diff options
Diffstat (limited to 'src/daemon/config')
| -rw-r--r-- | src/daemon/config/README.md | 66 | ||||
| -rw-r--r-- | src/daemon/config/dyncfg-echo.c | 6 | ||||
| -rw-r--r-- | src/daemon/config/dyncfg-intercept.c | 2 | ||||
| -rw-r--r-- | src/daemon/config/dyncfg-tree.c | 12 | ||||
| -rw-r--r-- | src/daemon/config/dyncfg-unittest.c | 6 | ||||
| -rw-r--r-- | src/daemon/config/dyncfg.c | 3 | ||||
| -rw-r--r-- | src/daemon/config/dyncfg.h | 2 |
7 files changed, 43 insertions, 54 deletions
diff --git a/src/daemon/config/README.md b/src/daemon/config/README.md index 3c0912fba..7217ec4ea 100644 --- a/src/daemon/config/README.md +++ b/src/daemon/config/README.md @@ -1,13 +1,3 @@ -<!-- -title: "Daemon configuration" -description: "The Netdata Agent's daemon is installed preconfigured to collect thousands of metrics every second, but is highly configurable for real-world workloads." -custom_edit_url: "https://github.com/netdata/netdata/edit/master/src/daemon/config/README.md" -sidebar_label: "Daemon" -learn_status: "Published" -learn_rel_path: "Configuration" -learn_doc_purpose: "Explain the daemon options, the log files, the process scheduling, virtual memory, explain how the netdata.conf is used and backlink to the netdata.conf file reference" ---> - # Daemon configuration <details> @@ -53,7 +43,7 @@ comment on settings it does not currently use. ## Applying changes -After `netdata.conf` has been modified, Netdata needs to be [restarted](/packaging/installer/README.md#maintaining-a-netdata-agent-installation) for +After `netdata.conf` has been modified, Netdata needs to be [restarted](/docs/netdata-agent/start-stop-restart.md) for changes to apply: ```bash @@ -86,24 +76,22 @@ Please note that your data history will be lost if you have modified `history` p ### [db] section options -| setting | default | info | -|:---------------------------------------------:|:----------:|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| -| mode | `dbengine` | `dbengine`: The default for long-term metrics storage with efficient RAM and disk usage. Can be extended with `dbengine page cache size MB` and `dbengine disk space MB`. <br />`ram`: The round-robin database will be temporary and it will be lost when Netdata exits. <br />`alloc`: Similar to `ram`, but can significantly reduce memory usage, when combined with a low retention and does not support KSM. <br />`none`: Disables the database at this host, and disables health monitoring entirely, as that requires a database of metrics. Not to be used together with streaming. | -| retention | `3600` | Used with `mode = ram/alloc`, not the default `mode = dbengine`. This number reflects the number of entries the `netdata` daemon will by default keep in memory for each chart dimension. Check [Memory Requirements](/src/database/README.md) for more information. | -| storage tiers | `3` | The number of storage tiers you want to have in your dbengine. Check the tiering mechanism in the [dbengine's reference](/src/database/engine/README.md#tiering). You can have up to 5 tiers of data (including the _Tier 0_). This number ranges between 1 and 5. | -| dbengine page cache size MB | `32` | Determines the amount of RAM in MiB that is dedicated to caching for _Tier 0_ Netdata metric values. | -| dbengine tier **`N`** page cache size MB | `32` | Determines the amount of RAM in MiB that is dedicated for caching Netdata metric values of the **`N`** tier. <br /> `N belongs to [1..4]` | -| dbengine disk space MB | `256` | Determines the amount of disk space in MiB that is dedicated to storing _Tier 0_ Netdata metric values and all related metadata describing them. This option is available **only for legacy configuration** (`Agent v1.23.2 and prior`). | -| dbengine multihost disk space MB | `256` | Same functionality as `dbengine disk space MB`, but includes support for storing metrics streamed to a parent node by its children. Can be used in single-node environments as well. This setting is only for _Tier 0_ metrics. | -| dbengine tier **`N`** multihost disk space MB | `256` | Same functionality as `dbengine multihost disk space MB`, but stores metrics of the **`N`** tier (both parent node and its children). Can be used in single-node environments as well. <br /> `N belongs to [1..4]` | -| update every | `1` | The frequency in seconds, for data collection. For more information see the [performance guide](/docs/netdata-agent/configuration/optimize-the-netdata-agents-performance.md). These metrics stored as _Tier 0_ data. Explore the tiering mechanism in the [dbengine's reference](/src/database/engine/README.md#tiering). | -| dbengine tier **`N`** update every iterations | `60` | The down sampling value of each tier from the previous one. For each Tier, the greater by one Tier has N (equal to 60 by default) less data points of any metric it collects. This setting can take values from `2` up to `255`. <br /> `N belongs to [1..4]` | -| dbengine tier **`N`** back fill | `New` | Specifies the strategy of recreating missing data on each Tier from the exact lower Tier. <br /> `New`: Sees the latest point on each Tier and save new points to it only if the exact lower Tier has available points for it's observation window (`dbengine tier N update every iterations` window). <br /> `none`: No back filling is applied. <br /> `N belongs to [1..4]` | -| memory deduplication (ksm) | `yes` | When set to `yes`, Netdata will offer its in-memory round robin database and the dbengine page cache to kernel same page merging (KSM) for deduplication. For more information check [Memory Deduplication - Kernel Same Page Merging - KSM](/src/database/README.md#ksm) | -| cleanup obsolete charts after secs | `3600` | See [monitoring ephemeral containers](/src/collectors/cgroups.plugin/README.md#monitoring-ephemeral-containers), also sets the timeout for cleaning up obsolete dimensions | -| gap when lost iterations above | `1` | | -| cleanup orphan hosts after secs | `3600` | How long to wait until automatically removing from the DB a remote Netdata host (child) that is no longer sending data. | -| enable zero metrics | `no` | Set to `yes` to show charts when all their metrics are zero. | +| setting | default | info | +|:---------------------------------------------:|:-------------------------------:|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| +| mode | `dbengine` | `dbengine`: The default for long-term metrics storage with efficient RAM and disk usage. Can be extended with `dbengine page cache size` and `dbengine tier X retention size`. <br />`ram`: The round-robin database will be temporary and it will be lost when Netdata exits. <br />`alloc`: Similar to `ram`, but can significantly reduce memory usage, when combined with a low retention and does not support KSM. <br />`none`: Disables the database at this host, and disables health monitoring entirely, as that requires a database of metrics. Not to be used together with streaming. | +| retention | `3600` | Used with `mode = ram/alloc`, not the default `mode = dbengine`. This number reflects the number of entries the `netdata` daemon will by default keep in memory for each chart dimension. Check [Memory Requirements](/src/database/README.md) for more information. | +| storage tiers | `3` | The number of storage tiers you want to have in your dbengine. Check the tiering mechanism in the [dbengine's reference](/src/database/engine/README.md#tiering). You can have up to 5 tiers of data (including the _Tier 0_). This number ranges between 1 and 5. | +| dbengine page cache size | `32MiB` | Determines the amount of RAM in MiB that is dedicated to caching for _Tier 0_ Netdata metric values. | +| dbengine tier **`N`** retention size | `1GiB` | The disk space dedicated to metrics storage, per tier. Can be used in single-node environments as well. <br /> `N belongs to [1..4]` | +| dbengine tier **`N`** retention time | `14d`, `3mo`, `1y`, `1y`, `1y` | The database retention, expressed in time. Can be used in single-node environments as well. <br /> `N belongs to [1..4]` | +| update every | `1` | The frequency in seconds, for data collection. For more information see the [performance guide](/docs/netdata-agent/configuration/optimize-the-netdata-agents-performance.md). These metrics stored as _Tier 0_ data. Explore the tiering mechanism in the [dbengine's reference](/src/database/engine/README.md#tiering). | +| dbengine tier **`N`** update every iterations | `60` | The down sampling value of each tier from the previous one. For each Tier, the greater by one Tier has N (equal to 60 by default) less data points of any metric it collects. This setting can take values from `2` up to `255`. <br /> `N belongs to [1..4]` | +| dbengine tier back fill | `new` | Specifies the strategy of recreating missing data on higher database Tiers.<br /> `new`: Sees the latest point on each Tier and save new points to it only if the exact lower Tier has available points for it's observation window (`dbengine tier N update every iterations` window). <br /> `none`: No back filling is applied. <br /> `N belongs to [1..4]` | +| memory deduplication (ksm) | `yes` | When set to `yes`, Netdata will offer its in-memory round robin database and the dbengine page cache to kernel same page merging (KSM) for deduplication. For more information check [Memory Deduplication - Kernel Same Page Merging - KSM](/src/database/README.md#ksm) | +| cleanup obsolete charts after | `1h` | See [monitoring ephemeral containers](/src/collectors/cgroups.plugin/README.md#monitoring-ephemeral-containers), also sets the timeout for cleaning up obsolete dimensions | +| gap when lost iterations above | `1` | | +| cleanup orphan hosts after | `1h` | How long to wait until automatically removing from the DB a remote Netdata host (child) that is no longer sending data. | +| enable zero metrics | `no` | Set to `yes` to show charts when all their metrics are zero. | > ### Info > @@ -140,7 +128,7 @@ There are additional configuration options for the logs. For more info, see [Net | health | `journal` | The filename to save the log of Netdata health collectors. You can also set it to `syslog` to send the access log to syslog, or `off` to disable this log. Defaults to `Journal` if using systemd. | | daemon | `journal` | The filename to save the log of Netdata daemon. You can also set it to `syslog` to send the access log to syslog, or `off` to disable this log. Defaults to `Journal` if using systemd. | | facility | `daemon` | A facility keyword is used to specify the type of system that is logging the message. | -| logs flood protection period | `60` | Length of period (in sec) during which the number of errors should not exceed the `errors to trigger flood protection`. | +| logs flood protection period | `1m` | Length of period during which the number of errors should not exceed the `errors to trigger flood protection`. | | logs to trigger flood protection | `1000` | Number of errors written to the log in `errors flood protection period` sec before flood protection is activated. | | level | `info` | Controls which log messages are logged, with error being the most important. Supported values: `info` and `error`. | @@ -172,15 +160,15 @@ monitoring](/src/health/README.md). [Alert notifications](/src/health/notifications/README.md) are configured in `health_alarm_notify.conf`. -| setting | default | info | -|:----------------------------------------------:|:------------------------------------------------:|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| -| enabled | `yes` | Set to `no` to disable all alerts and notifications | -| in memory max health log entries | 1000 | Size of the alert history held in RAM | -| script to execute on alarm | `/usr/libexec/netdata/plugins.d/alarm-notify.sh` | The script that sends alert notifications. Note that in versions before 1.16, the plugins.d directory may be installed in a different location in certain OSs (e.g. under `/usr/lib/netdata`). | -| run at least every seconds | `10` | Controls how often all alert conditions should be evaluated. | -| postpone alarms during hibernation for seconds | `60` | Prevents false alerts. May need to be increased if you get alerts during hibernation. | -| health log history | `432000` | Specifies the history of alert events (in seconds) kept in the agent's sqlite database. | -| enabled alarms | * | Defines which alerts to load from both user and stock directories. This is a [simple pattern](/src/libnetdata/simple_pattern/README.md) list of alert or template names. Can be used to disable specific alerts. For example, `enabled alarms = !oom_kill *` will load all alerts except `oom_kill`. | +| setting | default | info | +|:--------------------------------------:|:------------------------------------------------:|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| +| enabled | `yes` | Set to `no` to disable all alerts and notifications | +| in memory max health log entries | 1000 | Size of the alert history held in RAM | +| script to execute on alarm | `/usr/libexec/netdata/plugins.d/alarm-notify.sh` | The script that sends alert notifications. Note that in versions before 1.16, the plugins.d directory may be installed in a different location in certain OSs (e.g. under `/usr/lib/netdata`). | +| run at least every | `10s` | Controls how often all alert conditions should be evaluated. | +| postpone alarms during hibernation for | `1m` | Prevents false alerts. May need to be increased if you get alerts during hibernation. | +| health log retention | `5d` | Specifies the history of alert events (in seconds) kept in the agent's sqlite database. | +| enabled alarms | * | Defines which alerts to load from both user and stock directories. This is a [simple pattern](/src/libnetdata/simple_pattern/README.md) list of alert or template names. Can be used to disable specific alerts. For example, `enabled alarms = !oom_kill *` will load all alerts except `oom_kill`. | ### [web] section options diff --git a/src/daemon/config/dyncfg-echo.c b/src/daemon/config/dyncfg-echo.c index 95d40a025..f6eb48c35 100644 --- a/src/daemon/config/dyncfg-echo.c +++ b/src/daemon/config/dyncfg-echo.c @@ -96,7 +96,7 @@ void dyncfg_echo(const DICTIONARY_ITEM *item, DYNCFG *df, const char *id __maybe dyncfg_echo_cb, e, NULL, NULL, NULL, NULL, - NULL, string2str(df->dyncfg.source)); + NULL, string2str(df->dyncfg.source), false); } // ---------------------------------------------------------------------------- @@ -129,7 +129,7 @@ void dyncfg_echo_update(const DICTIONARY_ITEM *item, DYNCFG *df, const char *id) dyncfg_echo_cb, e, NULL, NULL, NULL, NULL, - df->dyncfg.payload, string2str(df->dyncfg.source)); + df->dyncfg.payload, string2str(df->dyncfg.source), false); } // ---------------------------------------------------------------------------- @@ -164,7 +164,7 @@ static void dyncfg_echo_payload_add(const DICTIONARY_ITEM *item_template __maybe dyncfg_echo_cb, e, NULL, NULL, NULL, NULL, - df_job->dyncfg.payload, string2str(df_job->dyncfg.source)); + df_job->dyncfg.payload, string2str(df_job->dyncfg.source), false); } void dyncfg_echo_add(const DICTIONARY_ITEM *item_template, const DICTIONARY_ITEM *item_job, DYNCFG *df_template, DYNCFG *df_job, const char *template_id, const char *job_name) { diff --git a/src/daemon/config/dyncfg-intercept.c b/src/daemon/config/dyncfg-intercept.c index 65f8383ed..b302d72aa 100644 --- a/src/daemon/config/dyncfg-intercept.c +++ b/src/daemon/config/dyncfg-intercept.c @@ -216,7 +216,7 @@ int dyncfg_function_intercept_cb(struct rrd_function_execute *rfe, void *data __ memcpy(buf, rfe->function, sizeof(buf)); char *words[20]; - size_t num_words = quoted_strings_splitter_pluginsd(buf, words, 20); + size_t num_words = quoted_strings_splitter_whitespace(buf, words, 20); size_t i = 0; char *config = get_word(words, num_words, i++); diff --git a/src/daemon/config/dyncfg-tree.c b/src/daemon/config/dyncfg-tree.c index 77d031fa0..4bad2f30f 100644 --- a/src/daemon/config/dyncfg-tree.c +++ b/src/daemon/config/dyncfg-tree.c @@ -71,12 +71,10 @@ static void dyncfg_tree_for_host(RRDHOST *host, BUFFER *wb, const char *path, co if(id && *id) template = string_strdupz(id); - ND_UUID host_uuid = uuid2UUID(host->host_uuid); - size_t path_len = strlen(path); DYNCFG *df; dfe_start_read(dyncfg_globals.nodes, df) { - if(!UUIDeq(df->host_uuid, host_uuid)) + if(!UUIDeq(df->host_uuid, host->host_id)) continue; if(strncmp(string2str(df->path), path, path_len) != 0) @@ -162,7 +160,7 @@ static int dyncfg_config_execute_cb(struct rrd_function_execute *rfe, void *data memcpy(buf, rfe->function, sizeof(buf)); char *words[MAX_FUNCTION_PARAMETERS]; // an array of pointers for the words in this line - size_t num_words = quoted_strings_splitter_pluginsd(buf, words, MAX_FUNCTION_PARAMETERS); + size_t num_words = quoted_strings_splitter_whitespace(buf, words, MAX_FUNCTION_PARAMETERS); const char *config = get_word(words, num_words, 0); const char *action = get_word(words, num_words, 1); @@ -266,7 +264,7 @@ static int dyncfg_config_execute_cb(struct rrd_function_execute *rfe, void *data rrd_call_function_error( rfe->result.wb, - "unknown config id given", code); + "Unknown config id given.", code); } cleanup: @@ -286,7 +284,7 @@ void dyncfg_host_init(RRDHOST *host) { // This function needs to be async, although it is internal. // The reason is that it can call by itself another function that may or may not be internal (sync). - rrd_function_add(host, NULL, PLUGINSD_FUNCTION_CONFIG, 120, - 1000, "Dynamic configuration", "config", HTTP_ACCESS_ANONYMOUS_DATA, + rrd_function_add(host, NULL, PLUGINSD_FUNCTION_CONFIG, 120, 1000, DYNCFG_FUNCTIONS_VERSION, + "Dynamic configuration", "config", HTTP_ACCESS_ANONYMOUS_DATA, false, dyncfg_config_execute_cb, host); } diff --git a/src/daemon/config/dyncfg-unittest.c b/src/daemon/config/dyncfg-unittest.c index 775dc7cbd..763451501 100644 --- a/src/daemon/config/dyncfg-unittest.c +++ b/src/daemon/config/dyncfg-unittest.c @@ -195,7 +195,7 @@ static int dyncfg_unittest_execute_cb(struct rrd_function_execute *rfe, void *da memcpy(buf, rfe->function, sizeof(buf)); char *words[MAX_FUNCTION_PARAMETERS]; // an array of pointers for the words in this line - size_t num_words = quoted_strings_splitter_pluginsd(buf, words, MAX_FUNCTION_PARAMETERS); + size_t num_words = quoted_strings_splitter_whitespace(buf, words, MAX_FUNCTION_PARAMETERS); const char *config = get_word(words, num_words, 0); const char *id = get_word(words, num_words, 1); @@ -426,7 +426,7 @@ static int dyncfg_unittest_run(const char *cmd, BUFFER *wb, const char *payload, memcpy(buf, cmd, sizeof(buf)); char *words[MAX_FUNCTION_PARAMETERS]; // an array of pointers for the words in this line - size_t num_words = quoted_strings_splitter_pluginsd(buf, words, MAX_FUNCTION_PARAMETERS); + size_t num_words = quoted_strings_splitter_whitespace(buf, words, MAX_FUNCTION_PARAMETERS); // const char *config = get_word(words, num_words, 0); const char *id = get_word(words, num_words, 1); @@ -473,7 +473,7 @@ static int dyncfg_unittest_run(const char *cmd, BUFFER *wb, const char *payload, NULL, NULL, NULL, NULL, NULL, NULL, - pld, source); + pld, source, false); if(!DYNCFG_RESP_SUCCESS(rc)) { nd_log(NDLS_DAEMON, NDLP_ERR, "DYNCFG UNITTEST: failed to run: %s; returned code %d", cmd, rc); dyncfg_unittest_register_error(NULL, NULL); diff --git a/src/daemon/config/dyncfg.c b/src/daemon/config/dyncfg.c index 2f484d1ed..e6c1768cc 100644 --- a/src/daemon/config/dyncfg.c +++ b/src/daemon/config/dyncfg.c @@ -192,7 +192,7 @@ const DICTIONARY_ITEM *dyncfg_add_internal(RRDHOST *host, const char *id, const rrd_function_execute_cb_t execute_cb, void *execute_cb_data, bool overwrite_cb) { DYNCFG tmp = { - .host_uuid = uuid2UUID(host->host_uuid), + .host_uuid = host->host_id, .path = string_strdupz(path), .cmds = cmds, .type = type, @@ -358,6 +358,7 @@ bool dyncfg_add_low_level(RRDHOST *host, const char *id, const char *path, string2str(df->function), 120, 1000, + DYNCFG_FUNCTIONS_VERSION, "Dynamic configuration", "config", (view_access & edit_access), diff --git a/src/daemon/config/dyncfg.h b/src/daemon/config/dyncfg.h index 539eddbfb..84fab07d2 100644 --- a/src/daemon/config/dyncfg.h +++ b/src/daemon/config/dyncfg.h @@ -7,6 +7,8 @@ #include "database/rrd.h" #include "database/rrdfunctions.h" +#define DYNCFG_FUNCTIONS_VERSION 0 + void dyncfg_add_streaming(BUFFER *wb); bool dyncfg_available_for_rrdhost(RRDHOST *host); void dyncfg_host_init(RRDHOST *host); |