RRDHOST *rrdhost_find_by_hostname(const char *hostname, uint32_t hash) {
if(unlikely(!strcmp(hostname, "localhost")))
return localhost;
if(unlikely(!hash)) hash = simple_hash(hostname);
rrd_rdlock();
RRDHOST *host;
rrdhost_foreach_read(host) {
if(unlikely((hash == host->hash_hostname && !strcmp(hostname, host->hostname)))) {
rrd_unlock();
return host;
}
}
rrd_unlock();
return NULL;
}
RRDHOST *rrdhost_find_or_create(
const char *hostname
, const char *guid
, const char *os
, int update_every
, long history
, RRD_MEMORY_MODE mode
, int health_enabled
, int rrdpush_enabled
, char *rrdpush_destination
, char *rrdpush_api_key
) {
debug(D_RRDHOST, "Searching for host '%s' with guid '%s'", hostname, guid);
rrd_wrlock();
RRDHOST *host = rrdhost_find_by_guid(guid, 0);
if(!host) {
host = rrdhost_create(
hostname
, guid
, os
, update_every
, history
, mode
, health_enabled
, rrdpush_enabled
, rrdpush_destination
, rrdpush_api_key
, 0
);
}
else {
host->health_enabled = health_enabled;
if(strcmp(host->hostname, hostname)) {
char *t = host->hostname;
host->hostname = strdupz(hostname);
host->hash_hostname = simple_hash(host->hostname);
freez(t);
}
if(host->rrd_update_every != update_every)
error("Host '%s' has an update frequency of %d seconds, but the wanted one is %d seconds.", host->hostname, host->rrd_update_every, update_every);
if(host->rrd_history_entries != history)
error("Host '%s' has history of %ld entries, but the wanted one is %ld entries.", host->hostname, host->rrd_history_entries, history);
if(host->rrd_memory_mode != mode)
error("Host '%s' has memory mode '%s', but the wanted one is '%s'.", host->hostname, rrd_memory_mode_name(host->rrd_memory_mode), rrd_memory_mode_name(mode));
}
rrd_unlock();
rrdhost_cleanup_orphan(host);
return host;
}
void *backends_main(void *ptr) {
netdata_thread_cleanup_push(backends_main_cleanup, ptr);
int default_port = 0;
int sock = -1;
BUFFER *b = buffer_create(1), *response = buffer_create(1);
int (*backend_request_formatter)(BUFFER *, const char *, RRDHOST *, const char *, RRDSET *, RRDDIM *, time_t, time_t, uint32_t) = NULL;
int (*backend_response_checker)(BUFFER *) = NULL;
// ------------------------------------------------------------------------
// collect configuration options
struct timeval timeout = {
.tv_sec = 0,
.tv_usec = 0
};
int enabled = config_get_boolean(CONFIG_SECTION_BACKEND, "enabled", 0);
const char *source = config_get(CONFIG_SECTION_BACKEND, "data source", "average");
const char *type = config_get(CONFIG_SECTION_BACKEND, "type", "graphite");
const char *destination = config_get(CONFIG_SECTION_BACKEND, "destination", "localhost");
backend_prefix = config_get(CONFIG_SECTION_BACKEND, "prefix", "netdata");
const char *hostname = config_get(CONFIG_SECTION_BACKEND, "hostname", localhost->hostname);
backend_update_every = (int)config_get_number(CONFIG_SECTION_BACKEND, "update every", backend_update_every);
int buffer_on_failures = (int)config_get_number(CONFIG_SECTION_BACKEND, "buffer on failures", 10);
long timeoutms = config_get_number(CONFIG_SECTION_BACKEND, "timeout ms", backend_update_every * 2 * 1000);
backend_send_names = config_get_boolean(CONFIG_SECTION_BACKEND, "send names instead of ids", backend_send_names);
charts_pattern = simple_pattern_create(config_get(CONFIG_SECTION_BACKEND, "send charts matching", "*"), NULL, SIMPLE_PATTERN_EXACT);
hosts_pattern = simple_pattern_create(config_get(CONFIG_SECTION_BACKEND, "send hosts matching", "localhost *"), NULL, SIMPLE_PATTERN_EXACT);
// ------------------------------------------------------------------------
// validate configuration options
// and prepare for sending data to our backend
backend_options = backend_parse_data_source(source, backend_options);
if(timeoutms < 1) {
error("BACKEND: invalid timeout %ld ms given. Assuming %d ms.", timeoutms, backend_update_every * 2 * 1000);
timeoutms = backend_update_every * 2 * 1000;
}
timeout.tv_sec = (timeoutms * 1000) / 1000000;
timeout.tv_usec = (timeoutms * 1000) % 1000000;
if(!enabled || backend_update_every < 1)
goto cleanup;
// ------------------------------------------------------------------------
// select the backend type
if(!strcmp(type, "graphite") || !strcmp(type, "graphite:plaintext")) {
default_port = 2003;
backend_response_checker = process_graphite_response;
if((backend_options & BACKEND_SOURCE_BITS) == BACKEND_SOURCE_DATA_AS_COLLECTED)
backend_request_formatter = format_dimension_collected_graphite_plaintext;
else
backend_request_formatter = format_dimension_stored_graphite_plaintext;
}
else if(!strcmp(type, "opentsdb") || !strcmp(type, "opentsdb:telnet")) {
default_port = 4242;
backend_response_checker = process_opentsdb_response;
if((backend_options & BACKEND_SOURCE_BITS) == BACKEND_SOURCE_DATA_AS_COLLECTED)
backend_request_formatter = format_dimension_collected_opentsdb_telnet;
else
backend_request_formatter = format_dimension_stored_opentsdb_telnet;
}
else if (!strcmp(type, "json") || !strcmp(type, "json:plaintext")) {
default_port = 5448;
backend_response_checker = process_json_response;
if ((backend_options & BACKEND_SOURCE_BITS) == BACKEND_SOURCE_DATA_AS_COLLECTED)
backend_request_formatter = format_dimension_collected_json_plaintext;
else
backend_request_formatter = format_dimension_stored_json_plaintext;
}
else {
error("BACKEND: Unknown backend type '%s'", type);
goto cleanup;
}
if(backend_request_formatter == NULL || backend_response_checker == NULL) {
error("BACKEND: backend is misconfigured - disabling it.");
goto cleanup;
}
// ------------------------------------------------------------------------
// prepare the charts for monitoring the backend operation
struct rusage thread;
collected_number
chart_buffered_metrics = 0,
chart_lost_metrics = 0,
chart_sent_metrics = 0,
chart_buffered_bytes = 0,
chart_received_bytes = 0,
chart_sent_bytes = 0,
chart_receptions = 0,
chart_transmission_successes = 0,
chart_transmission_failures = 0,
chart_data_lost_events = 0,
chart_lost_bytes = 0,
chart_backend_reconnects = 0,
chart_backend_latency = 0;
RRDSET *chart_metrics = rrdset_create_localhost("netdata", "backend_metrics", NULL, "backend", NULL, "Netdata Buffered Metrics", "metrics", "backends", NULL, 130600, backend_update_every, RRDSET_TYPE_LINE);
rrddim_add(chart_metrics, "buffered", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE);
rrddim_add(chart_metrics, "lost", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE);
rrddim_add(chart_metrics, "sent", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE);
RRDSET *chart_bytes = rrdset_create_localhost("netdata", "backend_bytes", NULL, "backend", NULL, "Netdata Backend Data Size", "KB", "backends", NULL, 130610, backend_update_every, RRDSET_TYPE_AREA);
rrddim_add(chart_bytes, "buffered", NULL, 1, 1024, RRD_ALGORITHM_ABSOLUTE);
rrddim_add(chart_bytes, "lost", NULL, 1, 1024, RRD_ALGORITHM_ABSOLUTE);
rrddim_add(chart_bytes, "sent", NULL, 1, 1024, RRD_ALGORITHM_ABSOLUTE);
rrddim_add(chart_bytes, "received", NULL, 1, 1024, RRD_ALGORITHM_ABSOLUTE);
RRDSET *chart_ops = rrdset_create_localhost("netdata", "backend_ops", NULL, "backend", NULL, "Netdata Backend Operations", "operations", "backends", NULL, 130630, backend_update_every, RRDSET_TYPE_LINE);
rrddim_add(chart_ops, "write", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE);
rrddim_add(chart_ops, "discard", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE);
rrddim_add(chart_ops, "reconnect", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE);
rrddim_add(chart_ops, "failure", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE);
rrddim_add(chart_ops, "read", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE);
/*
* this is misleading - we can only measure the time we need to send data
* this time is not related to the time required for the data to travel to
* the backend database and the time that server needed to process them
*
* issue #1432 and https://www.softlab.ntua.gr/facilities/documentation/unix/unix-socket-faq/unix-socket-faq-2.html
*
RRDSET *chart_latency = rrdset_create_localhost("netdata", "backend_latency", NULL, "backend", NULL, "Netdata Backend Latency", "ms", "backends", NULL, 130620, backend_update_every, RRDSET_TYPE_AREA);
rrddim_add(chart_latency, "latency", NULL, 1, 1000, RRD_ALGORITHM_ABSOLUTE);
*/
RRDSET *chart_rusage = rrdset_create_localhost("netdata", "backend_thread_cpu", NULL, "backend", NULL, "NetData Backend Thread CPU usage", "milliseconds/s", "backends", NULL, 130630, backend_update_every, RRDSET_TYPE_STACKED);
rrddim_add(chart_rusage, "user", NULL, 1, 1000, RRD_ALGORITHM_INCREMENTAL);
rrddim_add(chart_rusage, "system", NULL, 1, 1000, RRD_ALGORITHM_INCREMENTAL);
// ------------------------------------------------------------------------
// prepare the backend main loop
info("BACKEND: configured ('%s' on '%s' sending '%s' data, every %d seconds, as host '%s', with prefix '%s')", type, destination, source, backend_update_every, hostname, backend_prefix);
usec_t step_ut = backend_update_every * USEC_PER_SEC;
time_t after = now_realtime_sec();
int failures = 0;
heartbeat_t hb;
heartbeat_init(&hb);
while(!netdata_exit) {
// ------------------------------------------------------------------------
// Wait for the next iteration point.
heartbeat_next(&hb, step_ut);
time_t before = now_realtime_sec();
debug(D_BACKEND, "BACKEND: preparing buffer for timeframe %lu to %lu", (unsigned long)after, (unsigned long)before);
// ------------------------------------------------------------------------
// add to the buffer the data we need to send to the backend
netdata_thread_disable_cancelability();
size_t count_hosts = 0;
size_t count_charts_total = 0;
size_t count_dims_total = 0;
rrd_rdlock();
RRDHOST *host;
rrdhost_foreach_read(host) {
if(unlikely(!rrdhost_flag_check(host, RRDHOST_FLAG_BACKEND_SEND|RRDHOST_FLAG_BACKEND_DONT_SEND))) {
char *name = (host == localhost)?"localhost":host->hostname;
if (!hosts_pattern || simple_pattern_matches(hosts_pattern, name)) {
rrdhost_flag_set(host, RRDHOST_FLAG_BACKEND_SEND);
info("enabled backend for host '%s'", name);
}
else {
rrdhost_flag_set(host, RRDHOST_FLAG_BACKEND_DONT_SEND);
info("disabled backend for host '%s'", name);
}
}
if(unlikely(!rrdhost_flag_check(host, RRDHOST_FLAG_BACKEND_SEND)))
continue;
rrdhost_rdlock(host);
count_hosts++;
size_t count_charts = 0;
size_t count_dims = 0;
size_t count_dims_skipped = 0;
const char *__hostname = (host == localhost)?hostname:host->hostname;
RRDSET *st;
rrdset_foreach_read(st, host) {
if(likely(backends_can_send_rrdset(backend_options, st))) {
rrdset_rdlock(st);
count_charts++;
RRDDIM *rd;
rrddim_foreach_read(rd, st) {
if (likely(rd->last_collected_time.tv_sec >= after)) {
chart_buffered_metrics += backend_request_formatter(b, backend_prefix, host, __hostname, st, rd, after, before, backend_options);
count_dims++;
}
else {
debug(D_BACKEND, "BACKEND: not sending dimension '%s' of chart '%s' from host '%s', its last data collection (%lu) is not within our timeframe (%lu to %lu)", rd->id, st->id, __hostname, (unsigned long)rd->last_collected_time.tv_sec, (unsigned long)after, (unsigned long)before);
count_dims_skipped++;
}
}
rrdset_unlock(st);
}
}
debug(D_BACKEND, "BACKEND: sending host '%s', metrics of %zu dimensions, of %zu charts. Skipped %zu dimensions.", __hostname, count_dims, count_charts, count_dims_skipped);
count_charts_total += count_charts;
count_dims_total += count_dims;
rrdhost_unlock(host);
}
rrd_unlock();
netdata_thread_enable_cancelability();
debug(D_BACKEND, "BACKEND: buffer has %zu bytes, added metrics for %zu dimensions, of %zu charts, from %zu hosts", buffer_strlen(b), count_dims_total, count_charts_total, count_hosts);
// ------------------------------------------------------------------------
chart_buffered_bytes = (collected_number)buffer_strlen(b);
// reset the monitoring chart counters
chart_received_bytes =
chart_sent_bytes =
chart_sent_metrics =
chart_lost_metrics =
chart_transmission_successes =
chart_transmission_failures =
chart_data_lost_events =
chart_lost_bytes =
chart_backend_reconnects =
chart_backend_latency = 0;
if(unlikely(netdata_exit)) break;
//fprintf(stderr, "\nBACKEND BEGIN:\n%s\nBACKEND END\n", buffer_tostring(b)); // FIXME
//fprintf(stderr, "after = %lu, before = %lu\n", after, before);
// prepare for the next iteration
// to add incrementally data to buffer
after = before;
// ------------------------------------------------------------------------
// if we are connected, receive a response, without blocking
if(likely(sock != -1)) {
errno = 0;
// loop through to collect all data
while(sock != -1 && errno != EWOULDBLOCK) {
buffer_need_bytes(response, 4096);
ssize_t r = recv(sock, &response->buffer[response->len], response->size - response->len, MSG_DONTWAIT);
if(likely(r > 0)) {
// we received some data
response->len += r;
chart_received_bytes += r;
chart_receptions++;
}
else if(r == 0) {
error("BACKEND: '%s' closed the socket", destination);
close(sock);
sock = -1;
}
else {
// failed to receive data
if(errno != EAGAIN && errno != EWOULDBLOCK) {
error("BACKEND: cannot receive data from backend '%s'.", destination);
}
}
}
// if we received data, process them
if(buffer_strlen(response))
backend_response_checker(response);
}
// ------------------------------------------------------------------------
// if we are not connected, connect to a backend server
if(unlikely(sock == -1)) {
usec_t start_ut = now_monotonic_usec();
size_t reconnects = 0;
sock = connect_to_one_of(destination, default_port, &timeout, &reconnects, NULL, 0);
chart_backend_reconnects += reconnects;
chart_backend_latency += now_monotonic_usec() - start_ut;
}
if(unlikely(netdata_exit)) break;
// ------------------------------------------------------------------------
// if we are connected, send our buffer to the backend server
if(likely(sock != -1)) {
size_t len = buffer_strlen(b);
usec_t start_ut = now_monotonic_usec();
int flags = 0;
#ifdef MSG_NOSIGNAL
flags += MSG_NOSIGNAL;
#endif
ssize_t written = send(sock, buffer_tostring(b), len, flags);
chart_backend_latency += now_monotonic_usec() - start_ut;
if(written != -1 && (size_t)written == len) {
// we sent the data successfully
chart_transmission_successes++;
chart_sent_bytes += written;
chart_sent_metrics = chart_buffered_metrics;
// reset the failures count
failures = 0;
// empty the buffer
buffer_flush(b);
}
else {
// oops! we couldn't send (all or some of the) data
error("BACKEND: failed to write data to database backend '%s'. Willing to write %zu bytes, wrote %zd bytes. Will re-connect.", destination, len, written);
chart_transmission_failures++;
if(written != -1)
chart_sent_bytes += written;
// increment the counter we check for data loss
failures++;
// close the socket - we will re-open it next time
close(sock);
sock = -1;
}
}
else {
error("BACKEND: failed to update database backend '%s'", destination);
chart_transmission_failures++;
// increment the counter we check for data loss
failures++;
}
if(failures > buffer_on_failures) {
// too bad! we are going to lose data
chart_lost_bytes += buffer_strlen(b);
error("BACKEND: reached %d backend failures. Flushing buffers to protect this host - this results in data loss on back-end server '%s'", failures, destination);
buffer_flush(b);
failures = 0;
chart_data_lost_events++;
chart_lost_metrics = chart_buffered_metrics;
}
if(unlikely(netdata_exit)) break;
// ------------------------------------------------------------------------
// update the monitoring charts
if(likely(chart_ops->counter_done)) rrdset_next(chart_ops);
rrddim_set(chart_ops, "read", chart_receptions);
rrddim_set(chart_ops, "write", chart_transmission_successes);
rrddim_set(chart_ops, "discard", chart_data_lost_events);
rrddim_set(chart_ops, "failure", chart_transmission_failures);
rrddim_set(chart_ops, "reconnect", chart_backend_reconnects);
rrdset_done(chart_ops);
if(likely(chart_metrics->counter_done)) rrdset_next(chart_metrics);
rrddim_set(chart_metrics, "buffered", chart_buffered_metrics);
rrddim_set(chart_metrics, "lost", chart_lost_metrics);
rrddim_set(chart_metrics, "sent", chart_sent_metrics);
rrdset_done(chart_metrics);
if(likely(chart_bytes->counter_done)) rrdset_next(chart_bytes);
rrddim_set(chart_bytes, "buffered", chart_buffered_bytes);
rrddim_set(chart_bytes, "lost", chart_lost_bytes);
rrddim_set(chart_bytes, "sent", chart_sent_bytes);
rrddim_set(chart_bytes, "received", chart_received_bytes);
rrdset_done(chart_bytes);
/*
if(likely(chart_latency->counter_done)) rrdset_next(chart_latency);
rrddim_set(chart_latency, "latency", chart_backend_latency);
rrdset_done(chart_latency);
*/
getrusage(RUSAGE_THREAD, &thread);
if(likely(chart_rusage->counter_done)) rrdset_next(chart_rusage);
rrddim_set(chart_rusage, "user", thread.ru_utime.tv_sec * 1000000ULL + thread.ru_utime.tv_usec);
rrddim_set(chart_rusage, "system", thread.ru_stime.tv_sec * 1000000ULL + thread.ru_stime.tv_usec);
rrdset_done(chart_rusage);
if(likely(buffer_strlen(b) == 0))
chart_buffered_metrics = 0;
if(unlikely(netdata_exit)) break;
}
cleanup:
if(sock != -1)
close(sock);
buffer_free(b);
buffer_free(response);
netdata_thread_cleanup_pop(1);
return NULL;
}
void charts2json(RRDHOST *host, BUFFER *wb) {
static char *custom_dashboard_info_js_filename = NULL;
size_t c, dimensions = 0, memory = 0, alarms = 0;
RRDSET *st;
time_t now = now_realtime_sec();
if(unlikely(!custom_dashboard_info_js_filename))
custom_dashboard_info_js_filename = config_get(CONFIG_SECTION_WEB, "custom dashboard_info.js", "");
buffer_sprintf(wb, "{\n"
"\t\"hostname\": \"%s\""
",\n\t\"version\": \"%s\""
",\n\t\"os\": \"%s\""
",\n\t\"timezone\": \"%s\""
",\n\t\"update_every\": %d"
",\n\t\"history\": %ld"
",\n\t\"custom_info\": \"%s\""
",\n\t\"charts\": {"
, host->hostname
, host->program_version
, host->os
, host->timezone
, host->rrd_update_every
, host->rrd_history_entries
, custom_dashboard_info_js_filename
);
c = 0;
rrdhost_rdlock(host);
rrdset_foreach_read(st, host) {
if(rrdset_is_available_for_viewers(st)) {
if(c) buffer_strcat(wb, ",");
buffer_strcat(wb, "\n\t\t\"");
buffer_strcat(wb, st->id);
buffer_strcat(wb, "\": ");
rrdset2json(st, wb, &dimensions, &memory);
c++;
st->last_accessed_time = now;
}
}
RRDCALC *rc;
for(rc = host->alarms; rc ; rc = rc->next) {
if(rc->rrdset)
alarms++;
}
rrdhost_unlock(host);
buffer_sprintf(wb
, "\n\t}"
",\n\t\"charts_count\": %zu"
",\n\t\"dimensions_count\": %zu"
",\n\t\"alarms_count\": %zu"
",\n\t\"rrd_memory_bytes\": %zu"
",\n\t\"hosts_count\": %zu"
",\n\t\"hosts\": ["
, c
, dimensions
, alarms
, memory
, rrd_hosts_available
);
if(unlikely(rrd_hosts_available > 1)) {
rrd_rdlock();
size_t found = 0;
RRDHOST *h;
rrdhost_foreach_read(h) {
if(!rrdhost_should_be_removed(h, host, now)) {
buffer_sprintf(wb
, "%s\n\t\t{"
"\n\t\t\t\"hostname\": \"%s\""
"\n\t\t}"
, (found > 0) ? "," : ""
, h->hostname
);
found++;
}
}
rrd_unlock();
}