Maarten Litmaath wrote: > Burke, S (Stephen) wrote: > >> LHC Computer Grid - Rollout >> >>> [mailto:[log in to unmask]] On Behalf Of Jos van Wezel >> >> >> said: >> >>> The common misnomer nowadays, at least in part of the grid storage >>> world, is: "POSIX-like". This just means you have to rewrite your >>> program. >> >> >> >> I understand your point, but I think there is a valid distinction >> between something which just needs some headers which #define open() to >> rfio_open() etc and something which would need significant changes to >> the structure of the code - the former isn't really rewriting, just >> recompiling. Obviously some things can't easily be recompiled, but many >> can. > > > And a GFAL file system has already been tested, so at some point there > would not even be a real need to recompile programs that want to access > stuff under, say, /grid transparently. Or LFNs, GUIDs etc. We will also look into pre-load libraries that would allow the standard system calls to be overridden where needed (e.g. open() --> gfal_open() for grid files).