home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!olivea!hal.com!decwrl!sgi!rhyolite!vjs
- From: vjs@rhyolite.wpd.sgi.com (Vernon Schryver)
- Newsgroups: comp.protocols.nfs
- Subject: Re: NFS I/O Ops/seconds
- Message-ID: <nqr74rg@rhyolite.wpd.sgi.com>
- Date: 27 Jul 92 15:16:24 GMT
- References: <1992Jul22.061146.15641@u.washington.edu> <numb.711969731@root.co.uk> <JIM.92Jul27122141@hunter.cs.strath.ac.uk>
- Organization: Silicon Graphics, Inc. Mountain View, CA
- Lines: 48
-
- In article <JIM.92Jul27122141@hunter.cs.strath.ac.uk>, jim@cs.strath.ac.uk (Jim Reid) writes:
- > In article <noe56po@rhyolite.wpd.sgi.com> vjs@rhyolite.wpd.sgi.com (Vernon Schryver) writes:
- >
- > An NFS server or client on FDDI is intrinsically faster than a similar
- > machine over ethernet. This is because it takes significantly fewer
- > host cycles to generate 1 or 2 UDP/IP datagrams for a 4K or 8K read or
- > write than to generate 3 or 6.
- >
- > Yes, but.....
- >
- > 4K or 8K reads and writes tend not to be the most commonly used NFS
- > operations. Typically, 70-80% of the NFS requests will be lookups and
- > getattrs. These generate itty-bitty packets - 2-300 bytes or so -
- > which will fit quite comfortably in the maximum packet "frame" for
- > just about any network. Therefore, fragmentation of NFS requests is No
- > Big Deal.
- >
- > While what you say is true, the benefits of lower protocol processing
- > are negligible. This maybe saves 1000 instructions or so (a whole 30
- > microseconds of CPU on the average workstation these days) for perhaps
- > 20% of the server's NFS operations. I suspect that this will be lost
- > in the noise when compared with the CPU overhead of actually servicing
- > the NFS request and/or waiting for the disk.
- >
- > Jim
-
-
- Well, you're right about the effects of the mix. However, you're wrong
- about the potential of saving only 1000 instructions.
-
- If
- -your system uses 4KByte pages,
- -if your NFS implementation happens to use 4K blocks,
- -if your file system happens to like to use 4K buffers,
- and -if your FDDI hardware handles UDP checksums,
- then you can avoid around 1024 cache-missing loads and stores by using
- "page flipping". That is the equivalent of 10,000 to 100,000
- instructions per packet. (The cache miss penalty for an R4K at
- 50/100MHz is awesome.)
-
- I also don't think saving 1000 instructions is anything to sneeze at.
- Saving 1000 instructions would produce a large speed up in SGI NFS
- server. (We don't yet page-flip.) Also, remember that 1000
- instructions is not necessarly even close to 30 usec even at 33 MHz,
- unless your primary instruction cache is very large.
-
-
- Vernon Schryver, vjs@sgi.com
-