0
0
Fork 0
mirror of https://github.com/netdata/netdata.git synced 2025-04-14 17:48:37 +00:00
netdata_netdata/exporting/aws_kinesis/aws_kinesis.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

219 lines
7.7 KiB
C

// SPDX-License-Identifier: GPL-3.0-or-later
#include "aws_kinesis.h"
/**
* Clean AWS Kinesis *
*/
void aws_kinesis_cleanup(struct instance *instance)
{
netdata_log_info("EXPORTING: cleaning up instance %s ...", instance->config.name);
kinesis_shutdown(instance->connector_specific_data);
freez(instance->connector_specific_data);
struct aws_kinesis_specific_config *connector_specific_config = instance->config.connector_specific_config;
if (connector_specific_config) {
freez(connector_specific_config->auth_key_id);
freez(connector_specific_config->secure_key);
freez(connector_specific_config->stream_name);
freez(connector_specific_config);
}
netdata_log_info("EXPORTING: instance %s exited", instance->config.name);
instance->exited = 1;
}
/**
* Initialize AWS Kinesis connector instance
*
* @param instance an instance data structure.
* @return Returns 0 on success, 1 on failure.
*/
int init_aws_kinesis_instance(struct instance *instance)
{
instance->worker = aws_kinesis_connector_worker;
instance->start_batch_formatting = NULL;
instance->start_host_formatting = format_host_labels_json_plaintext;
instance->start_chart_formatting = NULL;
if (EXPORTING_OPTIONS_DATA_SOURCE(instance->config.options) == EXPORTING_SOURCE_DATA_AS_COLLECTED)
instance->metric_formatting = format_dimension_collected_json_plaintext;
else
instance->metric_formatting = format_dimension_stored_json_plaintext;
instance->end_chart_formatting = NULL;
instance->variables_formatting = NULL;
instance->end_host_formatting = flush_host_labels;
instance->end_batch_formatting = NULL;
instance->prepare_header = NULL;
instance->check_response = NULL;
instance->buffer = (void *)buffer_create(0, &netdata_buffers_statistics.buffers_exporters);
if (!instance->buffer) {
netdata_log_error("EXPORTING: cannot create buffer for AWS Kinesis exporting connector instance %s",
instance->config.name);
return 1;
}
if (uv_mutex_init(&instance->mutex))
return 1;
if (uv_cond_init(&instance->cond_var))
return 1;
if (!instance->engine->aws_sdk_initialized) {
aws_sdk_init();
instance->engine->aws_sdk_initialized = 1;
}
struct aws_kinesis_specific_config *connector_specific_config = instance->config.connector_specific_config;
struct aws_kinesis_specific_data *connector_specific_data = callocz(1, sizeof(struct aws_kinesis_specific_data));
instance->connector_specific_data = (void *)connector_specific_data;
if (!strcmp(connector_specific_config->stream_name, "")) {
netdata_log_error("stream name is a mandatory Kinesis parameter but it is not configured");
return 1;
}
kinesis_init(
(void *)connector_specific_data,
instance->config.destination,
connector_specific_config->auth_key_id,
connector_specific_config->secure_key,
instance->config.timeoutms);
return 0;
}
/**
* AWS Kinesis connector worker
*
* Runs in a separate thread for every instance.
*
* @param instance_p an instance data structure.
*/
void aws_kinesis_connector_worker(void *instance_p)
{
struct instance *instance = (struct instance *)instance_p;
struct aws_kinesis_specific_config *connector_specific_config = instance->config.connector_specific_config;
struct aws_kinesis_specific_data *connector_specific_data = instance->connector_specific_data;
while (!instance->engine->exit) {
unsigned long long partition_key_seq = 0;
struct stats *stats = &instance->stats;
uv_mutex_lock(&instance->mutex);
while (!instance->data_is_ready)
uv_cond_wait(&instance->cond_var, &instance->mutex);
instance->data_is_ready = 0;
if (unlikely(instance->engine->exit)) {
uv_mutex_unlock(&instance->mutex);
break;
}
// reset the monitoring chart counters
stats->received_bytes =
stats->sent_bytes =
stats->sent_metrics =
stats->lost_metrics =
stats->receptions =
stats->transmission_successes =
stats->transmission_failures =
stats->data_lost_events =
stats->lost_bytes =
stats->reconnects = 0;
BUFFER *buffer = (BUFFER *)instance->buffer;
size_t buffer_len = buffer_strlen(buffer);
stats->buffered_bytes = buffer_len;
size_t sent = 0;
while (sent < buffer_len) {
char partition_key[KINESIS_PARTITION_KEY_MAX + 1];
snprintf(partition_key, KINESIS_PARTITION_KEY_MAX, "netdata_%llu", partition_key_seq++);
size_t partition_key_len = strnlen(partition_key, KINESIS_PARTITION_KEY_MAX);
const char *first_char = buffer_tostring(buffer) + sent;
size_t record_len = 0;
// split buffer into chunks of maximum allowed size
if (buffer_len - sent < KINESIS_RECORD_MAX - partition_key_len) {
record_len = buffer_len - sent;
} else {
record_len = KINESIS_RECORD_MAX - partition_key_len;
while (record_len && *(first_char + record_len - 1) != '\n')
record_len--;
}
char error_message[ERROR_LINE_MAX + 1] = "";
netdata_log_debug(D_EXPORTING,
"EXPORTING: kinesis_put_record(): dest = %s, id = %s, key = %s, stream = %s, partition_key = %s, "
"buffer = %zu, record = %zu",
instance->config.destination,
connector_specific_config->auth_key_id,
connector_specific_config->secure_key,
connector_specific_config->stream_name,
partition_key,
buffer_len,
record_len);
kinesis_put_record(
connector_specific_data, connector_specific_config->stream_name, partition_key, first_char, record_len);
sent += record_len;
stats->transmission_successes++;
size_t sent_bytes = 0, lost_bytes = 0;
if (unlikely(kinesis_get_result(
connector_specific_data->request_outcomes, error_message, &sent_bytes, &lost_bytes))) {
// oops! we couldn't send (all or some of the) data
netdata_log_error("EXPORTING: %s", error_message);
netdata_log_error("EXPORTING: failed to write data to external database '%s'. Willing to write %zu bytes, wrote %zu bytes.",
instance->config.destination,
sent_bytes,
sent_bytes - lost_bytes);
stats->transmission_failures++;
stats->data_lost_events++;
stats->lost_bytes += lost_bytes;
// estimate the number of lost metrics
stats->lost_metrics += (collected_number)(
stats->buffered_metrics *
(buffer_len && (lost_bytes > buffer_len) ? (double)lost_bytes / buffer_len : 1));
break;
} else {
stats->receptions++;
}
if (unlikely(instance->engine->exit))
break;
}
stats->sent_bytes += sent;
if (likely(sent == buffer_len))
stats->sent_metrics = stats->buffered_metrics;
buffer_flush(buffer);
send_internal_metrics(instance);
stats->buffered_metrics = 0;
uv_mutex_unlock(&instance->mutex);
#ifdef UNIT_TESTING
return;
#endif
}
aws_kinesis_cleanup(instance);
}