Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Change the mapper output directory from $TMP/shards to $TMP/map_output #3960

Merged
merged 2 commits into from
Sep 19, 2019
Merged

Change the mapper output directory from $TMP/shards to $TMP/map_output #3960

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
27bc0cc
Change the mapper output directory from $TMP/shards to $TMP/map_output
Sep 11, 2019
756d9bd
Address review comments
ashish-goswami Sep 18, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion dgraph/cmd/bulk/mapper.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -89,7 +89,7 @@ func (m *mapper) openOutputFile(shardIdx int) (*os.File, error) {
fileNum := atomic.AddUint32(&m.mapFileId, 1)
filename := filepath.Join(
m.opt.TmpDir,
"shards",
mapShardDir,
fmt.Sprintf("%03d", shardIdx),
fmt.Sprintf("%06d.map.gz", fileNum),
)
Expand Down
15 changes: 10 additions & 5 deletions dgraph/cmd/bulk/merge_shards.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,12 +26,17 @@ import (
"github.com/dgraph-io/dgraph/x"
)

const (
mapShardDir = "map_output"
reduceShardDir = "shards"
)

func mergeMapShardsIntoReduceShards(opt options) {
mapShards := shardDirs(opt.TmpDir)
mapShards := shardDirs(filepath.Join(opt.TmpDir, mapShardDir))

var reduceShards []string
for i := 0; i < opt.ReduceShards; i++ {
shardDir := filepath.Join(opt.TmpDir, "shards", fmt.Sprintf("shard_%d", i))
shardDir := filepath.Join(opt.TmpDir, reduceShardDir, fmt.Sprintf("shard_%d", i))
x.Check(os.MkdirAll(shardDir, 0755))
reduceShards = append(reduceShards, shardDir)
}
Expand All @@ -47,14 +52,14 @@ func mergeMapShardsIntoReduceShards(opt options) {
}
}

func shardDirs(tmpDir string) []string {
dir, err := os.Open(filepath.Join(tmpDir, "shards"))
func shardDirs(d string) []string {
dir, err := os.Open(d)
x.Check(err)
shards, err := dir.Readdirnames(0)
x.Check(err)
dir.Close()
for i, shard := range shards {
shards[i] = filepath.Join(tmpDir, "shards", shard)
shards[i] = filepath.Join(d, shard)
}

// Allow largest shards to be shuffled first.
Expand Down
3 changes: 2 additions & 1 deletion dgraph/cmd/bulk/reduce.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,7 @@ import (
"io"
"log"
"os"
"path/filepath"
"sync/atomic"

"github.com/dgraph-io/badger"
Expand All @@ -45,7 +46,7 @@ type reducer struct {
}

func (r *reducer) run() error {
dirs := shardDirs(r.opt.TmpDir)
dirs := shardDirs(filepath.Join(r.opt.TmpDir, reduceShardDir))
x.AssertTrue(len(dirs) == r.opt.ReduceShards)
x.AssertTrue(len(r.opt.shardOutputDirs) == r.opt.ReduceShards)

Expand Down