The scheduler is really funny.
Seeing only 5.4 CPUs.

04.10.2011 23:05:30 SETI@home [sched_op] Starting scheduler request
04.10.2011 23:05:30 SETI@home Sending scheduler request: Requested by user.
04.10.2011 23:05:30 SETI@home Reporting 43 completed tasks, requesting new tasks for CPU and ATI GPU
04.10.2011 23:05:30 SETI@home [sched_op] CPU work request: 8902321.21 seconds; 5.40 CPUs
04.10.2011 23:05:30 SETI@home [sched_op] ATI GPU work request: 9069.50 seconds; 0.00 GPUs

That's 0.6 reserved for the ATI GPU (0.3 for each of 2 tasks it's hoping to get).

AFAICT the servers don't do anything with that count to ensure you get at least that many tasks for CPU, maybe sometime in the future. Having a non-zero instances does condition some logic to at least consider sending some work, though.

                                                                  Joe

Well, thanks to something stuffing up my computer for the second time in as many weeks, a bunch of tasks errored out.
Couple that with: 04/10/2011 23:16:35 | SETI@home | Project has no tasks available, I am now down to my final four tasks. It's OK though, they should keep me going until I can get my next fix, I mean, some more tasks :)

I can't even report wu's, http errors at the HE router I guess, I wish the nuts doing this would just get lost.

---

The T1 Trust, PRR T1 Class 4-4-4-4 #5550, 1 of America's First HST's

I'm sure all of you just read the latest news post.
http://setiathome.berkeley.edu/forum_thread.php?id=65678

She's down for the night, I'm sure. Hopefully, things will be fixed by the time the usual outage is done tomorrow.

Perhaps it is not only SETI. I came across this on Twitter about HE and a DDoS attack. I do not use Twitter but it looks current.

https://twitter.com/#!/henet

From the HE twitter feed
4 hours ago

Experiencing large DDos attack on our network. Network admins doing everything possible. No formal ETA at the moment. Will give update ASAP.

3 hours ago

Our network admins are still working as fast as posible to restore full connectivity and services. We'll continue to give updates as they come.

2 hours ago

Network still experiencing incidences of attack, though network admins are doing their best to keep the attack contained and mitigated.

It's not a Seti sever conking out this time, woohoo! :)

I wonder if Bank of America uses HE and SETI was caught in the crossfire.

http://abcnews.go.com/blogs/business/2011/10/bank-of-america-under-hacking-attack/

I wonder if Bank of America uses HE and SETI was caught in the crossfire.

http://abcnews.go.com/blogs/business/2011/10/bank-of-america-under-hacking-attack/

Just did a traceroute to see. Goes through a handful of hops on Level3 in Dallas and then directly to BoA's own allocated network addresses.

---

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

I'm sure all of you just read the latest news post.
http://setiathome.berkeley.edu/forum_thread.php?id=65678

She's down for the night, I'm sure. Hopefully, things will be fixed by the time the usual outage is done tomorrow.

Perhaps it is not only SETI. I came across this on Twitter about HE and a DDoS attack. I do not use Twitter but it looks current.

https://twitter.com/#!/henet

From the HE twitter feed
4 hours ago

Experiencing large DDos attack on our network. Network admins doing everything possible. No formal ETA at the moment. Will give update ASAP.

3 hours ago

Our network admins are still working as fast as possible to restore full connectivity and services. We'll continue to give updates as they come.

2 hours ago

Network still experiencing incidences of attack, though network admins are doing their best to keep the attack contained and mitigated.

It's not a Seti sever conking out this time, woohoo! :)

I wonder if Bank of America uses HE and SETI was caught in the crossfire.

http://abcnews.go.com/blogs/business/2011/10/bank-of-america-under-hacking-attack/

Yep, they do as seen here: http://bgp.he.net/AS10794#_whois

---

The T1 Trust, PRR T1 Class 4-4-4-4 #5550, 1 of America's First HST's

Has anyone heard anything on the Scheduler issue? I didn't see anything in the News or Tech news threads.
Even after the outage i still can't contact the Scheduler.

---

Grant
Darwin NT

Has anyone heard anything on the Scheduler issue? I didn't see anything in the News or Tech news threads.
Even after the outage i still can't contact the Scheduler.

I've had a few contacts over the last few hours, but it has been only about one in five attempts that are sucessful. Saying that I've rec'd no new tasks.

Also I noted about 3 hours ago there were 798,200 tasks available, that has now decreased to 783,867 and according to scarecrows graphs, creation rate is near 0.00 as you can get.

Think we need a full database clean up and compaction asap, rather than contact with the servers.

Think we need a full database clean up and compaction asap, rather than contact with the servers.

I was under the understanding that this was taken care of this morning while the servers were off line.

---

Well normally the tuesday outage does two things. One, it defragments and compresses the database, and then a copy of it is made and deployed on the replica (as well as sent to off-site storage).

So one would think that after defragging and compressing the database, it should be running smooth now, right? Well there's only so much of the database that will fit in RAM, and unfortunately, with 13M and climbing waiting to be purged, I'm guessing that is taking up RAM for task page queries or something else.

The issues we are experiencing with contacting the scheduler, internal DB operations in the server closet are likely as intermittent/slow because of the bloat.

I think turning the scheduler off and turning db_purge on until the backlog is cleared is about the only thing that can rectify this situation.

---

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

Well 40 mins later and the MB's waiting to be sent still remains at 783,867, so definitely something is causing problems at the server end.

I agree that things are getting out of control and something should be done about it. However, I think that turning off the scheduler is a bit drastic. Turning off the splitters seems more appropriate. This way people will still be able to report completed tasks (before the deadline).

Tom

Well normally the tuesday outage does two things. One, it defragments and compresses the database, and then a copy of it is made and deployed on the replica (as well as sent to off-site storage).

So one would think that after defragging and compressing the database, it should be running smooth now, right? Well there's only so much of the database that will fit in RAM, and unfortunately, with 13M and climbing waiting to be purged, I'm guessing that is taking up RAM for task page queries or something else.

The issues we are experiencing with contacting the scheduler, internal DB operations in the server closet are likely as intermittent/slow because of the bloat.

I think turning the scheduler off and turning db_purge on until the backlog is cleared is about the only thing that can rectify this situation.

---

This is not pretty.
The kitties are getting rather depressed.
My top rig has been doing MW since yesterday just to keep it warm because it runs 24/7.
Two other rigs are out of Seti work, and can't even connect to report the last of what they've completed.
The other 5 slower rigs are still crunching up their last.

The main router is on the fritz, and the servers are tied up in knots when you can connect. Even the forums are doggy at times.

Come on back, Seti.

The kitties will leave the light on for ya.

---

"Freedom is just Chaos, with better lighting." Alan Dean Foster

This is not pretty.
The kitties are getting rather depressed.
My top rig has been doing MW since yesterday just to keep it warm because it runs 24/7.
Two other rigs are out of Seti work, and can't even connect to report the last of what they've completed.
The other 5 slower rigs are still crunching up their last.

The main router is on the fritz, and the servers are tied up in knots when you can connect. Even the forums are doggy at times.

Come on back, Seti.

The kitties will leave the light on for ya.

Set NNT and then update, they will then report.

Don't forget to unset NNT after.

---

Kevin

This is not pretty.
The kitties are getting rather depressed.
My top rig has been doing MW since yesterday just to keep it warm because it runs 24/7.
Two other rigs are out of Seti work, and can't even connect to report the last of what they've completed.
The other 5 slower rigs are still crunching up their last.

The main router is on the fritz, and the servers are tied up in knots when you can connect. Even the forums are doggy at times.

Come on back, Seti.

The kitties will leave the light on for ya.

Set NNT and then update, they will then report.

Don't forget to unset NNT after.

Is that a bug work-around to be able to contact the scheduler again?

---

Janice

Just to let you know I rec'd one task, GPU VHAR, at 07:49:46.

Set NNT and then update, they will then report.

Don't forget to unset NNT after.

Is that a bug work-around to be able to contact the scheduler again?

On a 6.12.x client setting NNT forces 'report straight after upload' behaviour.
Which would help if the problem was getting the client to report and not getting the report through...

ahh gotcha. So no help in the just can not connect to scheduler. I have had 251 completed tasks here for hours on 6.10.58, and simply can not get there from here.

---

Janice

Time in last post was UTC
But checking back I had rec'd another about 20 mins earlier.

Strange thing is that Results ready to send is still at 783,867 thats over an hour after I last posted that number. So either the page is lying, or "Results ready to send" cannot be greater than that, for some reason. Unpurged WU/tasks maybe?

Set NNT and then update, they will then report.

Don't forget to unset NNT after.

It could be a coincidence but it worked for me:

5-10-2011 9:51:41 | SETI@home | work fetch suspended by user
5-10-2011 9:51:43 | SETI@home | update requested by user
5-10-2011 9:51:46 | SETI@home | Sending scheduler request: Requested by user.
5-10-2011 9:51:46 | SETI@home | Reporting 361 completed tasks, not requesting new tasks
5-10-2011 9:51:56 | SETI@home | Scheduler request completed
5-10-2011 9:52:13 | SETI@home | work fetch resumed by user

The scheduler is still unreachable when asking for new work though...

---

Seti@Netherlands website