On Fri, 2020-02-28 at 04:22 +0000, Al Viro wrote: > On Thu, Feb 27, 2020 at 07:34:12PM -0800, Matthew Wilcox wrote: > > On Thu, Feb 27, 2020 at 05:55:43PM +0800, Ian Kent wrote: > > > Not all file systems even produce negative hashed dentries. > > > > > > The most beneficial use of them is to improve performance of > > > rapid > > > fire lookups for non-existent names. Longer lived negative hashed > > > dentries don't give much benefit at all unless they suddenly have > > > lots of hits and that would cost a single allocation on the first > > > lookup if the dentry ttl expired and the dentry discarded. > > > > > > A ttl (say jiffies) set at appropriate times could be a better > > > choice all round, no sysctl values at all. > > > > The canonical argument in favour of negative dentries is to improve > > application startup time as every application searches the library > > path > > for the same libraries. Only they don't do that any more: > > Tell that to scripts that keep looking through $PATH for > binaries each time they are run. Tell that to cc(1) looking through > include path, etc. > > Ian, autofs is deeply pathological in that respect; that's OK, > since it has very unusual needs, but please don't use it as a model > for anything else - its needs *are* unusual. Ok, but my thoughts aren't based on autofs behaviours. But it sounds like you don't believe this is a sensible suggestion and you would know best so ... Ian
