0003-extract-technical-metadata-on-per-file-basis.md

layout	title	nav_order	permalink
default	ADR-0003	6	records/0003/

Extract Technical Metadata on a Per-File Basis

• Status: drafted
• Decider(s):
  • Andrew Berger
  • Vivian Wong
  • Infrastructure Team
    • Justin Coyne
    • Mike Giarlo
    • Peter Mangiafico
    • Jeremy Nelson
    • Justin Littman
    • Naomi Dushay
    • John Martin
    • Aaron Collier
• Date(s):
  • drafted: 2019-10-29
  • ...

Context and Problem Statement

Currently, we extract technical metadata per-object and run one extraction job serially per-file. This takes a problematically long time for objects with many files; blocks other objects from accessioning; and complicates restarts which must begin again and process the entire object.

NOTE: Needs discussion: Fedora 3 does not support concurrent writes on the same datastream so we can either split out filesets as a first-class objects in the F3 data model or use temporary caching to generate a consolidated techMD datastream.

Decision Drivers

• Blocker for Google Books project
• Slows down accessioning process

Considered Options

• Do nothing
• Extract metadata on a per-file basis rather than on a per-object basis to benefit from parallelism

Decision Outcome

TBD!

Positive Consequences

• [e.g., improvement of quality attribute satisfaction, follow-up decisions required, …]
• ...

Negative Consequences

• [e.g., compromising quality attribute, follow-up decisions required, …]
• ...

Pros and Cons of the Options

[option 1]

[example | description | pointer to more information | …]

• Good, because [argument a]
• Good, because [argument b]
• Bad, because [argument c]
• ...

[option 2]

[example | description | pointer to more information | …]

• Good, because [argument a]
• Good, because [argument b]
• Bad, because [argument c]
• ...

[option 3]

[example | description | pointer to more information | …]

• Good, because [argument a]
• Good, because [argument b]
• Bad, because [argument c]
• ...