mirror of
https://github.com/rustfs/rustfs.git
synced 2026-09-04 19:25:40 +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
@@ -22,6 +22,15 @@ pub const NAME_LABEL: &str = "name";
|
||||
pub const TYPE_LABEL: &str = "type";
|
||||
/// le label (for histogram buckets)
|
||||
pub const LE_LABEL: &str = "le";
|
||||
/// server label
|
||||
pub const SERVER_LABEL: &str = "server";
|
||||
|
||||
const API_NAME_TYPE_LABELS: [&str; 2] = [NAME_LABEL, TYPE_LABEL];
|
||||
const API_SERVER_NAME_TYPE_LABELS: [&str; 3] = [SERVER_LABEL, NAME_LABEL, TYPE_LABEL];
|
||||
const API_NAME_TYPE_LE_LABELS: [&str; 3] = [NAME_LABEL, TYPE_LABEL, LE_LABEL];
|
||||
const API_SERVER_NAME_TYPE_LE_LABELS: [&str; 4] = [SERVER_LABEL, NAME_LABEL, TYPE_LABEL, LE_LABEL];
|
||||
const API_TYPE_LABELS: [&str; 1] = [TYPE_LABEL];
|
||||
const API_SERVER_TYPE_LABELS: [&str; 2] = [SERVER_LABEL, TYPE_LABEL];
|
||||
|
||||
pub static API_REJECTED_AUTH_TOTAL_MD: LazyLock<MetricDescriptor> = LazyLock::new(|| {
|
||||
new_counter_md(
|
||||
@@ -81,7 +90,16 @@ pub static API_REQUESTS_IN_FLIGHT_TOTAL_MD: LazyLock<MetricDescriptor> = LazyLoc
|
||||
new_gauge_md(
|
||||
MetricName::ApiRequestsInFlightTotal,
|
||||
"Total number of requests currently in flight",
|
||||
&["name", "type"],
|
||||
&API_NAME_TYPE_LABELS,
|
||||
MetricSubsystem::ApiRequests,
|
||||
)
|
||||
});
|
||||
|
||||
pub static API_REQUESTS_IN_FLIGHT_TOTAL_BY_SERVER_MD: LazyLock<MetricDescriptor> = LazyLock::new(|| {
|
||||
new_gauge_md(
|
||||
MetricName::Custom("requests_in_flight_total_by_server".to_string()),
|
||||
"Total number of requests currently in flight by server",
|
||||
&API_SERVER_NAME_TYPE_LABELS,
|
||||
MetricSubsystem::ApiRequests,
|
||||
)
|
||||
});
|
||||
@@ -90,7 +108,16 @@ pub static API_REQUESTS_TOTAL_MD: LazyLock<MetricDescriptor> = LazyLock::new(||
|
||||
new_counter_md(
|
||||
MetricName::ApiRequestsTotal,
|
||||
"Total number of requests",
|
||||
&["name", "type"],
|
||||
&API_NAME_TYPE_LABELS,
|
||||
MetricSubsystem::ApiRequests,
|
||||
)
|
||||
});
|
||||
|
||||
pub static API_REQUESTS_TOTAL_BY_SERVER_MD: LazyLock<MetricDescriptor> = LazyLock::new(|| {
|
||||
new_counter_md(
|
||||
MetricName::Custom("requests_total_by_server".to_string()),
|
||||
"Total number of requests by server",
|
||||
&API_SERVER_NAME_TYPE_LABELS,
|
||||
MetricSubsystem::ApiRequests,
|
||||
)
|
||||
});
|
||||
@@ -99,7 +126,16 @@ pub static API_REQUESTS_ERRORS_TOTAL_MD: LazyLock<MetricDescriptor> = LazyLock::
|
||||
new_counter_md(
|
||||
MetricName::ApiRequestsErrorsTotal,
|
||||
"Total number of requests with (4xx and 5xx) errors",
|
||||
&["name", "type"],
|
||||
&API_NAME_TYPE_LABELS,
|
||||
MetricSubsystem::ApiRequests,
|
||||
)
|
||||
});
|
||||
|
||||
pub static API_REQUESTS_ERRORS_TOTAL_BY_SERVER_MD: LazyLock<MetricDescriptor> = LazyLock::new(|| {
|
||||
new_counter_md(
|
||||
MetricName::Custom("requests_errors_total_by_server".to_string()),
|
||||
"Total number of requests with (4xx and 5xx) errors by server",
|
||||
&API_SERVER_NAME_TYPE_LABELS,
|
||||
MetricSubsystem::ApiRequests,
|
||||
)
|
||||
});
|
||||
@@ -108,7 +144,16 @@ pub static API_REQUESTS_5XX_ERRORS_TOTAL_MD: LazyLock<MetricDescriptor> = LazyLo
|
||||
new_counter_md(
|
||||
MetricName::ApiRequests5xxErrorsTotal,
|
||||
"Total number of requests with 5xx errors",
|
||||
&["name", "type"],
|
||||
&API_NAME_TYPE_LABELS,
|
||||
MetricSubsystem::ApiRequests,
|
||||
)
|
||||
});
|
||||
|
||||
pub static API_REQUESTS_5XX_ERRORS_TOTAL_BY_SERVER_MD: LazyLock<MetricDescriptor> = LazyLock::new(|| {
|
||||
new_counter_md(
|
||||
MetricName::Custom("requests_5xx_errors_total_by_server".to_string()),
|
||||
"Total number of requests with 5xx errors by server",
|
||||
&API_SERVER_NAME_TYPE_LABELS,
|
||||
MetricSubsystem::ApiRequests,
|
||||
)
|
||||
});
|
||||
@@ -117,7 +162,16 @@ pub static API_REQUESTS_4XX_ERRORS_TOTAL_MD: LazyLock<MetricDescriptor> = LazyLo
|
||||
new_counter_md(
|
||||
MetricName::ApiRequests4xxErrorsTotal,
|
||||
"Total number of requests with 4xx errors",
|
||||
&["name", "type"],
|
||||
&API_NAME_TYPE_LABELS,
|
||||
MetricSubsystem::ApiRequests,
|
||||
)
|
||||
});
|
||||
|
||||
pub static API_REQUESTS_4XX_ERRORS_TOTAL_BY_SERVER_MD: LazyLock<MetricDescriptor> = LazyLock::new(|| {
|
||||
new_counter_md(
|
||||
MetricName::Custom("requests_4xx_errors_total_by_server".to_string()),
|
||||
"Total number of requests with 4xx errors by server",
|
||||
&API_SERVER_NAME_TYPE_LABELS,
|
||||
MetricSubsystem::ApiRequests,
|
||||
)
|
||||
});
|
||||
@@ -126,7 +180,16 @@ pub static API_REQUESTS_CANCELED_TOTAL_MD: LazyLock<MetricDescriptor> = LazyLock
|
||||
new_counter_md(
|
||||
MetricName::ApiRequestsCanceledTotal,
|
||||
"Total number of requests canceled by the client",
|
||||
&["name", "type"],
|
||||
&API_NAME_TYPE_LABELS,
|
||||
MetricSubsystem::ApiRequests,
|
||||
)
|
||||
});
|
||||
|
||||
pub static API_REQUESTS_CANCELED_TOTAL_BY_SERVER_MD: LazyLock<MetricDescriptor> = LazyLock::new(|| {
|
||||
new_counter_md(
|
||||
MetricName::Custom("requests_canceled_total_by_server".to_string()),
|
||||
"Total number of requests canceled by the client by server",
|
||||
&API_SERVER_NAME_TYPE_LABELS,
|
||||
MetricSubsystem::ApiRequests,
|
||||
)
|
||||
});
|
||||
@@ -135,7 +198,16 @@ pub static API_REQUESTS_TTFB_SECONDS_DISTRIBUTION_MD: LazyLock<MetricDescriptor>
|
||||
new_counter_md(
|
||||
MetricName::ApiRequestsTTFBSecondsDistribution,
|
||||
"Distribution of time to first byte across API calls",
|
||||
&["name", "type", "le"],
|
||||
&API_NAME_TYPE_LE_LABELS,
|
||||
MetricSubsystem::ApiRequests,
|
||||
)
|
||||
});
|
||||
|
||||
pub static API_REQUESTS_TTFB_SECONDS_DISTRIBUTION_BY_SERVER_MD: LazyLock<MetricDescriptor> = LazyLock::new(|| {
|
||||
new_counter_md(
|
||||
MetricName::Custom("requests_ttfb_seconds_distribution_by_server".to_string()),
|
||||
"Distribution of time to first byte across API calls by server",
|
||||
&API_SERVER_NAME_TYPE_LE_LABELS,
|
||||
MetricSubsystem::ApiRequests,
|
||||
)
|
||||
});
|
||||
@@ -144,7 +216,16 @@ pub static API_TRAFFIC_SENT_BYTES_MD: LazyLock<MetricDescriptor> = LazyLock::new
|
||||
new_counter_md(
|
||||
MetricName::ApiTrafficSentBytes,
|
||||
"Total number of bytes sent",
|
||||
&["type"],
|
||||
&API_TYPE_LABELS,
|
||||
MetricSubsystem::ApiRequests,
|
||||
)
|
||||
});
|
||||
|
||||
pub static API_TRAFFIC_SENT_BYTES_BY_SERVER_MD: LazyLock<MetricDescriptor> = LazyLock::new(|| {
|
||||
new_counter_md(
|
||||
MetricName::Custom("traffic_sent_bytes_by_server".to_string()),
|
||||
"Total number of bytes sent by server",
|
||||
&API_SERVER_TYPE_LABELS,
|
||||
MetricSubsystem::ApiRequests,
|
||||
)
|
||||
});
|
||||
@@ -153,7 +234,16 @@ pub static API_TRAFFIC_RECV_BYTES_MD: LazyLock<MetricDescriptor> = LazyLock::new
|
||||
new_counter_md(
|
||||
MetricName::ApiTrafficRecvBytes,
|
||||
"Total number of bytes received",
|
||||
&["type"],
|
||||
&API_TYPE_LABELS,
|
||||
MetricSubsystem::ApiRequests,
|
||||
)
|
||||
});
|
||||
|
||||
pub static API_TRAFFIC_RECV_BYTES_BY_SERVER_MD: LazyLock<MetricDescriptor> = LazyLock::new(|| {
|
||||
new_counter_md(
|
||||
MetricName::Custom("traffic_recv_bytes_by_server".to_string()),
|
||||
"Total number of bytes received by server",
|
||||
&API_SERVER_TYPE_LABELS,
|
||||
MetricSubsystem::ApiRequests,
|
||||
)
|
||||
});
|
||||
|
||||
Reference in New Issue
Block a user