Thanks Martin,

You've done very important work and have reached the result of making 
real-world "multiprocess" software run on top of a cloud hypervisor. 
Not many people in the world can claim the same (at least not yet! ;)

To further dissect your results, seems like the "app-tools" toolchain 
continues to work, and your "rumprun" tool is proving itself for running 
the images as services.  There were some minor hiccups, but the 
expectation of those will go away with a few more real world grade 
experiments -- if you take into account the lines of application code 
there were "practically" no platform bugs(!).  One important thing we 
need to start teaching service writers is to not needlessly waste 
resources (e.g. 512kB stacks) given that low-resource environments are 
coming.  Things have a natural tendency to consume ever resource 
available regardless of whether it is needed or not.  Starting to send 
patches against this type of arbitrary resource consumption will 
hopefully eventually result in an attitude change.  It's currently 
difficult to justify, given the "full OS" targets of the applications, 
multimegabyte stacks are not bugs per se, but we need to try.

So, as we've been discussing on irc, we're a database short of a RAMP(*) 
stack ;)

   - antti

*) my evil plan is to eventually have all software named after edibles

------------------------------------------------------------------------------
New Year. New Location. New Benefits. New Data Center in Ashburn, VA.
GigeNET is offering a free month of service with a new server in Ashburn.
Choose from 2 high performing configs, both with 100TB of bandwidth.
Higher redundancy.Lower latency.Increased capacity.Completely compliant.
http://p.sf.net/sfu/gigenet
_______________________________________________
rumpkernel-users mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/rumpkernel-users

Reply via email to