github.com/dolthub/dolt/go@v0.40.5-0.20240520175717-68db7794bea6/store/nbs/gc_copier.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 nbs
    16  
    17  import (
    18  	"context"
    19  	"fmt"
    20  	"strings"
    21  
    22  	"github.com/dolthub/dolt/go/store/hash"
    23  )
    24  
    25  type gcErrAccum map[string]error
    26  
    27  var _ error = gcErrAccum{}
    28  
    29  func (ea gcErrAccum) add(path string, err error) {
    30  	ea[path] = err
    31  }
    32  
    33  func (ea gcErrAccum) isEmpty() bool {
    34  	return len(ea) == 0
    35  }
    36  
    37  func (ea gcErrAccum) Error() string {
    38  	var sb strings.Builder
    39  	sb.WriteString("error garbage collecting the following files:")
    40  	for filePath, err := range ea {
    41  		sb.WriteString(fmt.Sprintf("\t%s: %s", filePath, err.Error()))
    42  	}
    43  	return sb.String()
    44  }
    45  
    46  type gcCopier struct {
    47  	writer *CmpChunkTableWriter
    48  }
    49  
    50  func newGarbageCollectionCopier() (*gcCopier, error) {
    51  	writer, err := NewCmpChunkTableWriter("")
    52  	if err != nil {
    53  		return nil, err
    54  	}
    55  	return &gcCopier{writer}, nil
    56  }
    57  
    58  func (gcc *gcCopier) addChunk(ctx context.Context, c CompressedChunk) error {
    59  	return gcc.writer.AddCmpChunk(c)
    60  }
    61  
    62  func (gcc *gcCopier) copyTablesToDir(ctx context.Context, tfp tableFilePersister) (ts []tableSpec, err error) {
    63  	var filename string
    64  	filename, err = gcc.writer.Finish()
    65  	if err != nil {
    66  		return nil, err
    67  	}
    68  
    69  	if gcc.writer.ChunkCount() == 0 {
    70  		return []tableSpec{}, nil
    71  	}
    72  
    73  	defer func() {
    74  		_ = gcc.writer.Remove()
    75  	}()
    76  
    77  	addr, ok := hash.MaybeParse(filename)
    78  	if !ok {
    79  		return nil, fmt.Errorf("invalid filename: %s", filename)
    80  	}
    81  
    82  	exists, err := tfp.Exists(ctx, addr, uint32(gcc.writer.ChunkCount()), nil)
    83  	if err != nil {
    84  		return nil, err
    85  	}
    86  
    87  	if exists {
    88  		return []tableSpec{
    89  			{
    90  				name:       addr,
    91  				chunkCount: uint32(gcc.writer.ChunkCount()),
    92  			},
    93  		}, nil
    94  	}
    95  
    96  	// Attempt to rename the file to the destination if we are working with a fsTablePersister...
    97  	if mover, ok := tfp.(movingTableFilePersister); ok {
    98  		err = mover.TryMoveCmpChunkTableWriter(ctx, filename, gcc.writer)
    99  		if err == nil {
   100  			return []tableSpec{
   101  				{
   102  					name:       addr,
   103  					chunkCount: uint32(gcc.writer.ChunkCount()),
   104  				},
   105  			}, nil
   106  		}
   107  	}
   108  
   109  	// Otherwise, write the file through CopyTableFile.
   110  	r, err := gcc.writer.Reader()
   111  	if err != nil {
   112  		return nil, err
   113  	}
   114  	defer r.Close()
   115  	sz := gcc.writer.ContentLength()
   116  
   117  	err = tfp.CopyTableFile(ctx, r, filename, sz, uint32(gcc.writer.ChunkCount()))
   118  	if err != nil {
   119  		return nil, err
   120  	}
   121  
   122  	return []tableSpec{
   123  		{
   124  			name:       addr,
   125  			chunkCount: uint32(gcc.writer.ChunkCount()),
   126  		},
   127  	}, nil
   128  }