chore: update Homebrew formula for master#2196
Closed
oferchen wants to merge 1 commit into
Closed
Conversation
4 tasks
oferchen
added a commit
that referenced
this pull request
May 15, 2026
Adds INC_RECURSE diagnostic counter I1 (#2196): the elapsed time from send_file_list() entry to the first wire byte the receiver can observe. A lightweight FirstByteWriter wraps the wire writer for the duration of send_file_list. It samples Instant::now() once on the first non-empty write and records the elapsed Duration. Per-entry overhead is one already-set Option check; there is no per-entry sampling. The latency is exposed through: - TransferTiming.flist_first_byte_latency (internal field) - GeneratorStats.flist_first_byte_latency (public API) - info_log!(Flist, 1, ...) and info_log!(Stats, 3, ...) for human output - debug_log!(Flist, 2, ...) with entry count context - tracing::info!(target = "rsync::flist", ...) when the tracing feature is enabled Two unit tests cover the populated-list and empty-list paths and assert that the recorded Duration is Some and non-zero. upstream: flist.c send_file_list / send_dir_name first-byte timing Refs #2089
Merged
3 tasks
oferchen
added a commit
that referenced
this pull request
May 17, 2026
… WorkQueue (#1573) (#4207) Engages with the #4173 audit conclusion that WorkQueueSender stays single-producer. Shows I1 (#2196) is the wrong instrument for the first-byte hypothesis - enumeration runs before send_file_list entry, so I1 excludes it by construction. Recommends defer pending a W1 benchmark (process start to first inbound flist byte) on multi-root cold-cache workloads.
4 tasks
oferchen
added a commit
that referenced
this pull request
May 17, 2026
Audit the sender-side INC_RECURSE capability gate, document the current disable mechanism, summarise the perf instrumentation that landed under tasks #2196-#2200, cross-reference the SSH and daemon push perf verification from #2209, and lay out the re-enable criteria for the eventual flip of inc_recursive_send from false to true. Recommendation: defer the flip until a 1M-file Mode C push profile run publishes I1-I5 totals alongside hyperfine wall-clock, and the gating criteria from docs/investigations/inc-recurse-sender-regression.md section 5 are met on two consecutive nightly runs. Includes a five-step plan for the eventual flip PR; the flip itself is out of scope here.
oferchen
added a commit
that referenced
this pull request
May 18, 2026
Adds INC_RECURSE diagnostic counter I1 (#2196): the elapsed time from send_file_list() entry to the first wire byte the receiver can observe. A lightweight FirstByteWriter wraps the wire writer for the duration of send_file_list. It samples Instant::now() once on the first non-empty write and records the elapsed Duration. Per-entry overhead is one already-set Option check; there is no per-entry sampling. The latency is exposed through: - TransferTiming.flist_first_byte_latency (internal field) - GeneratorStats.flist_first_byte_latency (public API) - info_log!(Flist, 1, ...) and info_log!(Stats, 3, ...) for human output - debug_log!(Flist, 2, ...) with entry count context - tracing::info!(target = "rsync::flist", ...) when the tracing feature is enabled Two unit tests cover the populated-list and empty-list paths and assert that the recorded Duration is Some and non-zero. upstream: flist.c send_file_list / send_dir_name first-byte timing Refs #2089
oferchen
added a commit
that referenced
this pull request
May 18, 2026
… WorkQueue (#1573) (#4207) Engages with the #4173 audit conclusion that WorkQueueSender stays single-producer. Shows I1 (#2196) is the wrong instrument for the first-byte hypothesis - enumeration runs before send_file_list entry, so I1 excludes it by construction. Recommends defer pending a W1 benchmark (process start to first inbound flist byte) on multi-root cold-cache workloads.
oferchen
added a commit
that referenced
this pull request
May 18, 2026
Audit the sender-side INC_RECURSE capability gate, document the current disable mechanism, summarise the perf instrumentation that landed under tasks #2196-#2200, cross-reference the SSH and daemon push perf verification from #2209, and lay out the re-enable criteria for the eventual flip of inc_recursive_send from false to true. Recommendation: defer the flip until a 1M-file Mode C push profile run publishes I1-I5 totals alongside hyperfine wall-clock, and the gating criteria from docs/investigations/inc-recurse-sender-regression.md section 5 are met on two consecutive nightly runs. Includes a five-step plan for the eventual flip PR; the flip itself is out of scope here.
oferchen
added a commit
that referenced
this pull request
May 18, 2026
Adds INC_RECURSE diagnostic counter I1 (#2196): the elapsed time from send_file_list() entry to the first wire byte the receiver can observe. A lightweight FirstByteWriter wraps the wire writer for the duration of send_file_list. It samples Instant::now() once on the first non-empty write and records the elapsed Duration. Per-entry overhead is one already-set Option check; there is no per-entry sampling. The latency is exposed through: - TransferTiming.flist_first_byte_latency (internal field) - GeneratorStats.flist_first_byte_latency (public API) - info_log!(Flist, 1, ...) and info_log!(Stats, 3, ...) for human output - debug_log!(Flist, 2, ...) with entry count context - tracing::info!(target = "rsync::flist", ...) when the tracing feature is enabled Two unit tests cover the populated-list and empty-list paths and assert that the recorded Duration is Some and non-zero. upstream: flist.c send_file_list / send_dir_name first-byte timing Refs #2089
oferchen
added a commit
that referenced
this pull request
May 18, 2026
… WorkQueue (#1573) (#4207) Engages with the #4173 audit conclusion that WorkQueueSender stays single-producer. Shows I1 (#2196) is the wrong instrument for the first-byte hypothesis - enumeration runs before send_file_list entry, so I1 excludes it by construction. Recommends defer pending a W1 benchmark (process start to first inbound flist byte) on multi-root cold-cache workloads.
oferchen
added a commit
that referenced
this pull request
May 18, 2026
Audit the sender-side INC_RECURSE capability gate, document the current disable mechanism, summarise the perf instrumentation that landed under tasks #2196-#2200, cross-reference the SSH and daemon push perf verification from #2209, and lay out the re-enable criteria for the eventual flip of inc_recursive_send from false to true. Recommendation: defer the flip until a 1M-file Mode C push profile run publishes I1-I5 totals alongside hyperfine wall-clock, and the gating criteria from docs/investigations/inc-recurse-sender-regression.md section 5 are met on two consecutive nightly runs. Includes a five-step plan for the eventual flip PR; the flip itself is out of scope here.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.