Outline for 3/6/98

• Last time: Distributed file systems
• Administrative: Questions, comments, requests?
• Objective:
  • Finish DFS
  • Distributed Shared Memory

• Server is stateless
• Requests are self-contained.
• Blocks are transferred and cached in memory.
• Timestamp of last known mod kept with cached file, compared with "true" timestamp at server on Open.
  (Good for an interval)
• Updates delayed but flushed before Close ends.

• Server keeps state of all clients holding copies (copy set)
• Callbacks when cached data are about to become stale
• Large units (whole files or 64K portions)
• Updates propagated upon close
• Cache on local disk -> memory

• Time-to-Live (TTL) fields - HTTP "expires" header
• Client polling -HTTP
  "if-modified-since" request headers
• polling frequency? possibly adaptive (e.g. based on age of object and assumed stability)

• Allows use of a shared memory programming model (shared address space) in a distributed system (processors with only local memory)

• Can use the local memory management hardware to generate fault when desired page is not locally present.
• Locate the page remotely - current "owner" of page
• Page sent in message to requesting node (read access makes copy; write migrates)
• Update protocol - invalidations or updates;
  directory is kept of caches holding copies

• Sequential consistency
• Weaker forms of consistency
  • quarantees are associated with synchronization primitives; at other times, it doesn't matter
  • For example:
    acquire lock - make sure others' writes are done release lock - make sure all my writes are seen by others