0
0
Fork 0
mirror of https://github.com/netdata/netdata.git synced 2025-04-17 11:12:42 +00:00
netdata_netdata/libnetdata/threads/threads.c
Costa Tsaousis 3e508c8f95
New logging layer ()
* cleanup of logging - wip

* first working iteration

* add errno annotator

* replace old logging functions with netdata_logger()

* cleanup

* update error_limit

* fix remanining error_limit references

* work on fatal()

* started working on structured logs

* full cleanup

* default logging to files; fix all plugins initialization

* fix formatting of numbers

* cleanup and reorg

* fix coverity issues

* cleanup obsolete code

* fix formatting of numbers

* fix log rotation

* fix for older systems

* add detection of systemd journal via stderr

* finished on access.log

* remove left-over transport

* do not add empty fields to the logs

* journal get compact uuids; X-Transaction-ID header is added in web responses

* allow compiling on systems without memfd sealing

* added libnetdata/uuid directory

* move datetime formatters to libnetdata

* add missing files

* link the makefiles in libnetdata

* added uuid_parse_flexi() to parse UUIDs with and without hyphens; the web server now read X-Transaction-ID and uses it for functions and web responses

* added stream receiver, sender, proc plugin and pluginsd log stack

* iso8601 advanced usage; line_splitter module in libnetdata; code cleanup

* add message ids to streaming inbound and outbound connections

* cleanup line_splitter between lines to avoid logging garbage; when killing children, kill them with SIGABRT if internal checks is enabled

* send SIGABRT to external plugins only if we are not shutting down

* fix cross cleanup in pluginsd parser

* fatal when there is a stack error in logs

* compile netdata with -fexceptions

* do not kill external plugins with SIGABRT

* metasync info logs to debug level

* added severity to logs

* added json output; added options per log output; added documentation; fixed issues mentioned

* allow memfd only on linux

* moved journal low level functions to journal.c/h

* move health logs to daemon.log with proper priorities

* fixed a couple of bugs; health log in journal

* updated docs

* systemd-cat-native command to push structured logs to journal from the command line

* fix makefiles

* restored NETDATA_LOG_SEVERITY_LEVEL

* fix makefiles

* systemd-cat-native can also work as the logger of Netdata scripts

* do not require a socket to systemd-journal to log-as-netdata

* alarm notify logs in native format

* properly compare log ids

* fatals log alerts; alarm-notify.sh working

* fix overflow warning

* alarm-notify.sh now logs the request (command line)

* anotate external plugins logs with the function cmd they run

* added context, component and type to alarm-notify.sh; shell sanitization removes control character and characters that may be expanded by bash

* reformatted alarm-notify logs

* unify cgroup-network-helper.sh

* added quotes around params

* charts.d.plugin switched logging to journal native

* quotes for logfmt

* unify the status codes of streaming receivers and senders

* alarm-notify: dont log anything, if there is nothing to do

* all external plugins log to stderr when running outside netdata; alarm-notify now shows an error when notifications menthod are needed but are not available

* migrate cgroup-name.sh to new logging

* systemd-cat-native now supports messages with newlines

* socket.c logs use priority

* cleanup log field types

* inherit the systemd set INVOCATION_ID if found

* allow systemd-cat-native to send messages to a systemd-journal-remote URL

* log2journal command that can convert structured logs to journal export format

* various fixes and documentation of log2journal

* updated log2journal docs

* updated log2journal docs

* updated documentation of fields

* allow compiling without libcurl

* do not use socket as format string

* added version information to newly added tools

* updated documentation and help messages

* fix the namespace socket path

* print errno with error

* do not timeout

* updated docs

* updated docs

* updated docs

* log2journal updated docs and params

* when talking to a remote journal, systemd-cat-native batches the messages

* enable lz4 compression for systemd-cat-native when sending messages to a systemd-journal-remote

* Revert "enable lz4 compression for systemd-cat-native when sending messages to a systemd-journal-remote"

This reverts commit b079d53c11.

* note about uncompressed traffic

* log2journal: code reorg and cleanup to make modular

* finished rewriting log2journal

* more comments

* rewriting rules support

* increased limits

* updated docs

* updated docs

* fix old log call

* use journal only when stderr is connected to journal

* update netdata.spec for libcurl, libpcre2 and log2journal

* pcre2-devel

* do not require pcre2 in centos < 8, amazonlinux < 2023, open suse

* log2journal only on systems pcre2 is available

* ignore log2journal in .gitignore

* avoid log2journal on centos 7, amazonlinux 2 and opensuse

* add pcre2-8 to static build

* undo last commit

* Bundle to static

Signed-off-by: Tasos Katsoulas <tasos@netdata.cloud>

* Add build deps for deb packages

Signed-off-by: Tasos Katsoulas <tasos@netdata.cloud>

* Add dependencies; build from source

Signed-off-by: Tasos Katsoulas <tasos@netdata.cloud>

* Test build for amazon linux and centos expect to fail for suse

Signed-off-by: Tasos Katsoulas <tasos@netdata.cloud>

* fix minor oversight

Signed-off-by: Tasos Katsoulas <tasos@netdata.cloud>

* Reorg code

* Add the install from source (deps) as a TODO
* Not enable the build on suse ecosystem

Signed-off-by: Tasos Katsoulas <tasos@netdata.cloud>

---------

Signed-off-by: Tasos Katsoulas <tasos@netdata.cloud>
Co-authored-by: Tasos Katsoulas <tasos@netdata.cloud>
2023-11-22 10:27:25 +02:00

344 lines
11 KiB
C

// SPDX-License-Identifier: GPL-3.0-or-later
#include "../libnetdata.h"
static pthread_attr_t *netdata_threads_attr = NULL;
// ----------------------------------------------------------------------------
// per thread data
typedef struct {
void *arg;
char tag[NETDATA_THREAD_NAME_MAX + 1];
SPINLOCK detach_lock;
void *(*start_routine) (void *);
NETDATA_THREAD_OPTIONS options;
} NETDATA_THREAD;
static __thread NETDATA_THREAD *netdata_thread = NULL;
inline int netdata_thread_tag_exists(void) {
return (netdata_thread && *netdata_thread->tag);
}
static const char *thread_name_get(bool recheck) {
static __thread char threadname[NETDATA_THREAD_NAME_MAX + 1] = "";
if(netdata_thread_tag_exists())
strncpyz(threadname, netdata_thread->tag, NETDATA_THREAD_NAME_MAX);
else {
if(!recheck && threadname[0])
return threadname;
#if defined(__FreeBSD__)
pthread_get_name_np(pthread_self(), threadname, NETDATA_THREAD_NAME_MAX + 1);
if(strcmp(threadname, "netdata") == 0)
strncpyz(threadname, "MAIN", NETDATA_THREAD_NAME_MAX);
#elif defined(__APPLE__)
strncpyz(threadname, "MAIN", NETDATA_THREAD_NAME_MAX);
#elif defined(HAVE_PTHREAD_GETNAME_NP)
pthread_getname_np(pthread_self(), threadname, NETDATA_THREAD_NAME_MAX + 1);
if(strcmp(threadname, "netdata") == 0)
strncpyz(threadname, "MAIN", NETDATA_THREAD_NAME_MAX);
#else
strncpyz(threadname, "MAIN", NETDATA_THREAD_NAME_MAX);
#endif
}
return threadname;
}
const char *netdata_thread_tag(void) {
return thread_name_get(false);
}
static size_t webrtc_id = 0;
static __thread bool webrtc_name_set = false;
void webrtc_set_thread_name(void) {
if(!netdata_thread && !webrtc_name_set) {
webrtc_name_set = true;
char threadname[NETDATA_THREAD_NAME_MAX + 1];
#if defined(__FreeBSD__)
snprintfz(threadname, NETDATA_THREAD_NAME_MAX, "WEBRTC[%zu]", __atomic_fetch_add(&webrtc_id, 1, __ATOMIC_RELAXED));
pthread_set_name_np(pthread_self(), threadname);
#elif defined(__APPLE__)
snprintfz(threadname, NETDATA_THREAD_NAME_MAX, "WEBRTC[%zu]", __atomic_fetch_add(&webrtc_id, 1, __ATOMIC_RELAXED));
pthread_setname_np(threadname);
#elif defined(HAVE_PTHREAD_GETNAME_NP)
pthread_getname_np(pthread_self(), threadname, NETDATA_THREAD_NAME_MAX+1);
if(strcmp(threadname, "netdata") == 0) {
snprintfz(threadname, NETDATA_THREAD_NAME_MAX, "WEBRTC[%zu]", __atomic_fetch_add(&webrtc_id, 1, __ATOMIC_RELAXED));
pthread_setname_np(pthread_self(), threadname);
}
#else
snprintfz(threadname, NETDATA_THREAD_NAME_MAX, "WEBRTC[%zu]", __atomic_fetch_add(&webrtc_id, 1, __ATOMIC_RELAXED));
pthread_setname_np(pthread_self(), threadname);
#endif
thread_name_get(true);
}
}
// ----------------------------------------------------------------------------
// compatibility library functions
static __thread pid_t gettid_cached_tid = 0;
pid_t gettid(void) {
pid_t tid = 0;
if(likely(gettid_cached_tid > 0))
return gettid_cached_tid;
#ifdef __FreeBSD__
tid = (pid_t)pthread_getthreadid_np();
#elif defined(__APPLE__)
#if (defined __MAC_OS_X_VERSION_MIN_REQUIRED && __MAC_OS_X_VERSION_MIN_REQUIRED >= 1060)
uint64_t curthreadid;
pthread_threadid_np(NULL, &curthreadid);
tid = (pid_t)curthreadid;
#else /* __MAC_OS_X_VERSION_MIN_REQUIRED */
tid = (pid_t)pthread_self;
#endif /* __MAC_OS_X_VERSION_MIN_REQUIRED */
#else /* __APPLE__*/
tid = (pid_t)syscall(SYS_gettid);
#endif /* __FreeBSD__, __APPLE__*/
gettid_cached_tid = tid;
return tid;
}
// ----------------------------------------------------------------------------
// early initialization
size_t netdata_threads_init(void) {
int i;
// --------------------------------------------------------------------
// get the required stack size of the threads of netdata
if(!netdata_threads_attr) {
netdata_threads_attr = callocz(1, sizeof(pthread_attr_t));
i = pthread_attr_init(netdata_threads_attr);
if (i != 0)
fatal("pthread_attr_init() failed with code %d.", i);
}
size_t stacksize = 0;
i = pthread_attr_getstacksize(netdata_threads_attr, &stacksize);
if(i != 0)
fatal("pthread_attr_getstacksize() failed with code %d.", i);
return stacksize;
}
// ----------------------------------------------------------------------------
// late initialization
void netdata_threads_init_after_fork(size_t stacksize) {
int i;
// ------------------------------------------------------------------------
// set pthread stack size
if(netdata_threads_attr && stacksize > (size_t)PTHREAD_STACK_MIN) {
i = pthread_attr_setstacksize(netdata_threads_attr, stacksize);
if(i != 0)
nd_log(NDLS_DAEMON, NDLP_WARNING, "pthread_attr_setstacksize() to %zu bytes, failed with code %d.", stacksize, i);
else
nd_log(NDLS_DAEMON, NDLP_DEBUG, "Set threads stack size to %zu bytes", stacksize);
}
else
nd_log(NDLS_DAEMON, NDLP_WARNING, "Invalid pthread stacksize %zu", stacksize);
}
// ----------------------------------------------------------------------------
// threads init for external plugins
void netdata_threads_init_for_external_plugins(size_t stacksize) {
size_t default_stacksize = netdata_threads_init();
if(default_stacksize < 1 * 1024 * 1024)
default_stacksize = 1 * 1024 * 1024;
netdata_threads_init_after_fork(stacksize ? stacksize : default_stacksize);
}
// ----------------------------------------------------------------------------
// netdata_thread_create
void rrdset_thread_rda_free(void);
void sender_thread_buffer_free(void);
void query_target_free(void);
void service_exits(void);
void rrd_collector_finished(void);
static void thread_cleanup(void *ptr) {
if(netdata_thread != ptr) {
NETDATA_THREAD *info = (NETDATA_THREAD *)ptr;
nd_log(NDLS_DAEMON, NDLP_ERR, "THREADS: internal error - thread local variable does not match the one passed to this function. Expected thread '%s', passed thread '%s'", netdata_thread->tag, info->tag);
}
spinlock_lock(&netdata_thread->detach_lock);
if(!(netdata_thread->options & NETDATA_THREAD_OPTION_DONT_LOG_CLEANUP))
nd_log(NDLS_DAEMON, NDLP_DEBUG, "thread with task id %d finished", gettid());
rrd_collector_finished();
sender_thread_buffer_free();
rrdset_thread_rda_free();
query_target_free();
thread_cache_destroy();
service_exits();
worker_unregister();
netdata_thread->tag[0] = '\0';
spinlock_unlock(&netdata_thread->detach_lock);
freez(netdata_thread);
netdata_thread = NULL;
}
static void thread_set_name_np(NETDATA_THREAD *nt) {
if (nt && nt->tag[0]) {
int ret = 0;
char threadname[NETDATA_THREAD_NAME_MAX+1];
strncpyz(threadname, nt->tag, NETDATA_THREAD_NAME_MAX);
#if defined(__FreeBSD__)
pthread_set_name_np(pthread_self(), threadname);
#elif defined(__APPLE__)
ret = pthread_setname_np(threadname);
#else
ret = pthread_setname_np(pthread_self(), threadname);
#endif
if (ret != 0)
nd_log(NDLS_DAEMON, NDLP_WARNING, "cannot set pthread name of %d to %s. ErrCode: %d", gettid(), threadname, ret);
else
nd_log(NDLS_DAEMON, NDLP_DEBUG, "set name of thread %d to %s", gettid(), threadname);
}
}
void uv_thread_set_name_np(uv_thread_t ut, const char* name) {
int ret = 0;
char threadname[NETDATA_THREAD_NAME_MAX+1];
strncpyz(threadname, name, NETDATA_THREAD_NAME_MAX);
#if defined(__FreeBSD__)
pthread_set_name_np(ut ? ut : pthread_self(), threadname);
#elif defined(__APPLE__)
// Apple can only set its own name
UNUSED(ut);
#else
ret = pthread_setname_np(ut ? ut : pthread_self(), threadname);
#endif
thread_name_get(true);
if (ret)
nd_log(NDLS_DAEMON, NDLP_NOTICE, "cannot set libuv thread name to %s. Err: %d", threadname, ret);
}
void os_thread_get_current_name_np(char threadname[NETDATA_THREAD_NAME_MAX + 1])
{
threadname[0] = '\0';
#if defined(__FreeBSD__)
pthread_get_name_np(pthread_self(), threadname, NETDATA_THREAD_NAME_MAX + 1);
#elif defined(HAVE_PTHREAD_GETNAME_NP) /* Linux & macOS */
(void)pthread_getname_np(pthread_self(), threadname, NETDATA_THREAD_NAME_MAX + 1);
#endif
}
static void *netdata_thread_init(void *ptr) {
netdata_thread = (NETDATA_THREAD *)ptr;
if(!(netdata_thread->options & NETDATA_THREAD_OPTION_DONT_LOG_STARTUP))
nd_log(NDLS_DAEMON, NDLP_DEBUG, "thread created with task id %d", gettid());
if(pthread_setcanceltype(PTHREAD_CANCEL_DEFERRED, NULL) != 0)
nd_log(NDLS_DAEMON, NDLP_WARNING, "cannot set pthread cancel type to DEFERRED.");
if(pthread_setcancelstate(PTHREAD_CANCEL_ENABLE, NULL) != 0)
nd_log(NDLS_DAEMON, NDLP_WARNING, "cannot set pthread cancel state to ENABLE.");
thread_set_name_np(ptr);
void *ret = NULL;
pthread_cleanup_push(thread_cleanup, ptr);
ret = netdata_thread->start_routine(netdata_thread->arg);
pthread_cleanup_pop(1);
return ret;
}
int netdata_thread_create(netdata_thread_t *thread, const char *tag, NETDATA_THREAD_OPTIONS options, void *(*start_routine) (void *), void *arg) {
NETDATA_THREAD *info = callocz(1, sizeof(NETDATA_THREAD));
info->arg = arg;
info->start_routine = start_routine;
info->options = options;
strncpyz(info->tag, tag, NETDATA_THREAD_NAME_MAX);
spinlock_init(&info->detach_lock);
spinlock_lock(&info->detach_lock);
int ret = pthread_create(thread, netdata_threads_attr, netdata_thread_init, info);
if(ret != 0)
nd_log(NDLS_DAEMON, NDLP_ERR, "failed to create new thread for %s. pthread_create() failed with code %d", tag, ret);
else {
if (!(options & NETDATA_THREAD_OPTION_JOINABLE)) {
int ret2 = pthread_detach(*thread);
if (ret2 != 0)
nd_log(NDLS_DAEMON, NDLP_WARNING, "cannot request detach of newly created %s thread. pthread_detach() failed with code %d", tag, ret2);
}
}
spinlock_unlock(&info->detach_lock);
return ret;
}
// ----------------------------------------------------------------------------
// netdata_thread_cancel
#ifdef NETDATA_INTERNAL_CHECKS
int netdata_thread_cancel_with_trace(netdata_thread_t thread, int line, const char *file, const char *function) {
#else
int netdata_thread_cancel(netdata_thread_t thread) {
#endif
int ret = pthread_cancel(thread);
if(ret != 0)
#ifdef NETDATA_INTERNAL_CHECKS
nd_log(NDLS_DAEMON, NDLP_WARNING, "cannot cancel thread. pthread_cancel() failed with code %d at %d@%s, function %s()", ret, line, file, function);
#else
nd_log(NDLS_DAEMON, NDLP_WARNING, "cannot cancel thread. pthread_cancel() failed with code %d.", ret);
#endif
return ret;
}
// ----------------------------------------------------------------------------
// netdata_thread_join
int netdata_thread_join(netdata_thread_t thread, void **retval) {
int ret = pthread_join(thread, retval);
if(ret != 0)
nd_log(NDLS_DAEMON, NDLP_WARNING, "cannot join thread. pthread_join() failed with code %d.", ret);
return ret;
}
int netdata_thread_detach(pthread_t thread) {
int ret = pthread_detach(thread);
if(ret != 0)
nd_log(NDLS_DAEMON, NDLP_WARNING, "cannot detach thread. pthread_detach() failed with code %d.", ret);
return ret;
}