting when the connection gets from some ISP or backbone to the Spanish ISP or backbone. Also the user who reports no issues at all is the one inside Spain. I would be interested in seeing if the internal network computers running alpha, beta, regular, or testing units are seeing any issues like we are seeing. I would also be interested in seeing if any of the students or members of staff (etc) have PCs at home in Spain that could test the "inside Spain" theory for us outside of the local network. And perhaps it is the ISP within Spain that is just not good at the handoff to other ISPs through the backbones or some filtering method being used on the Spanish ISP networks for packet capture and analyzation. I would think that would more prevalent in places like Turkey, China, and Pakistan where it is a known issue that the government is tracking all the traffic in and out of the country to censor it, but maybe Spain has something in place that does something for some reason having this effect on our connections to the project??? | |
ID: 45632 | Rating: 0 | rate: / Reply Quote | |
Everyone is saying it's the speed, but it's not my case in the US. I download fairly quickly....maybe 300KBps, then it totally stops after a few seconds. It's so bad that I can't even keep the work going. The downloads get exponentially longer retries then project backoff. | |
ID: 45647 | Rating: 0 | rate: / Reply Quote | |
I think there is value looking into the "inside Spain vs outside Spain" angle. Many of these traceroutes have an increase in ping time starting when the connection gets from some ISP or backbone to the Spanish ISP or backbone. Also the user who reports no issues at all is the one inside Spain. I would be interested in seeing if the internal network computers running alpha, beta, regular, or testing units are seeing any issues like we are seeing. I would also be interested in seeing if any of the students or members of staff (etc) have PCs at home in Spain that could test the "inside Spain" theory for us outside of the local network. And perhaps it is the ISP within Spain that is just not good at the handoff to other ISPs through the backbones or some filtering method being used on the Spanish ISP networks for packet capture and analyzation. I would think that would more prevalent in places like Turkey, China, and Pakistan where it is a known issue that the government is tracking all the traffic in and out of the country to censor it, but maybe Spain has something in place that does something for some reason having this effect on our connections to the project??? Why is it that I can connect to the Speedtest.net server in Barcelona, a few of them, and get 8.7Mbps that takes several seconds to measure, so it must be a larger file than most I would get from the project server. My ping is 222ms. The test seems to go well without interruption. Is this testing anything relevant? | |
ID: 45648 | Rating: 0 | rate: / Reply Quote | |
Everyone is saying it's the speed, but it's not my case in the US. I download fairly quickly....maybe 300KBps, then it totally stops after a few seconds. It's so bad that I can't even keep the work going. The downloads get exponentially longer retries then project backoff. Not sure who everyone is, but if they're saying that it's the speed they're wrong. It's not the speed. Personally I think the server is misconfigured. It's interesting that the stalling got much worse when the new server was installed. Hint, hint... The 3rd post in this thread has some tips that will help a little by reducing the timeout between retries and the transfer timeout: https://www.gpugrid.net/forum_thread.php?id=4373&nowrap=true#44374 Also, for those who have been saying it's due to high traffic volume. It's not. Even when there's hardly any work available (so barely any UL/DL going on) the stalling is just as bad when we do happen to receive a WU. And again: uploads are not affected, only downloads. | |
ID: 45654 | Rating: 0 | rate: / Reply Quote | |
Jeebus! I have a download that is as of this writing stuck for 4.5 hours - and still clocking!! That's a record for me. Usually the stuck downloads clear out in not more than 1.5-2 hours. | |
ID: 45762 | Rating: 0 | rate: / Reply Quote | |
I have a download that is as of this writing stuck for 4.5 hours - and still clocking!! That's a record for me. Usually the stuck downloads clear out in not more than 1.5-2 hours. In the line <http_transfer_timeout></http_transfer_timeout> inside the cc_config.xml file which is located (on a Win7/8/10 machine) in the C:\ProgramData\BOINC folder, change the value to 60. That will decrease the amount of time before it determines a timeout, then will try a new connection continuing from the same point in the file. That SHOULD help some of the time length you are seeing there.____________ 1 Corinthians 9:16 "For though I preach the gospel, I have nothing to glory of: for necessity is laid upon me; yea, woe is unto me, if I preach not the gospel!" Ephesians 6:18-20, please ;-) http://tbc-pa.org | |
ID: 45764 | Rating: 0 | rate: / Reply Quote | |
I already have that parameter and it is set to 45. Would 60 be an improvement? While the first hang was in progress, a second WU came in and downloaded "normally", around an hour or so. The slow WU finished downloading after about 5 hours. OBTW - I now have something I haven't seen in a while - two long runs running concurrently ;-) Yaaaa!! Thanks | |
ID: 45770 | Rating: 0 | rate: / Reply Quote | |
I already have that parameter and it is set to 45. Would 60 be an improvement? From what I have read here, yes, it would be. Apparently anything under 60 has results that are rather unpredictable to counter-productive. 60 seconds is apparently the lowest amount you can enter that will actually be consistently accurate at its set amount. a second WU came in and downloaded "normally", around an hour or so. I am not sure I am reading that correctly. Are you saying that to download a WU it normally takes you an hour just to download it? My downloads are usually less than 5 minutes for a WU and that is with a 60 second hang or two on a file or two. Sometimes it can be as long as 7-10 minutes to download if there are several 60 second hangs. Uploads can take at most 20 minutes, but are usually around 10-12 minutes. If a download of a single WU took an hour for me, I would think there was something severely wrong with something. When the download is actually moving, what speed registers? I get between 300 and 1000 KBps. I find that the faster it registers, the more likely it is to hang. I once did an experiment by self regulating the speed at which BOINC can download to 250 KBps and it didn't hang on any WU downloads at all for that whole week. For the larger files, it was better to have them not hang, but for the smaller files, it ended up taking longer overall for the whole WU. But for an hour to download, that is quite over the top excessive according to my results in good and in bad connection times. So I hope I am reading it incorrectly and you are just saying that after an hour of the other one hanging excessively, this new one downloaded fast. Let us know. You may have other issues yet to be dealt with or maybe you are just on a dial up modem and we are expecting broadband results from everyone in this day and age. ??? | |
ID: 45774 | Rating: 0 | rate: / Reply Quote | |
Sometimes they download as you described. Sometimes one file downloads continuously but very slowly - a few bytes at a time - for around an hour. Yesterday's 5 hour dl was a one-off. | |
ID: 45775 | Rating: 0 | rate: / Reply Quote | |
Has anyone tried increasing the network interface controller's number of receive buffers to the maximum? I am located in the USA, and I noticed that downloads from LHC@home in Switzerland to me sped up from kilobytes per second to near instant downloads when I bumped up the number of transmit and receive buffers from their default numbers to my NIC's maximum of 2048 buffers for both transmit and receive. Also, access to this website (which is in Spain) seemed vastly improved. Could it be that the default number of receive buffers your NIC is set to use be insufficient for efficient long distance communication over the Internet? It could be that our NICs are dropping packets due to not having enough buffers which forces timeouts and retransmissions, and increasing the number of buffers mitigates the problem. See http://www.intel.com/content/www/us/en/support/network-and-i-o/ethernet-products/000005593.html for some documentation on Intel NICs regarding this setting. | |
ID: 45782 | Rating: 0 | rate: / Reply Quote | |
Given the limited info I have to go on, this download issue is an internal network problem at their end but probably beyond the control of the research group. It's probably not the server (replaced). More likely to be a mapped IP to mac address on a L2 switch or router, bad pointer record or something obtuse like insufficient memory in a router, bandwidth caps or just old backbone kit. | |
ID: 45783 | Rating: 0 | rate: / Reply Quote | |
In my previous message, I should have written "Have any of the users tried increasing their network interface controllers' number of receive buffers to the maximum number allowed by their drivers?" instead of "Has anyone tried increasing the network interface controller's number of receive buffers to the maximum?". | |
ID: 45787 | Rating: 0 | rate: / Reply Quote | |
In my previous message, I should have written "Have any of the users tried increasing their network interface controllers' number of receive buffers to the maximum number allowed by their drivers?" instead of "Has anyone tried increasing the network interface controller's number of receive buffers to the maximum?". I changed the Transmit buffers and the Receive Buffers on the laptop to see if it makes a difference. Worth a try. | |
ID: 45791 | Rating: 0 | rate: / Reply Quote | |
I just got a Gerrard Long on my laptop and watched it download completely in less than 30 seconds! It is running now. Hmmmmmmm....... | |
ID: 45793 | Rating: 0 | rate: / Reply Quote | |
Don't worry, it's not just you. This issue is driving us all nuts. We have a publication which depends on us providing a stable webserver and it's not even possible to get that... I have no clue what's going on but it's beyong my control. | |
ID: 45809 | Rating: 0 | rate: / Reply Quote | |
Solution ? | |
ID: 45828 | Rating: 0 | rate: / Reply Quote | |
I also had errors with the stated command line. Boinc 7.6.33 x64 | |
ID: 45847 | Rating: 0 | rate: / Reply Quote | |
Over the last few days, this has got REALLY bad for me. | |
ID: 45849 | Rating: 0 | rate: / Reply Quote | |
I also had errors with the stated command line. Boinc 7.6.33 x64 That's because you were trying to start boincmgr.exe instead of boinc.exe. In your case the Windows shortcut would contain: "C:\Program Files\BOINC\boinc.exe" --pers_retry_delay_max 60 | |
ID: 45870 | Rating: 0 | rate: / Reply Quote | |
There are too many threads about this problem that it is hard to decide where to post, but here are most replies. traceroute to 84.89.134.145 (84.89.134.145), 30 hops max, 60 byte packets 1 192.168.0.1 (192.168.0.1) 2.416 ms 3.636 ms 4.878 ms 2 st-static-bckb-189.213-81-234.telecom.sk (213.81.234.189) 7.483 ms 10.608 ms 11.073 ms 3 st-static-bckb-165.213-81-237.telecom.sk (213.81.237.165) 17.225 ms 17.328 ms 17.434 ms 4 st-static-srk97.87-197-196.telecom.sk (87.197.196.97) 23.263 ms 28.461 ms 30.906 ms 5 80.156.160.98 (80.156.160.98) 30.904 ms 31.256 ms 31.588 ms 6 ae-1-3101.bar1.Madrid2.Level3.net (4.69.210.222) 72.930 ms 56.966 ms 53.664 ms 7 * ae-1-3101.bar1.Madrid2.Level3.net (4.69.210.222) 57.905 ms 61.126 ms 8 213.242.113.78 (213.242.113.78) 58.332 ms 57.116 ms 59.481 ms 9 TELMAD.AE4.uv.rt1.val.red.rediris.es (130.206.245.89) 61.419 ms 63.012 ms 63.987 ms 10 anella-val1-router.red.rediris.es (130.206.211.70) 70.758 ms 71.479 ms 74.027 ms 11 * * * 12 grosso.upf.edu (84.89.134.145) 67.483 ms 65.117 ms 67.104 ms 13 grosso.upf.edu (84.89.134.145) 68.139 ms 69.536 ms 68.875 ms 14 grosso.upf.edu (84.89.134.145) 69.612 ms !X 67.994 ms !X 71.975 ms !X And traceoute to another host on your net: traceroute to 84.89.134.149 (84.89.134.149), 30 hops max, 60 byte packets 1 192.168.0.1 (192.168.0.1) 2.383 ms 2.414 ms 2.758 ms 2 st-static-bckb-189.213-81-234.telecom.sk (213.81.234.189) 7.282 ms 8.930 ms 9.332 ms 3 st-static-bckb-165.213-81-237.telecom.sk (213.81.237.165) 12.443 ms 12.806 ms 13.816 ms 4 st-static-srk22.87-197-198.telecom.sk (87.197.198.22) 21.475 ms 21.942 ms 22.798 ms 5 80.156.160.98 (80.156.160.98) 20.297 ms 20.648 ms 22.916 ms 6 ae-1-3101.bar1.Madrid2.Level3.net (4.69.210.222) 68.372 ms 57.487 ms 53.777 ms 7 ae-1-3101.bar1.Madrid2.Level3.net (4.69.210.222) 56.167 ms 57.161 ms 57.497 ms 8 213.242.113.78 (213.242.113.78) 54.067 ms 55.685 ms 58.480 ms 9 TELMAD.AE4.uv.rt1.val.red.rediris.es (130.206.245.89) 62.530 ms 62.889 ms 63.361 ms 10 anella-val1-router.red.rediris.es (130.206.211.70) 70.073 ms 76.882 ms 77.247 ms 11 * * * 12 capablanca.upf.edu (84.89.134.149) 59.068 ms 59.149 ms 59.735 ms 13 capablanca.upf.edu (84.89.134.149) 62.916 ms 59.670 ms 60.177 ms 14 capablanca.upf.edu (84.89.134.149) 62.880 ms !X 64.946 ms !X 65.670 ms !X ____________ | |
ID: 45889 | Rating: 0 | rate: / Reply Quote | |
Can we pay for a DVD with 100 Tasks ready to load on a few computers? | |
ID: 45896 | Rating: 0 | rate: / Reply Quote | |
Dear Masters of Desaster, | |
ID: 45905 | Rating: 0 | rate: / Reply Quote | |
Same problem here, coming from Australia. It's not about speed, it's about connection being dropped. It downloads fast for about 1 or 2 seconds, and then stops. | |
ID: 45910 | Rating: 0 | rate: / Reply Quote | |
This has nothing to do with the users - this is purely a server or ISP configuration problem on GPUGRID's side. Some things on the user end have helped. Like on the Intel cards, changing the Receive Buffers and Transmit Buffers to max helps get more before it does that timeout. (I cannot figure out how to do this to my Wireless Broadcom 802.11ac Network Adapter, so my main system is still having the issue harder than my laptop now.) That are other things that help like changing the BOINC timeout setting to 60 seconds helps. But yes, the main issue is some misconfiguration at the lab, at the school, or at the ISP, or maybe even at the backbone going into Spain. There is a user inside Spain that says there is no problems for his downloads, but not much follow-up has been done asking that user to test different things for confirmation. | |
ID: 45925 | Rating: 0 | rate: / Reply Quote | |
Right now, not only am I getting slow WUs downloads on both computers, but the project web pages are loading slowly, and I have 2 ghost WU: | |
ID: 45926 | Rating: 0 | rate: / Reply Quote | |
Router Security problems ? | |
ID: 45930 | Rating: 0 | rate: / Reply Quote | |
Maybe this dump of traffic will help your network staff in determining the problem segment of network. | |
ID: 45931 | Rating: 0 | rate: / Reply Quote | |
Hello.The server downloads remain very slow using Boinc on windows, Get a few seconds of fast download then download stops and need to retry download. | |
ID: 45933 | Rating: 0 | rate: / Reply Quote | |
I think we have this problem solved now. | |
ID: 45975 | Rating: 0 | rate: / Reply Quote | |
I just downloaded one without a hitch. I think you did it. | |
ID: 45976 | Rating: 0 | rate: / Reply Quote | |
I think we have this problem solved now. Care to elaborate on how? :-) ____________ 1 Corinthians 9:16 "For though I preach the gospel, I have nothing to glory of: for necessity is laid upon me; yea, woe is unto me, if I preach not the gospel!" Ephesians 6:18-20, please ;-) http://tbc-pa.org | |
ID: 46031 | Rating: 0 | rate: / Reply Quote | |
This has nothing to do with the users - this is purely a server or ISP configuration problem on GPUGRID's side. Caffeine, can you please explain how do you increase the buffer sizes? What buffers? Are they related to hardware accelerated TCP/IP? I read about TCP and learned about receive window size tunable that affects performance, so it may be it. Note: I am just curious and know the issue was resolved server-size. | |
ID: 46036 | Rating: 0 | rate: / Reply Quote | |
Yes, it was discussed here and a link to the page that gives full instructions is given there. | |
ID: 46055 | Rating: 0 | rate: / Reply Quote | |
I had very slow at end of year but now I had a screaming 350k download and no pausing. What ever they did it worked! | |
ID: 46245 | Rating: 0 | rate: / Reply Quote | |
Message boards : Server and website : Why are Downloads So Slow