Yes, hope it is just Eric getting all his ducks in a row before starting the server initialization sequence.

BINGO!!! Just as I typed. All GREEN!

---

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

A proud member of the OFA (Old Farts Association)

Might be all green but I'm getting nout

Well at least there is something there to talk to. Internal server error for me but that means I just have to fight through all the others trying to connect. Only have one machine that is almost out of work. Just need to report the 3000 or so tasks.

---

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

A proud member of the OFA (Old Farts Association)

Saddle up, lock and load!

---

All crunched WU reported, still no new WU DL.

---

WOW you really have to be quick to get any work that was ready to go before the maint. window. I manually updated my faster machines first, then went to my slower machines and those machines I went to last can't get any work. Not sure if the download servers are over loaded or if the work that was ready has already been sucked up. At any rate, as Keith said, all green!

---

~Chris

The SSP only updates every ten minutes. Between the time the SSP said we had +300K tasks in the RTS buffer and the time the servers went all green, those tasks got sucked up immediately. Now just have to fight everyone else asking for work as the splitters ramp up to handle demand. It will be at least 6-8 hours before the RTS buffer starts filling again other than immediately dumping at every request.

---

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

A proud member of the OFA (Old Farts Association)

It will be at least 6-8 hours before the RTS buffer starts filling again other than immediately dumping at every request.

Maybe.
The WU-awaiting-deletion backlog continues to grow, and that impacts splitter output.
If it clears soon, then things should recover fairly quickly. If not, who knows how long it will take (as long as we don't run out of disk space).

---

Grant
Darwin NT

Almost 379,000 results received in the last hour, I guess that would dry up the well a bit when those machines then ask for work

---

~Chris

It will be at least 6-8 hours before the RTS buffer starts filling again other than immediately dumping at every request.

Maybe.
The WU-awaiting-deletion backlog continues to grow, and that impacts splitter output.
If it clears soon, then things should recover fairly quickly. If not, who knows how long it will take (as long as we don't run out of disk space).

I agree, that backlog of results purging is continuing to be worrisome. Hasn't reduced since last week's outage. I believe as you do that I/O contention impacts the splitters.

[Edit] And just as I posted, the creation rate cratered at Haveland. Think that means they are doing the wu and results purge.

---

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

A proud member of the OFA (Old Farts Association)

[Edit] And just as I posted, the creation rate cratered at Haveland.

Often does that after an outage (very bursty- lots, none, lots, none..), generally takes them a while to really get going.
I'm more concerned with the lack of work from the Scheduler at the moment. 300k+ WUs Ready-to-send, but i'm getting nothing but "Project has no tasks available" after 46 on the initial request.
Even after the last extended outage most requests resulted in at least some work.

---

Grant
Darwin NT

Yes, it nosedive, but it is picking back up again. I just put the one cruncher that was out of work onto a GPUGrid Long task and right after that it picked up 14 Seti tasks. So, work is trickling out as usual after the outage. That machine has the new hardware and was just changed over to two tasks per card, so it was the one that worked through my bunker the fastest. Still in good shape on the others.

Will have to get back to my compilation project to increase the allowed tasks.

---

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

A proud member of the OFA (Old Farts Association)

20 tasks stuck downloading. The last time I saw this, I had to edit my host file.

---

~Chris

Yes, I have mucho stalled downloads too. Haven't set logging options yet, but don't think the issue is DNS. Think it is just a lot of machines asking for work.

---

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

A proud member of the OFA (Old Farts Association)

Seems to be the thing at the moment.

---

20 tasks stuck downloading. The last time I saw this, I had to edit my host file.

Tried both servers- it's not DNS. Problems getting work from either server.
And i can't see it being load related as we've had similar (and heavier) loads in the past with no stalled downloads- just slower than usual downloads.

Problems with the servers again.

---

Grant
Darwin NT

No it's not a DNS problem as I just gave my host files a flick about and all variations failed.

Cheers.

It's going to be an extra-long outage until they can get the download servers straightened out.

---

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

A proud member of the OFA (Old Farts Association)

It's going to be an extra-long outage until they can get the download servers straightened out.

Yep.
Downloads are dead in the water.

---

Grant
Darwin NT

This makes for a long day now :(