/* * Select next block to sample. * * Uses linear probing algorithm for picking next block. */ static BlockNumber system_rows_nextsampleblock(SampleScanState *node) { SystemRowsSamplerData *sampler = (SystemRowsSamplerData *) node->tsm_state; TableScanDesc scan = node->ss.ss_currentScanDesc; HeapScanDesc hscan = (HeapScanDesc) scan; /* First call within scan? */ if (sampler->doneblocks == 0) { /* First scan within query? */ if (sampler->step == 0) { /* Initialize now that we have scan descriptor */ SamplerRandomState randstate; /* If relation is empty, there's nothing to scan */ if (hscan->rs_nblocks == 0) return InvalidBlockNumber; /* We only need an RNG during this setup step */ sampler_random_init_state(sampler->seed, randstate); /* Compute nblocks/firstblock/step only once per query */ sampler->nblocks = hscan->rs_nblocks; /* Choose random starting block within the relation */ /* (Actually this is the predecessor of the first block visited) */ sampler->firstblock = sampler_random_fract(randstate) * sampler->nblocks; /* Find relative prime as step size for linear probing */ sampler->step = random_relative_prime(sampler->nblocks, randstate); } /* Reinitialize lb */ sampler->lb = sampler->firstblock; } /* If we've read all blocks or returned all needed tuples, we're done */ if (++sampler->doneblocks > sampler->nblocks || sampler->donetuples >= sampler->ntuples) return InvalidBlockNumber; /* * It's probably impossible for scan->rs_nblocks to decrease between scans * within a query; but just in case, loop until we select a block number * less than scan->rs_nblocks. We don't care if scan->rs_nblocks has * increased since the first scan. */ do { /* Advance lb, using uint64 arithmetic to forestall overflow */ sampler->lb = ((uint64) sampler->lb + sampler->step) % sampler->nblocks; } while (sampler->lb >= hscan->rs_nblocks); return sampler->lb; }
/* * Reset state (called by ReScan). */ Datum tsm_system_time_reset(PG_FUNCTION_ARGS) { TableSampleDesc *tsdesc = (TableSampleDesc *) PG_GETARG_POINTER(0); SystemSamplerData *sampler = (SystemSamplerData *) tsdesc->tsmdata; sampler->lt = InvalidOffsetNumber; sampler->start_time = GetCurrentTimestamp(); sampler->end_time = TimestampTzPlusMilliseconds(sampler->start_time, sampler->time); sampler->estblocks = 2; sampler->doneblocks = 0; sampler_random_init_state(sampler->seed, sampler->randstate); sampler->step = random_relative_prime(sampler->nblocks, sampler->randstate); sampler->lb = sampler_random_fract(sampler->randstate) * (sampler->nblocks / sampler->step); PG_RETURN_VOID(); }
/* * Initializes the state. */ Datum tsm_system_time_init(PG_FUNCTION_ARGS) { TableSampleDesc *tsdesc = (TableSampleDesc *) PG_GETARG_POINTER(0); uint32 seed = PG_GETARG_UINT32(1); int32 time = PG_ARGISNULL(2) ? -1 : PG_GETARG_INT32(2); HeapScanDesc scan = tsdesc->heapScan; SystemSamplerData *sampler; if (time < 1) ereport(ERROR, (errcode(ERRCODE_NUMERIC_VALUE_OUT_OF_RANGE), errmsg("invalid time limit"), errhint("Time limit must be positive integer value."))); sampler = palloc0(sizeof(SystemSamplerData)); /* Remember initial values for reinit */ sampler->seed = seed; sampler->nblocks = scan->rs_nblocks; sampler->lt = InvalidOffsetNumber; sampler->estblocks = 2; sampler->doneblocks = 0; sampler->time = time; sampler->start_time = GetCurrentTimestamp(); sampler->end_time = TimestampTzPlusMilliseconds(sampler->start_time, sampler->time); sampler_random_init_state(sampler->seed, sampler->randstate); /* Find relative prime as step size for linear probing. */ sampler->step = random_relative_prime(sampler->nblocks, sampler->randstate); /* * Randomize start position so that blocks close to step size don't have * higher probability of being chosen on very short scan. */ sampler->lb = sampler_random_fract(sampler->randstate) * (sampler->nblocks / sampler->step); tsdesc->tsmdata = (void *) sampler; PG_RETURN_VOID(); }