Commit Graph

505 Commits

Author SHA1 Message Date
Jeff Roberson
084d64ac21 - Add the B_NEEDSGIANT flag which is only set if the vnode that owns a buf
requires Giant.  It is set in bgetvp and cleared in brelvp.
 - Create QUEUE_DIRTY_GIANT for dirty buffers that require giant.
 - In the buf daemon, only grab giant when processing QUEUE_DIRTY_GIANT and
   only if we think there are buffers in that queue.

Sponsored by:	Isilon Systems, Inc.
2006-03-31 02:56:30 +00:00
Pawel Jakub Dawidek
96c0381f5c Destroy "bip" bio in error case.
Found by:	Coverity Prevent analysis tool
Coverity ID:	795
MFC after:	3 days
2006-03-22 00:42:41 +00:00
Tor Egge
c78226329a For low memory situations, non-VMIO buffers didnt't release pages back to
the system when brelse() was called with B_RELBUF set on the buffer.  This
could be a problem when the system was low on memory, had many buffers on
QUEUE_EMPTYKVA and started to traverse directories.  For each getnewbuf(),
pages were allocated from the system, driving the free reserve downwards.
For each brelse(), the system put the buffer on QUEUE_CLEAN, with B_INVAL
set.

This commit changes the semantics of B_RELBUF to also free pages from
non-VMIO buffers.

Reviewed by:	alc
2006-02-02 21:37:39 +00:00
Alan Cox
bb53e2bf27 Remove an unnecessary call to pmap_remove_all(). The given page is not
mapped because its contents are invalid.

Reviewed by: tegge
2006-01-23 00:00:45 +00:00
Tor Egge
dffaf91aa3 Set flag in needsbuffer while still holding bqlock to avoid lost wakeup. 2006-01-16 22:09:47 +00:00
Alexander Leidinger
ef39c05baa MI changes:
- provide an interface (macros) to the page coloring part of the VM system,
   this allows to try different coloring algorithms without the need to
   touch every file [1]
 - make the page queue tuning values readable: sysctl vm.stats.pagequeue
 - autotuning of the page coloring values based upon the cache size instead
   of options in the kernel config (disabling of the page coloring as a
   kernel option is still possible)

MD changes:
 - detection of the cache size: only IA32 and AMD64 (untested) contains
   cache size detection code, every other arch just comes with a dummy
   function (this results in the use of default values like it was the
   case without the autotuning of the page coloring)
 - print some more info on Intel CPU's (like we do on AMD and Transmeta
   CPU's)

Note to AMD owners (IA32 and AMD64): please run "sysctl vm.stats.pagequeue"
and report if the cache* values are zero (= bug in the cache detection code)
or not.

Based upon work by:	Chad David <davidc@acns.ab.ca> [1]
Reviewed by:		alc, arch (in 2004)
Discussed with:		alc, Chad David, arch (in 2004)
2005-12-31 14:39:20 +00:00
Craig Rodrigues
6951bea6c8 Changes imported from XFS for FreeBSD project:
- add fields to struct buf (needed by XFS)
    - 3 private fields: b_fsprivate1, b_fsprivate2, b_fsprivate3
    - b_pin_count, count of pinned buffer

- add new B_MANAGED flag
- add breada() function to initiate asynchronous I/O on read-ahead blocks.
- add bufdone_finish(), bpin(), bunpin_wait() functions

Patches provided by:	kan
Reviewed by:		phk
Silence on:		arch@
2005-12-07 03:39:08 +00:00
Robert Watson
5bb84bc84b Normalize a significant number of kernel malloc type names:
- Prefer '_' to ' ', as it results in more easily parsed results in
  memory monitoring tools such as vmstat.

- Remove punctuation that is incompatible with using memory type names
  as file names, such as '/' characters.

- Disambiguate some collisions by adding subsystem prefixes to some
  memory types.

- Generally prefer lower case to upper case.

- If the same type is defined in multiple architecture directories,
  attempt to use the same name in additional cases.

Not all instances were caught in this change, so more work is required to
finish this conversion.  Similar changes are required for UMA zone names.
2005-10-31 15:41:29 +00:00
Tor Egge
8272da3106 Release clean buffer with wrong size and no dependencies also for non-VMIO
case.
2005-10-09 22:41:25 +00:00
Don Lewis
bd3c2d867d Un-staticize waitrunningbufspace() and call it before returning from
ffs_copyonwrite() if any async writes were launched.

Restore the threads previous TDP_NORUNNINGBUF state before returning
from ffs_copyonwrite().
2005-09-30 18:07:41 +00:00
Don Lewis
6c8b634f1d Un-staticize runningbufwakeup() and staticize updateproc.
Add a new private thread flag to indicate that the thread should
not sleep if runningbufspace is too large.

Set this flag on the bufdaemon and syncer threads so that they skip
the waitrunningbufspace() call in bufwrite() rather than than
checking the proc pointer vs. the known proc pointers for these two
threads.  A way of preventing these threads from being starved for
I/O but still placing limits on their outstanding I/O would be
desirable.

Set this flag in ffs_copyonwrite() to prevent bufwrite() calls from
blocking on the runningbufspace check while holding snaplk.  This
prevents snaplk from being held for an arbitrarily long period of
time if runningbufspace is high and greatly reduces the contention
for snaplk.  The disadvantage is that ffs_copyonwrite() can start
a large amount of I/O if there are a large number of snapshots,
which could cause a deadlock in other parts of the code.

Call runningbufwakeup() in ffs_copyonwrite() to decrement runningbufspace
before attempting to grab snaplk so that I/O requests waiting on
snaplk are not counted in runningbufspace as being in-progress.
Increment runningbufspace again before actually launching the
original I/O request.

Prior to the above two changes, the system could deadlock if enough
I/O requests were blocked by snaplk to prevent runningbufspace from
falling below lorunningspace and one of the bawrite() calls in
ffs_copyonwrite() blocked in waitrunningbufspace() while holding
snaplk.

See <http://www.holm.cc/stress/log/cons143.html>
2005-09-30 01:30:01 +00:00
Peter Edwards
d41c4674c2 Close a race in biodone(), whereby the bio_done field of the passed
bio may have been freed and reassigned by the wakeup before being
tested after releasing the bdonelock.

There's a non-zero chance this is the cause of a few of the crashes
knocking around with biodone() sitting in the stack backtrace.

Reviewed By: phk@
2005-09-29 10:37:20 +00:00
Jeff Roberson
9e2aaec1e3 - Use lockmgr_printinfo rather than rolling our own. This introduces a
slight problem by using printf instead of db_printf however
   'show lockedvnods' does the same so I believe it is ok for now.
2005-08-03 05:02:08 +00:00
Alan Cox
ec9c9e7363 Eliminate inconsistency in the setting of the B_DONE flag. Specifically,
make the b_iodone callback responsible for setting it if it is needed.
Previously, it was set unconditionally by bufdone() without holding
whichever lock is shared by the b_iodone callback and the corresponding
top-half function.  Consequently, in a race, the top-half function could
conclude that operation was done before the b_iodone callback finished.
See, for example, aio_physwakeup() and aio_fphysio().

Note: I don't believe that the other, more widely-used b_iodone callbacks
are affected.

Discussed with: jeff
Reviewed by: phk
MFC after: 2 weeks
2005-07-20 19:06:06 +00:00
Jeff Roberson
7a06fe49dc - Add and enhance asserts related to the wrong bufobj panic.
Sponsored by:	Isilon Systems, Inc.
Approved by:	re (blanket vfs)
2005-06-14 20:32:27 +00:00
Jeff Roberson
748c92fbad - Split one KASSERT in bremfree() into two to aid in debugging.
Sponsored by:	Isilon Systems, Inc.
2005-06-13 00:45:05 +00:00
Brian Feldman
cc3149b1ea Fix a serious deadlock with the NFS client. Given a large enough
atomic write request, it can fill the buffer cache with the entirety
of that write in order to handle retries.  However, it never drops
the vnode lock, or else it wouldn't be atomic, so it ends up waiting
indefinitely for more buf memory that cannot be gotten as it has it
all, and it waits in an uncancellable state.

To fix this, hibufspace is exported and scaled to a reasonable
fraction.  This is used as the limit of how much of an atomic write
request by the NFS client will be handled asynchronously.  If the
request is larger than this, it will be turned into a synchronous
request which won't deadlock the system.  It's possible this value is
far off from what is required by some, so it shall be tunable as soon
as mount_nfs(8) learns of the new field.

The slowdown between an asynchronous and a synchronous write on NFS
appears to be on the order of 2x-4x.

General nod by:	gad
MFC after:	2 weeks
More testing:	wes
PR:		kern/79208
2005-06-10 23:50:41 +00:00
Jeff Roberson
a3d239bc29 - My sub-par public school education has been exposed. s/sentinal/sentinel/
Noticed by:	Emil Mikulic
2005-06-09 04:40:20 +00:00
Jeff Roberson
9e879a5ee0 - Under heavy IO load the buf daemon can run for many hundereds of
milliseconds due to what is essentially n^2 algorithmic complexity.  This
   change makes the algorithm N*2 instead.  This heavy processing manifested
   itself as skipping in audio and video playback due to the long scheduling
   latencies and contention on giant by pcm.
 - flushbufqueues() is now responsible for flushing multiple buffers
   rather than one at a time.  This allows us to save our progress in the
   list by using a sentinal.  We must do the numdirtywakeup() and
   waitrunningbufspace() here now rather than in buf_daemon().
 - Also add a uio_yield() after we have processed the list once for bufs
   without deps and again for bufs with deps.  This is to release Giant
   and allow any other giant locked code to proceed.

Tested by:	Many users on current@
Revealed by:	schedgraph traces sent by Emil Mikulic & Anthony Ginepro
2005-06-08 20:26:05 +00:00
Jeff Roberson
1f22a07afd - Add bufobj_wrefl() to add a write ref to a bufobj that is already locked. 2005-05-30 07:01:18 +00:00
Jeff Roberson
4a723b3604 - Remove long dead splbio() calls and comments relating to the old
synchronization mechanism.
2005-04-30 12:18:50 +00:00
Jeff Roberson
ba4f7c7023 - Don't acquire Giant before calling b_biodone, individual consumers are
now required to do so themselves.

Sponsored by:	Isilon Systems, Inc.
2005-04-30 11:44:22 +00:00
Jeff Roberson
0d12524bbf - Add two KASSERTs to prevent us from recycling a buf that is still on a
bufobj list.

Sponsored by:	Isilon Systems, Inc.
2005-04-22 00:53:20 +00:00
Jeff Roberson
6c759f3558 - Add information about the buf lock to db_show_buffer.
- Add a 'show lockedbufs' command that is similar to show lockedvnods.

Sponsored by:	Isilon Systems, Inc.
2005-03-25 00:20:37 +00:00
Jeff Roberson
ec346d1040 - Lock access to the buffer_map with the vm_map lock. In 4.x this was
done with splbio, in 5.x this was done with Giant.

Discussed with:		alc
Reported by:		julian, pho
2005-03-08 09:34:54 +00:00
Poul-Henning Kamp
1ba212823f Make various vnode related functions static 2005-02-10 12:28:58 +00:00
Jeff Roberson
5c18d18b1d - Add more information to the getnewbuf() recycling KTR.
Sponsored by:	Isilon Systems, Inc.
2005-02-10 02:22:56 +00:00
Jeff Roberson
b56dc9a785 - Remove an invalid KASSERT added in recent background write reshuffling.
Sponsored by:	Isilon Systems, Inc.
2005-02-08 23:25:08 +00:00
Poul-Henning Kamp
dd19a799b8 Background writes are entirely an FFS/Softupdates thing.
Give FFS vnodes a specific bufwrite method which contains all the
background write stuff and then calls into the default bufwrite()
for the rest of the job.

Remove all the background write related stuff from the normal bufwrite.

This drags the softdep_move_dependencies() back into FFS.

Long term, it is worth looking at simply copying the data into
allocated memory and issuing the bio directly and not create the
"shadow buf" in the first place (just like copy-on-write is done
in snapshots for instance).  I don't think we really gain anything
but complexity from doing this with a buf.
2005-02-08 20:29:10 +00:00
Jeff Roberson
8364446643 - Don't release BKGRDINPROG until after we've bufdone'd the copy.
Sponsored by:	Isilon Systems, Inc.
2005-02-05 01:26:14 +00:00
Jeff Roberson
bd8d684fd7 - Don't drop the wref on the bufobj until after bufdone() has completed.
Without this, threads waiting in bufobj_wwait() may wakeup prior to
   bufdone() completing.

Sponsored by:	Isilon Systems, Inc.
2005-01-28 17:48:58 +00:00
Poul-Henning Kamp
8516dd18e1 Don't use VOP_GETVOBJECT, use vp->v_object directly. 2005-01-25 00:40:01 +00:00
Poul-Henning Kamp
35764be39e Kill the VV_OBJBUF and test the v_object for NULL instead. 2005-01-24 13:13:57 +00:00
Jeff Roberson
71ddd673b1 - Add CTR calls to trace the lifecycle of a buffer.
- Remove some KASSERTs which are invalid if the appropriate lock is
   not held.
 - Slightly restructure bremfree() so that it is more sane.
 - Change the flush code in bdwrite() to avoid acquiring a mutex
   whenever possible.
 - Change the flush code in bdwrite() to avoid holding the bufobj mutex
   while calling buf_countdeps().  This introduces a lock-order
   relationship with the softdep lock that can not otherwise be resolved.
 - Don't set B_DONE until bufdone() is complete, otherwise another
   processor may believe the buf is done before it is.
 - Only acquire Giant if the caller has set b_iodone.  Don't grab giant
   around normal bufdone() calls.

Sponsored By:	Isilon Systems, Inc.
2005-01-24 10:47:04 +00:00
Poul-Henning Kamp
6ef8480a88 Add BO_SYNC() and add a default which uses the secret vnode pointer
and VOP_FSYNC() for now.
2005-01-11 10:43:08 +00:00
Poul-Henning Kamp
8df6bac4c7 Remove the unused credential argument from VOP_FSYNC() and VFS_SYNC().
I'm not sure why a credential was added to these in the first place, it is
not used anywhere and it doesn't make much sense:

	The credentials for syncing a file (ability to write to the
	file) should be checked at the system call level.

	Credentials for syncing one or more filesystems ("none")
	should be checked at the system call level as well.

	If the filesystem implementation needs a particular credential
	to carry out the syncing it would logically have to the
	cached mount credential, or a credential cached along with
	any delayed write data.

Discussed with:	rwatson
2005-01-11 07:36:22 +00:00
Jeff Roberson
b646893f0f - Eliminate the acquisition and release of the bqlock in bremfree() by
setting the B_REMFREE flag in the buf.  This is done to prevent lock order
   reversals with code that must call bremfree() with a local lock held.
   This also reduces overhead by removing two lock operations per buf for
   fsync() and similar.
 - Check for the B_REMFREE flag in brelse() and bqrelse() after the bqlock
   has been acquired so that we may remove ourself from the free-list.
 - Provide a bremfreef() function to immediately remove a buf from a
   free-list for use only by NFS.  This is done because the nfsclient code
   overloads the b_freelist queue for its own async. io queue.
 - Simplify the numfreebuffers accounting by removing a switch statement
   that executed the same code in every possible case.
 - getnewbuf() can encounter locked bufs on free-lists once Giant is removed.
   Remove a panic associated with this condition and delay asserts that
   inspect the buf until after it is locked.

Reviewed by:	phk
Sponsored by:	Isilon Systems, Inc.
2004-11-18 08:44:09 +00:00
Poul-Henning Kamp
6e67e2a710 Retire b_magic now, we have the bufobj containing the same hint. 2004-11-04 09:48:18 +00:00
Poul-Henning Kamp
9f7a3028d5 Change buf->b_object to buf->b_bufobj->bo_object
some whitespace fixes.
2004-11-04 09:06:54 +00:00
Poul-Henning Kamp
9bc4d9a495 whitespace 2004-11-04 08:25:52 +00:00
Poul-Henning Kamp
c569065139 Remove buf->b_dev field. 2004-11-04 07:59:57 +00:00
Alan Cox
d19ef81437 The synchronization provided by vm object locking has eliminated the
need for most calls to vm_page_busy().  Specifically, most calls to
vm_page_busy() occur immediately prior to a call to vm_page_remove().
In such cases, the containing vm object is locked across both calls.
Consequently, the setting of the vm page's PG_BUSY flag is not even
visible to other threads that are following the synchronization
protocol.

This change (1) eliminates the calls to vm_page_busy() that
immediately precede a call to vm_page_remove() or functions, such as
vm_page_free() and vm_page_rename(), that call it and (2) relaxes the
requirement in vm_page_remove() that the vm page's PG_BUSY flag is
set.  Now, the vm page's PG_BUSY flag is set only when the vm object
lock is released while the vm page is still in transition.  Typically,
this is when it is undergoing I/O.
2004-11-03 20:17:31 +00:00
Poul-Henning Kamp
0cbda9dfd5 Remove the last call in the system to VOP_SPECSTRATEGY(): We can no
longer come through the VNODE layer to the disks since all the filesystems
now go via geom_vfs to GEOM.
2004-10-29 10:52:31 +00:00
Poul-Henning Kamp
6afb3b1c37 Give dev_strategy() an explict cdev argument in preparation for removing
buf->b-dev.

Put a bio between the buf passed to dev_strategy() and the device driver
strategy routine in order to not clobber fields in the buf.

Assert copyright on vfs_bio.c and update copyright message to canonical
text.  There is no legal difference between John Dysons two-clause
abbreviated BSD license and the canonical text.
2004-10-29 07:16:37 +00:00
Poul-Henning Kamp
c5995e45eb Lock bp->b_bufobj->b_object instead of bp->b_object 2004-10-28 08:38:46 +00:00
Poul-Henning Kamp
6e77a04170 The island council met and voted buf_prewrite() home.
Give ffs it's own bufobj->bo_ops vector and create a private strategy
routine, (currently misnamed for forwards compatibility), which is
just a copy of the generic bufstrategy routine except we call
softdep_disk_prewrite() directly instead of through the buf_prewrite()
indirection.

Teach UFS about the need for softdep_disk_prewrite() and call the
function directly in FFS.

Remove buf_prewrite() from the default bufstrategy() and from the
global bio_ops method vector.
2004-10-26 10:44:10 +00:00
Poul-Henning Kamp
5d9d81e7ea Put the I/O block size in bufobj->bo_bsize.
We keep si_bsize_phys around for now as that is the simplest way to pull
the number out of disk device drivers in devfs_open().  The correct solution
would be to do an ioctl(DIOCGSECTORSIZE), but the point is probably mooth
when filesystems sit on GEOM, so don't bother for now.
2004-10-26 07:39:12 +00:00
Alan Cox
cd9c0da805 Hold the lock on the containing vm object when calling
vm_page_sleep_if_busy().
2004-10-26 06:58:26 +00:00
Poul-Henning Kamp
ee1d0eb330 Remove vnode->v_bsize. This was a dead-end. 2004-10-25 07:50:59 +00:00
Alan Cox
a50b705403 Use VM_ALLOC_NOBUSY to eliminate vm_page_wakeup() calls and the acquisition
and release of the global page queues lock required to make the call.

Remove GIANT_REQUIRED from vm_hold_free_pages().  All of its VM operations
are properly synchronized.
2004-10-25 06:34:14 +00:00