Bump substreams for execout prefetching and scheduler fix - #238
Merged
Conversation
Brings tier1 execution-output prefetching and the scheduler fix that stops job picking from slowing down on long backprocessing ranges.
Contributor
🔍 Vulnerabilities of
|
| digest | sha256:bcbd8c456634efe997f30bb31c53c86da5cde2e5f111bfa0b005d7eb9546f5e6 |
| vulnerabilities |     |
| platform | linux/amd64 |
| size | 173 MB |
| packages | 509 |
📦 Base Image ubuntu:24.04
| also known as |
|
| digest | sha256:1e0a86e57d247923571b75e0aaf48a1449cf8c543d51fb3e07a4a7d7bfa79316 |
| vulnerabilities |   |
UlysseCorbeil
approved these changes
Sep 3, 2026
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Bumps
substreamstov1.22.1-0.20260903162505-4035f21109ec(compare).Four
substreams-tier1changes, all on the path that serves a production-mode client from cached files:Picking the next tier2 job walked every segment between the squasher and the job frontier on every call, so a run over N segments cost O(N²) in scheduling. The scheduler now keeps, per stage, the lowest segment that may still be pending and the completed prefix, and only looks at the segments those point at. On 3 stages with 4 workers and a squasher 3x slower than the jobs, scheduling 8000 segments went from 1.18s to 2.7ms. Job order is unchanged.
Cached execution output files for the next segments now download while the current one is being streamed, instead of each segment paying a full store round trip once the previous one is sent. Bounded per request at 4 segments ahead and 64 MiB of decompressed data, with no flag to set.
Each batch of cached execution output is sent on its own goroutine, so decoding the next batch overlaps with compressing and writing the current one, and decoding copies the payload one less time. Message order is unchanged.
The
substreams.spkgandlast_usedcache markers are written in the background, off the request's critical path, so they no longer delay the first block sent.No flag or configuration change. Changelog updated.