|
这篇文档基于qemu-kvm-1.1.0源代码进行分析。
首先,源代码中的hmp-commands.hx文件里有下面内容:
{
.name = "migrate",/* 在monitor命令行中所使用的命令名称 */
.args_type = "detach:-d,blk:-b,inc:-i,uri:s",
.params = "[-d] [-b] [-i] uri",/* 重要,是命令的附加參数,详细參照后文的分析 */
.help = "migrate to URI (using -d to not wait for completion)"
"\n\t\t\t -b for migration without shared storage with"
" full copy of disk\n\t\t\t -i for migration without "
"shared storage with incremental copy of disk "
"(base image shared between src and destination)",
.mhandler.cmd = hmp_migrate,/* 相应的处理函数 */
},
STEXI
@item migrate [-d] [-b] [-i] @var{uri}
@findex migrate
Migrate to @var{uri} (using -d to not wait for completion).
-b for migration with full copy of disk
-i for migration with incremental copy of disk (base image is shared)
ETEXI
这部分内容是与迁移命令相相应的。能够看到,与迁移命令相相应的处理函数是hmp_migrate(hmp.c)。
Qemu-kvm使用hmp-commands.hx这个文件保存命令行參数和相应的常量。然后使用hxtool工具,利用该文件产生相应的c头文件hmp-commands.h。
Sh /root/qemu-kvm-1.1.0/scripts/hxtool -h < /root/qemu-kvm-1.2.0/hmp-commands.hx > hmp-commands.h进行转换的时候,STEXI与ETEXI之间的内容是不被写入头文件的。
在monitor.c源文件里有例如以下内容:
/* mon_cmds andinfo_cmds would be sorted at runtime */
static mon_cmd_tmon_cmds[] = {
#include"hmp-commands.h"
{ NULL, NULL, },
};所以hmp-commands.hx文件终于的作用是给结构体数组mon_cmds赋值。
然后分析进入函数hmp_migrate后是怎样处理的:
调用关系依次例如以下(每一行就是一次函数调用):
Hmp_migrate(hm是human monitor的意思),
Qmp_migrate(qmp是qemu monitor protocal的意思),
tcp_start_outgoing_migration(以迁移时使用的uri是以tcp开头为例),
migrate_fd_connect,
然后migrate_fd_connect函数会先调用qemu_savevm_state_begin函数(进行迁移工作的初始化工作),然后进入migrate_fd_put_ready函数,
migrate_fd_put_ready则会首先调用qemu_savevm_state_iterate函数,该函数进行迁移的主要工作;完毕后进行新旧虚拟机的切换工作。
我们再来看看qemu_savevm_state_begin和qemu_savevm_state_iterate函数究竟是怎样工作的:
qemu_savevm_state_begin中有例如以下代码段:
QTAILQ_FOREACH(se, &savevm_handlers, entry) {
if(se->set_params == NULL) {
continue;
}
se->set_params(blk_enable, shared, se->opaque);
}
qemu_put_be32(f, QEMU_VM_FILE_MAGIC);
qemu_put_be32(f, QEMU_VM_FILE_VERSION);
QTAILQ_FOREACH(se, &savevm_handlers, entry) {
int len;
if (se->save_live_state == NULL)
continue;
/* Section type */
qemu_put_byte(f, QEMU_VM_SECTION_START);
qemu_put_be32(f, se->section_id);
/* ID string */
len = strlen(se->idstr);
qemu_put_byte(f, len);
qemu_put_buffer(f, (uint8_t *)se->idstr, len);
qemu_put_be32(f, se->instance_id);
qemu_put_be32(f, se->version_id);
ret = se->save_live_state(f, QEMU_VM_SECTION_START, se->opaque);
if (ret < 0) {
qemu_savevm_state_cancel(f);
return ret;
}
}
ret = qemu_file_get_error(f);
if (ret != 0) {
qemu_savevm_state_cancel(f);
}
qemu_savevm_state_iterate中有例如以下代码段:
QTAILQ_FOREACH(se, &savevm_handlers, entry) {
if (se->save_live_state == NULL)
continue;
/* Section type */
qemu_put_byte(f, QEMU_VM_SECTION_PART);
qemu_put_be32(f, se->section_id);
ret = se->save_live_state(f, QEMU_VM_SECTION_PART, se->opaque);
if (ret version_id = version_id;
se->section_id = global_section_id++;
se->set_params = set_params;
se->save_live_state = save_live_state;
se->save_state = save_state;
se->load_state = load_state;
se->opaque = opaque;
se->vmsd = NULL;
se->no_migrate = 0;
/* if this is a live_savem then set is_ram */
if (save_live_state != NULL) {
se->is_ram = 1;
}
if (dev && dev->parent_bus && dev->parent_bus->info->get_dev_path) {
char *id = dev->parent_bus->info->get_dev_path(dev);
if (id) {
pstrcpy(se->idstr, sizeof(se->idstr), id);
pstrcat(se->idstr, sizeof(se->idstr), "/");
g_free(id);
se->compat = g_malloc0(sizeof(CompatEntry));
pstrcpy(se->compat->idstr, sizeof(se->compat->idstr), idstr);
se->compat->instance_id = instance_id == -1 ?
calculate_compat_instance_id(idstr) : instance_id;
instance_id = -1;
}
}
pstrcat(se->idstr, sizeof(se->idstr), idstr);
if (instance_id == -1) {
se->instance_id = calculate_new_instance_id(se->idstr);
} else {
se->instance_id = instance_id;
}
assert(!se->compat || se->instance_id == 0);
/* add at the end of list */
QTAILQ_INSERT_TAIL(&savevm_handlers, se, entry);
return 0;
}
注冊后,SaveStateEntry对象就增加了savevm_handlers链表中。该链表是有一些SaveStateEntry对象组成的链表。
Vl.c文件里的main函数是整个qemu程序的起始。
对于ram设备,在vl.c的main函数中有例如以下调用:
register_savevm_live(NULL, "ram", 0, 4, NULL, ram_save_live, NULL,
ram_load, NULL);
能够看到,ram_save_live函数被传递给了save_live_state函数指针。而该函数也是真正实现ram的活迁移功能的函数。
所以回到刚才的介绍,对于ram设备,qemu_savevm_state_begin和qemu_savevm_state_iterate函数事实上是调用了ram_save_live函数。
以下简述一下预拷贝算法的实现:
int ram_save_live(QEMUFile *f, int stage, void *opaque)
调用时给stage赋予不同的值,ram_save_live会完毕不同阶段的功能,qemu_savevm_state_begin给stage赋值QEMU_VM_SECTION_START,完毕起始阶段的工作(比方将全部的内存页都设为脏页);qemu_savevm_state_iterate给stage赋值QEMU_VM_SECTION_PART,是内存进行迭代拷贝的阶段。qemu_savevm_state_iterate每调用ram_save_live一次,就迭代一次,它会多次调用ram_save_live进行迭代直至达到目标为止(expected_time |
|