简单数据库实现——Part5 - 持久存储到磁盘

简单数据库实现——Part5 - 持久存储到磁盘

目前的数据库在终止程序重新启动后会丢失所有记录，所以我们会通过将整个数据库保存到一个文件来保存记录。

我们已经通过将行序列化到页面大小的内存快中，为了增加持久性，我们可以简单的将内存块写入文件并在下次程序启动时读入内存。

为了简化这一过程，我们将进行一个称为寻呼机(pager)的抽象。我们向寻呼机询问页码x，寻呼机返回给我们一块内存。它会首先查看他的缓存(cache)，如果缓存中不存在，那么它会从磁盘(disk)中将数据复制到内存中。

寻呼机(pager)访问页面缓存和文件，表对象通过寻呼机请求页面：

+typedef struct {
+  int file_descriptor;
+  uint32_t file_length;
+  void* pages[TABLE_MAX_PAGES];
+} Pager;
+
 typedef struct {
-  void* pages[TABLE_MAX_PAGES];
+  Pager* pager;
   uint32_t num_rows;
 } Table;

将 new_table() 重命名为 db_open() ，因为它现在的作用是连接数据库：

• 打开数据库文件
• 初始化寻呼机(pager)数据结构
• 初始化表(table)数据结构

-Table* new_table() {
+Table* db_open(const char* filename) {
+  Pager* pager = pager_open(filename);
+  uint32_t num_rows = pager->file_length / ROW_SIZE;
+
   Table* table = malloc(sizeof(Table));
-  table->num_rows = 0;
+  table->pager = pager;
+  table->num_rows = num_rows;

   return table;
 }

db_open() 依次调用 paper_open()，这将打开数据文件并跟踪其大小。它还将页面缓存初始化为 NULL 。

函数的使用：
open()函数(APUE 3.3和4.5节)：

#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
int open(const char *pathname, int oflag,.../*, mode_t mode */);
/* 返回：若成功为文件描述符若出错为-1 */

pathname是要打开或创建的文件的名字。oflag参数可用来说明此函数的多个选择项。

• O_RDWR 读、写打开
• O_CREAT 若此文件不存在则创建它。使用此选择项时，需同时说明第三个参数mode，用其说明该新文件的存取许可权位。
• S_IWUSR 用户-写
• S_IRUSR 用户-读

lseek()函数(APUE 3.6节)：

#include <sys/types.h>
#include <unistd.h>
off_t lseek(int filedes, off_t offset, int whence);
/*返回：若成功为新的文件位移若出错为-1 */

对参数offset的解释与参数whence的值有关。

• 若whence是SEEK_END，则将该文件的位移量设置为文件长度加offset，offset可为正或负。
  若lseek成功执行，则返回新的文件位移量。

+Pager* pager_open(const char* filename) {
+  int fd = open(filename,
+                O_RDWR |      // Read/Write mode
+                    O_CREAT,  // Create file if it does not exist
+                S_IWUSR |     // User write permission
+                    S_IRUSR   // User read permission
+                );
+
+  if (fd == -1) {
+    printf("Unable to open file\n");
+    exit(EXIT_FAILURE);
+  }
+
+  off_t file_length = lseek(fd, 0, SEEK_END);
+
+  Pager* pager = malloc(sizeof(Pager));
+  pager->file_descriptor = fd;
+  pager->file_length = file_length;
+
+  for (uint32_t i = 0; i < TABLE_MAX_PAGES; i++) {
+    pager->pages[i] = NULL;
+  }
+
+  return pager;
+}

我们现在将获取页面移动到它自己的方法 get_page() 中。

 void* row_slot(Table* table, uint32_t row_num) {
   uint32_t page_num = row_num / ROWS_PER_PAGE;
-  void* page = table->pages[page_num];
-  if (page == NULL) {
-    // Allocate memory only when we try to access page
-    page = table->pages[page_num] = malloc(PAGE_SIZE);
-  }
+  void* page = get_page(table->pager, page_num);
   uint32_t row_offset = row_num % ROWS_PER_PAGE;
   uint32_t byte_offset = row_offset * ROW_SIZE;
   return page + byte_offset;
 }

get_page()方法可以处理缓存丢失。我们假设页面一个接一个保存在数据库文件中：第0页位于偏移量0，第1页位于偏移量4096，第2页位于偏移量8192，等等。如果请求的页面位于文件的边界之外，我们知道它应该是空的，所以我们只需分配一些内存并返回它。当我们稍后将缓存更新到磁盘时，该页面将被添加到文件中。

+void* get_page(Pager* pager, uint32_t page_num) {
+  if (page_num > TABLE_MAX_PAGES) {
+    printf("Tried to fetch page number out of bounds. %d > %d\n", page_num,
+           TABLE_MAX_PAGES);
+    exit(EXIT_FAILURE);
+  }
+
+  if (pager->pages[page_num] == NULL) {
+    // Cache miss. Allocate memory and load from file.
+    void* page = malloc(PAGE_SIZE);
+    uint32_t num_pages = pager->file_length / PAGE_SIZE;
+
+    // We might save a partial page at the end of the file
+    if (pager->file_length % PAGE_SIZE) {
+      num_pages += 1;
+    }
+
+    if (page_num <= num_pages) {
+      lseek(pager->file_descriptor, page_num * PAGE_SIZE, SEEK_SET);
+      ssize_t bytes_read = read(pager->file_descriptor, page, PAGE_SIZE);
+      if (bytes_read == -1) {
+        printf("Error reading file: %d\n", errno);
+        exit(EXIT_FAILURE);
+      }
+    }
+
+    pager->pages[page_num] = page;
+  }
+
+  return pager->pages[page_num];
+}

现在，我们等待将缓存更新到磁盘，直到用户关闭数据库连接。当用户退出时，我们将调用一个名为db_close()的新方法。这个方法将会：

• 将缓存更新到磁盘
• 关闭数据库文件
• 释放寻呼机和表数据结构的内存

+void db_close(Table* table) {
+  Pager* pager = table->pager;
+  uint32_t num_full_pages = table->num_rows / ROWS_PER_PAGE;
+
+  for (uint32_t i = 0; i < num_full_pages; i++) {
+    if (pager->pages[i] == NULL) {
+      continue;
+    }
+    pager_flush(pager, i, PAGE_SIZE);
+    free(pager->pages[i]);
+    pager->pages[i] = NULL;
+  }
+
+  // There may be a partial page to write to the end of the file
+  // This should not be needed after we switch to a B-tree
+  uint32_t num_additional_rows = table->num_rows % ROWS_PER_PAGE;
+  if (num_additional_rows > 0) {
+    uint32_t page_num = num_full_pages;
+    if (pager->pages[page_num] != NULL) {
+      pager_flush(pager, page_num, num_additional_rows * ROW_SIZE);
+      free(pager->pages[page_num]);
+      pager->pages[page_num] = NULL;
+    }
+  }
+
+  int result = close(pager->file_descriptor);
+  if (result == -1) {
+    printf("Error closing db file.\n");
+    exit(EXIT_FAILURE);
+  }
+  for (uint32_t i = 0; i < TABLE_MAX_PAGES; i++) {
+    void* page = pager->pages[i];
+    if (page) {
+      free(page);
+      pager->pages[i] = NULL;
+    }
+  }
+  free(pager);
+  free(table);
+}
+
-MetaCommandResult do_meta_command(InputBuffer* input_buffer) {
+MetaCommandResult do_meta_command(InputBuffer* input_buffer, Table* table) {
   if (strcmp(input_buffer->buffer, ".exit") == 0) {
+    db_close(table);
     exit(EXIT_SUCCESS);
   } else {
     return META_COMMAND_UNRECOGNIZED_COMMAND;

在我们当前的设计中，文件的长度编码了数据库中的行数，因此我们要在文件的末尾写入部分页面。这就是为什么pager_flush()同时接受页码和大小。它不是最好的设计，它会在我们开始实现B树时去除。

+void pager_flush(Pager* pager, uint32_t page_num, uint32_t size) {
+  if (pager->pages[page_num] == NULL) {
+    printf("Tried to flush null page\n");
+    exit(EXIT_FAILURE);
+  }
+
+  off_t offset = lseek(pager->file_descriptor, page_num * PAGE_SIZE, SEEK_SET);
+
+  if (offset == -1) {
+    printf("Error seeking: %d\n", errno);
+    exit(EXIT_FAILURE);
+  }
+
+  ssize_t bytes_written =
+      write(pager->file_descriptor, pager->pages[page_num], size);
+
+  if (bytes_written == -1) {
+    printf("Error writing: %d\n", errno);
+    exit(EXIT_FAILURE);
+  }
+}

最后，我们需要接受文件名作为命令行参数。不要忘记添加额外的参数来do_meta_command。

 int main(int argc, char* argv[]) {
-  Table* table = new_table();
+  if (argc < 2) {
+    printf("Must supply a database filename.\n");
+    exit(EXIT_FAILURE);
+  }
+
+  char* filename = argv[1];
+  Table* table = db_open(filename);
+
   InputBuffer* input_buffer = new_input_buffer();
   while (true) {
     print_prompt();
     read_input(input_buffer);

     if (input_buffer->buffer[0] == '.') {
-      switch (do_meta_command(input_buffer)) {
+      switch (do_meta_command(input_buffer, table)) {

通过这些更改，我们可以关闭然后重新打开数据库，并且我们的记录仍然在那里。

~ ./db mydb.db
db > insert 1 cstack [email protected]
Executed.
db > insert 2 voltorb [email protected]
Executed.
db > .exit
~
~ ./db mydb.db
db > select
(1, cstack, [email protected])
(2, voltorb, [email protected])
Executed.
db > .exit
~

实践结果：

原文中还研究了数据库文件中数据的存储方式，可参见原文，这里暂时不翻译了。

结论

现在如果在没有键入.exit的情况下终止了程序，更改将会丢失。另外我们要将所有的页面写回磁盘，其中也包含了读取后没有改变的页面。这是以后要解决的问题。

接下来我们要介绍游标(cursors)，它使实现B树更简单。

修改的部分

+#include <errno.h>
+#include <fcntl.h>
 #include <stdbool.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <stdint.h>
+#include <unistd.h>

 struct InputBuffer_t {
   char* buffer;
@@ -62,9 +65,16 @@ const uint32_t PAGE_SIZE = 4096;
 const uint32_t ROWS_PER_PAGE = PAGE_SIZE / ROW_SIZE;
 const uint32_t TABLE_MAX_ROWS = ROWS_PER_PAGE * TABLE_MAX_PAGES;

+typedef struct {
+  int file_descriptor;
+  uint32_t file_length;
+  void* pages[TABLE_MAX_PAGES];
+} Pager;
+
 typedef struct {
   uint32_t num_rows;
-  void* pages[TABLE_MAX_PAGES];
+  Pager* pager;
 } Table;

@@ -84,32 +94,81 @@ void deserialize_row(void *source, Row* destination) {
   memcpy(&(destination->email), source + EMAIL_OFFSET, EMAIL_SIZE);
 }

+void* get_page(Pager* pager, uint32_t page_num) {
+  if (page_num > TABLE_MAX_PAGES) {
+     printf("Tried to fetch page number out of bounds. %d > %d\n", page_num,
+     	TABLE_MAX_PAGES);
+     exit(EXIT_FAILURE);
+  }
+
+  if (pager->pages[page_num] == NULL) {
+     // Cache miss. Allocate memory and load from file.
+     void* page = malloc(PAGE_SIZE);
+     uint32_t num_pages = pager->file_length / PAGE_SIZE;
+
+     // We might save a partial page at the end of the file
+     if (pager->file_length % PAGE_SIZE) {
+         num_pages += 1;
+     }
+
+     if (page_num <= num_pages) {
+         lseek(pager->file_descriptor, page_num * PAGE_SIZE, SEEK_SET);
+         ssize_t bytes_read = read(pager->file_descriptor, page, PAGE_SIZE);
+         if (bytes_read == -1) {
+     	printf("Error reading file: %d\n", errno);
+     	exit(EXIT_FAILURE);
+         }
+     }
+
+     pager->pages[page_num] = page;
+  }
+
+  return pager->pages[page_num];
+}
+
 void* row_slot(Table* table, uint32_t row_num) {
   uint32_t page_num = row_num / ROWS_PER_PAGE;
-  void *page = table->pages[page_num];
-  if (page == NULL) {
-     // Allocate memory only when we try to access page
-     page = table->pages[page_num] = malloc(PAGE_SIZE);
-  }
+  void *page = get_page(table->pager, page_num);
   uint32_t row_offset = row_num % ROWS_PER_PAGE;
   uint32_t byte_offset = row_offset * ROW_SIZE;
   return page + byte_offset;
 }

-Table* new_table() {
-  Table* table = malloc(sizeof(Table));
-  table->num_rows = 0;
+Pager* pager_open(const char* filename) {
+  int fd = open(filename,
+     	  O_RDWR | 	// Read/Write mode
+     	      O_CREAT,	// Create file if it does not exist
+     	  S_IWUSR |	// User write permission
+     	      S_IRUSR	// User read permission
+     	  );
+
+  if (fd == -1) {
+     printf("Unable to open file\n");
+     exit(EXIT_FAILURE);
+  }
+
+  off_t file_length = lseek(fd, 0, SEEK_END);
+
+  Pager* pager = malloc(sizeof(Pager));
+  pager->file_descriptor = fd;
+  pager->file_length = file_length;
+
   for (uint32_t i = 0; i < TABLE_MAX_PAGES; i++) {
-     table->pages[i] = NULL;
+     pager->pages[i] = NULL;
   }
-  return table;
+
+  return pager;
 }

-void free_table(Table* table) {
-  for (int i = 0; table->pages[i]; i++) {
-     free(table->pages[i]);
-  }
-  free(table);
+Table* db_open(const char* filename) {
+  Pager* pager = pager_open(filename);
+  uint32_t num_rows = pager->file_length / ROW_SIZE;
+
+  Table* table = malloc(sizeof(Table));
+  table->pager = pager;
+  table->num_rows = num_rows;
+
+  return table;
 }

 InputBuffer* new_input_buffer() {
@@ -142,10 +201,76 @@ void close_input_buffer(InputBuffer* input_buffer) {
   free(input_buffer);
 }

+void pager_flush(Pager* pager, uint32_t page_num, uint32_t size) {
+  if (pager->pages[page_num] == NULL) {
+     printf("Tried to flush null page\n");
+     exit(EXIT_FAILURE);
+  }
+
+  off_t offset = lseek(pager->file_descriptor, page_num * PAGE_SIZE,
+     		 SEEK_SET);
+
+  if (offset == -1) {
+     printf("Error seeking: %d\n", errno);
+     exit(EXIT_FAILURE);
+  }
+
+  ssize_t bytes_written = write(
+     pager->file_descriptor, pager->pages[page_num], size
+     );
+
+  if (bytes_written == -1) {
+     printf("Error writing: %d\n", errno);
+     exit(EXIT_FAILURE);
+  }
+}
+
+void db_close(Table* table) {
+  Pager* pager = table->pager;
+  uint32_t num_full_pages = table->num_rows / ROWS_PER_PAGE;
+
+  for (uint32_t i = 0; i < num_full_pages; i++) {
+     if (pager->pages[i] == NULL) {
+         continue;
+     }
+     pager_flush(pager, i, PAGE_SIZE);
+     free(pager->pages[i]);
+     pager->pages[i] = NULL;
+  }
+
+  // There may be a partial page to write to the end of the file
+  // This should not be needed after we switch to a B-tree
+  uint32_t num_additional_rows = table->num_rows % ROWS_PER_PAGE;
+  if (num_additional_rows > 0) {
+     uint32_t page_num = num_full_pages;
+     if (pager->pages[page_num] != NULL) {
+         pager_flush(pager, page_num, num_additional_rows * ROW_SIZE);
+         free(pager->pages[page_num]);
+         pager->pages[page_num] = NULL;
+     }
+  }
+
+  int result = close(pager->file_descriptor);
+  if (result == -1) {
+     printf("Error closing db file.\n");
+     exit(EXIT_FAILURE);
+  }
+  for (uint32_t i = 0; i < TABLE_MAX_PAGES; i++) {
+     void* page = pager->pages[i];
+     if (page) {
+         free(page);
+         pager->pages[i] = NULL;
+     }
+  }
+
+  free(pager);
+  free(table);
+}
+
 MetaCommandResult do_meta_command(InputBuffer* input_buffer, Table *table) {
   if (strcmp(input_buffer->buffer, ".exit") == 0) {
     close_input_buffer(input_buffer);
-    free_table(table);
+    db_close(table);
     exit(EXIT_SUCCESS);
   } else {
     return META_COMMAND_UNRECOGNIZED_COMMAND;
@@ -182,6 +308,7 @@ PrepareResult prepare_insert(InputBuffer* input_buffer, Statement* statement) {
     return PREPARE_SUCCESS;

 }
+
 PrepareResult prepare_statement(InputBuffer* input_buffer,
                                 Statement* statement) {
   if (strncmp(input_buffer->buffer, "insert", 6) == 0) {
@@ -227,7 +354,14 @@ ExecuteResult execute_statement(Statement* statement, Table *table) {
 }

 int main(int argc, char* argv[]) {
-  Table* table = new_table();
+  if (argc < 2) {
+      printf("Must supply a database filename.\n");
+      exit(EXIT_FAILURE);
+  }
+
+  char* filename = argv[1];
+  Table* table = db_open(filename);
+
   InputBuffer* input_buffer = new_input_buffer();
   while (true) {
     print_prompt();