Commit Graph

135 Commits

Author SHA1 Message Date
John Dyson
4ced7dd5bf Avoid manipulating the buffer map at interrupt time by deferring bfreekva
to getnewbuf, and remove from brelse.
Reviewed by:	dg@root.com
1997-11-24 06:18:27 +00:00
Poul-Henning Kamp
4a11ca4e29 Remove a bunch of variables which were unused both in GENERIC and LINT.
Found by:	-Wunused
1997-11-07 08:53:44 +00:00
Poul-Henning Kamp
cb226aaa62 Move the "retval" (3rd) parameter from all syscall functions and put
it in struct proc instead.

This fixes a boatload of compiler warning, and removes a lot of cruft
from the sources.

I have not removed the /*ARGSUSED*/, they will require some looking at.

libkvm, ps and other userland struct proc frobbing programs will need
recompiled.
1997-11-06 19:29:57 +00:00
Bruce Evans
55b211e3af Removed unused #includes. 1997-10-28 15:59:26 +00:00
Poul-Henning Kamp
dba3870c10 VFS interior redecoration.
Rename vn_default_error to vop_defaultop all over the place.
Move vn_bwrite from vfs_bio.c to vfs_default.c and call it vop_stdbwrite.
Use vop_null instead of nullop.
Move vop_nopoll from vfs_subr.c to vfs_default.c
Move vop_sharedlock from vfs_subr.c to vfs_default.c
Move vop_nolock from vfs_subr.c to vfs_default.c
Move vop_nounlock from vfs_subr.c to vfs_default.c
Move vop_noislocked from vfs_subr.c to vfs_default.c
Use vop_ebadf instead of *_ebadf.
Add vop_defaultop for getpages on master vnode in MFS.
1997-10-26 20:55:39 +00:00
Poul-Henning Kamp
a1c995b626 Last major round (Unless Bruce thinks of somthing :-) of malloc changes.
Distribute all but the most fundamental malloc types.  This time I also
remembered the trick to making things static:  Put "static" in front of
them.

A couple of finer points by:	bde
1997-10-12 20:26:33 +00:00
Poul-Henning Kamp
55166637cd Distribute and statizice a lot of the malloc M_* types.
Substantial input from:	bde
1997-10-11 18:31:40 +00:00
Justin T. Gibbs
ab36c06737 init_main.c subr_autoconf.c:
Add support for "interrupt driven configuration hooks".
	A component of the kernel can register a hook, most likely
	during auto-configuration, and receive a callback once
	interrupt services are available.  This callback will occur before
	the root and dump devices are configured, so the configuration
	task can affect the selection of those two devices or complete
	any tasks that need to be performed prior to launching init.
	System boot is posponed so long as a hook is registered.  The
	hook owner is responsible for removing the hook once their task
	is complete or the system boot can continue.

kern_acct.c kern_clock.c kern_exit.c kern_synch.c kern_time.c:
	Change the interface and implementation for the kernel callout
	service.  The new implemntaion is based on the work of
	Adam M. Costello and George Varghese, published in a technical
	report entitled "Redesigning the BSD Callout and Timer Facilities".
	The interface used in FreeBSD is a little different than the one
	outlined in the paper.  The new function prototypes are:

	struct callout_handle timeout(void (*func)(void *),
				      void *arg, int ticks);

	void untimeout(void (*func)(void *), void *arg,
		       struct callout_handle handle);

	If a client wishes to remove a timeout, it must store the
	callout_handle returned by timeout and pass it to untimeout.

	The new implementation gives 0(1) insert and removal of callouts
	making this interface scale well even for applications that
	keep 100s of callouts outstanding.

	See the updated timeout.9 man page for more details.
1997-09-21 22:00:25 +00:00
John Dyson
804cd17e21 Re-institute a bugfix in allocation of anonymous buffer memory. 1997-09-21 04:49:30 +00:00
Poul-Henning Kamp
c1f95f1378 The patch is needed in order to not throw away unmodified
local filesystem metadata at the first brelse call when the
block device vnode has v_tag set to VT_NFS.

Reviewed by:	phk
Submitted by:	Tor Egge <tegge@idi.ntnu.no>
1997-09-10 20:09:22 +00:00
Bruce Evans
2d85d0df17 Some staticized variables were still declared to be extern. 1997-09-07 16:56:34 +00:00
John Dyson
a5db4bf475 Back out some incorrect changes that was worse than the original bug. 1997-08-26 04:36:27 +00:00
John Dyson
745b842305 Some corrections to the anonymous page managment.
Submitted by:	Peter Chen <pmchen@eecs.umich.edu>
1997-08-21 01:35:37 +00:00
John Dyson
c0ecffb96b Modify the scheduling policy to take into account disk I/O waits
as chargeable CPU usage.  This should mitigate the problem of processes
doing disk I/O hogging the CPU.  Various users have reported the
problem, and test code shows that the problem should now be gone.
1997-08-09 10:13:32 +00:00
John Dyson
6b195d32a1 Fix a problem with the VN device. Specifically, the VN device can
cause a problem of spiraling death due to buffer resource limitations.
The vfs_bio code in general had little ability to handle buffer resource
management, and now it does.  Also, there are a lot more knobs for tuning the
vfs_bio code now.  The knobs came free because of the need that there
always be some immediately available buffers (non-delayed or locked) for
use.  Note that the buffer cache code is much less likely to get bogged
down with lots of delayed writes, even more so than before.
1997-06-15 17:56:53 +00:00
Bruce Evans
bad324ca54 Fixed livelock in getnewbuf().
It is possible for multiple process to sleep concurrently waiting
for a buffer.  When the buffer shortage is a shortage of space but
not a shortage of buffer headers, the processes took turns creating
empty buffers and waking each other to advertise the brelse() of
the empties; progress was never made because tsleep() always found
another high-priority process to run and everything was done at
splbio(), so vfs_update never had a chance to flush delayed writes,
not to mention that i/o never had a chance to complete.

The problem seems to be rare in practice, but it can easily be
reproduced by misusing block devices, at least for sufficently slow
devices on machines with a sufficiently small buffer cache.  E.g.,
`tar cvf /dev/fd0 /kernel' on an 8MB system with no disk in fd0
causes the problem quickly; the same command with a disk in fd0
causes the problem not quite as quickly; and people have reported
problems newfs'ing file systems on block devices.

Block devices only cause this problem indirectly.  They are pessimized
for time and space, and the space pessimization causes the shortage
(it manifests as internal fragmentation in buffer_map).

This should be fixed in 2.2.
1997-06-13 08:30:40 +00:00
Doug Rabson
e90b93a1d0 Don't throw NFS B_DELWRI buffers back to the vm system in brelse.
Make sure that b_validoff..b_validend is at least as big as
b_dirtyoff..b_dirtyend.
1997-06-06 09:04:28 +00:00
Doug Rabson
501338ca4f Fix some performance problems with the NFS mmap fixes. 1997-06-03 09:42:43 +00:00
Doug Rabson
bc3718bb36 The previous fix didn't work properly for small block size filesystems,
which caused very slow file access for cd9660 and some ext2fs filesystems.

Reviewed by:	bde
1997-05-30 22:25:35 +00:00
Doug Rabson
32ad9cb531 Fix a few bugs with NFS and mmap caused by NFS' use of b_validoff
and b_validend.  The changes to vfs_bio.c are a bit ugly but hopefully
can be tidied up later by a slight redesign.

PR:		kern/2573, kern/2754, kern/3046 (possibly)
Reviewed by:	dyson
1997-05-19 14:36:56 +00:00
Joerg Wunsch
8eea4d3c76 Add a DDB command `show buffer', to display a struct buf. It's impossible
to display everything, so i've chosen a small subset.  Add more to this as
you think seems useful.
1997-05-10 09:09:42 +00:00
John Dyson
95395ca1c1 Improve the buffer cache memory policy by moving pages over to the
cache queue more often.  The pageout daemon had to be waken up
more often than necessary since pages were not put on the
cache queue, when they should have been.
Submitted by:	David Greenman <dg@freebsd.org>
1997-04-13 03:33:25 +00:00
Bruce Evans
3f39dbc52d Removed potentially harmful garbage <vm/lock.h> and fixed bogus
use of it.  It was actually harmless because the use was null due
to fortuitous include orders and identical (wrong) idempotency
macros.
1997-04-01 08:39:07 +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
Bruce Evans
16a02c1105 Removed redundant spl0()'s from kernel processes. They were work-arounds
for a bug in fork().
1997-01-15 19:05:08 +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
3596818baa Clean-up of the new buffer kva allocation code. Also, there was an
error in the !BOUNCE_BUFFERS case.
1996-12-05 04:28:52 +00:00
John Dyson
621d520e2f Fix a problem with the new buffer_map management code. Additionally,
decrease the size of buffer_map to approx 2/3 of what it used to be
(buffer_map can be smaller now.)  The original commit of these changes
increased the size of buffer_map to the point where the system would
not boot on large systems -- now large systems with large caches will
have even less problems than before.
1996-12-01 15:46:40 +00:00
John Dyson
09e0c6ccdd Implement a new totally dynamic (up to MAXPHYS) buffer kva allocation
scheme.  Additionally, add the capability for checking for unexpected
kernel page faults.  The maximum amount of kva space for buffers hasn't
been decreased from where it is, but it will now be possible to do so.

This scheme manages the kva space similar to the buffers themselves.  If
there isn't enough kva space because of usage or fragementation, buffers
will be reclaimed until a buffer allocation is successful.  This scheme
should be very resistant to fragmentation problems until/if the LFS code
is fixed and uses the bogus buffer locking scheme -- but a 'fixed' LFS
is not likely to use such a scheme.

Now there should be NO problem allocating buffers up to MAXPHYS.
1996-11-30 22:41:49 +00:00
John Dyson
71a5742716 Potentially fix a problem, whereby MSDOSFS can request buffers
larger than the vfs layer can provide.  We now automatically support
32K clusters if MSDOSFS is installed, and panic if a filesystem tries
to allocate a buffer larger than MAXBSIZE.

This commit is a result of some "prodding" by BDE.
1996-11-28 04:26:04 +00:00
John Dyson
9970cd3721 Improve the caching of small files like directories, while not
substantially increasing buffer space.  Specifically, we double
the number of buffers, but allocate only half the amount of memory
per buffer.  Note that VDIR files aren't cached unless instantiated
in a buffer.  This will significantly improve caching.
1996-11-17 02:11:01 +00:00
John Dyson
402bcb9621 Fix a problem that could cause msync (or many other things) to deadlock.
The heuristic for managment of memory backing the buffer cache was
nice, but didn't work due to some architectural problems.  Simplify
and improve the algorithm.
1996-10-17 03:04:43 +00:00
John Dyson
ffe2522e29 Fix 4 problems:
Major: When blocking occurs in allocbuf() for VMIO files,
	       excess wire counts could accumulate.
	Major: Pages are incorrectly accumulated into the physical
	       buffer for clustered reads.  This happens when bogus
	       page is needed.
	Minor: When reclaiming buffers, the async flag on the buffer
	       needs to be zero, or the reclaim is not optimal.
	Minor: The age flag should be cleared, if a buffer is wanted.
1996-10-06 07:50:05 +00:00
John Dyson
08c2c9ddf5 Fix an spl window, a page manipulation at interrupt time that was
incorrect, and correct the support for B_ORDERED.  The spl window
fix was from Peter Wemm, and his questions led me to find the problem with
the interrupt time page manipulation.
1996-09-20 02:26:35 +00:00
John Dyson
f9da2540d2 Add needed spl protection, and some minor cleanups in vfs_vmio_release.
Submitted by:	Peter Wemm <peter@spinner.dialix.com> and me.
1996-09-18 15:57:41 +00:00
John Dyson
8fdfa820e4 Clean up some more problems with freeing busy or wired pages. The
vfs_bio code was not waiting properly for page state until manipulating
it.
1996-09-14 04:40:33 +00:00
John Dyson
9fc1279b79 A modification that allows the driver strategy to modify the
B_ASYNC flag broke things pretty bad (freeing buffer already on
queue or other wierd buffer queue errors.)  The broken code is
left in commented out, but this makes the problem go away for
now.
1996-09-13 03:15:45 +00:00
John Dyson
5070c7f8c5 Addition of page coloring support. Various levels of coloring are afforded.
The default level works with minimal overhead, but one can also enable
full, efficient use of a 512K cache.  (Parameters can be generated
to support arbitrary cache sizes also.)
1996-09-08 20:44:49 +00:00
Justin T. Gibbs
0b64164fca Add bowrite.
Bowrite guarantees that buffers queued after a call to bowrite will
be written after the specified buffer (on a particular device).
Bowrite does this either by taking advantage of hardware ordering support
(e.g. tagged queueing on SCSI devices) or resorting to a synchronous write.
1996-09-06 05:37:53 +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
Poul-Henning Kamp
d1c4c866f0 Add separate kmalloc classes for BIO buffers and Ktrace info. 1996-08-04 20:13:08 +00:00
David Greenman
7c818168d5 Fixed a major bug that caused various pmap related panics, hangs, and reboots.
The i386 pmap module uses a special area of kernel virtual memory for mapping
of page tables pages when it needs to modify another process's virtual
address space. It's called the 'alternate page table map'. There is only one
of them and it's expected that only one process will be using it at once and
that the operation is atomic.
When the merged VM/buffer cache was implemented over a year ago, it became
necessary to rundown VM pages at I/O completion. The unfortunate and
unforeseen side effect of this is that pmap functions are now called at bio
interrupt time. If there happend to be a process using the alternate page
table map when this I/O completion occurred, it was possible for a different
process's address space to be switched into the alternate page table map -
leaving the current pmap process with the wrong address space mapped when
the interrupt completed. This resulted in BAD things happening like pages
being mapped or removed from the wrong address space, etc.. Since a very
common case of a process modifying another process's address space is during
fork when the kernel stack is inserted, one of the most common manifestations
of this bug was the kernel stack not being mapped properly, resulting in a
silent hang or reboot. This made it VERY difficult to troubleshoot this bug
(I've been trying to figure out the cause of this for >6 months). Fortunately,
the set of conditions that must be true before this problem occurs is
sufficiently rare enough that most people never saw the bug occur. As I/O
rates increase, however, so does the frequency of the crashes. This problem
used to kill wcarchive about every 10 days, but in more recent times when
the traffic exceeded >100GB/day, the machine could barely manage 6 hours of
uptime.
The fix is to make certain that no process has the pages mapped that are
involved in the I/O, before the I/O is started. The pages are made busy, so
no process will be able to map them, either, until the I/O has finished.
This side-steps the issue by still allowing the pmap functions to be called
at interrupt time, but also assuring that the alternate page table map won't
be switched.
Unfortunately, this appears to not be the only cause of this problem. :-(

Reviewed by:	dyson
1996-06-30 05:17:08 +00:00
Satoshi Asami
ad63a118b2 The Great PC98 Merge.
All new code is "#ifdef PC98"ed so this should make no difference to
PC/AT (and its clones) users.

Ok'd by:	core
Submitted by:	FreeBSD(98) development team
1996-06-14 11:02:28 +00:00
John Dyson
268e9c5397 Keep brelse from freeing busy pages. 1996-05-31 00:41:37 +00:00
John Dyson
301051a01e Make sure that we don't place a busy or held page onto the PQ_CACHE queue. 1996-05-24 05:21:58 +00:00
John Dyson
b18bfc3da7 This set of commits to the VM system does the following, and contain
contributions or ideas from Stephen McKay <syssgm@devetir.qld.gov.au>,
Alan Cox <alc@cs.rice.edu>, David Greenman <davidg@freebsd.org> and me:

	More usage of the TAILQ macros.  Additional minor fix to queue.h.
	Performance enhancements to the pageout daemon.
		Addition of a wait in the case that the pageout daemon
		has to run immediately.
		Slightly modify the pageout algorithm.
	Significant revamp of the pmap/fork code:
		1) PTE's and UPAGES's are NO LONGER in the process's map.
		2) PTE's and UPAGES's reside in their own objects.
		3) TOTAL elimination of recursive page table pagefaults.
		4) The page directory now resides in the PTE object.
		5) Implemented pmap_copy, thereby speeding up fork time.
		6) Changed the pv entries so that the head is a pointer
		   and not an entire entry.
		7) Significant cleanup of pmap_protect, and pmap_remove.
		8) Removed significant amounts of machine dependent
		   fork code from vm_glue.  Pushed much of that code into
		   the machine dependent pmap module.
		9) Support more completely the reuse of already zeroed
		   pages (Page table pages and page directories) as being
		   already zeroed.
	Performance and code cleanups in vm_map:
		1) Improved and simplified allocation of map entries.
		2) Improved vm_map_copy code.
		3) Corrected some minor problems in the simplify code.
	Implemented splvm (combo of splbio and splimp.)  The VM code now
		seldom uses splhigh.
	Improved the speed of and simplified kmem_malloc.
	Minor mod to vm_fault to avoid using pre-zeroed pages in the case
		of objects with backing objects along with the already
		existant condition of having a vnode.  (If there is a backing
		object, there will likely be a COW...  With a COW, it isn't
		necessary to start with a pre-zeroed page.)
	Minor reorg of source to perhaps improve locality of ref.
1996-05-18 03:38:05 +00:00
Poul-Henning Kamp
aa8de40ae5 Another sweep over the pmap/vm macros, this time with more focus on
the usage.  I'm not satisfied with the naming, but now at least there is
less bogus stuff around.
1996-05-03 21:01:54 +00:00
John Dyson
18ff64943e Correct handling of dirty pages in I/O buffers. The case where pages
residing in a buffer that had been dirtied by a process was being
handled incorrectly.  The pages were mistakenly placed into the
cache queue.  This would likely have the effect of mmaped page modifications
being lost when I/O system calls were being used simultaneously to
the same locations in a file.
Submitted by: davidg
1996-03-09 06:46:51 +00:00
John Dyson
c735bcf57d Fix the buffer queue problem differently. The previous fix could panic
with a buffer not on queue panic.
1996-03-03 01:04:28 +00:00
John Dyson
6538dda3dc 1) Fix a bug that a buffer is removed from a queue, but the
queue type is not set to QUEUE_NONE.  This appears to have
	caused a hang bug that has been lurking.
2)	Fix bugs that brelse'ing locked buffers do not "free" them, but the
	code assumes so.  This can cause hangs when LFS is used.
3)	Use malloced memory for directories when applicable.  The amount
	of malloced memory is seriously limited, but should decrease the
	amount of memory used by an average directory to 1/4 - 1/2 previous.
	This capability is fully tunable.  (Note that there is no config
	parameter, and might never be.)
4)	Bias slightly the buffer cache usage towards non-VMIO buffers.  Since
	the data in VMIO buffers is not lost when the buffer is reclaimed, this
	will help performance.  This is adjustable also.
1996-03-02 04:40:56 +00:00