fix: eth block returns correctly filled logs bloom field#7156
Open
akaladarshi wants to merge 10 commits into
Open
fix: eth block returns correctly filled logs bloom field#7156akaladarshi wants to merge 10 commits into
akaladarshi wants to merge 10 commits into
Conversation
akaladarshi
requested review from
LesnyRumcajs and
sudo-shashank
and removed request for
a team
Contributor
|
Note Reviews pausedIt looks like this branch is under active development. To avoid overwhelming you with review comments due to an influx of new commits, CodeRabbit has automatically paused this review. You can configure this behavior by changing the Use the following commands to manage reviews:
Use the checkboxes below for quick actions:
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
✨ Simplify code
Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (2)
src/rpc/methods/eth/filter/mod.rs (1)
392-392: ⚡ Quick winAdd context to the error propagation.
The
try_fromconversion lacks.context(), which violates the coding guideline to "add context with.context()when errors occur." While unlikely to fail in practice, adding context improves debuggability.🔧 Suggested fix
- let event_idx_base = u64::try_from(event_count)?; + let event_idx_base = u64::try_from(event_count) + .context("event count exceeds u64::MAX")?;🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@src/rpc/methods/eth/filter/mod.rs` at line 392, The conversion call let event_idx_base = u64::try_from(event_count)? should propagate a contextual error; replace the bare ? with a Context-wrapped error (e.g., call .context(...) before ?). Update the expression referencing u64::try_from(event_count) so failures include a clear message like "failed to convert event_count to u64" (affecting the event_idx_base assignment) to satisfy the `.context()` guideline.Source: Coding guidelines
src/rpc/methods/eth.rs (1)
4562-4600: ⚡ Quick winConsider adding a test for
compute_block_logs_bloom.The current test validates
accrue_eth_logbehavior well (empty bloom, single log, OR composition, idempotence). However, there's no unit test forcompute_block_logs_bloomitself, which handles event collection and address resolution. An integration test or unit test covering:
- Blocks with no events → empty bloom
- Blocks with valid EVM events → correct bloom
- Blocks with mixed valid/invalid events → partial bloom
would increase confidence in the full bloom computation path.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@src/rpc/methods/eth/filter/mod.rs`:
- Around line 358-365: Add a doc comment above the public function
collect_events_from_messages that succinctly describes its purpose (collect
events from executed messages in a tipset), its parameters (state_manager:
&StateManager, tipset: &Tipset, executed_messages: &[ExecutedMessage], spec:
Option<&impl Matcher>, skip_event: SkipEvent, collected_events: &mut
Vec<CollectedEvent>), its behavior (filters/matches events using spec, skips
events per skip_event, appends found CollectedEvent items into
collected_events), and its return value (anyhow::Result<()> indicating success
or error); make sure the doc mentions that collected_events is mutated in-place
and any notable side effects or error conditions the caller should expect.
---
Nitpick comments:
In `@src/rpc/methods/eth/filter/mod.rs`:
- Line 392: The conversion call let event_idx_base = u64::try_from(event_count)?
should propagate a contextual error; replace the bare ? with a Context-wrapped
error (e.g., call .context(...) before ?). Update the expression referencing
u64::try_from(event_count) so failures include a clear message like "failed to
convert event_count to u64" (affecting the event_idx_base assignment) to satisfy
the `.context()` guideline.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository UI
Review profile: CHILL
Plan: Pro
Run ID: 80cc42cd-3208-4465-a098-75793490f3be
📒 Files selected for processing (2)
src/rpc/methods/eth.rssrc/rpc/methods/eth/filter/mod.rs
akaladarshi
force-pushed
the
akaladarshi/fix-logs-bloom
branch
2 times, most recently
from
b0be642 to
96b6e9c
Compare
Codecov Report❌ Patch coverage is Additional details and impacted files
... and 4 files with indirect coverage changes Continue to review full report in Codecov by Harness.
🚀 New features to boost your workflow:
|
sudo-shashank
requested changes
Jun 19, 2026
sudo-shashank
left a comment
sudo-shashank
left a comment
Contributor
There was a problem hiding this comment.
like lotus we should store the computed logs bloom so we don't re-compute it again and again.
Contributor
|
There are few more changes required and needs to be ported from the list of changes filecoin-project/lotus#13618 for both correctness and performance. |
Collaborator
Author
@sudo-shashank When I started working on this, there was a possibility of us shifting to the SQL DB since, that is not the case anymore I will store the data in the current index DB |
akaladarshi
force-pushed
the
akaladarshi/fix-logs-bloom
branch
from
96b6e9c to
887dba6
Compare
Contributor
There was a problem hiding this comment.
Actionable comments posted: 3
🧹 Nitpick comments (4)
CHANGELOG.md (1)
50-50: 📐 Maintainability & Code Quality | 🔵 Trivial | ⚡ Quick winReference the issue instead of the PR.
This entry should link to issue
#7151rather than PR#7156so the changelog follows the repo’s traceability convention. Based on learnings, when both exist, use[#ISSUE_NO](link-to-issue): description.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@CHANGELOG.md` at line 50, The changelog entry currently links to the pull request instead of the tracking issue, so update the bullet in CHANGELOG.md to reference issue `#7151` using the repo’s standard [`#ISSUE_NO`](link-to-issue): description format. Keep the existing description text, but change the linked identifier from the PR reference to the issue reference so the entry matches the traceability convention.Source: Learnings
src/db/gc/snapshot.rs (1)
351-358: 🩺 Stability & Availability | 🔵 Trivial | ⚡ Quick winSilent no-op if
heaviest_car_tipset()fails.The
delete_blooms_before_heighterror path logs a warning, but ifdb.heaviest_car_tipset()itself returnsErr, the whole pruning step silently no-ops with no log line, unlike the similarOk(ts)pattern used later in this function (Lines 365-378) where failures elsewhere are still surfaced. Since this can leave stale bloom rows accumulating unnoticed, consider logging on theErrbranch too.Proposed fix
- if let Ok(head) = db.heaviest_car_tipset() { - let cutoff = head.epoch() - self.recent_state_roots; - if let Err(e) = db.delete_blooms_before_height(cutoff) { - tracing::warn!("failed to prune stale block blooms: {e:#}"); - } - } + match db.heaviest_car_tipset() { + Ok(head) => { + let cutoff = head.epoch() - self.recent_state_roots; + if let Err(e) = db.delete_blooms_before_height(cutoff) { + tracing::warn!("failed to prune stale block blooms: {e:#}"); + } + } + Err(e) => tracing::warn!("failed to get heaviest car tipset for bloom pruning: {e:#}"), + }🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@src/db/gc/snapshot.rs` around lines 351 - 358, The pruning block in snapshot cleanup silently skips work when db.heaviest_car_tipset() returns Err, so add explicit logging in that error branch instead of only handling the Ok(head) case. Update the bloom-pruning logic in the snapshot cleanup path to mirror the later Ok(ts) style used in the same function by surfacing the failure with tracing::warn! (or equivalent) and keeping the existing delete_blooms_before_height error handling unchanged.src/db/tests/subtests/mod.rs (1)
71-100: 🎯 Functional Correctness | 🔵 Trivial | 💤 Low valueConsider adding an exact-boundary case to the prune test.
The test exercises heights
100(deleted,< 150) and200(kept,> 150), but never a bloom stored exactly at the cutoff (height == 150), which perdecode_block_bloom'sh < heightcheck should be kept. A small addition would pin down the inclusive boundary explicitly.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@src/db/tests/subtests/mod.rs` around lines 71 - 100, The block bloom prune test in block_bloom_prune only covers values below and above the cutoff, so add an exact-cutoff case to lock in the boundary behavior. In the same test, write a bloom through EthBlockBloomStore at height 150, then call delete_blooms_before_height(150) and assert that read_bloom still returns it, alongside the existing assertions for the lower and higher heights.src/db/memory.rs (1)
150-172: 🎯 Functional Correctness | 🔵 Trivial | ⚡ Quick winResilient decode-failure handling — good pattern, but see parity_db.rs for a divergent (fail-fast) counterpart.
retainhere silently drops any entry that fails to decode, which is a reasonable, resilient default for pruning. Note thatParityDb::delete_blooms_before_height(src/db/parity_db.rs) instead propagates a decode error via?, aborting the entire prune on a single corrupted row — see the comment there for the concrete risk. Worth aligning both implementations to the same failure semantics.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@src/db/memory.rs` around lines 150 - 172, The bloom-pruning logic in MemoryDB::delete_blooms_before_height currently treats decode failures as silent drops, which diverges from the fail-fast behavior in ParityDb::delete_blooms_before_height. Align the failure semantics between the two implementations by choosing one consistent approach and applying it in the delete_blooms_before_height path, using the same decode_block_bloom handling pattern in both MemoryDB and ParityDb so a corrupted entry is either always tolerated or always surfaced the same way.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@src/db/migration/v0_33_7.rs`:
- Around line 46-54: Rollback the database rename if `parity_db::Db::add_column`
fails in `v0_33_7` so `old_db` is not left as an empty placeholder while
`temp_db` still contains the real data. Update the migration flow around the
`rename`, `create_dir_all`, and `add_column` steps to restore the original
directory or clean up both `old_db` and `temp_db` before returning the error, so
later startup logic does not delete the only valid copy.
In `@src/db/mod.rs`:
- Around line 156-170: decode_block_bloom currently accepts any payload after
the 8-byte height prefix, so malformed cached blooms can slip through as
logsBloom. Tighten the validation in decode_block_bloom (and any callers that
read its output) to require exactly the expected 256-byte bloom length, and
treat anything shorter or longer as invalid so the cache path falls back or is
ignored.
In `@src/db/parity_db.rs`:
- Around line 269-282: In `ParityDB::delete_blooms_before_height`, a single bad
bloom entry currently aborts pruning because `decode_block_bloom(&entry)?`
propagates immediately. Update this loop to mirror
`MemoryDB::delete_blooms_before_height` by handling decode failures per entry:
skip malformed rows, optionally log them, and continue collecting stale keys for
the rest. Keep the pruning path resilient so one corrupted `EthBlockBloom`
record does not stop `self.db.commit(...)` from deleting the valid stale
entries.
---
Nitpick comments:
In `@CHANGELOG.md`:
- Line 50: The changelog entry currently links to the pull request instead of
the tracking issue, so update the bullet in CHANGELOG.md to reference issue
`#7151` using the repo’s standard [`#ISSUE_NO`](link-to-issue): description format.
Keep the existing description text, but change the linked identifier from the PR
reference to the issue reference so the entry matches the traceability
convention.
In `@src/db/gc/snapshot.rs`:
- Around line 351-358: The pruning block in snapshot cleanup silently skips work
when db.heaviest_car_tipset() returns Err, so add explicit logging in that error
branch instead of only handling the Ok(head) case. Update the bloom-pruning
logic in the snapshot cleanup path to mirror the later Ok(ts) style used in the
same function by surfacing the failure with tracing::warn! (or equivalent) and
keeping the existing delete_blooms_before_height error handling unchanged.
In `@src/db/memory.rs`:
- Around line 150-172: The bloom-pruning logic in
MemoryDB::delete_blooms_before_height currently treats decode failures as silent
drops, which diverges from the fail-fast behavior in
ParityDb::delete_blooms_before_height. Align the failure semantics between the
two implementations by choosing one consistent approach and applying it in the
delete_blooms_before_height path, using the same decode_block_bloom handling
pattern in both MemoryDB and ParityDb so a corrupted entry is either always
tolerated or always surfaced the same way.
In `@src/db/tests/subtests/mod.rs`:
- Around line 71-100: The block bloom prune test in block_bloom_prune only
covers values below and above the cutoff, so add an exact-cutoff case to lock in
the boundary behavior. In the same test, write a bloom through
EthBlockBloomStore at height 150, then call delete_blooms_before_height(150) and
assert that read_bloom still returns it, alongside the existing assertions for
the lower and higher heights.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository UI
Review profile: CHILL
Plan: Pro
Run ID: a154e991-22c1-4133-82f4-19962bd5eaa2
📒 Files selected for processing (19)
CHANGELOG.mdscripts/tests/api_compare/filter-listscripts/tests/api_compare/filter-list-gatewaysrc/db/car/many.rssrc/db/db_impl.rssrc/db/gc/snapshot.rssrc/db/memory.rssrc/db/migration/migration_map.rssrc/db/migration/mod.rssrc/db/migration/v0_33_7.rssrc/db/mod.rssrc/db/parity_db.rssrc/db/parity_db/gc.rssrc/db/tests/mem_test.rssrc/db/tests/parity_test.rssrc/db/tests/subtests/mod.rssrc/rpc/methods/eth.rssrc/tool/subcommands/api_cmd/generate_test_snapshot.rssrc/tool/subcommands/api_cmd/test_snapshots.txt
🔗 Linked repositories identified
CodeRabbit considers these linked repositories for cross-repo context during reviews:
filecoin-project/lotus(manual)
💤 Files with no reviewable changes (1)
- scripts/tests/api_compare/filter-list
✅ Files skipped from review due to trivial changes (2)
- src/db/migration/mod.rs
- src/db/db_impl.rs
🚧 Files skipped from review as they are similar to previous changes (3)
- src/tool/subcommands/api_cmd/test_snapshots.txt
- scripts/tests/api_compare/filter-list-gateway
- src/rpc/methods/eth.rs
Comment on lines
+46
to
+54
| std::fs::rename(&old_db, &temp_db).context("failed to rename database directory")?; | ||
|
|
||
| // Create a placeholder so the delete step succeeds | ||
| std::fs::create_dir_all(&old_db).context("failed to create placeholder directory")?; | ||
|
|
||
| info!("Adding EthBlockBloom column to database"); | ||
| let mut opts = paritydb_0_33_6::to_options(temp_db.clone()); | ||
| parity_db::Db::add_column(&mut opts, paritydb_0_33_6::eth_block_bloom_column_options()) | ||
| .context("failed to add EthBlockBloom column")?; |
Contributor
There was a problem hiding this comment.
🩺 Stability & Availability | 🔴 Critical | ⚡ Quick win
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
set -euo pipefail
# Inspect migration wrapper behavior around migrate_core failures.
fd -p 'migration_map.rs' src/db/migration --exec sed -n '1,140p' {}
fd -p 'v0_33_7.rs' src/db/migration --exec sed -n '37,58p' {}Repository: ChainSafe/forest
Length of output: 6587
🏁 Script executed:
#!/bin/bash
set -euo pipefail
# Inspect the migration flow, rollback/error handling, and any tests covering failure paths.
rg -n "fn migrate\(|migrate_core\(|remove_dir_all\(|rename\(|rollback|temporary_db_path|migrate failed|migration" src/db/migration -g '!**/target/**'
echo '--- v0_33_7 ---'
sed -n '1,220p' src/db/migration/v0_33_7.rs
echo '--- migration map ---'
sed -n '1,220p' src/db/migration/migration_map.rs
echo '--- search tests ---'
rg -n "v0_33_7|Migration0_33_6_0_33_7|temporary_db|rollback|failed to add EthBlockBloom" src -g '*test*' -g '*tests*'Repository: ChainSafe/forest
Length of output: 31336
🏁 Script executed:
#!/bin/bash
set -euo pipefail
# Inspect how startup/version detection interacts with leftover old_db/temp_db directories.
sed -n '1,260p' src/db/migration/db_migration.rs
echo '---'
rg -n "current db version|version.*dir|old_db_path|new_db_path|temporary_db_path|is_migration_required|Mode::Current|current mode|version database|db version" src -g '!**/target/**'Repository: ChainSafe/forest
Length of output: 9388
🏁 Script executed:
#!/bin/bash
set -euo pipefail
# Inspect version detection and how leftover placeholder/temp directories are interpreted.
sed -n '1,220p' src/db/db_mode.rsRepository: ChainSafe/forest
Length of output: 5437
Rollback the rename on add_column failure. If this errors, old_db is left as an empty semver-named placeholder while temp_db still holds the only copy of the database; the next startup will treat the placeholder as the source DB and pre_checks will delete temp_db, losing the data. Restore old_db or clean up both paths before returning the error.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@src/db/migration/v0_33_7.rs` around lines 46 - 54, Rollback the database
rename if `parity_db::Db::add_column` fails in `v0_33_7` so `old_db` is not left
as an empty placeholder while `temp_db` still contains the real data. Update the
migration flow around the `rename`, `create_dir_all`, and `add_column` steps to
restore the original directory or clean up both `old_db` and `temp_db` before
returning the error, so later startup logic does not delete the only valid copy.
Contributor
There was a problem hiding this comment.
@LesnyRumcajs Sounds good — I'll hold off pending @akaladarshi's input on the rollback approach.
🧠 Learnings used
Learnt from: hanabi1224
Repo: ChainSafe/forest PR: 6381
File: src/lotus_json/actors/states/cron_state.rs:8-8
Timestamp: 2026-01-05T12:54:40.850Z
Learning: In Rust code reviews, do not derive Eq for a struct if any field does not implement Eq (e.g., types from external dependencies). If a type like CronStateLotusJson includes fields wrapping external dependencies that lack Eq, derive PartialEq (or implement PartialEq manually) but avoid deriving Eq. This ensures comparisons compile and reflect actual equivalence semantics. When needed, consider implementing custom PartialEq (and possibly Eq) only after ensuring all fields (or wrappers) implement Eq, or keep PartialEq-only if full equality semantics cannot be expressed.
Learnt from: hanabi1224
Repo: ChainSafe/forest PR: 6381
File: src/lotus_json/actors/states/evm_state.rs:41-44
Timestamp: 2026-01-05T12:56:13.802Z
Learning: In Rust codebases (e.g., Forest), do not add #[cfg(test)] to functions already annotated with #[test]. The #[test] attribute ensures the function is compiled only for tests, so a separate #[cfg(test)] is redundant and can be removed if present. Apply this check to all Rust files that contain #[test] functions.
Learnt from: hanabi1224
Repo: ChainSafe/forest PR: 6666
File: src/tool/subcommands/archive_cmd.rs:628-631
Timestamp: 2026-03-02T09:43:34.946Z
Learning: In Rust sources related to Forest snapshot handling, implement the rule: enable message_receipts and events (message_receipts: true, events: true) only for GC snapshots as defined in src/db/gc/snapshot.rs, since these are internal snapshots created during garbage collection. For user-facing export commands such as src/tool/subcommands/archive_cmd.rs, disable receipts and events by default (message_receipts: false, events: false) to keep user-facing snapshots smaller, unless explicitly requested. This guidance targets Rust files; apply consistently across similar snapshot-related modules, using the narrowest applicable scope when extending beyond the two specified files.
Learnt from: LesnyRumcajs
Repo: ChainSafe/forest PR: 6903
File: src/shim/executor.rs:243-251
Timestamp: 2026-04-14T17:24:13.631Z
Learning: In the ChainSafe/forest (LesnyRumcajs) codebase, do not require rustdoc comments on public methods when the method’s purpose is clearly self-explanatory from its name (e.g., `entries(&self)`, `into_entries(self)`). When reviewing Rust (`.rs`) files, avoid flagging missing documentation for these obviously named public APIs, reserving doc requirements for less clear or non-obvious public methods.
Learnt from: hanabi1224
Repo: ChainSafe/forest PR: 7077
File: src/utils/cache/size_tracking.rs:174-182
Timestamp: 2026-05-19T10:55:04.684Z
Learning: In ChainSafe/forest code reviews, avoid raising review comments for issues that are likely compile-time failures (e.g., missing imports, unresolved types, or other compiler errors that CI will catch). Instead, focus feedback on logic, correctness, and design/maintainability concerns, since the CI pipeline reliably verifies compilation.
Learnt from: LesnyRumcajs
Repo: ChainSafe/forest PR: 7113
File: src/rpc/mod.rs:954-975
Timestamp: 2026-05-27T13:30:50.172Z
Learning: In ChainSafe/forest, CI runs tests with `cargo nextest`, which executes each test in its own fresh process. As a result, process-global state is not shared across tests (e.g., metric registries like `crate::metrics::default_registry()`), so assertions on absolute metric counts in tests (e.g., `count == 1`) are expected to be safe. Reviewers should not require before/after delta comparisons or other cross-test pollution guards for metrics count assertions unless a test setup explicitly breaks the test-per-process isolation.
Learnt from: hanabi1224
Repo: ChainSafe/forest PR: 7129
File: src/blocks/tipset.rs:192-193
Timestamp: 2026-06-02T11:42:22.733Z
Learning: When implementing or reviewing `get_size2::GetSize` for Rust types in this repository, do not attempt to call `get_heap_size_with_tracker()` directly on fields typed as `Arc<NonEmpty<T>>` (i.e., `nunny::Vec<T>` / `NonEmpty<T>`). Because `nunny::Vec<T>` (NonEmpty<T>) does **not** implement `GetSize`, neither will `Arc<NonEmpty<T>>`. Instead, compute heap size for `Arc<NonEmpty<T>>` fields using the existing `nunny_vec_heap_size_helper` helper (in `src/utils/get_size/mod.rs`), which deref-coerces through the `Arc` to the inner `NonEmpty<T>` and provides the correct heap-size calculation.
Learnt from: akaladarshi
Repo: ChainSafe/forest PR: 7182
File: src/message_pool/msgpool/utils.rs:75-76
Timestamp: 2026-06-16T17:07:30.443Z
Learning: In the ChainSafe/forest codebase, SignedMessage (signed Filecoin messages) will never have an ID address in the sender (`from`) because protocol-level signature verification rejects ID senders. Therefore, when reviewing Rust code that processes SignedMessage and uses a map keyed by the sender `Address` (e.g., `HashMap<Address, ...>`), it is safe to do a direct lookup like `map.get_mut(from)` using the sender address from the SignedMessage. Do not flag this as an address-type mismatch or require iterating/resolving keys when the lookup is based on the SignedMessage’s own `from` value.
Contributor
There was a problem hiding this comment.
Seems like the humans are having a chat. I'll hop back into my burrow for now. If you need me again, just tag @coderabbitai in a new comment, and I'll come hopping out!
Contributor
There was a problem hiding this comment.
Oops, something went wrong! Please try again later. 🐰 💔
LesnyRumcajs
reviewed
Jul 2, 2026
| EthBlockBloomStore::write_bloom(self.writer(), key, height, bloom) | ||
| } | ||
|
|
||
| fn delete_blooms_before_height(&self, height: i64) -> anyhow::Result<()> { |
Member
There was a problem hiding this comment.
Suggested change
| fn delete_blooms_before_height(&self, height: i64) -> anyhow::Result<()> { | |
| fn delete_blooms_before_height(&self, height: ChainEpoch) -> anyhow::Result<()> { |
Here and elsewhere. It's not exactly strict typing, but type aliases in Rust exist for areason.
LesnyRumcajs
reviewed
Jul 2, 2026
| .unwrap_or_default() | ||
| ); | ||
|
|
||
| // Prune blooms whose events are no longer retained by the lite snapshot. |
LesnyRumcajs
reviewed
Jul 2, 2026
| "0.22.0" -> "0.22.1" @ Migration0_22_0_0_22_1, | ||
| "0.25.3" -> "0.26.0" @ Migration0_25_3_0_26_0, | ||
| "0.30.5" -> "0.31.0" @ Migration0_30_5_0_31_0, | ||
| "0.33.6" -> "0.33.7" @ Migration0_33_6_0_33_7, |
Member
There was a problem hiding this comment.
These need to be updated, no?
Collaborator
Author
There was a problem hiding this comment.
Yeah 0.33.7 is already released, will update to 0.33.8
akaladarshi
force-pushed
the
akaladarshi/fix-logs-bloom
branch
from
488c3c4 to
0fd4c9d
Compare
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.
Summary of changes
Changes introduced in this pull request:
Reference issue to close (if applicable)
Closes #7151
Other information and links
Change checklist
Outside contributions
Summary by CodeRabbit
logsBloomvalues so they are computed from actual block logs instead of using a placeholder value.