in 4.2-REL which I ripped out in -stable and -current when implementing the
low-memory handling solution. However, maxlaunder turns out to be the saving
grace in certain very heavily loaded systems (e.g. newsreader box). The new
algorithm limits the number of pages laundered in the first pageout daemon
pass. If that is not sufficient then suceessive will be run without any
limit.
Write I/O is now pipelined using two sysctls, vfs.lorunningspace and
vfs.hirunningspace. This prevents excessive buffered writes in the
disk queues which cause long (multi-second) delays for reads. It leads
to more stable (less jerky) and generally faster I/O streaming to disk
by allowing required read ops (e.g. for indirect blocks and such) to occur
without interrupting the write stream, amoung other things.
NOTE: eventually, filesystem write I/O pipelining needs to be done on a
per-device basis. At the moment it is globalized.
Removed most of the hacks that were trying to deal with low-memory
situations prior to now.
The new code is based on the concept that I/O must be able to function in
a low memory situation. All major modules related to I/O (except
networking) have been adjusted to allow allocation out of the system
reserve memory pool. These modules now detect a low memory situation but
rather then block they instead continue to operate, then return resources
to the memory pool instead of cache them or leave them wired.
Code has been added to stall in a low-memory situation prior to a vnode
being locked.
Thus situations where a process blocks in a low-memory condition while
holding a locked vnode have been reduced to near nothing. Not only will
I/O continue to operate, but many prior deadlock conditions simply no
longer exist.
Implement a number of VFS/BIO fixes
(found by Ian): in biodone(), bogus-page replacement code, the loop
was not properly incrementing loop variables prior to a continue
statement. We do not believe this code can be hit anyway but we
aren't taking any chances. We'll turn the whole section into a
panic (as it already is in brelse()) after the release is rolled.
In biodone(), the foff calculation was incorrectly
clamped to the iosize, causing the wrong foff to be calculated
for pages in the case of an I/O error or biodone() called without
initiating I/O. The problem always caused a panic before. Now it
doesn't. The problem is mainly an issue with NFS.
Fixed casts for ~PAGE_MASK. This code worked properly before only
because the calculations use signed arithmatic. Better to properly
extend PAGE_MASK first before inverting it for the 64 bit masking
op.
In brelse(), the bogus_page fixup code was improperly throwing
away the original contents of 'm' when it did the j-loop to
fix the bogus pages. The result was that it would potentially
invalidate parts of the *WRONG* page(!), leading to corruption.
There may still be cases where a background bitmap write is
being duplicated, causing potential corruption. We have identified
a potentially serious bug related to this but the fix is still TBD.
So instead this patch contains a KASSERT to detect the problem
and panic the machine rather then continue to corrupt the filesystem.
The problem does not occur very often.. it is very hard to
reproduce, and it may or may not be the cause of the corruption
people have reported.
Review by: (VFS/BIO: mckusick, Ian Dowse <iedowse@maths.tcd.ie>)
Testing by: (VM/Deadlock) Paul Saab <ps@yahoo-inc.com>
<sys/bio.h>.
<sys/bio.h> is now a prerequisite for <sys/buf.h> but it shall
not be made a nested include according to bdes teachings on the
subject of nested includes.
Diskdrivers and similar stuff below specfs::strategy() should no
longer need to include <sys/buf.> unless they need caching of data.
Still a few bogus uses of struct buf to track down.
Repocopy by: peter
Exceptions:
Vinum untouched. This means that it cannot be compiled.
Greg Lehey is on the case.
CCD not converted yet, casts to struct buf (still safe)
atapi-cd casts to struct buf to examine B_PHYS
(Much of this done by script)
Move B_ORDERED flag to b_ioflags and call it BIO_ORDERED.
Move b_pblkno and b_iodone_chain to struct bio while we transition, they
will be obsoleted once bio structs chain/stack.
Add bio_queue field for struct bio aware disksort.
Address a lot of stylistic issues brought up by bde.
async I/O's. The sequential read heuristic has been extended to
cover writes as well. We continue to call cluster_write() normally,
thus blocks in the file will still be reallocated for large (but still
random) I/O's, but I/O will only be initiated for truely sequential
writes.
This solves a number of annoying situations, especially with DBM (hash
method) writes, and also has the side effect of fixing a number of
(stupid) benchmarks.
Reviewed-by: mckusick
field in struct buf: b_iocmd. The b_iocmd is enforced to have
exactly one bit set.
B_WRITE was bogusly defined as zero giving rise to obvious coding
mistakes.
Also eliminate the redundant struct buf flag B_CALL, it can just
as efficiently be done by comparing b_iodone to NULL.
Should you get a panic or drop into the debugger, complaining about
"b_iocmd", don't continue. It is likely to write on your disk
where it should have been reading.
This change is a step in the direction towards a stackable BIO capability.
A lot of this patch were machine generated (Thanks to style(9) compliance!)
Vinum users: Greg has not had time to test this yet, be careful.
Merge the contents (less some trivial bordering the silly comments)
of <vm/vm_prot.h> and <vm/vm_inherit.h> into <vm/vm.h>. This puts
the #defines for the vm_inherit_t and vm_prot_t types next to their
typedefs.
This paves the road for the commit to follow shortly: change
useracc() to use VM_PROT_{READ|WRITE} rather than B_{READ|WRITE}
as argument.
large (1G) memory machine configurations. I was able to run 'dbench 32'
on a 32MB system without bring the machine to a grinding halt.
* buffer cache hash table now dynamically allocated. This will
have no effect on memory consumption for smaller systems and
will help scale the buffer cache for larger systems.
* minor enhancement to pmap_clearbit(). I noticed that
all the calls to it used constant arguments. Making
it an inline allows the constants to propogate to
deeper inlines and should produce better code.
* removal of inherent vfs_ioopt support through the emplacement
of appropriate #ifdef's, with John's permission. If we do not
find a use for it by the end of the year we will remove it entirely.
* removal of getnewbufloops* counters & sysctl's - no longer
necessary for debugging, getnewbuf() is now optimal.
* buffer hash table functions removed from sys/buf.h and localized
to vfs_bio.c
* VFS_BIO_NEED_DIRTYFLUSH flag and support code added
( bwillwrite() ), allowing processes to block when too many dirty
buffers are present in the system.
* removal of a softdep test in bdwrite() that is no longer necessary
now that bdwrite() no longer attempts to flush dirty buffers.
* slight optimization added to bqrelse() - there is no reason
to test for available buffer space on B_DELWRI buffers.
* addition of reverse-scanning code to vfs_bio_awrite().
vfs_bio_awrite() will attempt to locate clusterable areas
in both the forward and reverse direction relative to the
offset of the buffer passed to it. This will probably not
make much of a difference now, but I believe we will start
to rely on it heavily in the future if we decide to shift
some of the burden of the clustering closer to the actual
I/O initiation.
* Removal of the newbufcnt and lastnewbuf counters that Kirk
added. They do not fix any race conditions that haven't already
been fixed by the gbincore() test done after the only call
to getnewbuf(). getnewbuf() is a static, so there is no chance
of it being misused by other modules. ( Unless Kirk can think
of a specific thing that this code fixes. I went through it
very carefully and didn't see anything ).
* removal of VOP_ISLOCKED() check in flushbufqueues(). I do not
think this check is necessary, the buffer should flush properly
whether the vnode is locked or not. ( yes? ).
* removal of extra arguments passed to getnewbuf() that are not
necessary.
* missed cluster_wbuild() that had to be a cluster_wbuild_wb() in
vfs_cluster.c
* vn_write() now calls bwillwrite() *PRIOR* to locking the vnode,
which should greatly aid flushing operations in heavy load
situations - both the pageout and update daemons will be able
to operate more efficiently.
* removal of b_usecount. We may add it back in later but for now
it is useless. Prior implementations of the buffer cache never
had enough buffers for it to be useful, and current implementations
which make more buffers available might not benefit relative to
the amount of sophistication required to implement a b_usecount.
Straight LRU should work just as well, especially when most things
are VMIO backed. I expect that (even though John will not like
this assumption) directories will become VMIO backed some point soon.
Submitted by: Matthew Dillon <dillon@backplane.com>
Reviewed by: Kirk McKusick <mckusick@mckusick.com>
allow changes to the filesystem's write_behind behavior. By the
default the filesystem aggressively issues write_behind's. Three values
may be specified for vfs.write_behind. 0 disables write_behind, 1 results
in historical operation (agressive write_behind), and 2 is an experimental
backed-off write_behind. The values of 0 and 1 are recommended. The value
of 0 is recommended in conjuction with an increase in the number of
NBUF's and the number of dirty buffers allowed (vfs.{lo,hi}dirtybuffers).
Note that a value of 0 will radically increase the dirty buffer load on
the system. Future work on write_behind behavior will use values 2 and
greater for testing purposes.
Submitted by: Matthew Dillon <dillon@apollo.backplane.com>
Reviewed by: Kirk McKusick <mckusick@mckusick.com>
(really this time) fix pageout to swap and a couple of clustering cases.
This simplifies BUF_KERNPROC() so that it unconditionally reassigns the
lock owner rather than testing B_ASYNC and having the caller decide when
to do the reassign. At present this is required because some places use
B_CALL/b_iodone to free the buffers without B_ASYNC being set. Also,
vfs_cluster.c explicitly calls BUF_KERNPROC() when attaching the buffers
rather than the parent walking the cluster_head tailq.
Reviewed by: Kirk McKusick <mckusick@mckusick.com>
lockmgr locks. This commit should be functionally equivalent to the old
semantics. That is, all buffer locking is done with LK_EXCLUSIVE
requests. Changes to take advantage of LK_SHARED and LK_RECURSIVE will
be done in future commits.
would occur when clustering them - caused by running out of buffers
and taking a degenerate code path as a result. It appears that waiting
instead for buffers to become available is okay.
Submitted by: Matthew Dillon <dillon@apollo.backplane.com>
Discovered by: Craig A Soules <soules+@andrew.cmu.edu>
piecemeal, middle-of-file writes for NFS. These hacks have caused no
end of trouble, especially when combined with mmap(). I've removed
them. Instead, NFS will issue a read-before-write to fully
instantiate the struct buf containing the write. NFS does, however,
optimize piecemeal appends to files. For most common file operations,
you will not notice the difference. The sole remaining fragment in
the VFS/BIO system is b_dirtyoff/end, which NFS uses to avoid cache
coherency issues with read-merge-write style operations. NFS also
optimizes the write-covers-entire-buffer case by avoiding the
read-before-write. There is quite a bit of room for further
optimization in these areas.
The VM system marks pages fully-valid (AKA vm_page_t->valid =
VM_PAGE_BITS_ALL) in several places, most noteably in vm_fault. This
is not correct operation. The vm_pager_get_pages() code is now
responsible for marking VM pages all-valid. A number of VM helper
routines have been added to aid in zeroing-out the invalid portions of
a VM page prior to the page being marked all-valid. This operation is
necessary to properly support mmap(). The zeroing occurs most often
when dealing with file-EOF situations. Several bugs have been fixed
in the NFS subsystem, including bits handling file and directory EOF
situations and buf->b_flags consistancy issues relating to clearing
B_ERROR & B_INVAL, and handling B_DONE.
getblk() and allocbuf() have been rewritten. B_CACHE operation is now
formally defined in comments and more straightforward in
implementation. B_CACHE for VMIO buffers is based on the validity of
the backing store. B_CACHE for non-VMIO buffers is based simply on
whether the buffer is B_INVAL or not (B_CACHE set if B_INVAL clear,
and vise-versa). biodone() is now responsible for setting B_CACHE
when a successful read completes. B_CACHE is also set when a bdwrite()
is initiated and when a bwrite() is initiated. VFS VOP_BWRITE
routines (there are only two - nfs_bwrite() and bwrite()) are now
expected to set B_CACHE. This means that bowrite() and bawrite() also
set B_CACHE indirectly.
There are a number of places in the code which were previously using
buf->b_bufsize (which is DEV_BSIZE aligned) when they should have
been using buf->b_bcount. These have been fixed. getblk() now clears
B_DONE on return because the rest of the system is so bad about
dealing with B_DONE.
Major fixes to NFS/TCP have been made. A server-side bug could cause
requests to be lost by the server due to nfs_realign() overwriting
other rpc's in the same TCP mbuf chain. The server's kernel must be
recompiled to get the benefit of the fixes.
Submitted by: Matthew Dillon <dillon@apollo.backplane.com>
including alan, john, me, luoqi, and kirk
Submitted by: Matt Dillon <dillon@frebsd.org>
This change implements a relatively sophisticated fix to getnewbuf().
There were two problems with getnewbuf(). First, the writerecursion
can lead to a system stack overflow when you have NFS and/or VN
devices in the system. Second, the free/dirty buffer accounting was
completely broken. Not only did the nfs routines blow it trying to
manually account for the buffer state, but the accounting that was
done did not work well with the purpose of their existance: figuring
out when getnewbuf() needs to sleep.
The meat of the change is to kern/vfs_bio.c. The remaining diffs are
all minor except for NFS, which includes both the fixes for bp
interaction AND fixes for a 'biodone(): buffer already done' lockup.
Sys/buf.h also contains a chaining structure which is not used by
this patchset but is used by other patches that are coming soon.
This patch deliniated by tags PRE_MAT_GETBUF and POST_MAT_GETBUF.
(sorry for the missing T matt)
changes to the VM system to support the new swapper, VM bug
fixes, several VM optimizations, and some additional revamping of the
VM code. The specific bug fixes will be documented with additional
forced commits. This commit is somewhat rough in regards to code
cleanup issues.
Reviewed by: "John S. Dyson" <root@dyson.iquest.net>, "David Greenman" <dg@root.com>
system, the mapping from logical to physical block number may be lost.
Hence we have to check for a reconstituted buffer and redo the call to
VOP_BMAP if the physical block number has been lost.
MALLOC_DEFINE() and MALLOC_DEFINE() is needed by the recently
reenabled "reallocblks" code, but <sys/kernel.h> was only included
if CLUSTERDEBUG was defined. This was too harmless. gcc only
warns about garbage like `SYSINIT(blech);' at file scope ...
basically do a on-the-fly defragmentation of the FFS filesystem, changing
file block allocations to make them contiguous. Thanks to Kirk McKusick
for providing hints on what needed to be done to get this working.
Add some overflow checks to read/write (from bde).
Change all modifications to vm_page::flags, vm_page::busy, vm_object::flags
and vm_object::paging_in_progress to use operations which are not
interruptable.
Reviewed by: Bruce Evans <bde@zeta.org.au>
managed to avoid corruption of this variable by luck (the compiler used a
memory read-modify-write instruction which wasn't interruptable) but other
architectures cannot.
With this change, I am now able to 'make buildworld' on the alpha (sfx: the
crowd goes wild...)
as the value in b_vp is often not really what you want.
(and needs to be frobbed). more cleanups will follow this.
Reviewed by: Bruce Evans <bde@freebsd.org>
unexpectedly do not complete writes even with sync I/O requests.
This should help the behavior of mmaped files when using
softupdates (and perhaps in other circumstances also.)
called from vfs_bio_awrite() without going through cluster_write()
or ufs_bmaparray(), in particular for all writes to block disk devices.
Only ufs_bmaparray() sets vp->v_maxio in a correct way, and it doesn't
seem to be called early enough even for regular files.
In vfs_bio.c, remove b_generation count usage,
remove redundant reassignbuf,
remove redundant spl(s),
manage page PG_ZERO flags more correctly,
utilize in invalid value for b_offset until it
is properly initialized. Add asserts
for #ifdef DIAGNOSTIC, when b_offset is
improperly used.
when a process is not performing I/O, and just waiting
on a buffer generally, make the sleep priority
low.
only check page validity in getblk for B_VMIO buffers.
In vfs_cluster, add b_offset asserts, correct pointer calculation
for clustered reads. Improve readability of certain parts of
the code. Remove redundant spl(s).
In vfs_subr, correct usage of vfs_bio_awrite (From Andrew Gallatin
<gallatin@cs.duke.edu>). More vtruncbuf problems fixed.
problems. Tor Egge and others have helped with various VM bugs
lately, but don't blame him -- blame me!!!
pmap.c:
1) Create an object for kernel page table allocations. This
fixes a bogus allocation method previously used for such, by
grabbing pages from the kernel object, using bogus pindexes.
(This was a code cleanup, and perhaps a minor system stability
issue.)
pmap.c:
2) Pre-set the modify and accessed bits when prudent. This will
decrease bus traffic under certain circumstances.
vfs_bio.c, vfs_cluster.c:
3) Rather than calculating the beginning virtual byte offset
multiple times, stick the offset into the buffer header, so
that the calculated offset can be reused. (Long long multiplies
are often expensive, and this is a probably unmeasurable performance
improvement, and code cleanup.)
vfs_bio.c:
4) Handle write recursion more intelligently (but not perfectly) so
that it is less likely to cause a system panic, and is also
much more robust.
vfs_bio.c:
5) getblk incorrectly wrote out blocks that are incorrectly sized.
The problem is fixed, and writes blocks out ONLY when B_DELWRI
is true.
vfs_bio.c:
6) Check that already constituted buffers have fully valid pages. If
not, then make sure that the B_CACHE bit is not set. (This was
a major source of Sig-11 type problems.)
vfs_bio.c:
7) Fix a potential system deadlock due to an incorrectly specified
sleep priority while waiting for a buffer write operation. The
change that I made opens the system up to serious problems, and
we need to examine the issue of process sleep priorities.
vfs_cluster.c, vfs_bio.c:
8) Make clustered reads work more correctly (and more completely)
when buffers are already constituted, but not fully valid.
(This was another system reliability issue.)
vfs_subr.c, ffs_inode.c:
9) Create a vtruncbuf function, which is used by filesystems that
can truncate files. The vinvalbuf forced a file sync type operation,
while vtruncbuf only invalidates the buffers past the new end of file,
and also invalidates the appropriate pages. (This was a system reliabiliy
and performance issue.)
10) Modify FFS to use vtruncbuf.
vm_object.c:
11) Make the object rundown mechanism for OBJT_VNODE type objects work
more correctly. Included in that fix, create pager entries for
the OBJT_DEAD pager type, so that paging requests that might slip
in during race conditions are properly handled. (This was a system
reliability issue.)
vm_page.c:
12) Make some of the page validation routines be a little less picky
about arguments passed to them. Also, support page invalidation
change the object generation count so that we handle generation
counts a little more robustly.
vm_pageout.c:
13) Further reduce pageout daemon activity when the system doesn't
need help from it. There should be no additional performance
decrease even when the pageout daemon is running. (This was
a significant performance issue.)
vnode_pager.c:
14) Teach the vnode pager to handle race conditions during vnode
deallocations.
has been some bitrot and incorrect assumptions in the vfs_bio code. These
problems have manifest themselves worse on NFS type filesystems, but can
still affect local filesystems under certain circumstances. Most of
the problems have involved mmap consistancy, and as a side-effect broke
the vfs.ioopt code. This code might have been committed seperately, but
almost everything is interrelated.
1) Allow (pmap_object_init_pt) prefaulting of buffer-busy pages that
are fully valid.
2) Rather than deactivating erroneously read initial (header) pages in
kern_exec, we now free them.
3) Fix the rundown of non-VMIO buffers that are in an inconsistent
(missing vp) state.
4) Fix the disassociation of pages from buffers in brelse. The previous
code had rotted and was faulty in a couple of important circumstances.
5) Remove a gratuitious buffer wakeup in vfs_vmio_release.
6) Remove a crufty and currently unused cluster mechanism for VBLK
files in vfs_bio_awrite. When the code is functional, I'll add back
a cleaner version.
7) The page busy count wakeups assocated with the buffer cache usage were
incorrectly cleaned up in a previous commit by me. Revert to the
original, correct version, but with a cleaner implementation.
8) The cluster read code now tries to keep data associated with buffers
more aggressively (without breaking the heuristics) when it is presumed
that the read data (buffers) will be soon needed.
9) Change to filesystem lockmgr locks so that they use LK_NOPAUSE. The
delay loop waiting is not useful for filesystem locks, due to the
length of the time intervals.
10) Correct and clean-up spec_getpages.
11) Implement a fully functional nfs_getpages, nfs_putpages.
12) Fix nfs_write so that modifications are coherent with the NFS data on
the server disk (at least as well as NFS seems to allow.)
13) Properly support MS_INVALIDATE on NFS.
14) Properly pass down MS_INVALIDATE to lower levels of the VM code from
vm_map_clean.
15) Better support the notion of pages being busy but valid, so that
fewer in-transit waits occur. (use p->busy more for pageouts instead
of PG_BUSY.) Since the page is fully valid, it is still usable for
reads.
16) It is possible (in error) for cached pages to be busy. Make the
page allocation code handle that case correctly. (It should probably
be a printf or panic, but I want the system to handle coding errors
robustly. I'll probably add a printf.)
17) Correct the design and usage of vm_page_sleep. It didn't handle
consistancy problems very well, so make the design a little less
lofty. After vm_page_sleep, if it ever blocked, it is still important
to relookup the page (if the object generation count changed), and
verify it's status (always.)
18) In vm_pageout.c, vm_pageout_clean had rotted, so clean that up.
19) Push the page busy for writes and VM_PROT_READ into vm_pageout_flush.
20) Fix vm_pager_put_pages and it's descendents to support an int flag
instead of a boolean, so that we can pass down the invalidate bit.
MUST be PG_BUSY. It is bogus to free a page that isn't busy,
because it is in a state of being "unavailable" when being
freed. The additional advantage is that the page_remove code
has a better cross-check that the page should be busy and
unavailable for other use. There were some minor problems
with the collapse code, and this plugs those subtile "holes."
Also, the vfs_bio code wasn't checking correctly for PG_BUSY
pages. I am going to develop a more consistant scheme for
grabbing pages, busy or otherwise. For now, we are stuck
with the current morass.
