Cgroup
文件系统
static struct file_system_type cgroup_fs_type = {
.name = “cgroup”,
.mount = cgroup_mount,
.kill_sb = cgroup_kill_sb,
.fs_flags = FS_USERNS_MOUNT,
};
static struct file_system_type cgroup2_fs_type = {
.name = “cgroup2”,
.mount = cgroup_mount,
.kill_sb = cgroup_kill_sb,
.fs_flags = FS_USERNS_MOUNT,
};
Cgroups用户空间的管理是通过
cgroup
文件系统实现的。
比如要创建一个层级：V1
mount -t cgroup -o cpu,cpuset,memory none /sys/test_cgroup
这个命令就创建一个名为test_cgroup的层级，这个层级上附加了
cpu,cpuset,memory
三个子系统，并把层级挂载到了
/sys/test_cgroup
.
创建一个
cgroup
：
cd /sys/test_cgroup
mkdir test1
通过以上两个命令，我们就在刚才创建的层级下创建了一个叫test1
的
cgroup
。
你再cd test1，然后
ls
你会发现一些文件，这是
cgroups
相关子系统的控制文件，你可以读取这些控制文件，这些控制文件存储的值就是对相应的
cgrouop
的控制信息，你也可以写控制文件来更改控制信息。
在这些文件中，有一个叫
tasks
的文件，里面的包含了所有属于这个
cgroup
的进程的进程号。
在刚才创建的
test1
下，你
cat tasks
，应该是空的，因为此时这个
cgroup
里面还没有进程。你
change to root cgroup,
再
cat tasks
，你可以看到系统中所有进程的进程号，这是因为每创建一个层级的时候，系统的所有进程都会自动被加到该层级的根
cgroup
里面。
Tasks
文件不仅可以读，还可以写，你将一个进程的进程号写入到某个
cgroup
目录下的
tasks
里面，你就将这个进程加入了相应的
cgroup
。
/**
* cgroup_init – cgroup initialization
*
* Register cgroup filesystem and /proc file, and initialize
* any subsystems that didn’t request early init.
*/
int __init cgroup_init(void)
{
struct cgroup_subsys *ss;
int ssid;
BUILD_BUG_ON(CGROUP_SUBSYS_COUNT > 16);
BUG_ON(percpu_init_rwsem(&cgroup_threadgroup_rwsem));
BUG_ON(cgroup_init_cftypes(NULL, cgroup_dfl_base_files));
BUG_ON(cgroup_init_cftypes(NULL, cgroup_legacy_base_files));
/*
* The latency of the synchronize_sched() is too high for cgroups,
* avoid it at the cost of forcing all readers into the slow path.
*/
rcu_sync_enter_start(&cgroup_threadgroup_rwsem.rss);
get_user_ns(init_cgroup_ns.user_ns);
mutex_lock(&cgroup_mutex);
/*
* Add init_css_set to the hash table so that dfl_root can link to
* it during init.
*/
hash_add(css_set_table, &init_css_set.hlist,
css_set_hash(init_css_set.subsys));
BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0));
mutex_unlock(&cgroup_mutex);
for_each_subsys(ss, ssid) {
if (ss->early_init) {
struct cgroup_subsys_state *css =
init_css_set.subsys[ss->id];
css->id = cgroup_idr_alloc(&ss->css_idr, css, 1, 2,
GFP_KERNEL);
BUG_ON(css->id < 0);
} else {
cgroup_init_subsys(ss, false);
}
list_add_tail(&init_css_set.e_cset_node[ssid],
&cgrp_dfl_root.cgrp.e_csets[ssid]);
/*
* Setting dfl_root subsys_mask needs to consider the
* disabled flag and cftype registration needs kmalloc,
* both of which aren’t available during early_init.
*/
if (cgroup_disable_mask & (1 << ssid)) {
static_branch_disable(cgroup_subsys_enabled_key[ssid]);
printk(KERN_INFO “Disabling %s control group subsystem\n”,
ss->name);
continue;
}
if (cgroup_ssid_no_v1(ssid))
printk(KERN_INFO “Disabling %s control group subsystem in v1 mounts\n”,
ss->name);
cgrp_dfl_root.subsys_mask |= 1 << ss->id;
if (ss->implicit_on_dfl)
cgrp_dfl_implicit_ss_mask |= 1 << ss->id;
else if (!ss->dfl_cftypes)
cgrp_dfl_inhibit_ss_mask |= 1 << ss->id;
if (ss->dfl_cftypes == ss->legacy_cftypes) {
WARN_ON(cgroup_add_cftypes(ss, ss->dfl_cftypes));
} else {
WARN_ON(cgroup_add_dfl_cftypes(ss, ss->dfl_cftypes));
WARN_ON(cgroup_add_legacy_cftypes(ss, ss->legacy_cftypes));
}
if (ss->bind)
ss->bind(init_css_set.subsys[ssid]);
}
/* init_css_set.subsys[] has been updated, re-hash */
hash_del(&init_css_set.hlist);
hash_add(css_set_table, &init_css_set.hlist,
css_set_hash(init_css_set.subsys));
WARN_ON(sysfs_create_mount_point(fs_kobj, “cgroup”));
WARN_ON(register_filesystem(&cgroup_fs_type));
WARN_ON(register_filesystem(&cgroup2_fs_type));
WARN_ON(!proc_create(“cgroups”, 0, NULL, &proc_cgroupstats_operations));
return 0;
}
/**
* cgroup_init_early – cgroup initialization at system boot
*
* Initialize cgroups at system boot, and initialize any
* subsystems that request early init.
*/
int __init cgroup_init_early(void)
{
static struct cgroup_sb_opts opts;
struct cgroup_subsys *ss;
int i;
init_cgroup_root(&cgrp_dfl_root, &opts);
cgrp_dfl_root.cgrp.self.flags |= CSS_NO_REF;
RCU_INIT_POINTER(init_task.cgroups, &init_css_set);
for_each_subsys(ss, i) {
WARN(!ss->css_alloc || !ss->css_free || ss->name || ss->id,
“invalid cgroup_subsys %d:%s css_alloc=%p css_free=%p id:name=%d:%s\n”,
i, cgroup_subsys_name[i], ss->css_alloc, ss->css_free,
ss->id, ss->name);
WARN(strlen(cgroup_subsys_name[i]) > MAX_CGROUP_TYPE_NAMELEN,
“cgroup_subsys_name %s too long\n”, cgroup_subsys_name[i]);
ss->id = i;
ss->name = cgroup_subsys_name[i];
if (!ss->legacy_name)
ss->legacy_name = cgroup_subsys_name[i];
if (ss->early_init)
cgroup_init_subsys(ss, true);
}
return 0;
}