Sorry, please ignore previous reply, the modified sysctl is still running, the output earlier, was from the stock binary. On 2021-02-09 14:25, Alastair Hogge wrote: > On 2021-02-08 21:01, Hans Petter Selasky wrote: >> On 2/8/21 1:53 PM, Alastair Hogge wrote: >>> Boot to multi-user; login (getty): >>> $ doas kldload /boot/modules/amdgpu.ko >>> $ sysctl >>> [panic] >>> >>> ..is a guaranteed way to panic my system. >> >> Hi, >> >> Maybe you could do a hack and edit the sysctl source code: >> >> 1) print the sysctl before it is queried. >> 2) sleep 1 second between print and query. >> >> Should be easy to nail this down! > > This is all I am able to catch via the ssh session: > vm.uma.sackhole.size: 32 > vm.uma.hostcache.stats.xdomain: 0 > vm.uma.hostcache.stats.fails: 0 > vm.uma.hostcache.stats.frees: 0 > vm.uma.hostcache.stats.allocs: 0 > vm.uma.hostcache.stats.current: 0 > vm.uma.hostcache.domain.0.wss: 0 > vm.uma.hostcache.domain.0.imin: 0 > vm.uma.hostcache.domain.0.imax: 0 > vm.uma.hostcache.domain.0.nitems: 0 > vm.uma.hostcache.limit.bucket_max: 7680 > vm.uma.hostcache.limit.sleeps: 0 > vm.uma.hostcache.limit.sleepers: 0 > vm.uma.hostcache.limit.max_items: 15360 > vm.uma.hostcache.limit.items: 0 > vm.uma.hostcache.keg.domain.0.free_items: 0 > vm.uma.hostcache.keg.domain.0.pages: 0 > vm.uma.hostcache.keg.efficiency: 98 > vm.uma.hostcache.keg.reserve: 0 > vm.uma.hostcache.keg.align: 7 > vm.uma.hostcache.keg.ipers: 42 > vm.uma.hostcache.keg.ppera: 1 > vm.uma.hostcache.keg.rsize: 96 > vm.uma.hostcache.keg.name: hostcache > vm.uma.hostcache.bucket_size_max: 120 > vm.uma.hostcache.bucket_size: 120 > vm.uma.hostcache.flags: 0x43010000<TRASH,LIMIT,CTORDTOR,FIRSTTOUCH> > vm.uma.hostcache.size: 96 > vm.uma.syncache.stats.xdomain: 0 > vm.uma.syncache.stats.fails: 0 > vm.uma.syncache.stats.frees: 1 > vm.uma.syncache.stats.allocs: 1 > vm.uma.syncache.stats.current: 0 > vm.uma.syncache.domain.0.wss: 3 > vm.uma.syncache.domain.0.imin: 0 > vm.uma.syncache.domain.0.imax: 0 > vm.uma.syncache.domain.0.nitems: 0Received on Tue Feb 09 2021 - 05:32:59 UTC
This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:41:27 UTC