2012-07-31 06:50:01 utc |
hartog |
jmettraux: good $localtime! |
2012-07-31 06:50:24 utc |
hartog |
I have some more work for you to review ;) https://github.com/jmettraux/ruote/pull/57#commits-pushed-09128ca |
2012-07-31 07:55:54 utc |
jmettraux |
hartog: answering your email now, I'll look at the new version immediately after |
2012-07-31 07:56:35 utc |
hartog |
jmettraux: there's nothing new in the new version - just forgot to remove the workitem and updated the docs a little bit |
2012-07-31 07:58:50 utc |
jmettraux |
hartog: thanks for the help with Jordi, that's much appreciated |
2012-07-31 08:09:48 utc |
hartog |
np; glad to be of service |
2012-07-31 08:12:17 utc |
jmettraux |
I have to leave soon |
2012-07-31 08:14:19 utc |
jmettraux |
it's starting to look ready, the return; rescue; return is a bit heavy, but well |
2012-07-31 08:16:06 utc |
jmettraux |
ok, I'll be back later... |
2012-07-31 08:19:52 utc |
hartog |
l8r! |
2012-07-31 08:57:00 utc |
marco__ |
good morning |
2012-07-31 08:58:30 utc |
hartog |
good morning! |
2012-07-31 08:59:51 utc |
marco__ |
hi hartog :-) nice to find you on this channel, seems you're deeply involved into ruote dev meanwhile? |
2012-07-31 09:00:20 utc |
hartog |
marco__: im becoming one of the campers ;) |
2012-07-31 09:00:53 utc |
marco__ |
I'm a bit frustrated currently to be honest with our implementation .. |
2012-07-31 09:02:27 utc |
marco__ |
I have problems to run ruote multithreaded with postgres -> results in 'to many connection errors' .. currently all participants connecting to postgres run with do_not_thread |
2012-07-31 09:04:29 utc |
hartog |
john is away now; perhaps he can help with that when he returns |
2012-07-31 09:04:30 utc |
marco__ |
anyway, I will write to the mailing-list later .. |
2012-07-31 09:06:19 utc |
marco__ |
my second problem is that the workers are too slow, even with 3 processes, when the engine hits some load, It took far to long to process important workitems in time .. how many ruote-workers do you run usually? |
2012-07-31 09:06:59 utc |
marco__ |
is there a way to 'reserve' a worker for specific participants ? |
2012-07-31 09:09:35 utc |
hartog |
ai; I cant help you there! |
2012-07-31 09:12:00 utc |
hartog |
btw; 'reserving' a worker for specific participants could be done using ruote-amqp |
2012-07-31 09:12:31 utc |
hartog |
then you could dispatch the workitem to the resource-intensive participant on the other end of your cluster |
2012-07-31 09:13:12 utc |
hartog |
but perhaps john has an easier solution :) |
2012-07-31 09:13:54 utc |
marco__ |
ok, thats an option, did you use ruote-amqp . . maybe we can meet for a drink in KA after my holiday ? |
2012-07-31 09:14:52 utc |
hartog |
i'm using something ruote-amqp'ish (and waiting for the rework branch to get finished ;)) |
2012-07-31 09:15:23 utc |
hartog |
sure! it has been to long since I left durlach and ventured near a starbucks ;) |
2012-07-31 09:18:31 utc |
marco__ |
haha :-) great! say hello to Martin, Di and Jiri! |
2012-07-31 09:19:28 utc |
marco__ |
if you want we can meet today or tomorrow afterwork .. or after my holiday (16.8.) |
2012-07-31 09:21:21 utc |
hartog |
then after your holiday |
2012-07-31 10:50:33 utc |
hartog |
marco__: did you look at http://www.pgpool.net/? |
2012-07-31 10:50:53 utc |
hartog |
(although; be warned: https://github.com/rails/rails/issues/1627) |
2012-07-31 11:50:48 utc |
jmettraux |
hartog: hello, your pull request is final? No more changes? |
2012-07-31 11:51:54 utc |
hartog |
I only have the acts-like-participant question still open |
2012-07-31 11:52:24 utc |
hartog |
it seems a matter of taste |
2012-07-31 11:53:09 utc |
jmettraux |
I'm sorry, I can't remember what question it is |
2012-07-31 11:54:13 utc |
jmettraux |
could you please enlighten me? |
2012-07-31 12:08:46 utc |
hartog |
sry; was distracted |
2012-07-31 12:09:34 utc |
hartog |
https://github.com/jmettraux/ruote/pull/57#issuecomment-7390881 - The SillyObserver code sample (and the text surrounding) |
2012-07-31 12:18:10 utc |
jmettraux |
aah |
2012-07-31 12:18:12 utc |
jmettraux |
well |
2012-07-31 12:19:06 utc |
jmettraux |
one way to do it would be to provide two sugar-coated observers |
2012-07-31 12:19:42 utc |
jmettraux |
the interesting thing with that SillyObserver is that it can be very lazy, we only compute/grab stuff like workitems when they are demanded |
2012-07-31 12:20:13 utc |
jmettraux |
somehow, may I delegate that to you? |
2012-07-31 12:20:27 utc |
hartog |
sure np |
2012-07-31 12:20:34 utc |
jmettraux |
please explore the possibilities, I'll just pull in when you think it's ripe |
2012-07-31 12:20:42 utc |
jmettraux |
and we can iterate |
2012-07-31 12:20:47 utc |
jmettraux |
ripe++ |
2012-07-31 12:21:15 utc |
jmettraux |
when the iteration frequency drops, we'll document it (website wise, hopefully rdoc should follow) |
2012-07-31 12:22:16 utc |
hartog |
i think it is ripe as-is and that the lazy observer could well be done in a 2nd pull request |
2012-07-31 12:26:41 utc |
jmettraux |
ok, https://github.com/jmettraux/ruote/pull/57 pulled in, many thanks! |
2012-07-31 12:27:17 utc |
hartog |
/cc: Thank you sir! For beeing such a good sparring partner (and teaching me some Ruby tricks!) |
2012-07-31 12:28:08 utc |
jmettraux |
:-) yeah, I love the "let's put in back in perspective" triggers |
2012-07-31 12:49:30 utc |
jmettraux |
escaping to bed now, thanks for the hard work! |
2012-07-31 14:07:25 utc |
hartog |
time to go home now |