Thanks Ben. I've been experimenting with --max_old_space_size, but so far this hasn't resolved my issue.
In the test i ran last night in the approximate sweet spot between too little memory (crash) and too much memory (thrash) for our conditions, performance was averaging around 12.5 minutes per bundle of work, still far from node 0.8.x, where we average around 9 minutes per bundle. This was with --max_old_space_size=208. I'm trying another run now with --max_old_space_size=192, as at 208 we still eventually exceeded the max memory of the virtual machine (1GB). Just to confirm my understanding: max_old_space_size helps at all with this excessive RSS usage issue by forcing more full GCs, and thus cleaning up non-heap allocations associated with heap objects (such as Buffers), correct? How much awareness does V8 have of non-heap memory usage? I see there is a --max_executable_size flag available. Would this help here? Is it worth looking at what non-heap allocations are building up, and if so do you have any tool recommendations for this? Anything else you recommend trying? Thanks! -- -- Job Board: http://jobs.nodejs.org/ Posting guidelines: https://github.com/joyent/node/wiki/Mailing-List-Posting-Guidelines You received this message because you are subscribed to the Google Groups "nodejs" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [email protected] For more options, visit this group at http://groups.google.com/group/nodejs?hl=en?hl=en --- You received this message because you are subscribed to the Google Groups "nodejs" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. For more options, visit https://groups.google.com/groups/opt_out.
