From 9b08e534f02c2f80622013404dbb12a65d070aa3 Mon Sep 17 00:00:00 2001 From: Aditya Mukhopadhyay Date: Sat, 10 Oct 2026 10:57:25 +0530 Subject: [PATCH] fix(storage): refuse a sub-page file that is not a torn first write (#506) A file of 1..4095 bytes held no whole page, so open treated it as a new database and a read-write open re-initialised it. It now opens as new only when its bytes are zeros or a prefix of init_empty's generation-1 meta (the rule is_torn_initial_meta already applied to a full page 0); anything else is STG-045, read-write and read-only, with the file unchanged. StorageBackend gains partial_page() (bytes past the last whole page; None by default, forwarded by the mutex and fault-injection wrappers). The corrupt_file fuzzer no longer skips short files: they must fail to open or open empty. The #506 input and a meta-prefix truncation are corpus seeds. Co-Authored-By: Claude Opus 5.5 Claude-Session: https://claude.ai/code/session_012wXxZguv7PgKQjMMH4yJ5h --- CHANGELOG.md | 1 + CLAUDE.md | 2 +- README.md | 2 +- docs/ERROR_REFERENCE.md | 14 ++++++ docs/TEST_COVERAGE.md | 6 +-- .../corrupt_file/seed_truncate_sub_page.bin | Bin 0 -> 8 bytes .../seed_truncate_to_meta_prefix.bin | Bin 0 -> 5 bytes fuzz/fuzz_targets/corrupt_file.rs | 22 +++++--- src/error.rs | 9 ++++ src/storage/backend/fault_inject.rs | 4 ++ src/storage/backend/file.rs | 23 +++++++++ src/storage/btree.rs | 7 +++ src/storage/mod.rs | 9 ++++ src/storage/persistent_facts.rs | 26 +++++++--- tests/integrity_test.rs | 47 ++++++++++++++++++ 15 files changed, 155 insertions(+), 17 deletions(-) create mode 100644 fuzz/corpus/corrupt_file/seed_truncate_sub_page.bin create mode 100644 fuzz/corpus/corrupt_file/seed_truncate_to_meta_prefix.bin diff --git a/CHANGELOG.md b/CHANGELOG.md index 793748080a..72fb52807b 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -39,6 +39,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 - A retract that removes several values of one attribute in one call now hides all of them (#371). - Queries no longer lose or duplicate facts when more than 65,535 facts are waiting for a checkpoint (#445; also fixed in v2.0.3). - **A file shorter than its meta page count is refused at open with `STG-044`** (#497). Open never compared the meta page's `page_count` with the file's length. A truncated file (an interrupted copy, a partial download) opened, and its queries and checkpoints then failed with `INT-049` after the WAL had accepted writes. A meta with a `page_count` far past the end opened too: its next checkpoint wrote at that page id, leaving a sparse file of up to 4 EiB, and `verify()` scanned to that count and never finished. Open now refuses both, read-write and read-only, without modifying the file. It does not fall back to the other meta page, because a valid newer meta means that checkpoint happened. A checkpoint now fails with `INT-049` instead of writing a meta that counts pages the backend does not hold, and `verify()` reports a `page_count` past the end as `STG-044` and stops its page scan at the end of the file. `BrowserDb` is not checked: it keeps only live pages (#440), so its store has no length to compare. New code `STG-044`. +- **A file shorter than one page is refused at open with `STG-045` unless it is a torn first write** (#506). Open treated any file under 4 KiB as a new database, because it holds no whole page, and a read-write open wrote a new empty database over it. A database cut below one page by an interrupted copy, or an unrelated file at the path, was silently replaced. Now such a file opens as a new database only when its bytes are zeros or a prefix of the first meta page a new database writes (what a crash during creation can leave, the rule a torn full page 0 already followed); anything else is `STG-045`, read-write and read-only, and the file is not modified. A zero-length file is still a new database. New code `STG-045`. - Reopening next to a WAL whose entries were all already checkpointed no longer rewinds the transaction counter, so later transactions no longer reuse `tx_count` values and `:as-of` history stays correct (#447; also fixed in v2.0.3). ### Internal diff --git a/CLAUDE.md b/CLAUDE.md index 90209f1b53..f83e69bc18 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -197,7 +197,7 @@ Auto-migrates v7 → v8 on open (spec §9, with a backup meta page). v1–v6 are ## Test Coverage -**1380 tests** (1371 passing, 9 ignored; unit + integration + doc). +**1381 tests** (1372 passing, 9 ignored; unit + integration + doc). See `docs/TEST_COVERAGE.md` for the full per-file breakdown. **Testing conventions** — see the Testing Conventions section below before writing any tests. diff --git a/README.md b/README.md index c1ecf1de5b..e07e1de649 100644 --- a/README.md +++ b/README.md @@ -131,7 +131,7 @@ let r2 = pq.execute(&[("tx", BindValue::TxCount(2)), ("entity", BindValue::Entit ```bash cargo run # interactive Datalog REPL -cargo test # run 1380 tests +cargo test # run 1381 tests cargo run < demos/demo_recursive.txt # recursive rules demo ``` diff --git a/docs/ERROR_REFERENCE.md b/docs/ERROR_REFERENCE.md index df57c6870e..f81ace6f3a 100644 --- a/docs/ERROR_REFERENCE.md +++ b/docs/ERROR_REFERENCE.md @@ -156,6 +156,7 @@ with no `CodedError` anywhere in its chain. | STG-042 | Database file not found (read-only open) | Storage | | STG-043 | Log writer target already exists | Storage | | STG-044 | File shorter than its meta page count | Storage | +| STG-045 | File shorter than one page and not a new database | Storage | | WAL-001 | Invalid WAL magic number | WAL | | WAL-002 | Unsupported WAL version | WAL | | WAL-003 | Value size exceeds maximum | WAL | @@ -2289,6 +2290,19 @@ let mut out = LogWriter::create("memory.v2.graph", OpenOptions::new())?; **Scenario**: A `.graph` file is copied to another machine and the copy stops partway. +### STG-045 File shorter than one page and not a new database + +**Error text**: `File is {} bytes, shorter than one page, and is not a new Minigraf database` + +**Cause**: The file is longer than zero bytes but shorter than one 4 KiB page, and its bytes are not a torn first write of a new database. Creating a database writes its first meta page in one go, so a crash during that write can leave only a prefix of that page (or zeros); such a file is opened as a new, empty database. Any other short file is something else: a different file at the path, a database cut short by an interrupted copy, or a damaged file. Earlier versions opened it as a new database and a read-write open overwrote it. The file is not modified, read-write or read-only. + +**Resolution**: +- Check that the path points at the intended `.graph` file. +- Copy the database again from its source, or restore it from backup. +- If the file is not needed, delete it and open the path again to create a new database. + +**Scenario**: A copy of a `.graph` file stops after its first kilobyte, and the copy is opened. + --- ## WAL — Write-Ahead Log Errors diff --git a/docs/TEST_COVERAGE.md b/docs/TEST_COVERAGE.md index 8ac9badaa3..aadd458df5 100644 --- a/docs/TEST_COVERAGE.md +++ b/docs/TEST_COVERAGE.md @@ -2,11 +2,11 @@ ## Coverage Summary -**Verified**: 2026-10-08 with `cargo test --quiet` +**Verified**: 2026-10-10 with `cargo test --quiet` -**Result**: 1,371 passing tests and 9 ignored tests (1,380 total) +**Result**: 1,372 passing tests and 9 ignored tests (1,381 total) -This covers the unreleased file-format-v8 work (#287, #371): the index-key value-collision fix, the v7→v8 migration, and the drop of formats v1–v6. It otherwise still covers the public database API, the Datalog engine, storage and recovery paths, v2.0.0's locking and structured-error-code changes, and v2.0.1's regression test for rebuilding indexes on open after several checkpoints (#370). Merged from the v2.x line: `tests/point_query_history_test.rs` and new storage unit tests check that attribute-narrowed bound-entity lookups return exactly what a full scan returns, and that `net_asserted_facts` matches its previous implementation on randomized histories (#323). Attribute-scan tests check that the AEVT range covers exactly the queried attribute, including non-ASCII names such as `:丿` and prefix siblings such as `:ab` for `:a` (#381). Incremental B+tree rebuild tests check that checkpoints which copy untouched index leaves produce exactly the entries and file checksum a full rebuild would, including over repeated checkpoints, that single-fact checkpoints do not fragment the index, and that a damaged slot directory is rejected rather than copied (#315). B+tree cursor tests check that every scan walks the tree, not the leaf `next_leaf` chain: full scans and start positions match the input, `seek` from the current position lands where a fresh descent from the root would (randomized, plus within a leaf, to a sibling, across subtrees, past the end, into the gap after a leaf, and backwards as a no-op), a seek to the sibling leaf reads exactly one page, reads are unchanged with every `next_leaf` zeroed, a child pointer into a non-B+tree page is STG-013, and a cycle in child pointers is an error, not a hang (v8 storage format PR 1, #374). Directory-sync unit tests check that creating the `.graph` file or the WAL, and deleting the WAL, fsync the parent directory after the file operation, and that reopening an existing file does not (#389). Disjunction tests check that `or-join` returns an empty result, not INT-031, when no rows reach it: on an empty database, after a pattern that matches nothing, after a `not` that removes every row, and in a rule body (#405). A stratification unit test builds the same two-rule negative cycle 64 times and checks that the INT-054 message names the same predicate pair every time (#410). Magic-sets tests check that a recursive rule with a literal start that recurses through another rule returns the same results as without the literal (#297). API tests check that `execute()` and `WriteTransaction::execute()` reject `$slot` bind tokens in every position with API-010 (#407). The REPL `run()` test now runs in a child process with null stdin, so it no longer hangs when the test runner's stdin is an open non-TTY stream (#415). v8 page-format tests (PR 2, #374, #388) check the 24-byte page header (a flipped bit, a wrong page id and a future generation each give their own STG code, legacy page types fail before the CRC, and a failed page is never cached), meta-page encoding, the free-list chain, WAL v2's base generation, and every row of the meta-selection table: both slots valid, a torn newest slot with the WAL's base generation (opens at the older one), a WAL newer than the valid meta, pages of the next generation on the free list or past `page_count` with no WAL (all STG-033, with the file unmodified), an unknown feature bit (STG-034), and a pre-release v8 single header (STG-032). Fault-injection tests crash `save()` at every page write (cleanly and with torn pages, including the meta write) and every sync, and crash a v7 migration at every write; each reopen finds exactly the old or the new checkpoint, and every reachable page plus the free list covers the file exactly. Twenty-five consecutive saves never write a page the previous meta references. Covering-key tests (PR 3, #433) check that byte order equals logical order for every key component and value type on random tuples (negative, zero and large integers, NaN and ±0.0, strings with 0x00, 64- and 65-byte strings, FOREVER, newest-transaction-first) and that every component round-trips; that prefix-compressed leaves and shortest-separator internal nodes round-trip, agree with a linear scan, keep `max(left) < s ≤ min(right)`, and reject an overflow; that the byte-key B+tree's builds, incremental rebuilds, cursor and `seek` match their expected sets; that dictionary ids are assigned once, never reused, shared between a keyword attribute and value, and deterministic; that a re-asserted or retracted long value writes no new value page and a forced hash collision still finds the right value; that one transaction with two timestamps is STG-037 and a missing dictionary entry STG-036; that committed reads by entity, entity and attribute, attribute, and in full equal an in-memory model across eight checkpoints and a reopen; that short-valued reads touch no value page; that a v7 file with every value type, long strings, refs and retractions migrates to exactly the same facts; that a pre-covering-key v8 file is STG-032; and that string values over 4,068 bytes and attributes or keywords over 1,024 bytes are WAL-003. A WAL test checks that reopening next to a fully checkpointed WAL does not reuse transaction numbers (#447). Copy-on-write checkpoint tests (PR 4, #434) check that lazy free-list pops and pushes conserve every page across page boundaries, partial head pages and chain exhaustion, never hand out a page freed in the same generation, and share unread chain pages unchanged; that a copy-on-write insert equals a sorted merge for random batches (including keys below the first and above the last, many into one leaf, root growth to depth 3, and 1 KB separators that split internal nodes), leaves the old tree readable and unchanged, frees exactly the replaced nodes, writes only new pages, writes exactly one leaf and two internal nodes for one entry in a depth-3 tree, and does not fragment leaves under single inserts; that a checkpoint after 1 or 100 right-edge facts writes at most the tree-depth difference more pages at 100,000 facts than at 10,000, and at most one path per new entry per tree for random keys; and that four reader threads querying throughout 40 checkpoints never fail and never see the fact count go backwards. Hardening tests (PR 5) damage an index leaf, an internal node, a dictionary leaf, a value page and a free-list page in turn. Every committed read or checkpoint that reaches the damaged page fails with STG-029, never with wrong or fewer rows. A query through `Minigraf` on a file with damaged leaves fails with STG-029, and the file still opens at its last checkpoint. A size test measures at most 200 bytes per fact (142 measured) on 144k facts in #433's shape; its 1.15M-fact variant is ignored locally and runs in the nightly smoke workflow. A shared dictionary-cache test checks that cached ident and timestamp lookups return the same facts and that the cache stays bounded. Merged from the v2.x line: storage and `edge_cases_test.rs` tests check that more than 65,535 uncheckpointed facts each resolve to their own fact through entity lookups and attribute scans, in memory and file-backed (#445). Merged from the v2.x line: `tests/golden_corpus_test.rs` opens a copy of each committed golden file in `tests/golden/` (v7 files written by minigraf 2.0.3: one checkpoint, several checkpoints, indexes rebuilt on open, a crash-left WAL, an already-checkpointed WAL, same-transaction multi-values) and checks its manifest's CRC32, `tx_count` and query results after open, after a checkpoint and reopen, and after one more write; a second test checks that every golden file has a manifest (#391). On `v3` the same test checks that each v7 file has a v8 meta page after its first open and gives the same results after reopening the migrated file, and adds seven v8 golden files (one checkpoint, seven copy-on-write checkpoints, a crash-left v2 WAL, an already-checkpointed v2 WAL, same-transaction multi-values, a v7 file migrated in place, and long values at the size limits); the #371 queries, skipped on v2.x, run and pass. `tests/model_based_test.rs` runs random sequences of transacts, retracts, write transactions, checkpoints, reopens and simulated crashes against a file and, after every step, compares the transaction counter, `verify`, full rows with windows and tx counts, and six query shapes under `:as-of N` and `:valid-at T` with a reference model (#385). `tests/property_test.rs` writes random histories (batched transacts, retracts, write transactions, checkpoints) in memory and to a file, and compares random queries (one to three joined patterns, `not` or `not-join`, a comparison predicate, `:as-of`, `:valid-at` or `:any-valid-time`) with a reference evaluator, on the open file and after a reopen; a query error fails the test (#386). `tests/crash_kill_test.rs` kills a child process running a seeded workload (multi-valued batches, batched retracts, five checkpoint modes) at a random point and checks that the reopened file holds exactly the transactions the child logged as committed, or those plus the one in flight, through full-scan, AEVT, AVET, EAVT and `:as-of` queries and `verify`, again after a second reopen and after a checkpoint plus reopen (#384). Integrity tests (#373) check that intact files verify with no problems and an exact fact and page count, and that `verify` reports each kind of damage with its code: an EAVT, AEVT, AVET or VAET leaf missing an entry (STG-038), keys out of order and a page reached from two trees (STG-039), a rotted index leaf (STG-029), a free page still in use and a leaked page (STG-035), a missing transaction entry (STG-036), and an entity id whose UUID maps to another id (STG-040). After each index or free-list damage, `rebuild_indexes` leaves a file that verifies clean, reads back every fact and accounts for every page. The source is an index that agrees with another one, or the only intact one; three intact indexes that all disagree, or a damaged dictionary, give STG-041 with the file unchanged. A rebuild commits pending facts, including new ids and long values. A crash at every write (clean and torn) and every sync of a rebuild reopens either at the old generation with only its old damage or at the new one with none, never losing a fact. Through `Minigraf` (`tests/integrity_test.rs`), a rebuild commits WAL entries and deletes the WAL, and flipping a byte in each leaf of a file in turn is always reported, then either repaired (index leaves) or refused with STG-041 and the file unchanged (dictionary leaves). Page-count tests (#497) check that a CRC-valid meta whose `page_count` is past the end of the file (one page past, 2^50, `u64::MAX`; with the other slot valid or damaged; with or without a WAL) and a file cut short by one page, three pages or down to three pages are `STG-044` at open, with the file unchanged and not grown, while a `page_count` exactly at the end opens; that a checkpoint whose pages did not all reach the backend fails with `INT-049` before writing its meta, and the file reopens at the previous generation; and that `verify` at a meta counting pages past the end reports `STG-044` without scanning to that count. Through `Minigraf` (`tests/integrity_test.rs`), a file truncated by one or three pages and a file whose meta was rewritten with `page_count` 2^50 and a valid CRC are `STG-044` read-write and read-only, with no WAL created and the file length unchanged. The `file_header` fuzz input from #497 is a corpus seed. Live-read tests (#379) check that `triple_len` ends exactly where `tx↓` begins for every value type and index; that on random histories (several valid-time windows, retractions, re-assertions, several values per attribute, long values, 12 transactions per checkpoint) the committed live read for every scan kind and `:as-of` point is exactly the net-asserted set, that it stays equivalent with pending facts on top, and after reopen; and that a point read on a triple asserted and retracted 2,000 times reads under a third of the pages a history read does, with or without `:as-of`. `tests/live_reads_test.rs` runs the same history in a checkpointed file database and in memory and checks that point, attribute, full-scan, join, valid-time, `:as-of` and rule queries return the same rows, before and after reopen. One-window tests (#435) check that `net_asserted_facts` keeps each triple's newest transaction only (a later window replaces an earlier one, closing an open window, a retraction in the newest transaction hides it, records with two windows in one transaction keep both, once each) against a per-triple model on random histories; that the on-disk key walk agrees at every `:as-of` before and after reopen; and that `API-011` rejects two windows of one fact in one transaction without taking a `tx_count`. `tests/valid_time_window_test.rs` checks replacing, closing, extending, reopening and retract-then-reassert through entity-bound and attribute queries in memory, on a checkpointed file and after reopen, `API-011` from `transact` and from `WriteTransaction::execute`, and a later statement's window committed when two statements of a `WriteTransaction` give one fact different windows. Window-validation tests (#436) check that `check_valid_windows` rejects an empty window, an inverted one, and a `:valid-to` at or before the transaction time when `:valid-from` is left out, but not retractions; that `execute` rejects each such `transact` (both bounds, equal bounds, `:valid-to` only, a per-fact bound inverting the transaction's window) with `API-019` without writing or taking a `tx_count`, in memory, checkpointed and after reopen; that `tx.execute()` rejects them and the transaction still commits its other statements; that `commit()` rejects a default `valid_from` that has passed the `:valid-to` by commit time; and that `FactStorage::transact_batch` takes no `tx_count` on rejection. Statement-order tests (#477, `tests/statement_order_test.rs`) run every mix of two statements on one fact inside a `WriteTransaction` (retract then assert, assert then retract, two retracts, two windows, after a committed assertion and on an empty database) and check that reads inside the transaction and the committed rows agree, in memory, checkpointed and after reopen; that other facts of an overridden statement survive; that the commit is one transaction without the overridden records; and that two windows in one statement are `API-011` from `tx.execute()` while the rest commits. A unit test checks the commit collapse keeps each fact's newest statement in order. A log-writer test checks that an inverted window is `API-019`, a second window of a fact in one transaction `API-011`, and an assertion and a retraction of one fact in one transaction `API-020` in either order, each leaving the writer usable and the output exact, while duplicate retractions, identical repeats and the same fact in the next transaction are accepted. Cursor tests (#432, `tests/cursor_test.rs`) check that `query()` batches partition the `execute()` answer for several batch sizes (never empty, never over `max_rows`, `max_rows == 0` still progresses, `None` stays `None`), that the iterator and aggregates, rules, `:as-of` and `:any-valid-time` match `execute()`, that a cursor opened before a `transact`, a `WriteTransaction` commit, a retract or a checkpoint returns the pre-write answer to the end (in memory and file-backed), that `transact`/`retract`/`rule` are `API-012` and bind slots `API-010`, that a `WriteTransaction` thread gets `INT-001`, that rule limits give `INT-020` as from `execute()`, that `PreparedQuery::query` matches `PreparedQuery::execute`, and that a cursor is `Send` and outlives its database handle. Fact-log tests (#430, `tests/fact_log_test.rs`) check that `fact_log()` returns exactly the records written (assertions and retractions, with `tx_count` and `tx_id`) in memory, with everything pending, half checkpointed, fully checkpointed and after reopen, in both orders, with windows of 1 to 1,000 records and batch sizes of 1 to 1,000, in non-decreasing `tx_count` in Tx order; that every layout gives identical records, including valid-time windows and long string values; that a transaction larger than the window is split with no loss or duplicate; that attribute, attribute-prefix, entity and tx-range filters and their combinations match a model, and unknown names match nothing; that writes after open are not in the log; that `checkpoint()` and `rebuild_indexes()` are `API-013` while a log is open (a checkpoint with nothing to write is allowed), that automatic checkpoints from `execute()` and `WriteTransaction::commit` wait for the log, and that closing, dropping or finishing the log releases the database; that a `WriteTransaction` thread gets `INT-001`; and that a log is `Send`, outlives its database handle, and the deferred writes replay on the next open. Read-only open tests (#429, `tests/read_only_open_test.rs`) check that a read-only handle on a file with checkpointed facts and a pending WAL returns the same query results, `tx_count` and fact log as a read-write open; that queries, a cursor, a fact log, `verify`, `prepare`, rules and a UDF leave the `.graph` and WAL bytes and the `.graph` mtime unchanged, and no WAL is created; that `transact`, `retract`, `begin_write`, `checkpoint` and `rebuild_indexes` are `API-014` without taking a `tx_count`, also on a read-only in-memory database and through the builder path; that a missing file is `STG-042` and nothing is created; that an empty file is an empty database and stays 0 bytes; that read-only handles share a file while a read-write one is refused with `STG-025`, both ways; that a file without write permission opens read-only; and that small and whole-file page caches work. File-backend unit tests check that a shared-mode backend refuses page writes and syncs with `INT-056`, that the in-process registry counts readers and admits readers or one writer (also without kernel locks), and that a reader in another process shares the file with a reader here and refuses a writer here with `STG-026`. Storage unit tests check that a read-only open of a v7 file at every point of an interrupted migration (clean and torn writes) sees every fact and writes nothing, and that an empty backend stays empty. `tests/golden_corpus_test.rs` opens a copy of every golden file read-only first and checks its `tx_count` and queries, and that neither the file nor its WAL changes. Log-writer tests (#431, `tests/log_writer_test.rs`) copy a source's fact log (assertions, retractions, an explicit valid-time window, long strings, refs, keywords, checkpointed and pending facts) through `LogWriter` and check that the new file has no `.partial` or WAL, verifies clean, and gives the source's `tx_count`, fact log and query results (current, `:valid-at`, `:any-valid-time`, every `:as-of`, and entity-, attribute- and value-bound lookups) read-write, read-only and after reopen (#370); that it takes new writes at the source's next `tx_count`; that 90,000 facts over two batch commits verify clean and count correctly at `:as-of`; that a purged middle transaction is a hole whose `:as-of` equals the one before, and trailing holes keep the counter through `advance_tx_count`; that an empty log is an empty database with the counter; that `tx_count` 0, a lower or closed transaction and a backwards advance are `API-015`, a second `tx_id` `API-016`, a second window `API-011`, a retraction of an asserted fact in one transaction `API-020`, an empty window `API-019` and oversize values or idents `WAL-003`, each leaving the writer usable and the output exact, with repeats written once; that an existing target or WAL is `STG-043`, a second writer `STG-025` and `read_only` `API-014`; that a stale `.partial` is reused; that dropping an unfinished writer leaves nothing; that `finish` refuses a target created during the build and leaves it untouched; and that `LogWriter` is `Send`. Unit tests check that a batch commits only when a transaction opens past the batch size, never splitting one, and that `FileBackend::truncate` empties a file. A unit test in `error.rs` checks that `MinigrafError::invalid_argument` and `MinigrafError::closed`, the constructors for language bindings, give API-017 and API-018 with their text. Query-validation tests (#406, #414) check that a plain `:find` variable or a window function's argument, `:partition-by` or `:order-by` variable that no `:where` clause binds (including `?_` wildcards) is `PRS-080` from both `execute()` and `prepare()`, naming the variable, while variables bound by a pattern, an attribute position, a rule call, an expression binding, an `or-join`, every branch of an `or`, a pseudo-attribute or a window spec are accepted, and bind slots are not mistaken for `:find` variables; and that an unknown aggregate is `QRY-010` and an unknown window function `QRY-011` on an empty database, when no row matches, when rows match, through a rule query and through a prepared query, while a registered UDF in either position returns an empty result on an empty database. Three `BrowserDb` tests (wasm32, run with `wasm-bindgen-test` in a browser, not counted above) check that `query()` batches of 1, 7 and 1,000 give the rows of `execute()`, that a cursor keeps the answer from when it opened and returns the end after `close()`, and that a `transact` is API-012. The wasm32 targets run in CI (`.github/workflows/wasm.yml`). In a browser (`wasm-pack test --headless`, Firefox and Chrome): 32 `wasm_bindgen_test` tests: nineteen for `BrowserDb` (including IndexedDB persistence, the cursor, and the flush returning every dirty page and failing on one it cannot read, from #470), eleven for `BrowserBufferBackend` (which used `#[test]` and never ran before), and two checking that IndexedDB page keys accept only whole numbers from 0 to 2^53. Five of the `BrowserDb` tests (#411, #440) check that opening a v7 store written straight into IndexedDB stores a v8 meta page and only the live pages, with nothing written on the next open; that after each of 60 transacts memory, and at the end IndexedDB, hold exactly the pages not on the free list while the file grows by under one page per transact; that a commit applied in memory but never flushed reopens at the previous one and keeps working; that an export after churn is as long as the meta says and imports back with its free pages dropped; and that `importGraph()` deletes the replaced database's IndexedDB keys. Two buffer tests check that releasing a page drops its bytes and any unflushed write, and that export writes a released page as zeros. A native storage test checks that a file whose free pages are all zeros (as the browser exports them), both just migrated from v7 and after 20 saves, opens, verifies clean and keeps committing, and the free-list test checks that a checkpoint reports exactly the ids it newly lists. On `wasm32-wasip1` under Wasmtime: the unit and integration tests that do not use a file run, 935 passing; nine that spawn threads or a child process are ignored on WASI. These are not counted above. +This covers the unreleased file-format-v8 work (#287, #371): the index-key value-collision fix, the v7→v8 migration, and the drop of formats v1–v6. It otherwise still covers the public database API, the Datalog engine, storage and recovery paths, v2.0.0's locking and structured-error-code changes, and v2.0.1's regression test for rebuilding indexes on open after several checkpoints (#370). Merged from the v2.x line: `tests/point_query_history_test.rs` and new storage unit tests check that attribute-narrowed bound-entity lookups return exactly what a full scan returns, and that `net_asserted_facts` matches its previous implementation on randomized histories (#323). Attribute-scan tests check that the AEVT range covers exactly the queried attribute, including non-ASCII names such as `:丿` and prefix siblings such as `:ab` for `:a` (#381). Incremental B+tree rebuild tests check that checkpoints which copy untouched index leaves produce exactly the entries and file checksum a full rebuild would, including over repeated checkpoints, that single-fact checkpoints do not fragment the index, and that a damaged slot directory is rejected rather than copied (#315). B+tree cursor tests check that every scan walks the tree, not the leaf `next_leaf` chain: full scans and start positions match the input, `seek` from the current position lands where a fresh descent from the root would (randomized, plus within a leaf, to a sibling, across subtrees, past the end, into the gap after a leaf, and backwards as a no-op), a seek to the sibling leaf reads exactly one page, reads are unchanged with every `next_leaf` zeroed, a child pointer into a non-B+tree page is STG-013, and a cycle in child pointers is an error, not a hang (v8 storage format PR 1, #374). Directory-sync unit tests check that creating the `.graph` file or the WAL, and deleting the WAL, fsync the parent directory after the file operation, and that reopening an existing file does not (#389). Disjunction tests check that `or-join` returns an empty result, not INT-031, when no rows reach it: on an empty database, after a pattern that matches nothing, after a `not` that removes every row, and in a rule body (#405). A stratification unit test builds the same two-rule negative cycle 64 times and checks that the INT-054 message names the same predicate pair every time (#410). Magic-sets tests check that a recursive rule with a literal start that recurses through another rule returns the same results as without the literal (#297). API tests check that `execute()` and `WriteTransaction::execute()` reject `$slot` bind tokens in every position with API-010 (#407). The REPL `run()` test now runs in a child process with null stdin, so it no longer hangs when the test runner's stdin is an open non-TTY stream (#415). v8 page-format tests (PR 2, #374, #388) check the 24-byte page header (a flipped bit, a wrong page id and a future generation each give their own STG code, legacy page types fail before the CRC, and a failed page is never cached), meta-page encoding, the free-list chain, WAL v2's base generation, and every row of the meta-selection table: both slots valid, a torn newest slot with the WAL's base generation (opens at the older one), a WAL newer than the valid meta, pages of the next generation on the free list or past `page_count` with no WAL (all STG-033, with the file unmodified), an unknown feature bit (STG-034), and a pre-release v8 single header (STG-032). Fault-injection tests crash `save()` at every page write (cleanly and with torn pages, including the meta write) and every sync, and crash a v7 migration at every write; each reopen finds exactly the old or the new checkpoint, and every reachable page plus the free list covers the file exactly. Twenty-five consecutive saves never write a page the previous meta references. Covering-key tests (PR 3, #433) check that byte order equals logical order for every key component and value type on random tuples (negative, zero and large integers, NaN and ±0.0, strings with 0x00, 64- and 65-byte strings, FOREVER, newest-transaction-first) and that every component round-trips; that prefix-compressed leaves and shortest-separator internal nodes round-trip, agree with a linear scan, keep `max(left) < s ≤ min(right)`, and reject an overflow; that the byte-key B+tree's builds, incremental rebuilds, cursor and `seek` match their expected sets; that dictionary ids are assigned once, never reused, shared between a keyword attribute and value, and deterministic; that a re-asserted or retracted long value writes no new value page and a forced hash collision still finds the right value; that one transaction with two timestamps is STG-037 and a missing dictionary entry STG-036; that committed reads by entity, entity and attribute, attribute, and in full equal an in-memory model across eight checkpoints and a reopen; that short-valued reads touch no value page; that a v7 file with every value type, long strings, refs and retractions migrates to exactly the same facts; that a pre-covering-key v8 file is STG-032; and that string values over 4,068 bytes and attributes or keywords over 1,024 bytes are WAL-003. A WAL test checks that reopening next to a fully checkpointed WAL does not reuse transaction numbers (#447). Copy-on-write checkpoint tests (PR 4, #434) check that lazy free-list pops and pushes conserve every page across page boundaries, partial head pages and chain exhaustion, never hand out a page freed in the same generation, and share unread chain pages unchanged; that a copy-on-write insert equals a sorted merge for random batches (including keys below the first and above the last, many into one leaf, root growth to depth 3, and 1 KB separators that split internal nodes), leaves the old tree readable and unchanged, frees exactly the replaced nodes, writes only new pages, writes exactly one leaf and two internal nodes for one entry in a depth-3 tree, and does not fragment leaves under single inserts; that a checkpoint after 1 or 100 right-edge facts writes at most the tree-depth difference more pages at 100,000 facts than at 10,000, and at most one path per new entry per tree for random keys; and that four reader threads querying throughout 40 checkpoints never fail and never see the fact count go backwards. Hardening tests (PR 5) damage an index leaf, an internal node, a dictionary leaf, a value page and a free-list page in turn. Every committed read or checkpoint that reaches the damaged page fails with STG-029, never with wrong or fewer rows. A query through `Minigraf` on a file with damaged leaves fails with STG-029, and the file still opens at its last checkpoint. A size test measures at most 200 bytes per fact (142 measured) on 144k facts in #433's shape; its 1.15M-fact variant is ignored locally and runs in the nightly smoke workflow. A shared dictionary-cache test checks that cached ident and timestamp lookups return the same facts and that the cache stays bounded. Merged from the v2.x line: storage and `edge_cases_test.rs` tests check that more than 65,535 uncheckpointed facts each resolve to their own fact through entity lookups and attribute scans, in memory and file-backed (#445). Merged from the v2.x line: `tests/golden_corpus_test.rs` opens a copy of each committed golden file in `tests/golden/` (v7 files written by minigraf 2.0.3: one checkpoint, several checkpoints, indexes rebuilt on open, a crash-left WAL, an already-checkpointed WAL, same-transaction multi-values) and checks its manifest's CRC32, `tx_count` and query results after open, after a checkpoint and reopen, and after one more write; a second test checks that every golden file has a manifest (#391). On `v3` the same test checks that each v7 file has a v8 meta page after its first open and gives the same results after reopening the migrated file, and adds seven v8 golden files (one checkpoint, seven copy-on-write checkpoints, a crash-left v2 WAL, an already-checkpointed v2 WAL, same-transaction multi-values, a v7 file migrated in place, and long values at the size limits); the #371 queries, skipped on v2.x, run and pass. `tests/model_based_test.rs` runs random sequences of transacts, retracts, write transactions, checkpoints, reopens and simulated crashes against a file and, after every step, compares the transaction counter, `verify`, full rows with windows and tx counts, and six query shapes under `:as-of N` and `:valid-at T` with a reference model (#385). `tests/property_test.rs` writes random histories (batched transacts, retracts, write transactions, checkpoints) in memory and to a file, and compares random queries (one to three joined patterns, `not` or `not-join`, a comparison predicate, `:as-of`, `:valid-at` or `:any-valid-time`) with a reference evaluator, on the open file and after a reopen; a query error fails the test (#386). `tests/crash_kill_test.rs` kills a child process running a seeded workload (multi-valued batches, batched retracts, five checkpoint modes) at a random point and checks that the reopened file holds exactly the transactions the child logged as committed, or those plus the one in flight, through full-scan, AEVT, AVET, EAVT and `:as-of` queries and `verify`, again after a second reopen and after a checkpoint plus reopen (#384). Integrity tests (#373) check that intact files verify with no problems and an exact fact and page count, and that `verify` reports each kind of damage with its code: an EAVT, AEVT, AVET or VAET leaf missing an entry (STG-038), keys out of order and a page reached from two trees (STG-039), a rotted index leaf (STG-029), a free page still in use and a leaked page (STG-035), a missing transaction entry (STG-036), and an entity id whose UUID maps to another id (STG-040). After each index or free-list damage, `rebuild_indexes` leaves a file that verifies clean, reads back every fact and accounts for every page. The source is an index that agrees with another one, or the only intact one; three intact indexes that all disagree, or a damaged dictionary, give STG-041 with the file unchanged. A rebuild commits pending facts, including new ids and long values. A crash at every write (clean and torn) and every sync of a rebuild reopens either at the old generation with only its old damage or at the new one with none, never losing a fact. Through `Minigraf` (`tests/integrity_test.rs`), a rebuild commits WAL entries and deletes the WAL, and flipping a byte in each leaf of a file in turn is always reported, then either repaired (index leaves) or refused with STG-041 and the file unchanged (dictionary leaves). Page-count tests (#497) check that a CRC-valid meta whose `page_count` is past the end of the file (one page past, 2^50, `u64::MAX`; with the other slot valid or damaged; with or without a WAL) and a file cut short by one page, three pages or down to three pages are `STG-044` at open, with the file unchanged and not grown, while a `page_count` exactly at the end opens; that a checkpoint whose pages did not all reach the backend fails with `INT-049` before writing its meta, and the file reopens at the previous generation; and that `verify` at a meta counting pages past the end reports `STG-044` without scanning to that count. Through `Minigraf` (`tests/integrity_test.rs`), a file truncated by one or three pages and a file whose meta was rewritten with `page_count` 2^50 and a valid CRC are `STG-044` read-write and read-only, with no WAL created and the file length unchanged. The `file_header` fuzz input from #497 is a corpus seed. A sub-page test (#506, `tests/integrity_test.rs`) checks that a file of 1 to 4,095 bytes is `STG-045` read-write and read-only, unchanged and with no WAL, when it is a database cut below one page or foreign bytes, and opens as a new database that takes writes when it is a prefix of the first meta page or all zeros; a file-backend unit test checks that `partial_page` returns the bytes past the last whole page. The `corrupt_file` fuzzer no longer skips files under one page: they must fail to open or open empty, and the #506 input is a corpus seed. Live-read tests (#379) check that `triple_len` ends exactly where `tx↓` begins for every value type and index; that on random histories (several valid-time windows, retractions, re-assertions, several values per attribute, long values, 12 transactions per checkpoint) the committed live read for every scan kind and `:as-of` point is exactly the net-asserted set, that it stays equivalent with pending facts on top, and after reopen; and that a point read on a triple asserted and retracted 2,000 times reads under a third of the pages a history read does, with or without `:as-of`. `tests/live_reads_test.rs` runs the same history in a checkpointed file database and in memory and checks that point, attribute, full-scan, join, valid-time, `:as-of` and rule queries return the same rows, before and after reopen. One-window tests (#435) check that `net_asserted_facts` keeps each triple's newest transaction only (a later window replaces an earlier one, closing an open window, a retraction in the newest transaction hides it, records with two windows in one transaction keep both, once each) against a per-triple model on random histories; that the on-disk key walk agrees at every `:as-of` before and after reopen; and that `API-011` rejects two windows of one fact in one transaction without taking a `tx_count`. `tests/valid_time_window_test.rs` checks replacing, closing, extending, reopening and retract-then-reassert through entity-bound and attribute queries in memory, on a checkpointed file and after reopen, `API-011` from `transact` and from `WriteTransaction::execute`, and a later statement's window committed when two statements of a `WriteTransaction` give one fact different windows. Window-validation tests (#436) check that `check_valid_windows` rejects an empty window, an inverted one, and a `:valid-to` at or before the transaction time when `:valid-from` is left out, but not retractions; that `execute` rejects each such `transact` (both bounds, equal bounds, `:valid-to` only, a per-fact bound inverting the transaction's window) with `API-019` without writing or taking a `tx_count`, in memory, checkpointed and after reopen; that `tx.execute()` rejects them and the transaction still commits its other statements; that `commit()` rejects a default `valid_from` that has passed the `:valid-to` by commit time; and that `FactStorage::transact_batch` takes no `tx_count` on rejection. Statement-order tests (#477, `tests/statement_order_test.rs`) run every mix of two statements on one fact inside a `WriteTransaction` (retract then assert, assert then retract, two retracts, two windows, after a committed assertion and on an empty database) and check that reads inside the transaction and the committed rows agree, in memory, checkpointed and after reopen; that other facts of an overridden statement survive; that the commit is one transaction without the overridden records; and that two windows in one statement are `API-011` from `tx.execute()` while the rest commits. A unit test checks the commit collapse keeps each fact's newest statement in order. A log-writer test checks that an inverted window is `API-019`, a second window of a fact in one transaction `API-011`, and an assertion and a retraction of one fact in one transaction `API-020` in either order, each leaving the writer usable and the output exact, while duplicate retractions, identical repeats and the same fact in the next transaction are accepted. Cursor tests (#432, `tests/cursor_test.rs`) check that `query()` batches partition the `execute()` answer for several batch sizes (never empty, never over `max_rows`, `max_rows == 0` still progresses, `None` stays `None`), that the iterator and aggregates, rules, `:as-of` and `:any-valid-time` match `execute()`, that a cursor opened before a `transact`, a `WriteTransaction` commit, a retract or a checkpoint returns the pre-write answer to the end (in memory and file-backed), that `transact`/`retract`/`rule` are `API-012` and bind slots `API-010`, that a `WriteTransaction` thread gets `INT-001`, that rule limits give `INT-020` as from `execute()`, that `PreparedQuery::query` matches `PreparedQuery::execute`, and that a cursor is `Send` and outlives its database handle. Fact-log tests (#430, `tests/fact_log_test.rs`) check that `fact_log()` returns exactly the records written (assertions and retractions, with `tx_count` and `tx_id`) in memory, with everything pending, half checkpointed, fully checkpointed and after reopen, in both orders, with windows of 1 to 1,000 records and batch sizes of 1 to 1,000, in non-decreasing `tx_count` in Tx order; that every layout gives identical records, including valid-time windows and long string values; that a transaction larger than the window is split with no loss or duplicate; that attribute, attribute-prefix, entity and tx-range filters and their combinations match a model, and unknown names match nothing; that writes after open are not in the log; that `checkpoint()` and `rebuild_indexes()` are `API-013` while a log is open (a checkpoint with nothing to write is allowed), that automatic checkpoints from `execute()` and `WriteTransaction::commit` wait for the log, and that closing, dropping or finishing the log releases the database; that a `WriteTransaction` thread gets `INT-001`; and that a log is `Send`, outlives its database handle, and the deferred writes replay on the next open. Read-only open tests (#429, `tests/read_only_open_test.rs`) check that a read-only handle on a file with checkpointed facts and a pending WAL returns the same query results, `tx_count` and fact log as a read-write open; that queries, a cursor, a fact log, `verify`, `prepare`, rules and a UDF leave the `.graph` and WAL bytes and the `.graph` mtime unchanged, and no WAL is created; that `transact`, `retract`, `begin_write`, `checkpoint` and `rebuild_indexes` are `API-014` without taking a `tx_count`, also on a read-only in-memory database and through the builder path; that a missing file is `STG-042` and nothing is created; that an empty file is an empty database and stays 0 bytes; that read-only handles share a file while a read-write one is refused with `STG-025`, both ways; that a file without write permission opens read-only; and that small and whole-file page caches work. File-backend unit tests check that a shared-mode backend refuses page writes and syncs with `INT-056`, that the in-process registry counts readers and admits readers or one writer (also without kernel locks), and that a reader in another process shares the file with a reader here and refuses a writer here with `STG-026`. Storage unit tests check that a read-only open of a v7 file at every point of an interrupted migration (clean and torn writes) sees every fact and writes nothing, and that an empty backend stays empty. `tests/golden_corpus_test.rs` opens a copy of every golden file read-only first and checks its `tx_count` and queries, and that neither the file nor its WAL changes. Log-writer tests (#431, `tests/log_writer_test.rs`) copy a source's fact log (assertions, retractions, an explicit valid-time window, long strings, refs, keywords, checkpointed and pending facts) through `LogWriter` and check that the new file has no `.partial` or WAL, verifies clean, and gives the source's `tx_count`, fact log and query results (current, `:valid-at`, `:any-valid-time`, every `:as-of`, and entity-, attribute- and value-bound lookups) read-write, read-only and after reopen (#370); that it takes new writes at the source's next `tx_count`; that 90,000 facts over two batch commits verify clean and count correctly at `:as-of`; that a purged middle transaction is a hole whose `:as-of` equals the one before, and trailing holes keep the counter through `advance_tx_count`; that an empty log is an empty database with the counter; that `tx_count` 0, a lower or closed transaction and a backwards advance are `API-015`, a second `tx_id` `API-016`, a second window `API-011`, a retraction of an asserted fact in one transaction `API-020`, an empty window `API-019` and oversize values or idents `WAL-003`, each leaving the writer usable and the output exact, with repeats written once; that an existing target or WAL is `STG-043`, a second writer `STG-025` and `read_only` `API-014`; that a stale `.partial` is reused; that dropping an unfinished writer leaves nothing; that `finish` refuses a target created during the build and leaves it untouched; and that `LogWriter` is `Send`. Unit tests check that a batch commits only when a transaction opens past the batch size, never splitting one, and that `FileBackend::truncate` empties a file. A unit test in `error.rs` checks that `MinigrafError::invalid_argument` and `MinigrafError::closed`, the constructors for language bindings, give API-017 and API-018 with their text. Query-validation tests (#406, #414) check that a plain `:find` variable or a window function's argument, `:partition-by` or `:order-by` variable that no `:where` clause binds (including `?_` wildcards) is `PRS-080` from both `execute()` and `prepare()`, naming the variable, while variables bound by a pattern, an attribute position, a rule call, an expression binding, an `or-join`, every branch of an `or`, a pseudo-attribute or a window spec are accepted, and bind slots are not mistaken for `:find` variables; and that an unknown aggregate is `QRY-010` and an unknown window function `QRY-011` on an empty database, when no row matches, when rows match, through a rule query and through a prepared query, while a registered UDF in either position returns an empty result on an empty database. Three `BrowserDb` tests (wasm32, run with `wasm-bindgen-test` in a browser, not counted above) check that `query()` batches of 1, 7 and 1,000 give the rows of `execute()`, that a cursor keeps the answer from when it opened and returns the end after `close()`, and that a `transact` is API-012. The wasm32 targets run in CI (`.github/workflows/wasm.yml`). In a browser (`wasm-pack test --headless`, Firefox and Chrome): 32 `wasm_bindgen_test` tests: nineteen for `BrowserDb` (including IndexedDB persistence, the cursor, and the flush returning every dirty page and failing on one it cannot read, from #470), eleven for `BrowserBufferBackend` (which used `#[test]` and never ran before), and two checking that IndexedDB page keys accept only whole numbers from 0 to 2^53. Five of the `BrowserDb` tests (#411, #440) check that opening a v7 store written straight into IndexedDB stores a v8 meta page and only the live pages, with nothing written on the next open; that after each of 60 transacts memory, and at the end IndexedDB, hold exactly the pages not on the free list while the file grows by under one page per transact; that a commit applied in memory but never flushed reopens at the previous one and keeps working; that an export after churn is as long as the meta says and imports back with its free pages dropped; and that `importGraph()` deletes the replaced database's IndexedDB keys. Two buffer tests check that releasing a page drops its bytes and any unflushed write, and that export writes a released page as zeros. A native storage test checks that a file whose free pages are all zeros (as the browser exports them), both just migrated from v7 and after 20 saves, opens, verifies clean and keeps committing, and the free-list test checks that a checkpoint reports exactly the ids it newly lists. On `wasm32-wasip1` under Wasmtime: the unit and integration tests that do not use a file run, 935 passing; nine that spawn threads or a child process are ignored on WASI. These are not counted above. ### Covered Areas diff --git a/fuzz/corpus/corrupt_file/seed_truncate_sub_page.bin b/fuzz/corpus/corrupt_file/seed_truncate_sub_page.bin new file mode 100644 index 0000000000000000000000000000000000000000..abed1a0f7b49b8cf543fd24e8901da1032811a43 GIT binary patch literal 8 PcmY#c$HBnBu&xsT2mb;R literal 0 HcmV?d00001 diff --git a/fuzz/corpus/corrupt_file/seed_truncate_to_meta_prefix.bin b/fuzz/corpus/corrupt_file/seed_truncate_to_meta_prefix.bin new file mode 100644 index 0000000000000000000000000000000000000000..73ed3973ad671d278e3aebd0d71226c62f91ce8e GIT binary patch literal 5 McmZSKU|?VX0021v4FCWD literal 0 HcmV?d00001 diff --git a/fuzz/fuzz_targets/corrupt_file.rs b/fuzz/fuzz_targets/corrupt_file.rs index b8d50c5919..40db908f3c 100644 --- a/fuzz/fuzz_targets/corrupt_file.rs +++ b/fuzz/fuzz_targets/corrupt_file.rs @@ -15,7 +15,9 @@ //! Each query must fail or return exactly the answer of the last generation or //! of the one before it (the meta fallback when the active meta page is //! damaged), and every query that answers must agree on one generation. A -//! mismatch panics. `verify()` runs too and may fail, but must not panic. +//! mismatch panics. A file cut below one page must fail to open or open as a +//! new, empty database (#506). `verify()` runs too and may fail, but must not +//! panic. #![no_main] use libfuzzer_sys::fuzz_target; use minigraf::{Minigraf, OpenOptions, QueryResult}; @@ -162,11 +164,6 @@ fuzz_target!(|data: &[u8]| { 2 => bytes.truncate(trunc), _ => {} } - // An empty file opens as a new, empty database. A file shorter than one - // page does too today (#506); skipped until that is fixed. - if bytes.len() < PAGE_SIZE { - return; - } let Ok(dir) = tempfile::tempdir() else { return; @@ -180,6 +177,19 @@ fuzz_target!(|data: &[u8]| { return; }; + // A file shorter than one page opens only as a new, empty database: when + // it is empty, or what is left is a prefix of a first meta write (#506). + if bytes.len() < PAGE_SIZE { + assert_eq!(db.current_tx_count(), 0, "short file opened with data"); + for q in QUERIES { + assert!( + rows(&db, q).is_none_or(|r| r.is_empty()), + "short file answered with data" + ); + } + return; + } + // The last generation, or the one before it; narrowed by every answer. let mut candidates: Vec<&Answers> = t.generations[1..].iter().collect(); candidates.retain(|g| g.tx_count == db.current_tx_count()); diff --git a/src/error.rs b/src/error.rs index ff3ae12463..26c4467f48 100644 --- a/src/error.rs +++ b/src/error.rs @@ -188,6 +188,7 @@ pub(crate) enum ErrorCode { Stg042, Stg043, Stg044, + Stg045, Wal001, Wal002, Wal003, @@ -1093,6 +1094,12 @@ pub(crate) const REGISTRY: &[(ErrorCode, &str, &str, ErrorCategory)] = &[ "File is shorter than its meta page: the meta counts {} pages but the file holds {} (truncated?)", ErrorCategory::Storage, ), + ( + ErrorCode::Stg045, + "STG-045", + "File is {} bytes, shorter than one page, and is not a new Minigraf database", + ErrorCategory::Storage, + ), ( ErrorCode::Wal001, "WAL-001", @@ -2007,6 +2014,7 @@ mod tests { | ErrorCode::Stg042 | ErrorCode::Stg043 | ErrorCode::Stg044 + | ErrorCode::Stg045 | ErrorCode::Wal001 | ErrorCode::Wal002 | ErrorCode::Wal003 @@ -2229,6 +2237,7 @@ mod tests { ErrorCode::Stg042, ErrorCode::Stg043, ErrorCode::Stg044, + ErrorCode::Stg045, ErrorCode::Wal001, ErrorCode::Wal002, ErrorCode::Wal003, diff --git a/src/storage/backend/fault_inject.rs b/src/storage/backend/fault_inject.rs index 8963531066..96264d1646 100644 --- a/src/storage/backend/fault_inject.rs +++ b/src/storage/backend/fault_inject.rs @@ -102,6 +102,10 @@ impl StorageBackend for FaultInjectingBackend { self.inner.holds_every_page() } + fn partial_page(&self) -> Result>> { + self.inner.partial_page() + } + fn close(&mut self) -> Result<()> { let mut cfg = self.config.lock().unwrap(); let limit = cfg.fail_close_after; diff --git a/src/storage/backend/file.rs b/src/storage/backend/file.rs index e921e89134..487090aceb 100644 --- a/src/storage/backend/file.rs +++ b/src/storage/backend/file.rs @@ -442,6 +442,23 @@ impl StorageBackend for FileBackend { Ok(self.page_count) } + fn partial_page(&self) -> Result>> { + let start = self + .page_count + .checked_mul(PAGE_SIZE as u64) + .ok_or_else(|| { + err_coded!( + ErrorCode::Int048, + format!("page offset overflow for page_count {}", self.page_count) + ) + })?; + let mut file = &self.file; + file.seek(SeekFrom::Start(start))?; + let mut tail = Vec::new(); + file.take(PAGE_SIZE as u64).read_to_end(&mut tail)?; + Ok((!tail.is_empty()).then_some(tail)) + } + fn close(&mut self) -> Result<()> { if self.read_only { return Ok(()); @@ -494,6 +511,7 @@ mod tests { { let mut backend = FileBackend::open(&path).unwrap(); assert_eq!(backend.page_count().unwrap(), 0); + assert_eq!(backend.partial_page().unwrap(), None); backend.write_page(5, &vec![0xABu8; PAGE_SIZE]).unwrap(); assert_eq!(backend.page_count().unwrap(), 6); assert!(backend.read_page(6).is_err(), "past the end must fail"); @@ -511,9 +529,14 @@ mod tests { let mut backend = FileBackend::open(&path).unwrap(); assert!(backend.page_count().unwrap() > 0); assert_eq!(backend.page_count().unwrap(), 6, "partial page not counted"); + assert_eq!( + backend.partial_page().unwrap(), + Some(vec![0xCDu8; PAGE_SIZE / 2]) + ); backend.write_page(6, &vec![0x11u8; PAGE_SIZE]).unwrap(); assert_eq!(backend.read_page(6).unwrap()[PAGE_SIZE - 1], 0x11); assert_eq!(backend.page_count().unwrap(), 7); + assert_eq!(backend.partial_page().unwrap(), None, "tail overwritten"); } /// The child half of [`test_cross_process_lock_retries_then_fails_within_budget`]: diff --git a/src/storage/btree.rs b/src/storage/btree.rs index 8f3a700763..b55a67017c 100644 --- a/src/storage/btree.rs +++ b/src/storage/btree.rs @@ -745,6 +745,13 @@ impl StorageBackend for MutexStorageBackend { self.0.lock().map_or(true, |b| b.holds_every_page()) } + fn partial_page(&self) -> Result>> { + self.0 + .lock() + .map_err(|_| err_coded!(ErrorCode::Int050, "MutexStorageBackend"))? + .partial_page() + } + fn close(&mut self) -> Result<()> { bail_coded!(ErrorCode::Int049, "MutexStorageBackend is read-only") } diff --git a/src/storage/mod.rs b/src/storage/mod.rs index b561d812ba..760861d93d 100644 --- a/src/storage/mod.rs +++ b/src/storage/mod.rs @@ -102,6 +102,15 @@ pub trait StorageBackend: Send + Sync { true } + /// The bytes past the last whole page, if any: a file whose length is not + /// a multiple of `PAGE_SIZE` ends in a partial page that `page_count` + /// leaves out. Open uses it to tell a torn first write of a new file from + /// a short file that is something else (#506). Backends without a byte + /// length return `None`. + fn partial_page(&self) -> Result>> { + Ok(None) + } + /// Close the storage backend. /// /// Performs final sync and cleanup. diff --git a/src/storage/persistent_facts.rs b/src/storage/persistent_facts.rs index 1b249c46ab..7b34a031ba 100644 --- a/src/storage/persistent_facts.rs +++ b/src/storage/persistent_facts.rs @@ -183,6 +183,14 @@ impl PersistentFactStorage { let mut backend = self.lock()?; let page_count = backend.page_count()?; if page_count == 0 { + // A file shorter than one page is new only if it holds a torn + // first write of `init_empty`; anything else is not ours to + // re-initialise (#506). + if let Some(tail) = backend.partial_page()? + && !is_initial_meta_prefix(&tail) + { + bail_coded!(ErrorCode::Stg045, tail.len()); + } return Ok(Opened::Fresh); } let page0 = backend.read_page(0)?; @@ -796,12 +804,7 @@ fn check_single_valid( /// file: a prefix of its bytes, then zeros, with page 1 (if present) all zero. /// Such a file never committed anything, so it is safe to initialise again. fn is_torn_initial_meta(backend: &dyn StorageBackend, page0: &[u8]) -> Result { - let expected = MetaPage::empty(1).encode(); - let written = page0 - .iter() - .rposition(|&b| b != 0) - .map_or(0, |i| i.saturating_add(1)); - if page0.get(..written) != expected.get(..written) { + if !is_initial_meta_prefix(page0) { return Ok(false); } if backend.page_count()? > 1 && backend.read_page(1)?.iter().any(|&b| b != 0) { @@ -810,6 +813,17 @@ fn is_torn_initial_meta(backend: &dyn StorageBackend, page0: &[u8]) -> Result bool { + let expected = MetaPage::empty(1).encode(); + let written = bytes + .iter() + .rposition(|&b| b != 0) + .map_or(0, |i| i.saturating_add(1)); + bytes.get(..written) == expected.get(..written) +} + /// Encode `facts` for a checkpoint on top of `m`'s dictionary: assign ids, /// write new long values to fresh value pages, and build every tree's entries. fn encode( diff --git a/tests/integrity_test.rs b/tests/integrity_test.rs index 01b9796718..4ce4b5fa9a 100644 --- a/tests/integrity_test.rs +++ b/tests/integrity_test.rs @@ -170,6 +170,53 @@ fn truncated_file_is_refused_at_open() { } } +/// A file shorter than one page opens as a new database only when it is a +/// torn first write: zeros, or a prefix of the empty generation-1 meta. Any +/// other short file (here a database cut to under a page, or foreign bytes) is refused with STG-045, read-write and read-only, and is +/// left as it was; it used to be re-initialised (#506). +#[test] +fn sub_page_file_is_refused_unless_a_torn_first_write() { + let dir = tempfile::tempdir().unwrap(); + let (path, _) = checkpointed_file(dir.path(), "short.graph"); + // A second checkpoint moves page 0 off the empty generation-1 meta. A + // file cut below a page after one checkpoint is indistinguishable from a + // torn first write, and holds nothing to keep: every tree lies past it. + { + let db = Minigraf::open(&path).unwrap(); + fill(&db, 200, 210); + db.checkpoint().unwrap(); + } + let template = std::fs::read(&path).unwrap(); + std::fs::remove_file(&path).unwrap(); + let foreign = vec![0x5Au8; 100]; + for bytes in [&template[..2222], &template[..20], &foreign[..]] { + std::fs::write(&path, bytes).unwrap(); + assert_eq!(open_code(&path, false), "STG-045"); + assert_eq!(open_code(&path, true), "STG-045"); + assert_eq!(std::fs::read(&path).unwrap(), bytes, "file unchanged"); + assert!( + !dir.path().join("short.graph.wal").exists(), + "no WAL created" + ); + } + + // A torn first write: init_empty's page 0 cut short, or zeros. + let fresh = dir.path().join("fresh.graph"); + drop(Minigraf::open(&fresh).unwrap()); + let initial = std::fs::read(&fresh).unwrap(); + std::fs::remove_file(&fresh).unwrap(); + for bytes in [&initial[..8], &initial[..40], &[0u8; 300][..]] { + std::fs::write(&path, bytes).unwrap(); + assert_eq!(open_code(&path, true), "opened"); + let db = Minigraf::open(&path).unwrap(); + db.execute("(transact [[:a :b 1]])").unwrap(); + db.checkpoint().unwrap(); + drop(db); + assert_eq!(std::fs::metadata(&path).unwrap().len() % PAGE_SIZE, 0); + std::fs::remove_file(&path).unwrap(); + } +} + /// A CRC-valid meta whose `page_count` is far past the end of the file is /// refused at open: it used to open, and its next checkpoint wrote at that /// page id, leaving a 4 EiB sparse file (#497).