1
0
mirror of https://github.com/postgres/postgres.git synced 2025-07-05 07:21:24 +03:00

Add GetNamedDSA() and GetNamedDSHash().

Presently, the dynamic shared memory (DSM) registry only provides
GetNamedDSMSegment(), which allocates a fixed-size segment.  To use
the DSM registry for more sophisticated things like dynamic shared
memory areas (DSAs) or a hash table backed by a DSA (dshash), users
need to create a DSM segment that stores various handles and LWLock
tranche IDs and to write fairly complicated initialization code.
Furthermore, there is likely little variation in this
initialization code between libraries.

This commit introduces functions that simplify allocating a DSA or
dshash within the DSM registry.  These functions are very similar
to GetNamedDSMSegment().  Notable differences include the lack of
an initialization callback parameter and the prohibition of calling
the functions more than once for a given entry in each backend
(which should be trivially avoidable in most circumstances).  While
at it, this commit bumps the maximum DSM registry entry name length
from 63 bytes to 127 bytes.

Also note that even though one could presumably detach/destroy the
DSAs and dshashes created in the registry, such use-cases are not
yet well-supported, if for no other reason than the associated DSM
registry entries cannot be removed.  Adding such support is left as
a future exercise.

The test_dsm_registry test module contains tests for the new
functions and also serves as a complete usage example.

Reviewed-by: Dagfinn Ilmari Mannsåker <ilmari@ilmari.org>
Reviewed-by: Sami Imseih <samimseih@gmail.com>
Reviewed-by: Florents Tselai <florents.tselai@gmail.com>
Reviewed-by: Rahila Syed <rahilasyed90@gmail.com>
Discussion: https://postgr.es/m/aEC8HGy2tRQjZg_8%40nathan
This commit is contained in:
Nathan Bossart
2025-07-02 11:50:52 -05:00
parent 9ca30a0b04
commit fe07100e82
9 changed files with 400 additions and 46 deletions

View File

@ -15,6 +15,20 @@
* current backend. This function guarantees that only one backend
* initializes the segment and that all other backends just attach it.
*
* A DSA can be created in or retrieved from the registry by calling
* GetNamedDSA(). As with GetNamedDSMSegment(), if a DSA with the provided
* name does not yet exist, it is created. Otherwise, GetNamedDSA()
* ensures the DSA is attached to the current backend. This function
* guarantees that only one backend initializes the DSA and that all other
* backends just attach it.
*
* A dshash table can be created in or retrieved from the registry by
* calling GetNamedDSHash(). As with GetNamedDSMSegment(), if a hash
* table with the provided name does not yet exist, it is created.
* Otherwise, GetNamedDSHash() ensures the hash table is attached to the
* current backend. This function guarantees that only one backend
* initializes the table and that all other backends just attach it.
*
* Portions Copyright (c) 1996-2025, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
@ -32,6 +46,12 @@
#include "storage/shmem.h"
#include "utils/memutils.h"
#define DSMR_NAME_LEN 128
#define DSMR_DSA_TRANCHE_SUFFIX " DSA"
#define DSMR_DSA_TRANCHE_SUFFIX_LEN (sizeof(DSMR_DSA_TRANCHE_SUFFIX) - 1)
#define DSMR_DSA_TRANCHE_NAME_LEN (DSMR_NAME_LEN + DSMR_DSA_TRANCHE_SUFFIX_LEN)
typedef struct DSMRegistryCtxStruct
{
dsa_handle dsah;
@ -40,15 +60,48 @@ typedef struct DSMRegistryCtxStruct
static DSMRegistryCtxStruct *DSMRegistryCtx;
typedef struct DSMRegistryEntry
typedef struct NamedDSMState
{
char name[64];
dsm_handle handle;
size_t size;
} NamedDSMState;
typedef struct NamedDSAState
{
dsa_handle handle;
int tranche;
char tranche_name[DSMR_DSA_TRANCHE_NAME_LEN];
} NamedDSAState;
typedef struct NamedDSHState
{
NamedDSAState dsa;
dshash_table_handle handle;
int tranche;
char tranche_name[DSMR_NAME_LEN];
} NamedDSHState;
typedef enum DSMREntryType
{
DSMR_ENTRY_TYPE_DSM,
DSMR_ENTRY_TYPE_DSA,
DSMR_ENTRY_TYPE_DSH,
} DSMREntryType;
typedef struct DSMRegistryEntry
{
char name[DSMR_NAME_LEN];
DSMREntryType type;
union
{
NamedDSMState dsm;
NamedDSAState dsa;
NamedDSHState dsh;
} data;
} DSMRegistryEntry;
static const dshash_parameters dsh_params = {
offsetof(DSMRegistryEntry, handle),
offsetof(DSMRegistryEntry, type),
sizeof(DSMRegistryEntry),
dshash_strcmp,
dshash_strhash,
@ -141,7 +194,7 @@ GetNamedDSMSegment(const char *name, size_t size,
ereport(ERROR,
(errmsg("DSM segment name cannot be empty")));
if (strlen(name) >= offsetof(DSMRegistryEntry, handle))
if (strlen(name) >= offsetof(DSMRegistryEntry, type))
ereport(ERROR,
(errmsg("DSM segment name too long")));
@ -158,32 +211,39 @@ GetNamedDSMSegment(const char *name, size_t size,
entry = dshash_find_or_insert(dsm_registry_table, name, found);
if (!(*found))
{
NamedDSMState *state = &entry->data.dsm;
dsm_segment *seg;
entry->type = DSMR_ENTRY_TYPE_DSM;
/* Initialize the segment. */
dsm_segment *seg = dsm_create(size, 0);
seg = dsm_create(size, 0);
dsm_pin_segment(seg);
dsm_pin_mapping(seg);
entry->handle = dsm_segment_handle(seg);
entry->size = size;
state->handle = dsm_segment_handle(seg);
state->size = size;
ret = dsm_segment_address(seg);
if (init_callback)
(*init_callback) (ret);
}
else if (entry->size != size)
{
else if (entry->type != DSMR_ENTRY_TYPE_DSM)
ereport(ERROR,
(errmsg("requested DSM segment size does not match size of "
"existing segment")));
}
(errmsg("requested DSM segment does not match type of existing entry")));
else if (entry->data.dsm.size != size)
ereport(ERROR,
(errmsg("requested DSM segment size does not match size of existing segment")));
else
{
dsm_segment *seg = dsm_find_mapping(entry->handle);
NamedDSMState *state = &entry->data.dsm;
dsm_segment *seg;
/* If the existing segment is not already attached, attach it now. */
seg = dsm_find_mapping(state->handle);
if (seg == NULL)
{
seg = dsm_attach(entry->handle);
seg = dsm_attach(state->handle);
if (seg == NULL)
elog(ERROR, "could not map dynamic shared memory segment");
@ -198,3 +258,180 @@ GetNamedDSMSegment(const char *name, size_t size,
return ret;
}
/*
* Initialize or attach a named DSA.
*
* This routine returns a pointer to the DSA. A new LWLock tranche ID will be
* generated if needed. Note that the lock tranche will be registered with the
* provided name. Also note that this should be called at most once for a
* given DSA in each backend.
*/
dsa_area *
GetNamedDSA(const char *name, bool *found)
{
DSMRegistryEntry *entry;
MemoryContext oldcontext;
dsa_area *ret;
Assert(found);
if (!name || *name == '\0')
ereport(ERROR,
(errmsg("DSA name cannot be empty")));
if (strlen(name) >= offsetof(DSMRegistryEntry, type))
ereport(ERROR,
(errmsg("DSA name too long")));
/* Be sure any local memory allocated by DSM/DSA routines is persistent. */
oldcontext = MemoryContextSwitchTo(TopMemoryContext);
/* Connect to the registry. */
init_dsm_registry();
entry = dshash_find_or_insert(dsm_registry_table, name, found);
if (!(*found))
{
NamedDSAState *state = &entry->data.dsa;
entry->type = DSMR_ENTRY_TYPE_DSA;
/* Initialize the LWLock tranche for the DSA. */
state->tranche = LWLockNewTrancheId();
strcpy(state->tranche_name, name);
LWLockRegisterTranche(state->tranche, state->tranche_name);
/* Initialize the DSA. */
ret = dsa_create(state->tranche);
dsa_pin(ret);
dsa_pin_mapping(ret);
/* Store handle for other backends to use. */
state->handle = dsa_get_handle(ret);
}
else if (entry->type != DSMR_ENTRY_TYPE_DSA)
ereport(ERROR,
(errmsg("requested DSA does not match type of existing entry")));
else
{
NamedDSAState *state = &entry->data.dsa;
if (dsa_is_attached(state->handle))
ereport(ERROR,
(errmsg("requested DSA already attached to current process")));
/* Initialize existing LWLock tranche for the DSA. */
LWLockRegisterTranche(state->tranche, state->tranche_name);
/* Attach to existing DSA. */
ret = dsa_attach(state->handle);
dsa_pin_mapping(ret);
}
dshash_release_lock(dsm_registry_table, entry);
MemoryContextSwitchTo(oldcontext);
return ret;
}
/*
* Initialize or attach a named dshash table.
*
* This routine returns the address of the table. The tranche_id member of
* params is ignored; new tranche IDs will be generated if needed. Note that
* the DSA lock tranche will be registered with the provided name with " DSA"
* appended. The dshash lock tranche will be registered with the provided
* name. Also note that this should be called at most once for a given table
* in each backend.
*/
dshash_table *
GetNamedDSHash(const char *name, const dshash_parameters *params, bool *found)
{
DSMRegistryEntry *entry;
MemoryContext oldcontext;
dshash_table *ret;
Assert(params);
Assert(found);
if (!name || *name == '\0')
ereport(ERROR,
(errmsg("DSHash name cannot be empty")));
if (strlen(name) >= offsetof(DSMRegistryEntry, type))
ereport(ERROR,
(errmsg("DSHash name too long")));
/* Be sure any local memory allocated by DSM/DSA routines is persistent. */
oldcontext = MemoryContextSwitchTo(TopMemoryContext);
/* Connect to the registry. */
init_dsm_registry();
entry = dshash_find_or_insert(dsm_registry_table, name, found);
if (!(*found))
{
NamedDSAState *dsa_state = &entry->data.dsh.dsa;
NamedDSHState *dsh_state = &entry->data.dsh;
dshash_parameters params_copy;
dsa_area *dsa;
entry->type = DSMR_ENTRY_TYPE_DSH;
/* Initialize the LWLock tranche for the DSA. */
dsa_state->tranche = LWLockNewTrancheId();
sprintf(dsa_state->tranche_name, "%s%s", name, DSMR_DSA_TRANCHE_SUFFIX);
LWLockRegisterTranche(dsa_state->tranche, dsa_state->tranche_name);
/* Initialize the LWLock tranche for the dshash table. */
dsh_state->tranche = LWLockNewTrancheId();
strcpy(dsh_state->tranche_name, name);
LWLockRegisterTranche(dsh_state->tranche, dsh_state->tranche_name);
/* Initialize the DSA for the hash table. */
dsa = dsa_create(dsa_state->tranche);
dsa_pin(dsa);
dsa_pin_mapping(dsa);
/* Initialize the dshash table. */
memcpy(&params_copy, params, sizeof(dshash_parameters));
params_copy.tranche_id = dsh_state->tranche;
ret = dshash_create(dsa, &params_copy, NULL);
/* Store handles for other backends to use. */
dsa_state->handle = dsa_get_handle(dsa);
dsh_state->handle = dshash_get_hash_table_handle(ret);
}
else if (entry->type != DSMR_ENTRY_TYPE_DSH)
ereport(ERROR,
(errmsg("requested DSHash does not match type of existing entry")));
else
{
NamedDSAState *dsa_state = &entry->data.dsh.dsa;
NamedDSHState *dsh_state = &entry->data.dsh;
dsa_area *dsa;
/* XXX: Should we verify params matches what table was created with? */
if (dsa_is_attached(dsa_state->handle))
ereport(ERROR,
(errmsg("requested DSHash already attached to current process")));
/* Initialize existing LWLock tranches for the DSA and dshash table. */
LWLockRegisterTranche(dsa_state->tranche, dsa_state->tranche_name);
LWLockRegisterTranche(dsh_state->tranche, dsh_state->tranche_name);
/* Attach to existing DSA for the hash table. */
dsa = dsa_attach(dsa_state->handle);
dsa_pin_mapping(dsa);
/* Attach to existing dshash table. */
ret = dshash_attach(dsa, params, dsh_state->handle, NULL);
}
dshash_release_lock(dsm_registry_table, entry);
MemoryContextSwitchTo(oldcontext);
return ret;
}

View File

@ -531,6 +531,21 @@ dsa_attach(dsa_handle handle)
return area;
}
/*
* Returns whether the area with the given handle was already attached by the
* current process. The area must have been created with dsa_create (not
* dsa_create_in_place).
*/
bool
dsa_is_attached(dsa_handle handle)
{
/*
* An area handle is really a DSM segment handle for the first segment, so
* we can just search for that.
*/
return dsm_find_mapping(handle) != NULL;
}
/*
* Attach to an area that was created with dsa_create_in_place. The caller
* must somehow know the location in memory that was used when the area was

View File

@ -13,10 +13,15 @@
#ifndef DSM_REGISTRY_H
#define DSM_REGISTRY_H
#include "lib/dshash.h"
extern void *GetNamedDSMSegment(const char *name, size_t size,
void (*init_callback) (void *ptr),
bool *found);
extern dsa_area *GetNamedDSA(const char *name, bool *found);
extern dshash_table *GetNamedDSHash(const char *name,
const dshash_parameters *params,
bool *found);
extern Size DSMRegistryShmemSize(void);
extern void DSMRegistryShmemInit(void);

View File

@ -145,6 +145,7 @@ extern dsa_area *dsa_create_in_place_ext(void *place, size_t size,
size_t init_segment_size,
size_t max_segment_size);
extern dsa_area *dsa_attach(dsa_handle handle);
extern bool dsa_is_attached(dsa_handle handle);
extern dsa_area *dsa_attach_in_place(void *place, dsm_segment *segment);
extern void dsa_release_in_place(void *place);
extern void dsa_on_dsm_detach_release_in_place(dsm_segment *, Datum);

View File

@ -1,14 +1,26 @@
CREATE EXTENSION test_dsm_registry;
SELECT set_val_in_shmem(1236);
set_val_in_shmem
------------------
SELECT set_val_in_dsm(1236);
set_val_in_dsm
----------------
(1 row)
SELECT set_val_in_hash('test', '1414');
set_val_in_hash
-----------------
(1 row)
\c
SELECT get_val_in_shmem();
get_val_in_shmem
------------------
1236
SELECT get_val_in_dsm();
get_val_in_dsm
----------------
1236
(1 row)
SELECT get_val_in_hash('test');
get_val_in_hash
-----------------
1414
(1 row)

View File

@ -1,4 +1,6 @@
CREATE EXTENSION test_dsm_registry;
SELECT set_val_in_shmem(1236);
SELECT set_val_in_dsm(1236);
SELECT set_val_in_hash('test', '1414');
\c
SELECT get_val_in_shmem();
SELECT get_val_in_dsm();
SELECT get_val_in_hash('test');

View File

@ -3,8 +3,14 @@
-- complain if script is sourced in psql, rather than via CREATE EXTENSION
\echo Use "CREATE EXTENSION test_dsm_registry" to load this file. \quit
CREATE FUNCTION set_val_in_shmem(val INT) RETURNS VOID
CREATE FUNCTION set_val_in_dsm(val INT) RETURNS VOID
AS 'MODULE_PATHNAME' LANGUAGE C;
CREATE FUNCTION get_val_in_shmem() RETURNS INT
CREATE FUNCTION get_val_in_dsm() RETURNS INT
AS 'MODULE_PATHNAME' LANGUAGE C;
CREATE FUNCTION set_val_in_hash(key TEXT, val TEXT) RETURNS VOID
AS 'MODULE_PATHNAME' LANGUAGE C;
CREATE FUNCTION get_val_in_hash(key TEXT) RETURNS TEXT
AS 'MODULE_PATHNAME' LANGUAGE C;

View File

@ -15,6 +15,7 @@
#include "fmgr.h"
#include "storage/dsm_registry.h"
#include "storage/lwlock.h"
#include "utils/builtins.h"
PG_MODULE_MAGIC;
@ -24,15 +25,31 @@ typedef struct TestDSMRegistryStruct
LWLock lck;
} TestDSMRegistryStruct;
static TestDSMRegistryStruct *tdr_state;
typedef struct TestDSMRegistryHashEntry
{
char key[64];
dsa_pointer val;
} TestDSMRegistryHashEntry;
static TestDSMRegistryStruct *tdr_dsm;
static dsa_area *tdr_dsa;
static dshash_table *tdr_hash;
static const dshash_parameters dsh_params = {
offsetof(TestDSMRegistryHashEntry, val),
sizeof(TestDSMRegistryHashEntry),
dshash_strcmp,
dshash_strhash,
dshash_strcpy
};
static void
tdr_init_shmem(void *ptr)
init_tdr_dsm(void *ptr)
{
TestDSMRegistryStruct *state = (TestDSMRegistryStruct *) ptr;
TestDSMRegistryStruct *dsm = (TestDSMRegistryStruct *) ptr;
LWLockInitialize(&state->lck, LWLockNewTrancheId());
state->val = 0;
LWLockInitialize(&dsm->lck, LWLockNewTrancheId());
dsm->val = 0;
}
static void
@ -40,37 +57,91 @@ tdr_attach_shmem(void)
{
bool found;
tdr_state = GetNamedDSMSegment("test_dsm_registry",
sizeof(TestDSMRegistryStruct),
tdr_init_shmem,
&found);
LWLockRegisterTranche(tdr_state->lck.tranche, "test_dsm_registry");
tdr_dsm = GetNamedDSMSegment("test_dsm_registry_dsm",
sizeof(TestDSMRegistryStruct),
init_tdr_dsm,
&found);
LWLockRegisterTranche(tdr_dsm->lck.tranche, "test_dsm_registry");
if (tdr_dsa == NULL)
tdr_dsa = GetNamedDSA("test_dsm_registry_dsa", &found);
if (tdr_hash == NULL)
tdr_hash = GetNamedDSHash("test_dsm_registry_hash", &dsh_params, &found);
}
PG_FUNCTION_INFO_V1(set_val_in_shmem);
PG_FUNCTION_INFO_V1(set_val_in_dsm);
Datum
set_val_in_shmem(PG_FUNCTION_ARGS)
set_val_in_dsm(PG_FUNCTION_ARGS)
{
tdr_attach_shmem();
LWLockAcquire(&tdr_state->lck, LW_EXCLUSIVE);
tdr_state->val = PG_GETARG_INT32(0);
LWLockRelease(&tdr_state->lck);
LWLockAcquire(&tdr_dsm->lck, LW_EXCLUSIVE);
tdr_dsm->val = PG_GETARG_INT32(0);
LWLockRelease(&tdr_dsm->lck);
PG_RETURN_VOID();
}
PG_FUNCTION_INFO_V1(get_val_in_shmem);
PG_FUNCTION_INFO_V1(get_val_in_dsm);
Datum
get_val_in_shmem(PG_FUNCTION_ARGS)
get_val_in_dsm(PG_FUNCTION_ARGS)
{
int ret;
tdr_attach_shmem();
LWLockAcquire(&tdr_state->lck, LW_SHARED);
ret = tdr_state->val;
LWLockRelease(&tdr_state->lck);
LWLockAcquire(&tdr_dsm->lck, LW_SHARED);
ret = tdr_dsm->val;
LWLockRelease(&tdr_dsm->lck);
PG_RETURN_INT32(ret);
}
PG_FUNCTION_INFO_V1(set_val_in_hash);
Datum
set_val_in_hash(PG_FUNCTION_ARGS)
{
TestDSMRegistryHashEntry *entry;
char *key = TextDatumGetCString(PG_GETARG_DATUM(0));
char *val = TextDatumGetCString(PG_GETARG_DATUM(1));
bool found;
if (strlen(key) >= offsetof(TestDSMRegistryHashEntry, val))
ereport(ERROR,
(errmsg("key too long")));
tdr_attach_shmem();
entry = dshash_find_or_insert(tdr_hash, key, &found);
if (found)
dsa_free(tdr_dsa, entry->val);
entry->val = dsa_allocate(tdr_dsa, strlen(val) + 1);
strcpy(dsa_get_address(tdr_dsa, entry->val), val);
dshash_release_lock(tdr_hash, entry);
PG_RETURN_VOID();
}
PG_FUNCTION_INFO_V1(get_val_in_hash);
Datum
get_val_in_hash(PG_FUNCTION_ARGS)
{
TestDSMRegistryHashEntry *entry;
char *key = TextDatumGetCString(PG_GETARG_DATUM(0));
text *val = NULL;
tdr_attach_shmem();
entry = dshash_find(tdr_hash, key, false);
if (entry == NULL)
PG_RETURN_NULL();
val = cstring_to_text(dsa_get_address(tdr_dsa, entry->val));
dshash_release_lock(tdr_hash, entry);
PG_RETURN_TEXT_P(val);
}

View File

@ -601,6 +601,7 @@ DR_intorel
DR_printtup
DR_sqlfunction
DR_transientrel
DSMREntryType
DSMRegistryCtxStruct
DSMRegistryEntry
DWORD
@ -1737,6 +1738,9 @@ Name
NameData
NameHashEntry
NamedArgExpr
NamedDSAState
NamedDSHState
NamedDSMState
NamedLWLockTranche
NamedLWLockTrancheRequest
NamedTuplestoreScan
@ -3006,6 +3010,7 @@ Tcl_Obj
Tcl_Size
Tcl_Time
TempNamespaceStatus
TestDSMRegistryHashEntry
TestDSMRegistryStruct
TestDecodingData
TestDecodingTxnData