Systemd/src/journal/journald-server.h

213 lines
5.9 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: LGPL-2.1+ */
#pragma once
2012-01-04 20:40:04 +01:00
#include <stdbool.h>
#include <sys/types.h>
2012-01-04 20:40:04 +01:00
#include "sd-event.h"
typedef struct Server Server;
#include "conf-parser.h"
2012-01-04 20:40:04 +01:00
#include "hashmap.h"
#include "journal-file.h"
#include "journald-context.h"
#include "journald-rate-limit.h"
#include "journald-stream.h"
2012-01-04 20:40:04 +01:00
#include "list.h"
#include "prioq.h"
2012-01-04 20:40:04 +01:00
typedef enum Storage {
STORAGE_AUTO,
STORAGE_VOLATILE,
STORAGE_PERSISTENT,
STORAGE_NONE,
_STORAGE_MAX,
_STORAGE_INVALID = -1
} Storage;
typedef enum SplitMode {
SPLIT_UID,
SPLIT_LOGIN, /* deprecated */
SPLIT_NONE,
_SPLIT_MAX,
_SPLIT_INVALID = -1
} SplitMode;
typedef struct JournalCompressOptions {
bool enabled;
uint64_t threshold_bytes;
} JournalCompressOptions;
typedef struct JournalStorageSpace {
usec_t timestamp;
uint64_t available;
uint64_t limit;
uint64_t vfs_used; /* space used by journal files */
uint64_t vfs_available;
} JournalStorageSpace;
typedef struct JournalStorage {
const char *name;
char *path;
JournalMetrics metrics;
JournalStorageSpace space;
} JournalStorage;
struct Server {
2012-01-04 20:40:04 +01:00
int syslog_fd;
int native_fd;
int stdout_fd;
int dev_kmsg_fd;
int audit_fd;
int hostname_fd;
int notify_fd;
2012-01-04 20:40:04 +01:00
sd_event *event;
sd_event_source *syslog_event_source;
sd_event_source *native_event_source;
sd_event_source *stdout_event_source;
sd_event_source *dev_kmsg_event_source;
sd_event_source *audit_event_source;
sd_event_source *sync_event_source;
sd_event_source *sigusr1_event_source;
sd_event_source *sigusr2_event_source;
sd_event_source *sigterm_event_source;
sd_event_source *sigint_event_source;
sd_event_source *sigrtmin1_event_source;
sd_event_source *hostname_event_source;
sd_event_source *notify_event_source;
2015-11-03 12:28:19 +01:00
sd_event_source *watchdog_event_source;
2012-01-04 20:40:04 +01:00
JournalFile *runtime_journal;
JournalFile *system_journal;
OrderedHashmap *user_journals;
2012-01-04 20:40:04 +01:00
uint64_t seqnum;
char *buffer;
size_t buffer_size;
JournalRateLimit *rate_limit;
usec_t sync_interval_usec;
2012-01-04 20:40:04 +01:00
usec_t rate_limit_interval;
unsigned rate_limit_burst;
JournalStorage runtime_storage;
JournalStorage system_storage;
2012-01-04 20:40:04 +01:00
JournalCompressOptions compress;
bool seal;
bool read_kmsg;
2012-01-04 20:40:04 +01:00
bool forward_to_kmsg;
bool forward_to_syslog;
bool forward_to_console;
bool forward_to_wall;
unsigned n_forward_syslog_missed;
usec_t last_warn_forward_syslog_missed;
2012-01-04 20:40:04 +01:00
uint64_t var_available_timestamp;
usec_t max_retention_usec;
usec_t max_file_usec;
usec_t oldest_file_usec;
2012-01-04 20:40:04 +01:00
LIST_HEAD(StdoutStream, stdout_streams);
LIST_HEAD(StdoutStream, stdout_streams_notify_queue);
2012-01-04 20:40:04 +01:00
unsigned n_stdout_streams;
char *tty_path;
int max_level_store;
int max_level_syslog;
int max_level_kmsg;
int max_level_console;
int max_level_wall;
Storage storage;
SplitMode split_mode;
MMapCache *mmap;
Set *deferred_closes;
uint64_t *kernel_seqnum;
2015-11-03 12:28:19 +01:00
bool dev_kmsg_readable:1;
2015-11-03 12:28:19 +01:00
bool send_watchdog:1;
bool sent_notify_ready:1;
bool sync_scheduled:1;
char machine_id_field[sizeof("_MACHINE_ID=") + 32];
char boot_id_field[sizeof("_BOOT_ID=") + 32];
char *hostname_field;
/* Cached cgroup root, so that we don't have to query that all the time */
char *cgroup_root;
2015-11-03 12:28:19 +01:00
usec_t watchdog_usec;
usec_t last_realtime_clock;
size_t line_max;
/* Caching of client metadata */
Hashmap *client_contexts;
Prioq *client_contexts_lru;
ClientContext *my_context; /* the context of journald itself */
ClientContext *pid1_context; /* the context of PID 1 */
};
2012-01-04 20:40:04 +01:00
#define SERVER_MACHINE_ID(s) ((s)->machine_id_field + STRLEN("_MACHINE_ID="))
/* Extra fields for any log messages */
core: add "invocation ID" concept to service manager 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.
2016-08-30 23:18:46 +02:00
#define N_IOVEC_META_FIELDS 22
/* Extra fields for log messages that contain OBJECT_PID= (i.e. log about another process) */
#define N_IOVEC_OBJECT_FIELDS 18
/* Maximum number of fields we'll add in for driver (i.e. internal) messages */
#define N_IOVEC_PAYLOAD_FIELDS 16
/* kmsg: Maximum number of extra fields we'll import from the kernel's /dev/kmsg */
#define N_IOVEC_KERNEL_FIELDS 64
/* kmsg: Maximum number of extra fields we'll import from udev's devices */
#define N_IOVEC_UDEV_FIELDS 32
core: implement /run/systemd/units/-based path for passing unit info from PID 1 to journald And let's make use of it to implement two new unit settings with it: 1. LogLevelMax= is a new per-unit setting that may be used to configure log priority filtering: set it to LogLevelMax=notice and only messages of level "notice" and lower (i.e. more important) will be processed, all others are dropped. 2. LogExtraFields= is a new per-unit setting for configuring per-unit journal fields, that are implicitly included in every log record generated by the unit's processes. It takes field/value pairs in the form of FOO=BAR. Also, related to this, one exisiting unit setting is ported to this new facility: 3. The invocation ID is now pulled from /run/systemd/units/ instead of cgroupfs xattrs. This substantially relaxes requirements of systemd on the kernel version and the privileges it runs with (specifically, cgroupfs xattrs are not available in containers, since they are stored in kernel memory, and hence are unsafe to permit to lesser privileged code). /run/systemd/units/ is a new directory, which contains a number of files and symlinks encoding the above information. PID 1 creates and manages these files, and journald reads them from there. Note that this is supposed to be a direct path between PID 1 and the journal only, due to the special runtime environment the journal runs in. Normally, today we shouldn't introduce new interfaces that (mis-)use a file system as IPC framework, and instead just an IPC system, but this is very hard to do between the journal and PID 1, as long as the IPC system is a subject PID 1 manages, and itself a client to the journal. This patch cleans up a couple of types used in journal code: specifically we switch to size_t for a couple of memory-sizing values, as size_t is the right choice for everything that is memory. Fixes: #4089 Fixes: #3041 Fixes: #4441
2017-11-02 19:43:32 +01:00
void server_dispatch_message(Server *s, struct iovec *iovec, size_t n, size_t m, ClientContext *c, const struct timeval *tv, int priority, pid_t object_pid);
void server_driver_message(Server *s, pid_t object_pid, const char *message_id, const char *format, ...) _sentinel_ _printf_(4,0);
2012-01-04 20:40:04 +01:00
/* gperf lookup function */
const struct ConfigPerfItem* journald_gperf_lookup(const char *key, GPERF_LEN_TYPE length);
2012-01-04 20:40:04 +01:00
CONFIG_PARSER_PROTOTYPE(config_parse_storage);
CONFIG_PARSER_PROTOTYPE(config_parse_line_max);
CONFIG_PARSER_PROTOTYPE(config_parse_compress);
const char *storage_to_string(Storage s) _const_;
Storage storage_from_string(const char *s) _pure_;
CONFIG_PARSER_PROTOTYPE(config_parse_split_mode);
const char *split_mode_to_string(SplitMode s) _const_;
SplitMode split_mode_from_string(const char *s) _pure_;
int server_init(Server *s);
void server_done(Server *s);
void server_sync(Server *s);
int server_vacuum(Server *s, bool verbose);
void server_rotate(Server *s);
int server_schedule_sync(Server *s, int priority);
int server_flush_to_var(Server *s, bool require_flag_file);
void server_maybe_append_tags(Server *s);
int server_process_datagram(sd_event_source *es, int fd, uint32_t revents, void *userdata);
void server_space_usage_message(Server *s, JournalStorage *storage);