Hi all. Am preety new and 'green' when it come to this BOINC stuff. Was just wndering that if this is distributed computing, could they not take advantage of the vast number of computers connected and distribute the 'Splitters' work? That way, the amount of WU's for people will not drop to the 6 that it was earlier.

Just a crazy thought

---

<img border="0" src="http://boinc.mundayweb.com/one/stats.php?userID=515&amp;prj=1&amp;trans=off" />

> Hi all. Am preety new and 'green' when it come to this BOINC stuff. Was just
> wndering that if this is distributed computing, could they not take advantage
> of the vast number of computers connected and distribute the 'Splitters' work?
> That way, the amount of WU's for people will not drop to the 6 that it was
> earlier.
>
> Just a crazy thought
>
No because the problem is it is THEIR computers that are bound up not ours. Meaning that THEIR computer is just too busy to do what it is supposed to be doing, so adding ANOTHER task would just make the problem worse.
They are trying to figure out why it is sooo busy, when they solve that, things should start to get back to normal.

---

> Hi all. Am preety new and 'green' when it come to this BOINC stuff. Was just
> wndering that if this is distributed computing, could they not take advantage
> of the vast number of computers connected and distribute the 'Splitters' work?
> That way, the amount of WU's for people will not drop to the 6 that it was
> earlier.
>
> Just a crazy thought

The problem is that the process performed by the splitters is to take data off of the tape and make it into workunits. If they read off the tape to send it to you to split, well, the remaining portion is still bound to the performance of the database.

---

All understood. They should just throw a few more computers onto the splitting side of things. Still, cant complain. Have just got stacks of WU's through. Should keep the temps up for the next week

---

<img border="0" src="http://boinc.mundayweb.com/one/stats.php?userID=515&amp;prj=1&amp;trans=off" />

At the end of the day they are the backbone of a giant network...and thats a lot of work. theyve gotta keep up with the creation, returning and validation of units!

---

<BR>AMD XP3200+
<img src="http://boinc.mundayweb.com/seti2/stats.php?userID=2327&amp;trans=off"><img src="http://petrus.homeftp.org/bws/counter_big.php?id=7828479">
<a href="http://homepage.ntlworld.com/paulandrew.odell/">MY SITE!</a>

> All understood. They should just throw a few more computers onto the
> splitting side of things. Still, cant complain. Have just got stacks of WU's
> through. Should keep the temps up for the next week


As you can read on the front page of the web site it is not a problem of splitters.. the database is too busy doing 'something' so the splitters can't feed the workunits into the database quick enough:

--quote--
The splitters themselves are able to keep up but are not able to insert work fast enough because of competition for database access.
--unquote--

---

> All understood. They should just throw a few more computers onto the
> splitting side of things. Still, cant complain. Have just got stacks of WU's
> through. Should keep the temps up for the next week
>
They _are_ planning to 'throw a few more computers' at the problem. There is a whole new server waiting impatiently in the wings for the migration to happen :)

PS : Do the MySQL devs know about the problem with the server churning? Maybe the project has accidentally stumbled across an 'undocumented feature' :)

---

Need help? Check out the excellent Unofficial BOINC-Wiki!
'We are the BOINC. Prepare to be assimilated.'

It sounds to me like one of the programs on the server is caught in a loop and stealing time from everything else.

---

98SE XP2500+ @ 2.1 GHz Boinc v5.8.8

And God said"Let there be light."But then the program crashed because he was trying to access the 'light' property of a NULL universe pointer.