14:52:25 hrm.. does split /usr still work when booting? I'd like to construct an iso image with a small boot archive and then mount a larger /usr off the ISO image (vs. having one larger boot_archive), but don't know if that's something that'd still work 15:52:51 [illumos-gate] 18285 Want c23 uchar.h functions -- Robert Mustacchi 16:01:21 jbk thats how OI is working (from install media) and smartos too. the catch is about getting /usr to be mounted - you have to have the needed bits in rootfs. 16:54:11 jbk: what tsoome said and you need the right scripts from slim_source in the exact right boot order disabling normal mounting or setup scripts. 19:40:07 jbk: might have more luck with a linux-y root pivot 19:40:18 as far as future proofing and such 20:05:05 the problem is because we still boot like it's 2005, making the boot archive too large causes problems 20:05:26 already have hit this with some AMD systems where their UEFI implementations don't leave enough contiguous memory free below 4G 20:05:53 so we can't boot because our boot archives are too large 20:10:39 jbk: need this with another distro than Openindiana when there is no disk to keep / ? All other archives have been 200MB max 20:11:15 it's not for openindiana 20:11:30 but the general AMD issue is true across every illumos distro i've tried 20:11:31 is there enough memory _somewhere_? 20:11:38 yeah... above 4GB 20:11:44 plenty there 20:11:49 and loader etc can't bounce and pull that off 20:11:51 eugh 20:12:10 no, tsoome has been working on it 20:12:15 loader itself can, thats no problem;) 20:12:16 but it's basically unsupported by multiboot 20:13:31 but also apparently dboot seems to have some deep implicit assumptions about how physical memory is laid out 20:13:49 the assumptions about memory layout are on the way - assuming I understand the problem correctly. 20:14:45 booting is hard, and we should stop 20:20:56 that too:) well, the boot as such is not the problem. the problem is keeping some sanity while doing so;)