On Bandwidth (Jul 08 2009)


log in

Advanced search

Message boards : Technical News : On Bandwidth (Jul 08 2009)

Previous · 1 · 2 · 3 · 4 · 5 · Next
Author Message
1mp0£173
Volunteer tester
Send message
Joined: 3 Apr 99
Posts: 8423
Credit: 356,897
RAC: 0
United States
Message 916331 - Posted: 9 Jul 2009, 22:05:44 UTC - in response to Message 916327.

On a related note, would it be useful to get NASA or ESA involved in distributing radio telescope data?

Current U.S. Law severely restricts the use of federal funds for SETI of any sort.

... that's one reason for Astropulse: because it could produce results other than SETI, it can potentially get funding from sources that can't fund SETI.

I'm sure ESA has no such restrictions.
____________

Profile ML1
Volunteer tester
Send message
Joined: 25 Nov 01
Posts: 8368
Credit: 4,102,460
RAC: 1,088
United Kingdom
Message 916346 - Posted: 9 Jul 2009, 22:39:44 UTC - in response to Message 916322.
Last modified: 9 Jul 2009, 22:40:30 UTC


As mentioned previously, I believe it has already been mentioned that the SSL are already using grey fibre, but only at 100 Mb/s.

If you can find that anywhere, I'd be interested. I think the current wire is copper.

This is from:

Bit Ceiling (Oct 08 2008) - Richard Haselgrove

Bit Ceiling (Oct 08 2008) - ML1


This is the sort of source post I'm remembering:

The really big problem is us

And from Matt himself:

Tweenday Two (Dec 27 2007)

In reality, we have a 1GBit connection to the world via Hurricane Electric, but alas this is constrained by a 100 Mbit fiber coming out of the lab down to campus - it will take some big $$$ to upgrade that, which may happen sooner or later (as it would not only benefit us).

... We have gigabit all over our server closet (more or less - some older servers are 100Mbit going into the 1Gbit switch).



So, appears there's already fibre in place, but not the high speed connections.

I wonder which department is waiting for which department to provide the $$$?

Regards,
Martin
____________
See new freedom: Mageia4
Linux Voice See & try out your OS Freedom!
The Future is what We make IT (GPLv3)

1mp0£173
Volunteer tester
Send message
Joined: 3 Apr 99
Posts: 8423
Credit: 356,897
RAC: 0
United States
Message 916351 - Posted: 9 Jul 2009, 23:17:54 UTC - in response to Message 916346.

Tweenday Two (Dec 27 2007)

[i]In reality, we have a 1GBit connection to the world via Hurricane Electric, but alas this is constrained by a 100 Mbit fiber coming out of the lab down to campus - it will take some big $$$ to upgrade that, which may happen sooner or later (as it would not only benefit us).

It will be very interesting to find out what campus finds. Might not need to dig any trenches at all -- he says hopefully as Murphy stands menacingly just out side his field of view.
____________

Richard HaselgroveProject donor
Volunteer tester
Send message
Joined: 4 Jul 99
Posts: 8458
Credit: 48,672,783
RAC: 81,528
United Kingdom
Message 916352 - Posted: 9 Jul 2009, 23:26:00 UTC - in response to Message 916346.

Bit Ceiling (Oct 08 2008) - Richard Haselgrove

I retract - I am certainly not an authoritative source. But I may have had an unconscious memory of

Tweenday Two (Dec 27 2007)

In reality, we have a 1GBit connection to the world via Hurricane Electric, but alas this is constrained by a 100 Mbit fiber coming out of the lab down to campus - it will take some big $$$ to upgrade that, which may happen sooner or later (as it would not only benefit us).

I mentioned how we seem to have a 60Mbit ceiling...

... We have gigabit all over our server closet (more or less - some older servers are 100Mbit going into the 1Gbit switch).

But I do remember quite clearly how Matt eventually found that the 60 MB cap was the internal processing limit of the CISCO routers then in use. Upgrading the routers got us to the effective 95 MB cap we have now.

Josef W. SegurProject donor
Volunteer developer
Volunteer tester
Send message
Joined: 30 Oct 99
Posts: 4226
Credit: 1,041,833
RAC: 332
United States
Message 916398 - Posted: 10 Jul 2009, 2:18:31 UTC - in response to Message 916246.

If it is political, that there isn't better comms to the building, maybe we need to shame the 'powers that be' into action.
A few thousand e-mails from the us users might wake them up. Or ask the students to have a demonstration on our behalf.

I think if we want to have a "demonstration" it'd be best to mail in a $5 bill rather than try to "shame" the administration into spending more money on what is clearly an under-funded project flying under the radar.

The minimum donation the Berkeley system supports is 10 U.S. dollars. Mailing in a $5 bill would create a bureaucratic dilemma, that's the worst kind.

That $5 amount has been mentioned several times recently, it is certainly tempting to think in terms of how little each participant would need to contribute to make this a well-funded project. But the world seldom works as we would prefer, I'm just trying to keep the record straight so practicalities aren't forgotten.
Joe

1mp0£173
Volunteer tester
Send message
Joined: 3 Apr 99
Posts: 8423
Credit: 356,897
RAC: 0
United States
Message 916414 - Posted: 10 Jul 2009, 3:24:33 UTC - in response to Message 916398.

If it is political, that there isn't better comms to the building, maybe we need to shame the 'powers that be' into action.
A few thousand e-mails from the us users might wake them up. Or ask the students to have a demonstration on our behalf.

I think if we want to have a "demonstration" it'd be best to mail in a $5 bill rather than try to "shame" the administration into spending more money on what is clearly an under-funded project flying under the radar.

The minimum donation the Berkeley system supports is 10 U.S. dollars. Mailing in a $5 bill would create a bureaucratic dilemma, that's the worst kind.

That $5 amount has been mentioned several times recently, it is certainly tempting to think in terms of how little each participant would need to contribute to make this a well-funded project. But the world seldom works as we would prefer, I'm just trying to keep the record straight so practicalities aren't forgotten.
Joe

$5 is a metaphor, I meant "donate."

I should know that when dealing with engineering-types that it is better to specify the amount to three decimal places.
____________

Profile Gary CharpentierProject donor
Volunteer tester
Avatar
Send message
Joined: 25 Dec 00
Posts: 12372
Credit: 6,674,046
RAC: 8,749
United States
Message 916420 - Posted: 10 Jul 2009, 4:01:20 UTC - in response to Message 916414.

If it is political, that there isn't better comms to the building, maybe we need to shame the 'powers that be' into action.
A few thousand e-mails from the us users might wake them up. Or ask the students to have a demonstration on our behalf.

I think if we want to have a "demonstration" it'd be best to mail in a $5 bill rather than try to "shame" the administration into spending more money on what is clearly an under-funded project flying under the radar.

The minimum donation the Berkeley system supports is 10 U.S. dollars. Mailing in a $5 bill would create a bureaucratic dilemma, that's the worst kind.

That $5 amount has been mentioned several times recently, it is certainly tempting to think in terms of how little each participant would need to contribute to make this a well-funded project. But the world seldom works as we would prefer, I'm just trying to keep the record straight so practicalities aren't forgotten.
Joe

$5 is a metaphor, I meant "donate."

I should know that when dealing with engineering-types that it is better to specify the amount to three decimal places.

Never decimal places, always significant digits! :)

____________

Profile HAL9000
Volunteer tester
Avatar
Send message
Joined: 11 Sep 99
Posts: 4055
Credit: 111,102,913
RAC: 147,751
United States
Message 916424 - Posted: 10 Jul 2009, 4:09:41 UTC - in response to Message 916414.

If it is political, that there isn't better comms to the building, maybe we need to shame the 'powers that be' into action.
A few thousand e-mails from the us users might wake them up. Or ask the students to have a demonstration on our behalf.

I think if we want to have a "demonstration" it'd be best to mail in a $5 bill rather than try to "shame" the administration into spending more money on what is clearly an under-funded project flying under the radar.

The minimum donation the Berkeley system supports is 10 U.S. dollars. Mailing in a $5 bill would create a bureaucratic dilemma, that's the worst kind.

That $5 amount has been mentioned several times recently, it is certainly tempting to think in terms of how little each participant would need to contribute to make this a well-funded project. But the world seldom works as we would prefer, I'm just trying to keep the record straight so practicalities aren't forgotten.
Joe

$5 is a metaphor, I meant "donate."

I should know that when dealing with engineering-types that it is better to specify the amount to three decimal places.


I prefer 6 digit precision myself.
____________
SETI@home classic workunits: 93,865 CPU time: 863,447 hours

Join the BP6/VP6 User Group today!

1mp0£173
Volunteer tester
Send message
Joined: 3 Apr 99
Posts: 8423
Credit: 356,897
RAC: 0
United States
Message 916442 - Posted: 10 Jul 2009, 6:17:54 UTC - in response to Message 916420.
Last modified: 10 Jul 2009, 6:18:08 UTC


The minimum donation the Berkeley system supports is 10 U.S. dollars. Mailing in a $5 bill would create a bureaucratic dilemma, that's the worst kind.

That $5 amount has been mentioned several times recently, it is certainly tempting to think in terms of how little each participant would need to contribute to make this a well-funded project. But the world seldom works as we would prefer, I'm just trying to keep the record straight so practicalities aren't forgotten.
Joe

$5 is a metaphor, I meant "donate."

I should know that when dealing with engineering-types that it is better to specify the amount to three decimal places.

Never decimal places, always significant digits! :)

Whenever I start thinking floating point (and money is generally floating point), I automatically shift to scientific notation, so 3 decimal places is 4 significant digits.
____________

Profile Astro-AL
Send message
Joined: 31 Mar 00
Posts: 17
Credit: 49,844,753
RAC: 63,692
United States
Message 916806 - Posted: 11 Jul 2009, 14:36:01 UTC - in response to Message 916153.

I couldn't see where Matt responded to your comments. Have you heard anything about your suggestion.
____________

Profile Dr. C.E.T.I.
Avatar
Send message
Joined: 29 Feb 00
Posts: 15993
Credit: 690,597
RAC: 0
United States
Message 916822 - Posted: 11 Jul 2009, 16:15:34 UTC


> Thanks for the Postings Matt - as you can see - it's appreciated by all here @ the Project . . .

< Think-Tank [suggestion as mentioned to Eric Korpela] we should be able to fix practically everything that needs fixin' . . .

@ Berkeley - accolades to each of you for all that you do [as well, have done]




"I am he as you are he as you are me and we are all together . . ."




____________
BOINC Wiki . . .

Science Status Page . . .

Speedy
Volunteer tester
Avatar
Send message
Joined: 26 Jun 04
Posts: 659
Credit: 5,592,435
RAC: 8,070
New Zealand
Message 917073 - Posted: 12 Jul 2009, 5:15:14 UTC
Last modified: 12 Jul 2009, 5:15:57 UTC

Thanks to the team that keeps our crunchers fed with work. Here's my thought on the comment about turning downloads off. 1st Turn data recorders off, split the tapes that have just been filled with fresh data to save trashing data collected. Is the gigabit Internet connection a flat rate or is it a set rate per petabyte? from the Current Budget fall 2008 it says that to get a 1Gbit connection to the lab it will be $80000. I'm not sure if this is the connection that the lab can only use 100Mbit of.
____________

Live in NZ y not join Smile City?

1mp0£173
Volunteer tester
Send message
Joined: 3 Apr 99
Posts: 8423
Credit: 356,897
RAC: 0
United States
Message 917077 - Posted: 12 Jul 2009, 5:53:08 UTC - in response to Message 917073.

Thanks to the team that keeps our crunchers fed with work. Here's my thought on the comment about turning downloads off. 1st Turn data recorders off, split the tapes that have just been filled with fresh data to save trashing data collected. Is the gigabit Internet connection a flat rate or is it a set rate per petabyte? from the Current Budget fall 2008 it says that to get a 1Gbit connection to the lab it will be $80000. I'm not sure if this is the connection that the lab can only use 100Mbit of.

SETI buys their bandwidth delivered to one of the internet exchanges (PAIX) so it is very inexpensive.

Campus takes care of delivering it from PAIX to SSL. The university-owned connection isn't gigabit all the way from PAIX to SSL.

Bandwidth is available second-by-second, 24 hours/day. Turning off uploads and downloads, or limiting them to certain days, is just wasting every second during those days.
____________

Chelski
Avatar
Send message
Joined: 3 Jan 00
Posts: 121
Credit: 8,810,438
RAC: 738
Malaysia
Message 917279 - Posted: 13 Jul 2009, 3:44:12 UTC

Thanks for the updates. It looks like it will be months rather than weeks before a permanent corrective action can be in place for the bandwidth issue.

Meanwhile, is it possible for an interim solution? Even a 50% uptime wireless will help a lot with the frequent backlogs that take days to clear these days (since "normal" days the line is at least 80-90% utilised, and during recovery maybe 20% is available to clear backlogs). Or for that matter, since the "non-SETI" line up the hill is only using like 10mbits/sec or so, to have a throttled limit of SETI traffic to flow through it, like ~50mbits/sec will be of great help to the project.
____________

Profile Gary CharpentierProject donor
Volunteer tester
Avatar
Send message
Joined: 25 Dec 00
Posts: 12372
Credit: 6,674,046
RAC: 8,749
United States
Message 917296 - Posted: 13 Jul 2009, 5:06:45 UTC - in response to Message 917077.

Thanks to the team that keeps our crunchers fed with work. Here's my thought on the comment about turning downloads off. 1st Turn data recorders off, split the tapes that have just been filled with fresh data to save trashing data collected. Is the gigabit Internet connection a flat rate or is it a set rate per petabyte? from the Current Budget fall 2008 it says that to get a 1Gbit connection to the lab it will be $80000. I'm not sure if this is the connection that the lab can only use 100Mbit of.

SETI buys their bandwidth delivered to one of the internet exchanges (PAIX) so it is very inexpensive.

Campus takes care of delivering it from PAIX to SSL. The university-owned connection isn't gigabit all the way from PAIX to SSL.

Bandwidth is available second-by-second, 24 hours/day. Turning off uploads and downloads, or limiting them to certain days, is just wasting every second during those days.

$50,000+ and $2375/month
http://ist.berkeley.edu/services/is/net/fiberoptic

Much better buy
http://ist.berkeley.edu/services/is/dc/colo

And just in case they didn't see it:
http://ist.berkeley.edu/services/catalog/datacenter/serverdonation

____________

1mp0£173
Volunteer tester
Send message
Joined: 3 Apr 99
Posts: 8423
Credit: 356,897
RAC: 0
United States
Message 917299 - Posted: 13 Jul 2009, 5:48:43 UTC - in response to Message 917296.


SETI buys their bandwidth delivered to one of the internet exchanges (PAIX) so it is very inexpensive.

Campus takes care of delivering it from PAIX to SSL. The university-owned connection isn't gigabit all the way from PAIX to SSL.

Bandwidth is available second-by-second, 24 hours/day. Turning off uploads and downloads, or limiting them to certain days, is just wasting every second during those days.

$50,000+ and $2375/month
http://ist.berkeley.edu/services/is/net/fiberoptic

Much better buy
http://ist.berkeley.edu/services/is/dc/colo

And just in case they didn't see it:
http://ist.berkeley.edu/services/catalog/datacenter/serverdonation

This is worth reading:

Some things have changed, like replacing Cogent with Hurricane Electric (at a lower cost), but the concept is still there.

Note that your first link is for off-campus service, provided by Comcast cable, and the Space Sciences Lab is on-campus.
____________

Profile Gundolf Jahn
Send message
Joined: 19 Sep 00
Posts: 3184
Credit: 357,953
RAC: 37
Germany
Message 917311 - Posted: 13 Jul 2009, 7:38:15 UTC - in response to Message 917299.
Last modified: 13 Jul 2009, 7:40:02 UTC

This is worth reading: http://www.mail-archive.com/setiathome@klx.com/msg01049.html.

I changed [img] to [url] tags ;-)

Gruß,
Gundolf

Profile Gary CharpentierProject donor
Volunteer tester
Avatar
Send message
Joined: 25 Dec 00
Posts: 12372
Credit: 6,674,046
RAC: 8,749
United States
Message 917313 - Posted: 13 Jul 2009, 7:44:34 UTC - in response to Message 917299.


SETI buys their bandwidth delivered to one of the internet exchanges (PAIX) so it is very inexpensive.

Campus takes care of delivering it from PAIX to SSL. The university-owned connection isn't gigabit all the way from PAIX to SSL.

Bandwidth is available second-by-second, 24 hours/day. Turning off uploads and downloads, or limiting them to certain days, is just wasting every second during those days.

$50,000+ and $2375/month
http://ist.berkeley.edu/services/is/net/fiberoptic

Much better buy
http://ist.berkeley.edu/services/is/dc/colo

And just in case they didn't see it:
http://ist.berkeley.edu/services/catalog/datacenter/serverdonation

This is worth reading: http://www.mail-archive.com/setiathome@klx.com/msg01049.html

Some things have changed, like replacing Cogent with Hurricane Electric (at a lower cost), but the concept is still there.

Note that your first link is for off-campus service, provided by Comcast cable, and the Space Sciences Lab is on-campus.

Please read it more carefully
Service to provide fiber connectivity to a department building that is outside of the main campus perimeter.

SSL is outside the main campus perimeter. Check the campus map.
http://www.berkeley.edu/map/maps/large_map.html
This makes the $80,000 figure in the budget make sense.
____________

1mp0£173
Volunteer tester
Send message
Joined: 3 Apr 99
Posts: 8423
Credit: 356,897
RAC: 0
United States
Message 917398 - Posted: 13 Jul 2009, 17:58:59 UTC - in response to Message 917313.


Service to provide fiber connectivity to a department building that is outside of the main campus perimeter.

SSL is outside the main campus perimeter. Check the campus map.
http://www.berkeley.edu/map/maps/large_map.html
This makes the $80,000 figure in the budget make sense.

I'm really not trying to call you out, or question you, nor do I work for IST or at the SSL.

The page says:
This is provided by Comcast on a case-by-case basis, depending on their ability to provide fiber in the vicinity of the building. If fiber is available, the cost will vary depending on the amount of construction (e.g. trenching, provisioning for conduit) required to get the fiber into the building.

I'm not sure, but I'm guessing based on Matt's posts, that Comcast does not have fiber near SSL.

Either way, Matt says that IST is doing the analysis to see what's available, and what is possible.

I also think that in general, Campus has treated SETI@Home pretty well. They've not only let them buy bandwidth off-campus (instead of forcing them to pay campus rates), but they've provided transport from PAIX to SSL.
____________

deac
Send message
Joined: 28 Jan 00
Posts: 9
Credit: 1,675,239
RAC: 0
United States
Message 917781 - Posted: 15 Jul 2009, 3:45:56 UTC - in response to Message 915855.

You sound stressed, busy, and overly occupied. I have been in such positions, and yes, sometimes you need to pull the plug, reorganize, and come back on line with a refreshed vision, attitude, and better connection.

The constant demand that you push out work units can't possibly be healthy at all. Stop, reorganize, start stronger, begin anew with a better IT infrastructure, if that's what it takes, and you will be able to spend your days studying stellar clusters, instead of responding to complaints related to why 8500GT CUDA video cards overheat when they run version 36.09.09 vs version 36.09.10 graphic drivers...

Your dilemma is not a dilemma: you are trying to balance project participant's egos and complaints against real science; you are trying to please people that update that score daily, competitively so, against the real meaning of science behind the entire undertaking...You are in a sense engaging in a failing proposition, for the people crunching numbers on here could care less, if we discover a signal, they care much more about whether JoeBlo123's CUDA processor finished a workunit 5 minutes quicker than their SLI setup...

I don't envy you, it is a full time marketing job, or an HR job...However, while none of these number cruncher characters understand the statistics or the real science behind the enterprise, I can guarantee you, that they will be frustrated if their PC systems have nothing to do. And they will want to do something...They like SETI, it is part of them...

Shutdown for a month or two to upgrade your systems, do it. The people will return, for what you have going for you, is a most noble, exquisite, and promising enterprise, relating ONLY to what is the most fundamental and invigorating and puzzling question in our existence: " Are We alone"

P.S. I know the number crunchers aren't alone, or they think they aren't...I feel sorry for them...

Bye now, I must discover new primes...
____________

Previous · 1 · 2 · 3 · 4 · 5 · Next

Message boards : Technical News : On Bandwidth (Jul 08 2009)

Copyright © 2014 University of California