- Reorganize locking in UVM and provide extra serialisation for pmap(9).
New lock order: [vmpage-owner-lock] -> pmap-lock.
- Simplify locking in some pmap(9) modules by removing P->V locking.
- Use lock object on vmobjlock (and thus vnode_t::v_interlock) to share
the locks amongst UVM objects where necessary (tmpfs, layerfs, unionfs).
- Rewrite and optimise x86 TLB shootdown code, make it simpler and cleaner.
Add TLBSTATS option for x86 to collect statistics about TLB shootdowns.
- Unify /dev/mem et al in MI code and provide required locking (removes
kernel-lock on some ports). Also, avoid cache-aliasing issues.
Thanks to Andrew Doran and Joerg Sonnenberger, as their initial patches
formed the core changes of this branch.
already prevented). File systems are no longer responsible to check this.
Clean up and add asserts (note that dvp == vp cannot happen in vop_link).
OK dholland@
parent dir) associated with SAVESTART in relookup().
Check all call sites to make sure that SAVESTART wasn't set while
calling relookup(); if it was, adjust the refcount behavior. Remove
related references to SAVESTART.
The only code that was reaching the extra ref was msdosfs_rename,
where the refcount behavior was already fairly broken and/or gross;
repair it.
Add a dummy 4th argument to relookup to make sure code that hasn't
been inspected won't compile. (This will go away next time the
relookup semantics change, which they will.)
pathbuf object passed to namei as work space instead. (For now a pnbuf
pointer appears in struct nameidata, to support certain unclean things
that haven't been fixed yet, but it will be going away in the future.)
This removes the need for the SAVENAME and HASBUF namei flags.
- VOP_LOCK(vp, flags): Limit the set of allowed flags to LK_EXCLUSIVE,
LK_SHARED and LK_NOWAIT. LK_INTERLOCK is no longer allowed as it
makes no sense here.
- VOP_ISLOCKED(vp): Remove the for some time unused return value
LK_EXCLOTHER. Mark this operation as "diagnostic only".
Making a lock decision based on this operation is no longer allowed.
Discussed on tech-kern.
years ago when the kernel was modified to not alter ABI based on
DIAGNOSTIC, and now just call the respective function interfaces
(in lowercase). Plenty of mix'n match upper/lowercase has creeped
into the tree since then. Nuke the macros and convert all callsites
to lowercase.
no functional change
system generate heaps of odd allocations since the end of write request was
overwritten by the start of the second resulting in another relocation.
Also added a full flush of the file on a VOP_CLOSE(). This automatically
flushes file tails to disc.
out before automatically.
However, when dealing with faulty discs that fail to mount, system nodes are
of course not written out and thus may still be marked dirty, if only due to
access. Especially on sequential media this gave rise to panics on reading
trackinfo since the write track section had not yet been initialised.
Benefits are significant speed improvements on node creation/insertion while
keeping the lookup times low and still allowing sequential iteration over the
nodes.
member.
XXX No idea if this is the right solution to this problem, but it does
XXX at least allow thebuild to continue. The original committed should
XXX verify that this does what was intended!
(Hello again, Elad)
of free blocks on the device and when free blocks are getting tight it tries
to readjust/recalculate that value by syncing the FS.
Second stage will be resizing the data/metadata partitions.
the other routines of the same spirit.
Adjust file-system code to use it.
Keep vaccess() for KPI compatibility and to keep element of least
surprise. A "diagnostic" message warning that vaccess() is deprecated will
be printed when it's used (obviously, only in DIAGNOSTIC kernels).
No objections on tech-kern@:
http://mail-index.netbsd.org/tech-kern/2009/06/21/msg005310.html
improvements of at least 4 times in untarring and roughly 100 to 500 times
on file creation in big directories. Lookup of files was O(n*n) and is now
O(1) even for file creation. Free spaces in the directory are kept in a
seperate list for fast file creation.
The postmark benchmark gives:
UDF old:
pm>set transactions 2000
pm>set number 3000
pm>run
Creating files...Done
Performing transactions..........Done
Deleting files...Done
Time:
1593 seconds total
681 seconds of transactions (2 per second)
Files:
3956 created (2 per second)
Creation alone: 3000 files (4 per second)
Mixed with transactions: 956 files (1 per second)
990 read (1 per second)
1010 appended (1 per second)
3956 deleted (2 per second)
Deletion alone: 2912 files (9 per second)
Mixed with transactions: 1044 files (1 per second)
Data:
5.26 megabytes read (3.38 kilobytes per second)
21.93 megabytes written (14.10 kilobytes per second)
pm>
UDF new:
pm>set transactions 2000
pm>set number 3000
pm>run
Creating files...Done
Performing transactions..........Done
Deleting files...Done
Time:
19 seconds total
3 seconds of transactions (666 per second)
Files:
3956 created (208 per second)
Creation alone: 3000 files (230 per second)
Mixed with transactions: 956 files (318 per second)
990 read (330 per second)
1010 appended (336 per second)
3956 deleted (208 per second)
Deletion alone: 2912 files (970 per second)
Mixed with transactions: 1044 files (348 per second)
Data:
5.26 megabytes read (283.66 kilobytes per second)
21.93 megabytes written (1.15 megabytes per second)
unlock the source directory again on exit. The stub that doesn't allow
cross directory renames for now jumped to the wrong exit point and thus
left a locked directory node that paniced on next locking.
heavily fragmented files.
Also fixing some (rare) allocation bugs and function name streamlining.
Tested on harddisc, CD-RW and CD-R i.e. all three basic backend classes.
the name ".." on a parent path component. To prevent other similar errors,
name length checking is not done but the passed name that shouldn't be
passed is ignored.
