..and had to be emailed to Dr. A for manual upload.

When David is asking for such a file to be sent to him, he won't manually upload the contents of said file into the database or anything. He'll be using it to test with what happens to it - checking the backend, see what it does - when he tries to send such a file.

At the end of the day, the user that has the problem will still need to report all those tasks himself; or at least, his BOINC needs to do so.

---

Yes, limits of 40/320 are in place, but im wondering more about this:

SETI@home 19.09.2010 08:38:50 Scheduler request completed: got 58 new tasks

Thought, there was also a limit of about 20 per request? Seems, this doesn't apply any more.

Yes, the project's config.xml used to have max_wus_to_send set to 20, and that used to be applied directly. But changeset [trac]changeset:18255[/trac] revised it so the number is now scaled by number of CPUs and GPUs (*gpu_multiplier). The 20 is probably still there, but is being treated as 20 per CPU and 160 per GPU.

There are only 100 feeder slots so that's the absolute maximum which could be sent for one request, and for new work there are pairs of tasks for each WU. Getting more than 50 means some are unpaired reissues (_2 and up).

                                                                Joe

Probably time to up the server side limits.
Network traffic has finally eased off (apart from the AP bursts), but the inbound traffic has been steadily climbing- most likely from hosts that have reached the Server Side limit & still trying for work.

---

Grant
Darwin NT

Probably time to up the server side limits.
Network traffic has finally eased off (apart from the AP bursts), but the inbound traffic has been steadily climbing- most likely from hosts that have reached the Server Side limit & still trying for work.

I said that hours ago before I passed out, my friend.

---

"Time is simply the mechanism that keeps everything from happening all at once."

I remember the first time I noticed I could get more than 20 tasks in one request. It was nice when I needed to get 150-225 tasks to fill the cache back when I was doing MB work. Used to take a ton of requests, but then it would only take 4-6 requests instead of 10+.

Presently, my record for most APs in one request is 23. Just about all of the requests are 1-3 though, but every now and then, I can get 5-15 at a time.

---

Linux laptop:
record uptime: 1511d 20h 19m (ended due to the power brick giving-up)

Looks like the limits have been raised up, as I have picked up 250ish WU's within the last few hours. I had been banging off of the limit all weekend.

---

New message from the server !!

20/09/2010 12:21:27 SETI@home Message from server: Resent lost task 24ap10ae.5264.1058.11.10.50_2

Looks like some thing has finally been done about the ghost problem - Yeehaa

T.A.

YES indeed !!!!!!!

20-Sep-10 05:12:27	SETI@home	Scheduler request completed: got 20 new tasks
20-Sep-10 05:12:27	SETI@home	[sched_op_debug] Server version 611
20-Sep-10 05:12:27	SETI@home	Message from server: Resent lost task D%my10adep23.24198.12.10.222_2
20-Sep-10 05:12:27	SETI@home	Message from server: Resent lost task 31dc09af.17708.8411.12.10.90_3
20-Sep-10 05:12:27	SETI@home	Message from server: Resent lost task 31dc09af.17708.8411.12.10.102_2

Edit: But something is very wrong... I was tracking 26 ghosts after scheduler request timeout when I saw that message, but instead of those 26 I just got 20 tasks that are not on my rig's list at all ?! So, will I crunch someone else's wu's in the near future?

Edit 2: Things are going from bad to worse. I just got a bunch of fresh .vlars on my GPU ;-< Task 1712880409

---

Who the hell is General Failure and why is he reading my harddisk?¿

YES indeed !!!!!!!

20-Sep-10 05:12:27	SETI@home	Scheduler request completed: got 20 new tasks
20-Sep-10 05:12:27	SETI@home	[sched_op_debug] Server version 611
20-Sep-10 05:12:27	SETI@home	Message from server: Resent lost task D%my10adep23.24198.12.10.222_2
20-Sep-10 05:12:27	SETI@home	Message from server: Resent lost task 31dc09af.17708.8411.12.10.90_3
20-Sep-10 05:12:27	SETI@home	Message from server: Resent lost task 31dc09af.17708.8411.12.10.102_2

Edit: But something is very wrong... I was tracking 26 ghosts after scheduler request timeout when I saw that message, but instead of those 26 I just got 20 tasks that are not on my rig's list at all ?! So, will I crunch someone else's wu's in the near future?

Edit 2: Things are going from bad to worse. I just got a bunch of fresh .vlars on my GPU ;-< Task 1712880409

Ohh.. well.. - a new feature enabled and (unintentional) in the same time an other old feature disabled.. :-(

---

Looks like the limits have been raised up, as I have picked up 250ish WU's within the last few hours. I had been banging off of the limit all weekend.

Yes, fine. But as always for me - as a Power Cruncher - very late. I'm not
sure that i can download >4,000 workunits in the next 24 Hours. :-|

Helli

---

A loooong time ago: First Credits after SETI@home Restart

Looks like the limits have been raised up, as I have picked up 250ish WU's within the last few hours. I had been banging off of the limit all weekend.

Yes, fine. But as always for me - as a Power Cruncher - very late. I'm not
sure that i can download >4,000 workunits in the next 24 Hours. :-|

Helli

I have that problem too. It is very difficult to download a lot of work at what turns out to be the last minute. You really have to stay with your rig and baby sit it. I hope the new server will allow things to run with higher limits earlier on.

Steve

---

Warning, addicted to SETI crunching!
Crunching as a member of GPU Users Group.
GPUUG Website

You said it right, Steve. I sit here (maybe the next 4 hours) and push the Retry-Button because
i can't wait 11:32:45 Hours for the next automatic connect. ;-)

Helli

---

A loooong time ago: First Credits after SETI@home Restart

My machines will DL to tomorrow to the outage.. and with bad luck during the outage they will have a lot of backlogged DLs..

I have only DSL light (384/64 kbit/s).. :-(

For example, my GPU machine need at least 5 hours after every 3 day outage to UL all results of 3 days.. and during this time no work request..

After the 940 BE made the UL, then I enable the network for the E7600 machine..

Everyone have his own specially problems.. ;-)

---

...Everyone have his own specially problems.. ;-)

Yupp.

And i don't think that Oscar makes any Difference on this Situation.
IMHO the 100MBit Line in Combination with this 3-Day-in-7-Days Outage
is the Bottleneck. Maybe a 5-Day-in-14-Days Outage would be a better Choice for us.

Helli

---

A loooong time ago: First Credits after SETI@home Restart

...Everyone have his own specially problems.. ;-)

Yupp.

And i don't think that Oscar makes any Difference on this Situation.
IMHO the 100MBit Line in Combination with this 3-Day-in-7-Days Outage
is the Bottleneck. Maybe a 5-Day-in-14-Days Outage would be a better Choice for us.

Helli

I was thinking that after they shuffle the servers around, and add Oscar, the need for an extended down time might be some what aleviated. I am thinking that 96 Gig of RAM can process a whole lot of science. I am most likely wrong, but if the outage is so NTPC can work while not being bombarded with new files, then the ability to handle the files and do science may reduce the need for down time. Actually, I don't really know.

Steve

---

Warning, addicted to SETI crunching!
Crunching as a member of GPU Users Group.
GPUUG Website

2 parts is broken:

1st) .VLAR are being sent to GPU

2nd) Prefs of "Use CPU" = No, are getting cpu tasks.

---

I was thinking that after they shuffle the servers around, and add Oscar, the need for an extended down time might be some what aleviated.
....

If this would be possible, our (Special-)Donations would be a good Investment - for us also.


[Edit:]

Woah..

Not bad man, not bad.

I had luck and found a hole in the wall and downloaded >1,800 Workunits in the past 40 Minutes. Yiippieh..


Helli

---

A loooong time ago: First Credits after SETI@home Restart

...Everyone have his own specially problems.. ;-)

Yupp.

And i don't think that Oscar makes any Difference on this Situation.
IMHO the 100MBit Line in Combination with this 3-Day-in-7-Days Outage
is the Bottleneck. Maybe a 5-Day-in-14-Days Outage would be a better Choice for us.

Helli

I was thinking that after they shuffle the servers around, and add Oscar, the need for an extended down time might be some what aleviated. I am thinking that 96 Gig of RAM can process a whole lot of science. I am most likely wrong, but if the outage is so NTPC can work while not being bombarded with new files, then the ability to handle the files and do science may reduce the need for down time. Actually, I don't really know.

Steve

Oscar should be quite a beast after the generous response I got in my donation thread.....
It should be interesting to see if those in charge of actually setting the specs agree with the upgrades I proposed....especially the CPU upgrade to add more cores and speed and allow the RAM to run at it's rated speed. That should all add up to a nice increase in processing power.

More bandwidth would be nice at some point, but the weakest link has been the processing power of the server base. With mighty Oscar taking over some of the chores, the tasks running on the other servers might be spread around a bit, and Matt intends to retire some of the less reliable ones. Of course, if their load is lessened, that might not have to happen. He would be the judge of that.

If the servers can hold up their end, we can saturate the bandwidth like we have since coming back up last Thursday. And if the downtime is 3 days or less in the future, I think we can get by nicely with what is on tap right now.

---

"Time is simply the mechanism that keeps everything from happening all at once."

Ive been jumping all over the threads, so I cant find wich one said that they have the new line run up the hill. I take it that it hasnt been connected yet?
If not any idea when it will be?

Oscar and a new line, should be a WOW moment right there.

---

[/quote]

Old James

Ive been jumping all over the threads, so I cant find wich one said that they have the new line run up the hill. I take it that it hasnt been connected yet?
If not any idea when it will be?

Oscar and a new line, should be a WOW moment right there.

I could be wrong, but if I recall correctly, the discussion was that the new fiber link was NOT going to increase Seti's bandwidth.

---

"Time is simply the mechanism that keeps everything from happening all at once."