Compare commits

..

49 Commits

Author SHA1 Message Date
Andrew Kane
fc0d3e7fdb Added search parameters to EXPLAIN [skip ci] 2024-10-28 01:20:59 -07:00
Andrew Kane
c530a3c490 Updated comment [skip ci] 2024-10-28 00:56:10 -07:00
Andrew Kane
d8b9e8ef73 Updated readme [skip ci] 2024-10-28 00:55:25 -07:00
Andrew Kane
00894efed5 Updated readme [skip ci] 2024-10-28 00:45:26 -07:00
Andrew Kane
0aa0f6619b Updated readme [skip ci] 2024-10-28 00:43:39 -07:00
Andrew Kane
38d053001e Updated readme [skip ci] 2024-10-28 00:32:12 -07:00
Andrew Kane
ccb95407e7 Updated readme [skip ci] 2024-10-28 00:09:26 -07:00
Andrew Kane
04d5e934a1 Scan 2000 more tuples with default work_mem 2024-10-27 22:23:28 -07:00
Andrew Kane
b163b5b196 Moved code [skip ci] 2024-10-27 22:21:43 -07:00
Andrew Kane
6a30c1e824 Fixed test [skip ci] 2024-10-27 21:10:51 -07:00
Andrew Kane
2db1b19644 Use greater than [skip ci] 2024-10-27 21:07:22 -07:00
Andrew Kane
305d62146e Updated comment [skip ci] 2024-10-27 21:05:32 -07:00
Andrew Kane
f9d627c9a9 Updated default value of hnsw.scan_mem_multiplier [skip ci] 2024-10-27 21:05:04 -07:00
Andrew Kane
38f42820be Added test for hnsw.scan_mem_multiplier [skip ci] 2024-10-27 20:05:58 -07:00
Andrew Kane
15c8245b42 Updated readme [skip ci] 2024-10-27 19:30:40 -07:00
Andrew Kane
572a9ab404 Updated readme [skip ci] 2024-10-27 18:58:50 -07:00
Andrew Kane
00492d7e57 Ensure max memory fits into Size for HNSW index scans 2024-10-27 14:21:15 -07:00
Andrew Kane
857d716d9e Renamed iterative_search to iterative_scan 2024-10-27 14:02:22 -07:00
Andrew Kane
c5dd2af750 Added comments [skip ci] 2024-10-25 21:39:03 -07:00
Andrew Kane
78b877bdaf Revert "Renamed iterative_search to iterative_scan"
This reverts commit 7043cce893.
2024-10-24 20:32:07 -07:00
Andrew Kane
7043cce893 Renamed iterative_search to iterative_scan 2024-10-24 20:31:43 -07:00
Andrew Kane
62039d74f6 Added iterative search section to readme [skip ci] 2024-10-24 18:05:29 -07:00
Andrew Kane
ac6576e53a Added hnsw.search_mem_multiplier option 2024-10-24 18:02:20 -07:00
Andrew Kane
67eff41c44 Updated changelog [skip ci] 2024-10-23 15:12:40 -07:00
Andrew Kane
1291b12090 Added Postgres 18 to CI [skip ci] 2024-10-22 00:38:19 -07:00
Andrew Kane
24522700b8 Improved hnswrescan 2024-10-21 23:41:32 -07:00
Andrew Kane
bfb3a45b31 Use consistent order [skip ci] 2024-10-21 21:47:03 -07:00
Andrew Kane
e718eb8da4 Updated range and defaults for iterative search parameters 2024-10-21 20:38:50 -07:00
Andrew Kane
049972a4a3 Improved test output [skip ci] 2024-10-13 17:22:49 -07:00
Andrew Kane
61027645e9 Improved test output [skip ci] 2024-10-13 17:21:38 -07:00
Andrew Kane
a41b327b33 Speed up test [skip ci] 2024-10-13 17:12:12 -07:00
Andrew Kane
7f735ebd9b Added test for strict order [skip ci] 2024-10-13 17:04:03 -07:00
Andrew Kane
02b01e1ca9 Show tuples with memory usage [skip ci] 2024-10-12 22:05:13 -07:00
Andrew Kane
388e42f6e6 Fixed flaky test [skip ci] 2024-10-11 15:48:19 -07:00
Andrew Kane
bf379eed86 Use a memory context for IVFFlat index scans 2024-10-11 15:46:38 -07:00
Andrew Kane
e1bc929429 Simplify lists for IvfflatScanOpaque [skip ci] 2024-10-11 15:29:23 -07:00
Andrew Kane
38285aacc7 Revert "Updated IVFFlat to support multiple attributes (not enabled yet)"
This reverts commit 772ab69de6.
2024-10-11 15:01:54 -07:00
Andrew Kane
a2408e60fa Revert "Added IndexTuple to HNSW elements (first step to support multiple attributes)"
This reverts commit 53a8734bac.
2024-10-11 14:57:57 -07:00
Andrew Kane
53a8734bac Added IndexTuple to HNSW elements (first step to support multiple attributes) 2024-10-11 14:12:01 -07:00
Andrew Kane
7484625227 Added comments [skip ci] 2024-10-11 11:59:36 -07:00
Andrew Kane
d1ebb8db73 Use -1 for no limit for ivfflat.max_probes [skip ci] 2024-10-11 11:43:32 -07:00
Andrew Kane
42af8aa1d1 Updated GUC descriptions [skip ci] 2024-10-11 11:26:27 -07:00
Andrew Kane
9d15a76b60 Improved enum naming [skip ci] 2024-10-11 11:20:36 -07:00
Andrew Kane
a3a20f9816 Simplified GUC names [skip ci] 2024-10-11 11:18:01 -07:00
Andrew Kane
b26a21b848 Added regression tests for iterative search [skip ci] 2024-10-11 11:07:11 -07:00
Andrew Kane
2dc392ed6c Updated GUC names [skip ci] 2024-10-10 23:50:11 -07:00
Andrew Kane
960d2848cb Updated comment [skip ci] 2024-10-10 21:02:33 -07:00
Andrew Kane
8e88b481a6 Use a lower max allocation size than default to allow scanning more tuples for iterative search before exceeding work_mem [skip ci] 2024-10-10 20:57:57 -07:00
Andrew Kane
124018b8dd Added HnswInitSearchCandidate function 2024-10-10 19:30:47 -07:00
26 changed files with 549 additions and 701 deletions

View File

@@ -8,8 +8,8 @@ jobs:
fail-fast: false
matrix:
include:
# - postgres: 18
# os: ubuntu-24.04
- postgres: 18
os: ubuntu-24.04
- postgres: 17
os: ubuntu-24.04
- postgres: 16

View File

@@ -1,6 +1,5 @@
## 0.8.0 (unreleased)
- Added support for inline filtering with HNSW
- Added support for iterative index scans
- Added casts for arrays to `sparsevec`
- Improved cost estimation

View File

@@ -439,12 +439,6 @@ Create an index on one [or more](https://www.postgresql.org/docs/current/indexes
CREATE INDEX ON items (category_id);
```
Or a composite HNSW index for approximate search (added in 0.8.0)
```sql
CREATE INDEX ON items USING hnsw (embedding vector_l2_ops, category_id);
```
Or a [partial index](https://www.postgresql.org/docs/current/indexes-partial.html) on the vector column for approximate search
```sql
@@ -457,6 +451,89 @@ Use [partitioning](https://www.postgresql.org/docs/current/ddl-partitioning.html
CREATE TABLE items (embedding vector(3), category_id int) PARTITION BY LIST(category_id);
```
## Iterative Index Scans
*Unreleased*
With approximate indexes, queries with filtering can return less results (due to post-filtering). Starting with 0.8.0, you can enable iterative index scans. If too few results from the initial scan match the filters, the scan will resume until enough results are found (or it reaches `hnsw.max_scan_tuples` or `ivfflat.max_probes`). This can significantly improve recall.
There are two modes for iterative scans: strict and relaxed.
Strict ensures results are in the exact order by distance
```sql
SET hnsw.iterative_scan = strict_order;
```
Relaxed allows results to be slightly out of order by distance, but provides better recall
```sql
SET hnsw.iterative_scan = relaxed_order;
# or
SET ivfflat.iterative_scan = relaxed_order;
```
With relaxed ordering, you can use a [materialized CTE](https://www.postgresql.org/docs/current/queries-with.html#QUERIES-WITH-CTE-MATERIALIZATION) to get strict ordering
```sql
WITH relaxed_results AS MATERIALIZED (
SELECT id, embedding <-> '[1,2,3]' AS distance FROM items WHERE category_id = 123 ORDER BY distance LIMIT 5
) SELECT * FROM relaxed_results ORDER BY distance;
```
For queries that filter by distance, use a materialized CTE and place the distance filter outside of it for best performance (due to the [current behavior](https://www.postgresql.org/message-id/flat/CAOdR5yGUoMQ6j7M5hNUXrySzaqZVGf_Ne%2B8fwZMRKTFxU1nbJg%40mail.gmail.com) of the Postgres executor)
```sql
WITH nearest_results AS MATERIALIZED (
SELECT id, embedding <-> '[1,2,3]' AS distance FROM items ORDER BY distance LIMIT 5
) SELECT * FROM nearest_results WHERE distance < 5 ORDER BY distance;
```
Note: Place any other filters inside the CTE
### Iterative Scan Options
Since scanning a large portion of an approximate index is expensive, there are options to control when a scan ends
#### HNSW
Specify the max number of tuples to visit (20,000 by default)
```sql
SET hnsw.max_scan_tuples = 20000;
```
Note: This is approximate and does not affect the initial scan
Specify the max amount of memory to use, as a multiple of `work_mem` (1 by default)
```sql
SET hnsw.scan_mem_multiplier = 2;
```
You can see when increasing this is needed by enabling debug messages
```sql
SET client_min_messages = debug1;
```
which will show when a scan reaches the memory limit
```text
DEBUG: hnsw index scan reached memory limit after 20000 tuples
HINT: Increase hnsw.scan_mem_multiplier to scan more tuples.
```
#### IVFFlat
Specify the max number of probes
```sql
SET ivfflat.max_probes = 100;
```
Note: If this is lower than `ivfflat.probes`, `ivfflat.probes` will be used
## Half-Precision Vectors
*Added in 0.7.0*
@@ -1195,7 +1272,6 @@ Thanks to:
- [k-means++: The Advantage of Careful Seeding](https://theory.stanford.edu/~sergei/papers/kMeansPP-soda.pdf)
- [Concept Decompositions for Large Sparse Text Data using Clustering](https://www.cs.utexas.edu/users/inderjit/public_papers/concept_mlj.pdf)
- [Efficient and Robust Approximate Nearest Neighbor Search using Hierarchical Navigable Small World Graphs](https://arxiv.org/ftp/arxiv/papers/1603/1603.09320.pdf)
- [HQANN: Efficient and Robust Similarity Search for Hybrid Queries with Structured and Unstructured Constraints](https://arxiv.org/pdf/2207.07940.pdf)
## History

View File

@@ -24,11 +24,3 @@ CREATE CAST (double precision[] AS sparsevec)
CREATE CAST (numeric[] AS sparsevec)
WITH FUNCTION array_to_sparsevec(numeric[], integer, boolean) AS ASSIGNMENT;
CREATE FUNCTION hnsw_attribute_distance(integer, integer) RETURNS float8
AS 'MODULE_PATHNAME', 'hnsw_int4_attribute_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
CREATE OPERATOR CLASS vector_integer_ops
DEFAULT FOR TYPE integer USING hnsw AS
OPERATOR 2 = (integer, integer),
FUNCTION 4 hnsw_attribute_distance(integer, integer);

View File

@@ -916,13 +916,3 @@ CREATE OPERATOR CLASS sparsevec_l1_ops
OPERATOR 1 <+> (sparsevec, sparsevec) FOR ORDER BY float_ops,
FUNCTION 1 l1_distance(sparsevec, sparsevec),
FUNCTION 3 hnsw_sparsevec_support(internal);
-- hnsw attributes
CREATE FUNCTION hnsw_attribute_distance(integer, integer) RETURNS float8
AS 'MODULE_PATHNAME', 'hnsw_int4_attribute_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
CREATE OPERATOR CLASS vector_integer_ops
DEFAULT FOR TYPE integer USING hnsw AS
OPERATOR 2 = (integer, integer),
FUNCTION 4 hnsw_attribute_distance(integer, integer);

View File

@@ -18,16 +18,17 @@
#define MarkGUCPrefixReserved(x) EmitWarningsOnPlaceholders(x)
#endif
static const struct config_enum_entry hnsw_iterative_search_options[] = {
{"off", HNSW_ITERATIVE_SEARCH_OFF, false},
{"on", HNSW_ITERATIVE_SEARCH_RELAXED, false},
{"strict", HNSW_ITERATIVE_SEARCH_STRICT, false},
static const struct config_enum_entry hnsw_iterative_scan_options[] = {
{"off", HNSW_ITERATIVE_SCAN_OFF, false},
{"relaxed_order", HNSW_ITERATIVE_SCAN_RELAXED, false},
{"strict_order", HNSW_ITERATIVE_SCAN_STRICT, false},
{NULL, 0, false}
};
int hnsw_ef_search;
int hnsw_iterative_search_max_tuples;
int hnsw_iterative_search;
int hnsw_iterative_scan;
int hnsw_max_scan_tuples;
double hnsw_scan_mem_multiplier;
int hnsw_lock_tranche_id;
static relopt_kind hnsw_relopt_kind;
@@ -76,16 +77,21 @@ HnswInit(void)
DefineCustomIntVariable("hnsw.ef_search", "Sets the size of the dynamic candidate list for search",
"Valid range is 1..1000.", &hnsw_ef_search,
HNSW_DEFAULT_EF_SEARCH, HNSW_MIN_EF_SEARCH, HNSW_MAX_EF_SEARCH, PGC_USERSET, 0, NULL, NULL, NULL);
HNSW_DEFAULT_EF_SEARCH, HNSW_MIN_EF_SEARCH, HNSW_MAX_EF_SEARCH, PGC_USERSET, GUC_EXPLAIN, NULL, NULL, NULL);
DefineCustomEnumVariable("hnsw.iterative_search", "Sets iterative search",
NULL, &hnsw_iterative_search,
HNSW_ITERATIVE_SEARCH_OFF, hnsw_iterative_search_options, PGC_USERSET, 0, NULL, NULL, NULL);
DefineCustomEnumVariable("hnsw.iterative_scan", "Sets the mode for iterative scans",
NULL, &hnsw_iterative_scan,
HNSW_ITERATIVE_SCAN_OFF, hnsw_iterative_scan_options, PGC_USERSET, GUC_EXPLAIN, NULL, NULL, NULL);
/* TODO Ensure ivfflat.max_probes uses same value for "all" */
DefineCustomIntVariable("hnsw.iterative_search_max_tuples", "Sets the max number of candidates to visit for iterative search",
"-1 means all", &hnsw_iterative_search_max_tuples,
-1, -1, INT_MAX, PGC_USERSET, 0, NULL, NULL, NULL);
/* This is approximate and does not affect the initial scan */
DefineCustomIntVariable("hnsw.max_scan_tuples", "Sets the max number of tuples to visit for iterative scans",
NULL, &hnsw_max_scan_tuples,
20000, 1, INT_MAX, PGC_USERSET, GUC_EXPLAIN, NULL, NULL, NULL);
/* Same range as hash_mem_multiplier */
DefineCustomRealVariable("hnsw.scan_mem_multiplier", "Sets the multiple of work_mem to use for iterative scans",
NULL, &hnsw_scan_mem_multiplier,
1, 1, 1000, PGC_USERSET, GUC_EXPLAIN, NULL, NULL, NULL);
MarkGUCPrefixReserved("hnsw");
}
@@ -131,6 +137,10 @@ hnswcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
*indexSelectivity = 0;
*indexCorrelation = 0;
*indexPages = 0;
#if PG_VERSION_NUM >= 180000
/* See "On disable_cost" thread on pgsql-hackers */
path->path.disabled_nodes = 2;
#endif
return;
}
@@ -245,13 +255,13 @@ hnswhandler(PG_FUNCTION_ARGS)
IndexAmRoutine *amroutine = makeNode(IndexAmRoutine);
amroutine->amstrategies = 0;
amroutine->amsupport = 4;
amroutine->amsupport = 3;
amroutine->amoptsprocnum = 0;
amroutine->amcanorder = false;
amroutine->amcanorderbyop = true;
amroutine->amcanbackward = false; /* can change direction mid-scan */
amroutine->amcanunique = false;
amroutine->amcanmulticol = true;
amroutine->amcanmulticol = false;
amroutine->amoptionalkey = true;
amroutine->amsearcharray = false;
amroutine->amsearchnulls = false;
@@ -303,17 +313,3 @@ hnswhandler(PG_FUNCTION_ARGS)
PG_RETURN_POINTER(amroutine);
}
/*
* Get the distance between two int4 attributes
*/
PGDLLEXPORT PG_FUNCTION_INFO_V1(hnsw_int4_attribute_distance);
Datum
hnsw_int4_attribute_distance(PG_FUNCTION_ARGS)
{
int32 a = PG_GETARG_INT32(0);
int32 b = PG_GETARG_INT32(1);
double distance = ((double) a) - ((double) b);
PG_RETURN_FLOAT8(distance);
}

View File

@@ -19,7 +19,6 @@
#define HNSW_DISTANCE_PROC 1
#define HNSW_NORM_PROC 2
#define HNSW_TYPE_INFO_PROC 3
#define HNSW_ATTRIBUTE_DISTANCE_PROC 4
#define HNSW_VERSION 1
#define HNSW_MAGIC_NUMBER 0xA953A953
@@ -108,20 +107,19 @@
#define HnswPtrPointer(hp) (hp).ptr
#define HnswPtrOffset(hp) relptr_offset((hp).relptr)
#define HnswUseIndexTuple(index) (IndexRelationGetNumberOfAttributes(index) > 1)
/* Variables */
extern int hnsw_ef_search;
extern int hnsw_iterative_search;
extern int hnsw_iterative_search_max_tuples;
extern int hnsw_iterative_scan;
extern int hnsw_max_scan_tuples;
extern double hnsw_scan_mem_multiplier;
extern int hnsw_lock_tranche_id;
typedef enum HnswIterativeSearchType
typedef enum HnswIterativeScanMode
{
HNSW_ITERATIVE_SEARCH_OFF,
HNSW_ITERATIVE_SEARCH_RELAXED,
HNSW_ITERATIVE_SEARCH_STRICT
} HnswIterativeSearchType;
HNSW_ITERATIVE_SCAN_OFF,
HNSW_ITERATIVE_SCAN_RELAXED,
HNSW_ITERATIVE_SCAN_STRICT
} HnswIterativeScanMode;
typedef struct HnswElementData HnswElementData;
typedef struct HnswNeighborArray HnswNeighborArray;
@@ -136,7 +134,6 @@ HnswPtrDeclare(HnswElementData, HnswElementRelptr, HnswElementPtr);
HnswPtrDeclare(HnswNeighborArray, HnswNeighborArrayRelptr, HnswNeighborArrayPtr);
HnswPtrDeclare(HnswNeighborArrayPtr, HnswNeighborsRelptr, HnswNeighborsPtr);
HnswPtrDeclare(char, DatumRelptr, DatumPtr);
HnswPtrDeclare(IndexTupleData, IndexTupleRelptr, IndexTuplePtr);
struct HnswElementData
{
@@ -153,7 +150,6 @@ struct HnswElementData
OffsetNumber neighborOffno;
BlockNumber neighborPage;
DatumPtr value;
IndexTuplePtr itup;
LWLock lock;
};
@@ -179,7 +175,6 @@ typedef struct HnswSearchCandidate
pairingheap_node w_node;
HnswElementPtr element;
double distance;
bool matches;
} HnswSearchCandidate;
/* HNSW index options */
@@ -258,16 +253,14 @@ typedef struct HnswTypeInfo
typedef struct HnswSupport
{
FmgrInfo *procinfo[2];
FmgrInfo *procinfo;
FmgrInfo *normprocinfo;
Oid *collation;
Oid collation;
} HnswSupport;
typedef struct HnswQuery
{
Datum value;
IndexTuple itup;
ScanKeyData *keyData;
} HnswQuery;
typedef struct HnswBuildState
@@ -296,8 +289,6 @@ typedef struct HnswBuildState
HnswGraph *graph;
double ml;
int maxLevel;
bool useIndexTuple;
TupleDesc tupdesc;
/* Memory */
MemoryContext graphCtx;
@@ -382,6 +373,7 @@ typedef struct HnswScanOpaqueData
int m;
int64 tuples;
double previousDistance;
Size maxMemory;
MemoryContext tmpCtx;
/* Support functions */
@@ -425,32 +417,30 @@ bool HnswCheckNorm(HnswSupport * support, Datum value);
Buffer HnswNewBuffer(Relation index, ForkNumber forkNum);
void HnswInitPage(Buffer buf, Page page);
void HnswInit(void);
List *HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation index, HnswSupport * support, int m, bool inserting, HnswElement skipElement, bool inMemory, visited_hash * v, pairingheap **discarded, bool initVisited, int64 *tuples);
List *HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation index, HnswSupport * support, int m, bool inserting, HnswElement skipElement, visited_hash * v, pairingheap **discarded, bool initVisited, int64 *tuples);
HnswElement HnswGetEntryPoint(Relation index);
void HnswGetMetaPageInfo(Relation index, int *m, HnswElement * entryPoint);
void *HnswAlloc(HnswAllocator * allocator, Size size);
HnswElement HnswInitElement(char *base, ItemPointer tid, int m, double ml, int maxLevel, HnswAllocator * alloc);
HnswElement HnswInitElementFromBlock(BlockNumber blkno, OffsetNumber offno);
void HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, HnswSupport * support, int m, int efConstruction, bool existing, bool inMemory);
HnswSearchCandidate *HnswEntryCandidate(char *base, HnswElement em, HnswQuery * q, Relation rel, HnswSupport * support, bool loadVec, bool inMemory);
void HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, HnswSupport * support, int m, int efConstruction, bool existing);
HnswSearchCandidate *HnswEntryCandidate(char *base, HnswElement em, HnswQuery * q, Relation rel, HnswSupport * support, bool loadVec);
void HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, BlockNumber insertPage, ForkNumber forkNum, bool building);
void HnswSetNeighborTuple(char *base, HnswNeighborTuple ntup, HnswElement e, int m);
void HnswAddHeapTid(HnswElement element, ItemPointer heaptid);
HnswNeighborArray *HnswInitNeighborArray(int lm, HnswAllocator * allocator);
void HnswInitNeighbors(char *base, HnswElement element, int m, HnswAllocator * alloc);
bool HnswInsertTupleOnDisk(Relation index, HnswSupport * support, IndexTuple itup, ItemPointer heaptid, bool building, TupleDesc tupdesc);
bool HnswInsertTupleOnDisk(Relation index, HnswSupport * support, Datum value, ItemPointer heaptid, bool building);
void HnswUpdateNeighborsOnDisk(Relation index, HnswSupport * support, HnswElement e, int m, bool checkExisting, bool building);
void HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec, Relation index);
void HnswLoadElement(HnswElement element, double *distance, bool *matches, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance);
void HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element, bool useIndexTuple);
void HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec);
void HnswLoadElement(HnswElement element, double *distance, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance);
bool HnswFormIndexValue(Datum *out, Datum *values, bool *isnull, const HnswTypeInfo * typeInfo, HnswSupport * support);
void HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element);
void HnswUpdateConnection(char *base, HnswNeighborArray * neighbors, HnswElement newElement, float distance, int lm, int *updateIdx, Relation index, HnswSupport * support);
bool HnswFormIndexTuple(IndexTuple *out, Datum *values, bool *isnull, const HnswTypeInfo * typeInfo, HnswSupport * support, TupleDesc tupdesc);
bool HnswLoadNeighborTids(HnswElement element, ItemPointerData *indextids, Relation index, int m, int lm, int lc);
void HnswInitLockTranche(void);
const HnswTypeInfo *HnswGetTypeInfo(Relation index);
PGDLLEXPORT void HnswParallelBuildMain(dsm_segment *seg, shm_toc *toc);
Size HnswGetElementTupleSize(char *base, HnswElement element, bool useIndexTuple);
bool HnswIndexTupleIsEqual(IndexTuple a, IndexTuple b, TupleDesc tupdesc);
/* Index access methods */
IndexBuildResult *hnswbuild(Relation heap, Relation index, IndexInfo *indexInfo);

View File

@@ -148,7 +148,6 @@ CreateGraphPages(HnswBuildState * buildstate)
Page page;
HnswElementPtr iter = buildstate->graph->head;
char *base = buildstate->hnswarea;
bool useIndexTuple = buildstate->useIndexTuple;
/* Calculate sizes */
maxSize = HNSW_MAX_SIZE;
@@ -168,6 +167,7 @@ CreateGraphPages(HnswBuildState * buildstate)
Size etupSize;
Size ntupSize;
Size combinedSize;
Pointer valuePtr = HnswPtrAccess(base, element->value);
/* Update iterator */
iter = element->next;
@@ -176,7 +176,7 @@ CreateGraphPages(HnswBuildState * buildstate)
MemSet(etup, 0, HNSW_TUPLE_ALLOC_SIZE);
/* Calculate sizes */
etupSize = HnswGetElementTupleSize(base, element, useIndexTuple);
etupSize = HNSW_ELEMENT_TUPLE_SIZE(VARSIZE_ANY(valuePtr));
ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(element->level, buildstate->m);
combinedSize = etupSize + ntupSize + sizeof(ItemIdData);
@@ -186,7 +186,7 @@ CreateGraphPages(HnswBuildState * buildstate)
(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
errmsg("index tuple too large")));
HnswSetElementTuple(base, etup, element, useIndexTuple);
HnswSetElementTuple(base, etup, element);
/* Keep element and neighbors on the same page if possible */
if (PageGetFreeSpace(page) < etupSize || (combinedSize <= maxSize && PageGetFreeSpace(page) < combinedSize))
@@ -327,18 +327,19 @@ AddDuplicateInMemory(HnswElement element, HnswElement dup)
* Find duplicate element
*/
static bool
FindDuplicateInMemory(char *base, HnswElement element, bool useIndexTuple, TupleDesc tupdesc)
FindDuplicateInMemory(char *base, HnswElement element)
{
HnswNeighborArray *neighbors = HnswGetNeighbors(base, element, 0);
IndexTuple itup = HnswPtrAccess(base, element->itup);
Datum value = HnswGetValue(base, element);
for (int i = 0; i < neighbors->length; i++)
{
HnswCandidate *neighbor = &neighbors->items[i];
HnswElement neighborElement = HnswPtrAccess(base, neighbor->element);
Datum neighborValue = HnswGetValue(base, neighborElement);
/* Exit early since ordered by distance */
if (!HnswIndexTupleIsEqual(itup, HnswPtrAccess(base, neighborElement->itup), tupdesc))
if (!datumIsEqual(value, neighborValue, false, -1))
return false;
/* Check for space */
@@ -365,7 +366,7 @@ AddElementInMemory(char *base, HnswGraph * graph, HnswElement element)
* Update neighbors
*/
static void
UpdateNeighborsInMemory(char *base, Relation index, HnswSupport * support, HnswElement e, int m)
UpdateNeighborsInMemory(char *base, HnswSupport * support, HnswElement e, int m)
{
for (int lc = e->level; lc >= 0; lc--)
{
@@ -387,7 +388,7 @@ UpdateNeighborsInMemory(char *base, Relation index, HnswSupport * support, HnswE
Assert(neighborElement);
LWLockAcquire(&neighborElement->lock, LW_EXCLUSIVE);
HnswUpdateConnection(base, HnswGetNeighbors(base, neighborElement, lc), e, hc->distance, lm, NULL, index, support);
HnswUpdateConnection(base, HnswGetNeighbors(base, neighborElement, lc), e, hc->distance, lm, NULL, NULL, support);
LWLockRelease(&neighborElement->lock);
}
}
@@ -403,14 +404,14 @@ UpdateGraphInMemory(HnswSupport * support, HnswElement element, int m, int efCon
char *base = buildstate->hnswarea;
/* Look for duplicate */
if (FindDuplicateInMemory(base, element, buildstate->useIndexTuple, buildstate->tupdesc))
if (FindDuplicateInMemory(base, element))
return;
/* Add element */
AddElementInMemory(base, graph, element);
/* Update neighbors */
UpdateNeighborsInMemory(base, buildstate->index, support, element, m);
UpdateNeighborsInMemory(base, support, element, m);
/* Update entry point if needed (already have lock) */
if (entryPoint == NULL || element->level > entryPoint->level)
@@ -423,7 +424,6 @@ UpdateGraphInMemory(HnswSupport * support, HnswElement element, int m, int efCon
static void
InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element)
{
Relation index = buildstate->index;
HnswGraph *graph = buildstate->graph;
HnswSupport *support = &buildstate->support;
HnswElement entryPoint;
@@ -457,7 +457,7 @@ InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element)
}
/* Find neighbors for element */
HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, false, true);
HnswFindElementNeighbors(base, element, entryPoint, NULL, support, m, efConstruction, false);
/* Update graph in memory */
UpdateGraphInMemory(support, element, m, efConstruction, entryPoint, buildstate);
@@ -476,20 +476,18 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
HnswElement element;
HnswAllocator *allocator = &buildstate->allocator;
HnswSupport *support = &buildstate->support;
Size valueSize;
Pointer valuePtr;
LWLock *flushLock = &graph->flushLock;
char *base = buildstate->hnswarea;
TupleDesc tupdesc = buildstate->tupdesc;
IndexTuple itup;
Size itupSize;
IndexTuple itupShared;
bool unused;
Datum value;
/* Form index tuple */
if (!HnswFormIndexTuple(&itup, values, isnull, buildstate->typeInfo, support, tupdesc))
/* Form index value */
if (!HnswFormIndexValue(&value, values, isnull, buildstate->typeInfo, support))
return false;
/* Get tuple size */
itupSize = IndexTupleSize(itup);
/* Get datum size */
valueSize = VARSIZE_ANY(DatumGetPointer(value));
/* Ensure graph not flushed when inserting */
LWLockAcquire(flushLock, LW_SHARED);
@@ -499,7 +497,7 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
{
LWLockRelease(flushLock);
return HnswInsertTupleOnDisk(index, support, itup, heaptid, true, tupdesc);
return HnswInsertTupleOnDisk(index, support, value, heaptid, true);
}
/*
@@ -531,12 +529,12 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
LWLockRelease(flushLock);
return HnswInsertTupleOnDisk(index, support, itup, heaptid, true, tupdesc);
return HnswInsertTupleOnDisk(index, support, value, heaptid, true);
}
/* Ok, we can proceed to allocate the element */
element = HnswInitElement(base, heaptid, buildstate->m, buildstate->ml, buildstate->maxLevel, allocator);
itupShared = HnswAlloc(allocator, itupSize);
valuePtr = HnswAlloc(allocator, valueSize);
/*
* We have now allocated the space needed for the element, so we don't
@@ -545,10 +543,9 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
*/
LWLockRelease(&graph->allocatorLock);
/* Copy the tuple */
memcpy(itupShared, itup, itupSize);
HnswPtrStore(base, element->itup, itupShared);
HnswPtrStore(base, element->value, DatumGetPointer(index_getattr(itupShared, 1, tupdesc, &unused)));
/* Copy the datum */
memcpy(valuePtr, DatumGetPointer(value), valueSize);
HnswPtrStore(base, element->value, valuePtr);
/* Create a lock for the element */
LWLockInitialize(&element->lock, hnsw_lock_tranche_id);
@@ -675,19 +672,6 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("type not supported for hnsw index")));
/* TODO See if needed */
if (IndexRelationGetNumberOfKeyAttributes(index) > 2)
elog(ERROR, "index cannot have more than two columns");
if (!OidIsValid(index_getprocid(index, 1, HNSW_DISTANCE_PROC)))
elog(ERROR, "first column must be a vector");
for (int i = 1; i < IndexRelationGetNumberOfKeyAttributes(index); i++)
{
if (!OidIsValid(index_getprocid(index, i + 1, HNSW_ATTRIBUTE_DISTANCE_PROC)))
elog(ERROR, "column %d cannot be a vector", i + 1);
}
/* Require column to have dimensions to be indexed */
if (buildstate->dimensions < 0)
ereport(ERROR,
@@ -714,8 +698,6 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
buildstate->graph = &buildstate->graphData;
buildstate->ml = HnswGetMl(buildstate->m);
buildstate->maxLevel = HnswGetMaxLevel(buildstate->m);
buildstate->useIndexTuple = HnswUseIndexTuple(index);
buildstate->tupdesc = RelationGetDescr(index);
buildstate->graphCtx = GenerationContextCreate(CurrentMemoryContext,
"Hnsw build graph context",

View File

@@ -156,10 +156,9 @@ AddElementOnDisk(Relation index, HnswElement e, int m, BlockNumber insertPage, B
BlockNumber newInsertPage = InvalidBlockNumber;
uint8 tupleVersion;
char *base = NULL;
bool useIndexTuple = HnswUseIndexTuple(index);
/* Calculate sizes */
etupSize = HnswGetElementTupleSize(base, e, useIndexTuple);
etupSize = HNSW_ELEMENT_TUPLE_SIZE(VARSIZE_ANY(HnswPtrAccess(base, e->value)));
ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(e->level, m);
combinedSize = etupSize + ntupSize + sizeof(ItemIdData);
maxSize = HNSW_MAX_SIZE;
@@ -167,7 +166,7 @@ AddElementOnDisk(Relation index, HnswElement e, int m, BlockNumber insertPage, B
/* Prepare element tuple */
etup = palloc0(etupSize);
HnswSetElementTuple(base, etup, e, useIndexTuple);
HnswSetElementTuple(base, etup, e);
/* Prepare neighbor tuple */
ntup = palloc0(ntupSize);
@@ -384,9 +383,8 @@ LoadElementsForInsert(HnswNeighborArray * neighbors, HnswQuery * q, int *idx, Re
HnswCandidate *hc = &neighbors->items[i];
HnswElement element = HnswPtrAccess(base, hc->element);
double distance;
bool matches;
HnswLoadElement(element, &distance, &matches, q, index, support, true, NULL);
HnswLoadElement(element, &distance, q, index, support, true, NULL);
hc->distance = distance;
/* Prune element if being deleted */
@@ -430,8 +428,6 @@ GetUpdateIndex(HnswElement element, HnswElement newElement, float distance, int
HnswQuery q;
q.value = HnswGetValue(base, element);
q.itup = HnswPtrAccess(base, element->itup);
q.keyData = NULL;
LoadElementsForInsert(neighbors, &q, &idx, index, support);
@@ -637,30 +633,21 @@ AddDuplicateOnDisk(Relation index, HnswElement element, HnswElement dup, bool bu
* Find duplicate element
*/
static bool
FindDuplicateOnDisk(Relation index, HnswElement element, bool building, TupleDesc tupdesc)
FindDuplicateOnDisk(Relation index, HnswElement element, bool building)
{
char *base = NULL;
HnswNeighborArray *neighbors = HnswGetNeighbors(base, element, 0);
Datum value = HnswGetValue(base, element);
IndexTuple itup = HnswPtrAccess(base, element->itup);
for (int i = 0; i < neighbors->length; i++)
{
HnswCandidate *neighbor = &neighbors->items[i];
HnswElement neighborElement = HnswPtrAccess(base, neighbor->element);
Datum neighborValue = HnswGetValue(base, neighborElement);
if (HnswUseIndexTuple(index))
{
/* Exit early since ordered by distance */
if (!HnswIndexTupleIsEqual(itup, HnswPtrAccess(base, neighborElement->itup), tupdesc))
return false;
}
else
{
/* Exit early since ordered by distance */
if (!datumIsEqual(value, HnswGetValue(base, neighborElement), false, -1))
return false;
}
/* Exit early since ordered by distance */
if (!datumIsEqual(value, neighborValue, false, -1))
return false;
if (AddDuplicateOnDisk(index, element, neighborElement, building))
return true;
@@ -673,12 +660,12 @@ FindDuplicateOnDisk(Relation index, HnswElement element, bool building, TupleDes
* Update graph on disk
*/
static void
UpdateGraphOnDisk(Relation index, HnswSupport * support, HnswElement element, int m, int efConstruction, HnswElement entryPoint, bool building, TupleDesc tupdesc)
UpdateGraphOnDisk(Relation index, HnswSupport * support, HnswElement element, int m, int efConstruction, HnswElement entryPoint, bool building)
{
BlockNumber newInsertPage = InvalidBlockNumber;
/* Look for duplicate */
if (FindDuplicateOnDisk(index, element, building, tupdesc))
if (FindDuplicateOnDisk(index, element, building))
return;
/* Add element */
@@ -700,7 +687,7 @@ UpdateGraphOnDisk(Relation index, HnswSupport * support, HnswElement element, in
* Insert a tuple into the index
*/
bool
HnswInsertTupleOnDisk(Relation index, HnswSupport * support, IndexTuple itup, ItemPointer heaptid, bool building, TupleDesc tupdesc)
HnswInsertTupleOnDisk(Relation index, HnswSupport * support, Datum value, ItemPointer heaptid, bool building)
{
HnswElement entryPoint;
HnswElement element;
@@ -708,7 +695,6 @@ HnswInsertTupleOnDisk(Relation index, HnswSupport * support, IndexTuple itup, It
int efConstruction = HnswGetEfConstruction(index);
LOCKMODE lockmode = ShareLock;
char *base = NULL;
bool unused;
/*
* Get a shared lock. This allows vacuum to ensure no in-flight inserts
@@ -722,8 +708,7 @@ HnswInsertTupleOnDisk(Relation index, HnswSupport * support, IndexTuple itup, It
/* Create an element */
element = HnswInitElement(base, heaptid, m, HnswGetMl(m), HnswGetMaxLevel(m), NULL);
HnswPtrStore(base, element->itup, itup);
HnswPtrStore(base, element->value, DatumGetPointer(index_getattr(itup, 1, tupdesc, &unused)));
HnswPtrStore(base, element->value, DatumGetPointer(value));
/* Prevent concurrent inserts when likely updating entry point */
if (entryPoint == NULL || element->level > entryPoint->level)
@@ -740,10 +725,10 @@ HnswInsertTupleOnDisk(Relation index, HnswSupport * support, IndexTuple itup, It
}
/* Find neighbors for element */
HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, false, false);
HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, false);
/* Update graph on disk */
UpdateGraphOnDisk(index, support, element, m, efConstruction, entryPoint, building, tupdesc);
UpdateGraphOnDisk(index, support, element, m, efConstruction, entryPoint, building);
/* Release lock */
UnlockPage(index, HNSW_UPDATE_LOCK, lockmode);
@@ -757,18 +742,17 @@ HnswInsertTupleOnDisk(Relation index, HnswSupport * support, IndexTuple itup, It
static void
HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid)
{
IndexTuple itup;
Datum value;
const HnswTypeInfo *typeInfo = HnswGetTypeInfo(index);
TupleDesc tupdesc = RelationGetDescr(index);
HnswSupport support;
HnswInitSupport(&support, index);
/* Form index tuple */
if (!HnswFormIndexTuple(&itup, values, isnull, typeInfo, &support, tupdesc))
/* Form index value */
if (!HnswFormIndexValue(&value, values, isnull, typeInfo, &support))
return;
HnswInsertTupleOnDisk(index, &support, itup, heaptid, false, tupdesc);
HnswInsertTupleOnDisk(index, &support, value, heaptid, false);
}
/*

View File

@@ -22,30 +22,26 @@ GetScanItems(IndexScanDesc scan, Datum value)
int m;
HnswElement entryPoint;
char *base = NULL;
bool inMemory = false;
HnswQuery *q = &so->q;
q->value = value;
q->itup = NULL;
q->keyData = scan->keyData;
/* Get m and entry point */
HnswGetMetaPageInfo(index, &m, &entryPoint);
q->value = value;
so->m = m;
if (entryPoint == NULL)
return NIL;
ep = list_make1(HnswEntryCandidate(base, entryPoint, q, index, support, false, inMemory));
ep = list_make1(HnswEntryCandidate(base, entryPoint, q, index, support, false));
for (int lc = entryPoint->level; lc >= 1; lc--)
{
w = HnswSearchLayer(base, q, ep, 1, lc, index, support, m, false, NULL, inMemory, NULL, NULL, true, NULL);
w = HnswSearchLayer(base, q, ep, 1, lc, index, support, m, false, NULL, NULL, NULL, true, NULL);
ep = w;
}
return HnswSearchLayer(base, q, ep, hnsw_ef_search, 0, index, support, m, false, NULL, inMemory, &so->v, hnsw_iterative_search != HNSW_ITERATIVE_SEARCH_OFF ? &so->discarded : NULL, true, &so->tuples);
return HnswSearchLayer(base, q, ep, hnsw_ef_search, 0, index, support, m, false, NULL, &so->v, hnsw_iterative_scan != HNSW_ITERATIVE_SCAN_OFF ? &so->discarded : NULL, true, &so->tuples);
}
/*
@@ -76,7 +72,7 @@ ResumeScanItems(IndexScanDesc scan)
ep = lappend(ep, sc);
}
return HnswSearchLayer(base, &so->q, ep, batch_size, 0, index, &so->support, so->m, false, NULL, false, &so->v, &so->discarded, false, &so->tuples);
return HnswSearchLayer(base, &so->q, ep, batch_size, 0, index, &so->support, so->m, false, NULL, &so->v, &so->discarded, false, &so->tuples);
}
/*
@@ -100,12 +96,23 @@ GetScanValue(IndexScanDesc scan)
/* Normalize if needed */
if (so->support.normprocinfo != NULL)
value = HnswNormValue(so->typeInfo, so->support.collation[0], value);
value = HnswNormValue(so->typeInfo, so->support.collation, value);
}
return value;
}
#if defined(HNSW_MEMORY)
/*
* Show memory usage
*/
static void
ShowMemoryUsage(HnswScanOpaque so)
{
elog(INFO, "memory: %zu KB, tuples: " INT64_FORMAT, MemoryContextMemAllocated(so->tmpCtx, false) / 1024, so->tuples);
}
#endif
/*
* Prepare for an index scan
*/
@@ -114,21 +121,29 @@ hnswbeginscan(Relation index, int nkeys, int norderbys)
{
IndexScanDesc scan;
HnswScanOpaque so;
double maxMemory;
scan = RelationGetIndexScan(index, nkeys, norderbys);
so = (HnswScanOpaque) palloc(sizeof(HnswScanOpaqueData));
so->typeInfo = HnswGetTypeInfo(index);
so->first = true;
so->v.tids = NULL;
so->discarded = NULL;
so->tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
"Hnsw scan temporary context",
ALLOCSET_DEFAULT_SIZES);
/* Set support functions */
HnswInitSupport(&so->support, index);
/*
* Use a lower max allocation size than default to allow scanning more
* tuples for iterative search before exceeding work_mem
*/
so->tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
"Hnsw scan temporary context",
0, 8 * 1024, 256 * 1024);
/* Calculate max memory */
/* Add 256 extra bytes to fill last block when close */
maxMemory = (double) work_mem * hnsw_scan_mem_multiplier * 1024.0 + 256;
so->maxMemory = Min(maxMemory, (double) SIZE_MAX);
scan->opaque = so;
return scan;
@@ -142,13 +157,10 @@ hnswrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys, int no
{
HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
if (so->v.tids != NULL)
tidhash_reset(so->v.tids);
if (so->discarded != NULL)
pairingheap_reset(so->discarded);
so->first = true;
/* v and discarded are allocated in tmpCtx */
so->v.tids = NULL;
so->discarded = NULL;
so->tuples = 0;
so->previousDistance = -get_float8_infinity();
MemoryContextReset(so->tmpCtx);
@@ -208,7 +220,7 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
so->first = false;
#if defined(HNSW_MEMORY)
elog(INFO, "memory: %zu KB", MemoryContextMemAllocated(so->tmpCtx, false) / 1024);
ShowMemoryUsage(so);
#endif
}
@@ -221,15 +233,15 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
if (list_length(so->w) == 0)
{
if (hnsw_iterative_search == HNSW_ITERATIVE_SEARCH_OFF)
if (hnsw_iterative_scan == HNSW_ITERATIVE_SCAN_OFF)
break;
/* Empty index */
if (so->discarded == NULL)
break;
/* Reached max number of additional tuples */
if (hnsw_iterative_search_max_tuples != -1 && so->tuples >= hnsw_iterative_search_max_tuples)
/* Reached max number of tuples */
if (so->tuples >= hnsw_max_scan_tuples)
{
if (pairingheap_is_empty(so->discarded))
break;
@@ -238,13 +250,13 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
so->w = lappend(so->w, HnswGetSearchCandidate(w_node, pairingheap_remove_first(so->discarded)));
}
/* Prevent scans from consuming too much memory */
else if (MemoryContextMemAllocated(so->tmpCtx, false) > (Size) work_mem * 1024L)
else if (MemoryContextMemAllocated(so->tmpCtx, false) > so->maxMemory)
{
if (pairingheap_is_empty(so->discarded))
{
ereport(DEBUG1,
(errmsg("hnsw index scan exceeded work_mem after " INT64_FORMAT " tuples", so->tuples),
errhint("Increase work_mem to scan more tuples.")));
(errmsg("hnsw index scan reached memory limit after " INT64_FORMAT " tuples", so->tuples),
errhint("Increase hnsw.scan_mem_multiplier to scan more tuples.")));
break;
}
@@ -270,7 +282,7 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
UnlockPage(scan->indexRelation, HNSW_SCAN_LOCK, ShareLock);
#if defined(HNSW_MEMORY)
elog(INFO, "memory: %zu KB", MemoryContextMemAllocated(so->tmpCtx, false) / 1024);
ShowMemoryUsage(so);
#endif
}
@@ -282,12 +294,12 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
element = HnswPtrAccess(base, sc->element);
/* Move to next element if no valid heap TIDs */
if (!sc->matches || element->heaptidsLength == 0)
if (element->heaptidsLength == 0)
{
so->w = list_delete_last(so->w);
/* Mark memory as free for next iteration */
if (hnsw_iterative_search != HNSW_ITERATIVE_SEARCH_OFF)
if (hnsw_iterative_scan != HNSW_ITERATIVE_SCAN_OFF)
{
pfree(element);
pfree(sc);
@@ -298,7 +310,7 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
heaptid = &element->heaptids[--element->heaptidsLength];
if (hnsw_iterative_search == HNSW_ITERATIVE_SEARCH_STRICT)
if (hnsw_iterative_scan == HNSW_ITERATIVE_SCAN_STRICT)
{
if (sc->distance < so->previousDistance)
continue;

View File

@@ -146,39 +146,11 @@ HnswOptionalProcInfo(Relation index, uint16 procnum)
void
HnswInitSupport(HnswSupport * support, Relation index)
{
support->procinfo[0] = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
if (IndexRelationGetNumberOfKeyAttributes(index) > 1)
support->procinfo[1] = index_getprocinfo(index, 2, HNSW_ATTRIBUTE_DISTANCE_PROC);
support->collation = index->rd_indcollation;
support->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
support->collation = index->rd_indcollation[0];
support->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
}
/*
* Get element tuple size
*/
Size
HnswGetElementTupleSize(char *base, HnswElement element, bool useIndexTuple)
{
Size size;
if (useIndexTuple)
{
IndexTuple itup = HnswPtrAccess(base, element->itup);
size = IndexTupleSize(itup);
}
else
{
Pointer valuePtr = HnswPtrAccess(base, element->value);
size = VARSIZE_ANY(valuePtr);
}
return HNSW_ELEMENT_TUPLE_SIZE(size);
}
/*
* Normalize value
*/
@@ -194,38 +166,7 @@ HnswNormValue(const HnswTypeInfo * typeInfo, Oid collation, Datum value)
bool
HnswCheckNorm(HnswSupport * support, Datum value)
{
return DatumGetFloat8(FunctionCall1Coll(support->normprocinfo, support->collation[0], value)) > 0;
}
/*
* Check if index tuples are equal
*/
bool
HnswIndexTupleIsEqual(IndexTuple a, IndexTuple b, TupleDesc tupdesc)
{
for (int i = 0; i < tupdesc->natts; i++)
{
bool nullA;
bool nullB;
Datum datumA = index_getattr(a, i + 1, tupdesc, &nullA);
Datum datumB = index_getattr(b, i + 1, tupdesc, &nullB);
if (nullA || nullB)
{
if (nullA != nullB)
return false;
}
else
{
Form_pg_attribute att = TupleDescAttr(tupdesc, i);
if (!datumIsEqual(datumA, datumB, att->attbyval, att->attlen))
return false;
}
}
return true;
return DatumGetFloat8(FunctionCall1Coll(support->normprocinfo, support->collation, value)) > 0;
}
/*
@@ -316,7 +257,6 @@ HnswInitElement(char *base, ItemPointer heaptid, int m, double ml, int maxLevel,
HnswInitNeighbors(base, element, m, allocator);
HnswPtrStore(base, element->value, (Pointer) NULL);
HnswPtrStore(base, element->itup, (IndexTuple) NULL);
return element;
}
@@ -343,7 +283,6 @@ HnswInitElementFromBlock(BlockNumber blkno, OffsetNumber offno)
element->offno = offno;
HnswPtrStore(base, element->neighbors, (HnswNeighborArrayPtr *) NULL);
HnswPtrStore(base, element->value, (Pointer) NULL);
HnswPtrStore(base, element->itup, (IndexTuple) NULL);
return element;
}
@@ -456,13 +395,11 @@ HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, Bloc
}
/*
* Form index tuple
* Form index value
*/
bool
HnswFormIndexTuple(IndexTuple *out, Datum *values, bool *isnull, const HnswTypeInfo * typeInfo, HnswSupport * support, TupleDesc tupdesc)
HnswFormIndexValue(Datum *out, Datum *values, bool *isnull, const HnswTypeInfo * typeInfo, HnswSupport * support)
{
Datum newValues[2];
/* Detoast once for all calls */
Datum value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
@@ -476,14 +413,10 @@ HnswFormIndexTuple(IndexTuple *out, Datum *values, bool *isnull, const HnswTypeI
if (!HnswCheckNorm(support, value))
return false;
value = HnswNormValue(typeInfo, support->collation[0], value);
value = HnswNormValue(typeInfo, support->collation, value);
}
newValues[0] = value;
for (int i = 1; i < tupdesc->natts; i++)
newValues[i] = values[i];
*out = index_form_tuple(tupdesc, newValues, isnull);
*out = value;
return true;
}
@@ -492,8 +425,10 @@ HnswFormIndexTuple(IndexTuple *out, Datum *values, bool *isnull, const HnswTypeI
* Set element tuple, except for neighbor info
*/
void
HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element, bool useIndexTuple)
HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element)
{
Pointer valuePtr = HnswPtrAccess(base, element->value);
etup->type = HNSW_ELEMENT_TUPLE_TYPE;
etup->level = element->level;
etup->deleted = 0;
@@ -505,19 +440,7 @@ HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element, bool
else
ItemPointerSetInvalid(&etup->heaptids[i]);
}
if (useIndexTuple)
{
IndexTuple itup = HnswPtrAccess(base, element->itup);
memcpy(&etup->data, itup, IndexTupleSize(itup));
}
else
{
Pointer valuePtr = HnswPtrAccess(base, element->value);
memcpy(&etup->data, valuePtr, VARSIZE_ANY(valuePtr));
}
memcpy(&etup->data, valuePtr, VARSIZE_ANY(valuePtr));
}
/*
@@ -559,7 +482,7 @@ HnswSetNeighborTuple(char *base, HnswNeighborTuple ntup, HnswElement e, int m)
* Load an element from a tuple
*/
void
HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec, Relation index)
HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec)
{
element->level = etup->level;
element->deleted = etup->deleted;
@@ -583,128 +506,26 @@ HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHe
if (loadVec)
{
char *base = NULL;
Datum value = datumCopy(PointerGetDatum(&etup->data), false, -1);
if (HnswUseIndexTuple(index))
{
IndexTuple itup = CopyIndexTuple((IndexTuple) &etup->data);
TupleDesc tupdesc = RelationGetDescr(index);
bool unused;
HnswPtrStore(base, element->itup, itup);
HnswPtrStore(base, element->value, DatumGetPointer(index_getattr(itup, 1, tupdesc, &unused)));
}
else
{
Datum value = datumCopy(PointerGetDatum(&etup->data), false, -1);
HnswPtrStore(base, element->value, DatumGetPointer(value));
}
HnswPtrStore(base, element->value, DatumGetPointer(value));
}
}
/*
* Get the attribute distance
*/
static inline double
AttributeDistance(double e)
{
/* TODO Better bias */
/* must be >> max(w * g) + 1 / log10(2) */
double bias = 4.32;
return e > 0 ? bias - 1.0 / log10(e + 1) : 0;
}
/*
* Calculate the distance between values
*/
static double
HnswGetDistance(IndexTuple itup, Datum vec, HnswQuery * q, Relation index, HnswSupport * support, bool *matches)
static inline double
HnswGetDistance(Datum a, Datum b, HnswSupport * support)
{
double g;
if (DatumGetPointer(q->value) == NULL)
g = 0;
else
g = DatumGetFloat8(FunctionCall2Coll(support->procinfo[0], support->collation[0], q->value, vec));
Assert(PointerIsValid(matches));
*matches = true;
if (IndexRelationGetNumberOfKeyAttributes(index) > 1)
{
double w = 0.25;
double e = 0.0;
TupleDesc tupdesc = RelationGetDescr(index);
if (q->keyData)
{
/* TODO need to pass length of key data */
int keyCount = 1;
for (int i = 0; i < keyCount; i++)
{
ScanKey key = &q->keyData[i];
bool isnull;
Datum value = index_getattr(itup, key->sk_attno, tupdesc, &isnull);
bool attnull = key->sk_flags & SK_ISNULL;
if (isnull || attnull)
{
if (isnull != attnull)
{
e += 1000;
*matches = false;
}
}
else if (!DatumGetBool(FunctionCall2Coll(&key->sk_func, key->sk_collation, value, key->sk_argument)))
{
double ei = fabs(DatumGetFloat8(FunctionCall2Coll(support->procinfo[key->sk_attno - 1], support->collation[key->sk_attno - 1], value, key->sk_argument)));
if (ei > 0)
e += ei;
else
/* Distance is zero for inequality */
e += 1000;
*matches = false;
}
}
return w * g + AttributeDistance(e);
}
else if (q->itup)
{
int keyCount = IndexRelationGetNumberOfKeyAttributes(index) - 1;
for (int i = 0; i < keyCount; i++)
{
bool isnull;
bool attnull;
Datum value = index_getattr(itup, i + 2, tupdesc, &isnull);
Datum value2 = index_getattr(q->itup, i + 2, tupdesc, &attnull);
if (isnull || attnull)
{
if (isnull != attnull)
e += 1000;
}
else
e += fabs(DatumGetFloat8(FunctionCall2Coll(support->procinfo[i + 1], support->collation[i + 1], value, value2)));
}
return w * g + AttributeDistance(e);
}
}
return g;
return DatumGetFloat8(FunctionCall2Coll(support->procinfo, support->collation, a, b));
}
/*
* Load an element and optionally get its distance from q
*/
static void
HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, bool *matches, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance, HnswElement * element)
HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance, HnswElement * element)
{
Buffer buf;
Page page;
@@ -722,23 +543,10 @@ HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, boo
/* Calculate distance */
if (distance != NULL)
{
IndexTuple itup = NULL;
Datum value;
if (HnswUseIndexTuple(index))
{
TupleDesc tupdesc = RelationGetDescr(index);
bool unused;
itup = (IndexTuple) &etup->data;
value = index_getattr(itup, 1, tupdesc, &unused);
}
if (DatumGetPointer(q->value) == NULL)
*distance = 0;
else
{
value = PointerGetDatum(&etup->data);
}
*distance = HnswGetDistance(itup, value, q, index, support, matches);
*distance = HnswGetDistance(q->value, PointerGetDatum(&etup->data), support);
}
/* Load element */
@@ -747,7 +555,7 @@ HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, boo
if (*element == NULL)
*element = HnswInitElementFromBlock(blkno, offno);
HnswLoadElementFromTuple(*element, etup, true, loadVec, index);
HnswLoadElementFromTuple(*element, etup, true, loadVec);
}
UnlockReleaseBuffer(buf);
@@ -757,37 +565,50 @@ HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, boo
* Load an element and optionally get its distance from q
*/
void
HnswLoadElement(HnswElement element, double *distance, bool *matches, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance)
HnswLoadElement(HnswElement element, double *distance, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance)
{
HnswLoadElementImpl(element->blkno, element->offno, distance, matches, q, index, support, loadVec, maxDistance, &element);
HnswLoadElementImpl(element->blkno, element->offno, distance, q, index, support, loadVec, maxDistance, &element);
}
/*
* Get the distance for an element
*/
static double
GetElementDistance(char *base, HnswElement element, bool *matches, HnswQuery * q, Relation index, HnswSupport * support)
GetElementDistance(char *base, HnswElement element, HnswQuery * q, HnswSupport * support)
{
Datum value = HnswGetValue(base, element);
IndexTuple itup = HnswPtrAccess(base, element->itup);
return HnswGetDistance(itup, value, q, index, support, matches);
return HnswGetDistance(q->value, value, support);
}
/*
* Allocate a search candidate
*/
static HnswSearchCandidate *
HnswInitSearchCandidate(char *base, HnswElement element, double distance)
{
HnswSearchCandidate *sc = palloc(sizeof(HnswSearchCandidate));
HnswPtrStore(base, sc->element, element);
sc->distance = distance;
return sc;
}
/*
* Create a candidate for the entry point
*/
HnswSearchCandidate *
HnswEntryCandidate(char *base, HnswElement entryPoint, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, bool inMemory)
HnswEntryCandidate(char *base, HnswElement entryPoint, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec)
{
HnswSearchCandidate *sc = palloc(sizeof(HnswSearchCandidate));
bool inMemory = index == NULL;
double distance;
HnswPtrStore(base, sc->element, entryPoint);
if (inMemory)
sc->distance = GetElementDistance(base, entryPoint, &sc->matches, q, index, support);
distance = GetElementDistance(base, entryPoint, q, support);
else
HnswLoadElement(entryPoint, &sc->distance, &sc->matches, q, index, support, loadVec, NULL);
return sc;
HnswLoadElement(entryPoint, &distance, q, index, support, loadVec, NULL);
return HnswInitSearchCandidate(base, entryPoint, distance);
}
/*
@@ -990,7 +811,7 @@ HnswLoadUnvisitedFromDisk(HnswElement element, HnswUnvisited * unvisited, int *u
* Algorithm 2 from paper
*/
List *
HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation index, HnswSupport * support, int m, bool inserting, HnswElement skipElement, bool inMemory, visited_hash * v, pairingheap **discarded, bool initVisited, int64 *tuples)
HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation index, HnswSupport * support, int m, bool inserting, HnswElement skipElement, visited_hash * v, pairingheap **discarded, bool initVisited, int64 *tuples)
{
List *w = NIL;
pairingheap *C = pairingheap_allocate(CompareNearestCandidates, NULL);
@@ -1003,8 +824,7 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
int lm = HnswGetLayerM(m, lc);
HnswUnvisited *unvisited = palloc(lm * sizeof(HnswUnvisited));
int unvisitedLength;
uint64 additional = 0;
uint64 maxAdditional = q->keyData && lc == 0 ? 10000 : 0;
bool inMemory = index == NULL;
if (v == NULL)
{
@@ -1037,6 +857,7 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
{
AddToVisited(base, v, sc->element, inMemory, &found);
/* OK to count elements instead of tuples */
if (tuples != NULL)
(*tuples)++;
}
@@ -1044,10 +865,6 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
pairingheap_add(C, &sc->c_node);
pairingheap_add(W, &sc->w_node);
/* Do not count elements that do not match filter towards ef */
if (!sc->matches && ++additional <= maxAdditional)
continue;
/*
* Do not count elements being deleted towards ef when vacuuming. It
* would be ideal to do this for inserts as well, but this could
@@ -1073,6 +890,7 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
else
HnswLoadUnvisitedFromDisk(cElement, unvisited, &unvisitedLength, v, index, m, lm, lc);
/* OK to count elements instead of tuples */
if (tuples != NULL)
(*tuples) += unvisitedLength;
@@ -1081,7 +899,6 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
HnswElement eElement;
HnswSearchCandidate *e;
double eDistance;
bool eMatches;
bool alwaysAdd = wlen < ef;
f = HnswGetSearchCandidate(w_node, pairingheap_first(W));
@@ -1089,7 +906,7 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
if (inMemory)
{
eElement = unvisited[i].element;
eDistance = GetElementDistance(base, eElement, &eMatches, q, index, support);
eDistance = GetElementDistance(base, eElement, q, support);
}
else
{
@@ -1099,7 +916,7 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
/* Avoid any allocations if not adding */
eElement = NULL;
HnswLoadElementImpl(blkno, offno, &eDistance, &eMatches, q, index, support, inserting, alwaysAdd || discarded != NULL ? NULL : &f->distance, &eElement);
HnswLoadElementImpl(blkno, offno, &eDistance, q, index, support, inserting, alwaysAdd || discarded != NULL ? NULL : &f->distance, &eElement);
if (eElement == NULL)
continue;
@@ -1110,9 +927,7 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
if (discarded != NULL)
{
/* Create a new candidate */
e = palloc(sizeof(HnswSearchCandidate));
HnswPtrStore(base, e->element, eElement);
e->distance = eDistance;
e = HnswInitSearchCandidate(base, eElement, eDistance);
pairingheap_add(*discarded, &e->w_node);
}
@@ -1124,10 +939,7 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
continue;
/* Create a new candidate */
e = palloc(sizeof(HnswSearchCandidate));
HnswPtrStore(base, e->element, eElement);
e->distance = eDistance;
e->matches = eMatches;
e = HnswInitSearchCandidate(base, eElement, eDistance);
pairingheap_add(C, &e->c_node);
pairingheap_add(W, &e->w_node);
@@ -1138,10 +950,6 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
*/
if (CountElement(skipElement, eElement))
{
/* Do not count elements that do not match filter towards ef */
if (!e->matches && ++additional <= maxAdditional)
continue;
wlen++;
/* No need to decrement wlen */
@@ -1219,24 +1027,18 @@ CompareCandidateDistancesOffset(const ListCell *a, const ListCell *b)
* Check if an element is closer to q than any element from R
*/
static bool
CheckElementCloser(char *base, HnswCandidate * e, List *r, Relation index, HnswSupport * support)
CheckElementCloser(char *base, HnswCandidate * e, List *r, HnswSupport * support)
{
HnswElement eElement = HnswPtrAccess(base, e->element);
HnswQuery q;
Datum eValue = HnswGetValue(base, eElement);
ListCell *lc2;
q.value = HnswGetValue(base, eElement);
q.itup = HnswPtrAccess(base, eElement->itup);
q.keyData = NULL;
foreach(lc2, r)
{
HnswCandidate *ri = lfirst(lc2);
HnswElement riElement = HnswPtrAccess(base, ri->element);
Datum riValue = HnswGetValue(base, riElement);
IndexTuple ritup = HnswPtrAccess(base, riElement->itup);
bool matches;
float distance = HnswGetDistance(ritup, riValue, &q, index, support, &matches);
float distance = HnswGetDistance(eValue, riValue, support);
if (distance <= e->distance)
return false;
@@ -1249,7 +1051,7 @@ CheckElementCloser(char *base, HnswCandidate * e, List *r, Relation index, HnswS
* Algorithm 4 from paper
*/
static List *
SelectNeighbors(char *base, List *c, int lm, Relation index, HnswSupport * support, bool *closerSet, HnswCandidate * newCandidate, HnswCandidate * *pruned, bool sortCandidates)
SelectNeighbors(char *base, List *c, int lm, HnswSupport * support, bool *closerSet, HnswCandidate * newCandidate, HnswCandidate * *pruned, bool sortCandidates)
{
List *r = NIL;
List *w = list_copy(c);
@@ -1283,7 +1085,7 @@ SelectNeighbors(char *base, List *c, int lm, Relation index, HnswSupport * suppo
/* Use previous state of r and wd to skip work when possible */
if (mustCalculate)
e->closer = CheckElementCloser(base, e, r, index, support);
e->closer = CheckElementCloser(base, e, r, support);
else if (list_length(added) > 0)
{
/* Keep Valgrind happy for in-memory, parallel builds */
@@ -1296,7 +1098,8 @@ SelectNeighbors(char *base, List *c, int lm, Relation index, HnswSupport * suppo
*/
if (e->closer)
{
e->closer = CheckElementCloser(base, e, added, index, support);
e->closer = CheckElementCloser(base, e, added, support);
if (!e->closer)
removedAny = true;
}
@@ -1308,7 +1111,7 @@ SelectNeighbors(char *base, List *c, int lm, Relation index, HnswSupport * suppo
*/
if (removedAny)
{
e->closer = CheckElementCloser(base, e, r, index, support);
e->closer = CheckElementCloser(base, e, r, support);
if (e->closer)
added = lappend(added, e);
}
@@ -1316,7 +1119,7 @@ SelectNeighbors(char *base, List *c, int lm, Relation index, HnswSupport * suppo
}
else if (e == newCandidate)
{
e->closer = CheckElementCloser(base, e, r, index, support);
e->closer = CheckElementCloser(base, e, r, support);
if (e->closer)
added = lappend(added, e);
}
@@ -1393,7 +1196,7 @@ HnswUpdateConnection(char *base, HnswNeighborArray * neighbors, HnswElement newE
c = lappend(c, &neighbors->items[i]);
c = lappend(c, &newHc);
SelectNeighbors(base, c, lm, index, support, &neighbors->closerSet, &newHc, &pruned, true);
SelectNeighbors(base, c, lm, support, &neighbors->closerSet, &newHc, &pruned, true);
/* Should not happen */
if (pruned == NULL)
@@ -1464,19 +1267,17 @@ PrecomputeHash(char *base, HnswElement element)
* Algorithm 1 from paper
*/
void
HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, HnswSupport * support, int m, int efConstruction, bool existing, bool inMemory)
HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, HnswSupport * support, int m, int efConstruction, bool existing)
{
List *ep;
List *w;
int level = element->level;
int entryLevel;
HnswQuery q;
HnswElement skipElement = existing ? element : NULL;
bool inMemory = index == NULL;
q.value = HnswGetValue(base, element);
q.itup = HnswPtrAccess(base, element->itup);
q.keyData = NULL;
/* Precompute hash */
if (inMemory)
@@ -1487,13 +1288,13 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
return;
/* Get entry point and level */
ep = list_make1(HnswEntryCandidate(base, entryPoint, &q, index, support, true, inMemory));
ep = list_make1(HnswEntryCandidate(base, entryPoint, &q, index, support, true));
entryLevel = entryPoint->level;
/* 1st phase: greedy search to insert level */
for (int lc = entryLevel; lc >= level + 1; lc--)
{
w = HnswSearchLayer(base, &q, ep, 1, lc, index, support, m, true, skipElement, inMemory, NULL, NULL, true, NULL);
w = HnswSearchLayer(base, &q, ep, 1, lc, index, support, m, true, skipElement, NULL, NULL, true, NULL);
ep = w;
}
@@ -1512,7 +1313,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
List *lw = NIL;
ListCell *lc2;
w = HnswSearchLayer(base, &q, ep, efConstruction, lc, index, support, m, true, skipElement, inMemory, NULL, NULL, true, NULL);
w = HnswSearchLayer(base, &q, ep, efConstruction, lc, index, support, m, true, skipElement, NULL, NULL, true, NULL);
/* Convert search candidates to candidates */
foreach(lc2, w)
@@ -1536,7 +1337,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
* sortCandidates to true for in-memory builds to enable closer
* caching, but there does not seem to be a difference in performance.
*/
neighbors = SelectNeighbors(base, lw, lm, index, support, &HnswGetNeighbors(base, element, lc)->closerSet, NULL, NULL, false);
neighbors = SelectNeighbors(base, lw, lm, support, &HnswGetNeighbors(base, element, lc)->closerSet, NULL, NULL, false);
AddConnections(base, element, neighbors, lc);

View File

@@ -204,7 +204,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
element->heaptidsLength = 0;
/* Find neighbors for element, skipping itself */
HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, true, false);
HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, true);
/* Zero memory for each element */
MemSet(ntup, 0, HNSW_TUPLE_ALLOC_SIZE);
@@ -256,7 +256,7 @@ RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
LockPage(index, HNSW_UPDATE_LOCK, ShareLock);
/* Load element */
HnswLoadElement(highestPoint, NULL, NULL, NULL, index, support, true, NULL);
HnswLoadElement(highestPoint, NULL, NULL, index, support, true, NULL);
/* Repair if needed */
if (NeedsUpdated(vacuumstate, highestPoint))
@@ -294,7 +294,7 @@ RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
* is outdated, this can remove connections at higher levels in
* the graph until they are repaired, but this should be fine.
*/
HnswLoadElement(entryPoint, NULL, NULL, NULL, index, support, true, NULL);
HnswLoadElement(entryPoint, NULL, NULL, index, support, true, NULL);
if (NeedsUpdated(vacuumstate, entryPoint))
{
@@ -370,7 +370,7 @@ RepairGraph(HnswVacuumState * vacuumstate)
/* Create an element */
element = HnswInitElementFromBlock(blkno, offno);
HnswLoadElementFromTuple(element, etup, false, true, index);
HnswLoadElementFromTuple(element, etup, false, true);
elements = lappend(elements, element);
}
@@ -440,7 +440,6 @@ MarkDeleted(HnswVacuumState * vacuumstate)
BlockNumber insertPage = InvalidBlockNumber;
Relation index = vacuumstate->index;
BufferAccessStrategy bas = vacuumstate->bas;
bool useIndexTuple = HnswUseIndexTuple(index);
/*
* Wait for index scans to complete. Scans before this point may contain
@@ -522,14 +521,7 @@ MarkDeleted(HnswVacuumState * vacuumstate)
/* Overwrite element */
etup->deleted = 1;
if (useIndexTuple)
{
IndexTuple itup = (IndexTuple) &etup->data;
MemSet(itup, 0, IndexTupleSize(itup));
}
else
MemSet(&etup->data, 0, VARSIZE_ANY(&etup->data));
MemSet(&etup->data, 0, VARSIZE_ANY(&etup->data));
/* Overwrite neighbors */
for (int i = 0; i < ntup->count; i++)

View File

@@ -138,7 +138,7 @@ SampleRows(IvfflatBuildState * buildstate)
* Add tuple to sort
*/
static void
AddTupleToSort(Relation index, ItemPointer tid, Datum *values, bool *isnull, IvfflatBuildState * buildstate)
AddTupleToSort(Relation index, ItemPointer tid, Datum *values, IvfflatBuildState * buildstate)
{
double distance;
double minDistance = DBL_MAX;
@@ -184,11 +184,6 @@ AddTupleToSort(Relation index, ItemPointer tid, Datum *values, bool *isnull, Ivf
slot->tts_isnull[1] = false;
slot->tts_values[2] = value;
slot->tts_isnull[2] = false;
for (int i = 1; i < buildstate->tupdesc->natts; i++)
{
slot->tts_values[2 + i] = values[i];
slot->tts_isnull[2 + i] = isnull[i];
}
ExecStoreVirtualTuple(slot);
/*
@@ -220,7 +215,7 @@ BuildCallback(Relation index, ItemPointer tid, Datum *values,
oldCtx = MemoryContextSwitchTo(buildstate->tmpCtx);
/* Add tuple to sort */
AddTupleToSort(index, tid, values, isnull, buildstate);
AddTupleToSort(index, tid, values, buildstate);
/* Reset memory context */
MemoryContextSwitchTo(oldCtx);
@@ -231,20 +226,19 @@ BuildCallback(Relation index, ItemPointer tid, Datum *values,
* Get index tuple from sort state
*/
static inline void
GetNextTuple(Tuplesortstate *sortstate, TupleDesc tupdesc, TupleTableSlot *slot, Datum *values, bool *isnull, IndexTuple *itup, int *list)
GetNextTuple(Tuplesortstate *sortstate, TupleDesc tupdesc, TupleTableSlot *slot, IndexTuple *itup, int *list)
{
if (tuplesort_gettupleslot(sortstate, true, false, slot, NULL))
{
bool unused;
Datum value;
bool isnull;
*list = DatumGetInt32(slot_getattr(slot, 1, &unused));
for (int i = 0; i < tupdesc->natts; i++)
values[i] = slot_getattr(slot, 3 + i, &isnull[i]);
*list = DatumGetInt32(slot_getattr(slot, 1, &isnull));
value = slot_getattr(slot, 3, &isnull);
/* Form the index tuple */
*itup = index_form_tuple(tupdesc, values, isnull);
(*itup)->t_tid = *((ItemPointer) DatumGetPointer(slot_getattr(slot, 2, &unused)));
*itup = index_form_tuple(tupdesc, &value, &isnull);
(*itup)->t_tid = *((ItemPointer) DatumGetPointer(slot_getattr(slot, 2, &isnull)));
}
else
*list = -1;
@@ -262,14 +256,12 @@ InsertTuples(Relation index, IvfflatBuildState * buildstate, ForkNumber forkNum)
TupleTableSlot *slot = MakeSingleTupleTableSlot(buildstate->sortdesc, &TTSOpsMinimalTuple);
TupleDesc tupdesc = buildstate->tupdesc;
Datum *values = palloc(tupdesc->natts * sizeof(Datum));
bool *isnull = palloc(tupdesc->natts * sizeof(bool));
pgstat_progress_update_param(PROGRESS_CREATEIDX_SUBPHASE, PROGRESS_IVFFLAT_PHASE_LOAD);
pgstat_progress_update_param(PROGRESS_CREATEIDX_TUPLES_TOTAL, buildstate->indtuples);
GetNextTuple(buildstate->sortstate, tupdesc, slot, values, isnull, &itup, &list);
GetNextTuple(buildstate->sortstate, tupdesc, slot, &itup, &list);
for (int i = 0; i < buildstate->centers->length; i++)
{
@@ -305,7 +297,7 @@ InsertTuples(Relation index, IvfflatBuildState * buildstate, ForkNumber forkNum)
pgstat_progress_update_param(PROGRESS_CREATEIDX_TUPLES_DONE, ++inserted);
GetNextTuple(buildstate->sortstate, tupdesc, slot, values, isnull, &itup, &list);
GetNextTuple(buildstate->sortstate, tupdesc, slot, &itup, &list);
}
insertPage = BufferGetBlockNumber(buf);
@@ -315,9 +307,6 @@ InsertTuples(Relation index, IvfflatBuildState * buildstate, ForkNumber forkNum)
/* Set the start and insert pages */
IvfflatUpdateList(index, buildstate->listInfo[i], insertPage, InvalidBlockNumber, startPage, forkNum);
}
pfree(values);
pfree(isnull);
}
/*
@@ -368,11 +357,10 @@ InitBuildState(IvfflatBuildState * buildstate, Relation heap, Relation index, In
errmsg("dimensions must be greater than one for this opclass")));
/* Create tuple description for sorting */
buildstate->sortdesc = CreateTemplateTupleDesc(2 + buildstate->tupdesc->natts);
buildstate->sortdesc = CreateTemplateTupleDesc(3);
TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) 1, "list", INT4OID, -1, 0);
TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) 2, "tid", TIDOID, -1, 0);
for (int i = 0; i < buildstate->tupdesc->natts; i++)
TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) (3 + i), NULL, buildstate->tupdesc->attrs[i].atttypid, -1, 0);
TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) 3, "vector", buildstate->tupdesc->attrs[0].atttypid, -1, 0);
buildstate->slot = MakeSingleTupleTableSlot(buildstate->sortdesc, &TTSOpsVirtual);

View File

@@ -17,13 +17,13 @@
#endif
int ivfflat_probes;
int ivfflat_iterative_search;
int ivfflat_iterative_search_max_probes;
int ivfflat_iterative_scan;
int ivfflat_max_probes;
static relopt_kind ivfflat_relopt_kind;
static const struct config_enum_entry ivfflat_iterative_search_options[] = {
{"off", IVFFLAT_ITERATIVE_SEARCH_OFF, false},
{"on", IVFFLAT_ITERATIVE_SEARCH_RELAXED, false},
static const struct config_enum_entry ivfflat_iterative_scan_options[] = {
{"off", IVFFLAT_ITERATIVE_SCAN_OFF, false},
{"relaxed_order", IVFFLAT_ITERATIVE_SCAN_RELAXED, false},
{NULL, 0, false}
};
@@ -39,15 +39,16 @@ IvfflatInit(void)
DefineCustomIntVariable("ivfflat.probes", "Sets the number of probes",
"Valid range is 1..lists.", &ivfflat_probes,
IVFFLAT_DEFAULT_PROBES, IVFFLAT_MIN_LISTS, IVFFLAT_MAX_LISTS, PGC_USERSET, 0, NULL, NULL, NULL);
IVFFLAT_DEFAULT_PROBES, IVFFLAT_MIN_LISTS, IVFFLAT_MAX_LISTS, PGC_USERSET, GUC_EXPLAIN, NULL, NULL, NULL);
DefineCustomEnumVariable("ivfflat.iterative_search", "Sets whether to use iterative search",
NULL, &ivfflat_iterative_search,
IVFFLAT_ITERATIVE_SEARCH_OFF, ivfflat_iterative_search_options, PGC_USERSET, 0, NULL, NULL, NULL);
DefineCustomEnumVariable("ivfflat.iterative_scan", "Sets the mode for iterative scans",
NULL, &ivfflat_iterative_scan,
IVFFLAT_ITERATIVE_SCAN_OFF, ivfflat_iterative_scan_options, PGC_USERSET, GUC_EXPLAIN, NULL, NULL, NULL);
DefineCustomIntVariable("ivfflat.iterative_search_max_probes", "Sets the max number of probes for iterative search",
"Zero sets to the number of lists", &ivfflat_iterative_search_max_probes,
0, 0, IVFFLAT_MAX_LISTS, PGC_USERSET, 0, NULL, NULL, NULL);
/* If this is less than probes, probes is used */
DefineCustomIntVariable("ivfflat.max_probes", "Sets the max number of probes for iterative scans",
NULL, &ivfflat_max_probes,
IVFFLAT_MAX_LISTS, IVFFLAT_MIN_LISTS, IVFFLAT_MAX_LISTS, PGC_USERSET, GUC_EXPLAIN, NULL, NULL, NULL);
MarkGUCPrefixReserved("ivfflat");
}
@@ -98,6 +99,10 @@ ivfflatcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
*indexSelectivity = 0;
*indexCorrelation = 0;
*indexPages = 0;
#if PG_VERSION_NUM >= 180000
/* See "On disable_cost" thread on pgsql-hackers */
path->path.disabled_nodes = 2;
#endif
return;
}

View File

@@ -80,14 +80,14 @@
/* Variables */
extern int ivfflat_probes;
extern int ivfflat_iterative_search;
extern int ivfflat_iterative_search_max_probes;
extern int ivfflat_iterative_scan;
extern int ivfflat_max_probes;
typedef enum IvfflatIterativeSearchType
typedef enum IvfflatIterativeScanMode
{
IVFFLAT_ITERATIVE_SEARCH_OFF,
IVFFLAT_ITERATIVE_SEARCH_RELAXED
} IvfflatIterativeSearchType;
IVFFLAT_ITERATIVE_SCAN_OFF,
IVFFLAT_ITERATIVE_SCAN_RELAXED
} IvfflatIterativeScanMode;
typedef struct VectorArrayData
{
@@ -260,6 +260,7 @@ typedef struct IvfflatScanOpaqueData
int dimensions;
bool first;
Datum value;
MemoryContext tmpCtx;
/* Sorting */
Tuplesortstate *sortstate;
@@ -278,7 +279,7 @@ typedef struct IvfflatScanOpaqueData
pairingheap *listQueue;
BlockNumber *listPages;
int listIndex;
IvfflatScanList lists[FLEXIBLE_ARRAY_MEMBER]; /* must come last */
IvfflatScanList *lists;
} IvfflatScanOpaqueData;
typedef IvfflatScanOpaqueData * IvfflatScanOpaque;

View File

@@ -78,8 +78,6 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, R
BlockNumber insertPage = InvalidBlockNumber;
ListInfo listInfo;
BlockNumber originalInsertPage;
TupleDesc tupdesc = RelationGetDescr(index);
Datum *newValues = palloc(tupdesc->natts * sizeof(Datum));
/* Detoast once for all calls */
value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
@@ -104,12 +102,8 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, R
Assert(BlockNumberIsValid(insertPage));
originalInsertPage = insertPage;
newValues[0] = value;
for (int i = 1; i < tupdesc->natts; i++)
newValues[i] = values[i];
/* Form tuple */
itup = index_form_tuple(tupdesc, newValues, isnull);
itup = index_form_tuple(RelationGetDescr(index), &value, isnull);
itup->t_tid = *heap_tid;
/* Get tuple size */

View File

@@ -10,10 +10,7 @@
#include "miscadmin.h"
#include "pgstat.h"
#include "storage/bufmgr.h"
#ifdef IVFFLAT_MEMORY
#include "utils/memutils.h"
#endif
#define GetScanList(ptr) pairingheap_container(IvfflatScanList, ph_node, ptr)
#define GetScanListConst(ptr) pairingheap_const_container(IvfflatScanList, ph_node, ptr)
@@ -174,7 +171,7 @@ GetScanItems(IndexScanDesc scan, Datum value)
}
}
if (tuples < 100 && ivfflat_iterative_search == IVFFLAT_ITERATIVE_SEARCH_OFF)
if (tuples < 100 && ivfflat_iterative_scan == IVFFLAT_ITERATIVE_SCAN_OFF)
ereport(DEBUG1,
(errmsg("index scan found few tuples"),
errdetail("Index may have been created with little data."),
@@ -221,7 +218,13 @@ GetScanValue(IndexScanDesc scan)
/* Normalize if needed */
if (so->normprocinfo != NULL)
{
MemoryContext oldCtx = MemoryContextSwitchTo(so->tmpCtx);
value = IvfflatNormValue(so->typeInfo, so->collation, value);
MemoryContextSwitchTo(oldCtx);
}
}
return value;
@@ -253,26 +256,25 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
int dimensions;
int probes = ivfflat_probes;
int maxProbes;
MemoryContext oldCtx;
scan = RelationGetIndexScan(index, nkeys, norderbys);
/* Get lists and dimensions from metapage */
IvfflatGetMetaPageInfo(index, &lists, &dimensions);
if (probes > lists)
probes = lists;
if (ivfflat_iterative_search != IVFFLAT_ITERATIVE_SEARCH_OFF)
{
if (ivfflat_iterative_search_max_probes == 0)
maxProbes = lists;
else
maxProbes = Min(ivfflat_iterative_search_max_probes, lists);
}
if (ivfflat_iterative_scan != IVFFLAT_ITERATIVE_SCAN_OFF)
maxProbes = Max(ivfflat_max_probes, probes);
else
maxProbes = probes;
so = (IvfflatScanOpaque) palloc(offsetof(IvfflatScanOpaqueData, lists) + maxProbes * sizeof(IvfflatScanList));
if (probes > lists)
probes = lists;
if (maxProbes > lists)
maxProbes = lists;
so = (IvfflatScanOpaque) palloc(sizeof(IvfflatScanOpaqueData));
so->typeInfo = IvfflatGetTypeInfo(index);
so->first = true;
so->probes = probes;
@@ -284,6 +286,12 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
so->normprocinfo = IvfflatOptionalProcInfo(index, IVFFLAT_NORM_PROC);
so->collation = index->rd_indcollation[0];
so->tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
"Ivfflat scan temporary context",
ALLOCSET_DEFAULT_SIZES);
oldCtx = MemoryContextSwitchTo(so->tmpCtx);
/* Create tuple description for sorting */
so->tupdesc = CreateTemplateTupleDesc(2);
TupleDescInitEntry(so->tupdesc, (AttrNumber) 1, "distance", FLOAT8OID, -1, 0);
@@ -306,6 +314,9 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
so->listQueue = pairingheap_allocate(CompareLists, scan);
so->listPages = palloc(maxProbes * sizeof(BlockNumber));
so->listIndex = 0;
so->lists = palloc(maxProbes * sizeof(IvfflatScanList));
MemoryContextSwitchTo(oldCtx);
scan->opaque = so;
@@ -368,8 +379,6 @@ ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
IvfflatBench("GetScanItems", GetScanItems(scan, value));
so->first = false;
so->value = value;
/* TODO clean up if we allocated a new value */
}
while (!tuplesort_gettupleslot(so->sortstate, true, false, so->mslot, NULL))
@@ -396,13 +405,10 @@ ivfflatendscan(IndexScanDesc scan)
{
IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
pairingheap_free(so->listQueue);
pfree(so->listPages);
/* Free any temporary files */
tuplesort_end(so->sortstate);
FreeAccessStrategy(so->bas);
FreeTupleDesc(so->tupdesc);
/* TODO Free vslot and mslot without freeing TupleDesc */
MemoryContextDelete(so->tmpCtx);
pfree(so);
scan->opaque = NULL;

View File

@@ -99,6 +99,32 @@ SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <+> (SELECT NULL::vector)) t2
4
(1 row)
DROP TABLE t;
-- iterative
CREATE TABLE t (val vector(3));
INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
CREATE INDEX ON t USING hnsw (val vector_l2_ops);
SET hnsw.iterative_scan = strict_order;
SET hnsw.ef_search = 1;
SELECT * FROM t ORDER BY val <-> '[3,3,3]';
val
---------
[1,2,3]
[1,1,1]
[0,0,0]
(3 rows)
SET hnsw.iterative_scan = relaxed_order;
SELECT * FROM t ORDER BY val <-> '[3,3,3]';
val
---------
[1,2,3]
[1,1,1]
[0,0,0]
(3 rows)
RESET hnsw.iterative_scan;
RESET hnsw.ef_search;
DROP TABLE t;
-- unlogged
CREATE UNLOGGED TABLE t (val vector(3));
@@ -139,4 +165,29 @@ SET hnsw.ef_search = 0;
ERROR: 0 is outside the valid range for parameter "hnsw.ef_search" (1 .. 1000)
SET hnsw.ef_search = 1001;
ERROR: 1001 is outside the valid range for parameter "hnsw.ef_search" (1 .. 1000)
SHOW hnsw.iterative_scan;
hnsw.iterative_scan
---------------------
off
(1 row)
SET hnsw.iterative_scan = on;
ERROR: invalid value for parameter "hnsw.iterative_scan": "on"
HINT: Available values: off, relaxed_order, strict_order.
SHOW hnsw.max_scan_tuples;
hnsw.max_scan_tuples
----------------------
20000
(1 row)
SET hnsw.max_scan_tuples = 0;
ERROR: 0 is outside the valid range for parameter "hnsw.max_scan_tuples" (1 .. 2147483647)
SHOW hnsw.scan_mem_multiplier;
hnsw.scan_mem_multiplier
--------------------------
1
(1 row)
SET hnsw.scan_mem_multiplier = 0;
ERROR: 0 is outside the valid range for parameter "hnsw.scan_mem_multiplier" (1 .. 1000)
DROP TABLE t;

View File

@@ -81,6 +81,37 @@ SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <=> (SELECT NULL::vector)) t2
3
(1 row)
DROP TABLE t;
-- iterative
CREATE TABLE t (val vector(3));
INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
CREATE INDEX ON t USING ivfflat (val vector_l2_ops) WITH (lists = 3);
SET ivfflat.iterative_scan = relaxed_order;
SELECT * FROM t ORDER BY val <-> '[3,3,3]';
val
---------
[1,2,3]
[1,1,1]
[0,0,0]
(3 rows)
SET ivfflat.max_probes = 1;
SELECT * FROM t ORDER BY val <-> '[3,3,3]';
val
---------
[1,2,3]
(1 row)
SET ivfflat.max_probes = 2;
SELECT * FROM t ORDER BY val <-> '[3,3,3]';
val
---------
[1,2,3]
[1,1,1]
(2 rows)
RESET ivfflat.iterative_scan;
RESET ivfflat.max_probes;
DROP TABLE t;
-- unlogged
CREATE UNLOGGED TABLE t (val vector(3));
@@ -109,4 +140,27 @@ SHOW ivfflat.probes;
1
(1 row)
SET ivfflat.probes = 0;
ERROR: 0 is outside the valid range for parameter "ivfflat.probes" (1 .. 32768)
SET ivfflat.probes = 32769;
ERROR: 32769 is outside the valid range for parameter "ivfflat.probes" (1 .. 32768)
SHOW ivfflat.iterative_scan;
ivfflat.iterative_scan
------------------------
off
(1 row)
SET ivfflat.iterative_scan = on;
ERROR: invalid value for parameter "ivfflat.iterative_scan": "on"
HINT: Available values: off, relaxed_order.
SHOW ivfflat.max_probes;
ivfflat.max_probes
--------------------
32768
(1 row)
SET ivfflat.max_probes = 0;
ERROR: 0 is outside the valid range for parameter "ivfflat.max_probes" (1 .. 32768)
SET ivfflat.max_probes = 32769;
ERROR: 32769 is outside the valid range for parameter "ivfflat.max_probes" (1 .. 32768)
DROP TABLE t;

View File

@@ -57,6 +57,23 @@ SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <+> (SELECT NULL::vector)) t2
DROP TABLE t;
-- iterative
CREATE TABLE t (val vector(3));
INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
CREATE INDEX ON t USING hnsw (val vector_l2_ops);
SET hnsw.iterative_scan = strict_order;
SET hnsw.ef_search = 1;
SELECT * FROM t ORDER BY val <-> '[3,3,3]';
SET hnsw.iterative_scan = relaxed_order;
SELECT * FROM t ORDER BY val <-> '[3,3,3]';
RESET hnsw.iterative_scan;
RESET hnsw.ef_search;
DROP TABLE t;
-- unlogged
CREATE UNLOGGED TABLE t (val vector(3));
@@ -81,4 +98,16 @@ SHOW hnsw.ef_search;
SET hnsw.ef_search = 0;
SET hnsw.ef_search = 1001;
SHOW hnsw.iterative_scan;
SET hnsw.iterative_scan = on;
SHOW hnsw.max_scan_tuples;
SET hnsw.max_scan_tuples = 0;
SHOW hnsw.scan_mem_multiplier;
SET hnsw.scan_mem_multiplier = 0;
DROP TABLE t;

View File

@@ -44,6 +44,25 @@ SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <=> (SELECT NULL::vector)) t2
DROP TABLE t;
-- iterative
CREATE TABLE t (val vector(3));
INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
CREATE INDEX ON t USING ivfflat (val vector_l2_ops) WITH (lists = 3);
SET ivfflat.iterative_scan = relaxed_order;
SELECT * FROM t ORDER BY val <-> '[3,3,3]';
SET ivfflat.max_probes = 1;
SELECT * FROM t ORDER BY val <-> '[3,3,3]';
SET ivfflat.max_probes = 2;
SELECT * FROM t ORDER BY val <-> '[3,3,3]';
RESET ivfflat.iterative_scan;
RESET ivfflat.max_probes;
DROP TABLE t;
-- unlogged
CREATE UNLOGGED TABLE t (val vector(3));
@@ -62,4 +81,16 @@ CREATE INDEX ON t USING ivfflat (val vector_l2_ops) WITH (lists = 32769);
SHOW ivfflat.probes;
SET ivfflat.probes = 0;
SET ivfflat.probes = 32769;
SHOW ivfflat.iterative_scan;
SET ivfflat.iterative_scan = on;
SHOW ivfflat.max_probes;
SET ivfflat.max_probes = 0;
SET ivfflat.max_probes = 32769;
DROP TABLE t;

View File

@@ -23,7 +23,7 @@ $node->safe_psql("postgres", "CREATE INDEX ON tst USING ivfflat (v vector_l2_ops
my $count = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
SET ivfflat.probes = 10;
SET ivfflat.iterative_search = on;
SET ivfflat.iterative_scan = relaxed_order;
SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst LIMIT 1) LIMIT 11) t;
));
is($count, 10);
@@ -39,8 +39,8 @@ foreach ((30, 50, 70))
$count = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
SET ivfflat.probes = 10;
SET ivfflat.iterative_search = on;
SET ivfflat.iterative_search_max_probes = $max_probes;
SET ivfflat.iterative_scan = relaxed_order;
SET ivfflat.max_probes = $max_probes;
SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst WHERE i = $i) LIMIT 11) t;
));
$sum += $count;

View File

@@ -19,7 +19,7 @@ sub test_recall
my $explain = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
SET ivfflat.probes = $probes;
SET ivfflat.iterative_search = on;
SET ivfflat.iterative_scan = relaxed_order;
EXPLAIN ANALYZE SELECT i FROM tst WHERE i % $c = 0 ORDER BY v $operator '$queries[0]' LIMIT $limit;
));
like($explain, qr/Index Scan using idx on tst/);
@@ -29,7 +29,7 @@ sub test_recall
my $actual = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
SET ivfflat.probes = $probes;
SET ivfflat.iterative_search = on;
SET ivfflat.iterative_scan = relaxed_order;
SELECT i FROM tst WHERE i % $c = 0 ORDER BY v $operator '$queries[$i]' LIMIT $limit;
));
my @actual_ids = split("\n", $actual);
@@ -48,7 +48,7 @@ sub test_recall
$total += $limit;
}
cmp_ok($correct / $total, ">=", $min, $operator);
cmp_ok($correct / $total, ">=", $min, "$operator $c");
}
# Initialize node
@@ -103,7 +103,7 @@ for my $i (0 .. $#operators)
if ($c == 100)
{
test_recall($c, 1, 0.58, $operator);
test_recall($c, 1, 0.57, $operator);
test_recall($c, 10, 0.98, $operator);
}
else

View File

@@ -26,8 +26,9 @@ $node->safe_psql("postgres", qq(
my $count = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
SET hnsw.iterative_search = on;
SET work_mem = '8MB';
SET hnsw.iterative_scan = relaxed_order;
SET hnsw.max_scan_tuples = 100000;
SET hnsw.scan_mem_multiplier = 2;
SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst LIMIT 1) LIMIT 11) t;
));
is($count, 10);
@@ -42,9 +43,9 @@ foreach ((30000, 50000, 70000))
{
$count = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
SET hnsw.iterative_search = on;
SET hnsw.iterative_search_max_tuples = $max_tuples;
SET work_mem = '8MB';
SET hnsw.iterative_scan = relaxed_order;
SET hnsw.max_scan_tuples = $max_tuples;
SET hnsw.scan_mem_multiplier = 2;
SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst WHERE i = $i) LIMIT 11) t;
));
$sum += $count;
@@ -57,11 +58,11 @@ foreach ((30000, 50000, 70000))
my ($ret, $stdout, $stderr) = $node->psql("postgres", qq(
SET enable_seqscan = off;
SET hnsw.iterative_search = on;
SET hnsw.iterative_scan = relaxed_order;
SET client_min_messages = debug1;
SET work_mem = '2MB';
SET work_mem = '1MB';
SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst LIMIT 1) LIMIT 11) t;
));
like($stderr, qr/hnsw index scan exceeded work_mem after \d+ tuples/);
like($stderr, qr/hnsw index scan reached memory limit after \d+ tuples/);
done_testing();

View File

@@ -10,18 +10,18 @@ my @expected;
my $limit = 20;
my $dim = 3;
my $array_sql = join(",", ('random()') x $dim);
my @cs = (100, 1000);
my @cs = (50, 500);
sub test_recall
{
my ($c, $ef_search, $min, $operator) = @_;
my ($c, $ef_search, $min, $operator, $mode) = @_;
my $correct = 0;
my $total = 0;
my $explain = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
SET hnsw.ef_search = $ef_search;
SET hnsw.iterative_search = on;
SET hnsw.iterative_scan = $mode;
EXPLAIN ANALYZE SELECT i FROM tst WHERE i % $c = 0 ORDER BY v $operator '$queries[0]' LIMIT $limit;
));
like($explain, qr/Index Scan using idx on tst/);
@@ -31,7 +31,7 @@ sub test_recall
my $actual = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
SET hnsw.ef_search = $ef_search;
SET hnsw.iterative_search = on;
SET hnsw.iterative_scan = $mode;
SELECT i FROM tst WHERE i % $c = 0 ORDER BY v $operator '$queries[$i]' LIMIT $limit;
));
my @actual_ids = split("\n", $actual);
@@ -50,7 +50,7 @@ sub test_recall
$total += $limit;
}
cmp_ok($correct / $total, ">=", $min, $operator);
cmp_ok($correct / $total, ">=", $min, "$operator $mode $c");
}
# Initialize node
@@ -62,7 +62,7 @@ $node->start;
$node->safe_psql("postgres", "CREATE EXTENSION vector;");
$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim));");
$node->safe_psql("postgres",
"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 100000) i;"
"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 50000) i;"
);
# Generate queries
@@ -108,21 +108,8 @@ for my $i (0 .. $#operators)
push(@expected, $res);
}
if ($c == 100)
{
test_recall($c, 40, 0.99, $operator);
}
else
{
if ($operator eq "<->")
{
test_recall($c, 40, 0.99, $operator);
}
else
{
test_recall($c, 40, 0.99, $operator);
}
}
test_recall($c, 40, 0.99, $operator, "strict_order");
test_recall($c, 40, 0.99, $operator, "relaxed_order");
}
$node->safe_psql("postgres", "DROP INDEX idx;");

View File

@@ -1,113 +0,0 @@
use strict;
use warnings FATAL => 'all';
use PostgreSQL::Test::Cluster;
use PostgreSQL::Test::Utils;
use Test::More;
my $node;
my @queries = ();
my @cs = ();
my @expected;
my $limit = 20;
my $dim = 3;
my $array_sql = join(",", ('random()') x $dim);
my $nc = 1000;
sub test_recall
{
my ($min, $operator) = @_;
my $correct = 0;
my $total = 0;
my $explain = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
EXPLAIN ANALYZE SELECT i FROM tst WHERE c = $cs[0] ORDER BY v $operator '$queries[0]' LIMIT $limit;
));
like($explain, qr/Index Cond/);
for my $i (0 .. $#queries)
{
my $actual = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
SELECT i FROM tst WHERE c = $cs[$i] ORDER BY v $operator '$queries[$i]' LIMIT $limit;
));
my @actual_ids = split("\n", $actual);
my %actual_set = map { $_ => 1 } @actual_ids;
is(scalar(@actual_ids), $limit);
my @expected_ids = split("\n", $expected[$i]);
foreach (@expected_ids)
{
if (exists($actual_set{$_}))
{
$correct++;
}
$total++;
}
}
cmp_ok($correct / $total, ">=", $min, $operator);
}
# Initialize node
$node = PostgreSQL::Test::Cluster->new('node');
$node->init;
$node->start;
# Create table
$node->safe_psql("postgres", "CREATE EXTENSION vector;");
$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim), c int4);");
$node->safe_psql("postgres",
"INSERT INTO tst SELECT i, ARRAY[$array_sql], i % $nc FROM generate_series(1, 20000) i;"
);
# Generate queries
for (1 .. 20)
{
my @r = ();
for (1 .. $dim)
{
push(@r, rand());
}
push(@queries, "[" . join(",", @r) . "]");
push(@cs, int(rand() * $nc));
}
# Get exact results
@expected = ();
for my $i (0 .. $#queries)
{
my $res = $node->safe_psql("postgres", "SELECT i FROM tst WHERE c = $cs[$i] ORDER BY v <=> '$queries[$i]' LIMIT $limit;");
push(@expected, $res);
}
# Add index
$node->safe_psql("postgres", qq(
SET maintenance_work_mem = '256MB';
SET max_parallel_maintenance_workers = 2;
CREATE INDEX ON tst USING hnsw (v vector_cosine_ops, c);
));
# Test recall
test_recall(0.99, '<=>');
# Test vacuum
$node->safe_psql("postgres", "DELETE FROM tst WHERE c > 5;");
$node->safe_psql("postgres", "VACUUM tst;");
# Test columns
my ($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING hnsw (c);");
like($stderr, qr/first column must be a vector/);
($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING hnsw (c, v vector_cosine_ops);");
like($stderr, qr/first column must be a vector/);
($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING hnsw (v vector_cosine_ops, c, c);");
like($stderr, qr/index cannot have more than two columns/);
($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING hnsw (v vector_cosine_ops, v vector_cosine_ops);");
like($stderr, qr/column 2 cannot be a vector/);
done_testing();