Thanks Richard - I was on my phone and looking at two things at once on that is "problematic" - hopefully the new SERVER binaries will address some of the issues we've seen on main of late. (And Eric's note post dates the "new splitters broke Beta" announcement by a few weeks, and the more recent Beta stuff has flowed fairly smoothly....

---

Bob Smith
Member of Seti PIPPS (Pluto is a Planet Protest Society)
Somewhere in the (un)known Universe?

and we are back

---

But the splitters are offline. If Eric did deploy new server code, I hope we are not seeing the same issue that Beta had with the new server code.

---

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

A proud member of the OFA (Old Farts Association)

And the splitters are back online. But the SSP has not updated in 15 minutes. So who knows?

---

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

A proud member of the OFA (Old Farts Association)

Current result creation rate ** 0/sec 0.0148/sec 2.5690/sec 6m

This is not gud.

---

Is it just me, or are these new 02 WUs processing even faster than the previous 05s? Around 10sec on the GPUs and 4min on the CPU faster.
The servers weren't doing too well as it was, these new WUs will push them even harder.

. . Yes, they are processing slightly faster than those Blc05 units were. Not quite so dramatic here though they are around 30 secs faster on the 950 GPU and about one min on the i5-6400, maybe 10 secs on the 970s and 2 mins on the i5-6600, and finally about 10 to 12 secs faster on the 1050ti, the C2D doesn't crunch normally but during the outage it ran a couple of Blc02s and they were about 2 to 5 mins quicker (compared to 81 to 84 mins).

Stephen

PS:- the post outage hourly return nearly hit the 200,000 mark :(

Looks like we've reached that critical point of returned-last-hour, WU-waiting-deletion, in-progress and splitter load.
Waiting-deletion is going up, splitter output has gone down, and Ready-to-send buffer is rapidly emptying. And with the shorter WU run times, channels left to be split is rapidly diminishing also.

. . On that subject (channels to be split) I am left pondering why it is that all the "tapes" (Disks) show as 52.24 GB but while some show 80 to 120 channels others show only one or two. What causes that level of discrepancy?

Stephen

??

And the splitters are back online. But the SSP has not updated in 15 minutes. So who knows?

Splitters showing Green, and status page has updated. But still no work actually coming from the splitters.
Server code update broke our splitters as well as Betas?


Edit- over 2 hours since the project came back up, but still no splitter output.

---

Grant
Darwin NT

. . On that subject (channels to be split) I am left pondering why it is that all the "tapes" (Disks) show as 52.24 GB but while some show 80 to 120 channels others show only one or two. What causes that level of discrepancy?

Only those in progress (dark green), or have been processed (light green), show up.

---

Grant
Darwin NT

Apparently the splitters are splitting as showed by the Splitter status but where the splitted data is going?

---

I made it thru todays outrage but it looks like I will go dry this evening unless something gets fixed.

---

Apparently the splitters are splitting as showed by the Splitter status but where the splitted data is going?

I think it's a case of the splitters are running, but they're not actually doing anything.

Apparently, the updated server code broke the splitters on Beta.
They got that fixed, but it would appear there's some differences between the splitters here & at Beta that didn't cope too well with the new code.
It could be a while before work is flowing again.

---

Grant
Darwin NT

Nothing new on the graphs, the In Progress is still headed Down;


about a couple hours left, then my machines will be going cold...like the weather outside.

Nothing new on the graphs, the In Progress is still headed Down;

Even if they get the splitters fixed quickly, and they then split like never before, and maintain that level of output like never before, it's going to be a long and tough recovery.

---

Grant
Darwin NT

I made it thru todays outrage but it looks like I will go dry this evening unless something gets fixed.

. . I have about 3 to 5 hours for all machines to be empty. Considering it is after 9pm in Berkeley I guess the guys (computers) will get to sleep tonight...

Stephen

:(

someone needs to give the splitters a (re-) boot in the bum... 0 WU ready to send and only .7584 WU per second created (with 0 WU available, that should be in the 49-50 range!)

It's time to give your alternate projects some love... (IF they aren't also down [hello, GPUgrid?])

---

.

Hello, from Albany, CA!...

someone needs to give the splitters a (re-) boot in the bum... 0 WU ready to send and only .7584 WU per second created (with 0 WU available, that should be in the 49-50 range!)

Apparently a change was made that didn't go well. Splitters crashed shortly after the outage.

It's time to give your alternate projects some love... (IF they aren't also down [hello, GPUgrid?])

Yeah, only good news here is I finally got a config I'm happy with that lets Einstein take over when SETI goes sideways without having to dump a bunch of work when SETI resurfaces.

---

I don't personally think so IMO maybe the project is in disarray after what happened at Arecibo, they would be still finding there feet one would imagine..

I bet it is the patches for Meltdown and Spectre that's the reason for the server slowdowns.

If we're lucky.
If not, it's the increased load (of all those short running GBT WUs) showing the present systems limits, and the patches will just make things even worse when they are applied.

Present lack of work- most likely the server update that worked on Beta (after it was fixed for breaking the splitters there), broke the splitters here.

---

Grant
Darwin NT

Currently, the server status page is in an inconsistent state vis a vis the splitters for BLC.

It shows 14 splitters running, but 17 tapes being processed, one of which appears to have > 1 splitter associated with it.

With all the things that have happened recently, I don't recall ever seeing ghost splitters before.

Did I miss something?

---