src/sys/vm/vm_page.c, branch release/4.6.2 FreeBSD source tree MFC: [vm/vm_contig.c rev 1.5] Call vm_page_unqueue_nowakeup() 2002-03-10T05:03:19+00:00 Alan Cox alc@FreeBSD.org 2002-03-10T05:03:19+00:00 41233f77ec9317b145e9aa63d2e811b028da7600 in contigmalloc1() rather than duplicating it. 
 in contigmalloc1() rather than duplicating it.
MFC __P() macro cleanup, register keyword removal in preparation for 2002-03-06T01:07:09+00:00 Matthew Dillon dillon@FreeBSD.org 2002-03-06T01:07:09+00:00 49f80b2225c1f81fa8cb8db3c112e5f8585515d5 object->memq scan-marker work (similar to the buffer queue scan marker work). 
object->memq scan-marker work (similar to the buffer queue scan marker
work).
MFC: [Revision 1.94] Add a new page queue, PQ_HOLD. 2002-03-03T01:13:12+00:00 Alan Cox alc@FreeBSD.org 2002-03-03T01:13:12+00:00 fb347ba711c3fcd583e396eea6569416a7530185 [Revision 1.95] Remove dead code. 
     [Revision 1.95] Remove dead code.
MFC rev 1.177 2002-02-26T21:56:40+00:00 Mike Silbersack silby@FreeBSD.org 2002-02-26T21:56:40+00:00 b2d78e2b767a428da253163a7ba4b8a769957d55 Add one more comment to the OOM changes so that future readers of the code may better understand the code. 
  Add one more comment to the OOM changes so that future readers of
  the code may better understand the code.
MFC OOM killer changes: 2002-02-26T05:49:28+00:00 Mike Silbersack silby@FreeBSD.org 2002-02-26T05:49:28+00:00 9a005c1b120fb11e1accd2643f67fac228aa6558 Changes to make the OOM killer much more effective: - Allow the OOM killer to target processes currently locked in memory. These very often are the ones doing the memory hogging. - Drop the wakeup priority of processes currently sleeping while waiting for their page fault to complete. In order for the OOM killer to work well, the killed process and other system processes waiting on memory must be allowed to wakeup first. Revision Changes Path 1.128 +2 -2 src/sys/vm/vm_fault.c 1.176 +23 -0 src/sys/vm/vm_page.c 1.188 +1 -2 src/sys/vm/vm_pageout.c 1.28 +3 -1 src/sys/vm/vm_pageout.h 
  Changes to make the OOM killer much more effective:

  - Allow the OOM killer to target processes currently locked in
    memory.  These very often are the ones doing the memory hogging.
  - Drop the wakeup priority of processes currently sleeping while
    waiting for their page fault to complete.  In order for the OOM
    killer to work well, the killed process and other system processes
    waiting on memory must be allowed to wakeup first.

  Revision  Changes    Path
  1.128     +2 -2      src/sys/vm/vm_fault.c
  1.176     +23 -0     src/sys/vm/vm_page.c
  1.188     +1 -2      src/sys/vm/vm_pageout.c
  1.28      +3 -1      src/sys/vm/vm_pageout.h
MFC NFS and VM bug fixes (see my commit 2001/12/13 17:16:57 PST, 2001-12-20T19:56:30+00:00 Matthew Dillon dillon@FreeBSD.org 2001-12-20T19:56:30+00:00 e114756065fc4a400d7cc3aa9c8a79d0074e92bf kern/vfs_bio.c 1.295 and friends) Approved by: Release Engineers 
kern/vfs_bio.c 1.295 and friends)

Approved by:	Release Engineers
MFC implement kern.maxvnodes (primarily kern/vfs_subr.c 1.326), sync, 2001-11-03T19:59:28+00:00 Matthew Dillon dillon@FreeBSD.org 2001-11-03T19:59:28+00:00 8e442063f0d76b88afb63b63e0b8228d9446de0e and other VM optimizations and fixes. * Add VOBJDIRTY flag to vnode to avoid certain indirections. * Turn the mount structure vnode list into an LRU queue (LIST -> TAILQ) * Attempt to reuse vnodes when we hit the maxvnodes limit * Optimize msync() to avoid unnecessary v_interlocks * Optimize ffs_sync() for same * Fix vm_object double-termination bug * Add KASSERT to ensure that backing object is not freed out from under remaining VM pages. These fixes change the mount structure and will create a binary kld module incompatibility with filesystem kld's, but I deem the scaling issues with 4.x that we are fixing to be more important. 
and other VM optimizations and fixes.

* Add VOBJDIRTY flag to vnode to avoid certain indirections.
* Turn the mount structure vnode list into an LRU queue (LIST -> TAILQ)
* Attempt to reuse vnodes when we hit the maxvnodes limit
* Optimize msync() to avoid unnecessary v_interlocks
* Optimize ffs_sync() for same
* Fix vm_object double-termination bug
* Add KASSERT to ensure that backing object is not freed out from
  under remaining VM pages.

These fixes change the mount structure and will create a binary kld module
incompatibility with filesystem kld's, but I deem the scaling issues with
4.x that we are fixing to be more important.
MFC vm_contig.c 1.4, properly track vm_page_zero_count in contigmalloc1() 2001-10-17T17:35:16+00:00 Matthew Dillon dillon@FreeBSD.org 2001-10-17T17:35:16+00:00 0aa2e3f172022cbf422cee145944d83e398ebf1b Submitted by: mark tinguely <tinguely@web.cs.ndsu.nodak.edu> 
Submitted by:	mark tinguely <tinguely@web.cs.ndsu.nodak.edu>
MFC kern/vfs_subr.c 1.263, sys/vnode.h 1.118, vm/vm_page.c 1.153. This 2001-10-16T23:16:24+00:00 Matthew Dillon dillon@FreeBSD.org 2001-10-16T23:16:24+00:00 7c461d93c82471456be674aab57f46e474b33f28 MFCs Kirk's vnode freelist cleanup commit from July 2000 in preparation for further work that will eventually make kern.maxvnodes actually do something. 
MFCs Kirk's vnode freelist cleanup commit from July 2000 in preparation
for further work that will eventually make kern.maxvnodes actually do
something.
MFC vm_contig.c 1.3. note: contigmalloc in -4.x is in vm_page.c. Fix 2001-10-15T18:20:46+00:00 Matthew Dillon dillon@FreeBSD.org 2001-10-15T18:20:46+00:00 4de97dd6aa20bb59d716cb73fe74446eb98023c0 contigmalloc[1]() so contigfree() actually works. 
contigmalloc[1]() so contigfree() actually works.