Commit Graph

57 Commits

Author SHA1 Message Date
chs 4d069e8517 in uvm_vnp_setsize(), wait for any i/o in progress on pages that we free. 2001-12-31 07:00:15 +00:00
chs 8e9cdbbd63 replace "vnode" and "vtext" with "file" and "exec" in uvmexp field names. 2001-12-09 03:07:43 +00:00
lukem b616d1ca1d add RCSIDs, and in some cases, slightly cleanup #include order 2001-11-10 07:36:59 +00:00
chs 365f4c4313 change the names of the arguments to uvn_put() to match their usage. 2001-09-26 07:23:51 +00:00
sommerfeld cc8633edd3 VOP_PUTPAGES must release the uobj's lock for us, so ensure it's locked
beforehand and unlocked afterwards using LOCK_ASSERT().
2001-09-22 22:33:16 +00:00
chs 64c6d1d2dc a whole bunch of changes to improve performance and robustness under load:
- remove special treatment of pager_map mappings in pmaps.  this is
   required now, since I've removed the globals that expose the address range.
   pager_map now uses pmap_kenter_pa() instead of pmap_enter(), so there's
   no longer any need to special-case it.
 - eliminate struct uvm_vnode by moving its fields into struct vnode.
 - rewrite the pageout path.  the pager is now responsible for handling the
   high-level requests instead of only getting control after a bunch of work
   has already been done on its behalf.  this will allow us to UBCify LFS,
   which needs tighter control over its pages than other filesystems do.
   writing a page to disk no longer requires making it read-only, which
   allows us to write wired pages without causing all kinds of havoc.
 - use a new PG_PAGEOUT flag to indicate that a page should be freed
   on behalf of the pagedaemon when it's unlocked.  this flag is very similar
   to PG_RELEASED, but unlike PG_RELEASED, PG_PAGEOUT can be cleared if the
   pageout fails due to eg. an indirect-block buffer being locked.
   this allows us to remove the "version" field from struct vm_page,
   and together with shrinking "loan_count" from 32 bits to 16,
   struct vm_page is now 4 bytes smaller.
 - no longer use PG_RELEASED for swap-backed pages.  if the page is busy
   because it's being paged out, we can't release the swap slot to be
   reallocated until that write is complete, but unlike with vnodes we
   don't keep a count of in-progress writes so there's no good way to
   know when the write is done.  instead, when we need to free a busy
   swap-backed page, just sleep until we can get it busy ourselves.
 - implement a fast-path for extending writes which allows us to avoid
   zeroing new pages.  this substantially reduces cpu usage.
 - encapsulate the data used by the genfs code in a struct genfs_node,
   which must be the first element of the filesystem-specific vnode data
   for filesystems which use genfs_{get,put}pages().
 - eliminate many of the UVM pagerops, since they aren't needed anymore
   now that the pager "put" operation is a higher-level operation.
 - enhance the genfs code to allow NFS to use the genfs_{get,put}pages
   instead of a modified copy.
 - clean up struct vnode by removing all the fields that used to be used by
   the vfs_cluster.c code (which we don't use anymore with UBC).
 - remove kmem_object and mb_object since they were useless.
   instead of allocating pages to these objects, we now just allocate
   pages with no object.  such pages are mapped in the kernel until they
   are freed, so we can use the mapping to find the page to free it.
   this allows us to remove splvm() protection in several places.

The sum of all these changes improves write throughput on my
decstation 5000/200 to within 1% of the rate of NetBSD 1.5
and reduces the elapsed time for "make release" of a NetBSD 1.5
source tree on my 128MB pc to 10% less than a 1.5 kernel took.
2001-09-15 20:36:31 +00:00
chs 2c441082d4 allow mappings of VBLK vnodes. 2001-08-17 05:53:02 +00:00
chs 11a9651c8f replace vm_page_t with struct vm_page *. 2001-05-26 21:27:10 +00:00
chs 3845302904 remove trailing whitespace. 2001-05-25 04:06:11 +00:00
chs dd82ad8e2c eliminate the VM_PAGER_* error codes in favor of the traditional E* codes.
the mapping is:

VM_PAGER_OK		        0
VM_PAGER_BAD		        <unused>
VM_PAGER_FAIL		        <unused>
VM_PAGER_PEND		        0 (see below)
VM_PAGER_ERROR		        EIO
VM_PAGER_AGAIN		        EAGAIN
VM_PAGER_UNLOCK		        EBUSY
VM_PAGER_REFAULT	        ERESTART

for async i/o requests, it used to be possible for the request to
be convert to sync, and the pager would return VM_PAGER_OK or VM_PAGER_PEND
to indicate whether the caller should perform post-i/o cleanup.
this is no longer allowed; pagers must now return 0 to indicate that
the async i/o was successfully started, and the caller never needs to
worry about doing the post-i/o cleanup.
2001-03-10 22:46:45 +00:00
chs 83d071a318 add UBC memory-usage balancing. we track the number of pages in use for
each of the basic types (anonymous data, executable image, cached files)
and prevent the pagedaemon from reusing a given page if that would reduce
the count of that type of page below a sysctl-setable minimum threshold.
the thresholds are controlled via three new sysctl tunables:
vm.anonmin, vm.vnodemin, and vm.vtextmin.  these tunables are the
percentages of pageable memory reserved for each usage, and we do not allow
the sum of the minimums to be more than 95% so that there's always some
memory that can be reused.
2001-03-09 01:02:10 +00:00
enami 79dbb12278 When shrinking file size, don't dispose of a page still in use. 2001-02-22 01:02:09 +00:00
chs 7b76ca8254 in uvn_flush(), add a fast path for the case where the vnode has no pages.
update the comment above this function while I'm here.
2001-02-18 19:40:25 +00:00
chs 4be5f47040 remove a debug printf() that has outlived its usefulness. 2001-02-08 06:43:05 +00:00
chs 43eb344e3f in uvn_flush(), interpret a "stop" value of 0 as meaning all pages at
offsets equal to or higher than "start".  use this in uvm_vnp_setsize()
instead of the vnode's size since there can be pages past EOF.
2001-02-06 10:53:23 +00:00
thorpej 1779f8f71b Page scanner improvements, behavior is actually a bit more like
Mach VM's now.  Specific changes:
- Pages now need not have all of their mappings removed before being
  put on the inactive list.  They only need to have the "referenced"
  attribute cleared.  This makes putting pages onto the inactive list
  much more efficient.  In order to eliminate redundant clearings of
  "refrenced", callers of uvm_pagedeactivate() must now do this
  themselves.
- When checking the "modified" attribute for a page (for clearing
  PG_CLEAN), make sure to only do it if PG_CLEAN is currently set on
  the page (saves a potentially expensive pmap operation).
- When scanning the inactive list, if a page is referenced, reactivate
  it (this part was actually added in uvm_pdaemon.c,v 1.27).  This
  now works properly now that pages on the inactive list are allowed to
  have mappings.
- When scanning the inactive list and considering a page for freeing,
  remove all mappings, and then check the "modified" attribute if the
  page is marked PG_CLEAN.
- When scanning the active list, if the page was referenced since its
  last sweep by the scanner, don't deactivate it.  (This part was
  actually added in uvm_pdaemon.c,v 1.28.)

These changes greatly improve interactive performance during
moderate to high memory and I/O load.
2001-01-28 23:30:42 +00:00
chs f0ff6fc897 in uvn_flush(), when PGO_SYNCIO is specified then we should wait for
pending i/os to complete before returning even if PGO_CLEANIT is not
specified.  this fixes two races:

 (1) NFS write rpcs vs. setattr operations which truncate the file.
     if the truncate doesn't wait for pending writes to complete then
     a later write rpc completion can undo the effect of the truncate.
     this problem has been reported by several people.

 (2) write i/os in disk-based filesystem vs. the disk block being
     freed by a truncation, allocated to a new file, and written
     again with different data.  if the disk driver reorders the requests
     and does the second i/o first, the old data will clobber the new,
     corrupting the new file.  I haven't heard of anyone experiencing
     this problem yet, but it's fixed now anyway.
2001-01-08 06:21:13 +00:00
chs 34a059b354 in uvn_flush(), don't deactivate busy pages. 2000-12-16 06:17:09 +00:00
chs a8609aaac8 in uvn_findpage(), only increment the counter of vnode pages
if we succeed in allocating a page.

from Lars Heidieker <lars@heidieker.de> in PR 11636.
2000-12-06 03:37:30 +00:00
simonb 33999a4224 Move uvm_pgcnt_vnode and uvm_pgcnt_anon into uvmexp (as vnodepages and
anonpages), and add vtextpages which is currently unused but will be
used to trace the number of pages used by vtext vnodes.
2000-11-30 11:04:43 +00:00
chs aeda8d3b77 Initial integration of the Unified Buffer Cache project. 2000-11-27 08:39:39 +00:00
chs f9fb6f5a55 g/c unused pager ops "asyncget" and "aiodone". 2000-11-24 20:34:01 +00:00
mrg dea44a9ec4 remove include of <vm/vm.h> 2000-06-27 17:29:17 +00:00
mrg 2f159a1bac remove/move more mach vm header files:
<vm/pglist.h> -> <uvm/uvm_pglist.h>
	<vm/vm_inherit.h> -> <uvm/uvm_inherit.h>
	<vm/vm_kern.h> -> into <uvm/uvm_extern.h>
	<vm/vm_object.h> -> nothing
	<vm/vm_pager.h> -> into <uvm/uvm_pager.h>

also includes a bunch of <vm/vm_page.h> include removals (due to redudancy
with <vm/vm.h>), and a scattering of other similar headers.
2000-06-26 14:20:25 +00:00
thorpej 655b21e17d Tell uvm_pagermapin() the direction of the I/O so that it can map
with only the protection that it needs.
2000-05-19 03:45:04 +00:00
chs 03a4ef3a79 remove the "shareprot" pagerop. it's not needed anymore since
share maps are long gone.
2000-04-03 07:35:23 +00:00
kleink a51ef2c3f9 Kill duplicate uvn_attach() prototype (public, already in uvm_vnode.h). 2000-03-27 16:58:23 +00:00
kleink 6e5b64c8a0 Merge parts of chs-ubc2 into the trunk:
Add a new type voff_t (defined as a synonym for off_t) to describe offsets
into uvm objects, and update the appropriate interfaces to use it, the
most visible effect being the ability to mmap() file offsets beyond
the range of a vaddr_t.

Originally by Chuck Silvers; blame me for problems caused by merging this
into non-UBC.
2000-03-26 20:54:45 +00:00
soren 95054da1a1 Fix doubled 'the's in comments. 2000-03-13 23:52:25 +00:00
chs 26c744c85b remove a debug printf that has outlived its usefulness. 2000-01-28 08:02:48 +00:00
chs b16ae5a8a5 put various debugging printfs under #ifdef DEBUG. 1999-10-19 16:04:45 +00:00
chs f3a668ed84 eliminate the PMAP_NEW option by making it required for all ports.
ports which previously had no support for PMAP_NEW now implement
the pmap_k* interfaces as wrappers around the non-k versions.
1999-09-12 01:16:55 +00:00
thorpej 3f176180d5 Garbage collect thread_sleep()/thread_wakeup() left over from the old
Mach VM code.  Also nuke iprintf(), which was no longer used anywhere.

Add proclist locking where appropriate.
1999-07-22 22:58:38 +00:00
thorpej 2c668fb0d4 0 -> FALSE in a few places. 1999-07-22 21:27:32 +00:00
chs f455dd6596 add a `flags' argument to uvm_pagealloc_strat().
define a flag UVM_PGA_USERESERVE to allow non-kernel object
allocations to use pages from the reserve.
use the new flag for allocations in pmap modules.
1999-04-11 04:04:04 +00:00
mrg a0139bc39d remove now >1 year old pre-release message. 1999-03-25 18:48:49 +00:00
sommerfe f1a508e354 Prevent deadlock cited in PR4629 from crashing the system. (copyout
and system call now just return EFAULT).  A complete fix will
presumably have to wait for UBC and/or for vnode locking protocols to
be revamped to allow use of shared locks.
1999-03-25 00:20:35 +00:00
cgd 37c88c58da after discussion with chuck, nuke pgo_attach from uvm_pagerops 1999-03-24 03:45:27 +00:00
chs 0c38ab98fa fix printf arg types. 1999-03-04 06:48:54 +00:00
bouyer b87a535a9f A small typo fix, + enclose "used_vnode_size = %qu" debug printf inside
#ifdef DEBUG/#endif
1999-01-29 12:56:17 +00:00
chs 23ed4b5656 we must unlock a vp's object's lock before calling vrele(). 1998-11-04 06:21:40 +00:00
chs 549cd579e5 shift by PAGE_SHIFT instead of multiplying or dividing by PAGE_SIZE. 1998-10-18 23:49:59 +00:00
eeh a2dd74ed79 Merge paddr_t changes into the main branch. 1998-08-13 02:10:37 +00:00
perry 2c8717021d bzero->memset, bcopy->memcpy, bcmp->memcmp 1998-08-09 22:36:37 +00:00
thorpej 8d986de632 Add support for mmap'ing disk block devices. 1998-07-07 23:22:13 +00:00
sommerfe 7ba7fbbb23 Always include fifos; "not an option any more". 1998-06-24 20:58:44 +00:00
sommerfe becaafeea0 defopt for options FIFO 1998-06-22 22:00:59 +00:00
kleink 182e12f413 Remove inclusions of syscall (and syscall argument) related header files;
we don't need them here.
1998-05-05 20:51:04 +00:00
chuck 927ec8b012 bug fix: when doing uvm_vnp_sync() actually skip over blocked uvn's so
that we don't try and sync them later.   should get rid of the
"uvm_vnp_sync: dying vnode on sync list" related warnings that were
occuring during a "make install."
1998-03-11 01:37:40 +00:00
mrg 8106d13596 KNF. 1998-03-09 00:58:55 +00:00