Hi Jim, Yes, I figured a minimum of 2 years to completely re-write and test. I bumped into the new VPM work 2 weeks ago teaching a solaris internals course, but didn't give it a good look (the labs I do in the course with VM still work). I guess I'll take a closer look. Do you know if any of Eric Lowe's work is going into this? (I may not be correct, but I think it was Eric Lowe who made a presentation with a slide that said, "Layers are for Cakes, not Operating Systems", or something to that effect).
thanks, max Jim Mauro wrote: > > Hi Max - There is nothing publically available (that I am aware of) on > the > VM 2.0 effort. As you can imagine, it's massive, with changes making > their > way into Solaris today as part of the move to a new virtual memory > system. > > For example, the VPM (vnode page mappings) work that is now in NV > (http://cvs.opensolaris.org/source/xref/onnv/onnv-gate/usr/src/uts/common/vm/vpm.h), > > > represents a step towards VM 2.0. > > I'm not sure what the timeline is on getting to the whole enchilada, > but I'm > thinking it's at least another 2 years or so... > > Thanks, > /jim > > > [EMAIL PROTECTED] wrote: >> Hi Bart, >> Bart Smaalders wrote: >> >>> adrian cockcroft wrote: >>> >>>> Why can't you adapt ZFS for swap? It does the transactional >>>> clustering of random writes into sequential related blocks, >>>> aggressive prefetch on read, and would also guard against corrupt >>>> blocks in swap. Anon-ZFS? >>>> >>> This is planned as part of the VM 2.0 project. Note that the plan >>> is to >>> use a DMU object per address space or one per segment of an address >>> space. >>> >>> - Bart >>> >>> >> So, the VM 2.0 project. Is this a new memory management mechanism? >> If so, any documentation? I saw a >> paper by Erik Lowe (I think it was Erik?) about re-writing the memory >> management subsystem that he >> wrote about a year ago, but then nothing. >> >> thanks, >> max >> >> _______________________________________________ >> perf-discuss mailing list >> perf-discuss@opensolaris.org >> > _______________________________________________ perf-discuss mailing list perf-discuss@opensolaris.org
