staff blogs

distributed.net staff keep (relatively) up-to-date logs of their activities in .plan files. These were traditionally available via finger, but we've put them on the web for easier consumption.

2002-01-02

ivo [02-Jan-2002 @ 23:53]

Filed under: Uncategorized @ 23:53 +00:00

:: 02-Jan-2002 23:56 (Wednesday) ::

As you know, stats.distributed.net now points to blower, the new and
improved Quad Xeon beast in the United Devices data center.

Current blower status: – OGR has catched up until January 2nd, 2002 –
RC5 is catching up, yes, if you’re seeing something like
“Data shown reflects all blocks received as of 17-Dec-2001” we’re busy
catching up. While stats are on, hmm, processor power…

2001-06-15

ivo [15-Jun-2001 @ 15:01]

Filed under: Uncategorized @ 15:01 +00:00

:: 15-Jun-2001 15:02 (Friday) ::

The master backlog has been processed, but one proxy still has 1M blocks
in its outbuffer. It is expected that this will flush today or tomorrow.

After the weekend everyone’s total stats should be correct again.

2001-06-13

ivo [13-Jun-2001 @ 16:50]

Filed under: Uncategorized @ 16:50 +00:00

:: 13-Jun-2001 16:54 (Wednesday) ::

Yesterday, June 12th, we had some minor problems with our keymaster. This
resulted in backlogs on both the proxies and the master. As a result, the
stats for June 12th are not correct.

We hope to process all of the backlog soon, so your missing June-12-blocks
should show up in the next couple of days.

2001-03-23

ivo [23-Mar-2001 @ 15:14]

Filed under: Uncategorized @ 15:14 +00:00

:: 23-Mar-2001 15:24 (Friday) ::

FOR IMMEDIATE RELEASE ———————

Several distributed.net participants have expressed their concern with
regard to the distributed.net client and the recent outbreaks of
Foot-and-Mouth disease.

Some members asked if they could moove their computer with the cow client
on it, others were afraid to flush the cow, and thus spreading the disease
around the world, even to the master servers of distributed.net in the
United States.

distributed.net’s CCO (Chief Cow Officer) Jeff Lawson acted swiftly and
called his high school buddy EU Food Safety Commissioner Mr David Byrne.
Mr Byrne went great ways to grant distributed.net an exception to the very
strict transportation ban currently in place in large parts of Western
Europe.

distributed.net assures its members they can go on and flush as ever
before. There is no need to slaughter (kill -9) their cattle or let the
flushed blocks go to /dev/cesspool, as recommended by various national
governments in Western Europe. Also, piling up blocks and transport them
only after the crisis is over is strongly deprecated.

distributed.net wants to make very clear that the recent disease in some
cows, dubbed the “8012-flaw”, has nothing to do with the initial outbreak
of Foot-and-Mouth disease in England earlier this month, despite of rumors
circulating the internet.

If you suspect your cow is infected with the virus and want to be on the
safe side, go to http://www.distributed.net/trojans.html and download our
‘wormfree’ program. Be advised, though, that in most parts of the world,
virus vaccination of cows is forbidden! distributed.net will in no case
accept liability when participants get fined because of illegal vaccination.

2001-02-28

ivo [28-Feb-2001 @ 20:40]

Filed under: Uncategorized @ 20:40 +00:00

:: 28-Feb-2001 20:41 (Wednesday) ::

After Decibel’s plan from yesterday, there are some things that need
explanation. We’ve had a lot of complaints from DPC members that argued
that there was no organized megaflush going on and that the accusation
made by the DCTI staff yesterday was premature and partly false.

What seemed to be the cause for the backlog was individual team members
who saved up some blocks flushed them because they feared their 8012 blocks
would become invalid soon. A valid reason to flush, one would say.
Unfortunately it turned out that this caused a lot of blocks flushed at
the same time, blocks that normally would have been distributed over days.

Some remarks on this practice: It’s _not_ good to save up blocks. Even
when you do it only on your own or ‘just for a few weeks’. Why?

Our master is optimized for processing keys from 1 or at most a couple of
subspaces. Every subspace takes up 32MB paged-in memory. A lower number
of paged-in subspaces means a faster master. Due to the optimizations in
the code, even switching between in-core spaces means a huge performance
hit. As soon as the master process has a backlog of a couple of million
blocks from 20 or so different subspaces, it chokes.

Some people justify their flushing by saying: ‘But hey, if you can’t cope
the load of a couple of million blocks more per day, how are you going to
handle this in the future when these loads are normal?’ I hope above
mentioned explanation will show this reasoning is false for once and for
all. We have a perfectly capable master box, its specs are still way
adequate, load testing shows that when blocks are somewhat from the same
subspaces, we can easily handle 1000Gkeys/s with the current hardware.
Normally, blocks from unopened spaces are kept in a separate queue which
is processed at quiet times. When suddenly a lot of blocks come from a
lot of unopened spaces, that theoretical 1000Gkey ceiling jumps down to
a something below our current rate, hence the backlog which is very hard
to get rid of.

With this explanation I hope to have convinced people not to save up too
many blocks. Daily stats are what they are for: Daily rankings. Not for
getting a #1 spot for 1 day because you’ve saved up more or longer than
your friends. If you really want to be #1, just recruit more computers!

We try to suit as many participants as possible and we are very pleased
with all the enthusiasm distributed.net participants show. But if people
keep doing things against the policies set out by distributed.net staff,
we might have to take measures against it, by blocking people from stats
or changing the lifetime of a block. This is not because we suddenly
dislike those participants, but because we want the contests to be
satisfying for _all_ users. without backlogs, so everyone can have their
blocks tallied in time.

One more thing on backlogs: Backlogs don’t mean our system is broken, it
just means our system is handling the load sort of well. We do accept all
blocks, and never give a connection refused on our proxies. We _will_
process all those blocks in the end. Maybe not today, but eventually. So
in the end each and every blocks you flush will be counted. Your stats
total will reflect your total work done. And if we all take care in
flushing to the system as it was designed, backlogs will be kept to a
minimum and daily stats will be correct, too.

Keep on crunching!

2000-03-31

ivo [31-Mar-2000 @ 17:25]

Filed under: Uncategorized @ 17:25 +00:00

:: 31-Mar-2000 17:28 (Friday) ::

Hmm, it seems the planmailer still had a weird bug. Hopefully fixed now!
(for the ones not subscribed to plans@lists.distributed.net, this bug
caused all plans since the beginning of this system to be mailed out.
And in case I didn’t remove this bug completely, we now check for the
mailings not te be bigger than 10k in size, and if they are bigger, it
has to be approved by hand.

2000-02-11

ivo [11-Feb-2000 @ 16:33]

Filed under: Uncategorized @ 16:33 +00:00

:: 11-Feb-2000 16:38 (Friday) ::

.plan mailings are up again!

If you have no idea what I’m talking about, you can have the daily updates
from dcti-staff (like this one) mailed to you every night. Send mail to
majordomo@lists.distributed.net with “subscribe plans” in the body of the
message to enable these mailings.

2000-02-02

ivo [02-Feb-2000 @ 23:16]

Filed under: Uncategorized @ 23:16 +00:00

:: 02-Feb-2000 23:17 (Wednesday) ::

Well, this planupdate is mainly for two reasons: a) To let you know I’m
in the process of fixing the
nightly planmailings and b) To test-plan something so I can check if
my
fixing is any good

1999-11-18

ivo [18-Nov-1999 @ 00:09]

Filed under: Uncategorized @ 00:09 +00:00

:: 18-Nov-1999 00:14 (Thursday) ::

Wow, it sure has been a long time since I updated this plan.
Seems CSC is rolling allright! That’s why I took another look
at fetch@distributed.net and flush@distributed.net.
They now accept CSC blocks to flush and if you want to fetch
CSC buffers add “contest=csc” to your request.

1999-07-14

ivo [14-Jul-1999 @ 21:16]

Filed under: Uncategorized @ 21:16 +00:00

:: 14-Jul-1999 21:17 (Wednesday) ::

fetch@distributed.net and flush@distributed.net
can handle big blocks now, since the client behind
those scripts is build 443 now.

Older Posts »