The collected works of gtogl

Hello all,

I am in the process of porting the Zabbix Agent to IRIX, so that most sensors that work under Linux also work under IRIX.

Does anybody know if it is possible to access the information from the L1 Controller from an 3x00 machine or f.e. a Fuel from within IRIX? Some command I can't seem to find?

Another problem I have is determining CPU load. Parsing top isn't something I wanna do, since I think it's an ugly hack. Under Linux, I always get the CPU Load (and Zabbix does to) from /proc/stat, is there an equivalent under IRIX?

best regards and thanx in advance for all help provided!

tuo

ah, yes, l1cmd, now that I read it, I know I have seen this somewhere before! Thanx!!!

Concerning the load, sorry, my post was unclear. I mean the per cpu load percentage, not the "load" as in processes currently running.

Under Linux, you have the /proc/stat with the the amount of time each cpu spent on f.e. kernel tasks, user tasks, idle task etc. so you can easily calculate the % of cpu utilization, that's what I'm looking for.

But pcp sound very promising, I will look into that! Thanks for the help to both of you, much appreciated!

of course I'm interested, that would be great if you could post the code.

currently, I am working on a PHP Interface to the l1cmd, which automatically reads the configuration of the system from the l1, display the racks and bricks on a page and pulls status info for them. in active mode, it will even be possible to actively control the l1 (f.e. power up/down), but that mode should be looked upon by more than two eyes to prevent security issues.

I know that larger origin system have the l2 and l3 for similar things, it's basically just some playing around on my side, I want to extend the information my zabbix network is able to display for SGI systems with an l1.

so any code is greatly appreciated, and if anyone is actually interested in this PHP interface, I will put it up somewhere for download

wow, many thanks for the code

btw: that's exactly how I determin the % under linux, simply parse /proc/stats, sleep a second, parse again, compute difference, compute percentage.

and I guess that's how f.e. "top" works, because top always needs that first second before all the values seem sane

edit: your code works like a charm. I am currently writing a little script to compute the cpu % (among other things) and display it on the L1 display of the bricks, as soon as I'm finished, I'm gonna post it here if anyone is interested

Hi all, I just revive this thread instead of starting a new one.

I just installed Boinc with Seti as explained by nekonoko earlier in this thread, but I have some small problems on my Origin3400:

1) I often get this



How does Boinc detect wether a user is active? My machine currently has 16 R12K CPUs, which where at 99.5% idle while above message popped up.

2) The second problem is, that my client seems to post too many request too get any workunits at all. I always have entries like this:



It seems that my machine is asking for work two times in a row, which is then always answered with the "last RPC too recent: 6 sec".

I have it running for about two hours now, and while my x86-box is getting work-units without any problem, the Origin get's none.

Anybody experienced this problem before? And yes, I checked if there is a second instance of boinc running.

best regards and thanx in advance for any help

tuo

I sometimes get work on my Win-Machine, but it is far from satisfieing. I'd say it is working maybe 2 hours a day, the rest it is either waiting to get new units or to post completed units. And I have already played around with some settings as supposed in the official boinc/seti forum.

In the last 31 days, my winbox made around 7000 "points".

With Seti-Classic, my servers and workstations where working at 100% all the time.

The Origin - until now - didn't get any work units. at this very moment, my winbox also has the status "wartende scheduleranfrage", which I would translate to "pending scheduler-request"...the status it "works in" most of the time.

Is it just me or is Seti quite broken since it moved to Boinc? Is anyone here getting work units on a regular basis to keep their machine at 100% 24/7?

best regards

tuo

fixed the problem

I changed my boinc setting so that it runs always (didn't know I have to tell boinc this) and that it should keep a cache of 10 days.

first, my origin-client didn't update the settings, so I added them manually to global_prefs.xml

now everything works like a charm, three cpus currently at 100%, and I red in some forums that it takes some time until boinc uses all...*crossedfingers

thanx for the great help, dr.(how fitting ) dave

I found out how to change it just a few seconds before you postet, but your advice definitely made the difference. now everything works

at first - since the origin didn't update the global_prefs.xml - I thought I had to update it by hand (that's why I wrote that first, but editet my post after I noticed it DID update the file after a while).

thanx again

go to your settings page:

setiathome.berkeley.edu

Change the "General Preferences".

The somewhat misleading preference "Connect to network about every" has to be changed to ten. This does not mean that your machine will connect every ten days, but it will influence the caching behaviour, thus your machines will fill their cache with ten days worth of work units.

I also changed the settings to even work when there is user activity.

Now, you can either wait until your boinc client downloads the updated settings, or you can shut down the client and restart it with -update_prefs to get the on program startup.

After I changed this value, all my machines filled up their work unit cache to the max, and are crunching 24/7 since 2.5 days.