Commit Graph

90 Commits

Author SHA1 Message Date
John Dyson
23be6be853 Fix a problem with the vfs vnode caching that it doesn't grow quickly
enough and can cause some strange performance problems.  Specifically, at
or near startup time is when the problem is worst.  To reproduce
the problem, run "lat_syscall stat" from the alpha lmbench code right
after bootup.  A positive side effect of this mod is that the name
cache can be set to grow again by sysctl.  A noticable positive
performance impact is realized due to a larger namecache being available
as needed (or tuned.)
1997-08-04 07:43:28 +00:00
Doug Rabson
f6b4c28555 Merge WebNFS support from NetBSD
Obtained from:	NetBSD
1997-07-17 07:17:33 +00:00
John Dyson
3c631446d3 Remove a window during running down a file vnode. Also, the OBJ_DEAD
flag wasn't being respected during vref(), et. al.  Note that this
isn't the eventual fix for the locking problem.  Fine grained SMP
in the VM and VFS code will require (lots) more work.
1997-06-22 03:00:24 +00:00
David Greenman
2e58c0f892 Disabled the kern.vnode sysctl variable. It's causing system crashes on
large systems and needs to be re-thinked or removed wholesale.
1997-06-10 02:48:08 +00:00
Poul-Henning Kamp
8670684a2f Fix a race condition that did, after all, exist.
Reviewed by:	phk
Submitted by:	dfr
1997-05-06 15:19:38 +00:00
Poul-Henning Kamp
b15a966ec6 1. Add a {pointer, v_id} pair to the vnode to store the reference to the
".." vnode.  This is cheaper storagewise than keeping it in the
    namecache, and it makes more sense since it's a 1:1 mapping.

2.  Also handle the case of "." more intelligently rather than stuff
    the namecache with pointless entries.

3.  Add two lists to the vnode and hang namecache entries which go from
    or to this vnode.  When cleaning a vnode, delete all namecache
    entries it invalidates.

4.  Never reuse namecache enties, malloc new ones when we need it, free
    old ones when they die.  No longer a hard limit on how many we can
    have.

5.  Remove the upper limit on namelength of namecache entries.

6.  Make a global list for negative namecache entries, limit their number
    to a sysctl'able (debug.ncnegfactor) fraction of the total namecache.
    Currently the default fraction is 1/16th.  (Suggestions for better
    default wanted!)

7.  Assign v_id correctly in the face of 32bit rollover.

8.  Remove the LRU list for namecache entries, not needed.  Remove the
    #ifdef NCH_STATISTICS stuff, it's not needed either.

9.  Use the vnode freelist as a true LRU list, also for namecache accesses.

10. Reuse vnodes more aggresively but also more selectively, if we can't
    reuse, malloc a new one.  There is no longer a hard limit on their
    number, they grow to the point where we don't reuse potentially
    usable vnodes.  A vnode will not get recycled if still has pages in
    core or if it is the source of namecache entries (Yes, this does
    indeed work :-)  "." and ".." are not namecache entries any longer...)

11. Do not overload the v_id field in namecache entries with whiteout
    information, use a char sized flags field instead, so we can get
    rid of the vpid and v_id fields from the namecache struct.  Since
    we're linked to the vnodes and purged when they're cleaned, we don't
    have to check the v_id any more.

12. NFS knew about the limitation on name length in the namecache, it
    shouldn't and doesn't now.

Bugs:
        The namecache statistics no longer includes the hits for ".."
        and "." hits.

Performance impact:
        Generally in the +/- 0.5% for "normal" workstations, but
        I hope this will allow the system to be selftuning over a
        bigger range of "special" applications.  The case where
        RAM is available but unused for cache because we don't have
        any vnodes should be gone.

Future work:
        Straighten out the namecache statistics.

        "desiredvnodes" is still used to (bogusly ?) size hash
        tables in the filesystems.

        I have still to find a way to safely free unused vnodes
        back so their number can shrink when not needed.

        There is a few uses of the v_id field left in the filesystems,
        scheduled for demolition at a later time.

        Maybe a one slot cache for unused namecache entries should
        be implemented to decrease the malloc/free frequency.
1997-05-04 09:17:38 +00:00
John Dyson
82b8e119b4 Staticize an unnecessarily global function: vputrele.
Submitted by:	 Michael Hancock <michaelh@cet.co.jp>
1997-04-30 03:09:15 +00:00
Peter Wemm
5f61c81d66 copyin the export network mask to the correct variable.
Submitted by: Mike Hibler <mike@marker.cs.utah.edu>, PR#3380
1997-04-25 06:47:12 +00:00
Doug Rabson
de15ef6aef Add a function vop_sharedlock which a copy of vop_nolock without the
implementation #ifdef out.  This can be used for now by NFS.  As soon
as all the other filesystems' locking is fixed, this can go away.

Print the vnode address in vprint for easier debugging.
1997-04-04 17:46:21 +00:00
Bruce Evans
0f1adf65ab Use OID_AUTO instead of magic number for the Lite2 sysctl debug.busyprt.
Removed declaration of vfs_unmountroot() again.

Staticized vgonel().
1997-04-01 13:05:34 +00:00
David Greenman
2f2160da3b Fixed splbio problems in vinvalbuf. Closes PR#2875, although fixed
differently by me.
1997-03-05 04:54:54 +00:00
Bruce Evans
4a8b966013 Attach vfs_sysctl() one level lower so that only the levels below
VFS_GENERIC aren't done in the FreeBSD way.  The previous commit
broke the nfs sysctls.
1997-03-04 18:31:56 +00:00
Bruce Evans
3a76a5949b Merged Lite2's vfs_sysctl(). It doesn't fit very well into FreeBSD's
(phk's) sysctl framework, and I needed special code to disambiguate
the VFS_GENERIC node from the VFS_VFSCONF leaf, so I only converted
the leaves to the FreeBSD framework.  The error handling isn't quite
right.  CSRGS's sysctls seem to return ENOTDIR too much and FreeBSD's
sysctls don't agree with the man page.
1997-03-03 12:58:20 +00:00
Bruce Evans
dc91a89e83 Restored some pre-Lite2-merge source-level compatibility to the mount()
and getvfsbyname() interfaces.  The new interfaces are now hidden from
applications unless _NEW_VFSCONF is defined.  The new vfsconf interfaces
don't work yet.
1997-03-02 17:53:37 +00:00
Bruce Evans
a896f0256c Moved vfs sysctls to where Lite2 put them. No code changes yet. 1997-03-02 11:06:22 +00:00
Bruce Evans
b98afd0d00 Fixed Lite2 merge of spechash simplelocking. It was misplaced in
checkalias() and missing in vfinddev() and vcount().
1997-02-27 16:08:43 +00:00
John Dyson
fd7f690f94 Fix the previous simple_lock fix breakage in the combined
vput/vrele routine.  Fix a panic message.  Fix the vop_nounlock
routine so that "special" filesystems that use it work correctly.
1997-02-27 05:28:58 +00:00
John Dyson
0d955f71a1 Fix the simple_lock problem with the physical I/O buffer code, and
also fix the missing simple_unlock in vrele, and improve vrele/vput
by merging them into one routine.  BDE pointed these problems out.
1997-02-27 02:57:03 +00:00
Bruce Evans
7c1557c4af Fixed unmounting of the root fs. vfs_unmountroot() wasn't fully updated
to do Lite2 locking and vfs_unmountall() wasn't as simple as the Lite2
version.
1997-02-26 15:35:42 +00:00
Bruce Evans
c35e283a80 Merged some missing locking from Lite2:
- getnewvnode() and vref() were missing one simple_unlock() each.
- the Lite2 locking changes weren't merged at all in
  printlockedvnodes() or sysctl_vnode().  Merging these undid
  some KNF style regressions.
1997-02-25 19:33:23 +00:00
Peter Wemm
6875d25465 Back out part 1 of the MCFH that changed $Id$ to $FreeBSD$. We are not
ready for it yet.
1997-02-22 09:48:43 +00:00
John Dyson
996c772f58 This is the kernel Lite/2 commit. There are some requisite userland
changes, so don't expect to be able to run the kernel as-is (very well)
without the appropriate Lite/2 userland changes.

The system boots and can mount UFS filesystems.

Untested: ext2fs, msdosfs, NFS
Known problems: Incorrect Berkeley ID strings in some files.
		Mount_std mounts will not work until the getfsent
		library routine is changed.

Reviewed by:	various people
Submitted by:	Jeffery Hsu <hsu@freebsd.org>
1997-02-10 02:22:35 +00:00
Bruce Evans
5131d64e0c Removed option EXTRAVNODES. All versions of FreeBSD-2.x have a sysctl
variable `kern.maxvnodes' which gives much better control over vnode
allocation than EXTRAVNODES (except in -current between 1995/10/28 and
1996/11/12, kern.maxvnodes was read-only and thus useless).
1997-01-16 13:16:10 +00:00
Jordan K. Hubbard
1130b656e5 Make the long-awaited change from $Id$ to $FreeBSD$
This will make a number of things easier in the future, as well as (finally!)
avoiding the Id-smashing problem which has plagued developers for so long.

Boy, I'm glad we're not using sup anymore.  This update would have been
insane otherwise.
1997-01-14 07:20:47 +00:00
John Dyson
8b612c4b4a This commit is the embodiment of some VFS read clustering improvements.
Firstly, now our read-ahead clustering is on a file descriptor basis and not
on a per-vnode basis.  This will allow multiple processes reading the
same file to take advantage of read-ahead clustering.  Secondly, there
previously was a problem with large reads still using the ramp-up
algorithm.  Of course, that was bogus, and now we read the entire
"chunk" off of the disk in one operation.   The read-ahead clustering
algorithm should use less CPU than the previous also (I hope :-)).

NOTE:  THAT LKMS MUST BE REBUILT!!!
1996-12-29 02:45:28 +00:00
Bruce Evans
b83ddf9c86 Restored writability of kern.maxvnodes. It was broken a year ago in
rev.1.29 of kern_sysctl.c.

Should be in 2.2.
1996-11-12 09:24:31 +00:00
Poul-Henning Kamp
19060a3ad9 init_main.c: pass -d to init if DEVFS_ROOT
kern_conf.c:	gd driver is a disk.
vfs_subr.c:	include opt_devfs.h
1996-10-28 11:34:57 +00:00
Jordan K. Hubbard
0082fb4657 I'm not sure why, but Netcon's TFS filesystem code doesn't want to
add free vnodes back to the freelist.  They must do their own vnode
management.  Anyway, this change is *only* activated with their filesystem
and doesn't affect anyone else.  Whoops, forgot the submitted-by lines
in my previous commits too.. :-(
Submitted-By: Tony Ardolino <tony@netcon.com>
1996-10-17 17:56:07 +00:00
John Dyson
ad98052216 Clean up the rundown of the object backing a vnode. This should fix
NFS problems associated with forcible dismounts.
1996-10-17 02:49:35 +00:00
John Dyson
a8f42fa9a6 Correct vget by removing a window where a vnode can potentially go away. 1996-09-28 03:36:07 +00:00
Nate Williams
030e2e9ebb In sys/time.h, struct timespec is defined as:
/*
         * Structure defined by POSIX.4 to be like a timeval.
         */
        struct timespec {
                time_t  ts_sec;         /* seconds */
                long    ts_nsec;        /* and nanoseconds */
        };

        The correct names of the fields are tv_sec and tv_nsec.

Reminded by:	James Drobina <jdrobina@infinet.com>
1996-09-19 18:21:32 +00:00
John Dyson
6476c0d204 Even though this looks like it, this is not a complex code change.
The interface into the "VMIO" system has changed to be more consistant
and robust.  Essentially, it is now no longer necessary to call vn_open
to get merged VM/Buffer cache operation, and exceptional conditions
such as merged operation of VBLK devices is simpler and more correct.

This code corrects a potentially large set of problems including the
problems with ktrace output and loaded systems, file create/deletes,
etc.

Most of the changes to NFS are cosmetic and name changes, eliminating
a layer of subroutine calls.  The direct calls to vput/vrele have
been re-instituted for better cross platform compatibility.

Reviewed by: davidg
1996-08-21 21:56:23 +00:00
John Dyson
619594e898 Certain vnode buffer list operations were not being spl protected,
and they needed to be.  Brelse for example can be called at interrupt
level, and the buffer list operations were not being protected from it.
1996-08-15 06:45:01 +00:00
Bruce Evans
8c2ff39670 Only use the special bdevvp() for DEVFS if DEVFS_ROOT is defined. This
makes option DEVFS safe to use again (although mounting devfs is unsafe).
1996-07-30 18:00:32 +00:00
Poul-Henning Kamp
e83cf165d6 DEVFS needs a special bdevvp(). 1996-07-24 21:21:43 +00:00
Bruce Evans
cba2a7c614 Staticized a few variables.
Fixed warnings about unused variables.
1996-07-12 07:41:34 +00:00
Peter Wemm
114a8cff43 Add an option "EXTRA_VNODES" to cause an extra number of vnode structures
to be allocated at boot time.  This is an expensive option, as they
consume physical ram and are not pageable etc.  In certain situations,
this kind of option is quite useful, especially for news servers that
access a large number of directories at random and torture the name cache.
Defining 5000 or 10000 extra vnodes should cut down the amount of vnode
recycling somewhat, which should allow better name and directory caching
etc.

This is a "your mileage may vary" option, with no real indication of
what works best for your machine except trial and error.  Too many will
cost you ram that you could otherwise use for disk buffers etc.

This is based on something John Dyson mentioned to me a while ago.
1996-05-31 00:20:34 +00:00
John Dyson
e5fadd05f2 Put the "free vnode isn't" check back in the right place. 1996-03-09 06:43:19 +00:00
John Dyson
bd7e5f992e Eliminated many redundant vm_map_lookup operations for vm_mmap.
Speed up for vfs_bio -- addition of a routine bqrelse to greatly diminish
	overhead for merged cache.
Efficiency improvement for vfs_cluster.  It used to do alot of redundant
	calls to cluster_rbuild.
Correct the ordering for vrele of .text and release of credentials.
Use the selective tlb update for 486/586/P6.
Numerous fixes to the size of objects allocated for files.  Additionally,
	fixes in the various pagers.
Fixes for proper positioning of vnode_pager_setsize in msdosfs and ext2fs.
Fixes in the swap pager for exhausted resources.  The pageout code
	will not as readily thrash.
Change the page queue flags (PG_ACTIVE, PG_INACTIVE, PG_FREE, PG_CACHE) into
	page queue indices (PQ_ACTIVE, PQ_INACTIVE, PQ_FREE, PQ_CACHE),
	thereby improving efficiency of several routines.
Eliminate even more unnecessary vm_page_protect operations.
Significantly speed up process forks.
Make vm_object_page_clean more efficient, thereby eliminating the pause
	that happens every 30seconds.
Make sequential clustered writes B_ASYNC instead of B_DELWRI even in the
	case of filesystems mounted async.
Fix a panic with busy pages when write clustering is done for non-VMIO
	buffers.
1996-01-19 04:00:31 +00:00
Garrett Wollman
0e41ee3037 Convert DDB to new-style option. 1996-01-04 21:13:23 +00:00
David Greenman
864ef7d17e Moved the #ifdef DIAGNOSTIC in vrele() so that the check for negative
v_usecount is always performed and only the call to vprint is conditional.
1996-01-02 18:13:20 +00:00
Poul-Henning Kamp
27a0b398a7 Staticize.
Unstaticize a function in scsi/scsi_base that was used, with an undocumented
option.
My last count on the LINT kernel shows:
Total symbols:  3647
unref symbols:   463
undef symbols:     4
1 ref symbols:  1751
2 ref symbols:   485
Approaching the pain threshold now.
1995-12-17 21:23:44 +00:00
John Dyson
a316d390bd Changes to support 1Tb filesizes. Pages are now named by an
(object,index) pair instead of (object,offset) pair.
1995-12-11 04:58:34 +00:00
David Greenman
efeaf95a41 Untangled the vm.h include file spaghetti. 1995-12-07 12:48:31 +00:00
Poul-Henning Kamp
65d0bc1387 A couple of minor tweaks to the sysctl stuff. 1995-12-06 13:27:39 +00:00
Bruce Evans
98d938220c Completed function declarations and/or added prototypes. 1995-12-02 18:58:56 +00:00
Poul-Henning Kamp
2d0b1d708c A test was backwards.
Noticed by:	Cheng, Hsiao-Yang <sycheng@cis.ufl.edu>
1995-11-29 11:28:00 +00:00
Poul-Henning Kamp
4b2af45f4b Mega commit for sysctl.
Convert the remaining sysctl stuff to the new way of doing things.
the devconf stuff is the reason for the large number of files.
Cleaned up some compiler warnings while I were there.
1995-11-20 12:42:39 +00:00
Bruce Evans
986f4ce75e Fixed support for DIAGNOSTIC option. SYSCTL_INT() depends on kernel.h. 1995-11-16 09:45:23 +00:00
Poul-Henning Kamp
395e673587 Change some of the debug sysctl vars. The semantics of these will change. 1995-11-14 09:19:16 +00:00