mirror of
https://github.com/netdata/netdata.git
synced 2025-04-14 09:38:34 +00:00

* 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>
243 lines
6.8 KiB
C
243 lines
6.8 KiB
C
// SPDX-License-Identifier: GPL-3.0-or-later
|
|
|
|
#include "debugfs_plugin.h"
|
|
#include "libnetdata/required_dummies.h"
|
|
|
|
static char *user_config_dir = CONFIG_DIR;
|
|
static char *stock_config_dir = LIBCONFIG_DIR;
|
|
|
|
static int update_every = 1;
|
|
|
|
static struct debugfs_module {
|
|
const char *name;
|
|
|
|
int enabled;
|
|
|
|
int (*func)(int update_every, const char *name);
|
|
} debugfs_modules[] = {
|
|
// Memory Fragmentation
|
|
{ .name = "/sys/kernel/debug/extfrag", .enabled = CONFIG_BOOLEAN_YES,
|
|
.func = do_debugfs_extfrag},
|
|
{ .name = "/sys/kernel/debug/zswap", .enabled = CONFIG_BOOLEAN_YES,
|
|
.func = do_debugfs_zswap},
|
|
// Linux powercap metrics is here because it needs privilege to read each RAPL zone
|
|
{ .name = "/sys/devices/virtual/powercap", .enabled = CONFIG_BOOLEAN_YES,
|
|
.func = do_sys_devices_virtual_powercap},
|
|
|
|
// The terminator
|
|
{ .name = NULL, .enabled = CONFIG_BOOLEAN_NO, .func = NULL}
|
|
};
|
|
|
|
#ifdef HAVE_CAPABILITY
|
|
static int debugfs_check_capabilities()
|
|
{
|
|
cap_t caps = cap_get_proc();
|
|
if (!caps) {
|
|
netdata_log_error("Cannot get current capabilities.");
|
|
return 0;
|
|
}
|
|
|
|
int ret = 1;
|
|
cap_flag_value_t cfv = CAP_CLEAR;
|
|
if (cap_get_flag(caps, CAP_DAC_READ_SEARCH, CAP_EFFECTIVE, &cfv) == -1) {
|
|
netdata_log_error("Cannot find if CAP_DAC_READ_SEARCH is effective.");
|
|
ret = 0;
|
|
} else {
|
|
if (cfv != CAP_SET) {
|
|
netdata_log_error("debugfs.plugin should run with CAP_DAC_READ_SEARCH.");
|
|
ret = 0;
|
|
}
|
|
}
|
|
cap_free(caps);
|
|
|
|
return ret;
|
|
}
|
|
#else
|
|
static int debugfs_check_capabilities()
|
|
{
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
// TODO: This is a function used by 3 different collector, we should do it global (next PR)
|
|
static int debugfs_am_i_running_as_root()
|
|
{
|
|
uid_t uid = getuid(), euid = geteuid();
|
|
|
|
if (uid == 0 || euid == 0) {
|
|
return 1;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
void debugfs2lower(char *name)
|
|
{
|
|
while (*name) {
|
|
*name = tolower(*name);
|
|
name++;
|
|
}
|
|
}
|
|
|
|
// Consiidering our goal to redce binaries, I preferred to copy function, instead to force link with unecessary libs
|
|
const char *debugfs_rrdset_type_name(RRDSET_TYPE chart_type) {
|
|
switch(chart_type) {
|
|
case RRDSET_TYPE_LINE:
|
|
default:
|
|
return RRDSET_TYPE_LINE_NAME;
|
|
|
|
case RRDSET_TYPE_AREA:
|
|
return RRDSET_TYPE_AREA_NAME;
|
|
|
|
case RRDSET_TYPE_STACKED:
|
|
return RRDSET_TYPE_STACKED_NAME;
|
|
}
|
|
}
|
|
|
|
const char *debugfs_rrd_algorithm_name(RRD_ALGORITHM algorithm) {
|
|
switch(algorithm) {
|
|
case RRD_ALGORITHM_ABSOLUTE:
|
|
default:
|
|
return RRD_ALGORITHM_ABSOLUTE_NAME;
|
|
|
|
case RRD_ALGORITHM_INCREMENTAL:
|
|
return RRD_ALGORITHM_INCREMENTAL_NAME;
|
|
|
|
case RRD_ALGORITHM_PCENT_OVER_ROW_TOTAL:
|
|
return RRD_ALGORITHM_PCENT_OVER_ROW_TOTAL_NAME;
|
|
|
|
case RRD_ALGORITHM_PCENT_OVER_DIFF_TOTAL:
|
|
return RRD_ALGORITHM_PCENT_OVER_DIFF_TOTAL_NAME;
|
|
}
|
|
}
|
|
|
|
int debugfs_check_sys_permission() {
|
|
int ret = 0;
|
|
|
|
char filename[FILENAME_MAX + 1];
|
|
|
|
snprintfz(filename, FILENAME_MAX, "%s/sys/kernel/debug/extfrag/extfrag_index", netdata_configured_host_prefix);
|
|
|
|
procfile *ff = procfile_open(filename, NULL, PROCFILE_FLAG_NO_ERROR_ON_FILE_IO);
|
|
if(!ff) goto dcsp_cleanup;
|
|
|
|
ff = procfile_readall(ff);
|
|
if(!ff) goto dcsp_cleanup;
|
|
|
|
ret = 1;
|
|
|
|
dcsp_cleanup:
|
|
if (!ret)
|
|
perror("Cannot open /sys/kernel/debug/extfrag/extfrag_index file");
|
|
procfile_close(ff);
|
|
return ret;
|
|
}
|
|
|
|
static void debugfs_parse_args(int argc, char **argv)
|
|
{
|
|
int i, freq = 0;
|
|
for(i = 1; i < argc; i++) {
|
|
if(!freq) {
|
|
int n = (int)str2l(argv[i]);
|
|
if(n > 0) {
|
|
freq = n;
|
|
continue;
|
|
}
|
|
}
|
|
|
|
if(strcmp("test-permissions", argv[i]) == 0 || strcmp("-t", argv[i]) == 0) {
|
|
if(!debugfs_check_sys_permission()) {
|
|
exit(2);
|
|
}
|
|
printf("OK\n");
|
|
exit(0);
|
|
}
|
|
}
|
|
|
|
if(freq > 0) update_every = freq;
|
|
}
|
|
|
|
int main(int argc, char **argv)
|
|
{
|
|
clocks_init();
|
|
nd_log_initialize_for_external_plugins("debugfs.plugin");
|
|
|
|
netdata_configured_host_prefix = getenv("NETDATA_HOST_PREFIX");
|
|
if (verify_netdata_host_prefix() == -1)
|
|
exit(1);
|
|
|
|
user_config_dir = getenv("NETDATA_USER_CONFIG_DIR");
|
|
if (user_config_dir == NULL) {
|
|
user_config_dir = CONFIG_DIR;
|
|
}
|
|
|
|
stock_config_dir = getenv("NETDATA_STOCK_CONFIG_DIR");
|
|
if (stock_config_dir == NULL) {
|
|
// netdata_log_info("NETDATA_CONFIG_DIR is not passed from netdata");
|
|
stock_config_dir = LIBCONFIG_DIR;
|
|
}
|
|
|
|
// FIXME: should first check if /sys/kernel/debug is mounted
|
|
|
|
// FIXME: remove debugfs_check_sys_permission() after https://github.com/netdata/netdata/issues/15048 is fixed
|
|
if (!debugfs_check_capabilities() && !debugfs_am_i_running_as_root() && !debugfs_check_sys_permission()) {
|
|
uid_t uid = getuid(), euid = geteuid();
|
|
#ifdef HAVE_CAPABILITY
|
|
netdata_log_error(
|
|
"debugfs.plugin should either run as root (now running with uid %u, euid %u) or have special capabilities. "
|
|
"Without these, debugfs.plugin cannot access /sys/kernel/debug. "
|
|
"To enable capabilities run: sudo setcap cap_dac_read_search,cap_sys_ptrace+ep %s; "
|
|
"To enable setuid to root run: sudo chown root:netdata %s; sudo chmod 4750 %s; ",
|
|
uid,
|
|
euid,
|
|
argv[0],
|
|
argv[0],
|
|
argv[0]);
|
|
#else
|
|
netdata_log_error(
|
|
"debugfs.plugin should either run as root (now running with uid %u, euid %u) or have special capabilities. "
|
|
"Without these, debugfs.plugin cannot access /sys/kernel/debug."
|
|
"Your system does not support capabilities. "
|
|
"To enable setuid to root run: sudo chown root:netdata %s; sudo chmod 4750 %s; ",
|
|
uid,
|
|
euid,
|
|
argv[0],
|
|
argv[0]);
|
|
#endif
|
|
exit(1);
|
|
}
|
|
|
|
// if (!debugfs_check_sys_permission()) {
|
|
// exit(2);
|
|
// }
|
|
|
|
debugfs_parse_args(argc, argv);
|
|
|
|
size_t iteration;
|
|
usec_t step = update_every * USEC_PER_SEC;
|
|
heartbeat_t hb;
|
|
heartbeat_init(&hb);
|
|
|
|
for (iteration = 0; iteration < 86400; iteration++) {
|
|
heartbeat_next(&hb, step);
|
|
int enabled = 0;
|
|
|
|
for (int i = 0; debugfs_modules[i].name; i++) {
|
|
struct debugfs_module *pm = &debugfs_modules[i];
|
|
if (unlikely(!pm->enabled))
|
|
continue;
|
|
|
|
pm->enabled = !pm->func(update_every, pm->name);
|
|
if (likely(pm->enabled))
|
|
enabled++;
|
|
}
|
|
if (!enabled) {
|
|
netdata_log_info("all modules are disabled, exiting...");
|
|
return 1;
|
|
}
|
|
}
|
|
|
|
fprintf(stdout, "EXIT\n");
|
|
fflush(stdout);
|
|
return 0;
|
|
}
|