server status has lots of red and orange . . . but luckily I´m a slow and still got some in the cache . . .

---

"less than a pixel"

Work is flowing out again.

For the moment anyway.

Cheers.

The Ready-to-send buffer is now down to 550k, so it would be nice if the splitters would now start to produce some more work before it makes it's way to zero again.

Edit-
and bingo. Post about the problem, and it gets sorted. Ready-to-send now down to 470k, but at least the splitters have fired up again.

---

Grant
Darwin NT

Looking god here, at this point.

---

... and bingo. Post about the problem, and it gets sorted. Ready-to-send now down to 470k, but at least the splitters have fired up again.

I think it takes the splitters some time to get out of bed, after they receive the 'wake up' call. I have some sympathy with their point of view.

Might be time to consider panic. It's 6:30 am local time, USA east coast. My top machine is at 75% of in progress jobs and just got "no tasks available" from the servers. The server status page shows about 400,000 available.

---

Results out in the field	0	54,630	6,877,527	2m
Results received in last hour **	0	1,160	150,141	1h
Result turnaround time (last hour average) **	0.00 hours	38.91 hours	35.51 hours	1h
Results returned and awaiting validation	0	41,513	8,732,314	2m
Workunits waiting for validation	0	0	86,180	2m
Workunits waiting for assimilation	0	6	1,461,188	2m
Workunit files waiting for deletion	0	16,546	908,196	2m
Result files waiting for deletion	0	0	290	2m
Workunits waiting for db purging	0	6,832	2,586,456	2m
Results waiting for db purging	71	49,274	7,288,759	2m

With such high numbers sure the servers are having a "hard time".

Maybe that proves we where right when we keep the spoofed builds closed to a small group exactly to avoid this.

Even a small increase of the WU cache multiplied with the huge amount of working hosts could leave the servers to it's limits.

Now just imagine what instead of having a 300 WU limit you have 6400 without control... sure a server crash.

Hope they could find a way to resolve this.

my 0.02

<edit>BTW I tried to do my part by avoid my lone host to contact the servers for the rest of the day or until i see the issue solved.
Maybe some others with big crunchers and large caches could do the same to release some workload from the servers at this time.

---

Got up this morning (Thursday) and I have no GPU tasks running. Pure CPU tasks and a couple hundred "waiting to report" in Queue.

I think we should put off Panicking until about 10am PST Friday.

It would be interesting to see an analysis of the system logs that shows exactly what is "bottle necking" now because all we really have are "black box" reports.

Just bumped the update manually and a bunch of gpu tasks started downloading. <Shrug> I dunno....

Tom

---

A proud member of the OFA (Old Farts Association).

Got up this morning (Thursday) and I have no GPU tasks running. Pure CPU tasks and a couple hundred "waiting to report" in Queue.

I think we should put off Panicking until about 10am PST Friday.

It would be interesting to see an analysis of the system logs that shows exactly what is "bottle necking" now because all we really have are "black box" reports.

Just bumped the update manually and a bunch of gpu tasks started downloading. <Shrug> I dunno....

Tom

That is exactly what happening when you have an unstable system, sometimes works, sometimes no. Something i agree they need time to see the analysis logs and find the bottle neck. Hope they could find and solve the issue soon.

---

All my caches are down and hosts being met with no tasks are available with the RTS at 720K.

Something is still plugging up the servers.

Database can't handle any host lookup. Driving blind now.

---

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

A proud member of the OFA (Old Farts Association)

Plenty in the RTS
Results ready to send 0 3,418 765,855 5m
It just isn't doing much sending :-(

I've set myself to NNT again until things are better.

Greetings,

A few minutes ago I checked BT and saw that I had a boat load of tasks to report. I left it as-is (I did not use my trigger finger). ;)

I came here and checked a few things out and left and went into BOINC to check my Event Log. I saw that downloads were happening. I just got a boat load of replacement WUs to chew on. :) I don't know that it was just a fluke that I got downloads or not. But it does seem that WUs are going out to those in need of them.

I believe they should further reduce the limit or even go back to the 100 per device limit. I never saw this much of a problem before, unless there was a server crash like the scheduler a while back. All seemed to run regularly smooth when there were no problems server side and we had the 100 limit.

Have a great day! :)

Siran

---

CAPT Siran d'Vel'nahr - L L & P _\\//
Winders 11 OS? "What a piece of junk!" - L. Skywalker
"Logic is the cement of our civilization with which we ascend from chaos using reason as our guide." - T'Plana-hath

Seems we are slowly coming back to life.

---

Seti@Home classic workunits: 29,492 CPU time: 134,419 hours

Yes, but with stuck downloads as a result...

This is like playing whack-a-mole.

---

is it really down again?!?

12/19/2019 2:03:54 PM | SETI@home | Sending scheduler request: To fetch work.
12/19/2019 2:03:54 PM | SETI@home | Requesting new tasks for CPU
12/19/2019 2:03:55 PM | SETI@home | Scheduler request completed: got 0 new tasks
12/19/2019 2:03:55 PM | SETI@home | Project is temporarily shut down for maintenance

---

is it really down again?!?

12/19/2019 2:03:54 PM | SETI@home | Sending scheduler request: To fetch work.
12/19/2019 2:03:54 PM | SETI@home | Requesting new tasks for CPU
12/19/2019 2:03:55 PM | SETI@home | Scheduler request completed: got 0 new tasks
12/19/2019 2:03:55 PM | SETI@home | Project is temporarily shut down for maintenance

. . That's what the servers are telling us ...

Stephen

??

Yup - the scheduler (and a lot of the workunit related daemons) are showing 'disabled' now, although - as you can see - the message boards are still up. Must be trying to sort something out in the data flow.

It is down for now. Lots of disabled servers. Aw well.....s--happens

---

Ok Back to Suspend Network Activity until fixed. Again...

---