diff --git a/.github/workflows/smoke.yml b/.github/workflows/smoke.yml index 916e9b4f93..154ce1989f 100644 --- a/.github/workflows/smoke.yml +++ b/.github/workflows/smoke.yml @@ -47,3 +47,22 @@ jobs: run: cargo test --profile bench --test recursive_acceptance_test -- --ignored --nocapture env: RUST_BACKTRACE: 1 + + # #549 / #575: 1M aggregate groups complete or stop with QRY-012 under a + # limit; a 13-pattern cartesian product streams in a few MiB. Without + # test-oracle: the executor would run out of memory on the product. + memory-limit-acceptance: + name: Query memory limit acceptance + runs-on: ubuntu-latest + timeout-minutes: 30 + + steps: + - uses: actions/checkout@v4 + + - name: Install Rust stable + uses: dtolnay/rust-toolchain@stable + + - name: Run the acceptance tests + run: cargo test --profile bench --test memory_limit_acceptance_test -- --ignored --nocapture --test-threads=1 + env: + RUST_BACKTRACE: 1 diff --git a/CHANGELOG.md b/CHANGELOG.md index 977d1ce1ad..6bbf35a762 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -120,6 +120,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 - **Answers that depend on the plan fail the tests (#596).** A test-only switch (`minigraf::__reorder`, `test-oracle` feature) turns off every place the native build reorders: the pattern selectivity sort, the `not`/`not-join` and `or`/`or-join` cost sorts and the `or` short-circuits (#250), and the engine's `HashJoin` build side. `tests/plan_independence_test.rs` runs a matrix of queries (joins, expressions, rules, `or`/`or-join`, `not`/`not-join`, keyword and ref, floats, long strings, aggregates, time travel), in memory and on file, through `execute` and a cursor, with the switch on and off, and requires the same rows. Under `test-oracle` the model-based (#385) and property (#386) tests also run every generated query with the switch off. - **Rule queries on the engine (#548).** `tests/recursive_engine_test.rs` (10 tests) runs rule queries in memory, on a file with pending facts and after a checkpoint, and under `test-oracle` against the executor: transitive closure (linear and non-linear), mutual recursion, strata whose `not` and `or` rules recurse, rules that read their stratum outside a top-level invocation, derived facts seen by every pattern, the identity of derived facts, `nil` metadata, heads, both `INT-020` limits, and rule queries with aggregates, `not-join`, `or` and windows. Every existing rule suite (`recursive_rules_test`, `negation_test`, `disjunction_test`, `magic_sets_test`, the model-based and property tests) now runs its rule queries on the engine with the oracle. Engine unit tests cover routing and derived rows read across batches. - **Recursive rules at 5M derived facts (#473 acceptance, #548).** `tests/recursive_acceptance_test.rs` (ignored; the nightly smoke workflow runs it) derives 4,882,500 `reach` facts in 62 rounds over a layered graph of 155,000 edges and checks that every one is returned and that the query's peak RSS stays under 256 bytes per derived fact (169 measured); the default `max_derived_facts` then stops the same rule with `INT-020`. The #394 envelope has a `recursive` shape: the whole transitive closure of `:manager`, with no constant, so no magic sets. +- **Query memory at 1M groups and on the #575 product (#549).** `tests/memory_limit_acceptance_test.rs` (ignored; the nightly smoke workflow runs it without `test-oracle`) returns 1M aggregate groups, or `QRY-012` naming `Aggregate` under a 32 MiB limit, and streams the 1.6M rows of 13 patterns sharing no variable over the fuzz harness's 3 facts in under 64 MiB of peak RSS (the executor held more than 5.7 GB), or `QRY-012` naming `HashJoin` under a 64-byte limit. An ignored engine test prints the meter's peak against the peak RSS: 435 MiB against about 545 MiB for the groups (`docs/BENCHMARKS.md`). Measuring it found `Aggregate`'s sorted map of groups uncharged while its hash table was still held; the map is now charged and the table freed first, which lowered the real peak from 651 MiB. - **Negation bodies in both forms (#546).** A second test-only switch (`minigraf::__subplans`, `test-oracle` feature) forces the engine's `not` / `not-join` bodies to run hashed or correlated. `tests/plan_independence_test.rs` runs every query with the body forms chosen, forced hashed and forced correlated, each with reordering on and off; its matrix gains negations over floats near zero, `0.0` and `-0.0`, keywords and refs of one entity, long strings, bodies reading an imported variable they do not bind, variable-free bodies and `:db/valid-at`. `tests/negation_equality_test.rs` checks the changed answers on every executor path, in memory and after a checkpoint. The property test's rerun also forces hashed bodies. Engine unit tests cover the form the planner picks, routing, multiplicity, failing expressions in bodies, and that a hashed body is read once and a correlated one probes once per row. - **Disjunctions (#546).** `tests/or_equality_test.rs` checks the changed `or` / `or-join` answers through `execute` and a cursor, in memory and after a checkpoint. `tests/plan_independence_test.rs` gains disjunctions (keywords meeting refs, floats near zero, long strings as keys, branches naming different outer variables or no join variable, a branch with `not`, an `or` with nothing before it, a cross product, `:db/valid-at` in a branch), run with branches chosen, forced hashed and forced correlated. The property test generates `or` and `or-join` over bound variables, with a reference evaluator that deduplicates the rows they keep. Engine unit tests run every disjunction shape with each branch form forced against the executor, and cover routing, the form the planner picks, `Distinct`, and that a hashed branch is read once. - **Aggregates and windows (#547).** `src/query/datalog/aggregate.rs` unit tests check every accumulator over every order of small inputs (exact float sums against hand-computed values, cancellation, subnormals, signed zeros, infinities and NaN, integer saturation, errors decided at the end) and that the value order is total. `tests/aggregate_window_rules_test.rs` checks the changed answers; `tests/plan_independence_test.rs` gains aggregate, window and mixed queries over ties, keywords and refs, and floats. diff --git a/CLAUDE.md b/CLAUDE.md index d64892777c..6c58de27ba 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -206,7 +206,7 @@ Auto-migrates v7 → v8 on open (spec §9, with a backup meta page). v1–v6 are ## Test Coverage -**1720 tests** (1709 passing, 11 ignored; unit + integration + doc). +**1725 tests** (1711 passing, 14 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 6a93bc28fb..eec4b939ea 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 1720 tests +cargo test # run 1725 tests cargo run < demos/demo_recursive.txt # recursive rules demo ``` diff --git a/docs/BENCHMARKS.md b/docs/BENCHMARKS.md index 5d0ae1280c..5af10e26b9 100644 --- a/docs/BENCHMARKS.md +++ b/docs/BENCHMARKS.md @@ -171,6 +171,19 @@ The executor copied the database into a `FactStorage` for every rule query; the The acceptance test (`tests/recursive_acceptance_test.rs`, ignored; the nightly smoke workflow runs it) derives 4,882,500 `reach` facts over a layered graph of 155,000 edges (63 layers of 50 nodes, complete bipartite between neighbours) in 62 rounds: 226 s and 169 bytes of RSS per derived fact on a laptop. Each fact is derived through 50 middle nodes, so the rounds probe about 250M candidate rows; the time is in those entity probes and the identity set, not in memory. +### Query memory accounting (#549) + +**Command**: `cargo test --profile bench --test memory_limit_acceptance_test -- --ignored --nocapture --test-threads=1` (the nightly smoke workflow runs it) and `cargo test --profile bench --lib meter_peak_against_rss -- --ignored --nocapture`, on a dedicated 88-vCPU Linux server, pinned to one NUMA node, three runs each. + +| Shape | Rows | Time | Meter peak | Peak RSS added | +|---|---:|---:|---:|---:| +| 1M groups, `[:find ?g (count ?e) :where [?e :g ?g]]` | 1,000,000 | 3.5–3.6 s | 435 MiB | 542–549 MiB | +| #575 cartesian, 13 patterns sharing no variable over 3 facts | 1,594,323 | 2.6 s | 4 KiB | 9.6–9.7 MiB in a fresh process; under 50 KiB after another query | + +The meter's estimate is within the spec's factor of two of the RSS a query adds (1.25× for the groups). The rest is allocator rounding, hash-table capacity beyond its entries, and the reader's pages, which no holder counts. The cartesian product held more than 5.7 GB on the executor (#575); on the engine every join builds on its 3-row inner pattern and the 1.6M rows stream through, so what a fresh process adds is the reader and the cursor, not the rows. With `query_memory_limit` at 32 MiB the groups query stops with `QRY-012` naming `Aggregate`, and at 64 bytes the product stops with `QRY-012` naming `HashJoin`. + +Measuring this found that `Aggregate` built its sorted map of groups uncharged while its hash table was still alive: the meter read 282 MiB against 651 MiB of RSS. The map is now charged, and the table goes first, which also cut the real peak to the figure above. + ### Python FFI round trip **Command**: `python bench/envelope.py --report envelope.json --scale ` in [minigraf-python](https://github.com/project-minigraf/minigraf-python) (`v3`), on the same fixtures and report. The binding is built with `maturin develop --release` against this commit. It runs the same queries through `db.query(...)`, drains them with `next_batch(1000)`, and decodes each JSON batch with `json.loads`. Python 3.14.7. diff --git a/docs/TEST_COVERAGE.md b/docs/TEST_COVERAGE.md index 20188b7a9f..ca9781cda4 100644 --- a/docs/TEST_COVERAGE.md +++ b/docs/TEST_COVERAGE.md @@ -4,7 +4,7 @@ **Verified**: 2026-10-21 with `cargo test --quiet` -**Result**: 1,709 passing tests and 11 ignored tests (1,720 total) +**Result**: 1,711 passing tests and 14 ignored tests (1,725 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. 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. Damaged v7 fact page tests (#496) check that a page in the counted fact range whose type byte is anything but the fact-page type (zero, `0x01`, the v2.x B+tree types, `0xFF`, a zeroed page; first and last page) is `STG-014` rather than skipped, while a range derived from the first index root skips only v2.x B+tree pages; that opening such a v7 file read-write or read-only fails with `STG-014` and writes nothing; and, in `tests/migration_matrix_test.rs`, that the golden `v7_basic.graph` with page 1's type byte changed or page 1 overwritten with noise fails both opens with the file unchanged and no WAL created. Both inputs are `fact_page` corpus seeds. Merged from the v2.x line: `tests/edge_cases_test.rs` checks the same refusal and acceptance through `Minigraf::open` on a database checkpointed twice (#506). Torn-WAL-tail tests (#513) check that opening a WAL writer cuts off a partial last entry (cut in the checksum, the header or the payload) or an entry with a bad checksum and everything after it, then appends where replay reaches, and leaves an intact WAL byte for byte; that an append that fails part-way makes every later append `WAL-007` while a rejected oversize fact (`WAL-003`, nothing written) does not; through `Minigraf`, that the failed transaction is not applied, later `transact` and `commit` are `WAL-007`, and a `checkpoint()` makes writes work again; and, in `tests/wal_test.rs`, that a commit made after reopening a crash-left WAL with each kind of torn tail survives a second crash. The fault matrix (#390, `src/fault_matrix.rs`) drives a test-only fault plan through the real file backend, WAL and directory fsync: an EIO, a short or torn write (1, 40 and 4,095 bytes), a full disk that keeps failing every later write, a failed fsync, and a failed fsync that also loses the writes since the last good one ("fsyncgate"), each at every write or sync call of a transact, a transact that creates the WAL, an automatic checkpoint, `checkpoint()`, the close-time checkpoint and `rebuild_indexes()`, on a database committed over two checkpoints with multi-valued, retracted and long values and entries pending in the WAL. After each fault, the handle holds the old facts or those plus the whole transaction, never part of one; after a failed checkpoint another is `STG-046`; a later write succeeds or is `WAL-007`/`STG-046`; a kill and reopen gives exactly the handle's facts, plus the failed transaction whole or not at all, and `verify` finds nothing; and a commit after recovery survives another kill. Two more tests fill the disk halfway through a checkpoint (`STG-046`, reads unchanged, reopen intact), and fail the fsync after a checkpoint's meta write and then retry the checkpoint, crashing at each of its writes: the retry is refused and every reopen is intact (without the refusal, a reopen hits `STG-029`). Unit tests check the fault plan's counting, and that a `rebuild_indexes` refused with `STG-041` leaves the handle usable. 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. Coverage-gate tests (#396) check that replay stops at a WAL entry whose first fact is longer than 10 MB or that claims more than 1M facts, that a WAL writer cannot be opened in a missing directory, and that a failed cut of a torn WAL tail fails the open and leaves the file as it was; that a short v7 page and a slot past the record count are `INT-024`; that a migration backup meta of another generation or file length is not used (`STG-032`, file unchanged), and a torn first meta with data in page 1 is `STG-032`, not a new file; that `save` with nothing pending writes nothing, `into_backend` saves pending facts, and `rebuild_indexes` with nothing checkpointed commits the pending facts; and that unsorted or repeated B+tree input and a stored key inserted with another value are `INT-049`, a tree pointer to a free-list page is `STG-013` from `get`, a leaf walk and a copy-on-write insert, and the read-only `MutexStorageBackend` refuses writes, syncs and close. A page-cache test holds two threads in the backend read so both miss the same page, and checks that both get the one cached copy; before it, that path ran only when the scheduler happened to race the threads, and the gate flapped. 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, 956 passing; ten that spawn threads or a child process are ignored on WASI. These are not counted above. A WAL test checks that a checkpoint with no facts to flush still removes a WAL whose entries are all already in the file, and the golden-corpus test now requires the WAL to be gone after a checkpoint for the `stale_wal` fixtures too (#457). A WAL test checks that closing a handle opened with `wal_checkpoint_threshold(usize::MAX)`, in both sync modes, leaves the `.graph` file byte for byte as it was and keeps the WAL, whose entries replay on the next open, and a unit test closes an in-memory handle under the same setting (#476). A recursive-rule test checks that a rule query on a database with more live facts than `max_results` returns its answer, with a bound and with a free first argument, and that a query deriving more facts than its `:max-results` is still `INT-020` (#528). A log-writer test runs the online backup from `docs/DURABILITY.md`: it copies a read-write handle with an uncheckpointed transaction through `fact_log` and `LogWriter` while another thread writes past the automatic checkpoint threshold, and checks that the copy verifies clean, holds exactly the records the log returned and the counter read after the log opened, and that every concurrent write reaches the source's file once the log is dropped (#398). Rule-body tests in `tests/recursive_rules_test.rs` check that a `:db/valid-at` pattern in a rule definition, in its `not` and `not-join` bodies and in its `or` branches binds the query's valid time, on the semi-naive, stratified and magic-sets paths (#617). Tests in `tests/not_join_test.rs` check that a rule calling a rule with `not-join`, `not` or `or` returns that rule's rows, with a free and a literal argument and through a forwarding rule, and that a rule with its own `not-join` calling one gets the same rows whether or not the query asks for the callee first; stratification unit tests check that such a caller, a rule forwarding to it and a caller of a recursive one sit above the callee, and that recursion through a rule with a `not` still stratifies (#628). Tests in `tests/not_join_test.rs` check that recursion through a rule with `not`, `not-join` or `or`, directly or through another rule, returns every row along a chain, and that the `not` still removes the rows it should; evaluator unit tests check that such recursion stops at its fixpoint that `max_iterations` and `max_results` end one that does not with INT-020, and that `max_results` counts the facts every pass derives, not only the mixed rule's (#633). @@ -19,7 +19,7 @@ This covers the unreleased file-format-v8 work (#287, #371): the index-key value - **`or` with no shared variable** (#610): `tests/disjunction_test.rs` checks that an `or` sharing no variable with the earlier clauses joins as a cross product, before or after them, through the seeded path (a branch with `not`) and in a rule body, keeps the earlier clauses' variables and fact metadata (a pseudo-attribute), and gives no rows when no branch matches. - **Prepared time travel** (#603): `tests/prepared_statements_test.rs` runs literal `:as-of` (counter and timestamp), `:valid-at`, `:any-valid-time` and a per-fact pseudo-attribute query through `execute`, a prepared `execute` and a prepared cursor, which must agree; a `prepared.rs` unit test checks that `substitute` keeps non-slot `:as-of` and `:valid-at`. - **Rule queries on the engine** (`tests/recursive_engine_test.rs`, 10 tests; #548): linear and non-linear transitive closure, mutual recursion, strata whose `not` and `or` rules recurse (#633's cases), naive rules (a same-stratum read in an `or` branch, through a `:p` pattern, through `[?y ?a ?z]`), derived facts visible to every pattern and the magic-set predicate's attribute, identity of derived facts (keyword vs ref, `-0.0` vs `0.0`, long strings, a head equal to a stored fact), `nil` metadata and `:db/valid-at` over derived facts, one-argument heads, `QRY-013` and `INT-022` heads, both `INT-020` limits, and rule queries with aggregates, expressions, `not-join`, `or` and windows; each in memory, on a file with pending facts and after a checkpoint, and under `test-oracle` against the executor. Engine unit tests check routing (`:as-of` timestamp, an unplannable rule body, a three-argument call and a write transaction stay on the executor) and derived rows read across batches before and after a checkpoint; `relation.rs` unit tests check row identity and the `Old` / `Delta` / `Full` ranges. -- **Query memory limit** (`tests/memory_limit_test.rs`, 7 tests; #549): `OpenOptions::query_memory_limit` is off by default and set by its builder; `QRY-012` through `execute`, a cursor's first pull, a prepared query and a rule query (from `execute`, and from `query` when the rules run at open); the database answers after a query fails; a write transaction's query is counted until it stages a write, then runs uncounted on the executor; a prepared rule query uses the database's `max_derived_facts`. Engine unit tests (`src/query/engine/tests.rs`, 7 more): `HashJoin`, `AntiJoin`, `Union`, `Aggregate` and `Window` charge while they hold state and the meter is back at 0 after a drain and after an early drop; `QRY-012` names the holder over the limit (each operator, `IdSpace`, `Recursive`, `Distinct` and `Relations`), and its allocator form through the `try_reserve` test hook; a cursor returns rows, then `QRY-012`, then nothing; `rewind` and `close` release; the planner builds a keyless join on the side with the smaller product estimate (#575's shape, a selective outer side, a tie, reordering off). `meter.rs` (4 unit tests) checks charge, release, drop, peak and the allocator form. +- **Query memory limit** (`tests/memory_limit_test.rs`, 7 tests; #549): `OpenOptions::query_memory_limit` is off by default and set by its builder; `QRY-012` through `execute`, a cursor's first pull, a prepared query and a rule query (from `execute`, and from `query` when the rules run at open); the database answers after a query fails; a write transaction's query is counted until it stages a write, then runs uncounted on the executor; a prepared rule query uses the database's `max_derived_facts`. Engine unit tests (`src/query/engine/tests.rs`, 7 more): `HashJoin`, `AntiJoin`, `Union`, `Aggregate` and `Window` charge while they hold state and the meter is back at 0 after a drain and after an early drop; `QRY-012` names the holder over the limit (each operator, `IdSpace`, `Recursive`, `Distinct` and `Relations`), and its allocator form through the `try_reserve` test hook; a cursor returns rows, then `QRY-012`, then nothing; `rewind` and `close` release; the planner builds a keyless join on the side with the smaller product estimate (#575's shape, a selective outer side, a tie, reordering off). `meter.rs` (4 unit tests) checks charge, release, drop, peak and the allocator form. `Aggregate` charges its sorted map of groups until every row is built, and lets its hash table and group rows go first, with `sum-distinct` members charged once (`aggregate_finish_charges_its_sorted_groups`, `aggregate_finish_keeps_sum_distinct_members_charged_once`). - **Join rules** (`tests/join_rules_test.rs`, 10 tests; #545): a join on a float value pairs `0.0` with `-0.0`, through the hash key and as a shared variable, and a float constant still matches within epsilon; a variable bound to a keyword by one pattern and to the ref of the same entity by another returns the kind from the first pattern in `:where` text order, when the planner runs the patterns in another order, through the attribute position, before and after a rule call, and with a repeated pattern; an expression binding unifies with a pattern binding the same variable, and the first binder in the text, pattern or expression, gives the value (#596); a pseudo-attribute pattern never gives a variable its value, even when it runs first (#606; the plan-independence matrix checks it with reordering off). Under the `test-oracle` feature the joins among them also run on the streaming engine. A unit test checks that `-0.0` and `0.0` hash alike. - **Pseudo-attribute sources** (`tests/pseudo_source_test.rs`, 12 tests; #594): a per-fact pseudo-attribute reads the nearest earlier pattern in the text with the same entity term (#594's example in both text orders), two pseudo-attributes share a source, `[:alice ?a _]` gives one row per fact, constant and bound value terms check, `:alice` and its UUID are one term while `?e` and `:alice` are not, PRS-081 for a pattern after it, alone, `_`/`?_x` entities, another entity's pattern and a rule call; a `not` body reads the outer fact (and a source inside the body), `not-join` crosses for a listed variable only, `or` branches read the outer fact and never a sibling, `or-join`, closed rule bodies, `$slot`s by name at prepare time, and `:db/valid-at` once per fact. Parser unit tests check the hidden variables (`?#.`), the join variable a crossed `not-join` gains, and the PRS-081 text; an optimizer test places a pseudo-attribute pattern after its source and the pattern binding its value; matcher tests read the hidden variable, a substituted integer, and nothing without a source; the engine tests run the sourced shapes and check PRS-081 for the old fallback shapes. The plan-independence matrix gains eleven pseudo-attribute shapes. - **Negation equality** (`tests/negation_equality_test.rs`, 5 tests; #546): a value a `not` / `not-join` body takes from the outer row compares by join equality on every path (exclusion set, per-row body with an expression, a query that invokes a rule, a rule body): `1e-20` and `2e-20` differ, `0.0` equals `-0.0`, a keyword imported into an entity position equals the ref, and a float literal in the body still matches within `f64::EPSILON`; through `execute` and a cursor, in memory and after a checkpoint. Engine unit tests (`src/query/engine/tests.rs`, 6 more) run every negation shape (hashed and correlated bodies, keys on entity, value and attribute positions, floats, keywords and refs, long strings, bodies reading an imported variable, variable-free bodies, per-fact pseudo-attributes and `:db/valid-at` in bodies, deferred and repeated negations) at six temporal settings with each body form forced and reordering on and off, in memory and on file before and after checkpoints, against the executor; and check the form the planner picks, routing, multiplicity, failing expressions and unknown predicates in bodies, and that a hashed body is read once while a correlated one probes once per outer row. Optimizer unit tests cover `plan_seeded` and the `SUBPLANS` switch. @@ -36,7 +36,7 @@ This covers the unreleased file-format-v8 work (#287, #371): the index-key value ### Ignored Tests -The eleven ignored tests are intentionally excluded from a normal local run: +The fourteen ignored tests are intentionally excluded from a normal local run: - Six rustdoc examples that reference internal types and cannot compile as standalone examples. - One high-contention concurrency stress test intended for scheduled runs. @@ -44,6 +44,8 @@ The eleven ignored tests are intentionally excluded from a normal local run: - One soak test at 10M facts (`soak`), run weekly by `.github/workflows/soak.yml` (#392); `soak_short` runs the same driver at 20K facts in the normal suite. The memory bound is measured in a child process (`soak_memory_child`, #542). - One size test at 1.15M facts (`size_per_fact_in_433_shape_1m`), run by the nightly smoke workflow. - One recursive-rule acceptance test (`reach_5m`, #548): a layered graph whose `reach` rule derives 4,882,500 facts in 62 rounds must return them all with peak RSS under 256 bytes per derived fact, and the default `max_derived_facts` must stop the same rule with `INT-020`; run by the nightly smoke workflow. +- Two query-memory acceptance tests (`tests/memory_limit_acceptance_test.rs`, #549, #575): 1M aggregate groups return 1M rows, and with `query_memory_limit` at 32 MiB stop with `QRY-012` naming `Aggregate`, after which the database answers; 13 patterns sharing no variable over the fuzz harness's 3 facts stream 3^13 rows with peak RSS under 64 MiB, and with a 64-byte limit stop with `QRY-012` naming `HashJoin`. Run one at a time by the nightly smoke workflow, without `test-oracle`. +- One measurement test (`meter_peak_against_rss`, `src/query/engine/tests.rs`, #549): prints the meter's peak against the peak RSS for the same two shapes, opening the engine without the executor oracle. ### Reproducing diff --git a/src/db.rs b/src/db.rs index 204be45da7..b4f9480913 100644 --- a/src/db.rs +++ b/src/db.rs @@ -1102,6 +1102,12 @@ impl Minigraf { self.inner.fact_storage.current_tx_count() } + /// One state of the store, for tests that open the engine directly. + #[cfg(test)] + pub(crate) fn snapshot(&self) -> Result { + self.inner.fact_storage.snapshot() + } + /// End the handle as a killed process would: no close-time checkpoint and /// no save on drop. Whatever reached the file stays; the lock is released. #[cfg(all(test, not(target_arch = "wasm32")))] diff --git a/src/query/engine/aggregate.rs b/src/query/engine/aggregate.rs index a23676906a..2a62c00fb1 100644 --- a/src/query/engine/aggregate.rs +++ b/src/query/engine/aggregate.rs @@ -74,6 +74,18 @@ impl Acc { } /// The accumulator as an [`Agg`], whose `finish` gives its result. + /// The bytes `step` charged for the members of a set that stays in the + /// `Agg`: `sum-distinct`'s. A `count-distinct` set ends as its count. + fn member_bytes(&self) -> usize { + match self { + Acc::Values(Agg::SumDistinct(set)) => set + .iter() + .map(|v| value_bytes(v) + HASH_ENTRY_OVERHEAD) + .sum(), + _ => 0, + } + } + fn into_agg(self) -> Agg { match self { Acc::Count(n) => Agg::Count(n), @@ -206,18 +218,34 @@ impl Aggregate { row.extend(vec![Cell::Val(Scalar::Int(0)); self.aggs.len()]); return Ok(vec![row]); } - // Sorted and finished as the executor's groups are. + // Sorted and finished as the executor's groups are. The sorted map + // holds each group's values twice and its accumulators, with their + // `sum-distinct` members, until every row is built, so it is charged + // as `finished` too. + self.table = HashMap::new(); let mut groups = Groups::new(); + let mut sorted = 0; for group in std::mem::take(&mut self.rows) { let values = group .cells .iter() .map(|c| value(c, ctx)) .collect::>>()?; + let members: usize = group.accs.iter().map(Acc::member_bytes).sum(); + let n = 2 * (size_of::>() + values.iter().map(value_bytes).sum::()) + + size_of::>() + + group.accs.len() * size_of::() + + members + + HASH_ENTRY_OVERHEAD; + // The members move from `held` to `finished`, so they are not + // counted twice. + self.held.uncharge(members); + self.finished.charge(n)?; + sorted += n; let accs = group.accs.into_iter().map(Acc::into_agg).collect(); groups.insert(values.clone(), (values, accs)); } - self.table.clear(); + self.held.release(); let funcs: Vec<&str> = self.aggs.iter().map(|(f, _)| f.as_str()).collect(); let mut rows = Vec::new(); for (shown, results) in finish_groups(groups, &funcs)? { @@ -232,7 +260,7 @@ impl Aggregate { self.finished.reserve(rows.try_reserve(1), n, refused)?; rows.push(row); } - self.held.release(); + self.finished.uncharge(sorted); rows.reverse(); Ok(rows) } diff --git a/src/query/engine/tests.rs b/src/query/engine/tests.rs index bc978cca0a..d474f6bc59 100644 --- a/src/query/engine/tests.rs +++ b/src/query/engine/tests.rs @@ -2191,3 +2191,154 @@ fn planner_builds_a_keyless_join_on_the_smaller_product() { "reorder off builds inner" ); } + +/// The two acceptance shapes of `tests/memory_limit_acceptance_test.rs`: +/// a checkpointed database at `path`, and the query. +fn acceptance_shape(name: &str, path: &std::path::Path) -> String { + let db = Minigraf::open(path).unwrap(); + if name == "groups" { + for chunk in 0..10 { + let facts: String = (chunk * 100_000..(chunk + 1) * 100_000) + .map(|i| format!("[:e{i} :g {i}]")) + .collect(); + db.execute(&format!("(transact [{facts}])")).unwrap(); + db.checkpoint().unwrap(); + } + "(query [:find ?g (count ?e) :where [?e :g ?g]])".to_string() + } else { + db.execute(r#"(transact [[:alice :name "Alice"] [:bob :name "Bob"] [:alice :age 30]])"#) + .unwrap(); + db.checkpoint().unwrap(); + let patterns: String = (0..13).map(|i| format!("[?e{i} ?a{i} ?v{i}]")).collect(); + format!("(query [:find ?v0 :where {patterns}])") + } +} + +/// A `kB` field of `/proc/self/status`; 0 where it does not exist. +fn proc_status_kb(field: &str) -> usize { + std::fs::read_to_string("/proc/self/status") + .ok() + .and_then(|s| { + s.lines() + .find_map(|l| l.strip_prefix(field)?.strip_prefix(':').map(str::to_owned)) + }) + .and_then(|v| v.trim().trim_end_matches("kB").trim().parse().ok()) + .unwrap_or(0) +} + +/// The meter's peak against the peak RSS the query adds, for both +/// acceptance shapes (#549 spec §3.2: the estimate is meant to be within a +/// factor of two). Opens the engine directly, without the executor oracle, +/// which would run out of memory on the cartesian shape. Prints only; run +/// alone, as the high-water mark is per process: +/// +/// ```text +/// cargo test --profile bench --lib meter_peak_against_rss -- --ignored --nocapture +/// ``` +#[test] +#[ignore] +fn meter_peak_against_rss() { + use crate::query::datalog::functions::FunctionRegistry; + use crate::query::datalog::parser::parse_datalog_command; + use crate::query::datalog::types::DatalogCommand; + for name in ["groups", "cartesian"] { + let dir = tempfile::tempdir().unwrap(); + let path = dir.path().join("shape.graph"); + let query = acceptance_shape(name, &path); + let db = Minigraf::open(&path).unwrap(); + let Ok(DatalogCommand::Query(query)) = parse_datalog_command(&query) else { + panic!("expected a query"); + }; + let plan = super::plan(&query).expect("an engine plan"); + let functions = + std::sync::Arc::new(std::sync::RwLock::new(FunctionRegistry::with_builtins())); + let snapshot = db.snapshot().unwrap(); + let reset = std::fs::write("/proc/self/clear_refs", "5").is_ok(); + let before_kb = proc_status_kb("VmRSS"); + let mut stream = + super::open(snapshot, plan, functions, usize::MAX).expect("the engine runs it"); + let meter = stream.meter().clone(); + let mut rows = 0; + while let Some(batch) = stream.next_rows().unwrap() { + rows += batch.len(); + } + drop(stream); + let added_kb = proc_status_kb("VmHWM").saturating_sub(before_kb); + eprintln!( + "{name}: {rows} rows; meter peak {} KiB, peak RSS added {added_kb} KiB{}", + meter.peak() / 1024, + if reset { + "" + } else { + " (high-water mark not reset)" + } + ); + assert_eq!(meter.used(), 0, "released after the drain"); + } +} + +/// `Aggregate::finish` charges its sorted map of groups until every row is +/// built, and lets the hash table and group rows go first, so once rows are +/// returned only the ones not yet returned stay charged (#549). +#[test] +fn aggregate_finish_charges_its_sorted_groups() { + use super::meter::{HASH_ENTRY_OVERHEAD, row_bytes, value_bytes}; + use crate::graph::types::Value; + use crate::query::datalog::aggregate::Agg; + use std::mem::size_of; + let n = 3000; + let meter = super::Meter::unlimited(); + let mut aggregate = super::aggregate::Aggregate::new( + Box::new(Ints { n, at: 0 }), + vec![0], + vec![("count".to_string(), 0)], + false, + &meter, + ); + let batch = pull_once(&mut aggregate, &meter).unwrap().expect("a batch"); + let row = [ + super::cell::Cell::Val(super::cell::Scalar::Int(0)), + super::cell::Cell::Val(super::cell::Scalar::Int(1)), + ]; + let n = usize::try_from(n).unwrap(); + assert_eq!( + meter.used(), + (n - batch.len) * row_bytes(&row), + "only the rows not yet returned" + ); + let sorted = 2 * (size_of::>() + value_bytes(&Value::Integer(0))) + + size_of::>() + + size_of::() + + HASH_ENTRY_OVERHEAD; + assert!( + meter.peak() >= n * (sorted + row_bytes(&row)), + "the sorted groups and the finished rows at once" + ); +} + +/// A `sum-distinct` set's members stay charged once, in the sorted map, +/// until the rows are built (#549). +#[test] +fn aggregate_finish_keeps_sum_distinct_members_charged_once() { + use super::meter::row_bytes; + let n = 3000; + let meter = super::Meter::unlimited(); + let mut aggregate = super::aggregate::Aggregate::new( + Box::new(Ints { n, at: 0 }), + vec![], + vec![("sum-distinct".to_string(), 0)], + false, + &meter, + ); + pull_once(&mut aggregate, &meter).unwrap().expect("a batch"); + assert_eq!(meter.used(), 0, "the one row returned, nothing held"); + let members = usize::try_from(n).unwrap() + * (super::meter::value_bytes(&crate::graph::types::Value::Integer(0)) + + super::meter::HASH_ENTRY_OVERHEAD); + let row = [super::cell::Cell::Val(super::cell::Scalar::Int(0))]; + assert!(meter.peak() >= members, "members charged"); + assert!( + meter.peak() < 2 * members + row_bytes(&row), + "members not counted twice" + ); +} diff --git a/tests/memory_limit_acceptance_test.rs b/tests/memory_limit_acceptance_test.rs new file mode 100644 index 0000000000..2e0a551030 --- /dev/null +++ b/tests/memory_limit_acceptance_test.rs @@ -0,0 +1,151 @@ +//! Acceptance tests for query memory accounting (#549 spec §6.2, and #575): +//! a query whose state is large either completes or fails with `QRY-012` +//! under `OpenOptions::query_memory_limit`, and a cartesian product streams +//! instead of holding its rows. +//! +//! Ignored by default; `.github/workflows/smoke.yml` runs them nightly, one +//! at a time because the peak RSS is per process: +//! +//! ```text +//! cargo test --profile bench --test memory_limit_acceptance_test -- --ignored --nocapture --test-threads=1 +//! ``` +//! +//! Peak RSS comes from `/proc/self/status` (Linux only): the high-water mark +//! is reset just before the query. Without the `test-oracle` feature, as the +//! executor would itself run out of memory on the cartesian shape. +// +// File-backed (Minigraf::open, tempfile): native only, like the other file tests. +#![cfg(not(target_arch = "wasm32"))] + +use minigraf::{Minigraf, OpenOptions}; + +const GROUPS: usize = 1_000_000; +/// Below what 1M groups cost the meter: each group's key and hash entry are +/// at least 40 bytes (spec §3.2), 40 MB in all. +const GROUPS_LIMIT: usize = 32 << 20; + +/// Patterns in the cartesian query, each of the 3 facts: 3^13 rows. +const K: u32 = 13; +/// Peak RSS the cartesian query may add. The executor held every row (more +/// than 5.7 GB at k = 13, #575); the engine holds a 3-row build side per join. +const CARTESIAN_MAX_RSS: usize = 64 << 20; + +/// `n` entities, each with its number as `:g`, checkpointed. +fn groups_db(dir: &tempfile::TempDir, opts: OpenOptions) -> Minigraf { + let db = opts.path(dir.path().join("groups.graph")).open().unwrap(); + for chunk in 0..GROUPS / 100_000 { + let facts: String = (chunk * 100_000..(chunk + 1) * 100_000) + .map(|i| format!("[:e{i} :g {i}]")) + .collect(); + db.execute(&format!("(transact [{facts}])")).unwrap(); + db.checkpoint().unwrap(); + } + db +} + +/// The `datalog_eval` fuzz harness's 3 facts (#575), checkpointed. +fn cartesian_db(dir: &tempfile::TempDir, opts: OpenOptions) -> Minigraf { + let db = opts + .path(dir.path().join("cartesian.graph")) + .open() + .unwrap(); + db.execute(r#"(transact [[:alice :name "Alice"] [:bob :name "Bob"] [:alice :age 30]])"#) + .unwrap(); + db.checkpoint().unwrap(); + db +} + +/// `K` patterns that share no variable, returning one pattern's value. +fn cartesian_query() -> String { + let patterns: String = (0..K).map(|i| format!("[?e{i} ?a{i} ?v{i}]")).collect(); + format!("(query [:find ?v0 :where {patterns}])") +} + +/// A `kB` field of `/proc/self/status`; 0 where it does not exist. +fn proc_status_kb(field: &str) -> usize { + std::fs::read_to_string("/proc/self/status") + .ok() + .and_then(|s| { + s.lines() + .find_map(|l| l.strip_prefix(field)?.strip_prefix(':').map(str::to_owned)) + }) + .and_then(|v| v.trim().trim_end_matches("kB").trim().parse().ok()) + .unwrap_or(0) +} + +/// Every row of `query`, counted and dropped; or the first error. +fn drain(db: &Minigraf, query: &str) -> Result { + let mut cursor = db.query(query)?; + let mut rows = 0; + while let Some(batch) = cursor.next_batch(1_000)? { + rows += batch.len(); + } + Ok(rows) +} + +#[test] +#[ignore] +fn grouped_count_1m_groups() { + let query = "(query [:find ?g (count ?e) :where [?e :g ?g]])"; + let dir = tempfile::tempdir().unwrap(); + let db = groups_db(&dir, OpenOptions::new()); + let start = std::time::Instant::now(); + let rows = drain(&db, query).unwrap(); + eprintln!( + "grouped_count_1m_groups: {rows} rows in {:.2?}", + start.elapsed() + ); + assert_eq!(rows, GROUPS, "one row per group"); + drop(db); + + let db = OpenOptions::new() + .query_memory_limit(GROUPS_LIMIT) + .path(dir.path().join("groups.graph")) + .open() + .unwrap(); + let err = drain(&db, query).err().expect("over the limit"); + assert_eq!(err.code(), "QRY-012", "stopped by the limit"); + assert!(err.to_string().contains("Aggregate"), "names Aggregate"); + // The database answers other queries. + assert_eq!( + drain(&db, "(query [:find ?e :where [?e :g 7]])").unwrap(), + 1, + "usable after QRY-012" + ); +} + +#[test] +#[ignore] +fn cartesian_k13_streams() { + let query = cartesian_query(); + let dir = tempfile::tempdir().unwrap(); + let db = cartesian_db(&dir, OpenOptions::new()); + // Reset the high-water mark to the current RSS, so the peak read after + // the query is the query's own (Linux 4.0+; elsewhere nothing is checked). + let reset = std::fs::write("/proc/self/clear_refs", "5").is_ok(); + let before_kb = proc_status_kb("VmRSS"); + let start = std::time::Instant::now(); + let rows = drain(&db, &query).unwrap(); + let peak_kb = proc_status_kb("VmHWM"); + let added = peak_kb.saturating_sub(before_kb) * 1024; + eprintln!( + "cartesian_k13_streams: {rows} rows in {:.2?}; peak RSS {} MiB, {} KiB added by the query", + start.elapsed(), + peak_kb / 1024, + added / 1024 + ); + assert_eq!(rows, 3usize.pow(K), "one row per binding"); + if reset && peak_kb > 0 { + assert!(added < CARTESIAN_MAX_RSS, "the product streams"); + } + drop(db); + + let db = OpenOptions::new() + .query_memory_limit(64) + .path(dir.path().join("cartesian.graph")) + .open() + .unwrap(); + let err = drain(&db, &query).err().expect("over the limit"); + assert_eq!(err.code(), "QRY-012", "stopped by the limit"); + assert!(err.to_string().contains("HashJoin"), "names HashJoin"); +}