News archive
News archive |
|
May 6, 2008
Earlier today we released a similar version 4.04 which gave users
checksum errors and failed to run. This has been fixed in 4.05.
The snap server continues to run well. During all of this some web site files were lost and these are being
restored now. We plan to release major version 4 of BOINC and SETI@Home
tomorrow.
A clarification about last week's fallback to an earlier
DB state: all work that was uploaded during the period of
August 13th to 18th
was lost and so cannot be credited. As well, all work that
was generated and downloaded during that period was lost to the DB and so cannot
be credited. This work is being regenerated and redistributed. Another note about the database restoration: All user profile/preferences updates
between August 13th and 18th were lost as well.
SETI@home Project Scientist Eric Korpela speaks about the probablility of finding intelligent life on earthlike planets as one of the guests interviewed by Seth Shostak on this week edition of 'Are We Alone', the SETI Institute's Weekly radio magazine.
May 1, 2008
Congratulations to team SETI.USA. Their total BOINC credits have exceeded 1 billion cobblestones!
April 28, 2008
The Near Time Persistency Checker (software we are developing to get up-to-date analysis of SETI@home results) has enjoyed recent progress.
There is work still to be done, but the basic plumbing is in place - for example, on the Science Status page we
added counts of signals SETI@home found where the Arecibo is currently pointing.
April 7, 2008
Some SETI@home volunteers put together a tribute to Arthur C. Clarke as a means of paying their final respects. We are sure he would have been touched by your sentiments.
April 3, 2008
Last night the BOINC database server crashed - all services are recovering now.
March 18, 2008
Arthur C. Clarke, visionary science fiction writer and friend of the SETI@home Project, passed away today at the age of 90.
January 31, 2008
A tip of the hat to the
Clemson University #1 team, which has been
the top-ranked team in the University category for several years.
January 18, 2008
We have been informed of the passing of a dedicated SETI@home volunteer and active participant on the forums, Dennis Peters, (aka Dogbytes). Our condolences go out to his family and friends.
January 15, 2008
A new article from the Planetary Society:
From SETI@home to Hominid Fossils: Citizen Cyberscience Reshapes Research Landscape.
January 3, 2008
UC Berkeley Press Release: SETI@home looking for more volunteers.
December 7, 2007
Outage Update: Last night (December 6) around 15:00 PST we powered
down the entire project for lab-wide electrical repairs. Without much ado we turned everything
back on this morning, and all data servers are slowly catching up.
November 28, 2007
Live in Washington DC? Get together with other BOINC users via
Meetup
(or create a Meetup
in your own city).
November 18, 2007
The preferences for email notification of private messages
was mistakenly initialized to 'on'.
We have changed it to 'off' for all users.
If you want to turn it back on,
go here.
November 16, 2007
We will be having a 4 hour outage on Monday, 11/19/2007, starting at 10:00 PST. The purpose of this outage is to reroute many of the power cords for
the project servers, rearrange some of our UPSs and pull deprecated equipment out of
the server room.
November 8, 2007
New science newsletter:
Planetary System Detected Around SETI@home Target Star
(article from the the Planetary Society).
November 8, 2007
A big index build is stressing our science databases and the splitters are running very slowly. This
has resulted in the project running out of work to send. We hope to see it clear by tomorrow morning.
October 17, 2007
SETI@home user Melt Wreckage sent us a song Arecibo Dance inspired by the
1974 radio transmission from Arecibo.
October 14, 2007
We are having air conditioning problems. The project is down for the night.
October 8, 2007
In order to quickly recover from the fallout of recent server outages, we'll be offline all night to clean up the database. Data transactions will resume Tuesday afternoon.
October 5, 2007
Upload service is back to normal. Details are in technical news.
October 4, 2007
We tried moving the upload store off of a possibly flaky disk array yesterday. This slowed upload service
dramatically. The slowdown was unexpected and we are in the process of fixing it..
October 1, 2007
We had three server crashes over the weekend and are recovering now. Details later today in technical news.
September 19, 2007
We note the passing of dedicated SETI@home volunteer John McCoy. Our thoughts and sympathies go out to his friends and family.
September 10, 2007
There were some problems with our science database server over the weekend but we are
currently creating and sending out new work.
August 12, 2007
The problematic server is back up and work is flowing.
August 11, 2007
Were're having problems with one our servers. We'll be down until someone can get into the lab to fix it.
August 6, 2007
Our BOINC database server crashed this afternoon and finally recovered. However other
systems are having problems. We're probably going to be offline all night.
All data services will be off until we clean all these things up.
July 23, 2007
Our Internet connectivity was restored at 01:00 PDT today.
July 22, 2007
All of our servers came up fine after the power outage. However we are currently experiencing a routing problem that we are working with campus on. This problem is preventing the distribution of work. At this point it looks like we will be off the air until tomorrow.
July 19, 2007
If you are having problems with the MacOS version of SETI@home (5.21) please reset the project to get version 5.22.
July 19, 2007
There will be a lab-wide power outage (for repairs in a nearby building) this weekend. We'll be shutting down BOINC/SETI@home services around 16:00 PDT on Saturday, and coming back on line 08:00 PDT on Sunday. All web/data servers will be unreachable during this time.
July 9, 2007
A mysterious source of radio interference has been identified and fixed - read about it here.
July 9, 2007
Here's a SETI@home Update (article written by the Planetary Society).
July 2, 2007
Amir Alexander of The Planetary Society talks about
SETI, distributed computing, and space exploration in an interview by Mike of BOINC UK.
June 27, 2007
Help increase SETI@home's computing power -
publicize SETI@home and BOINC by writing to computer magazines.
June 19, 2007
We have an update on the Arecibo Painting Upgrade.
June 13, 2007
We're having a brief server outage to reconfigure our databases. We should be back up in an hour or so.
June 12, 2007
Read about how to participate in grid computing projects that benefit humanity.
June 11, 2007
We're moving our usual Tuesday outage to today (Monday) in order to clean
up some problems we've been having with the BOINC database over the weekend.
The data servers and most web pages will be offline during this time.
May 25, 2007
We are back up after some additional complications. There will be a period
of "catch up" before things are back to normal.
May 25, 2007
The database and project have been down for a few hours. We're working on the slow
feeder problem that was causing work distribution to go slowly.
May 21, 2007
We've solved yesterday's problem and we're back up.
May 18, 2007
If your BOINC client is not able to upload to or download from
the SETI@Home servers, look for the message Message from Server: Incomplete request received
in the BOINC Manager messages area. If you see that message, stopping
and restarting your BOINC client should fix the problem.
May 12, 2007
We got the new server yesterday, inserted our old disks and booted
it up. It came right up, but verifying the file systems took overnight.
The work is being created, the splitters and assimilators are working.
It will be a while before we catch up. Thank you for your continued
patience and support.
May 9, 2007
Our science database server died on Tuesday, May 1st.
We haven't been able to create new workunits since then (though we are still
accepting completed results). Sun is graciously
replacing this server. The bad news is, despite earlier claims, it won't be
here until Friday the 11th, which means the earliest we'll be creating new
work is Monday the 14th. Thank you for your continued patience! Updates,
discussion, and more information about this and other server-related topics
can be found in
Technical News.
May 4, 2007
Great news! Sun Microsystems is coming to the rescue
and will be replacing our inoperative science data base server. They are preparing
the machine now and will be rushing it to us on Monday. Once we have
the machine up and the database recovered, we can start sending work out
again. Details on the server crash and our recovery from it can be found in Technical News.
May 1, 2007
Happy May Day. Unfortunately for us it's been "Mayday! Mayday!" At 4:43 (PDT) this morning, our science database machine, thumper, became hasenfeffer. It currently refuses to acknowledge that it has any disk drives. Since the controllers are attached to the motherboard, major repairs will probably be required. No work can be created until this machine gets fixed. We are on the phone with Sun now in hopes of securing repair or a replacement. More info in Technical News.
April 30, 2007
Since the announcement of Gliese 581c
(the first possibly habitable extrasolar planet), we've been asked many times about
what we have seen during our observations of this red dwarf star.
Unfortunately, Gliese 581 is located just beyond the visible sky we
can see at Arecibo Observatory, so we actually made no such observations.
April 23, 2007
Arecibo Observatory is currently shut down for three months to
clean up corrosion on the telescope platform (which includes safe
removal of lead paint). SETI@home will continue to operate on
classic data, and we have a backlog of new multibeam data to
analyze as well. While not collecting data we'll have extra time to
work on Astropulse.
April 21, 2007
As we are close to distributing new data recorded with the multi-beam
recorder, we decreased redundancy levels for current data. In the near
term, there may be periods when it is difficult to obtain work.
Your BOINC clients should retry regularly on their own
and will eventually get data to process.
April 4, 2007
We are moving our database service around. Db_dump (stats) is off
for a couple of days..
March 5, 2007
This week our servers are being patched to include the new
Daylight Savings Time schedule. Certain services (web sites, data
transfers, etc.) may by off-line for short periods.
February 21, 2007
Yet another reason to run SETI@home - it can help
recover stolen laptops.
February 13, 2007
We are in process of making network changes which may have affected
your SETI@home client's ability to connect to our servers. If you are
having trouble, try this.
February 5, 2007
GridRepublic
has been selected as a finalist for the Web Awards
at the 2007 SXSW Interactive Festival. Please
click here
to cast your vote for them at the SXSW website.
February 1, 2007
We're currently in the middle of network/database testing.
Connections to our web and data servers may be intermittent.
January 15, 2007
We are experiencing a database problem that is leading to erratic
work distribution. We will run diagnostics
and rebuild the affected tables(s) tomorrow.
January 6, 2007
MySpace members: check out the
BOINC on MySpace group.
January 3, 2007
We recovered from database problems over the past weekend. This
was resulting in erratic workunit downloads. More in Tech
News.
December 4, 2006
BOINC's new Online Help system
lets you get help from volunteers
by talking with them using Skype.
Volunteers speak several languages.
December 4, 2006
SETI@home Classic users:
you can now
transfer your workunit totals to your SETI@home/BOINC account,
even if you lost your Classic password.
November 7, 2006
Check out new add-on software:
the SETI@home Toolbar
for Firefox and IE on Windows, and
Boinctray,
a system tray application for Linux.
November 5, 2006
Vote for SETI@home (or not) in the
BOINCcast.de screensaver contest
(in German). UPDATE: SETI@home wins in the Natural Sciences
division, edging out QMC at home.
Vote tally is here.
November 3, 2006
Dr. Eric Korpela was interviewed by Graeme Knight
(a Post Graduate Astronomy student with
Swinburne University, Victoria, Australia).
Eric explains how SETI@home works, how the data is processed
and the possibilities of finding ET.
Download the MP3 file (11.8 MB).
The interview was recorded at the studios of
Radio KLFM.
October 25, 2006
Check out this SETI@home wallpaper from Scott Linder:
October 15, 2006
We had a couple minor server issues over the weekend.
Details in Technical News.
October 4, 2006
Eric Korpela and David Anderson were interviewed today
by Mike O'Connell of BOINC UK.
Many topics were covered, including the question of
credit and optimized clients.
Download a recording of the conversation (MP3, 13.5 MB) from
BOINC UK
or a mirror at Berkeley.
October 4, 2006
Update: We are wrapping up a database upgrade and ran out of work
to send out. However, we are now finally creating more. Expect heavy traffic
on our servers.
September 12, 2006
If you're interested in donating time -
rather than computing power - to help Astronomical research,
check out Clickworkers
(from NASA Ames Research Center)
and Stardust@home
(from UC Berkeley Space Sciences Lab).
September 11, 2006
Outage update: Though we moved a bulk of the data onto the new science
database server over the weekend, there is still plenty to do before
we can start using this new server. In the meantime, we may be able to
start creating new work to send out later today.
September 8, 2006
The Planetary Society article on the new multibeam
receiver and data recorder is now available
as an MP3 file,
thanks to the efforts of BOINC UK.
September 8, 2006
We ran out of work to send out due to our science database going down.
More details in Technical News.
September 4, 2006
Check out the screensaver background image
submitted by a user (and send us your own).
August 24, 2006
GridRepublic,
which lets you manage your account on SETI@home
and other BOINC projects, recently moved into beta test.
It was written up by CNET.
August 21, 2006
Teams may now order
SETI@home T-shirts and mugs with their team logo added.
August 14, 2006
Read the latest
science
newsletter from the Planetary Society about our new
multi-beam receiver.
July 28, 2006
Spread the word about SETI@home -
send email to your friends and family.
July 22, 2006
BOINC user survey:
due to a bug in our software, answers to the question
'Which are the most important factors when you decide whether to participate in a BOINC project?' were not recorded correctly.
Please fill out the survey form again.
We apologize for the inconvenience.
July 15, 2006
Please fill out the BOINC user survey.
Your responses will help us improve SETI@home.
July 14, 2006
We had a power glitch this morning that brought down our
science database. The assimilators and splitters are off
while we run checks on the tables.
July 7, 2006
Last night we had a lab-wide power outage to diagnose
electrical problems in a nearby facility.
More detail available in Technical News.
June 15, 2006
Last week the new multi-beam data recorder was installed
at Arecibo Observatory and has already taken some data. A science newsletter with
more details is forthcoming.
June 2, 2006
There will be a brief outage today at 17:00 UTC for database maintenance. We estimate the data servers and web pages will be offline for 2 hours, after which the usual "catch up" period will follow.
May 30, 2006
The SETI@home store is now open.
Buy unique SETI@home items - coffee mugs, T-shirts, caps, space pens and more -
all with SETI@home logos and graphics.
Part of the proceeds go to support SETI@home.
May 30, 2006
At 13:30 UTC yesterday the SETI@home upload/download server failed. We've solved the problem, so you should be able to upload results and download new work at this time. There will probably be a long period where the servers are overloaded with backlogged requests. Thank you for your patience.
May 17, 2006
The costs of electricity, both monetary and environmental,
are increasing.
Be aware of the
energy considerations
associated with SETI@home and volunteer computing.
May 16, 2006
All of our splitters have been altered to create workunits for SETI@home enhanced. Thanks for your patience during this transition.
May 16, 2006
A cascade of problems today caused inability to return results and later, the inability to download new work. One of the data servers lost the ability to see the upload directory. After reboot, it temporarily lost the ability to see the entire network.
May 14, 2006
An excellent Catalan-language site,
www.seti.cat,
has recently opened; check it out.
May 11, 2006
A scene in the new television film, Mammoth (Sci-Fi Channel), prominently features the SETI@Home screensaver. Access the clip here
May 8, 2006
The first SETI@home fundraising drive has drawn to a close. Thanks to your help, we've raised over $250,000 for continued operations, about one-third of our total goal. Because of this we've been able to complete and release our SETI@home Enhanced application. In addition, in June we will be going to Arecibo to install the new Multi-beam data recorder. If you haven't yet donated, please do.
May 4, 2006
We've started distributing work for a new version of SETI@home called
SETI@home Enhanced.
April 26, 2006
Last evening a problem developed on the scheduler host that caused
work distribution to slow and then stop. This has been fixed. However,
the number of unsent results is low so work distribution may still be
spotty for a while. This will correct itself.
April 22, 2006
SETI@Home Chief Scientist Dan Werthimer will be giving a free, public
talk about SETI and SETI@Home today on the UC Berkeley campus at 1pm.
You're invited to join him in Room 120 Latimer Hall on campus.
Also, the SETI Lab will be open for visiting and short tours between
11:00am and 3:00pm.
That's in Room 325 at the Space Sciences Laboratory behind the
University.
April 18, 2006
We're not sure what they're for,
but 'kinhull' made a set of
SETI@home stamps.
Also, Marco Sunder recorded a song
Don't you hear us?
about elusive aliens.
April 17, 2006
Our regular Wednesday maintenance outage has been moved to Tuesdays beginning this week. We're doing this to accomodate a number of scheduling conflicts that prevented all of the engineers from being available during the outages.
April 4, 2006
We're now over $225,000 so far during our
first annual fundraising drive. Thank you for your
help so far! Please help us reach our goal by
contributing today.
April 3, 2006
BOINCstats.com is one of
several excellent web sites showing the statistics
of SETI@home and other BOINC projects.
It's available in a number of languages, now including
Chinese.
March 9, 2006
Added a link detailing future plans
to the about SETI@home page.
March 4, 2006
Our master science database has been checked and is OK. We
are (as of yesterday evening) sending out new work.
March 3, 2006
Our master science database recovered from an unexpected
power outage Tuesday morning, but we are still in the process
of thoroughly checking the data.
More in Technical News.
February 19, 2006
BOINCcast
is the first German Podcast about BOINC.
Weekly episodes of 5 minutes length will explain Distributed Computing
and the Goals of BOINC to the German public,
and will present and explain the projects that use BOINC.
February 14, 2006
BOINC and Climateprediction.net have joined forces with the BBC
to launch a new experiment, a full simulation of climate change
from 1920 to 2080, described on
a BBC television documentary Meltdown
(BBC-4, February 20th, for UK BOINCers).
SETI@home participants can attach to
http://bbc.cpdn.org
(be warned that a 160-year climate simulation is a long workunit even
by Climateprediction.net's extravagant standards).
February 6, 2006
BOINC lets you mix in other scientific computing with SETI@home.
For example, check out
SIMAP,
a new project from the Technical University of Munich.
SIMAP calculate similarities between proteins,
and supplies the resulting data
to many bioinformatics research projects.
Or join the
SZTAKI Desktop Grid,
from the MTA-SZTAKI Laboratory of Parallel
and Distributed Systems in Budapest, Hungary, which is attempting
to find all the generalized binary number systems.
January 20, 2006
We finished our science database merge (consolidating all
data from Classic SETI@home and SETI@home/BOINC) and are
back online serving workunits. Our servers may be overly
busy trying to create/send work for a day or two. More
information in Technical News.
January 16, 2006
It looks like we may be experiencing local SSL network
problems again. If so, this will likely be fixed tomorrow.
Today is a university holiday. In the meantime there will
be intermittent problems contacting the scheduling server.
January 14, 2006
SETI@home Classic users: if you've been unable to link
your BOINC and Classic accounts (with the error message
'No SETI@home/BOINC account with Classic
ID xxxx was found') please try again;
we fixed a bug in the script.
January 13, 2006
There have been numerous but very brief network drop outs over the past few days
affecting all of the Space Sciences Lab. This turned out
to be a problem with the SSL firewall and is hopefully fixed
at this point.
January 5, 2006
The final SETI@home Classic work totals have been
copied to SETI@home/BOINC, and are shown on User Pages.
January 5, 2006
The outage is over, but there will be a long period of time
as our servers work hard to catch up. Connectivity will be
intermittent as we return to normal.
More about it in Technical News.
December 23, 2005
Yesterday we stopped accepting results for SETI@home Classic.
The Classic project stats are now frozen.
December 15, 2005
A story
about SETI@home's transition to BOINC appears in the Nature web site.
December 15, 2005
After 6 years of operation,
SETI@home Classic sent out its last workunit.
We will clean up and synchronize the Classic stats with the current
SETI@home project in the coming weeks.
Thanks to all SETI@home Classic participants for their
tremendous dedication to the project.
You made SETI@home into something of lasting significance.
Read a brief history of SETI@home.
December 13, 2005
We are now successfully recovering from a week of server
connection problems. Some connections may still break, but
most are getting through at this time.
We will be extending the deadline for returning results so that
the troubles with the result upload handler will not result in
lost credit. More in Technical News.
November 26, 2005
Windows users: if you were having problems attaching to SETI@home,
please download new client software (5.2.12) and try again.
We have fixed some problems involving personal Internet Firewalls.
November 26, 2005
You can now attach to SETI@home using your account key,
without setting a password first.
(This is a server change - no client download needed.)
November 25, 2005
We are getting reports of problems attaching to SETI@home,
and are working to resolve them.
Please go to the
Questions and Answers area for help.
November 22, 2005
We recently had some problems with busy web servers. This is
clearing up now. More info in Technical News.
November 18, 2005
The official SETI@home Certificate frame
is on sale for $34.95!
Get one before they're gone.
November 15, 2005
The old SETI@home Classic project
will stop issuing work on December 15, 2005.
Anyone still running SETI@home Classic should deactivate it
and install SETI@home/BOINC (see instructions under
'Getting started' on this page).
November 14, 2005
Tomorrow we will start merging the SETI@home classic
science database with SETI@home/BOINC. This will take
several days, during which some back-end servers will be offline
(splitters and assimilators). We stored up a large queue of
work - we are hoping this will keep all BOINC clients occupied
during the outage.
Progress will be detailed in Technical News.
November 1, 2005
Give your computer some variety - check out
Rosetta@home.
This new BOINC-based project aims to solve the ab initio
protein structure prediction problem,
and to design new chemical catalysts and potential HIV vaccines.
Participants who found the lowest energy structures have already
been acknowledged in a scientific paper describing the results.
October 26, 2005
Version 5.2 of the BOINC client software has been released.
It lets you attach to projects,
and log in to their web sites,
using email address and password, instead of account key.
Users have not chosen a password may do so
here.
October 14, 2005
Our upload/download server is no longer dropping connections.
We had the validators off overnight to hasten the recovery.
They are now back on.
October 13, 2005
Our upload/download server has been dropping connections
since yesterday's regular outage. We are not yet sure
what the bottleneck is. It may be that our load of
old-but-undeleted results and workunits has passed some
threshold. We'll be cleaning this up parallel to normal
operations. At this point, the connection drop rate is
decreasing and should reach zero by the end of the day (PDT).
September 27, 2005
Rocky Cudd, a long-time SETI@home participant
and active community member, passed away recently.
We honor him as User of the Day.
He'll be remembered.
September 20, 2005
SETI pioneer Carl Sagan's groundbreaking series COSMOS
is returning to television on The Science Channel.
The first two episodes premiere on Tuesday Sept. 27
at 9 and 10 PM (ET/PT),
with subsequent episodes airing every Tuesday night at 9 PM.
September 20, 2005
Message board postings and user profiles have been converted
from HTML to BBCode. You might need to tweak your profile
to make it look right.
September 9, 2005
Now when you donate to SETI@home,
a 
will appear next to your user name
on this web site (unless you choose to remain anonymous).
September 9, 2005
Outage Notice: We are still in the middle of an outage
to reconfigure our upload/download file systems - the copying
of data is taking longer than expected.
Uploads and downloads will be unavailable at this time.
This should vastly improve our general system performance.
More information in Technical News.
September 6, 2005
SETI@home Classic will process its
two billionth workunit today.
Congratulations to everyone for this achievement.
September 3, 2005
A number of accounts were accidentally deleted on August 26,
causing users to get 'Invalid or missing account key' messages.
These accounts have now been restored.
We apologize for the inconvenience.
August 31, 2005
Most of the servers are back up, but still dropping a lot
of connections as we recover from a week-long outage.
More information in Technical News.
August 26, 2005
You can now log in to this web site using
your email address and a password of your choice.
Set your password here,
BOINC is being changed to use email/password
instead of account keys (the long random strings)
to identify accounts.
This is detailed
here.
August 19, 2005
Outage Notice. Starting on Monday, August 22, we will be having
daily 3 hour outages for a few days. This will allow us to clear
the upload directory of old results. The outages will begin at 17:00
UTC. See Technical News.
August 18, 2005
Outage Notice. We have gotten word that there will be a 2 hour lab wide outage
starting August 19 at 01:00. That's just in a few hours. The outage is to repair
a faulty router. The web site and the scheduler will be off the air.
August 17, 2005
Outge Notice. We will be having a 1 hour outage tomorrow starting
at 17:00 UTC
to test the deletion of old result files. See Technical News.
August 11, 2005
There is a hardware problem with the building network here
at SSL. This is affecting the scheduling and web servers. You
may see intermittent connection problems. The SSL network
folks are working on a fix.
August 10, 2005
We are just now coming out of our regular weekly outage (which
took a bit longer than expected). More news eventually be posted
in Technical News. Until then, servers
may be clogged as the backlog of work clears.
August 7, 2005
We are back up after the power outage. Some backend services
will remain off until the initial demand dies down.
August 4, 2005
Outage notice:
We will be having a 14 hour outage, starting this Sunday (August 7)
at 02:00 UTC, because of major electrical work being done at the lab.
July 26, 2005
We recently made a DNS switch affecting the scheduler. This and more
can be read about in detail in Technical News.
July 22, 2005
We are looking for ways to boost workunit production See
Technical News.
At the current time the system having difficulty meeting
demand a number of clients are getting No Work from Project
messages.
July 19, 2005 Update
We now have the new data server online. It has 3x the capacity of the
old one. Details will be appearing in Technical News.
This should help clear the backlog of result uploads.
July 19, 2005
We are still trying to figure out if there is a software reason
for the connection drops that are causing the upload and download
failures. We are also working on a hardware solution in the
form of a more powerful data server machine. There are several
steps to getting a new machine online but, barring any show stoppers,
we hope to have it online in the next day or so.
July 15, 2005
The data server is continuing to drop connections, which is very unusual
this long after an outage. We are working to figure out why.
July 12, 2005
We safely restarted the project after an all-night (planned) power outage.
It will take significant time for the servers to catch up. More info in
Technical News.
July 7, 2005
Read the new Planetary Society newsletter:
Analyzing Signals
in Real Time.
July 6, 2005
We had a four-hour outage this morning for database backup and UPS maintenance (one hour longer
than expected).
June 30, 2005
The file upload handler crashed last night, but is back up and running now.
June 25, 2005
BOINC statistics sites continue to evolve.
Check out Every Earthly Hour, developed by Hydnum Repandum
June 23, 2005
Update: Today's outage is postponed with the date TBD.
June 22, 2005
Outage Notice. We will be having an outage tomorrow for UPS
maintenance. This will start at 17:00 UTC and should not
last more than an hour.
June 22, 2005
We have released the SETI@home application version 4.18 for windows
and Mac OS X. Graphics are now available for Mac OS X.
The Windows release fixes an ATI graphics bug.
June 21, 2005
Outage Notice. We will be having an outage tomorrow in order to back up
the database. The outage will start at 17:00 UTC and last two to three
hours.
June 16, 2005
Outage Notice. We will be having an outage tomorrow in order to add an
index to the result table in the seti/boinc database. This index will
be used to better track client errors.
The outage will begin at 17:30 UTC and may last up to 2 hours.
June 1, 2005
We are switching the http://setiathome.berkeley.edu/ URL
to point here.
The SETI@home Classic web site has been moved to
http://seticlassic.ssl.berkeley.edu.
May 26, 2005
The science database has been successfully relocated. The splitters and assimilator are
back online.
May 24, 2005
The splitters and assimilator are offline for a day or so while we relocate
the backend science database.
April 29, 2005
The DB reinit went fine. But then we had a problem with a recently installed
software firewall. It was working when we left the lab yesterday but cut
off the data service interface a short time later. We have switched off this
firewall for now. Software firewalls are now required for all machines by
campus policy but we will get an exception until ours is working. Note that
we are, and always have been, behind a hardware firewall that works great.
Given the length of this outage, service will be slow with lots of connection
drops until the backlog is cleared.
April 27, 2005
We will be having a general outage tomorrow to do a database backup and to
reinitialize our replica database server. The replica became corrupt last
week due to a disk space issue. After this is done, we should not have to
have outages for backups. We will start at 17:00 UTC. The outage will last
several hours.
April 25, 2005
In memoriam: Philip Morrison.
Professor Morrison pioneered the concept of interstellar communication in 1959, creating the field of SETI.
Phil will be deeply missed by the Berkeley SETI team.
April 20, 2005
There is an excellent document about the European connectivity issue along
with work around proxy information here.
Appreciation goes to setiathomer tigher for putting together this page and to many
others on the messages boards for contributing information.
April 18, 2005
We have confirmed that there is a known network peering issue between Cogent
(our ISP) and OpenTransit (France Telcom) that is affecting connectivity for
many participants in Europe. Campus has opened a trouble ticket with Cogent
but we are unsure that this will result in a fix. We will post news items as
we learn more. Many thanks go to the posters in this message board thread for their diagnostics and work arounds.
April 17, 2005
There are reports of a connectivity problem between some parts of Europe and
our Cogent facing server. We are making inquires. For discussion of the problem
and a suggested workaround using proxies, see
this message board thread.
April 11, 2005
Volunteers have ported SETI@home and BOINC to
a variety of platforms,
including Solaris/x86-64, Linux/x86-64, Linux/PPC, HP-UX, and FreeBSD.
April 4, 2005
You can now
select a language for this site
without changing your browser's language preference.
April 2, 2005
We have temporarily taken down 4.10;
it did not solve the graphics problem.
April 1, 2005
We have released version 4.10 of the SETI@home application for Windows.
This release fixes a bug that caused graphics not to display.
March 29, 2005
Now you can print a
SETI@home Certificate of Computation
that shows your Classic work, BOINC work, or both.
While you're at it, support SETI@home and
buy an Official SETI@home Certificate Frame.
March 23, 2005
SETI@home Classic participants: you can now
activate your SETI@home/BOINC account
(with your Classic work totals)
even if the email address of your Classic account
is no longer valid.
March 22, 2005
We're now fully back on-line. More information about
recent outages can be found in Technical News.
March 21, 2005
Our Internet link through Cogent went down at around
midnight UTC on March 18/19. It was repaired this evening, and the
servers may be bogged down as they try to make up for lost time.
We'll post more information once we're told what happened.
Please note that we still plan to have an outage tomorrow
morning (see message below).
March 18, 2005
The project will be down for 4 hours this coming
Tuesday, March 22, starting at 14:00 UTC. Our building
will be without power as campus tries to find the reason
for the power losses we experienced a couple of weeks
ago.
March 17, 2005
In preparation for shutting down SETI@home Classic
(in about 1 month, hopefully)
we're trying to make sure that SETI@home Classic accounts
are linked to the proper SETI@home/BOINC account.
This is a bit complicated because of email address changes.
See our current transition plan.
March 17, 2005
We have cleaned up our account database,
merging accounts with conflicting email addresses.
This may cause some users to get 'Invalid or missing account key'
messages. This is easy to fix;
instructions are here.
March 16, 2005
We have updated the SETI@home/BOINC database
with current information from SETI@home Classic.
March 12, 2005
Official SETI@home Certificate frames
are now available!
March 9, 2005
Star Trek is going off the air!
Read
here how Star Trek Helped Launch SETI@home.
March 7, 2005
All services are up and graceful shutdown in case of
a power outage is in place.
February 28, 2005
Around 18:00 UTC we had another unexpected lab-wide power outage.
The cause of these random failures is being investigated by campus,
but all our systems/databases survived without any corruption. We will
be down as we work to further protect ourselves. More info and updates in
Technical News.
February 25, 2005
The database has been restored and all services are back up.
The data server is very busy right now. There will be upload
and download problems until the load normalizes.
More info in Technical News.
February 23, 2005
Update: a breaker blew and the power for the entire lab was off for
several hours. Power returned at 23:30 UTC, but we will be dealing
with fallout for a while - the project will probably be down all night and
through tomorrow morning. More info in Technical News.
February 21, 2005
We are looking for volunteers to translate
the SETI@home web site into non-English languages.
If you're interested, learn more.
February 20, 2005
For data server updates, see Technical News.
February 19, 2005
The Einstein@home
project was officially launched this morning.
We encourage SETI@home users to also participate in this project,
which searches for spinning neutron stars (also called pulsars)
using data from the LIGO and GEO gravitational wave detectors.
February 19, 2005
We are still dealing with a data server storage problem. The project will
be going up and down as we work on this. See Technical News.
February 18, 2005
Update. Yet another data server array hang. The vendor is looking into it.
The project has been up for several hours although the data server
is a bit overwhelmed with pent up demand. We are adding services
back one at a time while we monitor the data server storage array.
February 17, 2005
Update. Once the RAID rebuilds we are going to run a job to delete
old workunits and results from the array. These would normally be deleted
by the file deleter but the latter is still backed up from before the database
migration. The project will remain off through all of this.
The data server failed around 20:30 UTC for the third time in as many days.
The project will be down as we continue to diagnose the problem.
February 15, 2005
The RAID resync is complete and the project is up, although
the data server is a bit overwhelmed at the moment. In positive
news, the new database server is running great (today's malfunction
was not on that machine).
February 10, 2005
We have moved the primary database service over to the the new system.
See Technical News.
February 7, 2005
The initial migration of the database to the new server is complete.
Tomorrow we will make this new server a database replica. If all
goes well it will become the database primary in a few days.
February 4, 2005
We will restart the database migration to the new hardware
Monday, February 7, at 18:00 UT. The outage will be several hours
long.
Currently, workunit production is falling behind demand. The
splitters themselves are able to keep up but are not able to insert
work fast enough because of competition for database access.
February 3, 2005
The project was offline most of the day today due to a
database problem.
February 1, 2005
We have created a new
SETI@home bookstore
in partnership with Alibris.com.
Find great books, read about science (fact and fiction),
and benefit SETI@home!
January 31, 2005
The DB migration stopped when the new server crashed.
See Technical News.
January 30, 2005
We will begin the migration to the new hardware at 19:00
UT tomorrow, 1/31. The project will be down for several
hours.
January 28, 2005
We have turned on db_purge in preparation for the DB
migration to the new hardware. This will reduce the
size of the DB and so the migration will go faster.
The validator will probably fall even more
behind in the meantime. The migration will occur early
next week. We will post the time once we have pinned it down
January 26, 2005
Due to recent database problems, we had to turn off
XML stats generation for the time being.
January 20, 2005
We're looking for a Certificate of Appreciation
design based on the new SETI@home logo.
If you know PHP and do graphic design,
maybe you can help.
January 6, 2005
The validation backlog is slowly clearing. There appears to
be no problem with validation other than the slowness the backlog
itself is causing.
January 4, 2005
We are still running a backlog of results waiting to be validated
and are looking into it.
December 31, 2004
The waiting for validation/transition counts on the
server status page are disabled
until we diagnose a recent DB slowdown.
December 28, 2004
We have decided to send out 4 copies of each workunit
and use a quorum size of 3 for validation.
Validation should be quick because a single result in error
will not delay reaching a quorum.
December 27, 2004
We have started removing database records for results
that were completed more than 7 days ago.
This will limit the size of the workunit and result tables
in our database.
Happy holidays!
December 27, 2004
We are experimenting with redundancy parameters.
We will continue to send 3 copies of each workunit,
but will validate results and grant credit
when 2 (rather than 3) of them are returned.
This should result in faster validation.
December 6, 2004
The project will be down for roughly the next 24 hours
while make some changes to the database structure.
[ Good news - changes are all done, and it only took 2 hours ].
November 21, 2004
Versions of BOINC and SETI@home for Solaris/x86
are available,
courtesy of Jochen van Waasen.
November 19, 2004
Windows application version 4.08 is released.
It should fix the graphics preferences problem.
November 18, 2004
We had an unexpected 3 hour outage this morning. More info
in Technical News.
November 5, 2004
SETI@home application version 4.07 is released.
This build should increase speed over the previous version.
October 27, 2004
The disk array has resynced and the scheduler is back on.
October 27, 2004
The disk array holding the upload/download directories crashed
last night. Until we are able to reboot and resync the drives,
the scheduler will be off (i.e. your clients won't be able to
connect to our servers). More details
in Technical News.
October 20, 2004
There was a two hour outage this morning for hardware upgrades.
Read more about it in Technical News.
October 19, 2004
SETI@home and BOINC are featured on Catalan TV news.
See the
Movie
(RealVideo) or the English transcript.
October 18, 2004
Each team now has a Create team account URL.
Accounts created through this URL will belong to the team,
and will have the project preferences of its founder.
Team founders: put this URL on your team's web page.
October 17, 2004
The web server was offline for a brief time (around 19:00 PST)
when its disk filled up. Files were cleaned up, old logs removed,
and everything is back to normal.
October 16, 2004
For the first time in a very long time the validator has caught up
on the large backlog of results waiting for credit. Of course, many
results still have pending credit until similar results are returned
by other users (and therefore cannot be validated yet).
October 14, 2004
Version 4.13 of the core client is now available. Version 4.12, which
contained various bug fixes, including one pertaining to file upload
problems, was released two days ago. Version 4.13 contains an
additional bug fix involving a rare case where user permissions
weren't being understood correctly by the client.
October 13, 2004
We added more data and informative text to our
Server Status page.
October 12, 2004
We just had (about 21:00 UTC) an unexpected outage due to a disk
crash. Everything is back up now.
October 12, 2004
Read more technical details about our project in the new
Technical News section.
October 12, 2004
This morning's outage lasted a bit longer than expected, but we are
now back up and running again. The outage was for reconfiguration
of the new replica database.
October 9, 2004
We added some new message-board features.
October 9, 2004
A problem with file uploads has existed for the last few days.
This problem causes file uploads to fail.
We now understand the problem and are working on a fix -
it will probably require upgrading your BOINC client.
Please stay tuned.
October 8, 2004
This morning a hardware failure caused one of our storage arrays
to require resetting.
Downloads will be temporarily halted until the drives have
completed re-synchronizing.
This should be complete in the early evening hours (Pacific Time).
October 6, 2004
There's been a problem with file uploading
for the last few days.
We think it is fixed now.
Our apologies if you lost work because of this.
October 6, 2004
The disk array holding the upload and download directories
failed yesterday and needed to be rebooted and resync'ed.
The project has been mostly down since last night, but as of
now it is back up and running.
October 5, 2004
UPDATED: We successfully swapped our database hardware, giving the
master database access to much faster disks. Within a couple hours
weeks-old queues drained completely. We're not completley done with
the swap, but all parts of the BOINC system are back up and running
full blast.
September 30, 2004
UPDATED: A new version (4.05) of the windows SETI@home client is available
(and will be automatically picked up by your core clients next time you
contact our servers). Changes include: the "heads up" mode now works and the
progress bar advances in a more linear fashion.
September 29, 2004
Learn how to customize SETI@home graphics.
September 28, 2004
A software error on our scheduling server made it impossible for any
schedulers to start. Clients were unable to connect
since yesterday afternoon. We tracked down the bug this morning and
fixed it. You should be able to connect to the schedulers now, though
there may be heavy traffic for a while (as the backlog clears up)
preventing you from getting through right away.
September 26, 2004
The upload directory move completed this morning and we turned the
file deleter and validator back on.
September 24, 2004
We have relocated the upload directory to off load demand from the DB
server. We are currently moving all of the old upload files (results)
to the new location. Until the move is complete the file deleter, validator and
assimilator need to be off.
September 23, 2004
The scheduler is back on. We are still investigating the transitioner lag.
September 22, 2004
Both the transitioner and the validator have fallen behind. We are
determining whether this situation is because of a software or hardware
bottleneck. In the meantime we need to allow these programs to catch up so the
scheduler is off over night. We are in the process of obtaining faster hardware
for DB server.
September 21, 2004
The upload of user-profile images
has been broken since July 22; it's fixed now.
September 19, 2004
Early this morning campus got a call from SANS that the seti@home classic web site
appeared to be hijacked. At that point campus (rightly so) blocked access
to our site at the campus router. As it turns out though, we were not
hijacked at all. Our nightly front page regen script had malfunctioned and
produced a truncated page. This is now fixed.
September 17, 2004
We have released a new version of the core client for all
platforms, this should fix the various issues with the
Win9x platform.
NOTE: If you are using a Win9x machine, please upgrade
to this release as soon as possible.
September 14, 2004
We have added
a web page showing server status.
The permanent link is under
Participate in SETI@home.
September 14, 2004
SETI@home is open source,
so you can port it to new platforms
or optimize it for specific architectures.
We have set up an mailing list,
boinc_opt@ssl.berkeley.edu, for people interested in this.
Details are
here.
September 13, 2004
Sometime last night the scheduling server (which handles all workunit/result
transfers) crashed. We're looking into what exactly
happened, but in the meantime it has been restarted and data is being
sent/returned normally.
September 10, 2004
The validator fix (see September 8, 2004) and an associated
transitioner fix have been implemented, tested, and placed
online. Credits are flowing.
September 10, 2004
We have added a number of new features to the message boards.
Details are here.
Thanks to Janus Kristensen for contributing this.
September 9, 2004
Stats are now available on your cell phone.
See 'Your Account' for the URL.
This feature was developed by Carl Christensen of CPDN.
September 8, 2004
Yesterday we discovered that when result files are lost, say due
to a restore from a backup (restores involve both the DB and the ULDL
directories) the validator ends up in a endless loop. The entire result
set for an affected workunit gets ignored and after a while the validator
ends up enumerating only affected workunits and is thus in a loop. We
turned off the validator when we discovered this. Today we have coded
a fix and are testing it in the alpha project. While the validator is off
credits are not given but they should show up once we turn the validator
back on.
September 7, 2004
We came up this morning and had to tune the data server to
keep connection drops from happening. The download/md5 errors
should no longer be occurring.
September 5, 2004
Because of the holiday weekend and family commitments we are
a bit short handed and short on time. So the uldl move is
taking us longer than expected.
September 3, 2004
The SnapApp folks were here for most of the afternoon. They replaced
the processors with ones that are faster and have larger caches. More
importantly, we talked about how to stabilize the system. The plan is
to simplify both the HW and service mix as much as possible in the hopes
of removing the variable that is causing the hangs (and of course they will
be going for the root cause at their lab). We altered the startup
so that a bare minimal set of services are running. And we are going to
only use the 18000 head unit for now, keeping no data on the sd30 expansion.
This means moving some data around. We first have to move the upload/download
data to a temporary volume on the sd30, then reconfigure the space on the
18000 head, then move the uldl to the head. The move to the temp volume
is happening now. Tomorrow morning we will do the reconfiguration and
start final move. With luck we will have the project up by EOD tomorrow.
September 3, 2004
Some technical folks from Snap Appliance are on their way
to SSL to provide on site support. They will likely swap
out the CPUs.
September 2, 2004
The Snap App hung again. We will be down for the night.
September 2, 2004
We have completed the SnapApp work around. We had a bit of a scare
with a volume mounting issue but once again Snap App gave us great
support and all seems fine at this point.
September 1, 2004
We will be having a short (less than 1 hour) data server
outage tomorrow at 16:30 UTC. We will be implementing the
Snap Applicance work around on the 18000.
August 30, 2004
Our storage array hung again (the SnapApp work around is not
yet implemented). It has not yet responded to a reboot command.
Data service may well be off until we can hard reset it tomorrow
morning.
August 30, 2004
We are investigating the Win98 hang/crashing issues in this
Thread
Please check it out for any updates.
NOTE: This bug puts your machine in a state that causes you
to reset your machine in order to be able to use it, this in turn can
cause disk corruption. We recommend that you hold off executing BOINC
on Win98 and WinME until this issue is resolved.
August 30, 2004
Climateprediction.net,
another BOINC-based project, is now open.
We urge all SETI@home to consider participating in
Climateprediction.net.
This will keep your computer busy (and earning credit)
even when SETI@home has no work available.
August 30, 2004
Starting with version 4, BOINC does 'time-slicing'
to divide CPU time between projects.
Learn more
here.
August 30, 2004
We are back up after restarting the Snap Appliance and making sure
everything is OK. We had a long conference call with the engineers
at Snap this morning they have come up with a work around as well as
a potential fix that should end the system hangs. Thanks go to the
Snap App folks for working very hard on this problem.
August 29, 2004
A fix to scheduler code to get around a possible memory leak
was causing it to bomb after a number of connections.
We have backed out this change for
now and the scheduler seems to be working OK at this point.
August 29, 2004
After fixing a few inevitable gotchas,
we are back up with the major version upgrade to 4.x.
The servers may be slow in responding as all clients will be
getting a new supply of work.
Everyone will need to download a new core client.
August 28, 2004
The migration plan has been rescheduled for tomorrow the 29th at 10am PDT. We
have brought down the scheduler and file upload handler until the migration
happens to give the splitters and transitioners time to produce enough workunits
and results to send out after the migration when the clients reset themselves.
August 27, 2004
The last set of hardware issues have been resolved. Due to the time of
day and other factors the upgrade will be delayed until at least tomorrow
morning. We'll post the revised schedule as soon as plans have been firmed up.
August 27, 2004
We are currently experiencing a hardware issue with our scheduling server,
we expect this issue to be resolved within the hour. The upgrade to 4.x will
start around 11am PDT and will take roughly an hour. Anybody who has any
remaining results to report should get them in before the upgrade.
After the
upgrade you'll need the 4.x clients to report new results, and upgrading to
the 4.x client will reset the project on your machine. Roughly 100,000
results are queued up and ready to be sent out after the upgrade, plus the
three splitters will be up and running producing work as quickly as possible.
August 26, 2004
We fixed the bogus URL bug and all servers are back up. If your cache is
empty of all valid workunits and you have any of the bogus workunits, then
reset the project.
August 26, 2004
We have brought down the splitters, transitioners, and scheduler until a
bug in the splitter can be resolved which was causing a bogus URL to be
posted for the work-unit.
August 25, 2004
A trio of splitters are now up and producing new work.
August 23, 2004
The validator is up and running and credit is now being calculated
for all those backlogged results.
August 20, 2004
We are currently working on getting the alpha/beta projects working again, as well
as getting new workunits generated so that when we restart the public SETI@home project
there will be work to send out to the clients.
August 19, 2004
The database has been restored and is being checked now. You may notice
that message board posts made in the past week are now missing - this is because
we had to fall back to an earlier copy of the database. Sorry for the
inconvenience.
August 18, 2004
We are now recovering the database from a snapshot made
a few days ago. This process will continue through tomorrow.
August 17, 2004
The project ended up running all night despite the dropouts, but this
afternoon we encountered a sudden raid failure that caused some data
corruption. The project will remain down until we recover the database.
August 16, 2004
Currently the project is up, as we were unable to recreate the
problems we were seeing on Friday. Now there are occasional dropouts,
but nothing devastating. We will keep everything running for the
time being, but may have to stop if problems arise.
August 16, 2004
Today we are continuing to work with Snap technical support to
solve our mounting problems. In the meantime, you may notice the
project being started/stopped for brief periods as part of our
testing.
August 14, 2004
We encourage everyone to run SETI@home Classic
during our server outages.
SETI@home Classic makes the same scientific contribution
as SETI@home/BOINC.
August 13, 2004
All the data has been copied to the Snap device. Both attempts to
bring the project online met with an unexpected NFS issue. Roughly
ten minutes after bringing the project online the NFS daemon drops
the mount point. Hats off to the Snap technical support team who
have been helping us work through this issue. We are still
investigating this issue and don't expect to be back online until
the beginning of next week. In the meantime everyone have a great
weekend.
August 12, 2004
The download directory is fully transferred at this point, but we
are still waiting for the upload directory to finish. We predict
it will finish late in the evening, and we'll start the project
fresh tomorrow morning.
August 12, 2004
The DB is now on the Snap Appliance and the web site is back up.
The project itself is still down as the transfer of the upload and
download directories is still under way.
August 11, 2004
The project is now down for the move of the DB and the upload
directory to the Snap Appliance. Along with the still running
download move, this will be a long process. We hope to be back
up midday tomorrow.
August 10, 2004
We have started the copy of the download directory to the Snap
Appliance 18000.
August 8, 2004
The servers are back up as far as receiving results but not as
far as distributing new workunits. We are simultaneously clearing
out the old download directory and preparing to move both it and the
upload directory to the Snap Appliance, along with the DB.
Allowing result uploads will ultimately speed both the deletion
of old workunits and results and the granting of credit. Credit
for the backlog of results will start being granted once we move
to the Snap Appliance and turn on the hierarchical directory structure.
August 7, 2004
The scheduling server is down while we work on a download storage
problem. This may take a day or so.
August 6, 2004
We developed a hierarchical directory structure to get around the
big directory problem (see August 4, below). This solution is backward
compatible with all current work units. It is being tested
in alpha now. Next week it will go to beta and then to public.
We also have a tool to distribute all recent results into the
new hierarchy. When that tool is run, credit will appear for
all of these results. The credit appearance will be spread over
a number of days.
In other news, we have the SnapAppliance 18000 configured. It
shows a 10x speed up over the software RAID we are now using. We
are awaiting a UPS for it.
August 5, 2004
A misconfigured scheduling server ran for about an hour this morning,
misinforming users that they had to upgrade to version 4 of the
BOINC software. This message was in error - please remain with version 3.
August 4, 2004
We discovered that the sheer number of files in the upload directory
was killing NFS performance for the file_upload_handler. We started
with a new empty upload directory and the file_upload_handler performed
much better. The rate of connection drops on the upload server dropped
to zero (most of the time). Of course we need to get all those older
results back into play somehow.
We are preparing our new SnapAppliance 18000 to host the database. We
need to fit it into the power load in our already fairly full data
closet, configure the DB volume, run some tests, and then copy over
the DB files. We will post the progress as we go.
August 3, 2004
While the project is up and functioning normally, the database and
web servers are overloaded. Because of this you may have noticed
difficulty in transferring work and loading certain web pages.
We're tuning these servers and trying to find the bottlenecks now.
August 2, 2004
The project remained down all weekend, but we are back up now.
To add insult to injury, the entire lab lost network connectivity
to the rest of the world for a few hours this morning.
In light of the unexpected length of this last outage, we are looking
into mechanisms that allow us to keep certain parts of the
project up while others remain down for repair.
July 30, 2004
The project is *still* down. The database cleanup for the bug
found on July 28 is going much slower than expected. We hope to
have everything back up later today or early tomorrow. Sorry for
the inconvenience!
July 28, 2004
The project is currently down. We found a bug in the scheduling
code such that returned results were not being updated in the
database. We are now running a fix script on the DB, marking
each affected result as unsent so that it will be resent.
Unfortunately, credit was not given for results affected by the
bug.
July 25, 2004
We have shutdown the schedulers and file upload handlers so the transitioners
can play catch up again. The transitioners keep falling behind because the DB
is I/O bound. We believe that the new hardware we have coming online will
resolve this issue. Until it is online we'll be continuing these rolling
blackout style server outages.
July 25, 2004
The project is down while we deal with a backup problem. We hope to be
back up soon.
July 23, 2004
The good news is that the scheduler is now running as a fast cgi
which means it maintains a persistent connection to the DB. The
load on the scheduling server has gone way down which is a good
thing and the mysql server is using more CPU which is also a good
thing. The bad news is that the transitioner is still way behind
and so the project will probably run out of send-able work as
early as 04:00 UT tomorrow. The transitioner is slow because the
mysql server is IO bound. We are having Sun look at our IO system
to see if it can be tuned to better performance. At the same time
we are planning on moving the physical DB to a high performance Snap
Appliance box in the near future. So we are hopeful that these IO
problems can be solved.
July 23, 2004
We are now up and running again, during the night we generated 400k
results to be sent out. Things might be a bit weird for awhile, somebody
decided to launch a denial of service attack yesterday afternoon.
July 22, 2004
We found and fixed the no results bug. It was a malformed
embedded SQL query. But we are leaving the scheduler off
overnight to let the transitioner work through it's backlog.
The transitioner works a great deal faster with a small
backlog and we hope yesterday's changes will go a long
way in preventing a large backlog from recurring.
July 22, 2004
Yesterday we introduced a bunch of performance enhancements to the
system. During the course of letting the system run overnight, we have
detected a bug that keeps results from being sent to hosts. It looks
at though this bug has only been around for about 13 hours. While we
are debugging this issue we have decided to shutdown the scheduler
and try and let the transitioners pick up the pace a bit.
July 21, 2004
The log files are currently being compressed, after thats done the
project should return to normal.
July 19, 2004
We have brought up an additional transitioner to try and cut through
the backlog we have accrued. Since the beginning of the project we have
already processed 2.7 million results. For comparison, the beta project
had only processed 6 million through the whole life of that project to date.
July 19, 2004
Sometime between 5pm and 12am PDT, the splitters seem to have
stopped producing new workunits. We have restarted the splitters
and they are back to creating new workunits.
July 17, 2004
A server bug was preventing
new results from being created in response to failed results.
If 2 out of 3 results for a WU succeeded and the 3rd failed,
the 2 successful results would not be validated or credited.
This is now fixed and the system will issue new results for
all workunits in this state.
July 13, 2004
Our database server hung and had to be forcibly terminated.
It took several hours to check all the tables and indices.
Then we ran into problems with our
Network Attached Storage device, which we rebooted
for the first time in 18 months.
Additional outages may occur throughout the night and possibly tomorrow.
July 9, 2004
It looks as though the server components
(splitter, transitioner, feeder, scheduler)
are now keeping up with demand.
July 8, 2004
Since yesterday evening we have distributed over
600,000 results. Thats a six-fold increase in
overall system performance from our previous best. Now it looks
as though we'll have occasional workunit shortages as we'll
have to bring additional splitters online to keep up with demand.
It's 8:50pm PDT and we have about 30,000 results in the queue, and we
are sending about 1,000 every 10 minutes. Currently
the splitters generate 4 workunits per minute which creates 12 results
per minute.
July 8, 2004
We have moved the scheduling server to another machine in
order to free up CPU and memory for the DB server. Active
clients will fail 10 times to connect to the old scheduling
server and then will self correct by contacting the master URL.
To force the correction right away, simply detach and then
(re)attach the project.
July 7, 2004
We're making some major changes to deal with
server performance problems.
The project will be shut down for several hours today.
July 2, 2004
We made some progress and are turning the project on.
You may still have problems getting work.
If that is the case, you might consider switching
back to SETI@home Classic for the next few days.
July 2, 2004
We've been having problems with server performance.
To address these problems we're making some changes to our database.
The project will be shut down most of today while this is being done.
June 30, 2004
Yesterday morning we shut down the front end of the system
to let the transitioners catch up with several days worth
of backlogged work, which is why some of you were noticing
three results and no credit assignment. During the down
time we also converted the scheduler into a fast-CGI
application. Upon bringing the system back up the new
fast-CGI scheduler decided to choke on something that it
hadn't choked on in Alpha. We are currently debugging the
new scheduler. We were able to get through 60% of the
backlogged work.
June 27, 2004
The web site has been reenabled.
We have several upgrades scheduled throughout
the week which should help with the performance problems.
If the project runs out of work again you are welcome to
revert back to the original SAH client.
June 27, 2004
We passed the safe threshold again,
so the web site has been shut down until Monday,
after we have had a chance to relocate some more infrastructure
services.
June 27, 2004
An additional transitioner has been brought online.
We are turning on the web site and will be monitoring the system.
We may have to shut it down again if traffic becomes too bad.
We are investigating further performance enhancements.
June 26, 2004
We are going to leave the project down until Monday.
We are going to bring back up the scheduler in an hour.
The transitioner was moved to its own machine and is
processing workunits at a much faster rate.
June 25, 2004
Memory for our web server was defective;
we are waiting on replacements before bringing it online.
June 25, 2004
The transitioner is not currently able to keep up with the splitters.
We are going to top the project to allow the
transitioner a chance to catch up with the rest of the system.
June 25, 2004
We added a second splitter and then hit the next bottleneck which
was the transitioner.
June 24, 2004
To handle increased demand for work,
we are bringing another splitter online.
June 23, 2004
We will be having a short server outage tomorrow at 17:00 UTC.
June 23, 2004
Read about SETI@home's
transition to BOINC
June 22, 2004
The URL of this project is http://setiathome.berkeley.edu.
If you joined using a different URL, please detach
and attach to this URL.
June 22, 2004
Version 3.19 of the BOINC core client for Windows is released.
Please upgrade.
June 22, 2004
Welcome to the new SETI@home!
The project is now officially active.
We've reset the project by deleting all results and workunits,
and setting all credits (user, team, host) to zero.
Thanks to everyone who participated in the
alpha and beta
tests for their help in debugging SETI@home and BOINC.
June 22, 2004
Our database server crashed yesterday,
and it's taken a while for the database to repair itself.
Some message-board postings and user profiles
may have been lost.
June 8, 2004
NOTICE: this project is not officially active.
Use at your own risk.
We may delete results and reset credits at any time.
June 5,
