initial commit

src/mr/worker.go

@@ -1,77 +1,175 @@
 package mr
 
-import "fmt"
-import "log"
-import "net/rpc"
-import "hash/fnv"
+import (
+	"bytes"
+	"encoding/json"
+	"fmt"
+	"hash/fnv"
+	"io"
+	"log"
+	"net/rpc"
+	"os"
+	"path/filepath"
+	"strings"
+)
 
-
-//
 // Map functions return a slice of KeyValue.
-//
 type KeyValue struct {
 	Key   string
 	Value string
 }
 
-//
 // use ihash(key) % NReduce to choose the reduce
 // task number for each KeyValue emitted by Map.
-//
 func ihash(key string) int {
 	h := fnv.New32a()
 	h.Write([]byte(key))
 	return int(h.Sum32() & 0x7fffffff)
 }
 
-
-//
 // main/mrworker.go calls this function.
-//
 func Worker(mapf func(string, string) []KeyValue,
 	reducef func(string, []string) string) {
-
 	// Your worker implementation here.
+	taskType, inFilename, nReduce := RequestTask()
+	fmt.Printf("Perform %s task on: %s", taskType, inFilename)
+	file, err := os.Open(inFilename)
+	if err != nil {
+		log.Fatalf("cannot open %v", inFilename)
+	}
+	content, err := io.ReadAll(file)
+	if err != nil {
+		log.Fatalf("cannot read %v", inFilename)
+	}
+	file.Close()
+	if taskType == "map" {
+		intermediateFiles := []string{}
+		kva := mapf(inFilename, string(content))
+		//hash the map job id
+		mapTaskIdx := ihash(inFilename)
+		for i := range kva {
+			log.Printf("%s: %s", kva[i].Key, kva[i].Value)
+			idx := ihash(kva[i].Key) % nReduce
+			mapOutFn := fmt.Sprintf("mr-%d-%d", mapTaskIdx, idx)
+			// add to intermediate file list
+			intermediateFiles = append(intermediateFiles, mapOutFn)
+			// write intermidiate files
+			data, err := json.MarshalIndent(kva[i], "", " ")
+			if err != nil {
+				log.Fatalf("failed to serialize map to JSON: %w", err)
+			}
+			if err = WriteTempAtomic(mapOutFn, data); err != nil {
+				log.Fatalf("failed to write KV map to file: %w", err)
+			}
+		}
+		SetTaskDone("map", inFilename, intermediateFiles)
+		return
 
-	// uncomment to send the Example RPC to the coordinator.
-	// CallExample()
+	} else if taskType == "reduce" {
+		intermediate := []KeyValue{}
 
+		// Prepare output file
+		oFilename := strings.Split(inFilename, ",")[1]
+		var buffer bytes.Buffer
+		i := 0
+		for i < len(intermediate) {
+			j := i + 1
+			for j < len(intermediate) && intermediate[j].Key == intermediate[i].Key {
+				j++
+			}
+			values := []string{}
+			for k := i; k < j; k++ {
+				values = append(values, intermediate[k].Value)
+			}
+			output := reducef(intermediate[i].Key, values)
+
+			// this is the correct format for each line of Reduce output.
+			fmt.Fprintf(&buffer, "%v %v\n", intermediate[i].Key, output)
+
+			i = j
+		}
+		if err = WriteTempAtomic(oFilename, buffer.Bytes()); err != nil {
+			log.Fatalf("failed to write KV map to file: %w", err)
+		}
+		SetTaskDone("reduce", inFilename, []string{})
+		return
+	}
 }
 
-//
-// example function to show how to make an RPC call to the coordinator.
-//
-// the RPC argument and reply types are defined in rpc.go.
-//
-func CallExample() {
+func WriteTempAtomic(fn string, data []byte) error {
+	// Create a temporary file in the target directory
+	currentDir, err := os.Getwd()
+	tempFile, err := os.CreateTemp(currentDir, fn)
+	if err != nil {
+		return fmt.Errorf("failed to create temp file: %w", err)
+	}
+	tempPath := tempFile.Name()
 
-	// declare an argument structure.
-	args := ExampleArgs{}
+	if _, err := tempFile.Write(data); err != nil {
+		tempFile.Close()
+		os.Remove(tempPath)
+		return fmt.Errorf("failed to write to temp file: %w", err)
+	}
 
-	// fill in the argument(s).
-	args.X = 99
+	// Ensure the file is fully written to disk
+	if err := tempFile.Sync(); err != nil {
+		tempFile.Close()
+		os.Remove(tempPath)
+		return fmt.Errorf("failed to sync temp file: %w", err)
+	}
 
-	// declare a reply structure.
-	reply := ExampleReply{}
+	if err := tempFile.Close(); err != nil {
+		os.Remove(tempPath)
+		return fmt.Errorf("failed to close temp file: %w", err)
+	}
 
-	// send the RPC request, wait for the reply.
-	// the "Coordinator.Example" tells the
-	// receiving server that we'd like to call
-	// the Example() method of struct Coordinator.
-	ok := call("Coordinator.Example", &args, &reply)
+	// Compute the target file path
+	targetPath := filepath.Join(currentDir, fn)
+
+	// Atomically replace the target file with the temporary file
+	if err := os.Rename(tempPath, targetPath); err != nil {
+		os.Remove(tempPath)
+		return fmt.Errorf("failed to rename temp file to target: %w", err)
+	}
+	return nil
+}
+
+// RPC call to set the task status to done
+func SetTaskDone(taskType string, filename string, intermediateFiles []string) {
+	args := RpcArgument{}
+	args.Method = "set_task_done"
+	args.TaskType = taskType
+	args.Filename = filename
+	args.IntermediateFiles = intermediateFiles
+	reply := RpcReply{}
+	ok := call("Coordinator.SetTaskDone", &args, &reply)
 	if ok {
-		// reply.Y should be 100.
-		fmt.Printf("reply.Y %v\n", reply.Y)
+		fmt.Printf("ok")
 	} else {
 		fmt.Printf("call failed!\n")
 	}
 }
 
-//
+// RPC call to request task from coordinator
+func RequestTask() (string, string, int) {
+	// declare an arg and reply
+	args := RpcArgument{}
+	args.Method = "request_task"
+	reply := RpcReply{}
+
+	ok := call("Coordinator.GetTask", &args, &reply)
+	if ok {
+		fmt.Printf("reply.TaskType %v\n", reply.TaskType)
+		fmt.Printf("reply.InFilename %v\n", reply.Filename)
+	} else {
+		fmt.Printf("call failed!\n")
+	}
+	return reply.TaskType, reply.Filename, reply.NReduce
+}
+
 // send an RPC request to the coordinator, wait for the response.
 // usually returns true.
 // returns false if something goes wrong.
-//
 func call(rpcname string, args interface{}, reply interface{}) bool {
 	// c, err := rpc.DialHTTP("tcp", "127.0.0.1"+":1234")
 	sockname := coordinatorSock()