updated readme

README.md

@@ -1,3 +1,9 @@
+# Introduction
+
+#todo
+
+# Usage
+
 ```
 // Generates a random.txt file with parameters specified, and exits
 // parameters besides N, are only used internally to specify how big are the chunks written
@@ -19,3 +25,44 @@
   - N = 100000
   - b = 10
   - n = 101
+
+# Technical stuff
+
+## memory alocated
+
+- in total a b*m*sizeof(record) is alocated to memory for the buffers
+  - in stage 1 it is used as a continuous block for reading, sorting, and writing
+  - in stage 2 it is divided into b blocks, 1 for output, and b-1 for input, each block of size n
+- an additional (b-1)\*2 bytes is alocated separately to create the heap (saved as a pointer to record + file index)
+  - if could be carved out of the main memory block, but that would mean that buffers at stage 2 would need to be slightly smaller, and thus not cleanly divisible by n
+  - the amount of memory for this heap is negligable in the scope of the entire memory usage anyway
+
+## algorithm outline
+
+### stage 1
+
+In stage 1 the file is read in chunks of size b\*n, sorted in-memory, and saved as its own file
+The amount of created runs is saved in memory
+
+### stage 2
+
+In stage 2 each buffer is populated by the HEAD of the coresponding file
+
+- the HEAD pointer of each buffer is fed into a min heap, along with the computed g(record) value, and the buffer index
+- when a pop is performed from the heap, another record is read from the same buffer, and the popped item written to output buffer
+- when the output buffer is full, it is written to a file, subsequent writes are written to the same file
+- when an input buffer is empty, more of the file is read into it
+- when all input buffers are empty, the steps are repeated for any unprocessed input files
+  The amount of runs is saved in memory, if more than one run reamain the process is repeated
+
+## required functions
+
+- [ ] split_buffer - splits the buffer into an array of buffers of size n
+- [ ] heap_push, heap_pop
+  - the heap is operating on structs of type g(record), index, buffer_index, and comparing them based on g(record)
+  - [ ] push operation requires heapify function
+- [ ] buffer i/o operations
+
+# Analysis
+
+#todo

main.c

@@ -25,8 +25,9 @@ int sort_file(Configuration* opts)
 {
     buffer buff = create_buffer(opts->b * opts->n);
     FILE* in = fopen(opts->input_file, "r");
+    int runs;
     // <stage 1>
-    for (int i = 0; true; i++) {
+    for (runs = 0; true; runs++) {
         //     read buffer
         int status = read_buffer(&buff, in);
         if (status != SUCCESS && status != EOF) {
@@ -37,22 +38,22 @@ int sort_file(Configuration* opts)
         sort_buffer(&buff);
         //     write run
         char* filename = malloc(256);
-        sprintf(filename, "%s/%d", opts->directory, i);
+        sprintf(filename, "%s/%d", opts->directory, runs);
         FILE* tmp = fopen(filename, "w");
         write_buffer(&buff, tmp);
         fclose(tmp);
         free(filename);
-        // write_buffer_debug(&buff, stdout);
         if (status != SUCCESS) {
             break;
         }
     }
     // <stage 2>
-    // while tmp:
+    // while (runs > 1) {
-    //     merge b-1 runs
+    //     // split buffers
-    //
+    //     // read buffers
-    // close file
+    //     for (int i = 0; i < opts->b - 1; i++) {
-    // free buffer
+    //     }
+    // }
     fclose(in);
     free(buff.location);
     return SUCCESS;