From: Gilad R. <gi...@fa...> - 2008-11-03 12:52:54
|
I ran a simple benchmark once that involved running fusexmp, which basically does nothing, using it to mount an empty XFS partition, and running dd/bonnie++ and a few other tests. Later, I terminated fuse and repeated the tests on the same directory using the original mount point. My benchmarks showed fuse can reach about 30% of the original file system's performance. (cached reads were about 2000MB/s, whereas w/o fuse I got about 6000MB/s). -- Gilad On Mon, 2008-11-03 at 12:36 +0100, Rob Meijer wrote: > I am trying to advocate use of fuse as the location to place several disk > image format libraries rather than putting the libraries in all the > seperate tools. I only have very limited numbers to be able to say > something well grounded about the performance overhead that Fuse poses on > read only access to big (tens to hundreds of GB) files. > > Does anyone know of studies on Fuse overhead, and or have more substantial > information than can be gathered from simply running and timing dd on a > raw disk image, and comparing it to the same dd run trough a simple loop > back fuse file system? > > T.I.A. > > Rob J Meijer > > > ------------------------------------------------------------------------- > This SF.Net email is sponsored by the Moblin Your Move Developer's challenge > Build the coolest Linux based applications with Moblin SDK & win great prizes > Grand prize is a trip for two to an Open Source event anywhere in the world > http://moblin-contest.org/redirect.php?banner_id=100&url=/ > _______________________________________________ > fuse-devel mailing list > fus...@li... > https://lists.sourceforge.net/lists/listinfo/fuse-devel |