0
0
Fork 0
mirror of https://github.com/netdata/netdata.git synced 2025-05-10 11:50:55 +00:00
netdata_netdata/database/sqlite/sqlite_aclk_node.c
Costa Tsaousis 8fc3b351a2
Allow netdata plugins to expose functions for querying more information about specific charts ()
* function renames and code cleanup in popen.c; no actual code changes

* netdata popen() now opens both child process stdin and stdout and returns FILE * for both

* pass both input and output to parser structures

* updated rrdset to call custom functions

* RRDSET FUNCTION leading calls for both sync and async operation

* put RRDSET functions to a separate file

* added format and timeout at function definition

* support for synchronous (internal plugins) and asynchronous (external plugins and children) functions

* /api/v1/function endpoint

* functions are now attached to the host and there is a dictionary view per chart

* functions implemented at plugins.d

* remove the defer until keyword hook from plugins.d when it is done

* stream sender implementation of functions

* sanitization of all functions so that certain characters are only allowed

* strictier sanitization

* common max size

* 1st working plugins.d example

* always init inflight dictionary

* properly destroy dictionaries to avoid parallel insertion of items

* add more debugging on disconnection reasons

* add more debugging on disconnection reasons again

* streaming receiver respects newlines

* dont use the same fp for both streaming receive and send

* dont free dbengine memory with internal checks

* make sender proceed in the buffer

* added timing info and garbage collection at plugins.d

* added info about routing nodes

* added info about routing nodes with delay

* added more info about delays

* added more info about delays again

* signal sending thread to wake up

* streaming version labeling and commented code to support capabilities

* added functions to /api/v1/data, /api/v1/charts, /api/v1/chart, /api/v1/info

* redirect top output to stdout

* address coverity findings

* fix resource leaks of popen

* log attempts to connect to individual destinations

* better messages

* properly parse destinations

* try to find a function from the most matching to the least matching

* log added streaming destinations

* rotate destinations bypassing a node in the middle that does not accept our connection

* break the loops properly

* use typedef to define callbacks

* capabilities negotiation during streaming

* functions exposed upstream based on capabilities; compression disabled per node persisting reconnects; always try to connect with all capabilities

* restore functionality to lookup functions

* better logging of capabilities

* remove old versions from capabilities when a newer version is there

* fix formatting

* optimization for plugins.d rrdlabels to avoid creating and destructing dictionaries all the time

* delayed health initialization for rrddim and rrdset

* cleanup health initialization

* fix for popen() not returning the right value

* add health worker jobs for initializing rrdset and rrddim

* added content type support for functions; apps.plugin permanent function to display all the processes

* fixes for functions parameters parsing in apps.plugin

* fix for process matching in apps.plugiin

* first working function for apps.plugin

* Dashboard ACL is disabled for functions; Function errors are all in JSON format

* apps.plugin function processes returns json table

* use json_escape_string() to escape message

* fix formatting

* apps.plugin exposes all its metrics to function processes

* fix json formatting when filtering out some rows

* reopen the internal pipe of rrdpush in case of errors

* misplaced statement

* do not use buffer->len

* support for GLOBAL functions (functions that are not linked to a chart

* added /api/v1/functions endpoint; removed format from the FUNCTIONS api;

* swagger documentation about the new api end points

* added plugins.d documentation about functions

* never re-close a file

* remove uncessesary ifdef

* fixed issues identified by codacy

* fix for null label value

* make edit-config copy-and-paste friendly

* Revert "make edit-config copy-and-paste friendly"

This reverts commit 54500c0e0a.

* reworked sender handshake to fix coverity findings

* timeout is zero, for both send_timeout() and recv_timeout()

* properly detect that parent closed the socket

* support caching of function responses; limit function response to 10MB; added protection from malformed function responses

* disabled excessive logging

* added units to apps.plugin function processes and normalized all values to be human readable

* shorter field names

* fixed issues reported

* fixed apps.plugin error response; tested that pluginsd can properly handle faulty responses

* use double linked list macros for double linked list management

* faster apps.plugin function printing by minimizing file operations

* added memory percentage

* fix compatibility issues with older compilers and FreeBSD

* rrdpush sender code cleanup; rrhost structure cleanup from sender flags and variables;

* fix letftover variable in ifdef

* apps.plugin: do not call detach from the thread; exit immediately when input is broken

* exclude AR charts from health

* flush cleaner; prefer sender output

* clarity

* do not fill the cbuffer if not connected

* fix

* dont enabled host->sender if streaming is not enabled; send host label updates to parent;

* functions are only available through ACLK

* Prepared statement reports only in dev mode

* fix AR chart detection

* fix for streaming not being enabling itself

* more cleanup of sender and receiver structures

* moved read-only flags and configuration options to rrdhost->options

* fixed merge with master

* fix for incomplete rename

* prevent service thread from working on charts that are being collected

Co-authored-by: Stelios Fragkakis <52996999+stelfrag@users.noreply.github.com>
2022-10-05 14:13:46 +03:00

137 lines
5.3 KiB
C

// SPDX-License-Identifier: GPL-3.0-or-later
#include "sqlite_functions.h"
#include "sqlite_aclk_node.h"
#include "../../aclk/aclk_contexts_api.h"
#ifdef ENABLE_ACLK
DICTIONARY *collectors_from_charts(RRDHOST *host, DICTIONARY *dict) {
RRDSET *st;
char name[500];
rrdset_foreach_read(st, host) {
if (rrdset_is_available_for_viewers(st)) {
struct collector_info col = {
.plugin = rrdset_plugin_name(st),
.module = rrdset_module_name(st)
};
snprintfz(name, 499, "%s:%s", col.plugin, col.module);
dictionary_set(dict, name, &col, sizeof(struct collector_info));
}
}
rrdset_foreach_done(st);
return dict;
}
#endif
void sql_build_node_collectors(struct aclk_database_worker_config *wc)
{
#ifdef ENABLE_ACLK
if (!wc->host)
return;
struct update_node_collectors upd_node_collectors;
DICTIONARY *dict = dictionary_create(DICT_OPTION_SINGLE_THREADED);
upd_node_collectors.node_id = wc->node_id;
upd_node_collectors.claim_id = get_agent_claimid();
upd_node_collectors.node_collectors = collectors_from_charts(wc->host, dict);
aclk_update_node_collectors(&upd_node_collectors);
dictionary_destroy(dict);
freez(upd_node_collectors.claim_id);
log_access("ACLK RES [%s (%s)]: NODE COLLECTORS SENT", wc->node_id, rrdhost_hostname(wc->host));
#else
UNUSED(wc);
#endif
return;
}
void sql_build_node_info(struct aclk_database_worker_config *wc, struct aclk_database_cmd cmd)
{
UNUSED(cmd);
#ifdef ENABLE_ACLK
struct update_node_info node_info;
if (!wc->host) {
wc->node_info_send = 1;
return;
}
rrd_rdlock();
node_info.node_id = wc->node_id;
node_info.claim_id = get_agent_claimid();
node_info.machine_guid = wc->host_guid;
node_info.child = (wc->host != localhost);
node_info.ml_info.ml_capable = ml_capable(localhost);
node_info.ml_info.ml_enabled = ml_enabled(wc->host);
struct capability instance_caps[] = {
{ .name = "proto", .version = 1, .enabled = 1 },
{ .name = "ml", .version = ml_capable(localhost), .enabled = ml_enabled(wc->host) },
{ .name = "mc", .version = enable_metric_correlations ? metric_correlations_version : 0, .enabled = enable_metric_correlations },
{ .name = "ctx", .version = 1, .enabled = 1 },
{ .name = NULL, .version = 0, .enabled = 0 }
};
node_info.node_instance_capabilities = instance_caps;
now_realtime_timeval(&node_info.updated_at);
RRDHOST *host = wc->host;
char *host_version = NULL;
if (host != localhost) {
netdata_mutex_lock(&host->receiver_lock);
host_version = strdupz(host->receiver && host->receiver->program_version ? host->receiver->program_version : "unknown");
netdata_mutex_unlock(&host->receiver_lock);
}
node_info.data.name = rrdhost_hostname(host);
node_info.data.os = rrdhost_os(host);
node_info.data.os_name = host->system_info->host_os_name;
node_info.data.os_version = host->system_info->host_os_version;
node_info.data.kernel_name = host->system_info->kernel_name;
node_info.data.kernel_version = host->system_info->kernel_version;
node_info.data.architecture = host->system_info->architecture;
node_info.data.cpus = host->system_info->host_cores ? str2uint32_t(host->system_info->host_cores) : 0;
node_info.data.cpu_frequency = host->system_info->host_cpu_freq ? host->system_info->host_cpu_freq : "0";
node_info.data.memory = host->system_info->host_ram_total ? host->system_info->host_ram_total : "0";
node_info.data.disk_space = host->system_info->host_disk_space ? host->system_info->host_disk_space : "0";
node_info.data.version = host_version ? host_version : VERSION;
node_info.data.release_channel = get_release_channel();
node_info.data.timezone = rrdhost_abbrev_timezone(host);
node_info.data.virtualization_type = host->system_info->virtualization ? host->system_info->virtualization : "unknown";
node_info.data.container_type = host->system_info->container ? host->system_info->container : "unknown";
node_info.data.custom_info = config_get(CONFIG_SECTION_WEB, "custom dashboard_info.js", "");
node_info.data.machine_guid = wc->host_guid;
struct capability node_caps[] = {
{ .name = "ml", .version = host->system_info->ml_capable, .enabled = host->system_info->ml_enabled },
{ .name = "mc", .version = host->system_info->mc_version ? host->system_info->mc_version : 0, .enabled = host->system_info->mc_version ? 1 : 0 },
{ .name = NULL, .version = 0, .enabled = 0 }
};
node_info.node_capabilities = node_caps;
node_info.data.ml_info.ml_capable = host->system_info->ml_capable;
node_info.data.ml_info.ml_enabled = host->system_info->ml_enabled;
node_info.data.host_labels_ptr = host->rrdlabels;
aclk_update_node_info(&node_info);
log_access("ACLK RES [%s (%s)]: NODE INFO SENT for guid [%s] (%s)", wc->node_id, rrdhost_hostname(wc->host), wc->host_guid, wc->host == localhost ? "parent" : "child");
rrd_unlock();
freez(node_info.claim_id);
freez(host_version);
wc->node_collectors_send = now_realtime_sec();
#else
UNUSED(wc);
#endif
return;
}