Alan Cox 13458803f4 Give vm_fault()'s sequential access optimization a makeover. ... There are two aspects to the sequential access optimization: (1) read ahead of pages that are expected to be accessed in the near future and (2) unmap and cache behind of pages that are not expected to be accessed again. This revision changes both aspects. The read ahead optimization is now more effective. It starts with the same initial read window as before, but arithmetically grows the window on sequential page faults. This can yield increased read bandwidth. For example, on one of my machines, a program using mmap() to read a file that is several times larger than the machine's physical memory takes about 17% less time to complete. The unmap and cache behind optimization is now more selectively applied. The read ahead window must grow to its maximum size before unmap and cache behind is performed. This significantly reduces the number of times that pages are unmapped and cached only to be reactivated a short time later. The unmap and cache behind optimization now clears each page's referenced flag. Previously, in the case of dirty pages, if the containing file was still mapped at the time that the page daemon examined the dirty pages, they would be reactivated. From a stylistic standpoint, this revision also cleanly separates the implementation of the read ahead and unmap/cache behind optimizations. Glanced at: kib MFC after: 2 weeks		2012-05-10 15:16:42 +00:00
..
default_pager.c
device_pager.c
memguard.c
memguard.h
phys_pager.c
pmap.h
redzone.c
redzone.h
sg_pager.c
swap_pager.c	Remove direct access to si_name.	2012-02-10 12:35:57 +00:00
swap_pager.h
uma_core.c	exclude kmem_alloc'ed ARC data buffers from kernel minidumps on amd64	2012-01-27 20:18:31 +00:00
uma_dbg.c
uma_dbg.h
uma_int.h
uma.h	exclude kmem_alloc'ed ARC data buffers from kernel minidumps on amd64	2012-01-27 20:18:31 +00:00
vm_contig.c	In vm_object_page_clean(), do not clean OBJ_MIGHTBEDIRTY object flag	2012-03-17 23:00:32 +00:00
vm_extern.h
vm_fault.c	Give vm_fault()'s sequential access optimization a makeover.	2012-05-10 15:16:42 +00:00
vm_glue.c	Move kstack_cache_entry into the private header, and make the	2011-12-16 10:56:16 +00:00
vm_init.c
vm_kern.c	Simplify kmem_alloc() by eliminating code that existed on account of	2012-02-29 05:41:29 +00:00
vm_kern.h
vm_map.c	Give vm_fault()'s sequential access optimization a makeover.	2012-05-10 15:16:42 +00:00
vm_map.h	Give vm_fault()'s sequential access optimization a makeover.	2012-05-10 15:16:42 +00:00
vm_meter.c
vm_mmap.c	When MAP_STACK mapping is created, the map entry is created only to	2012-04-21 18:36:53 +00:00
vm_object.c	Fix madvise(MADV_WILLNEED) to properly handle individual mappings larger	2012-03-19 18:47:34 +00:00
vm_object.h	Fix madvise(MADV_WILLNEED) to properly handle individual mappings larger	2012-03-19 18:47:34 +00:00
vm_page.c	Avoid a lock order reversal in pmap_extract_and_hold() from relocking	2012-04-22 17:58:30 +00:00
vm_page.h	Fix mincore(2) so that it reports PG_CACHED pages as resident.	2012-04-08 18:25:12 +00:00
vm_pageout.c	In vm_object_page_clean(), do not clean OBJ_MIGHTBEDIRTY object flag	2012-03-17 23:00:32 +00:00
vm_pageout.h	In vm_object_page_clean(), do not clean OBJ_MIGHTBEDIRTY object flag	2012-03-17 23:00:32 +00:00
vm_pager.c
vm_pager.h
vm_param.h
vm_phys.c	Bah, just revert my earlier change entirely. (Missed alc's request to do	2012-03-19 19:06:40 +00:00
vm_phys.h
vm_reserv.c	If a page belonging a reservation is cached, then mark the reservation so	2012-04-08 17:00:46 +00:00
vm_reserv.h
vm_unix.c
vm_zeroidle.c
vm.h
vnode_pager.c	Keep track of the mount point associated with a special device	2012-03-28 20:49:11 +00:00
vnode_pager.h	Account the writeable shared mappings backed by file in the vnode	2012-02-23 21:07:16 +00:00