What happened to S@H being able to spread out storage amongst the clients? To my knowledge, that feature has never been used. There are countless petabytes of storage space available that they could use.

I have asked the same thing and gotten an answer that did make sense.. Bandwidth issues. For safety it would need to be sent and stored on multiple PC's..I am guessing 2 would not be enough due to the transiant nature of many crunchers.

---

Janice

What happened to S@H being able to spread out storage amongst the clients? To my knowledge, that feature has never been used. There are countless petabytes of storage space available that they could use.

It can be done only for backup purposes, but AFAIK they already have good backup storage provider.
For data analysis one need directly access to whole data array. Such analysis would be just impossible if data distributed over different hosts with less than gigabit network connection between each over (and even in this case processing speed would drop on few orders of magnitude due to absence of memory caching of data).

With everything off line I wonder why the bandwidth usage is so high ??

The Cricket graphs are still showing 30Mbps going into Berkeley which is the normal level for a Saturday. However as no-one can report or upload......

T.A.

Yes - strange..

The server are down, but the cricket graph show traffic..

Since ~ 6 hours 'server down': ~ 5 Mbits/sec DL and ~ 30 Mbits/sec UL..

Hmm.. maybe there is something wrong (because of changed server) and we see now the 'internel' traffic between some server..?

---

See my post here.

---

Boinc....Boinc....Boinc....Boinc....

Panic Mode On...Hyperventilating...Need paper bag...Need Valium.
OK now, The Staff WILL work things out.

---

I Desire Peace and Justice, Jim Scott (Mod-Ret.)

All but out of work, are they going to let us get any this week?

---

Official Abuser of Boinc Buttons...
And no good credit hound!

I got so many .vlar wu last week that I doubt I would (could) download anything. Only wish to report work now.

---

Boinc....Boinc....Boinc....Boinc....

I have still hundreds of backlogged DLs in BOINC's transfer overview.. :-(

In a few hours the GPUs of the GPU machine will idle.
I have currently ~ 30 days rescheduled VLARs on/for the CPU..

---

Ugh, why don't they enable the scheduler?! In order to process all the workunits, my machine needs to report everything that's already uploaded.

This is the why they're out of space:
Results returned and awaiting validation 7,315,135

"Master database queries/second" is also broken since last outage.

From Jeff in tech news

Reality got a little ahead of us on this one. We were days, a week tops, away from migrating
upload service from bruno to bambi. This will double our upload space and allow us to turn
off bruno.

We will now move this up and make it top priority come Monday. We need to reconfigure
the raid on bambi and then let the raid sync. At that point we can both turn the projects
on and start migrating the results from bruno to bambi. We hope that this will be early in
the week. We'll then leave the projects on through next weekend, ie no normal 3 day outage.

From Jeff in tech news

Reality got a little ahead of us on this one. We were days, a week tops, away from migrating
upload service from bruno to bambi. This will double our upload space and allow us to turn
off bruno.

We will now move this up and make it top priority come Monday. We need to reconfigure
the raid on bambi and then let the raid sync. At that point we can both turn the projects
on and start migrating the results from bruno to bambi. We hope that this will be early in
the week. We'll then leave the projects on through next weekend, ie no normal 3 day outage.

3 Cheers for Jeff and the Staff!

Hip hip hooray! Hip hip hooray! Hip hip hooray!

And I mean that most sincerely too. :D

---

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

I have the GX60 & Amilo laptop off for now as they're dry, but I'm happy that the project should remain up over the coming week to let things settle down again. Next sched outage therefore sounds like should be Tue 5 Oct.

Well the download server is up but not the upload server. Have tons of uploads so I can download...Oh Well.

---

Official Abuser of Boinc Buttons...
And no good credit hound!

Well the download server is up but not the upload server. Have tons of uploads so I can download...Oh Well.

It may show as being up, but either it's not really online or nobody has anything to download, 'cuz the Cricket graphs have not changed much since it showed as being up hours ago.

---

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

I have still hundreds of backlogged DLs in the transfer overview in BOINC - and nothing come down.. :-(

---

I have the GX60 & Amilo laptop off for now as they're dry, but I'm happy that the project should remain up over the coming week to let things settle down again. Next sched outage therefore sounds like should be Tue 5 Oct.

The way things are going, better you should ask "When is the next scheduled UPage?"

---

I have the GX60 & Amilo laptop off for now as they're dry, but I'm happy that the project should remain up over the coming week to let things settle down again. Next sched outage therefore sounds like should be Tue 5 Oct.

The way things are going, better you should ask "When is the next scheduled UPage?"

Mmmmm, I can smell Uptime coming at any moment now. I feel it in my bad knee also.

I sure hope you are right - I'm out of CUDA WUs on one machine, and all the CPUs left are VLARs...guess I should be happy the 4 GT240s on this baby are getting a nice rest.

---

Then set your managers to not request new work until the cricket graph shows uploads tapering off

---

Then set your managers to not request new work until the cricket graph shows uploads tapering off

Many if not most of us who read these boards do that already.

Sten-Arne is only pointing out that the vast majority of S@H users Don't read these boards -they are "set and forget" users who's BOINC Managers are continuously trying to reach the servers, and even with automatic back-off, will drive bandwidth to the max as soon as ANY of the Upload/Download/Scheduling servers come online. (Yes, I know the Server Status page says Download Server 2 on Vader is running, but the Cricket Graph says it isn't "online".)

---

Donald
Infernal Optimist / Submariner, retired