From: Alexy Khrabrov (khrabrov@unagi.cis.upenn.edu)
Date: 09/14/99-12:33:54 PM Z
Date: Tue, 14 Sep 1999 13:33:54 -0400 (EDT) Message-Id: <199909141733.NAA19975@unagi.cis.upenn.edu> From: Alexy Khrabrov <khrabrov@unagi.cis.upenn.edu> Subject: Re: fsync() fails under NFS, right? Greetings -- I was away from my mail, but want to thank all who responded. For us, the issue is very crucial, and it is interesting that it doesn't look as such to many NFS folks. The "educated guesses" about our model are remarkably correct. What surpises me is that I get an impression that most NFS folks assume fsync() is supposed to work under NFS. However, a dilettante I am, only having read Tanenbaum book, I always assumed NFS is stateless -- it doesn't maintain cursors for each user, then how can it do fsync()?? Flush all I/O on the file? Thus, I'd like to hear what do NFS people say think -- fsync() must work under NFS, if it doesn't, it's a particular client bug, a correct server allows fsync() to work, and there's no theoretical problems preventing NFS model from having totally operable fsync(). Is that right? -- Cheers, Alexy Khrabrov -- www.suffix.com -- Segmentation f%^(&
This archive was generated by hypermail 2.1.2 : 03/04/05-01:47:34 AM Z CST