"c1fbc251cd43f57703976219d84bfb31a5716cf8" (history) in projects: freebsd

Project(s)

Full Search
Definition
Symbol
File Path
History
Type

Searched hist:c1fbc251cd43f57703976219d84bfb31a5716cf8 (Results 1 – 4 of 4) sorted by relevance

/freebsd/sys/vm/
H A D	vm.h	diff c1fbc251cd43f57703976219d84bfb31a5716cf8 Mon Aug 16 08:16:12 CEST 2004 Alan Cox <alc@FreeBSD.org> - Introduce and use a new tunable "debug.mpsafevm". At present, setting "debug.mpsafevm" results in (almost) Giant-free execution of zero-fill page faults. (Giant is held only briefly, just long enough to determine if there is a vnode backing the faulting address.) Also, condition the acquisition and release of Giant around calls to pmap_remove() on "debug.mpsafevm". The effect on performance is significant. On my dual Opteron, I see a 3.6% reduction in "buildworld" time. - Use atomic operations to update several counters in vm_fault(). diff c1fbc251cd43f57703976219d84bfb31a5716cf8 Mon Aug 16 08:16:12 CEST 2004 Alan Cox <alc@FreeBSD.org> - Introduce and use a new tunable "debug.mpsafevm". At present, setting "debug.mpsafevm" results in (almost) Giant-free execution of zero-fill page faults. (Giant is held only briefly, just long enough to determine if there is a vnode backing the faulting address.) Also, condition the acquisition and release of Giant around calls to pmap_remove() on "debug.mpsafevm". The effect on performance is significant. On my dual Opteron, I see a 3.6% reduction in "buildworld" time. - Use atomic operations to update several counters in vm_fault().
H A D	vm_meter.c	diff c1fbc251cd43f57703976219d84bfb31a5716cf8 Mon Aug 16 08:16:12 CEST 2004 Alan Cox <alc@FreeBSD.org> - Introduce and use a new tunable "debug.mpsafevm". At present, setting "debug.mpsafevm" results in (almost) Giant-free execution of zero-fill page faults. (Giant is held only briefly, just long enough to determine if there is a vnode backing the faulting address.) Also, condition the acquisition and release of Giant around calls to pmap_remove() on "debug.mpsafevm". The effect on performance is significant. On my dual Opteron, I see a 3.6% reduction in "buildworld" time. - Use atomic operations to update several counters in vm_fault(). diff c1fbc251cd43f57703976219d84bfb31a5716cf8 Mon Aug 16 08:16:12 CEST 2004 Alan Cox <alc@FreeBSD.org> - Introduce and use a new tunable "debug.mpsafevm". At present, setting "debug.mpsafevm" results in (almost) Giant-free execution of zero-fill page faults. (Giant is held only briefly, just long enough to determine if there is a vnode backing the faulting address.) Also, condition the acquisition and release of Giant around calls to pmap_remove() on "debug.mpsafevm". The effect on performance is significant. On my dual Opteron, I see a 3.6% reduction in "buildworld" time. - Use atomic operations to update several counters in vm_fault().
H A D	vm_fault.c	diff c1fbc251cd43f57703976219d84bfb31a5716cf8 Mon Aug 16 08:16:12 CEST 2004 Alan Cox <alc@FreeBSD.org> - Introduce and use a new tunable "debug.mpsafevm". At present, setting "debug.mpsafevm" results in (almost) Giant-free execution of zero-fill page faults. (Giant is held only briefly, just long enough to determine if there is a vnode backing the faulting address.) Also, condition the acquisition and release of Giant around calls to pmap_remove() on "debug.mpsafevm". The effect on performance is significant. On my dual Opteron, I see a 3.6% reduction in "buildworld" time. - Use atomic operations to update several counters in vm_fault(). diff c1fbc251cd43f57703976219d84bfb31a5716cf8 Mon Aug 16 08:16:12 CEST 2004 Alan Cox <alc@FreeBSD.org> - Introduce and use a new tunable "debug.mpsafevm". At present, setting "debug.mpsafevm" results in (almost) Giant-free execution of zero-fill page faults. (Giant is held only briefly, just long enough to determine if there is a vnode backing the faulting address.) Also, condition the acquisition and release of Giant around calls to pmap_remove() on "debug.mpsafevm". The effect on performance is significant. On my dual Opteron, I see a 3.6% reduction in "buildworld" time. - Use atomic operations to update several counters in vm_fault().
H A D	vm_map.c	diff c1fbc251cd43f57703976219d84bfb31a5716cf8 Mon Aug 16 08:16:12 CEST 2004 Alan Cox <alc@FreeBSD.org> - Introduce and use a new tunable "debug.mpsafevm". At present, setting "debug.mpsafevm" results in (almost) Giant-free execution of zero-fill page faults. (Giant is held only briefly, just long enough to determine if there is a vnode backing the faulting address.) Also, condition the acquisition and release of Giant around calls to pmap_remove() on "debug.mpsafevm". The effect on performance is significant. On my dual Opteron, I see a 3.6% reduction in "buildworld" time. - Use atomic operations to update several counters in vm_fault(). diff c1fbc251cd43f57703976219d84bfb31a5716cf8 Mon Aug 16 08:16:12 CEST 2004 Alan Cox <alc@FreeBSD.org> - Introduce and use a new tunable "debug.mpsafevm". At present, setting "debug.mpsafevm" results in (almost) Giant-free execution of zero-fill page faults. (Giant is held only briefly, just long enough to determine if there is a vnode backing the faulting address.) Also, condition the acquisition and release of Giant around calls to pmap_remove() on "debug.mpsafevm". The effect on performance is significant. On my dual Opteron, I see a 3.6% reduction in "buildworld" time. - Use atomic operations to update several counters in vm_fault().