github.com/dolthub/dolt/go@v0.40.5-0.20240520175717-68db7794bea6/libraries/doltcore/sqle/index/async_indexed_lookups.go (about)

     1  // Copyright 2020 Dolthub, Inc.
     2  //
     3  // Licensed under the Apache License, Version 2.0 (the "License");
     4  // you may not use this file except in compliance with the License.
     5  // You may obtain a copy of the License at
     6  //
     7  //     http://www.apache.org/licenses/LICENSE-2.0
     8  //
     9  // Unless required by applicable law or agreed to in writing, software
    10  // distributed under the License is distributed on an "AS IS" BASIS,
    11  // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
    12  // See the License for the specific language governing permissions and
    13  // limitations under the License.
    14  
    15  package index
    16  
    17  import (
    18  	"context"
    19  	"fmt"
    20  	"runtime"
    21  
    22  	"github.com/dolthub/go-mysql-server/sql"
    23  
    24  	"github.com/dolthub/dolt/go/libraries/utils/async"
    25  	"github.com/dolthub/dolt/go/store/types"
    26  )
    27  
    28  type lookupResult struct {
    29  	idx uint64
    30  	r   sql.Row
    31  	err error
    32  }
    33  
    34  // toLookup represents an table lookup that should be performed by one of the global asyncLookups instance's worker routines
    35  type toLookup struct {
    36  	idx        uint64
    37  	t          types.Tuple
    38  	tupleToRow func(context.Context, types.Tuple) (sql.Row, error)
    39  	resBuf     *async.RingBuffer
    40  	epoch      int
    41  	ctx        context.Context
    42  }
    43  
    44  // asyncLookups is a pool of worker routines reading from a channel doing table lookups
    45  type asyncLookups struct {
    46  	ctx        context.Context
    47  	toLookupCh chan toLookup
    48  }
    49  
    50  // newAsyncLookups kicks off a number of worker routines and creates a channel for sending lookups to workers.  The
    51  // routines live for the life of the program
    52  func newAsyncLookups(bufferSize int) *asyncLookups {
    53  	toLookupCh := make(chan toLookup, bufferSize)
    54  	art := &asyncLookups{toLookupCh: toLookupCh}
    55  
    56  	return art
    57  }
    58  
    59  func (art *asyncLookups) start(numWorkers int) {
    60  	for i := 0; i < numWorkers; i++ {
    61  		go func() {
    62  			art.workerFunc()
    63  		}()
    64  	}
    65  }
    66  
    67  func (art *asyncLookups) workerFunc() {
    68  	f := func() {
    69  		var curr toLookup
    70  		var ok bool
    71  
    72  		defer func() {
    73  			if r := recover(); r != nil {
    74  				// Attempt to write a failure to the channel and discard any additional errors
    75  				if err, ok := r.(error); ok {
    76  					_ = curr.resBuf.Push(lookupResult{idx: curr.idx, r: nil, err: err}, curr.epoch)
    77  				} else {
    78  					_ = curr.resBuf.Push(lookupResult{idx: curr.idx, r: nil, err: fmt.Errorf("%v", r)}, curr.epoch)
    79  				}
    80  			}
    81  
    82  			// if the channel used for lookups is closed then fail spectacularly
    83  			if !ok {
    84  				panic("toLookup channel closed.  All lookups will fail and will result in a deadlock")
    85  			}
    86  		}()
    87  
    88  		for {
    89  			curr, ok = <-art.toLookupCh
    90  
    91  			if !ok {
    92  				break
    93  			}
    94  
    95  			r, err := curr.tupleToRow(curr.ctx, curr.t)
    96  			_ = curr.resBuf.Push(lookupResult{idx: curr.idx, r: r, err: err}, curr.epoch)
    97  		}
    98  	}
    99  
   100  	// these routines will run forever unless f is allowed to panic which only happens when the lookup channel is closed
   101  	for {
   102  		f()
   103  	}
   104  }
   105  
   106  // lookups is a global asyncLookups instance which is used by the indexLookupRowIterAdapter
   107  var lookups *asyncLookups
   108  
   109  func init() {
   110  	lookups = newAsyncLookups(runtime.NumCPU() * 256)
   111  	lookups.start(runtime.NumCPU())
   112  }