Part3 - 一个内存存储-只可追加-单数据表的数据库
我们将先实现一个小规模的数据库。它现在可以做到:
- 支持两种操作:插入一行和打印所有行
- 仅驻留在内存中(没有磁盘永久性)
- 支持单个硬编码(hard-coded)的数据表
我们的硬编码表储存用户的如下信息:
colume | type |
---|---|
id | integer |
username | varchar(32) |
varchar(255) |
这是一个简单的模式(schema),但它使我们能够支持多种数据类型和多种大小的文本数据类型。
insert语句现在看起来是这样的:
// insert id username email
insert 1 cstack foo@bar.com
这意味着我们需要更新我们的prepare_statement函数来解析参数。
if (strncmp(input_buffer->buffer, "insert", 6) == 0) {
statement->type = STATEMENT_INSERT;
+ int args_assigned = sscanf(
+ input_buffer->buffer, "insert %d %s %s", &(statement->row_to_insert.id),
+ statement->row_to_insert.username, statement->row_to_insert.email);
+ if (args_assigned < 3) {
+ return PREPARE_SYNTAX_ERROR;
+ }
return PREPARE_SUCCESS;
}
if (strcmp(input_buffer->buffer, "select") == 0) {
我们将这些解析后的参数存储到一个叫Row的新数据结构。
+#define COLUMN_USERNAME_SIZE 32
+#define COLUMN_EMAIL_SIZE 255
+typedef struct {
+ uint32_t id;
+ char username[COLUMN_USERNAME_SIZE];
+ char email[COLUMN_EMAIL_SIZE];
+} Row;
+
typedef struct {
StatementType type;
+ Row row_to_insert; // only used by insert statement
} Statement;
现在我们需要将数据复制到表示表的数据结构中。sqlite使用B树进行快速查找、插入和删除。我们从简单的开始,与B树类似,它将把行分组到页面中,但不是将这些页面存储在树中,而是将它们存储在数组中。
下面是我的计划:
- 将行存储在称为页的内存块中(关于页的部分可以参考操作系统中的分页存储)
- 每个页面存储尽可能多的行
- 每一行都被序列化为一个紧凑的表示形式
- 页只在需要时分配
- 保持一个固定大小的指向页数组
首先,我们定义行的紧凑表示:
#define size_of_attribute(Struct, Attribute) sizeof(((Struct*)0)->Attribute)
const uint32_t ID_SIZE = size_of_attribute(Row, id);
const uint32_t USERNAME_SIZE = size_of_attribute(Row, username);
const uint32_t EMAIL_SIZE = size_of_attribute(Row, email);
const uint32_t ID_OFFSET = 0;
// 这部分在我的电脑上跑不了,我将其写成了初始化函数
const uint32_t USERNAME_OFFSET = ID_OFFSET + ID_SIZE;
const uint32_t EMAIL_OFFSET = USERNAME_OFFSET + USERNAME_SIZE;
const uint32_t ROW_SIZE = ID_SIZE + USERNAME_SIZE + EMAIL_SIZE;
这意味着一个序列化的行将会有以下的布局:
column | size(bytes) | offset |
---|---|---|
id | 4 | 0 |
username | 32 | 4 |
255 | 36 | |
total | 291 |
我们还需要编写转换行的紧凑表示的代码。
// 序列化
void serialize_row(Row* source, void* destination) {
memcpy(destination + ID_OFFSET, &(source->id), ID_SIZE);
memcpy(destination + USERNAME_OFFSET, &(source->username), USERNAME_SIZE);
memcpy(destination + EMAIL_OFFSET, &(source->email), EMAIL_SIZE);
}
// 解序列化
void deserialize_row(void* source, Row* destination) {
memcpy(&(destination->id), source + ID_OFFSET, ID_SIZE);
memcpy(&(destination->username), source + USERNAME_OFFSET, USERNAME_SIZE);
memcpy(&(destination->email), source + EMAIL_OFFSET, EMAIL_SIZE);
}
接下来是一个表结构,它指向行页面同时含有保存多少行的参数。
const uint32_t PAGE_SIZE = 4096;
// 使用define的原因是要作为声明数组的参数,而const不可以
#define TABLE_MAX_PAGES 100
// 这部分在我的电脑上跑不了,我将其写成了初始化函数
const uint32_t ROWS_PER_PAGE = PAGE_SIZE / ROW_SIZE;
const uint32_t TABLE_MAX_ROWS = ROWS_PER_PAGE * TABLE_MAX_PAGES;
typedef struct {
uint32_t num_rows;
void* pages[TABLE_MAX_PAGES];
} Table;
我将页面大小设置为4 kb(4096),因为它与大多数计算机架构的虚拟内存系统中使用的页面大小相同。这意味着数据库中的一个页面对应于操作系统使用的一个页面。操作系统将把页面作为一个整体移入和移出内存。
我们设置页数限制为100页供我们分配。当我们转而使用树存储结构时,我们的数据库最大尺寸只会受到文件最大大小的限制。(尽管我们仍然限制一次在内存中保留多少页)
行不应跨越页面边界(就是说一个行必须被存储在一个单独的页里), 由于内存中的页面可能不会彼此相邻,因此这种假设使读取/写入行更加容易。
这是我们如何确定特定行在内存中的读取/写入位置:
void* row_slot(Table* table, uint32_t row_num) {
// 计算页号
uint32_t page_num = row_num / ROWS_PER_PAGE;
// 找到对应页
void* page = table->pages[page_num];
// 页为空,开辟新空间
if (page == NULL) {
// Allocate memory only when we try to access page
page = table->pages[page_num] = malloc(PAGE_SIZE);
}
// 计算行位移
uint32_t row_offset = row_num % ROWS_PER_PAGE;
// 计算字节位移
uint32_t byte_offset = row_offset * ROW_SIZE;
// 返回读取/写入位置
return page + byte_offset;
}
现在我们可以利用execute_statement函数从表结构中读取/写入:
-void execute_statement(Statement* statement) {
+// 插入数据
+ExecuteResult execute_insert(Statement* statement, Table* table) {
+ if (table->num_rows >= TABLE_MAX_ROWS) {
+ return EXECUTE_TABLE_FULL;
+ }
+
+ Row* row_to_insert = &(statement->row_to_insert);
+
+ // 序列化,并存入数据库
+ serialize_row(row_to_insert, row_slot(table, table->num_rows));
+ table->num_rows += 1;
+
+ return EXECUTE_SUCCESS;
+}
+
+// 目前仅可以显示所有行
+ExecuteResult execute_select(Statement* statement, Table* table) {
+ Row row;
+ for (uint32_t i = 0; i < table->num_rows; i++) {
+ // 取出行,解序列化,使之能够显示
+ deserialize_row(row_slot(table, i), &row);
+ print_row(&row);
+ }
+ return EXECUTE_SUCCESS;
+}
+
+// 选择操作
+ExecuteResult execute_statement(Statement* statement, Table* table) {
switch (statement->type) {
case (STATEMENT_INSERT):
- printf("This is where we would do an insert.\n");
- break;
+ return execute_insert(statement, table);
case (STATEMENT_SELECT):
- printf("This is where we would do a select.\n");
- break;
+ return execute_select(statement, table);
}
}
最后,我们需要初始化表,创建相应的内存释放函数,并处理更多的错误情况
// 新建表,并初始化
Table* new_table() {
// 这个地方有问题,正确的做法如下:
// Table* table = (Table*)malloc(sizeof(Table));
Table* table = malloc(sizeof(Table));
table->num_rows = 0;
for (uint32_t i = 0; i < TABLE_MAX_PAGES; i++) {
table->pages[i] = NULL;
}
return table;
}
// 释放表,注意要释放每一页
void free_table(Table* table) {
for (int i = 0; table->pages[i]; i++) {
free(table->pages[i]);
}
free(table);
}
其他要修改的小地方
int main(int argc, char* argv[]) {
+ Table* table = new_table();
InputBuffer* input_buffer = new_input_buffer();
while (true) {
print_prompt();
@@ -105,13 +203,22 @@ int main(int argc, char* argv[]) {
switch (prepare_statement(input_buffer, &statement)) {
case (PREPARE_SUCCESS):
break;
+ case (PREPARE_SYNTAX_ERROR):
+ printf("Syntax error. Could not parse statement.\n");
+ continue;
case (PREPARE_UNRECOGNIZED_STATEMENT):
printf("Unrecognized keyword at start of '%s'.\n",
input_buffer->buffer);
continue;
}
- execute_statement(&statement);
- printf("Executed.\n");
+ switch (execute_statement(&statement, table)) {
+ case (EXECUTE_SUCCESS):
+ printf("Executed.\n");
+ break;
+ case (EXECUTE_TABLE_FULL):
+ printf("Error: Table full.\n");
+ break;
+ }
}
}
通过这些更改,我们实际上可以将数据保存到数据库中。
~ ./db
db > insert 1 cstack foo@bar.com
Executed.
db > insert 2 bob bob@example.com
Executed.
db > select
(1, cstack, foo@bar.com)
(2, bob, bob@example.com)
Executed.
db > insert foo bar 1
Syntax error. Could not parse statement.
db > .exit
~
实践结果:
现在是做一些测试的好机会,因为:
- 我们正计划对存储表的数据结构进行重大更改,而测试可以发现缺陷。
- 有一些极端情况我们还没有进行测试(比如填满表)
下面是与上一部分不同的地方,有些地方可能有误,我已标出。
@@ -2,6 +2,7 @@
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
+#include <stdint.h>
typedef struct {
char* buffer;
@@ -10,6 +11,105 @@ typedef struct {
} InputBuffer;
+typedef enum { EXECUTE_SUCCESS, EXECUTE_TABLE_FULL } ExecuteResult;
+
+typedef enum {
+ META_COMMAND_SUCCESS,
+ META_COMMAND_UNRECOGNIZED_COMMAND
+} MetaCommandResult;
+
+typedef enum {
+ PREPARE_SUCCESS,
+ PREPARE_SYNTAX_ERROR,
+ PREPARE_UNRECOGNIZED_STATEMENT
+ } PrepareResult;
+
+typedef enum { STATEMENT_INSERT, STATEMENT_SELECT } StatementType;
+
+#define COLUMN_USERNAME_SIZE 32
+#define COLUMN_EMAIL_SIZE 255
+typedef struct {
+ uint32_t id;
+ char username[COLUMN_USERNAME_SIZE];
+ char email[COLUMN_EMAIL_SIZE];
+} Row;
+
+typedef struct {
+ StatementType type;
+ Row row_to_insert; //only used by insert statement
+} Statement;
+
+#define size_of_attribute(Struct, Attribute) sizeof(((Struct*)0)->Attribute)
+
+const uint32_t ID_SIZE = size_of_attribute(Row, id);
+const uint32_t USERNAME_SIZE = size_of_attribute(Row, username);
+const uint32_t EMAIL_SIZE = size_of_attribute(Row, email);
+const uint32_t ID_OFFSET = 0;
+// 有误,应写成函数
+const uint32_t USERNAME_OFFSET = ID_OFFSET + ID_SIZE;
+const uint32_t EMAIL_OFFSET = USERNAME_OFFSET + USERNAME_SIZE;
+const uint32_t ROW_SIZE = ID_SIZE + USERNAME_SIZE + EMAIL_SIZE;
+
+const uint32_t PAGE_SIZE = 4096;
+#define TABLE_MAX_PAGES 100
+// 有误,应写成函数
+const uint32_t ROWS_PER_PAGE = PAGE_SIZE / ROW_SIZE;
+const uint32_t TABLE_MAX_ROWS = ROWS_PER_PAGE * TABLE_MAX_PAGES;
+
+typedef struct {
+ uint32_t num_rows;
+ void* pages[TABLE_MAX_PAGES];
+} Table;
+
+void print_row(Row* row) {
+ printf("(%d, %s, %s)\n", row->id, row->username, row->email);
+}
+
+void serialize_row(Row* source, void* destination) {
+ // 会报warning,消除warning可以强转成(uint32_t*),下同。
+ // 例如:memcpy((uint32_t*)destination + ID_OFFSET, &(source->id), ID_SIZE);
+ memcpy(destination + ID_OFFSET, &(source->id), ID_SIZE);
+ memcpy(destination + USERNAME_OFFSET, &(source->username), USERNAME_SIZE);
+ memcpy(destination + EMAIL_OFFSET, &(source->email), EMAIL_SIZE);
+}
+
+void deserialize_row(void *source, Row* destination) {
+ memcpy(&(destination->id), source + ID_OFFSET, ID_SIZE);
+ memcpy(&(destination->username), source + USERNAME_OFFSET, USERNAME_SIZE);
+ memcpy(&(destination->email), source + EMAIL_OFFSET, EMAIL_SIZE);
+}
+
+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);
+ }
+ uint32_t row_offset = row_num % ROWS_PER_PAGE;
+ uint32_t byte_offset = row_offset * ROW_SIZE;
+ return page + byte_offset;
+}
+
+Table* new_table() {
+ // 此处malloc有误,见上文
+ Table* table = malloc(sizeof(Table));
+ table->num_rows = 0;
+ for (uint32_t i = 0; i < TABLE_MAX_PAGES; i++) {
+ table->pages[i] = NULL;
+ }
+ return table;
+}
+
+void free_table(Table* table) {
+ for (int i = 0; table->pages[i]; i++) {
+ free(table->pages[i]);
+ }
+ free(table);
+}
+
InputBuffer* new_input_buffer() {
InputBuffer* input_buffer = malloc(sizeof(InputBuffer));
input_buffer->buffer = NULL;
@@ -40,17 +140,105 @@ void close_input_buffer(InputBuffer* input_buffer) {
free(input_buffer);
}
+MetaCommandResult do_meta_command(InputBuffer* input_buffer, Table *table) {
+ if (strcmp(input_buffer->buffer, ".exit") == 0) {
+ close_input_buffer(input_buffer);
+ free_table(table);
+ exit(EXIT_SUCCESS);
+ } else {
+ return META_COMMAND_UNRECOGNIZED_COMMAND;
+ }
+}
+
+PrepareResult prepare_statement(InputBuffer* input_buffer,
+ Statement* statement) {
+ if (strncmp(input_buffer->buffer, "insert", 6) == 0) {
+ statement->type = STATEMENT_INSERT;
+ int args_assigned = sscanf(
+ input_buffer->buffer, "insert %d %s %s", &(statement->row_to_insert.id),
+ statement->row_to_insert.username, statement->row_to_insert.email
+ );
+ if (args_assigned < 3) {
+ return PREPARE_SYNTAX_ERROR;
+ }
+ return PREPARE_SUCCESS;
+ }
+ if (strcmp(input_buffer->buffer, "select") == 0) {
+ statement->type = STATEMENT_SELECT;
+ return PREPARE_SUCCESS;
+ }
+
+ return PREPARE_UNRECOGNIZED_STATEMENT;
+}
+
+ExecuteResult execute_insert(Statement* statement, Table* table) {
+ if (table->num_rows >= TABLE_MAX_ROWS) {
+ return EXECUTE_TABLE_FULL;
+ }
+
+ Row* row_to_insert = &(statement->row_to_insert);
+
+ serialize_row(row_to_insert, row_slot(table, table->num_rows));
+ table->num_rows += 1;
+
+ return EXECUTE_SUCCESS;
+}
+
+ExecuteResult execute_select(Statement* statement, Table* table) {
+ Row row;
+ for (uint32_t i = 0; i < table->num_rows; i++) {
+ deserialize_row(row_slot(table, i), &row);
+ print_row(&row);
+ }
+ return EXECUTE_SUCCESS;
+}
+
+ExecuteResult execute_statement(Statement* statement, Table *table) {
+ switch (statement->type) {
+ case (STATEMENT_INSERT):
+ return execute_insert(statement, table);
+ case (STATEMENT_SELECT):
+ return execute_select(statement, table);
+ }
+}
+
int main(int argc, char* argv[]) {
+ Table* table = new_table();
InputBuffer* input_buffer = new_input_buffer();
while (true) {
print_prompt();
read_input(input_buffer);
- if (strcmp(input_buffer->buffer, ".exit") == 0) {
- close_input_buffer(input_buffer);
- exit(EXIT_SUCCESS);
- } else {
- printf("Unrecognized command '%s'.\n", input_buffer->buffer);
+ if (input_buffer->buffer[0] == '.') {
+ switch (do_meta_command(input_buffer, table)) {
+ case (META_COMMAND_SUCCESS):
+ continue;
+ case (META_COMMAND_UNRECOGNIZED_COMMAND):
+ printf("Unrecognized command '%s'\n", input_buffer->buffer);
+ continue;
+ }
+ }
+
+ Statement statement;
+ switch (prepare_statement(input_buffer, &statement)) {
+ case (PREPARE_SUCCESS):
+ break;
+ case (PREPARE_SYNTAX_ERROR):
+ printf("Syntax error. Could not parse statement.\n");
+ continue;
+ case (PREPARE_UNRECOGNIZED_STATEMENT):
+ printf("Unrecognized keyword at start of '%s'.\n",
+ input_buffer->buffer);
+ continue;
+ }
+
+ switch (execute_statement(&statement, table)) {
+ case (EXECUTE_SUCCESS):
+ printf("Executed.\n");
+ break;
+ case (EXECUTE_TABLE_FULL):
+ printf("Error: Table full.\n");
+ break;
}
}
}