home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.unix.wizards
- Path: sparky!uunet!charon.amdahl.com!pacbell.com!sgiblab!zaphod.mps.ohio-state.edu!saimiri.primate.wisc.edu!ames!kronos.arc.nasa.gov!iscnvx!netcomsv!netcom.com!netapp
- From: netapp@netcom.com (Network Appliance)
- Subject: Re: SUN NFS sync
- Message-ID: <1992Nov6.223031.13503@netcom.com>
- Keywords: sync
- Organization: Netcom - Online Communication Services (408 241-9760 guest)
- References: <bharat.720655786@Xenon.Stanford.EDU> <1d1vksINN3d@playroom.rochester.East.Sun.COM> <15358@auspex-gw.auspex.com>
- Date: Fri, 6 Nov 1992 22:30:31 GMT
- Lines: 30
-
- In article <15358@auspex-gw.auspex.com> guy@Auspex.COM (Guy Harris) writes:
- >Umm, I don't think it was even the case in 3.x - or 2.x, for that matter
- >- that NFS writes were synchronous on the client side.
-
- Last time I checked, NFS writes were handled very differently in the
- SunOS client code as compared with the client code that Sun distributes
- to other UNIX vendors who buy NFS from Sun.
-
- In SunOS, the write(2) system call just dirties buffers in memory, and
- expects biod's to do the writes when they are able. In the
- distributed NFS, the write(2) system call tries to schedule a biod to
- immediately send the write, and if no biod is available, then the
- process doing the write(2) does the send itself.
-
- In both cases the write is asychronous with respect to the client
- process, but in one case the write is always scheduled immediately
- (even if the process must do it itself), whereas in the other case, the
- write is only scheduled immediately if a biod is available, otherwise
- it may sit in memory for a while. (This is similar to the difference
- between ASYNC and DELWRI on buffers going to disk locally.)
-
- (I can't remember for sure -- it may be that writes less than 8K may
- sit in memory for a while in both versions.)
-
- I wonder, Guy, do you remember if older versions of SunOS match the
- behavior of the current NFS vendor distribution? Could that change
- have been part of the massive memory whacking around SunOS 4.0?
-
- Dave Hitz netapp.com
- Network Appliance (408) 562-1906
-