summaryrefslogtreecommitdiffstats
path: root/userspace/cuda/docs/06-tooling.md
diff options
context:
space:
mode:
authorArthur Hanson Rasmusson <arthur@vgpu.io>2026-10-23 16:33:48 -0400
committerArthur Hanson Rasmusson <arthur@vgpu.io>2026-10-23 16:33:48 -0400
commit127d41aae5a68f07c87785193cdf17469412ba1b (patch)
treee3a5b482e7c4bf6bca416c362193cd77b5d6c257 /userspace/cuda/docs/06-tooling.md
parent8cbb6003478d3a8ba1ee063dd1d207e252076a5d (diff)
downloadopen-iov-127d41aae5a68f07c87785193cdf17469412ba1b.tar.gz
open-iov-127d41aae5a68f07c87785193cdf17469412ba1b.zip
vgsp-sema r563b: the stall self-heal clears the walk-state blockers (force opdef flush + per-channel state)
r564 evidence: the STALL-DUMPs fired (4x, done=12700 held=727 frozen) but ZERO STALL-HEAL lines - the force-consume budget never engaged because the walk breaks BEFORE the instrumented hold sites (the cheap-wait unread window at the loop top, or a stale GR hold/nocap index). The self-heal now acts on the state every break site consults: - svc_opdef_force_flush(): deliver every withheld release forward-only, record the delivered marks (so a re-decode cannot re-hold), clear the slots - the same edge the 3 s bound would run, at the watchdog's discretion; - per channel (under chan_lock): unread_va/unread_until = 0 (the cheap-wait break), gr_hold_idx/gr_hold_until/gr_nocap_idx/gr_nocap_va reset; - the force-consume budget stays as the belt for the hold sites. One loud STALL-HEAL line per firing.
Diffstat (limited to 'userspace/cuda/docs/06-tooling.md')
0 files changed, 0 insertions, 0 deletions