mirror of
https://github.com/pgvector/pgvector.git
synced 2026-07-22 03:57:34 +08:00
Compare commits
1 Commits
hnsw-strea
...
ivfflat-co
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
0f36e15bea |
@@ -1,9 +1,7 @@
|
||||
## 0.8.0 (unreleased)
|
||||
|
||||
- Added support for iterative index scans
|
||||
- Added casts for arrays to `sparsevec`
|
||||
- Improved cost estimation
|
||||
- Improved performance of HNSW inserts and on-disk index builds
|
||||
- Reduced memory usage for HNSW index scans
|
||||
- Dropped support for Postgres 12
|
||||
|
||||
|
||||
71
README.md
71
README.md
@@ -451,77 +451,6 @@ 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 Search [unreleased]
|
||||
|
||||
*Added in 0.8.0*
|
||||
|
||||
With approximate indexes, you can end up with less results than expected due to filtering conditions in the query.
|
||||
|
||||
Starting with 0.8.0, you can enable iterative search. If too few results from the initial index scan match the query filters, it will resume scanning until enough results are found. This can significantly improve recall (at the cost of speed).
|
||||
|
||||
```tsql
|
||||
SET hnsw.streaming = on;
|
||||
-- or
|
||||
SET ivfflat.streaming = on;
|
||||
```
|
||||
|
||||
However, there are some important caveats.
|
||||
|
||||
### Iterative Caveats
|
||||
|
||||
With iterative search, it’s possible for rows to be slightly out of order by distance. For strict ordering, use:
|
||||
|
||||
```sql
|
||||
WITH approx_order AS MATERIALIZED (
|
||||
SELECT *, embedding <-> '[1,2,3]' AS distance FROM items WHERE ... ORDER BY distance LIMIT 5
|
||||
) SELECT * FROM approx_order ORDER BY distance;
|
||||
```
|
||||
|
||||
For distance filters, use a CTE and place the filter outside it.
|
||||
|
||||
```sql
|
||||
WITH approx_order AS MATERIALIZED (
|
||||
SELECT *, embedding <-> '[1,2,3]' AS distance FROM items WHERE ... ORDER BY distance LIMIT 5
|
||||
) SELECT * FROM approx_order WHERE distance < 0.1 ORDER BY distance;
|
||||
```
|
||||
|
||||
### Iterative Options
|
||||
|
||||
Since scanning a large portion of the index is expensive, there are options to control when the scan ends.
|
||||
|
||||
#### HNSW
|
||||
|
||||
Specify the max number of additional tuples visited
|
||||
|
||||
```sql
|
||||
SET hnsw.ef_stream = 10000;
|
||||
```
|
||||
|
||||
The scan will also end if reaches `work_mem`. You can see when this happens by enabling debug messages.
|
||||
|
||||
```sql
|
||||
SET client_min_messages = debug1;
|
||||
```
|
||||
|
||||
```text
|
||||
DEBUG: hnsw index scan exceeded work_mem after 10000 tuples
|
||||
HINT: Increase work_mem to scan more tuples.
|
||||
```
|
||||
|
||||
If the server has enough memory, you can adjust this with:
|
||||
|
||||
```sql
|
||||
SET work_mem = '8MB';
|
||||
```
|
||||
|
||||
#### IVFFlat
|
||||
|
||||
Specify the max number of probes
|
||||
|
||||
```sql
|
||||
SET ivfflat.max_probes = 100;
|
||||
```
|
||||
|
||||
## Half-Precision Vectors
|
||||
|
||||
*Added in 0.7.0*
|
||||
|
||||
62
src/hnsw.c
62
src/hnsw.c
@@ -18,18 +18,7 @@
|
||||
#define MarkGUCPrefixReserved(x) EmitWarningsOnPlaceholders(x)
|
||||
#endif
|
||||
|
||||
static const struct config_enum_entry hnsw_iterative_search_options[] = {
|
||||
{"off", HNSW_ITERATIVE_SEARCH_OFF, false},
|
||||
{"strict", HNSW_ITERATIVE_SEARCH_STRICT, false},
|
||||
{"relaxed", HNSW_ITERATIVE_SEARCH_RELAXED, false},
|
||||
/* TODO Change to strict before merging */
|
||||
{"on", HNSW_ITERATIVE_SEARCH_RELAXED, false},
|
||||
{NULL, 0, false}
|
||||
};
|
||||
|
||||
int hnsw_ef_search;
|
||||
int hnsw_max_iterative_tuples;
|
||||
int hnsw_iterative_search;
|
||||
int hnsw_lock_tranche_id;
|
||||
static relopt_kind hnsw_relopt_kind;
|
||||
|
||||
@@ -80,17 +69,6 @@ HnswInit(void)
|
||||
"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);
|
||||
|
||||
/* TODO Change name */
|
||||
DefineCustomEnumVariable("hnsw.streaming", "Iterative search mode",
|
||||
NULL, &hnsw_iterative_search,
|
||||
HNSW_ITERATIVE_SEARCH_OFF, hnsw_iterative_search_options, PGC_USERSET, 0, NULL, NULL, NULL);
|
||||
|
||||
/* TODO Change name */
|
||||
/* TODO Ensure ivfflat.max_probes uses same value for "all" */
|
||||
DefineCustomIntVariable("hnsw.ef_stream", "Sets the max number of additional candidates to visit for streaming search",
|
||||
"-1 means all", &hnsw_max_iterative_tuples,
|
||||
HNSW_DEFAULT_EF_STREAM, HNSW_MIN_EF_STREAM, HNSW_MAX_EF_STREAM, PGC_USERSET, 0, NULL, NULL, NULL);
|
||||
|
||||
MarkGUCPrefixReserved("hnsw");
|
||||
}
|
||||
|
||||
@@ -122,8 +100,10 @@ hnswcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
|
||||
{
|
||||
GenericCosts costs;
|
||||
int m;
|
||||
double ratio;
|
||||
double startupPages;
|
||||
int entryLevel;
|
||||
int layer0TuplesMax;
|
||||
double layer0Selectivity;
|
||||
double scalingFactor = 0.55;
|
||||
double spc_seq_page_cost;
|
||||
Relation index;
|
||||
|
||||
@@ -140,8 +120,6 @@ hnswcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
|
||||
|
||||
MemSet(&costs, 0, sizeof(costs));
|
||||
|
||||
genericcostestimate(root, path, loop_count, &costs);
|
||||
|
||||
index = index_open(path->indexinfo->indexoid, NoLock);
|
||||
HnswGetMetaPageInfo(index, &m, NULL);
|
||||
index_close(index, NoLock);
|
||||
@@ -173,38 +151,30 @@ hnswcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
|
||||
* at L0, accounting for previously visited tuples, multiplied by the
|
||||
* "scalingFactor" (currently hardcoded).
|
||||
*/
|
||||
if (path->indexinfo->tuples > 0)
|
||||
{
|
||||
double scalingFactor = 0.55;
|
||||
int entryLevel = (int) (log(path->indexinfo->tuples) * HnswGetMl(m));
|
||||
int layer0TuplesMax = HnswGetLayerM(m, 0) * hnsw_ef_search;
|
||||
double layer0Selectivity = scalingFactor * log(path->indexinfo->tuples) / (log(m) * (1 + log(hnsw_ef_search)));
|
||||
entryLevel = (int) (log(path->indexinfo->tuples + 1) * HnswGetMl(m));
|
||||
layer0TuplesMax = HnswGetLayerM(m, 0) * hnsw_ef_search;
|
||||
layer0Selectivity = (scalingFactor * log(path->indexinfo->tuples + 1)) /
|
||||
(log(m) * (1 + log(hnsw_ef_search)));
|
||||
|
||||
ratio = (entryLevel * m + layer0TuplesMax * layer0Selectivity) / path->indexinfo->tuples;
|
||||
costs.numIndexTuples = (entryLevel * m) +
|
||||
(layer0TuplesMax * layer0Selectivity);
|
||||
|
||||
if (ratio > 1)
|
||||
ratio = 1;
|
||||
}
|
||||
else
|
||||
ratio = 1;
|
||||
genericcostestimate(root, path, loop_count, &costs);
|
||||
|
||||
get_tablespace_page_costs(path->indexinfo->reltablespace, NULL, &spc_seq_page_cost);
|
||||
|
||||
/* Startup cost is cost before returning the first row */
|
||||
costs.indexStartupCost = costs.indexTotalCost * ratio;
|
||||
|
||||
/* Adjust cost if needed since TOAST not included in seq scan cost */
|
||||
startupPages = costs.numIndexPages * ratio;
|
||||
if (startupPages > path->indexinfo->rel->pages && ratio < 0.5)
|
||||
if (costs.numIndexPages > path->indexinfo->rel->pages)
|
||||
{
|
||||
/* Change all page cost from random to sequential */
|
||||
costs.indexStartupCost -= startupPages * (costs.spc_random_page_cost - spc_seq_page_cost);
|
||||
costs.indexTotalCost -= costs.numIndexPages * (costs.spc_random_page_cost - spc_seq_page_cost);
|
||||
|
||||
/* Remove cost of extra pages */
|
||||
costs.indexStartupCost -= (startupPages - path->indexinfo->rel->pages) * spc_seq_page_cost;
|
||||
costs.indexTotalCost -= (costs.numIndexPages - path->indexinfo->rel->pages) * spc_seq_page_cost;
|
||||
}
|
||||
|
||||
*indexStartupCost = costs.indexStartupCost;
|
||||
/* Use total cost since most work happens before first tuple is returned */
|
||||
*indexStartupCost = costs.indexTotalCost;
|
||||
*indexTotalCost = costs.indexTotalCost;
|
||||
*indexSelectivity = costs.indexSelectivity;
|
||||
*indexCorrelation = costs.indexCorrelation;
|
||||
|
||||
91
src/hnsw.h
91
src/hnsw.h
@@ -42,9 +42,6 @@
|
||||
#define HNSW_DEFAULT_EF_SEARCH 40
|
||||
#define HNSW_MIN_EF_SEARCH 1
|
||||
#define HNSW_MAX_EF_SEARCH 1000
|
||||
#define HNSW_DEFAULT_EF_STREAM -1
|
||||
#define HNSW_MIN_EF_STREAM -1
|
||||
#define HNSW_MAX_EF_STREAM INT_MAX
|
||||
|
||||
/* Tuple types */
|
||||
#define HNSW_ELEMENT_TUPLE_TYPE 1
|
||||
@@ -91,9 +88,6 @@
|
||||
/* Ensure fits on page and in uint8 */
|
||||
#define HnswGetMaxLevel(m) Min(((BLCKSZ - MAXALIGN(SizeOfPageHeaderData) - MAXALIGN(sizeof(HnswPageOpaqueData)) - offsetof(HnswNeighborTupleData, indextids) - sizeof(ItemIdData)) / (sizeof(ItemPointerData)) / (m)) - 2, 255)
|
||||
|
||||
#define HnswGetSearchCandidate(membername, ptr) pairingheap_container(HnswSearchCandidate, membername, ptr)
|
||||
#define HnswGetSearchCandidateConst(membername, ptr) pairingheap_const_container(HnswSearchCandidate, membername, ptr)
|
||||
|
||||
#define HnswGetValue(base, element) PointerGetDatum(HnswPtrAccess(base, (element)->value))
|
||||
|
||||
#if PG_VERSION_NUM < 140005
|
||||
@@ -112,17 +106,8 @@
|
||||
|
||||
/* Variables */
|
||||
extern int hnsw_ef_search;
|
||||
extern int hnsw_max_iterative_tuples;
|
||||
extern int hnsw_iterative_search;
|
||||
extern int hnsw_lock_tranche_id;
|
||||
|
||||
typedef enum HnswIterativeSearchType
|
||||
{
|
||||
HNSW_ITERATIVE_SEARCH_OFF,
|
||||
HNSW_ITERATIVE_SEARCH_STRICT,
|
||||
HNSW_ITERATIVE_SEARCH_RELAXED
|
||||
} HnswIterativeSearchType;
|
||||
|
||||
typedef struct HnswElementData HnswElementData;
|
||||
typedef struct HnswNeighborArray HnswNeighborArray;
|
||||
|
||||
@@ -144,7 +129,6 @@ struct HnswElementData
|
||||
uint8 heaptidsLength;
|
||||
uint8 level;
|
||||
uint8 deleted;
|
||||
uint8 version;
|
||||
uint32 hash;
|
||||
HnswNeighborsPtr neighbors;
|
||||
BlockNumber blkno;
|
||||
@@ -176,7 +160,7 @@ typedef struct HnswSearchCandidate
|
||||
pairingheap_node c_node;
|
||||
pairingheap_node w_node;
|
||||
HnswElementPtr element;
|
||||
double distance;
|
||||
float distance;
|
||||
} HnswSearchCandidate;
|
||||
|
||||
/* HNSW index options */
|
||||
@@ -201,8 +185,8 @@ typedef struct HnswGraph
|
||||
|
||||
/* Allocations state */
|
||||
LWLock allocatorLock;
|
||||
Size memoryUsed;
|
||||
Size memoryTotal;
|
||||
long memoryUsed;
|
||||
long memoryTotal;
|
||||
|
||||
/* Flushed state */
|
||||
LWLock flushLock;
|
||||
@@ -253,18 +237,6 @@ typedef struct HnswTypeInfo
|
||||
void (*checkValue) (Pointer v);
|
||||
} HnswTypeInfo;
|
||||
|
||||
typedef struct HnswSupport
|
||||
{
|
||||
FmgrInfo *procinfo;
|
||||
FmgrInfo *normprocinfo;
|
||||
Oid collation;
|
||||
} HnswSupport;
|
||||
|
||||
typedef struct HnswQuery
|
||||
{
|
||||
Datum value;
|
||||
} HnswQuery;
|
||||
|
||||
typedef struct HnswBuildState
|
||||
{
|
||||
/* Info */
|
||||
@@ -284,7 +256,9 @@ typedef struct HnswBuildState
|
||||
double reltuples;
|
||||
|
||||
/* Support functions */
|
||||
HnswSupport support;
|
||||
FmgrInfo *procinfo;
|
||||
FmgrInfo *normprocinfo;
|
||||
Oid collation;
|
||||
|
||||
/* Variables */
|
||||
HnswGraph graphData;
|
||||
@@ -332,10 +306,10 @@ typedef struct HnswElementTupleData
|
||||
uint8 type;
|
||||
uint8 level;
|
||||
uint8 deleted;
|
||||
uint8 version;
|
||||
uint8 unused;
|
||||
ItemPointerData heaptids[HNSW_HEAPTIDS];
|
||||
ItemPointerData neighbortid;
|
||||
uint16 unused;
|
||||
uint16 unused2;
|
||||
Vector data;
|
||||
} HnswElementTupleData;
|
||||
|
||||
@@ -344,41 +318,24 @@ typedef HnswElementTupleData * HnswElementTuple;
|
||||
typedef struct HnswNeighborTupleData
|
||||
{
|
||||
uint8 type;
|
||||
uint8 version;
|
||||
uint8 unused;
|
||||
uint16 count;
|
||||
ItemPointerData indextids[FLEXIBLE_ARRAY_MEMBER];
|
||||
} HnswNeighborTupleData;
|
||||
|
||||
typedef HnswNeighborTupleData * HnswNeighborTuple;
|
||||
|
||||
typedef union
|
||||
{
|
||||
struct pointerhash_hash *pointers;
|
||||
struct offsethash_hash *offsets;
|
||||
struct tidhash_hash *tids;
|
||||
} visited_hash;
|
||||
|
||||
typedef union
|
||||
{
|
||||
HnswElement element;
|
||||
ItemPointerData indextid;
|
||||
} HnswUnvisited;
|
||||
|
||||
typedef struct HnswScanOpaqueData
|
||||
{
|
||||
const HnswTypeInfo *typeInfo;
|
||||
bool first;
|
||||
List *w;
|
||||
visited_hash v;
|
||||
pairingheap *discarded;
|
||||
HnswQuery q;
|
||||
int m;
|
||||
int64 tuples;
|
||||
double previousDistance;
|
||||
MemoryContext tmpCtx;
|
||||
|
||||
/* Support functions */
|
||||
HnswSupport support;
|
||||
FmgrInfo *procinfo;
|
||||
FmgrInfo *normprocinfo;
|
||||
Oid collation;
|
||||
} HnswScanOpaqueData;
|
||||
|
||||
typedef HnswScanOpaqueData * HnswScanOpaque;
|
||||
@@ -396,7 +353,8 @@ typedef struct HnswVacuumState
|
||||
int efConstruction;
|
||||
|
||||
/* Support functions */
|
||||
HnswSupport support;
|
||||
FmgrInfo *procinfo;
|
||||
Oid collation;
|
||||
|
||||
/* Variables */
|
||||
struct tidhash_hash *deleted;
|
||||
@@ -412,33 +370,30 @@ typedef struct HnswVacuumState
|
||||
int HnswGetM(Relation index);
|
||||
int HnswGetEfConstruction(Relation index);
|
||||
FmgrInfo *HnswOptionalProcInfo(Relation index, uint16 procnum);
|
||||
void HnswInitSupport(HnswSupport * support, Relation index);
|
||||
Datum HnswNormValue(const HnswTypeInfo * typeInfo, Oid collation, Datum value);
|
||||
bool HnswCheckNorm(HnswSupport * support, Datum value);
|
||||
bool HnswCheckNorm(FmgrInfo *procinfo, Oid collation, 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, visited_hash * v, pairingheap **discarded, bool initVisited, int64 *tuples);
|
||||
List *HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement);
|
||||
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);
|
||||
HnswSearchCandidate *HnswEntryCandidate(char *base, HnswElement em, HnswQuery * q, Relation rel, HnswSupport * support, bool loadVec);
|
||||
void HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo *procinfo, Oid collation, int m, int efConstruction, bool existing);
|
||||
HnswSearchCandidate *HnswEntryCandidate(char *base, HnswElement em, Datum q, Relation rel, FmgrInfo *procinfo, Oid collation, 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, Datum value, ItemPointer heaptid, bool building);
|
||||
void HnswUpdateNeighborsOnDisk(Relation index, HnswSupport * support, HnswElement e, int m, bool checkExisting, bool building);
|
||||
bool HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull, ItemPointer heap_tid, bool building);
|
||||
void HnswUpdateNeighborsOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting, bool building);
|
||||
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 HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec, float *maxDistance);
|
||||
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 HnswLoadNeighborTids(HnswElement element, ItemPointerData *indextids, Relation index, int m, int lm, int lc);
|
||||
void HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int lm, int lc, int *updateIdx, Relation index, FmgrInfo *procinfo, Oid collation);
|
||||
void HnswLoadNeighbors(HnswElement element, Relation index, int m);
|
||||
void HnswInitLockTranche(void);
|
||||
const HnswTypeInfo *HnswGetTypeInfo(Relation index);
|
||||
PGDLLEXPORT void HnswParallelBuildMain(dsm_segment *seg, shm_toc *toc);
|
||||
|
||||
@@ -366,7 +366,7 @@ AddElementInMemory(char *base, HnswGraph * graph, HnswElement element)
|
||||
* Update neighbors
|
||||
*/
|
||||
static void
|
||||
UpdateNeighborsInMemory(char *base, HnswSupport * support, HnswElement e, int m)
|
||||
UpdateNeighborsInMemory(char *base, FmgrInfo *procinfo, Oid collation, HnswElement e, int m)
|
||||
{
|
||||
for (int lc = e->level; lc >= 0; lc--)
|
||||
{
|
||||
@@ -388,7 +388,7 @@ UpdateNeighborsInMemory(char *base, HnswSupport * support, HnswElement e, int m)
|
||||
Assert(neighborElement);
|
||||
|
||||
LWLockAcquire(&neighborElement->lock, LW_EXCLUSIVE);
|
||||
HnswUpdateConnection(base, HnswGetNeighbors(base, neighborElement, lc), e, hc->distance, lm, NULL, NULL, support);
|
||||
HnswUpdateConnection(base, e, hc, lm, lc, NULL, NULL, procinfo, collation);
|
||||
LWLockRelease(&neighborElement->lock);
|
||||
}
|
||||
}
|
||||
@@ -398,7 +398,7 @@ UpdateNeighborsInMemory(char *base, HnswSupport * support, HnswElement e, int m)
|
||||
* Update graph in memory
|
||||
*/
|
||||
static void
|
||||
UpdateGraphInMemory(HnswSupport * support, HnswElement element, int m, int efConstruction, HnswElement entryPoint, HnswBuildState * buildstate)
|
||||
UpdateGraphInMemory(FmgrInfo *procinfo, Oid collation, HnswElement element, int m, int efConstruction, HnswElement entryPoint, HnswBuildState * buildstate)
|
||||
{
|
||||
HnswGraph *graph = buildstate->graph;
|
||||
char *base = buildstate->hnswarea;
|
||||
@@ -411,7 +411,7 @@ UpdateGraphInMemory(HnswSupport * support, HnswElement element, int m, int efCon
|
||||
AddElementInMemory(base, graph, element);
|
||||
|
||||
/* Update neighbors */
|
||||
UpdateNeighborsInMemory(base, support, element, m);
|
||||
UpdateNeighborsInMemory(base, procinfo, collation, element, m);
|
||||
|
||||
/* Update entry point if needed (already have lock) */
|
||||
if (entryPoint == NULL || element->level > entryPoint->level)
|
||||
@@ -424,8 +424,9 @@ UpdateGraphInMemory(HnswSupport * support, HnswElement element, int m, int efCon
|
||||
static void
|
||||
InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element)
|
||||
{
|
||||
FmgrInfo *procinfo = buildstate->procinfo;
|
||||
Oid collation = buildstate->collation;
|
||||
HnswGraph *graph = buildstate->graph;
|
||||
HnswSupport *support = &buildstate->support;
|
||||
HnswElement entryPoint;
|
||||
LWLock *entryLock = &graph->entryLock;
|
||||
LWLock *entryWaitLock = &graph->entryWaitLock;
|
||||
@@ -457,10 +458,10 @@ InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element)
|
||||
}
|
||||
|
||||
/* Find neighbors for element */
|
||||
HnswFindElementNeighbors(base, element, entryPoint, NULL, support, m, efConstruction, false);
|
||||
HnswFindElementNeighbors(base, element, entryPoint, NULL, procinfo, collation, m, efConstruction, false);
|
||||
|
||||
/* Update graph in memory */
|
||||
UpdateGraphInMemory(support, element, m, efConstruction, entryPoint, buildstate);
|
||||
UpdateGraphInMemory(procinfo, collation, element, m, efConstruction, entryPoint, buildstate);
|
||||
|
||||
/* Release entry lock */
|
||||
LWLockRelease(entryLock);
|
||||
@@ -472,19 +473,30 @@ InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element)
|
||||
static bool
|
||||
InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, HnswBuildState * buildstate)
|
||||
{
|
||||
const HnswTypeInfo *typeInfo = buildstate->typeInfo;
|
||||
HnswGraph *graph = buildstate->graph;
|
||||
HnswElement element;
|
||||
HnswAllocator *allocator = &buildstate->allocator;
|
||||
HnswSupport *support = &buildstate->support;
|
||||
Size valueSize;
|
||||
Pointer valuePtr;
|
||||
LWLock *flushLock = &graph->flushLock;
|
||||
char *base = buildstate->hnswarea;
|
||||
Datum value;
|
||||
|
||||
/* Form index value */
|
||||
if (!HnswFormIndexValue(&value, values, isnull, buildstate->typeInfo, support))
|
||||
return false;
|
||||
/* Detoast once for all calls */
|
||||
Datum value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
|
||||
|
||||
/* Check value */
|
||||
if (typeInfo->checkValue != NULL)
|
||||
typeInfo->checkValue(DatumGetPointer(value));
|
||||
|
||||
/* Normalize if needed */
|
||||
if (buildstate->normprocinfo != NULL)
|
||||
{
|
||||
if (!HnswCheckNorm(buildstate->normprocinfo, buildstate->collation, value))
|
||||
return false;
|
||||
|
||||
value = HnswNormValue(typeInfo, buildstate->collation, value);
|
||||
}
|
||||
|
||||
/* Get datum size */
|
||||
valueSize = VARSIZE_ANY(DatumGetPointer(value));
|
||||
@@ -497,7 +509,7 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
|
||||
{
|
||||
LWLockRelease(flushLock);
|
||||
|
||||
return HnswInsertTupleOnDisk(index, support, value, heaptid, true);
|
||||
return HnswInsertTupleOnDisk(index, value, values, isnull, heaptid, true);
|
||||
}
|
||||
|
||||
/*
|
||||
@@ -529,7 +541,7 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
|
||||
|
||||
LWLockRelease(flushLock);
|
||||
|
||||
return HnswInsertTupleOnDisk(index, support, value, heaptid, true);
|
||||
return HnswInsertTupleOnDisk(index, value, values, isnull, heaptid, true);
|
||||
}
|
||||
|
||||
/* Ok, we can proceed to allocate the element */
|
||||
@@ -595,7 +607,7 @@ BuildCallback(Relation index, ItemPointer tid, Datum *values,
|
||||
* Initialize the graph
|
||||
*/
|
||||
static void
|
||||
InitGraph(HnswGraph * graph, char *base, Size memoryTotal)
|
||||
InitGraph(HnswGraph * graph, char *base, long memoryTotal)
|
||||
{
|
||||
/* Initialize the lock tranche if needed */
|
||||
HnswInitLockTranche();
|
||||
@@ -692,9 +704,11 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
|
||||
buildstate->indtuples = 0;
|
||||
|
||||
/* Get support functions */
|
||||
HnswInitSupport(&buildstate->support, index);
|
||||
buildstate->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
|
||||
buildstate->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
|
||||
buildstate->collation = index->rd_indcollation[0];
|
||||
|
||||
InitGraph(&buildstate->graphData, NULL, (Size) maintenance_work_mem * 1024L);
|
||||
InitGraph(&buildstate->graphData, NULL, maintenance_work_mem * 1024L);
|
||||
buildstate->graph = &buildstate->graphData;
|
||||
buildstate->ml = HnswGetMl(buildstate->m);
|
||||
buildstate->maxLevel = HnswGetMaxLevel(buildstate->m);
|
||||
|
||||
319
src/hnswinsert.c
319
src/hnswinsert.c
@@ -36,7 +36,7 @@ GetInsertPage(Relation index)
|
||||
* Check for a free offset
|
||||
*/
|
||||
static bool
|
||||
HnswFreeOffset(Relation index, Buffer buf, Page page, HnswElement element, Size etupSize, Size ntupSize, Buffer *nbuf, Page *npage, OffsetNumber *freeOffno, OffsetNumber *freeNeighborOffno, BlockNumber *newInsertPage, uint8 *tupleVersion)
|
||||
HnswFreeOffset(Relation index, Buffer buf, Page page, HnswElement element, Size etupSize, Size ntupSize, Buffer *nbuf, Page *npage, OffsetNumber *freeOffno, OffsetNumber *freeNeighborOffno, BlockNumber *newInsertPage)
|
||||
{
|
||||
OffsetNumber offno;
|
||||
OffsetNumber maxoffno = PageGetMaxOffsetNumber(page);
|
||||
@@ -98,7 +98,6 @@ HnswFreeOffset(Relation index, Buffer buf, Page page, HnswElement element, Size
|
||||
{
|
||||
*freeOffno = offno;
|
||||
*freeNeighborOffno = neighborOffno;
|
||||
*tupleVersion = etup->version;
|
||||
return true;
|
||||
}
|
||||
else if (*nbuf != buf)
|
||||
@@ -154,7 +153,6 @@ AddElementOnDisk(Relation index, HnswElement e, int m, BlockNumber insertPage, B
|
||||
OffsetNumber freeOffno = InvalidOffsetNumber;
|
||||
OffsetNumber freeNeighborOffno = InvalidOffsetNumber;
|
||||
BlockNumber newInsertPage = InvalidBlockNumber;
|
||||
uint8 tupleVersion;
|
||||
char *base = NULL;
|
||||
|
||||
/* Calculate sizes */
|
||||
@@ -204,7 +202,7 @@ AddElementOnDisk(Relation index, HnswElement e, int m, BlockNumber insertPage, B
|
||||
}
|
||||
|
||||
/* Next, try space from a deleted element */
|
||||
if (HnswFreeOffset(index, buf, page, e, etupSize, ntupSize, &nbuf, &npage, &freeOffno, &freeNeighborOffno, &newInsertPage, &tupleVersion))
|
||||
if (HnswFreeOffset(index, buf, page, e, etupSize, ntupSize, &nbuf, &npage, &freeOffno, &freeNeighborOffno, &newInsertPage))
|
||||
{
|
||||
if (nbuf != buf)
|
||||
{
|
||||
@@ -214,10 +212,6 @@ AddElementOnDisk(Relation index, HnswElement e, int m, BlockNumber insertPage, B
|
||||
npage = GenericXLogRegisterBuffer(state, nbuf, 0);
|
||||
}
|
||||
|
||||
/* Set tuple version */
|
||||
etup->version = tupleVersion;
|
||||
ntup->version = tupleVersion;
|
||||
|
||||
break;
|
||||
}
|
||||
|
||||
@@ -340,107 +334,6 @@ AddElementOnDisk(Relation index, HnswElement e, int m, BlockNumber insertPage, B
|
||||
*updatedInsertPage = newInsertPage;
|
||||
}
|
||||
|
||||
/*
|
||||
* Load neighbors
|
||||
*/
|
||||
static HnswNeighborArray *
|
||||
HnswLoadNeighbors(HnswElement element, Relation index, int m, int lm, int lc)
|
||||
{
|
||||
char *base = NULL;
|
||||
HnswNeighborArray *neighbors = HnswInitNeighborArray(lm, NULL);
|
||||
ItemPointerData indextids[HNSW_MAX_M * 2];
|
||||
|
||||
if (!HnswLoadNeighborTids(element, indextids, index, m, lm, lc))
|
||||
return neighbors;
|
||||
|
||||
for (int i = 0; i < lm; i++)
|
||||
{
|
||||
ItemPointer indextid = &indextids[i];
|
||||
HnswElement e;
|
||||
HnswCandidate *hc;
|
||||
|
||||
if (!ItemPointerIsValid(indextid))
|
||||
break;
|
||||
|
||||
e = HnswInitElementFromBlock(ItemPointerGetBlockNumber(indextid), ItemPointerGetOffsetNumber(indextid));
|
||||
hc = &neighbors->items[neighbors->length++];
|
||||
HnswPtrStore(base, hc->element, e);
|
||||
}
|
||||
|
||||
return neighbors;
|
||||
}
|
||||
|
||||
/*
|
||||
* Load elements for insert
|
||||
*/
|
||||
static void
|
||||
LoadElementsForInsert(HnswNeighborArray * neighbors, HnswQuery * q, int *idx, Relation index, HnswSupport * support)
|
||||
{
|
||||
char *base = NULL;
|
||||
|
||||
for (int i = 0; i < neighbors->length; i++)
|
||||
{
|
||||
HnswCandidate *hc = &neighbors->items[i];
|
||||
HnswElement element = HnswPtrAccess(base, hc->element);
|
||||
double distance;
|
||||
|
||||
HnswLoadElement(element, &distance, q, index, support, true, NULL);
|
||||
hc->distance = distance;
|
||||
|
||||
/* Prune element if being deleted */
|
||||
if (element->heaptidsLength == 0)
|
||||
{
|
||||
*idx = i;
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
* Get update index
|
||||
*/
|
||||
static int
|
||||
GetUpdateIndex(HnswElement element, HnswElement newElement, float distance, int m, int lm, int lc, Relation index, HnswSupport * support, MemoryContext updateCtx)
|
||||
{
|
||||
char *base = NULL;
|
||||
int idx = -1;
|
||||
HnswNeighborArray *neighbors;
|
||||
MemoryContext oldCtx = MemoryContextSwitchTo(updateCtx);
|
||||
|
||||
/*
|
||||
* Get latest neighbors since they may have changed. Do not lock yet since
|
||||
* selecting neighbors can take time. Could use optimistic locking to
|
||||
* retry if another update occurs before getting exclusive lock.
|
||||
*/
|
||||
neighbors = HnswLoadNeighbors(element, index, m, lm, lc);
|
||||
|
||||
/*
|
||||
* Could improve performance for vacuuming by checking neighbors against
|
||||
* list of elements being deleted to find index. It's important to exclude
|
||||
* already deleted elements for this since they can be replaced at any
|
||||
* time.
|
||||
*/
|
||||
|
||||
if (neighbors->length < lm)
|
||||
idx = -2;
|
||||
else
|
||||
{
|
||||
HnswQuery q;
|
||||
|
||||
q.value = HnswGetValue(base, element);
|
||||
|
||||
LoadElementsForInsert(neighbors, &q, &idx, index, support);
|
||||
|
||||
if (idx == -1)
|
||||
HnswUpdateConnection(base, neighbors, newElement, distance, lm, &idx, index, support);
|
||||
}
|
||||
|
||||
MemoryContextSwitchTo(oldCtx);
|
||||
MemoryContextReset(updateCtx);
|
||||
|
||||
return idx;
|
||||
}
|
||||
|
||||
/*
|
||||
* Check if connection already exists
|
||||
*/
|
||||
@@ -461,94 +354,14 @@ ConnectionExists(HnswElement e, HnswNeighborTuple ntup, int startIdx, int lm)
|
||||
return false;
|
||||
}
|
||||
|
||||
/*
|
||||
* Update neighbor
|
||||
*/
|
||||
static void
|
||||
UpdateNeighborOnDisk(HnswElement element, HnswElement newElement, int idx, int m, int lm, int lc, Relation index, bool checkExisting, bool building)
|
||||
{
|
||||
Buffer buf;
|
||||
Page page;
|
||||
GenericXLogState *state;
|
||||
HnswNeighborTuple ntup;
|
||||
int startIdx;
|
||||
OffsetNumber offno = element->neighborOffno;
|
||||
|
||||
/* Register page */
|
||||
buf = ReadBuffer(index, element->neighborPage);
|
||||
LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
|
||||
if (building)
|
||||
{
|
||||
state = NULL;
|
||||
page = BufferGetPage(buf);
|
||||
}
|
||||
else
|
||||
{
|
||||
state = GenericXLogStart(index);
|
||||
page = GenericXLogRegisterBuffer(state, buf, 0);
|
||||
}
|
||||
|
||||
/* Get tuple */
|
||||
ntup = (HnswNeighborTuple) PageGetItem(page, PageGetItemId(page, offno));
|
||||
|
||||
/* Calculate index for update */
|
||||
startIdx = (element->level - lc) * m;
|
||||
|
||||
/* Check for existing connection */
|
||||
if (checkExisting && ConnectionExists(newElement, ntup, startIdx, lm))
|
||||
idx = -1;
|
||||
else if (idx == -2)
|
||||
{
|
||||
/* Find free offset if still exists */
|
||||
/* TODO Retry updating connections if not */
|
||||
for (int j = 0; j < lm; j++)
|
||||
{
|
||||
if (!ItemPointerIsValid(&ntup->indextids[startIdx + j]))
|
||||
{
|
||||
idx = startIdx + j;
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
else
|
||||
idx += startIdx;
|
||||
|
||||
/* Make robust to issues */
|
||||
if (idx >= 0 && idx < ntup->count)
|
||||
{
|
||||
ItemPointer indextid = &ntup->indextids[idx];
|
||||
|
||||
/* Update neighbor on the buffer */
|
||||
ItemPointerSet(indextid, newElement->blkno, newElement->offno);
|
||||
|
||||
/* Commit */
|
||||
if (building)
|
||||
MarkBufferDirty(buf);
|
||||
else
|
||||
GenericXLogFinish(state);
|
||||
}
|
||||
else if (!building)
|
||||
GenericXLogAbort(state);
|
||||
|
||||
UnlockReleaseBuffer(buf);
|
||||
}
|
||||
|
||||
/*
|
||||
* Update neighbors
|
||||
*/
|
||||
void
|
||||
HnswUpdateNeighborsOnDisk(Relation index, HnswSupport * support, HnswElement e, int m, bool checkExisting, bool building)
|
||||
HnswUpdateNeighborsOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting, bool building)
|
||||
{
|
||||
char *base = NULL;
|
||||
|
||||
/* Use separate memory context to improve performance for larger vectors */
|
||||
MemoryContext updateCtx = GenerationContextCreate(CurrentMemoryContext,
|
||||
"Hnsw insert update context",
|
||||
#if PG_VERSION_NUM >= 150000
|
||||
128 * 1024, 128 * 1024,
|
||||
#endif
|
||||
128 * 1024);
|
||||
|
||||
for (int lc = e->level; lc >= 0; lc--)
|
||||
{
|
||||
int lm = HnswGetLayerM(m, lc);
|
||||
@@ -557,20 +370,96 @@ HnswUpdateNeighborsOnDisk(Relation index, HnswSupport * support, HnswElement e,
|
||||
for (int i = 0; i < neighbors->length; i++)
|
||||
{
|
||||
HnswCandidate *hc = &neighbors->items[i];
|
||||
Buffer buf;
|
||||
Page page;
|
||||
GenericXLogState *state;
|
||||
HnswNeighborTuple ntup;
|
||||
int idx = -1;
|
||||
int startIdx;
|
||||
HnswElement neighborElement = HnswPtrAccess(base, hc->element);
|
||||
int idx;
|
||||
OffsetNumber offno = neighborElement->neighborOffno;
|
||||
|
||||
idx = GetUpdateIndex(neighborElement, e, hc->distance, m, lm, lc, index, support, updateCtx);
|
||||
/*
|
||||
* Get latest neighbors since they may have changed. Do not lock
|
||||
* yet since selecting neighbors can take time. Could use
|
||||
* optimistic locking to retry if another update occurs before
|
||||
* getting exclusive lock.
|
||||
*/
|
||||
HnswLoadNeighbors(neighborElement, index, m);
|
||||
|
||||
/*
|
||||
* Could improve performance for vacuuming by checking neighbors
|
||||
* against list of elements being deleted to find index. It's
|
||||
* important to exclude already deleted elements for this since
|
||||
* they can be replaced at any time.
|
||||
*/
|
||||
|
||||
/* Select neighbors */
|
||||
HnswUpdateConnection(NULL, e, hc, lm, lc, &idx, index, procinfo, collation);
|
||||
|
||||
/* New element was not selected as a neighbor */
|
||||
if (idx == -1)
|
||||
continue;
|
||||
|
||||
UpdateNeighborOnDisk(neighborElement, e, idx, m, lm, lc, index, checkExisting, building);
|
||||
/* Register page */
|
||||
buf = ReadBuffer(index, neighborElement->neighborPage);
|
||||
LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
|
||||
if (building)
|
||||
{
|
||||
state = NULL;
|
||||
page = BufferGetPage(buf);
|
||||
}
|
||||
else
|
||||
{
|
||||
state = GenericXLogStart(index);
|
||||
page = GenericXLogRegisterBuffer(state, buf, 0);
|
||||
}
|
||||
|
||||
/* Get tuple */
|
||||
ntup = (HnswNeighborTuple) PageGetItem(page, PageGetItemId(page, offno));
|
||||
|
||||
/* Calculate index for update */
|
||||
startIdx = (neighborElement->level - lc) * m;
|
||||
|
||||
/* Check for existing connection */
|
||||
if (checkExisting && ConnectionExists(e, ntup, startIdx, lm))
|
||||
idx = -1;
|
||||
else if (idx == -2)
|
||||
{
|
||||
/* Find free offset if still exists */
|
||||
/* TODO Retry updating connections if not */
|
||||
for (int j = 0; j < lm; j++)
|
||||
{
|
||||
if (!ItemPointerIsValid(&ntup->indextids[startIdx + j]))
|
||||
{
|
||||
idx = startIdx + j;
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
else
|
||||
idx += startIdx;
|
||||
|
||||
/* Make robust to issues */
|
||||
if (idx >= 0 && idx < ntup->count)
|
||||
{
|
||||
ItemPointer indextid = &ntup->indextids[idx];
|
||||
|
||||
/* Update neighbor on the buffer */
|
||||
ItemPointerSet(indextid, e->blkno, e->offno);
|
||||
|
||||
/* Commit */
|
||||
if (building)
|
||||
MarkBufferDirty(buf);
|
||||
else
|
||||
GenericXLogFinish(state);
|
||||
}
|
||||
else if (!building)
|
||||
GenericXLogAbort(state);
|
||||
|
||||
UnlockReleaseBuffer(buf);
|
||||
}
|
||||
}
|
||||
|
||||
MemoryContextDelete(updateCtx);
|
||||
}
|
||||
|
||||
/*
|
||||
@@ -660,7 +549,7 @@ FindDuplicateOnDisk(Relation index, HnswElement element, bool building)
|
||||
* Update graph on disk
|
||||
*/
|
||||
static void
|
||||
UpdateGraphOnDisk(Relation index, HnswSupport * support, HnswElement element, int m, int efConstruction, HnswElement entryPoint, bool building)
|
||||
UpdateGraphOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement element, int m, int efConstruction, HnswElement entryPoint, bool building)
|
||||
{
|
||||
BlockNumber newInsertPage = InvalidBlockNumber;
|
||||
|
||||
@@ -676,7 +565,7 @@ UpdateGraphOnDisk(Relation index, HnswSupport * support, HnswElement element, in
|
||||
HnswUpdateMetaPage(index, 0, NULL, newInsertPage, MAIN_FORKNUM, building);
|
||||
|
||||
/* Update neighbors */
|
||||
HnswUpdateNeighborsOnDisk(index, support, element, m, false, building);
|
||||
HnswUpdateNeighborsOnDisk(index, procinfo, collation, element, m, false, building);
|
||||
|
||||
/* Update entry point if needed */
|
||||
if (entryPoint == NULL || element->level > entryPoint->level)
|
||||
@@ -687,12 +576,14 @@ UpdateGraphOnDisk(Relation index, HnswSupport * support, HnswElement element, in
|
||||
* Insert a tuple into the index
|
||||
*/
|
||||
bool
|
||||
HnswInsertTupleOnDisk(Relation index, HnswSupport * support, Datum value, ItemPointer heaptid, bool building)
|
||||
HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull, ItemPointer heap_tid, bool building)
|
||||
{
|
||||
HnswElement entryPoint;
|
||||
HnswElement element;
|
||||
int m;
|
||||
int efConstruction = HnswGetEfConstruction(index);
|
||||
FmgrInfo *procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
|
||||
Oid collation = index->rd_indcollation[0];
|
||||
LOCKMODE lockmode = ShareLock;
|
||||
char *base = NULL;
|
||||
|
||||
@@ -707,7 +598,7 @@ HnswInsertTupleOnDisk(Relation index, HnswSupport * support, Datum value, ItemPo
|
||||
HnswGetMetaPageInfo(index, &m, &entryPoint);
|
||||
|
||||
/* Create an element */
|
||||
element = HnswInitElement(base, heaptid, m, HnswGetMl(m), HnswGetMaxLevel(m), NULL);
|
||||
element = HnswInitElement(base, heap_tid, m, HnswGetMl(m), HnswGetMaxLevel(m), NULL);
|
||||
HnswPtrStore(base, element->value, DatumGetPointer(value));
|
||||
|
||||
/* Prevent concurrent inserts when likely updating entry point */
|
||||
@@ -725,10 +616,10 @@ HnswInsertTupleOnDisk(Relation index, HnswSupport * support, Datum value, ItemPo
|
||||
}
|
||||
|
||||
/* Find neighbors for element */
|
||||
HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, false);
|
||||
HnswFindElementNeighbors(base, element, entryPoint, index, procinfo, collation, m, efConstruction, false);
|
||||
|
||||
/* Update graph on disk */
|
||||
UpdateGraphOnDisk(index, support, element, m, efConstruction, entryPoint, building);
|
||||
UpdateGraphOnDisk(index, procinfo, collation, element, m, efConstruction, entryPoint, building);
|
||||
|
||||
/* Release lock */
|
||||
UnlockPage(index, HNSW_UPDATE_LOCK, lockmode);
|
||||
@@ -740,19 +631,31 @@ HnswInsertTupleOnDisk(Relation index, HnswSupport * support, Datum value, ItemPo
|
||||
* Insert a tuple into the index
|
||||
*/
|
||||
static void
|
||||
HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid)
|
||||
HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid)
|
||||
{
|
||||
Datum value;
|
||||
const HnswTypeInfo *typeInfo = HnswGetTypeInfo(index);
|
||||
HnswSupport support;
|
||||
FmgrInfo *normprocinfo;
|
||||
Oid collation = index->rd_indcollation[0];
|
||||
|
||||
HnswInitSupport(&support, index);
|
||||
/* Detoast once for all calls */
|
||||
value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
|
||||
|
||||
/* Form index value */
|
||||
if (!HnswFormIndexValue(&value, values, isnull, typeInfo, &support))
|
||||
return;
|
||||
/* Check value */
|
||||
if (typeInfo->checkValue != NULL)
|
||||
typeInfo->checkValue(DatumGetPointer(value));
|
||||
|
||||
HnswInsertTupleOnDisk(index, &support, value, heaptid, false);
|
||||
/* Normalize if needed */
|
||||
normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
|
||||
if (normprocinfo != NULL)
|
||||
{
|
||||
if (!HnswCheckNorm(normprocinfo, collation, value))
|
||||
return;
|
||||
|
||||
value = HnswNormValue(typeInfo, collation, value);
|
||||
}
|
||||
|
||||
HnswInsertTupleOnDisk(index, value, values, isnull, heap_tid, false);
|
||||
}
|
||||
|
||||
/*
|
||||
|
||||
149
src/hnswscan.c
149
src/hnswscan.c
@@ -5,74 +5,39 @@
|
||||
#include "pgstat.h"
|
||||
#include "storage/bufmgr.h"
|
||||
#include "storage/lmgr.h"
|
||||
#include "utils/float.h"
|
||||
#include "utils/memutils.h"
|
||||
|
||||
/*
|
||||
* Algorithm 5 from paper
|
||||
*/
|
||||
static List *
|
||||
GetScanItems(IndexScanDesc scan, Datum value)
|
||||
GetScanItems(IndexScanDesc scan, Datum q)
|
||||
{
|
||||
HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
|
||||
Relation index = scan->indexRelation;
|
||||
HnswSupport *support = &so->support;
|
||||
FmgrInfo *procinfo = so->procinfo;
|
||||
Oid collation = so->collation;
|
||||
List *ep;
|
||||
List *w;
|
||||
int m;
|
||||
HnswElement entryPoint;
|
||||
char *base = NULL;
|
||||
HnswQuery *q = &so->q;
|
||||
|
||||
/* 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));
|
||||
ep = list_make1(HnswEntryCandidate(base, entryPoint, q, index, procinfo, collation, false));
|
||||
|
||||
for (int lc = entryPoint->level; lc >= 1; lc--)
|
||||
{
|
||||
w = HnswSearchLayer(base, q, ep, 1, lc, index, support, m, false, NULL, NULL, NULL, true, NULL);
|
||||
w = HnswSearchLayer(base, q, ep, 1, lc, index, procinfo, collation, m, false, NULL);
|
||||
ep = w;
|
||||
}
|
||||
|
||||
return HnswSearchLayer(base, q, ep, hnsw_ef_search, 0, index, support, m, false, NULL, &so->v, hnsw_iterative_search != HNSW_ITERATIVE_SEARCH_OFF ? &so->discarded : NULL, true, &so->tuples);
|
||||
}
|
||||
|
||||
/*
|
||||
* Resume scan at ground level with discarded candidates
|
||||
*/
|
||||
static List *
|
||||
ResumeScanItems(IndexScanDesc scan)
|
||||
{
|
||||
HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
|
||||
Relation index = scan->indexRelation;
|
||||
List *ep = NIL;
|
||||
char *base = NULL;
|
||||
int batch_size = hnsw_ef_search;
|
||||
|
||||
if (pairingheap_is_empty(so->discarded))
|
||||
return NIL;
|
||||
|
||||
/* Get next batch of candidates */
|
||||
for (int i = 0; i < batch_size; i++)
|
||||
{
|
||||
HnswSearchCandidate *sc;
|
||||
|
||||
if (pairingheap_is_empty(so->discarded))
|
||||
break;
|
||||
|
||||
sc = HnswGetSearchCandidate(w_node, pairingheap_remove_first(so->discarded));
|
||||
|
||||
ep = lappend(ep, sc);
|
||||
}
|
||||
|
||||
return HnswSearchLayer(base, &so->q, ep, batch_size, 0, index, &so->support, so->m, false, NULL, &so->v, &so->discarded, false, &so->tuples);
|
||||
return HnswSearchLayer(base, q, ep, hnsw_ef_search, 0, index, procinfo, collation, m, false, NULL);
|
||||
}
|
||||
|
||||
/*
|
||||
@@ -95,8 +60,8 @@ GetScanValue(IndexScanDesc scan)
|
||||
Assert(!VARATT_IS_EXTENDED(DatumGetPointer(value)));
|
||||
|
||||
/* Normalize if needed */
|
||||
if (so->support.normprocinfo != NULL)
|
||||
value = HnswNormValue(so->typeInfo, so->support.collation, value);
|
||||
if (so->normprocinfo != NULL)
|
||||
value = HnswNormValue(so->typeInfo, so->collation, value);
|
||||
}
|
||||
|
||||
return value;
|
||||
@@ -116,14 +81,14 @@ hnswbeginscan(Relation index, int nkeys, int 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);
|
||||
so->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
|
||||
so->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
|
||||
so->collation = index->rd_indcollation[0];
|
||||
|
||||
scan->opaque = so;
|
||||
|
||||
@@ -138,15 +103,7 @@ 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;
|
||||
so->tuples = 0;
|
||||
so->previousDistance = -get_float8_infinity();
|
||||
MemoryContextReset(so->tmpCtx);
|
||||
|
||||
if (keys && scan->numberOfKeys > 0)
|
||||
@@ -208,100 +165,22 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
|
||||
#endif
|
||||
}
|
||||
|
||||
for (;;)
|
||||
while (list_length(so->w) > 0)
|
||||
{
|
||||
char *base = NULL;
|
||||
HnswSearchCandidate *sc;
|
||||
HnswElement element;
|
||||
HnswSearchCandidate *hc = llast(so->w);
|
||||
HnswElement element = HnswPtrAccess(base, hc->element);
|
||||
ItemPointer heaptid;
|
||||
|
||||
if (list_length(so->w) == 0)
|
||||
{
|
||||
if (hnsw_iterative_search == HNSW_ITERATIVE_SEARCH_OFF)
|
||||
break;
|
||||
|
||||
/* Empty index */
|
||||
if (so->discarded == NULL)
|
||||
break;
|
||||
|
||||
/* Reached max number of additional tuples */
|
||||
if (hnsw_max_iterative_tuples != -1 && so->tuples >= hnsw_ef_search + hnsw_max_iterative_tuples)
|
||||
{
|
||||
if (pairingheap_is_empty(so->discarded))
|
||||
break;
|
||||
|
||||
/* Return remaining tuples */
|
||||
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)
|
||||
{
|
||||
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.")));
|
||||
|
||||
break;
|
||||
}
|
||||
|
||||
/* Return remaining tuples */
|
||||
so->w = lappend(so->w, HnswGetSearchCandidate(w_node, pairingheap_remove_first(so->discarded)));
|
||||
}
|
||||
else
|
||||
{
|
||||
/*
|
||||
* Locking ensures when neighbors are read, the elements they
|
||||
* reference will not be deleted (and replaced) during the
|
||||
* iteration.
|
||||
*
|
||||
* Elements loaded into memory on previous iterations may have
|
||||
* been deleted (and replaced), so when reading neighbors, the
|
||||
* element version must be checked.
|
||||
*/
|
||||
LockPage(scan->indexRelation, HNSW_SCAN_LOCK, ShareLock);
|
||||
|
||||
so->w = ResumeScanItems(scan);
|
||||
|
||||
UnlockPage(scan->indexRelation, HNSW_SCAN_LOCK, ShareLock);
|
||||
|
||||
#if defined(HNSW_MEMORY)
|
||||
elog(INFO, "memory: %zu KB", MemoryContextMemAllocated(so->tmpCtx, false) / 1024);
|
||||
#endif
|
||||
}
|
||||
|
||||
if (list_length(so->w) == 0)
|
||||
break;
|
||||
}
|
||||
|
||||
sc = llast(so->w);
|
||||
element = HnswPtrAccess(base, sc->element);
|
||||
|
||||
/* Move to next element if no valid heap TIDs */
|
||||
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)
|
||||
{
|
||||
pfree(element);
|
||||
pfree(sc);
|
||||
}
|
||||
|
||||
continue;
|
||||
}
|
||||
|
||||
heaptid = &element->heaptids[--element->heaptidsLength];
|
||||
|
||||
if (hnsw_iterative_search == HNSW_ITERATIVE_SEARCH_STRICT)
|
||||
{
|
||||
if (sc->distance < so->previousDistance)
|
||||
continue;
|
||||
|
||||
so->previousDistance = sc->distance;
|
||||
}
|
||||
|
||||
MemoryContextSwitchTo(oldCtx);
|
||||
|
||||
scan->xs_heaptid = *heaptid;
|
||||
|
||||
448
src/hnswutils.c
448
src/hnswutils.c
@@ -100,6 +100,19 @@ hash_offset(Size offset)
|
||||
#define SH_DEFINE
|
||||
#include "lib/simplehash.h"
|
||||
|
||||
typedef union
|
||||
{
|
||||
pointerhash_hash *pointers;
|
||||
offsethash_hash *offsets;
|
||||
tidhash_hash *tids;
|
||||
} visited_hash;
|
||||
|
||||
typedef union
|
||||
{
|
||||
HnswElement element;
|
||||
ItemPointerData indextid;
|
||||
} HnswUnvisited;
|
||||
|
||||
/*
|
||||
* Get the max number of connections in an upper layer for each element in the index
|
||||
*/
|
||||
@@ -140,17 +153,6 @@ HnswOptionalProcInfo(Relation index, uint16 procnum)
|
||||
return index_getprocinfo(index, 1, procnum);
|
||||
}
|
||||
|
||||
/*
|
||||
* Init support functions
|
||||
*/
|
||||
void
|
||||
HnswInitSupport(HnswSupport * support, Relation index)
|
||||
{
|
||||
support->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
|
||||
support->collation = index->rd_indcollation[0];
|
||||
support->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
|
||||
}
|
||||
|
||||
/*
|
||||
* Normalize value
|
||||
*/
|
||||
@@ -164,9 +166,9 @@ HnswNormValue(const HnswTypeInfo * typeInfo, Oid collation, Datum value)
|
||||
* Check if non-zero norm
|
||||
*/
|
||||
bool
|
||||
HnswCheckNorm(HnswSupport * support, Datum value)
|
||||
HnswCheckNorm(FmgrInfo *procinfo, Oid collation, Datum value)
|
||||
{
|
||||
return DatumGetFloat8(FunctionCall1Coll(support->normprocinfo, support->collation, value)) > 0;
|
||||
return DatumGetFloat8(FunctionCall1Coll(procinfo, collation, value)) > 0;
|
||||
}
|
||||
|
||||
/*
|
||||
@@ -195,7 +197,7 @@ HnswInitPage(Buffer buf, Page page)
|
||||
/*
|
||||
* Allocate a neighbor array
|
||||
*/
|
||||
HnswNeighborArray *
|
||||
static HnswNeighborArray *
|
||||
HnswInitNeighborArray(int lm, HnswAllocator * allocator)
|
||||
{
|
||||
HnswNeighborArray *a = HnswAlloc(allocator, HNSW_NEIGHBOR_ARRAY_SIZE(lm));
|
||||
@@ -251,8 +253,6 @@ HnswInitElement(char *base, ItemPointer heaptid, int m, double ml, int maxLevel,
|
||||
|
||||
element->level = level;
|
||||
element->deleted = 0;
|
||||
/* Start at one to make it easier to find issues */
|
||||
element->version = 1;
|
||||
|
||||
HnswInitNeighbors(base, element, m, allocator);
|
||||
|
||||
@@ -394,33 +394,6 @@ HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, Bloc
|
||||
UnlockReleaseBuffer(buf);
|
||||
}
|
||||
|
||||
/*
|
||||
* Form index value
|
||||
*/
|
||||
bool
|
||||
HnswFormIndexValue(Datum *out, Datum *values, bool *isnull, const HnswTypeInfo * typeInfo, HnswSupport * support)
|
||||
{
|
||||
/* Detoast once for all calls */
|
||||
Datum value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
|
||||
|
||||
/* Check value */
|
||||
if (typeInfo->checkValue != NULL)
|
||||
typeInfo->checkValue(DatumGetPointer(value));
|
||||
|
||||
/* Normalize if needed */
|
||||
if (support->normprocinfo != NULL)
|
||||
{
|
||||
if (!HnswCheckNorm(support, value))
|
||||
return false;
|
||||
|
||||
value = HnswNormValue(typeInfo, support->collation, value);
|
||||
}
|
||||
|
||||
*out = value;
|
||||
|
||||
return true;
|
||||
}
|
||||
|
||||
/*
|
||||
* Set element tuple, except for neighbor info
|
||||
*/
|
||||
@@ -432,7 +405,6 @@ HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element)
|
||||
etup->type = HNSW_ELEMENT_TUPLE_TYPE;
|
||||
etup->level = element->level;
|
||||
etup->deleted = 0;
|
||||
etup->version = element->version;
|
||||
for (int i = 0; i < HNSW_HEAPTIDS; i++)
|
||||
{
|
||||
if (i < element->heaptidsLength)
|
||||
@@ -475,7 +447,69 @@ HnswSetNeighborTuple(char *base, HnswNeighborTuple ntup, HnswElement e, int m)
|
||||
}
|
||||
|
||||
ntup->count = idx;
|
||||
ntup->version = e->version;
|
||||
}
|
||||
|
||||
/*
|
||||
* Load neighbors from page
|
||||
*/
|
||||
static void
|
||||
LoadNeighborsFromPage(HnswElement element, Relation index, Page page, int m)
|
||||
{
|
||||
char *base = NULL;
|
||||
|
||||
HnswNeighborTuple ntup = (HnswNeighborTuple) PageGetItem(page, PageGetItemId(page, element->neighborOffno));
|
||||
int neighborCount = (element->level + 2) * m;
|
||||
|
||||
Assert(HnswIsNeighborTuple(ntup));
|
||||
|
||||
HnswInitNeighbors(base, element, m, NULL);
|
||||
|
||||
/* Ensure expected neighbors */
|
||||
if (ntup->count != neighborCount)
|
||||
return;
|
||||
|
||||
for (int i = 0; i < neighborCount; i++)
|
||||
{
|
||||
HnswElement e;
|
||||
int level;
|
||||
HnswCandidate *hc;
|
||||
ItemPointer indextid;
|
||||
HnswNeighborArray *neighbors;
|
||||
|
||||
indextid = &ntup->indextids[i];
|
||||
|
||||
if (!ItemPointerIsValid(indextid))
|
||||
continue;
|
||||
|
||||
e = HnswInitElementFromBlock(ItemPointerGetBlockNumber(indextid), ItemPointerGetOffsetNumber(indextid));
|
||||
|
||||
/* Calculate level based on offset */
|
||||
level = element->level - i / m;
|
||||
if (level < 0)
|
||||
level = 0;
|
||||
|
||||
neighbors = HnswGetNeighbors(base, element, level);
|
||||
hc = &neighbors->items[neighbors->length++];
|
||||
HnswPtrStore(base, hc->element, e);
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
* Load neighbors
|
||||
*/
|
||||
void
|
||||
HnswLoadNeighbors(HnswElement element, Relation index, int m)
|
||||
{
|
||||
Buffer buf;
|
||||
Page page;
|
||||
|
||||
buf = ReadBuffer(index, element->neighborPage);
|
||||
LockBuffer(buf, BUFFER_LOCK_SHARE);
|
||||
page = BufferGetPage(buf);
|
||||
|
||||
LoadNeighborsFromPage(element, index, page, m);
|
||||
|
||||
UnlockReleaseBuffer(buf);
|
||||
}
|
||||
|
||||
/*
|
||||
@@ -486,7 +520,6 @@ HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHe
|
||||
{
|
||||
element->level = etup->level;
|
||||
element->deleted = etup->deleted;
|
||||
element->version = etup->version;
|
||||
element->neighborPage = ItemPointerGetBlockNumber(&etup->neighbortid);
|
||||
element->neighborOffno = ItemPointerGetOffsetNumber(&etup->neighbortid);
|
||||
element->heaptidsLength = 0;
|
||||
@@ -512,20 +545,11 @@ HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHe
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
* Calculate the distance between values
|
||||
*/
|
||||
static inline double
|
||||
HnswGetDistance(Datum a, Datum b, HnswSupport * support)
|
||||
{
|
||||
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, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance, HnswElement * element)
|
||||
HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, float *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec, float *maxDistance, HnswElement * element)
|
||||
{
|
||||
Buffer buf;
|
||||
Page page;
|
||||
@@ -543,10 +567,10 @@ HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, Hns
|
||||
/* Calculate distance */
|
||||
if (distance != NULL)
|
||||
{
|
||||
if (DatumGetPointer(q->value) == NULL)
|
||||
if (DatumGetPointer(*q) == NULL)
|
||||
*distance = 0;
|
||||
else
|
||||
*distance = HnswGetDistance(q->value, PointerGetDatum(&etup->data), support);
|
||||
*distance = (float) DatumGetFloat8(FunctionCall2Coll(procinfo, collation, *q, PointerGetDatum(&etup->data)));
|
||||
}
|
||||
|
||||
/* Load element */
|
||||
@@ -565,39 +589,41 @@ HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, Hns
|
||||
* Load an element and optionally get its distance from q
|
||||
*/
|
||||
void
|
||||
HnswLoadElement(HnswElement element, double *distance, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance)
|
||||
HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec, float *maxDistance)
|
||||
{
|
||||
HnswLoadElementImpl(element->blkno, element->offno, distance, q, index, support, loadVec, maxDistance, &element);
|
||||
HnswLoadElementImpl(element->blkno, element->offno, distance, q, index, procinfo, collation, loadVec, maxDistance, &element);
|
||||
}
|
||||
|
||||
/*
|
||||
* Get the distance for an element
|
||||
*/
|
||||
static double
|
||||
GetElementDistance(char *base, HnswElement element, HnswQuery * q, HnswSupport * support)
|
||||
static float
|
||||
GetElementDistance(char *base, HnswElement element, Datum q, FmgrInfo *procinfo, Oid collation)
|
||||
{
|
||||
Datum value = HnswGetValue(base, element);
|
||||
|
||||
return HnswGetDistance(q->value, value, support);
|
||||
return DatumGetFloat8(FunctionCall2Coll(procinfo, collation, q, value));
|
||||
}
|
||||
|
||||
/*
|
||||
* Create a candidate for the entry point
|
||||
*/
|
||||
HnswSearchCandidate *
|
||||
HnswEntryCandidate(char *base, HnswElement entryPoint, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec)
|
||||
HnswEntryCandidate(char *base, HnswElement entryPoint, Datum q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec)
|
||||
{
|
||||
HnswSearchCandidate *sc = palloc(sizeof(HnswSearchCandidate));
|
||||
bool inMemory = index == NULL;
|
||||
HnswSearchCandidate *hc = palloc(sizeof(HnswSearchCandidate));
|
||||
|
||||
HnswPtrStore(base, sc->element, entryPoint);
|
||||
if (inMemory)
|
||||
sc->distance = GetElementDistance(base, entryPoint, q, support);
|
||||
HnswPtrStore(base, hc->element, entryPoint);
|
||||
if (index == NULL)
|
||||
hc->distance = GetElementDistance(base, entryPoint, q, procinfo, collation);
|
||||
else
|
||||
HnswLoadElement(entryPoint, &sc->distance, q, index, support, loadVec, NULL);
|
||||
return sc;
|
||||
HnswLoadElement(entryPoint, &hc->distance, &q, index, procinfo, collation, loadVec, NULL);
|
||||
return hc;
|
||||
}
|
||||
|
||||
#define HnswGetSearchCandidate(membername, ptr) pairingheap_container(HnswSearchCandidate, membername, ptr)
|
||||
#define HnswGetSearchCandidateConst(membername, ptr) pairingheap_const_container(HnswSearchCandidate, membername, ptr)
|
||||
|
||||
/*
|
||||
* Compare candidate distances
|
||||
*/
|
||||
@@ -613,21 +639,6 @@ CompareNearestCandidates(const pairingheap_node *a, const pairingheap_node *b, v
|
||||
return 0;
|
||||
}
|
||||
|
||||
/*
|
||||
* Compare discarded candidate distances
|
||||
*/
|
||||
static int
|
||||
CompareNearestDiscardedCandidates(const pairingheap_node *a, const pairingheap_node *b, void *arg)
|
||||
{
|
||||
if (HnswGetSearchCandidateConst(w_node, a)->distance < HnswGetSearchCandidateConst(w_node, b)->distance)
|
||||
return 1;
|
||||
|
||||
if (HnswGetSearchCandidateConst(w_node, a)->distance > HnswGetSearchCandidateConst(w_node, b)->distance)
|
||||
return -1;
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
/*
|
||||
* Compare candidate distances
|
||||
*/
|
||||
@@ -647,9 +658,9 @@ CompareFurthestCandidates(const pairingheap_node *a, const pairingheap_node *b,
|
||||
* Init visited
|
||||
*/
|
||||
static inline void
|
||||
InitVisited(char *base, visited_hash * v, bool inMemory, int ef, int m)
|
||||
InitVisited(char *base, visited_hash * v, Relation index, int ef, int m)
|
||||
{
|
||||
if (!inMemory)
|
||||
if (index != NULL)
|
||||
v->tids = tidhash_create(CurrentMemoryContext, ef * m * 2, NULL);
|
||||
else if (base != NULL)
|
||||
v->offsets = offsethash_create(CurrentMemoryContext, ef * m * 2, NULL);
|
||||
@@ -661,9 +672,9 @@ InitVisited(char *base, visited_hash * v, bool inMemory, int ef, int m)
|
||||
* Add to visited
|
||||
*/
|
||||
static inline void
|
||||
AddToVisited(char *base, visited_hash * v, HnswElementPtr elementPtr, bool inMemory, bool *found)
|
||||
AddToVisited(char *base, visited_hash * v, HnswElementPtr elementPtr, Relation index, bool *found)
|
||||
{
|
||||
if (!inMemory)
|
||||
if (index != NULL)
|
||||
{
|
||||
HnswElement element = HnswPtrAccess(base, elementPtr);
|
||||
ItemPointerData indextid;
|
||||
@@ -724,60 +735,45 @@ HnswLoadUnvisitedFromMemory(char *base, HnswElement element, HnswUnvisited * unv
|
||||
HnswCandidate *hc = &localNeighborhood->items[i];
|
||||
bool found;
|
||||
|
||||
AddToVisited(base, v, hc->element, true, &found);
|
||||
AddToVisited(base, v, hc->element, NULL, &found);
|
||||
|
||||
if (!found)
|
||||
unvisited[(*unvisitedLength)++].element = HnswPtrAccess(base, hc->element);
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
* Load neighbor index TIDs
|
||||
*/
|
||||
bool
|
||||
HnswLoadNeighborTids(HnswElement element, ItemPointerData *indextids, Relation index, int m, int lm, int lc)
|
||||
{
|
||||
Buffer buf;
|
||||
Page page;
|
||||
HnswNeighborTuple ntup;
|
||||
int start;
|
||||
|
||||
buf = ReadBuffer(index, element->neighborPage);
|
||||
LockBuffer(buf, BUFFER_LOCK_SHARE);
|
||||
page = BufferGetPage(buf);
|
||||
|
||||
ntup = (HnswNeighborTuple) PageGetItem(page, PageGetItemId(page, element->neighborOffno));
|
||||
|
||||
/*
|
||||
* Ensure the neighbor tuple has not been deleted or replaced between
|
||||
* index scan iterations
|
||||
*/
|
||||
if (ntup->version != element->version || ntup->count != (element->level + 2) * m)
|
||||
{
|
||||
UnlockReleaseBuffer(buf);
|
||||
return false;
|
||||
}
|
||||
|
||||
/* Copy to minimize lock time */
|
||||
start = (element->level - lc) * m;
|
||||
memcpy(indextids, ntup->indextids + start, lm * sizeof(ItemPointerData));
|
||||
|
||||
UnlockReleaseBuffer(buf);
|
||||
return true;
|
||||
}
|
||||
|
||||
/*
|
||||
* Load unvisited neighbors from disk
|
||||
*/
|
||||
static void
|
||||
HnswLoadUnvisitedFromDisk(HnswElement element, HnswUnvisited * unvisited, int *unvisitedLength, visited_hash * v, Relation index, int m, int lm, int lc)
|
||||
{
|
||||
Buffer buf;
|
||||
Page page;
|
||||
HnswNeighborTuple ntup;
|
||||
int start;
|
||||
ItemPointerData indextids[HNSW_MAX_M * 2];
|
||||
|
||||
*unvisitedLength = 0;
|
||||
buf = ReadBuffer(index, element->neighborPage);
|
||||
LockBuffer(buf, BUFFER_LOCK_SHARE);
|
||||
page = BufferGetPage(buf);
|
||||
|
||||
if (!HnswLoadNeighborTids(element, indextids, index, m, lm, lc))
|
||||
ntup = (HnswNeighborTuple) PageGetItem(page, PageGetItemId(page, element->neighborOffno));
|
||||
|
||||
/* Ensure expected neighbors */
|
||||
if (ntup->count != (element->level + 2) * m)
|
||||
{
|
||||
UnlockReleaseBuffer(buf);
|
||||
return;
|
||||
}
|
||||
|
||||
/* Copy to minimize lock time */
|
||||
start = (element->level - lc) * m;
|
||||
memcpy(&indextids, ntup->indextids + start, lm * sizeof(ItemPointerData));
|
||||
|
||||
UnlockReleaseBuffer(buf);
|
||||
|
||||
*unvisitedLength = 0;
|
||||
|
||||
for (int i = 0; i < lm; i++)
|
||||
{
|
||||
@@ -798,37 +794,24 @@ 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, visited_hash * v, pairingheap **discarded, bool initVisited, int64 *tuples)
|
||||
HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement)
|
||||
{
|
||||
List *w = NIL;
|
||||
pairingheap *C = pairingheap_allocate(CompareNearestCandidates, NULL);
|
||||
pairingheap *W = pairingheap_allocate(CompareFurthestCandidates, NULL);
|
||||
int wlen = 0;
|
||||
visited_hash vh;
|
||||
visited_hash v;
|
||||
ListCell *lc2;
|
||||
HnswNeighborArray *localNeighborhood = NULL;
|
||||
Size neighborhoodSize = 0;
|
||||
int lm = HnswGetLayerM(m, lc);
|
||||
HnswUnvisited *unvisited = palloc(lm * sizeof(HnswUnvisited));
|
||||
int unvisitedLength;
|
||||
bool inMemory = index == NULL;
|
||||
|
||||
if (v == NULL)
|
||||
{
|
||||
v = &vh;
|
||||
initVisited = true;
|
||||
}
|
||||
|
||||
if (initVisited)
|
||||
{
|
||||
InitVisited(base, v, inMemory, ef, m);
|
||||
|
||||
if (discarded != NULL)
|
||||
*discarded = pairingheap_allocate(CompareNearestDiscardedCandidates, NULL);
|
||||
}
|
||||
InitVisited(base, &v, index, ef, m);
|
||||
|
||||
/* Create local memory for neighborhood if needed */
|
||||
if (inMemory)
|
||||
if (index == NULL)
|
||||
{
|
||||
neighborhoodSize = HNSW_NEIGHBOR_ARRAY_SIZE(lm);
|
||||
localNeighborhood = palloc(neighborhoodSize);
|
||||
@@ -837,26 +820,20 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
|
||||
/* Add entry points to v, C, and W */
|
||||
foreach(lc2, ep)
|
||||
{
|
||||
HnswSearchCandidate *sc = (HnswSearchCandidate *) lfirst(lc2);
|
||||
HnswSearchCandidate *hc = (HnswSearchCandidate *) lfirst(lc2);
|
||||
bool found;
|
||||
|
||||
if (initVisited)
|
||||
{
|
||||
AddToVisited(base, v, sc->element, inMemory, &found);
|
||||
AddToVisited(base, &v, hc->element, index, &found);
|
||||
|
||||
if (tuples != NULL)
|
||||
(*tuples)++;
|
||||
}
|
||||
|
||||
pairingheap_add(C, &sc->c_node);
|
||||
pairingheap_add(W, &sc->w_node);
|
||||
pairingheap_add(C, &hc->c_node);
|
||||
pairingheap_add(W, &hc->w_node);
|
||||
|
||||
/*
|
||||
* Do not count elements being deleted towards ef when vacuuming. It
|
||||
* would be ideal to do this for inserts as well, but this could
|
||||
* affect insert performance.
|
||||
*/
|
||||
if (CountElement(skipElement, HnswPtrAccess(base, sc->element)))
|
||||
if (CountElement(skipElement, HnswPtrAccess(base, hc->element)))
|
||||
wlen++;
|
||||
}
|
||||
|
||||
@@ -871,27 +848,24 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
|
||||
|
||||
cElement = HnswPtrAccess(base, c->element);
|
||||
|
||||
if (inMemory)
|
||||
HnswLoadUnvisitedFromMemory(base, cElement, unvisited, &unvisitedLength, v, lc, localNeighborhood, neighborhoodSize);
|
||||
if (index == NULL)
|
||||
HnswLoadUnvisitedFromMemory(base, cElement, unvisited, &unvisitedLength, &v, lc, localNeighborhood, neighborhoodSize);
|
||||
else
|
||||
HnswLoadUnvisitedFromDisk(cElement, unvisited, &unvisitedLength, v, index, m, lm, lc);
|
||||
|
||||
if (tuples != NULL)
|
||||
(*tuples) += unvisitedLength;
|
||||
HnswLoadUnvisitedFromDisk(cElement, unvisited, &unvisitedLength, &v, index, m, lm, lc);
|
||||
|
||||
for (int i = 0; i < unvisitedLength; i++)
|
||||
{
|
||||
HnswElement eElement;
|
||||
HnswSearchCandidate *e;
|
||||
double eDistance;
|
||||
float eDistance;
|
||||
bool alwaysAdd = wlen < ef;
|
||||
|
||||
f = HnswGetSearchCandidate(w_node, pairingheap_first(W));
|
||||
|
||||
if (inMemory)
|
||||
if (index == NULL)
|
||||
{
|
||||
eElement = unvisited[i].element;
|
||||
eDistance = GetElementDistance(base, eElement, q, support);
|
||||
eDistance = GetElementDistance(base, eElement, q, procinfo, collation);
|
||||
}
|
||||
else
|
||||
{
|
||||
@@ -901,25 +875,16 @@ 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, q, index, support, inserting, alwaysAdd || discarded != NULL ? NULL : &f->distance, &eElement);
|
||||
HnswLoadElementImpl(blkno, offno, &eDistance, &q, index, procinfo, collation, inserting, alwaysAdd ? NULL : &f->distance, &eElement);
|
||||
|
||||
if (eElement == NULL)
|
||||
continue;
|
||||
}
|
||||
|
||||
if (eElement == NULL || !(eDistance < f->distance || alwaysAdd))
|
||||
{
|
||||
if (discarded != NULL)
|
||||
{
|
||||
/* Create a new candidate */
|
||||
e = palloc(sizeof(HnswSearchCandidate));
|
||||
HnswPtrStore(base, e->element, eElement);
|
||||
e->distance = eDistance;
|
||||
pairingheap_add(*discarded, &e->w_node);
|
||||
}
|
||||
|
||||
if (!(eDistance < f->distance || alwaysAdd))
|
||||
continue;
|
||||
}
|
||||
|
||||
Assert(!eElement->deleted);
|
||||
|
||||
/* Make robust to issues */
|
||||
if (eElement->level < lc)
|
||||
@@ -943,12 +908,7 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
|
||||
|
||||
/* No need to decrement wlen */
|
||||
if (wlen > ef)
|
||||
{
|
||||
HnswSearchCandidate *d = HnswGetSearchCandidate(w_node, pairingheap_remove_first(W));
|
||||
|
||||
if (discarded != NULL)
|
||||
pairingheap_add(*discarded, &d->w_node);
|
||||
}
|
||||
pairingheap_remove_first(W);
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -956,9 +916,9 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
|
||||
/* Add each element of W to w */
|
||||
while (!pairingheap_is_empty(W))
|
||||
{
|
||||
HnswSearchCandidate *sc = HnswGetSearchCandidate(w_node, pairingheap_remove_first(W));
|
||||
HnswSearchCandidate *hc = HnswGetSearchCandidate(w_node, pairingheap_remove_first(W));
|
||||
|
||||
w = lappend(w, sc);
|
||||
w = lappend(w, hc);
|
||||
}
|
||||
|
||||
return w;
|
||||
@@ -1012,22 +972,32 @@ CompareCandidateDistancesOffset(const ListCell *a, const ListCell *b)
|
||||
return 0;
|
||||
}
|
||||
|
||||
/*
|
||||
* Calculate the distance between elements
|
||||
*/
|
||||
static float
|
||||
HnswGetDistance(char *base, HnswElement a, HnswElement b, FmgrInfo *procinfo, Oid collation)
|
||||
{
|
||||
Datum aValue = HnswGetValue(base, a);
|
||||
Datum bValue = HnswGetValue(base, b);
|
||||
|
||||
return DatumGetFloat8(FunctionCall2Coll(procinfo, collation, aValue, bValue));
|
||||
}
|
||||
|
||||
/*
|
||||
* Check if an element is closer to q than any element from R
|
||||
*/
|
||||
static bool
|
||||
CheckElementCloser(char *base, HnswCandidate * e, List *r, HnswSupport * support)
|
||||
CheckElementCloser(char *base, HnswCandidate * e, List *r, FmgrInfo *procinfo, Oid collation)
|
||||
{
|
||||
HnswElement eElement = HnswPtrAccess(base, e->element);
|
||||
Datum eValue = HnswGetValue(base, eElement);
|
||||
ListCell *lc2;
|
||||
|
||||
foreach(lc2, r)
|
||||
{
|
||||
HnswCandidate *ri = lfirst(lc2);
|
||||
HnswElement riElement = HnswPtrAccess(base, ri->element);
|
||||
Datum riValue = HnswGetValue(base, riElement);
|
||||
float distance = HnswGetDistance(eValue, riValue, support);
|
||||
float distance = HnswGetDistance(base, eElement, riElement, procinfo, collation);
|
||||
|
||||
if (distance <= e->distance)
|
||||
return false;
|
||||
@@ -1040,14 +1010,15 @@ CheckElementCloser(char *base, HnswCandidate * e, List *r, HnswSupport * support
|
||||
* Algorithm 4 from paper
|
||||
*/
|
||||
static List *
|
||||
SelectNeighbors(char *base, List *c, int lm, HnswSupport * support, bool *closerSet, HnswCandidate * newCandidate, HnswCandidate * *pruned, bool sortCandidates)
|
||||
SelectNeighbors(char *base, List *c, int lm, int lc, FmgrInfo *procinfo, Oid collation, HnswElement e2, HnswCandidate * newCandidate, HnswCandidate * *pruned, bool sortCandidates)
|
||||
{
|
||||
List *r = NIL;
|
||||
List *w = list_copy(c);
|
||||
HnswCandidate **wd;
|
||||
int wdlen = 0;
|
||||
int wdoff = 0;
|
||||
bool mustCalculate = !(*closerSet);
|
||||
HnswNeighborArray *neighbors = HnswGetNeighbors(base, e2, lc);
|
||||
bool mustCalculate = !neighbors->closerSet;
|
||||
List *added = NIL;
|
||||
bool removedAny = false;
|
||||
|
||||
@@ -1074,7 +1045,7 @@ SelectNeighbors(char *base, List *c, int lm, HnswSupport * support, bool *closer
|
||||
|
||||
/* Use previous state of r and wd to skip work when possible */
|
||||
if (mustCalculate)
|
||||
e->closer = CheckElementCloser(base, e, r, support);
|
||||
e->closer = CheckElementCloser(base, e, r, procinfo, collation);
|
||||
else if (list_length(added) > 0)
|
||||
{
|
||||
/* Keep Valgrind happy for in-memory, parallel builds */
|
||||
@@ -1087,7 +1058,7 @@ SelectNeighbors(char *base, List *c, int lm, HnswSupport * support, bool *closer
|
||||
*/
|
||||
if (e->closer)
|
||||
{
|
||||
e->closer = CheckElementCloser(base, e, added, support);
|
||||
e->closer = CheckElementCloser(base, e, added, procinfo, collation);
|
||||
|
||||
if (!e->closer)
|
||||
removedAny = true;
|
||||
@@ -1100,7 +1071,7 @@ SelectNeighbors(char *base, List *c, int lm, HnswSupport * support, bool *closer
|
||||
*/
|
||||
if (removedAny)
|
||||
{
|
||||
e->closer = CheckElementCloser(base, e, r, support);
|
||||
e->closer = CheckElementCloser(base, e, r, procinfo, collation);
|
||||
if (e->closer)
|
||||
added = lappend(added, e);
|
||||
}
|
||||
@@ -1108,7 +1079,7 @@ SelectNeighbors(char *base, List *c, int lm, HnswSupport * support, bool *closer
|
||||
}
|
||||
else if (e == newCandidate)
|
||||
{
|
||||
e->closer = CheckElementCloser(base, e, r, support);
|
||||
e->closer = CheckElementCloser(base, e, r, procinfo, collation);
|
||||
if (e->closer)
|
||||
added = lappend(added, e);
|
||||
}
|
||||
@@ -1124,7 +1095,7 @@ SelectNeighbors(char *base, List *c, int lm, HnswSupport * support, bool *closer
|
||||
}
|
||||
|
||||
/* Cached value can only be used in future if sorted deterministically */
|
||||
*closerSet = sortCandidates;
|
||||
neighbors->closerSet = sortCandidates;
|
||||
|
||||
/* Keep pruned connections */
|
||||
while (wdoff < wdlen && list_length(r) < lm)
|
||||
@@ -1159,16 +1130,18 @@ AddConnections(char *base, HnswElement element, List *neighbors, int lc)
|
||||
* Update connections
|
||||
*/
|
||||
void
|
||||
HnswUpdateConnection(char *base, HnswNeighborArray * neighbors, HnswElement newElement, float distance, int lm, int *updateIdx, Relation index, HnswSupport * support)
|
||||
HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int lm, int lc, int *updateIdx, Relation index, FmgrInfo *procinfo, Oid collation)
|
||||
{
|
||||
HnswCandidate newHc;
|
||||
HnswElement hce = HnswPtrAccess(base, hc->element);
|
||||
HnswNeighborArray *currentNeighbors = HnswGetNeighbors(base, hce, lc);
|
||||
HnswCandidate hc2;
|
||||
|
||||
HnswPtrStore(base, newHc.element, newElement);
|
||||
newHc.distance = distance;
|
||||
HnswPtrStore(base, hc2.element, element);
|
||||
hc2.distance = hc->distance;
|
||||
|
||||
if (neighbors->length < lm)
|
||||
if (currentNeighbors->length < lm)
|
||||
{
|
||||
neighbors->items[neighbors->length++] = newHc;
|
||||
currentNeighbors->items[currentNeighbors->length++] = hc2;
|
||||
|
||||
/* Track update */
|
||||
if (updateIdx != NULL)
|
||||
@@ -1177,26 +1150,54 @@ HnswUpdateConnection(char *base, HnswNeighborArray * neighbors, HnswElement newE
|
||||
else
|
||||
{
|
||||
/* Shrink connections */
|
||||
List *c = NIL;
|
||||
HnswCandidate *pruned = NULL;
|
||||
|
||||
/* Add candidates */
|
||||
for (int i = 0; i < neighbors->length; i++)
|
||||
c = lappend(c, &neighbors->items[i]);
|
||||
c = lappend(c, &newHc);
|
||||
/* Load elements on insert */
|
||||
if (index != NULL)
|
||||
{
|
||||
Datum q = HnswGetValue(base, hce);
|
||||
|
||||
SelectNeighbors(base, c, lm, support, &neighbors->closerSet, &newHc, &pruned, true);
|
||||
for (int i = 0; i < currentNeighbors->length; i++)
|
||||
{
|
||||
HnswCandidate *hc3 = ¤tNeighbors->items[i];
|
||||
HnswElement hc3Element = HnswPtrAccess(base, hc3->element);
|
||||
|
||||
if (HnswPtrIsNull(base, hc3Element->value))
|
||||
HnswLoadElement(hc3Element, &hc3->distance, &q, index, procinfo, collation, true, NULL);
|
||||
else
|
||||
hc3->distance = GetElementDistance(base, hc3Element, q, procinfo, collation);
|
||||
|
||||
/* Prune element if being deleted */
|
||||
if (hc3Element->heaptidsLength == 0)
|
||||
{
|
||||
pruned = ¤tNeighbors->items[i];
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/* Should not happen */
|
||||
if (pruned == NULL)
|
||||
return;
|
||||
{
|
||||
List *c = NIL;
|
||||
|
||||
/* Add candidates */
|
||||
for (int i = 0; i < currentNeighbors->length; i++)
|
||||
c = lappend(c, ¤tNeighbors->items[i]);
|
||||
c = lappend(c, &hc2);
|
||||
|
||||
SelectNeighbors(base, c, lm, lc, procinfo, collation, hce, &hc2, &pruned, true);
|
||||
|
||||
/* Should not happen */
|
||||
if (pruned == NULL)
|
||||
return;
|
||||
}
|
||||
|
||||
/* Find and replace the pruned element */
|
||||
for (int i = 0; i < neighbors->length; i++)
|
||||
for (int i = 0; i < currentNeighbors->length; i++)
|
||||
{
|
||||
if (HnswPtrEqual(base, neighbors->items[i].element, pruned->element))
|
||||
if (HnswPtrEqual(base, currentNeighbors->items[i].element, pruned->element))
|
||||
{
|
||||
neighbors->items[i] = newHc;
|
||||
currentNeighbors->items[i] = hc2;
|
||||
|
||||
/* Track update */
|
||||
if (updateIdx != NULL)
|
||||
@@ -1256,20 +1257,17 @@ 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)
|
||||
HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo *procinfo, Oid collation, int m, int efConstruction, bool existing)
|
||||
{
|
||||
List *ep;
|
||||
List *w;
|
||||
int level = element->level;
|
||||
int entryLevel;
|
||||
HnswQuery q;
|
||||
Datum q = HnswGetValue(base, element);
|
||||
HnswElement skipElement = existing ? element : NULL;
|
||||
bool inMemory = index == NULL;
|
||||
|
||||
q.value = HnswGetValue(base, element);
|
||||
|
||||
/* Precompute hash */
|
||||
if (inMemory)
|
||||
if (index == NULL)
|
||||
PrecomputeHash(base, element);
|
||||
|
||||
/* No neighbors if no entry point */
|
||||
@@ -1277,13 +1275,13 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
|
||||
return;
|
||||
|
||||
/* Get entry point and level */
|
||||
ep = list_make1(HnswEntryCandidate(base, entryPoint, &q, index, support, true));
|
||||
ep = list_make1(HnswEntryCandidate(base, entryPoint, q, index, procinfo, collation, 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, NULL, NULL, true, NULL);
|
||||
w = HnswSearchLayer(base, q, ep, 1, lc, index, procinfo, collation, m, true, skipElement);
|
||||
ep = w;
|
||||
}
|
||||
|
||||
@@ -1302,7 +1300,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
|
||||
List *lw = NIL;
|
||||
ListCell *lc2;
|
||||
|
||||
w = HnswSearchLayer(base, &q, ep, efConstruction, lc, index, support, m, true, skipElement, NULL, NULL, true, NULL);
|
||||
w = HnswSearchLayer(base, q, ep, efConstruction, lc, index, procinfo, collation, m, true, skipElement);
|
||||
|
||||
/* Convert search candidates to candidates */
|
||||
foreach(lc2, w)
|
||||
@@ -1318,7 +1316,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
|
||||
|
||||
/* Elements being deleted or skipped can help with search */
|
||||
/* but should be removed before selecting neighbors */
|
||||
if (!inMemory)
|
||||
if (index != NULL)
|
||||
lw = RemoveElements(base, lw, skipElement);
|
||||
|
||||
/*
|
||||
@@ -1326,7 +1324,7 @@ 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, support, &HnswGetNeighbors(base, element, lc)->closerSet, NULL, NULL, false);
|
||||
neighbors = SelectNeighbors(base, lw, lm, lc, procinfo, collation, element, NULL, NULL, false);
|
||||
|
||||
AddConnections(base, element, neighbors, lc);
|
||||
|
||||
|
||||
@@ -184,12 +184,13 @@ static void
|
||||
RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswElement entryPoint)
|
||||
{
|
||||
Relation index = vacuumstate->index;
|
||||
HnswSupport *support = &vacuumstate->support;
|
||||
Buffer buf;
|
||||
Page page;
|
||||
GenericXLogState *state;
|
||||
int m = vacuumstate->m;
|
||||
int efConstruction = vacuumstate->efConstruction;
|
||||
FmgrInfo *procinfo = vacuumstate->procinfo;
|
||||
Oid collation = vacuumstate->collation;
|
||||
BufferAccessStrategy bas = vacuumstate->bas;
|
||||
HnswNeighborTuple ntup = vacuumstate->ntup;
|
||||
Size ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(element->level, m);
|
||||
@@ -204,7 +205,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
|
||||
element->heaptidsLength = 0;
|
||||
|
||||
/* Find neighbors for element, skipping itself */
|
||||
HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, true);
|
||||
HnswFindElementNeighbors(base, element, entryPoint, index, procinfo, collation, m, efConstruction, true);
|
||||
|
||||
/* Zero memory for each element */
|
||||
MemSet(ntup, 0, HNSW_TUPLE_ALLOC_SIZE);
|
||||
@@ -228,7 +229,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
|
||||
UnlockReleaseBuffer(buf);
|
||||
|
||||
/* Update neighbors */
|
||||
HnswUpdateNeighborsOnDisk(index, support, element, m, true, false);
|
||||
HnswUpdateNeighborsOnDisk(index, procinfo, collation, element, m, true, false);
|
||||
}
|
||||
|
||||
/*
|
||||
@@ -238,7 +239,6 @@ static void
|
||||
RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
|
||||
{
|
||||
Relation index = vacuumstate->index;
|
||||
HnswSupport *support = &vacuumstate->support;
|
||||
HnswElement highestPoint = &vacuumstate->highestPoint;
|
||||
HnswElement entryPoint;
|
||||
MemoryContext oldCtx = MemoryContextSwitchTo(vacuumstate->tmpCtx);
|
||||
@@ -256,7 +256,7 @@ RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
|
||||
LockPage(index, HNSW_UPDATE_LOCK, ShareLock);
|
||||
|
||||
/* Load element */
|
||||
HnswLoadElement(highestPoint, NULL, NULL, index, support, true, NULL);
|
||||
HnswLoadElement(highestPoint, NULL, NULL, index, vacuumstate->procinfo, vacuumstate->collation, 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, index, support, true, NULL);
|
||||
HnswLoadElement(entryPoint, NULL, NULL, index, vacuumstate->procinfo, vacuumstate->collation, true, NULL);
|
||||
|
||||
if (NeedsUpdated(vacuumstate, entryPoint))
|
||||
{
|
||||
@@ -527,14 +527,6 @@ MarkDeleted(HnswVacuumState * vacuumstate)
|
||||
for (int i = 0; i < ntup->count; i++)
|
||||
ItemPointerSetInvalid(&ntup->indextids[i]);
|
||||
|
||||
/* Increment version */
|
||||
/* This is used to avoid incorrect reads for iterative scans */
|
||||
/* Reserve some bits for future use */
|
||||
etup->version++;
|
||||
if (etup->version > 15)
|
||||
etup->version = 1;
|
||||
ntup->version = etup->version;
|
||||
|
||||
/*
|
||||
* We modified the tuples in place, no need to call
|
||||
* PageIndexTupleOverwrite
|
||||
@@ -581,13 +573,13 @@ InitVacuumState(HnswVacuumState * vacuumstate, IndexVacuumInfo *info, IndexBulkD
|
||||
vacuumstate->callback_state = callback_state;
|
||||
vacuumstate->efConstruction = HnswGetEfConstruction(index);
|
||||
vacuumstate->bas = GetAccessStrategy(BAS_BULKREAD);
|
||||
vacuumstate->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
|
||||
vacuumstate->collation = index->rd_indcollation[0];
|
||||
vacuumstate->ntup = palloc0(HNSW_TUPLE_ALLOC_SIZE);
|
||||
vacuumstate->tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
|
||||
"Hnsw vacuum temporary context",
|
||||
ALLOCSET_DEFAULT_SIZES);
|
||||
|
||||
HnswInitSupport(&vacuumstate->support, index);
|
||||
|
||||
/* Get m from metapage */
|
||||
HnswGetMetaPageInfo(index, &vacuumstate->m, NULL);
|
||||
|
||||
|
||||
@@ -69,8 +69,6 @@ ivfflatcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
|
||||
GenericCosts costs;
|
||||
int lists;
|
||||
double ratio;
|
||||
double sequentialRatio = 0.5;
|
||||
double startupPages;
|
||||
double spc_seq_page_cost;
|
||||
Relation index;
|
||||
|
||||
@@ -98,23 +96,25 @@ ivfflatcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
|
||||
if (ratio > 1.0)
|
||||
ratio = 1.0;
|
||||
|
||||
/* Set startup cost since most work happens before first tuple is returned */
|
||||
costs.indexStartupCost = costs.indexTotalCost * ratio;
|
||||
costs.numIndexPages *= ratio;
|
||||
|
||||
get_tablespace_page_costs(path->indexinfo->reltablespace, NULL, &spc_seq_page_cost);
|
||||
|
||||
/* Change some page cost from random to sequential */
|
||||
costs.indexTotalCost -= sequentialRatio * costs.numIndexPages * (costs.spc_random_page_cost - spc_seq_page_cost);
|
||||
|
||||
/* Startup cost is cost before returning the first row */
|
||||
costs.indexStartupCost = costs.indexTotalCost * ratio;
|
||||
|
||||
/* Adjust cost if needed since TOAST not included in seq scan cost */
|
||||
startupPages = costs.numIndexPages * ratio;
|
||||
if (startupPages > path->indexinfo->rel->pages && ratio < 0.5)
|
||||
if (costs.numIndexPages > path->indexinfo->rel->pages && ratio < 0.5)
|
||||
{
|
||||
/* Change rest of page cost from random to sequential */
|
||||
costs.indexStartupCost -= (1 - sequentialRatio) * startupPages * (costs.spc_random_page_cost - spc_seq_page_cost);
|
||||
/* Change all page cost from random to sequential */
|
||||
costs.indexStartupCost -= costs.numIndexPages * (costs.spc_random_page_cost - spc_seq_page_cost);
|
||||
|
||||
/* Remove cost of extra pages */
|
||||
costs.indexStartupCost -= (startupPages - path->indexinfo->rel->pages) * spc_seq_page_cost;
|
||||
costs.indexStartupCost -= (costs.numIndexPages - path->indexinfo->rel->pages) * spc_seq_page_cost;
|
||||
}
|
||||
else
|
||||
{
|
||||
/* Change some page cost from random to sequential */
|
||||
costs.indexStartupCost -= 0.5 * costs.numIndexPages * (costs.spc_random_page_cost - spc_seq_page_cost);
|
||||
}
|
||||
|
||||
*indexStartupCost = costs.indexStartupCost;
|
||||
@@ -122,6 +122,9 @@ ivfflatcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
|
||||
*indexSelectivity = costs.indexSelectivity;
|
||||
*indexCorrelation = costs.indexCorrelation;
|
||||
*indexPages = costs.numIndexPages;
|
||||
|
||||
Assert(*indexStartupCost > 0);
|
||||
Assert(*indexTotalCost > 0);
|
||||
}
|
||||
|
||||
/*
|
||||
|
||||
@@ -41,7 +41,8 @@ my $c = int(rand() * $nc);
|
||||
my $explain = $node->safe_psql("postgres", qq(
|
||||
EXPLAIN ANALYZE SELECT i FROM tst WHERE c = $c ORDER BY v <-> '$query' LIMIT $limit;
|
||||
));
|
||||
like($explain, qr/Seq Scan/);
|
||||
# TODO Do not use index
|
||||
like($explain, qr/Index Scan using idx/);
|
||||
|
||||
# Test attribute filtering with few rows removed
|
||||
$explain = $node->safe_psql("postgres", qq(
|
||||
@@ -59,7 +60,8 @@ like($explain, qr/Index Scan using idx/);
|
||||
$explain = $node->safe_psql("postgres", qq(
|
||||
EXPLAIN ANALYZE SELECT i FROM tst WHERE c < 1 ORDER BY v <-> '$query' LIMIT $limit;
|
||||
));
|
||||
like($explain, qr/Seq Scan/);
|
||||
# TODO Do not use index
|
||||
like($explain, qr/Index Scan using idx/);
|
||||
|
||||
# Test attribute filtering with few rows removed like
|
||||
$explain = $node->safe_psql("postgres", qq(
|
||||
|
||||
@@ -17,11 +17,12 @@ $node->safe_psql("postgres", "CREATE EXTENSION vector;");
|
||||
for my $dim (@dims)
|
||||
{
|
||||
my $array_sql = join(",", ('random()') x $dim);
|
||||
my $n = $dim == 384 ? 3000 : 1000;
|
||||
|
||||
# Create table and index
|
||||
$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim));");
|
||||
$node->safe_psql("postgres",
|
||||
"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 2000) i;"
|
||||
"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, $n) i;"
|
||||
);
|
||||
$node->safe_psql("postgres", "CREATE INDEX idx ON tst USING hnsw (v vector_l2_ops);");
|
||||
$node->safe_psql("postgres", "ANALYZE tst;");
|
||||
@@ -39,16 +40,6 @@ for my $dim (@dims)
|
||||
));
|
||||
like($explain, qr/Index Scan using idx/);
|
||||
|
||||
# 3x the rows are needed for distance filters
|
||||
# since the planner uses DEFAULT_INEQ_SEL for the selectivity (should be 1)
|
||||
# Recreate index for performance
|
||||
$node->safe_psql("postgres", "DROP INDEX idx;");
|
||||
$node->safe_psql("postgres",
|
||||
"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(2001, 6000) i;"
|
||||
);
|
||||
$node->safe_psql("postgres", "CREATE INDEX idx ON tst USING hnsw (v vector_l2_ops);");
|
||||
$node->safe_psql("postgres", "ANALYZE tst;");
|
||||
|
||||
$explain = $node->safe_psql("postgres", qq(
|
||||
EXPLAIN ANALYZE SELECT i FROM tst WHERE v <-> '$query' < 1 ORDER BY v <-> '$query' LIMIT $limit;
|
||||
));
|
||||
|
||||
@@ -21,7 +21,7 @@ for my $dim (@dims)
|
||||
# Create table and index
|
||||
$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim));");
|
||||
$node->safe_psql("postgres",
|
||||
"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 5000) i;"
|
||||
"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 6000) i;"
|
||||
);
|
||||
$node->safe_psql("postgres", "CREATE INDEX idx ON tst USING ivfflat (v vector_l2_ops) WITH (lists = 5);");
|
||||
$node->safe_psql("postgres", "ANALYZE tst;");
|
||||
|
||||
@@ -1,67 +0,0 @@
|
||||
use strict;
|
||||
use warnings FATAL => 'all';
|
||||
use PostgreSQL::Test::Cluster;
|
||||
use PostgreSQL::Test::Utils;
|
||||
use Test::More;
|
||||
|
||||
my $dim = 3;
|
||||
my $array_sql = join(",", ('random()') x $dim);
|
||||
|
||||
# Initialize node
|
||||
my $node = PostgreSQL::Test::Cluster->new('node');
|
||||
$node->init;
|
||||
$node->start;
|
||||
|
||||
# Create table
|
||||
$node->safe_psql("postgres", "CREATE EXTENSION vector;");
|
||||
$node->safe_psql("postgres", "CREATE TABLE tst (i int4 PRIMARY KEY, v vector($dim));");
|
||||
$node->safe_psql("postgres",
|
||||
"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 100000) i;"
|
||||
);
|
||||
$node->safe_psql("postgres", qq(
|
||||
SET maintenance_work_mem = '128MB';
|
||||
SET max_parallel_maintenance_workers = 2;
|
||||
CREATE INDEX ON tst USING hnsw (v vector_l2_ops)
|
||||
));
|
||||
|
||||
my $count = $node->safe_psql("postgres", qq(
|
||||
SET enable_seqscan = off;
|
||||
SET hnsw.streaming = on;
|
||||
SET work_mem = '8MB';
|
||||
SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst LIMIT 1) LIMIT 11) t;
|
||||
));
|
||||
is($count, 10);
|
||||
|
||||
foreach ((30000, 50000, 70000))
|
||||
{
|
||||
my $ef_stream = $_;
|
||||
my $expected = $ef_stream / 10000;
|
||||
my $sum = 0;
|
||||
|
||||
for my $i (1 .. 20)
|
||||
{
|
||||
$count = $node->safe_psql("postgres", qq(
|
||||
SET enable_seqscan = off;
|
||||
SET hnsw.streaming = on;
|
||||
SET hnsw.ef_stream = $ef_stream;
|
||||
SET work_mem = '8MB';
|
||||
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;
|
||||
}
|
||||
|
||||
my $avg = $sum / 20;
|
||||
cmp_ok($avg, '>', $expected - 2);
|
||||
cmp_ok($avg, '<', $expected + 2);
|
||||
}
|
||||
|
||||
my ($ret, $stdout, $stderr) = $node->psql("postgres", qq(
|
||||
SET enable_seqscan = off;
|
||||
SET hnsw.streaming = on;
|
||||
SET client_min_messages = debug1;
|
||||
SET work_mem = '2MB';
|
||||
SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst LIMIT 1) LIMIT 11) t;
|
||||
));
|
||||
like($stderr, qr/hnsw index scan exceeded work_mem after \d+ tuples/);
|
||||
|
||||
done_testing();
|
||||
@@ -1,131 +0,0 @@
|
||||
use strict;
|
||||
use warnings FATAL => 'all';
|
||||
use PostgreSQL::Test::Cluster;
|
||||
use PostgreSQL::Test::Utils;
|
||||
use Test::More;
|
||||
|
||||
my $node;
|
||||
my @queries = ();
|
||||
my @expected;
|
||||
my $limit = 20;
|
||||
my $dim = 3;
|
||||
my $array_sql = join(",", ('random()') x $dim);
|
||||
my @cs = (100, 1000);
|
||||
|
||||
sub test_recall
|
||||
{
|
||||
my ($c, $ef_search, $min, $operator) = @_;
|
||||
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.streaming = on;
|
||||
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/);
|
||||
|
||||
for my $i (0 .. $#queries)
|
||||
{
|
||||
my $actual = $node->safe_psql("postgres", qq(
|
||||
SET enable_seqscan = off;
|
||||
SET hnsw.ef_search = $ef_search;
|
||||
SET hnsw.streaming = on;
|
||||
SELECT i FROM tst WHERE i % $c = 0 ORDER BY v $operator '$queries[$i]' LIMIT $limit;
|
||||
));
|
||||
my @actual_ids = split("\n", $actual);
|
||||
|
||||
my @expected_ids = split("\n", $expected[$i]);
|
||||
my %expected_set = map { $_ => 1 } @expected_ids;
|
||||
|
||||
foreach (@actual_ids)
|
||||
{
|
||||
if (exists($expected_set{$_}))
|
||||
{
|
||||
$correct++;
|
||||
}
|
||||
}
|
||||
|
||||
$total += $limit;
|
||||
}
|
||||
|
||||
cmp_ok($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));");
|
||||
$node->safe_psql("postgres",
|
||||
"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 100000) i;"
|
||||
);
|
||||
|
||||
# Generate queries
|
||||
for (1 .. 20)
|
||||
{
|
||||
my @r = ();
|
||||
for (1 .. $dim)
|
||||
{
|
||||
push(@r, rand());
|
||||
}
|
||||
push(@queries, "[" . join(",", @r) . "]");
|
||||
}
|
||||
|
||||
# Check each index type
|
||||
my @operators = ("<->", "<=>");
|
||||
my @opclasses = ("vector_l2_ops", "vector_cosine_ops");
|
||||
|
||||
for my $i (0 .. $#operators)
|
||||
{
|
||||
my $operator = $operators[$i];
|
||||
my $opclass = $opclasses[$i];
|
||||
|
||||
$node->safe_psql("postgres", qq(
|
||||
SET maintenance_work_mem = '128MB';
|
||||
CREATE INDEX idx ON tst USING hnsw (v $opclass);
|
||||
));
|
||||
|
||||
foreach (@cs)
|
||||
{
|
||||
my $c = $_;
|
||||
|
||||
# Get exact results
|
||||
@expected = ();
|
||||
foreach (@queries)
|
||||
{
|
||||
my $res = $node->safe_psql("postgres", qq(
|
||||
SET enable_indexscan = off;
|
||||
WITH top AS (
|
||||
SELECT v $operator '$_' AS distance FROM tst WHERE i % $c = 0 ORDER BY distance LIMIT $limit
|
||||
)
|
||||
SELECT i FROM tst WHERE (v $operator '$_') <= (SELECT MAX(distance) FROM top)
|
||||
));
|
||||
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);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
$node->safe_psql("postgres", "DROP INDEX idx;");
|
||||
}
|
||||
|
||||
done_testing();
|
||||
Reference in New Issue
Block a user