15:59:24 <gitomat> [illumos-gate] 18309 format: remove -Wno-clobbered -- Toomas Soome <tsoome⊙mc>
16:05:24 <gitomat> [illumos-gate] 18302 libsecdb crashes on memory exhaustion due to unchecked allocations -- Andy Fiddaman <illumos⊙fn>
16:05:24 <gitomat> [illumos-gate] 18303 pfexecd door thread pool grows without bound -- Andy Fiddaman <illumos⊙fn>
19:41:53 <richlowe> jbk, jclulow: turns out the linux pivot does much more than I thought.  what I'm in favour of is just mounting a real root filesystem normally, after we're done with the archive
19:42:08 <richlowe> maybe that comes off a USB and ends up in a ramdisk
20:39:04 <jbk> always fun with the panic handler itself locks up...
20:48:30 <richlowe> my best luck there is to break before the crosscalls
20:50:09 <richlowe> (but then you haven't really "panicked" and the debugger can be a bit odd)
20:50:40 <richlowe> but if I remember, anywhere before panicsys raises the spl is for the best.  even just `panic` or `vpanic`
21:04:24 <richlowe> (obviously for the _best_ is to not screw up page tables/interrupts/etc, so this isn't a problem)
21:16:00 <jbk> heh.. that's the thing, wasn't touching any of that (well possibly using interrupts, but not the interrupt infra itself)...i'm sure it's something silly..
21:47:07 <jbk> it's a debug kernel, so panic prints all of that extra stuff out
21:47:19 <jbk> i'm wondering if there's a timing bug w/ writing to a framebuffer and that
22:11:44 <jbk> also annoyingly... that tends to push out the actual useful contents of hte msgbuf on sytstems w/ large # of cores