Date: Tue, 6 Jul 2010 07:11:04 +0000 (UTC) From: Jeff Roberson <jeff@FreeBSD.org> To: cvs-src-old@freebsd.org Subject: cvs commit: src/sys/ufs/ffs ffs_alloc.c ffs_inode.c ffs_softdep.c ffs_vnops.c softdep.h src/sys/ufs/ufs inode.h ufs_inode.c ufs_lookup.c ufs_vnops.c Message-ID: <201007060711.o667BQGv054329@repoman.freebsd.org>
index | next in thread | raw e-mail
jeff 2010-07-06 07:11:04 UTC
FreeBSD src repository
Modified files:
sys/ufs/ffs ffs_alloc.c ffs_inode.c ffs_softdep.c
ffs_vnops.c softdep.h
sys/ufs/ufs inode.h ufs_inode.c ufs_lookup.c
ufs_vnops.c
Log:
SVN rev 209717 on 2010-07-06 07:11:04Z by jeff
- Handle the truncation of an inode with an effective link count of 0 in
the context of the process that reduced the effective count. Previously
all truncation as a result of unlink happened in the softdep flush
thread. This had the effect of being impossible to rate limit properly
with the journal code. Now the process issuing unlinks is suspended
when the journal files. This has a side-effect of improving rm
performance by allowing more concurrent work.
- Handle two cases in inactive, one for effnlink == 0 and another when
nlink finally reaches 0.
- Eliminate the SPACECOUNTED related code since the truncation is no
longer delayed.
Discussed with: mckusick
Revision Changes Path
1.159 +0 -20 src/sys/ufs/ffs/ffs_alloc.c
1.119 +2 -4 src/sys/ufs/ffs/ffs_inode.c
1.245 +8 -74 src/sys/ufs/ffs/ffs_softdep.c
1.195 +0 -3 src/sys/ufs/ffs/ffs_vnops.c
1.22 +1 -1 src/sys/ufs/ffs/softdep.h
1.58 +0 -1 src/sys/ufs/ufs/inode.h
1.71 +9 -5 src/sys/ufs/ufs/ufs_inode.c
1.105 +2 -0 src/sys/ufs/ufs/ufs_lookup.c
1.322 +12 -20 src/sys/ufs/ufs/ufs_vnops.c
help
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?201007060711.o667BQGv054329>