Пример #1
0
// destroy the cache and free all the memory it uses
void web_client_cache_destroy(void) {
#ifdef NETDATA_INTERNAL_CHECKS
    if(unlikely(web_clients_cache.pid != 0 && web_clients_cache.pid != gettid()))
        error("Oops! wrong thread accessing the cache. Expected %d, found %d", (int)web_clients_cache.pid, (int)gettid());

    web_client_cache_verify(1);
#endif

    netdata_thread_disable_cancelability();

    struct web_client *w, *t;

    w = web_clients_cache.used;
    while(w) {
        t = w;
        w = w->next;
        web_client_free(t);
    }
    web_clients_cache.used = NULL;
    web_clients_cache.used_count = 0;

    w = web_clients_cache.avail;
    while(w) {
        t = w;
        w = w->next;
        web_client_free(t);
    }
    web_clients_cache.avail = NULL;
    web_clients_cache.avail_count = 0;

    netdata_thread_enable_cancelability();
}
Пример #2
0
void web_client_release(struct web_client *w) {
#ifdef NETDATA_INTERNAL_CHECKS
    if(unlikely(web_clients_cache.pid != 0 && web_clients_cache.pid != gettid()))
        error("Oops! wrong thread accessing the cache. Expected %d, found %d", (int)web_clients_cache.pid, (int)gettid());

    if(unlikely(w->running))
        error("%llu: releasing web client from %s port %s, but it still running.", w->id, w->client_ip, w->client_port);
#endif

    debug(D_WEB_CLIENT_ACCESS, "%llu: Closing web client from %s port %s.", w->id, w->client_ip, w->client_port);

    web_server_log_connection(w, "DISCONNECTED");
    web_client_request_done(w);
    web_client_disconnected();

    netdata_thread_disable_cancelability();

    if(web_server_mode != WEB_SERVER_MODE_STATIC_THREADED) {
        if (w->ifd != -1) close(w->ifd);
        if (w->ofd != -1 && w->ofd != w->ifd) close(w->ofd);
        w->ifd = w->ofd = -1;
    }

    // unlink it from the used
    if (w == web_clients_cache.used) web_clients_cache.used = w->next;
    if(w->prev) w->prev->next = w->next;
    if(w->next) w->next->prev = w->prev;
    web_clients_cache.used_count--;

    if(web_clients_cache.avail_count >= 2 * web_clients_cache.used_count) {
        // we have too many of them - free it
        web_client_free(w);
    }
    else {
        // link it to the avail
        if (web_clients_cache.avail) web_clients_cache.avail->prev = w;
        w->next = web_clients_cache.avail;
        w->prev = NULL;
        web_clients_cache.avail = w;
        web_clients_cache.avail_count++;
    }

    netdata_thread_enable_cancelability();
}
Пример #3
0
struct web_client *web_client_get_from_cache_or_allocate() {

#ifdef NETDATA_INTERNAL_CHECKS
    if(unlikely(web_clients_cache.pid == 0))
        web_clients_cache.pid = gettid();

    if(unlikely(web_clients_cache.pid != 0 && web_clients_cache.pid != gettid()))
        error("Oops! wrong thread accessing the cache. Expected %d, found %d", (int)web_clients_cache.pid, (int)gettid());
#endif

    netdata_thread_disable_cancelability();

    struct web_client *w = web_clients_cache.avail;

    if(w) {
        // get it from avail
        if (w == web_clients_cache.avail) web_clients_cache.avail = w->next;
        if(w->prev) w->prev->next = w->next;
        if(w->next) w->next->prev = w->prev;
        web_clients_cache.avail_count--;
        web_client_zero(w);
        web_clients_cache.reused++;
    }
    else {
        // allocate it
        w = web_client_alloc();
        web_clients_cache.allocated++;
    }

    // link it to used web clients
    if (web_clients_cache.used) web_clients_cache.used->prev = w;
    w->next = web_clients_cache.used;
    w->prev = NULL;
    web_clients_cache.used = w;
    web_clients_cache.used_count++;

    // initialize it
    w->id = web_client_connected();
    w->mode = WEB_CLIENT_MODE_NORMAL;

    netdata_thread_enable_cancelability();

    return w;
}
Пример #4
0
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;
}