docs: design per-session io_uring ring pool footprint controls#4014
Merged
Conversation
Adds the per-session ring pool design that focuses on reducing per-process io_uring memory cost when many oc-rsync invocations run concurrently. Surveys current ring construction, names the four in-scope levers (lazy ring construction, adaptive registered-buffer count, soft cap via CLI/env, probe-cache invariant), and sequences them as independent PRs.
github-actions
Bot
added
the
documentation
3 tasks
oferchen
added a commit
that referenced
this pull request
May 18, 2026
#4014) Adds the per-session ring pool design that focuses on reducing per-process io_uring memory cost when many oc-rsync invocations run concurrently. Surveys current ring construction, names the four in-scope levers (lazy ring construction, adaptive registered-buffer count, soft cap via CLI/env, probe-cache invariant), and sequences them as independent PRs.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
docs/design/io-uring-ring-pool.mdcovering the per-session io_uring ring pool design tracked by Fix clippy warning in sparse executor test #1936.registered_buffer_count, a soft cap via--io-uring-max-rings/OC_RSYNC_IO_URING_MAX_RINGS, and locking in the existing cached availability probe.SCM_RIGHTSfd transfer, the in-process MPMC pool already tracked by Deduplicate PATHEXT extensions when resolving fallbacks #1937).BgidAllocator, merged via feat: bound io_uring buffer group ID allocation #4005) as the upper bound on adaptive buffer-pool sizing and Align cross-compile matrix with build_daemon metadata #2045 for the adaptive-sizing audit.Survey highlights
IoUringDiskBatch::try_newincrates/transfer/src/disk_commit/thread.rs:78.crates/fast_io/src/io_uring/config.rs:368) - approximately 520 KiB pinned per ring, up to 4 MiB underfor_large_files()presets.--dry-runand list-only modes already bypass the disk thread viarun_dry_run_loop(crates/transfer/src/receiver/transfer/pipeline.rs:401) so they construct no ring today.Migration plan
R1-R4 are independent; each can ship as its own PR. Suggested order is R1 (lazy construction) -> R2 (adaptive buffer count) -> R3 (soft cap) -> R4 (doc-only probe-cache invariant).
Test plan