Re: [nodejs] deadlock, how to hunt it down?

2012-05-17 Thread Erik Dubbelboer
to send you the core so you can have a look yourself? Thanks in advance, Erik On Thursday, May 10, 2012 2:19:45 PM UTC+2, Ben Noordhuis wrote: On Thu, May 10, 2012 at 12:48 PM, Erik Dubbelboer e...@dubbelboer.com wrote: We have an application that handles a couple of http and udp requests per

[nodejs] deadlock, how to hunt it down?

2012-05-10 Thread Erik Dubbelboer
We have an application that handles a couple of http and udp requests per second. It uses no C modules, only modules written in javascript. From time to time the application will hang. Attaching strace at this point will only output lines of: futex(0x10e36c8, FUTEX_WAKE_PRIVATE, 1) = 1 As you

Re: [nodejs] deadlock, how to hunt it down?

2012-05-10 Thread Erik Dubbelboer
) /lib64/ld-linux-x86-64.so.2 (0x7fd790ee5000) On Thu, May 10, 2012 at 2:19 PM, Ben Noordhuis i...@bnoordhuis.nl wrote: On Thu, May 10, 2012 at 12:48 PM, Erik Dubbelboer e...@dubbelboer.com wrote: We have an application that handles a couple of http and udp requests per second. It uses

Re: [nodejs] Re: [PATCH] Add runtime accessor process.maxIOThreads

2012-03-02 Thread Erik Dubbelboer
On Thursday, March 1, 2012 11:50:21 PM UTC+1, Ben Noordhuis wrote: On Thu, Mar 1, 2012 at 22:16, Erik Dubbelboer e...@dubbelboer.com wrote: Hi Everyone, I was wondering what the status is for this API. I couldn't find anything in the current documentation so I'm guessing it hasn't been

Re: [nodejs] Re: [PATCH] Add runtime accessor process.maxIOThreads

2012-03-02 Thread Erik Dubbelboer
On Friday, March 2, 2012 5:11:04 PM UTC+1, Jorge wrote: Please note that time passes in parallel (N threads doing usleep()s in parallel are always going to be faster than MN threads running N usleep()s), but real disk I/O jobs even when ran in parallel in separate threads tend to be

[nodejs] Re: [PATCH] Add runtime accessor process.maxIOThreads

2012-03-01 Thread Erik Dubbelboer
Hi Everyone, I was wondering what the status is for this API. I couldn't find anything in the current documentation so I'm guessing it hasn't been implemented yet? If this is the case I guess I could take a look at it since it would really be nice to have this for machines with a lot of cores