4b58153dd2
This adds a new invocation ID concept to the service manager. The invocation ID identifies each runtime cycle of a unit uniquely. A new randomized 128bit ID is generated each time a unit moves from and inactive to an activating or active state. The primary usecase for this concept is to connect the runtime data PID 1 maintains about a service with the offline data the journal stores about it. Previously we'd use the unit name plus start/stop times, which however is highly racy since the journal will generally process log data after the service already ended. The "invocation ID" kinda matches the "boot ID" concept of the Linux kernel, except that it applies to an individual unit instead of the whole system. The invocation ID is passed to the activated processes as environment variable. It is additionally stored as extended attribute on the cgroup of the unit. The latter is used by journald to automatically retrieve it for each log logged message and attach it to the log entry. The environment variable is very easily accessible, even for unprivileged services. OTOH the extended attribute is only accessible to privileged processes (this is because cgroupfs only supports the "trusted." xattr namespace, not "user."). The environment variable may be altered by services, the extended attribute may not be, hence is the better choice for the journal. Note that reading the invocation ID off the extended attribute from journald is racy, similar to the way reading the unit name for a logging process is. This patch adds APIs to read the invocation ID to sd-id128: sd_id128_get_invocation() may be used in a similar fashion to sd_id128_get_boot(). PID1's own logging is updated to always include the invocation ID when it logs information about a unit. A new bus call GetUnitByInvocationID() is added that allows retrieving a bus path to a unit by its invocation ID. The bus path is built using the invocation ID, thus providing a path for referring to a unit that is valid only for the current runtime cycleof it. Outlook for the future: should the kernel eventually allow passing of cgroup information along AF_UNIX/SOCK_DGRAM messages via a unique cgroup id, then we can alter the invocation ID to be generated as hash from that rather than entirely randomly. This way we can derive the invocation race-freely from the messages.
257 lines
10 KiB
C
257 lines
10 KiB
C
#pragma once
|
|
|
|
/***
|
|
This file is part of systemd.
|
|
|
|
Copyright 2010 Lennart Poettering
|
|
|
|
systemd is free software; you can redistribute it and/or modify it
|
|
under the terms of the GNU Lesser General Public License as published by
|
|
the Free Software Foundation; either version 2.1 of the License, or
|
|
(at your option) any later version.
|
|
|
|
systemd is distributed in the hope that it will be useful, but
|
|
WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
Lesser General Public License for more details.
|
|
|
|
You should have received a copy of the GNU Lesser General Public License
|
|
along with systemd; If not, see <http://www.gnu.org/licenses/>.
|
|
***/
|
|
|
|
#include <dirent.h>
|
|
#include <stdbool.h>
|
|
#include <stdint.h>
|
|
#include <stdio.h>
|
|
#include <sys/types.h>
|
|
|
|
#include "def.h"
|
|
#include "hashmap.h"
|
|
#include "macro.h"
|
|
#include "set.h"
|
|
|
|
/* An enum of well known cgroup controllers */
|
|
typedef enum CGroupController {
|
|
CGROUP_CONTROLLER_CPU,
|
|
CGROUP_CONTROLLER_CPUACCT,
|
|
CGROUP_CONTROLLER_IO,
|
|
CGROUP_CONTROLLER_BLKIO,
|
|
CGROUP_CONTROLLER_MEMORY,
|
|
CGROUP_CONTROLLER_DEVICES,
|
|
CGROUP_CONTROLLER_PIDS,
|
|
_CGROUP_CONTROLLER_MAX,
|
|
_CGROUP_CONTROLLER_INVALID = -1,
|
|
} CGroupController;
|
|
|
|
#define CGROUP_CONTROLLER_TO_MASK(c) (1 << (c))
|
|
|
|
/* A bit mask of well known cgroup controllers */
|
|
typedef enum CGroupMask {
|
|
CGROUP_MASK_CPU = CGROUP_CONTROLLER_TO_MASK(CGROUP_CONTROLLER_CPU),
|
|
CGROUP_MASK_CPUACCT = CGROUP_CONTROLLER_TO_MASK(CGROUP_CONTROLLER_CPUACCT),
|
|
CGROUP_MASK_IO = CGROUP_CONTROLLER_TO_MASK(CGROUP_CONTROLLER_IO),
|
|
CGROUP_MASK_BLKIO = CGROUP_CONTROLLER_TO_MASK(CGROUP_CONTROLLER_BLKIO),
|
|
CGROUP_MASK_MEMORY = CGROUP_CONTROLLER_TO_MASK(CGROUP_CONTROLLER_MEMORY),
|
|
CGROUP_MASK_DEVICES = CGROUP_CONTROLLER_TO_MASK(CGROUP_CONTROLLER_DEVICES),
|
|
CGROUP_MASK_PIDS = CGROUP_CONTROLLER_TO_MASK(CGROUP_CONTROLLER_PIDS),
|
|
_CGROUP_MASK_ALL = CGROUP_CONTROLLER_TO_MASK(_CGROUP_CONTROLLER_MAX) - 1
|
|
} CGroupMask;
|
|
|
|
/* Special values for all weight knobs on unified hierarchy */
|
|
#define CGROUP_WEIGHT_INVALID ((uint64_t) -1)
|
|
#define CGROUP_WEIGHT_MIN UINT64_C(1)
|
|
#define CGROUP_WEIGHT_MAX UINT64_C(10000)
|
|
#define CGROUP_WEIGHT_DEFAULT UINT64_C(100)
|
|
|
|
#define CGROUP_LIMIT_MIN UINT64_C(0)
|
|
#define CGROUP_LIMIT_MAX ((uint64_t) -1)
|
|
|
|
static inline bool CGROUP_WEIGHT_IS_OK(uint64_t x) {
|
|
return
|
|
x == CGROUP_WEIGHT_INVALID ||
|
|
(x >= CGROUP_WEIGHT_MIN && x <= CGROUP_WEIGHT_MAX);
|
|
}
|
|
|
|
/* IO limits on unified hierarchy */
|
|
typedef enum CGroupIOLimitType {
|
|
CGROUP_IO_RBPS_MAX,
|
|
CGROUP_IO_WBPS_MAX,
|
|
CGROUP_IO_RIOPS_MAX,
|
|
CGROUP_IO_WIOPS_MAX,
|
|
|
|
_CGROUP_IO_LIMIT_TYPE_MAX,
|
|
_CGROUP_IO_LIMIT_TYPE_INVALID = -1
|
|
} CGroupIOLimitType;
|
|
|
|
extern const uint64_t cgroup_io_limit_defaults[_CGROUP_IO_LIMIT_TYPE_MAX];
|
|
|
|
const char* cgroup_io_limit_type_to_string(CGroupIOLimitType t) _const_;
|
|
CGroupIOLimitType cgroup_io_limit_type_from_string(const char *s) _pure_;
|
|
|
|
/* Special values for the cpu.shares attribute */
|
|
#define CGROUP_CPU_SHARES_INVALID ((uint64_t) -1)
|
|
#define CGROUP_CPU_SHARES_MIN UINT64_C(2)
|
|
#define CGROUP_CPU_SHARES_MAX UINT64_C(262144)
|
|
#define CGROUP_CPU_SHARES_DEFAULT UINT64_C(1024)
|
|
|
|
static inline bool CGROUP_CPU_SHARES_IS_OK(uint64_t x) {
|
|
return
|
|
x == CGROUP_CPU_SHARES_INVALID ||
|
|
(x >= CGROUP_CPU_SHARES_MIN && x <= CGROUP_CPU_SHARES_MAX);
|
|
}
|
|
|
|
/* Special values for the blkio.weight attribute */
|
|
#define CGROUP_BLKIO_WEIGHT_INVALID ((uint64_t) -1)
|
|
#define CGROUP_BLKIO_WEIGHT_MIN UINT64_C(10)
|
|
#define CGROUP_BLKIO_WEIGHT_MAX UINT64_C(1000)
|
|
#define CGROUP_BLKIO_WEIGHT_DEFAULT UINT64_C(500)
|
|
|
|
static inline bool CGROUP_BLKIO_WEIGHT_IS_OK(uint64_t x) {
|
|
return
|
|
x == CGROUP_BLKIO_WEIGHT_INVALID ||
|
|
(x >= CGROUP_BLKIO_WEIGHT_MIN && x <= CGROUP_BLKIO_WEIGHT_MAX);
|
|
}
|
|
|
|
/* Default resource limits */
|
|
#define DEFAULT_TASKS_MAX_PERCENTAGE 15U /* 15% of PIDs, 4915 on default settings */
|
|
#define DEFAULT_USER_TASKS_MAX_PERCENTAGE 33U /* 33% of PIDs, 10813 on default settings */
|
|
|
|
typedef enum CGroupUnified {
|
|
CGROUP_UNIFIED_UNKNOWN = -1,
|
|
CGROUP_UNIFIED_NONE = 0, /* Both systemd and controllers on legacy */
|
|
CGROUP_UNIFIED_SYSTEMD = 1, /* Only systemd on unified */
|
|
CGROUP_UNIFIED_ALL = 2, /* Both systemd and controllers on unified */
|
|
} CGroupUnified;
|
|
|
|
/*
|
|
* General rules:
|
|
*
|
|
* We accept named hierarchies in the syntax "foo" and "name=foo".
|
|
*
|
|
* We expect that named hierarchies do not conflict in name with a
|
|
* kernel hierarchy, modulo the "name=" prefix.
|
|
*
|
|
* We always generate "normalized" controller names, i.e. without the
|
|
* "name=" prefix.
|
|
*
|
|
* We require absolute cgroup paths. When returning, we will always
|
|
* generate paths with multiple adjacent / removed.
|
|
*/
|
|
|
|
int cg_enumerate_processes(const char *controller, const char *path, FILE **_f);
|
|
int cg_read_pid(FILE *f, pid_t *_pid);
|
|
int cg_read_event(const char *controller, const char *path, const char *event,
|
|
char **val);
|
|
|
|
int cg_enumerate_subgroups(const char *controller, const char *path, DIR **_d);
|
|
int cg_read_subgroup(DIR *d, char **fn);
|
|
|
|
typedef enum CGroupFlags {
|
|
CGROUP_SIGCONT = 1,
|
|
CGROUP_IGNORE_SELF = 2,
|
|
CGROUP_REMOVE = 4,
|
|
} CGroupFlags;
|
|
|
|
typedef void (*cg_kill_log_func_t)(pid_t pid, int sig, void *userdata);
|
|
|
|
int cg_kill(const char *controller, const char *path, int sig, CGroupFlags flags, Set *s, cg_kill_log_func_t kill_log, void *userdata);
|
|
int cg_kill_recursive(const char *controller, const char *path, int sig, CGroupFlags flags, Set *s, cg_kill_log_func_t kill_log, void *userdata);
|
|
|
|
int cg_migrate(const char *cfrom, const char *pfrom, const char *cto, const char *pto, CGroupFlags flags);
|
|
int cg_migrate_recursive(const char *cfrom, const char *pfrom, const char *cto, const char *pto, CGroupFlags flags);
|
|
int cg_migrate_recursive_fallback(const char *cfrom, const char *pfrom, const char *cto, const char *pto, CGroupFlags flags);
|
|
|
|
int cg_split_spec(const char *spec, char **controller, char **path);
|
|
int cg_mangle_path(const char *path, char **result);
|
|
|
|
int cg_get_path(const char *controller, const char *path, const char *suffix, char **fs);
|
|
int cg_get_path_and_check(const char *controller, const char *path, const char *suffix, char **fs);
|
|
|
|
int cg_pid_get_path(const char *controller, pid_t pid, char **path);
|
|
|
|
int cg_trim(const char *controller, const char *path, bool delete_root);
|
|
|
|
int cg_rmdir(const char *controller, const char *path);
|
|
|
|
int cg_create(const char *controller, const char *path);
|
|
int cg_attach(const char *controller, const char *path, pid_t pid);
|
|
int cg_attach_fallback(const char *controller, const char *path, pid_t pid);
|
|
int cg_create_and_attach(const char *controller, const char *path, pid_t pid);
|
|
|
|
int cg_set_attribute(const char *controller, const char *path, const char *attribute, const char *value);
|
|
int cg_get_attribute(const char *controller, const char *path, const char *attribute, char **ret);
|
|
int cg_get_keyed_attribute(const char *controller, const char *path, const char *attribute, const char **keys, char **values);
|
|
|
|
int cg_set_group_access(const char *controller, const char *path, mode_t mode, uid_t uid, gid_t gid);
|
|
int cg_set_task_access(const char *controller, const char *path, mode_t mode, uid_t uid, gid_t gid);
|
|
|
|
int cg_set_xattr(const char *controller, const char *path, const char *name, const void *value, size_t size, int flags);
|
|
int cg_get_xattr(const char *controller, const char *path, const char *name, void *value, size_t size);
|
|
|
|
int cg_install_release_agent(const char *controller, const char *agent);
|
|
int cg_uninstall_release_agent(const char *controller);
|
|
|
|
int cg_is_empty(const char *controller, const char *path);
|
|
int cg_is_empty_recursive(const char *controller, const char *path);
|
|
|
|
int cg_get_root_path(char **path);
|
|
|
|
int cg_path_get_session(const char *path, char **session);
|
|
int cg_path_get_owner_uid(const char *path, uid_t *uid);
|
|
int cg_path_get_unit(const char *path, char **unit);
|
|
int cg_path_get_user_unit(const char *path, char **unit);
|
|
int cg_path_get_machine_name(const char *path, char **machine);
|
|
int cg_path_get_slice(const char *path, char **slice);
|
|
int cg_path_get_user_slice(const char *path, char **slice);
|
|
|
|
int cg_shift_path(const char *cgroup, const char *cached_root, const char **shifted);
|
|
int cg_pid_get_path_shifted(pid_t pid, const char *cached_root, char **cgroup);
|
|
|
|
int cg_pid_get_session(pid_t pid, char **session);
|
|
int cg_pid_get_owner_uid(pid_t pid, uid_t *uid);
|
|
int cg_pid_get_unit(pid_t pid, char **unit);
|
|
int cg_pid_get_user_unit(pid_t pid, char **unit);
|
|
int cg_pid_get_machine_name(pid_t pid, char **machine);
|
|
int cg_pid_get_slice(pid_t pid, char **slice);
|
|
int cg_pid_get_user_slice(pid_t pid, char **slice);
|
|
|
|
int cg_path_decode_unit(const char *cgroup, char **unit);
|
|
|
|
char *cg_escape(const char *p);
|
|
char *cg_unescape(const char *p) _pure_;
|
|
|
|
bool cg_controller_is_valid(const char *p);
|
|
|
|
int cg_slice_to_path(const char *unit, char **ret);
|
|
|
|
typedef const char* (*cg_migrate_callback_t)(CGroupMask mask, void *userdata);
|
|
|
|
int cg_create_everywhere(CGroupMask supported, CGroupMask mask, const char *path);
|
|
int cg_attach_everywhere(CGroupMask supported, const char *path, pid_t pid, cg_migrate_callback_t callback, void *userdata);
|
|
int cg_attach_many_everywhere(CGroupMask supported, const char *path, Set* pids, cg_migrate_callback_t callback, void *userdata);
|
|
int cg_migrate_everywhere(CGroupMask supported, const char *from, const char *to, cg_migrate_callback_t callback, void *userdata);
|
|
int cg_trim_everywhere(CGroupMask supported, const char *path, bool delete_root);
|
|
int cg_enable_everywhere(CGroupMask supported, CGroupMask mask, const char *p);
|
|
|
|
int cg_mask_supported(CGroupMask *ret);
|
|
|
|
int cg_kernel_controllers(Set *controllers);
|
|
|
|
bool cg_ns_supported(void);
|
|
|
|
int cg_all_unified(void);
|
|
int cg_unified(const char *controller);
|
|
void cg_unified_flush(void);
|
|
|
|
bool cg_is_unified_wanted(void);
|
|
bool cg_is_legacy_wanted(void);
|
|
bool cg_is_unified_systemd_controller_wanted(void);
|
|
bool cg_is_legacy_systemd_controller_wanted(void);
|
|
|
|
const char* cgroup_controller_to_string(CGroupController c) _const_;
|
|
CGroupController cgroup_controller_from_string(const char *s) _pure_;
|
|
|
|
int cg_weight_parse(const char *s, uint64_t *ret);
|
|
int cg_cpu_shares_parse(const char *s, uint64_t *ret);
|
|
int cg_blkio_weight_parse(const char *s, uint64_t *ret);
|