mirror of
https://github.com/jmcorgan/fips.git
synced 2026-10-05 19:18:25 +00:00
Johnathan Corgan
9f8b266e5d
The decrypt worker's module doc and its fallback-path comment framed the code as a step in an architectural plan this repository does not carry, and named a "DataShard end-state" that exists nowhere in the tree. State the property directly instead: each worker owns its session state, and a worker that also owned the rx_loop side could restore the EndpointData fast path. The reworded comments are rewrapped to the surrounding width. The metrics registry docs described off-thread reads as a later step, but the control read handle already serves show_metrics from the registry off the rx_loop task. Put both the module doc and the Padded doc in the present tense, with the single writer the code has. Three source comments cited commits by hash (an abandoned republish design, the change that made sessions shard-owned, and the fix that moved encrypt dispatch off round-robin). None of those hashes resolves in this repository, so a reader cannot follow them. Say what the commit did instead. The one hash cited in the routing tests is on every branch and stays. The bloom-storm scenario README pointed readers at a reproduction harness and results file outside this repository, told them to check out a commit and a branch that are not here, and named the regressing commit, which is not here either. Describe the harness and the regressed build without those references and anchor the confirmation procedure on the fix commit, which every branch contains. The off-loop snapshot dispatch test's name carried a stage label from an outside plan. Rename it to say what it checks: show_acl, show_stats_peers and show_stats_history_all_peers are served off-loop through snapshot_dispatch and render byte-identically to their on-loop forms. Nothing refers to the old name.