I noticed that sys_fsync can be very slow, because it has to scan all
cached pages of the file (this takes about 1ms/MByte on my dual P3-450).
I wrote a patch that fixes this problem and adds an implementation of
fdatasync (the inode does not get flushed if only mtime/ctime are
changed).
I
Here are some benchmark data to show the difference my fastsync patch
(posted here a few days ago as "faster fsync and real fdatasync") can
make.
Basically this patch omits a scan through all the cached blocks of a
file
on fsync and it enables fdatasync not to sync the inode if only
On Fri, 8 Oct 1999, Mikulas Patocka wrote:
Here goes quick'n'dirty patch. It does bforget(). It should prevent file
corruption.
wrong patch. bforget give you no guarantee at all. bfoget always fallback
to brelse if necessary.
What I said about bforget in my old email is still true. The _only_
On Fri, 8 Oct 1999, Alexander Viro wrote:
yep we knew about this problem ... it's not quite an easy hack though.
Putting the directory block cache (and symlink block cache) into the page
cache would be the preferred method - this would also clean up the code
alot i think.
More or