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

Added support for xidmap in bulkloader #5090

Merged
merged 6 commits into from
Apr 8, 2020
Merged

Added support for xidmap in bulkloader #5090

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
f4c8af0
Added support for xidmap in bulkloader
all-seeing-code Apr 3, 2020
86d1c97
Removed options as per review
all-seeing-code Apr 6, 2020
da87074
Remove unnecessary conditional block
all-seeing-code Apr 6, 2020
2ac0e04
Close the db
all-seeing-code Apr 7, 2020
e784930
Minor formatting
all-seeing-code Apr 7, 2020
0853225
Do not close a nil db
all-seeing-code Apr 7, 2020
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
11 changes: 10 additions & 1 deletion dgraph/cmd/bulk/loader.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,6 +61,7 @@ type options struct {
IgnoreErrors bool
CustomTokenizers string
NewUids bool
ClientDir string

MapShards int
ReduceShards int
Expand Down Expand Up @@ -161,7 +162,15 @@ func readSchema(filename string) *schema.ParsedSchema {

func (ld *loader) mapStage() {
ld.prog.setPhase(mapPhase)
ld.xids = xidmap.New(ld.zero, nil)
var db *badger.DB
if len(ld.opt.ClientDir) > 0 {
x.Check(os.MkdirAll(ld.opt.ClientDir, 0700))

var err error
db, err = badger.Open(badger.DefaultOptions(ld.opt.ClientDir))
x.Checkf(err, "Error while creating badger KV posting store")
}
ld.xids = xidmap.New(ld.zero, db)

files := x.FindDataFiles(ld.opt.DataFiles, []string{".rdf", ".rdf.gz", ".json", ".json.gz"})
if len(files) == 0 {
Expand Down
2 changes: 2 additions & 0 deletions dgraph/cmd/bulk/run.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,6 +81,7 @@ func init() {
flag.Bool("version", false, "Prints the version of Dgraph Bulk Loader.")
flag.BoolP("store_xids", "x", false, "Generate an xid edge for each node.")
flag.StringP("zero", "z", "localhost:5080", "gRPC address for Dgraph zero")
flag.String("xidmap", "", "Directory to store xid to uid mapping")
// TODO: Potentially move http server to main.
flag.String("http", "localhost:8080",
"Address to serve http (pprof).")
Expand Down Expand Up @@ -129,6 +130,7 @@ func run() {
ReduceShards: Bulk.Conf.GetInt("reduce_shards"),
CustomTokenizers: Bulk.Conf.GetString("custom_tokenizers"),
NewUids: Bulk.Conf.GetBool("new_uids"),
ClientDir: Bulk.Conf.GetString("xidmap"),

BadgerKeyFile: Bulk.Conf.GetString("encryption_key_file"),
BadgerCompressionLevel: Bulk.Conf.GetInt("badger.compression_level"),
Expand Down