Message boards :
Number crunching :
Rescheduling Hosts - Bad Practice
Message board moderation
Previous · 1 . . . 7 · 8 · 9 · 10 · 11 · Next
Author | Message |
---|---|
juan BFP Send message Joined: 16 Mar 07 Posts: 9786 Credit: 572,710,851 RAC: 3,799 |
But it´s not fair! Their (the reschedulers) keep their caches filled (until 17 March!) and ours are empty NOW!. |
Wiggo Send message Joined: 24 Jan 00 Posts: 34773 Credit: 261,360,520 RAC: 489 |
It seems nothing will stop the "hoarders", but I noticed that 1 of our original "trashes" (those who abort MB work when AP's are being split) has would up with mud on his face as he didn't get his fill this time (looks like the servers finally took action on him) and he still hasn't been able to get up to his maximum tasks quota yet. No cheers here for the Hoarders & Trashes, but cheers to the servers for the treatment given to 1 Trash producer. |
HAL9000 Send message Joined: 11 Sep 99 Posts: 6534 Credit: 196,805,888 RAC: 57 |
It seems nothing will stop the "hoarders", but I noticed that 1 of our original "trashes" (those who abort MB work when AP's are being split) has would up with mud on his face as he didn't get his fill this time (looks like the servers finally took action on him) and he still hasn't been able to get up to his maximum tasks quota yet. It would be a shame if there were something on the back end that did server side aborts of all those extra tasks. SETI@home classic workunits: 93,865 CPU time: 863,447 hours Join the [url=http://tinyurl.com/8y46zvu]BP6/VP6 User Group[ |
Wiggo Send message Joined: 24 Jan 00 Posts: 34773 Credit: 261,360,520 RAC: 489 |
It seems nothing will stop the "hoarders", but I noticed that 1 of our original "trashes" (those who abort MB work when AP's are being split) has would up with mud on his face as he didn't get his fill this time (looks like the servers finally took action on him) and he still hasn't been able to get up to his maximum tasks quota yet. It most certainly wouldn't bother me in anyway, in fact quite a few of us would very extremely happy to see this to happen just so we could hear the squeals of those greedy few who think that they're above the rules. :-D Cheers. |
rob smith Send message Joined: 7 Mar 03 Posts: 22206 Credit: 416,307,556 RAC: 380 |
Server side aborts for the "AP hoarders" would be great idea - along with limiting them to 10 WU per day for a year. Bob Smith Member of Seti PIPPS (Pluto is a Planet Protest Society) Somewhere in the (un)known Universe? |
Wiggo Send message Joined: 24 Jan 00 Posts: 34773 Credit: 261,360,520 RAC: 489 |
Server side aborts for the "AP hoarders" would be great idea - along with limiting them to 10 WU per day for a year. I'd vote for this without even thinking about it. :-D Cheers. |
Raistmer Send message Joined: 16 Jun 01 Posts: 6325 Credit: 106,370,077 RAC: 121 |
Pity, that in pursue own "fair" AP tasks you guys go so far from project's interests. All task abortion will be waste of server resources. Any additional limitations will reduce project's computational powers. If you so bothered with anothers cache maybe would be better to find some another project to whine ? SETI apps news We're not gonna fight them. We're gonna transcend them. |
Raistmer Send message Joined: 16 Jun 01 Posts: 6325 Credit: 106,370,077 RAC: 121 |
After such wrong-directed proposals would be good IMHO to remind positive ways to reduce tension: would be nice if servers will be reconfigured for LESS number of AP splitters (this was used some time ago, looks like additional number reduce required). This will lead to more even AP task distribution giving less chances for fast GPUs sit idle and leaves less need for current 100 tasks per ALL GPUs limit breakage. SETI apps news We're not gonna fight them. We're gonna transcend them. |
Wiggo Send message Joined: 24 Jan 00 Posts: 34773 Credit: 261,360,520 RAC: 489 |
Pity, that in pursue own "fair" AP tasks you guys go so far from project's interests. I thought much better of you Raistmer, but obviously you are a cheater as well it seems and we can do without you to if you can't follow the set rules that the majority of us have to play by. :-( 4517643 AP's In progress (229) at time of posting. The limit is 100 for CPU, 100 for GPU's = 200 No cheers here for you either now so go away, no excuses accepted. |
juan BFP Send message Joined: 16 Mar 07 Posts: 9786 Credit: 572,710,851 RAC: 3,799 |
... you guys go so far from project's interests. Sorry but i can´t agree with that, think: There is a roule on the project: 100 WU GPU + 100WU AP MAX per host. Those who "cheat" that roule are the ones against the project´s interests, not us. If they where right, then why the project admins set the roule? If build that huge caches is OK then Why not release the limits to all? Why most of them "hide" under the anonymous wall? Now imagine all doing the same... all "breaking the roule" by the use of the rescheduling script or program?... Another "crash" on the DB due it´s size could be expected? The computation power of the entire project will not change if all respect the roules, since keep days of WU on the caches have nothing to do with computational power, maybe only with the DB size or storage capacity but i´m sure you knows that lot better than most of us. |
Raistmer Send message Joined: 16 Jun 01 Posts: 6325 Credit: 106,370,077 RAC: 121 |
I think about you and your interest much better too, if you wanna go to personalities. But your last proposals so harmful that my attitude changed. Yes, I put more AP tasks to keep my GPU busy, and do this proudly no matter you and others like you saying. Cause I'm here to fullfill project's goal as fast as possible, not to whine about "fairness" in completely inappropriate for this area. I explained why such actions help project some post before, if you can't comprehend, sorry not my fault. SETI apps news We're not gonna fight them. We're gonna transcend them. |
Raistmer Send message Joined: 16 Jun 01 Posts: 6325 Credit: 106,370,077 RAC: 121 |
... you guys go so far from project's interests. Well, I can write full answer on this topic (as I understand this limitation) little later. For now, to reduce damage from rogue hosts. It's the short and quite correct answer. SETI apps news We're not gonna fight them. We're gonna transcend them. |
Raistmer Send message Joined: 16 Jun 01 Posts: 6325 Credit: 106,370,077 RAC: 121 |
but i´m sure you knows that lot better than most of us. Yes, I have no additional inside knowledge, but I'm thinking on already known. Knowledge should be applied to be useful. More - later (perhaps). SETI apps news We're not gonna fight them. We're gonna transcend them. |
draco Send message Joined: 6 Dec 05 Posts: 119 Credit: 3,327,457 RAC: 0 |
Ð’Ñ‹ ещё подеритеÑÑŒ,горÑчие финÑкие парни....(ц) Генерал из "Ðациональных оÑобенноÑтей" :D |
Raistmer Send message Joined: 16 Jun 01 Posts: 6325 Credit: 106,370,077 RAC: 121 |
No cheers here for you either now so go away, no excuses accepted. If I would same as you with your attitude I would say "not use my apps then, cause I go away", but because I'm not I will just continue to do my everyday work for betternig project no matter what personsl like you think about me and my efforts :P Good luck. SETI apps news We're not gonna fight them. We're gonna transcend them. |
Raistmer Send message Joined: 16 Jun 01 Posts: 6325 Credit: 106,370,077 RAC: 121 |
Ð’Ñ‹ ещё подеритеÑÑŒ,горÑчие финÑкие парни....(ц) Генерал из "Ðациональных оÑобенноÑтей" :D :)))))))))))))) 5 баллов :)))))))) Ладно, пойду оÑтывать :))))))) SETI apps news We're not gonna fight them. We're gonna transcend them. |
draco Send message Joined: 6 Dec 05 Posts: 119 Credit: 3,327,457 RAC: 0 |
ладно, небери близко к Ñердцу :) кÑтати, Ñ‚Ñ‹ навернÑка копал Ñей Ð²Ð¾Ð¿Ñ€Ð¾Ñ Ð³Ð»ÑƒÐ±Ð¶Ðµ Ð¼ÐµÐ½Ñ - каким раком SETI ищут Ñигнал - Ñ Ñ‚Ð°Ðº понÑл - они ищут повторÑющийÑÑ ÑпецÑигнал? не пытаютÑÑ Ð¿ÐµÑ€ÐµÑ…Ð²Ð°Ñ‚Ð¸Ñ‚ÑŒ взаимную коммуникацию или широковещательные Ñигналы ( тиви, радио?), как Ñ Ð´ÑƒÐ¼Ð°Ð» раньше? также Ð²Ñ€ÐµÐ¼Ñ Ð¿Ñ€Ð¸Ñ‘Ð¼Ð° Ñ Ð¾Ð´Ð½Ð¾Ð¹ координаты ÑоÑтавлÑет порÑдка вÑего 107 Ñекунд и в крайне узком Ñекторе? еÑли Ñто так - то по мне проÑкт Ñкорее дайÑтвует чтобы приноÑить какие то деньги его зачинателÑм, так как чтото обнаружить таким образом - крайне маловероÑтно, даже еÑли наши окреÑтноÑти кишат цивилизациÑми +/- ÑƒÑ€Ð¾Ð½Ð°Ñ Ð½Ð°ÑˆÐµÐ¹....? |
juan BFP Send message Joined: 16 Mar 07 Posts: 9786 Credit: 572,710,851 RAC: 3,799 |
BTW I was talking about the ones who build very large caches in the range of 700 AP WU or more as posted, not the ones with 20 or 30 and don´t even show their names to the rest of the community, they are the real "cheaters!. |
Link Send message Joined: 18 Sep 03 Posts: 834 Credit: 1,807,369 RAC: 0 |
... you guys go so far from project's interests. The official statement was about the database size, nothing else. For rogue hosts we have the quota system (OK, that needs few improvements). The problem with the current limit is, that we don't have 200 WUs as a hard limit per host, also it would be nice, if the servers would be able to correct any "wrong" assignments of WUs, i.e. resend them on each scheduler request to the device where they belong. This should stop most cheaters. |
Wiggo Send message Joined: 24 Jan 00 Posts: 34773 Credit: 261,360,520 RAC: 489 |
No cheers here for you either now so go away, no excuses accepted. Rules and limits are rules and limits, cheats are just that, cheats, no matter who you think that you are. There are people out there that complain that they can't get any AP's and 6-12 of them would carry them through a 10 day cache. It doesn't matter whether you are a "Volunteer developer" or an ordinary "Joe", but as a "Volunteer developer" you should show a better attitude and respect for those set limits and set an example to others because of it. If you don't like that then take your apps and go somewhere else to play if you think that you are above others as I'm sure that someone else will soon fill your socks. As to my attitude, it's simple, do the right thing by others and don't break those rules. |
©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.