mirror of
https://github.com/rustfs/rustfs.git
synced 2026-09-04 03:05:39 +00:00
feat(obs): add bounded metrics dimensions (#5645)
* feat(obs): add drive topology detail metrics Expose additive drive info, topology, state, and per-drive API metrics while preserving the existing drive metric label sets. Backlog: rustfs/backlog#1655 Co-Authored-By: heihutu <heihutu@gmail.com> * fix(obs): preserve suspect drive runtime state Keep suspect as a bounded drive runtime state and avoid all-zero runtime_state samples for that storage health state. Co-Authored-By: heihutu <heihutu@gmail.com> * fix(obs): skip unknown drive inode samples Avoid exporting zero inode gauges for missing or stale drive snapshots and ignore zero-count API latency buckets. Co-Authored-By: heihutu <heihutu@gmail.com> * feat(obs): add scanner source work detail metrics Expose additive scanner source and cycle work metrics with bounded server/source/state labels while leaving the existing aggregate scanner metrics unchanged. Co-Authored-By: heihutu <heihutu@gmail.com> * feat(obs): add ilm action detail metrics Expose additive ILM action/state task metrics with a server label while preserving the existing aggregate ILM series. Co-Authored-By: heihutu <heihutu@gmail.com> * feat(obs): add delivery target server metrics Expose additive audit and notification delivery target metrics with server labels and extend removed-target tombstones for the server-aware series. Co-Authored-By: heihutu <heihutu@gmail.com> * feat(obs): add replication target flow metrics Expose additive bucket replication target sent and failed-flow metrics while preserving existing bucket aggregates and target backlog series. Co-Authored-By: heihutu <heihutu@gmail.com> * feat(obs): add request server metrics Expose additive API request metrics with server labels while preserving the existing request and traffic metric label sets. Co-Authored-By: heihutu <heihutu@gmail.com> * style(obs): apply rustfmt to metrics changes Apply rustfmt output to the metrics dimension changes without altering behavior. Co-Authored-By: heihutu <heihutu@gmail.com> * style(obs): reuse audit target label constant Use the exported audit target_id label constant for legacy audit target metrics. Co-Authored-By: heihutu <heihutu@gmail.com> * feat(obs): populate drive disk metrics Co-Authored-By: heihutu <heihutu@gmail.com> * feat(obs): add scanner bucket drive result metrics Co-Authored-By: heihutu <heihutu@gmail.com> * feat(obs): add replication proxy server metrics Co-Authored-By: heihutu <heihutu@gmail.com> * fix(obs): address metric liveness review Use checked division for drive API latency aggregation and keep recovered drive, scanner current-cycle, replication flow, audit target, and notification target series from retaining stale values. Co-Authored-By: heihutu <heihutu@gmail.com> * fix(obs): address metric dimension review Co-Authored-By: heihutu <heihutu@gmail.com> * fix(obs): address additional metric review Co-Authored-By: heihutu <heihutu@gmail.com> * fix(obs): count drive calls at start Co-Authored-By: heihutu <heihutu@gmail.com> * fix(obs): address metrics dimension review Co-Authored-By: heihutu <heihutu@gmail.com> * fix(metrics): address dimension review gaps Co-Authored-By: heihutu <heihutu@gmail.com> * fix(metrics): address scanner review follow-ups Co-Authored-By: heihutu <heihutu@gmail.com> * fix(metrics): address runtime review follow-ups Co-Authored-By: heihutu <heihutu@gmail.com> * fix(metrics): reduce disk metric contention Co-Authored-By: heihutu <heihutu@gmail.com> * fix(metrics): address runtime review follow-ups Co-Authored-By: heihutu <heihutu@gmail.com> * fix(metrics): retire stale dimension series Co-Authored-By: heihutu <heihutu@gmail.com> --------- Co-authored-by: heihutu <heihutu@gmail.com>
This commit is contained in:
houseme
@@ -17,18 +17,31 @@
|
||||
use crate::{MetricDescriptor, MetricName, new_gauge_md, subsystems};
|
||||
use std::sync::LazyLock;
|
||||
|
||||
const TARGET_ID: &str = "target_id";
|
||||
pub const TARGET_ID: &str = "target_id";
|
||||
pub const SERVER: &str = "server";
|
||||
pub const RESULT: &str = "result"; // success / failure
|
||||
pub const STATUS: &str = "status"; // success / failure
|
||||
|
||||
pub const SUCCESS: &str = "success";
|
||||
pub const FAILURE: &str = "failure";
|
||||
|
||||
const TARGET_LABELS: [&str; 1] = [TARGET_ID];
|
||||
const TARGET_SERVER_LABELS: [&str; 2] = [SERVER, TARGET_ID];
|
||||
|
||||
pub static AUDIT_FAILED_MESSAGES_MD: LazyLock<MetricDescriptor> = LazyLock::new(|| {
|
||||
new_gauge_md(
|
||||
MetricName::AuditFailedMessages,
|
||||
"Total number of messages that failed to send since start",
|
||||
&[TARGET_ID],
|
||||
&TARGET_LABELS,
|
||||
subsystems::AUDIT,
|
||||
)
|
||||
});
|
||||
|
||||
pub static AUDIT_FAILED_MESSAGES_BY_SERVER_MD: LazyLock<MetricDescriptor> = LazyLock::new(|| {
|
||||
new_gauge_md(
|
||||
MetricName::Custom("failed_messages_by_server".to_string()),
|
||||
"Total number of messages that failed to send since start by server and target",
|
||||
&TARGET_SERVER_LABELS,
|
||||
subsystems::AUDIT,
|
||||
)
|
||||
});
|
||||
@@ -37,7 +50,16 @@ pub static AUDIT_FAILED_STORE_LENGTH_MD: LazyLock<MetricDescriptor> = LazyLock::
|
||||
new_gauge_md(
|
||||
MetricName::AuditFailedStoreLength,
|
||||
"Number of audit messages held in the failed-events store for target",
|
||||
&[TARGET_ID],
|
||||
&TARGET_LABELS,
|
||||
subsystems::AUDIT,
|
||||
)
|
||||
});
|
||||
|
||||
pub static AUDIT_FAILED_STORE_LENGTH_BY_SERVER_MD: LazyLock<MetricDescriptor> = LazyLock::new(|| {
|
||||
new_gauge_md(
|
||||
MetricName::Custom("failed_store_length_by_server".to_string()),
|
||||
"Number of audit messages held in the failed-events store by server and target",
|
||||
&TARGET_SERVER_LABELS,
|
||||
subsystems::AUDIT,
|
||||
)
|
||||
});
|
||||
@@ -46,7 +68,16 @@ pub static AUDIT_TARGET_QUEUE_LENGTH_MD: LazyLock<MetricDescriptor> = LazyLock::
|
||||
new_gauge_md(
|
||||
MetricName::AuditTargetQueueLength,
|
||||
"Number of unsent messages in queue for target",
|
||||
&[TARGET_ID],
|
||||
&TARGET_LABELS,
|
||||
subsystems::AUDIT,
|
||||
)
|
||||
});
|
||||
|
||||
pub static AUDIT_TARGET_QUEUE_LENGTH_BY_SERVER_MD: LazyLock<MetricDescriptor> = LazyLock::new(|| {
|
||||
new_gauge_md(
|
||||
MetricName::Custom("target_queue_length_by_server".to_string()),
|
||||
"Number of unsent audit messages in queue by server and target",
|
||||
&TARGET_SERVER_LABELS,
|
||||
subsystems::AUDIT,
|
||||
)
|
||||
});
|
||||
@@ -55,7 +86,16 @@ pub static AUDIT_TOTAL_MESSAGES_MD: LazyLock<MetricDescriptor> = LazyLock::new(|
|
||||
new_gauge_md(
|
||||
MetricName::AuditTotalMessages,
|
||||
"Total number of messages sent since start",
|
||||
&[TARGET_ID],
|
||||
&TARGET_LABELS,
|
||||
subsystems::AUDIT,
|
||||
)
|
||||
});
|
||||
|
||||
pub static AUDIT_TOTAL_MESSAGES_BY_SERVER_MD: LazyLock<MetricDescriptor> = LazyLock::new(|| {
|
||||
new_gauge_md(
|
||||
MetricName::Custom("total_messages_by_server".to_string()),
|
||||
"Total number of messages sent since start by server and target",
|
||||
&TARGET_SERVER_LABELS,
|
||||
subsystems::AUDIT,
|
||||
)
|
||||
});
|
||||
|
||||
Reference in New Issue
Block a user