Skip site navigation (1)Skip section navigation (2)
Date:      Fri, 26 Jul 1996 20:24:14 -0700 (PDT)
From:      John Dyson <dyson>
To:        CVS-committers, cvs-all, cvs-sys
Subject:   cvs commit:  src/sys/i386/include pmap.h src/sys/kern kern_exec.c kern_exit.c src/sys/vm swap_pager.c vm_fault.c vm_map.c vm_map.h vm_mmap.c vm_object.c vm_page.c vm_page.h vm_pageout.c vnode_pager.c src/sys/i386/i386 pmap.c
Message-ID:  <199607270324.UAA04916@freefall.freebsd.org>

next in thread | raw e-mail | index | archive | help

dyson       96/07/26 20:24:13

  Modified:    sys/i386/i386  pmap.c
               sys/i386/include  pmap.h
               sys/kern  kern_exec.c kern_exit.c
               sys/vm    swap_pager.c vm_fault.c vm_map.c vm_map.h
                        vm_mmap.c  vm_object.c vm_page.c vm_page.h
                        vm_pageout.c vnode_pager.c
  Log:
  This commit is meant to solve a couple of VM system problems or
  performance issues.
  
  	1) The pmap module has had too many inlines, and so the
  	   object file is simply bigger than it needs to be.
  	   Some common code is also merged into subroutines.
  	2) Removal of some *evil* PHYS_TO_VM_PAGE macro calls.
  	   Unfortunately, a few have needed to be added also.
  	   The removal caused the need for more vm_page_lookups.
  	   I added lookup hints to minimize the need for the
  	   page table lookup operations.
  	3) Removal of some bogus performance improvements, that
  	   mostly made the code more complex (tracking individual
  	   page table page updates unnecessarily).  Those improvements
  	   actually hurt 386 processors perf (not that people who
  	   worry about perf use 386 processors anymore :-)).
  	4) Changed pv queue manipulations/structures to be TAILQ's.
  	5) The pv queue code has had some performance problems since
  	   day one.  Some significant scalability issues are resolved
  	   by threading the pv entries from the pmap AND the physical
  	   address instead of just the physical address.  This makes
  	   certain pmap operations run much faster.  This does
  	   not affect most micro-benchmarks, but should help loaded system
  	   performance *significantly*.  DG helped and came up with most
  	   of the solution for this one.
  	6) Most if not all pmap bit operations follow the pattern:
  		pmap_test_bit();
  		pmap_clear_bit();
  	   That made for twice the necessary pv list traversal.   The
  	   pmap interface now supports only pmap_tc_bit type operations:
  	   pmap_[test/clear]_modified, pmap_[test/clear]_referenced.
  	   Additionally, the modified routine now takes a vm_page_t arg
  	   instead of a phys address.  This eliminates a PHYS_TO_VM_PAGE
  	   operation.
  	7) Several rewrites of routines that contain redundant code to
  	   use common routines, so that there is a greater likelihood of
  	   keeping the cache footprint smaller.
  
  Revision  Changes    Path
  1.110     +426 -515  src/sys/i386/i386/pmap.c
  1.41      +19 -6     src/sys/i386/include/pmap.h
  1.45      +2 -2      src/sys/kern/kern_exec.c
  1.34      +2 -3      src/sys/kern/kern_exit.c
  1.69      +18 -11    src/sys/vm/swap_pager.c
  1.54      +34 -27    src/sys/vm/vm_fault.c
  1.53      +77 -68    src/sys/vm/vm_map.c
  1.14      +2 -1      src/sys/vm/vm_map.h
  1.45      +177 -27   src/sys/vm/vm_mmap.c
  1.77      +4 -3      src/sys/vm/vm_object.c
  1.61      +16 -33    src/sys/vm/vm_page.c
  1.30      +5 -5      src/sys/vm/vm_page.h
  1.83      +28 -30    src/sys/vm/vm_pageout.c
  1.61      +4 -4      src/sys/vm/vnode_pager.c



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199607270324.UAA04916>