Сlassified Bad Connections and Handshake Failures in API

Co-Authored-By: brekotis <93345790+brekotis@users.noreply.github.com>
This commit is contained in:
Alexey
2026-04-24 10:55:37 +03:00
parent 493f5c9680
commit 8960fad8cd
8 changed files with 187 additions and 70 deletions

View File

@@ -41,7 +41,7 @@ use config_store::{current_revision, load_config_from_disk, parse_if_match};
use events::ApiEventStore;
use http_utils::{error_response, read_json, read_optional_json, success_response};
use model::{
ApiFailure, CreateUserRequest, DeleteUserResponse, HealthData, HealthReadyData,
ApiFailure, ClassCount, CreateUserRequest, DeleteUserResponse, HealthData, HealthReadyData,
PatchUserRequest, RotateSecretRequest, SummaryData, UserActiveIps,
};
use runtime_edge::{
@@ -334,10 +334,24 @@ async fn handle(
}
("GET", "/v1/stats/summary") => {
let revision = current_revision(&shared.config_path).await?;
let connections_bad_by_class = shared
.stats
.get_connects_bad_class_counts()
.into_iter()
.map(|(class, total)| ClassCount { class, total })
.collect();
let handshake_failures_by_class = shared
.stats
.get_handshake_failure_class_counts()
.into_iter()
.map(|(class, total)| ClassCount { class, total })
.collect();
let data = SummaryData {
uptime_seconds: shared.stats.uptime_secs(),
connections_total: shared.stats.get_connects_all(),
connections_bad_total: shared.stats.get_connects_bad(),
connections_bad_by_class,
handshake_failures_by_class,
handshake_timeouts_total: shared.stats.get_handshake_timeouts(),
configured_users: cfg.access.users.len(),
};

View File

@@ -71,11 +71,19 @@ pub(super) struct HealthReadyData {
pub(super) total_upstreams: usize,
}
#[derive(Serialize, Clone)]
pub(super) struct ClassCount {
pub(super) class: String,
pub(super) total: u64,
}
#[derive(Serialize)]
pub(super) struct SummaryData {
pub(super) uptime_seconds: f64,
pub(super) connections_total: u64,
pub(super) connections_bad_total: u64,
pub(super) connections_bad_by_class: Vec<ClassCount>,
pub(super) handshake_failures_by_class: Vec<ClassCount>,
pub(super) handshake_timeouts_total: u64,
pub(super) configured_users: usize,
}
@@ -91,6 +99,8 @@ pub(super) struct ZeroCoreData {
pub(super) uptime_seconds: f64,
pub(super) connections_total: u64,
pub(super) connections_bad_total: u64,
pub(super) connections_bad_by_class: Vec<ClassCount>,
pub(super) handshake_failures_by_class: Vec<ClassCount>,
pub(super) handshake_timeouts_total: u64,
pub(super) accept_permit_timeout_total: u64,
pub(super) configured_users: usize,

View File

@@ -7,8 +7,8 @@ use crate::transport::upstream::IpPreference;
use super::ApiShared;
use super::model::{
DcEndpointWriters, DcStatus, DcStatusData, MeWriterStatus, MeWritersData, MeWritersSummary,
MinimalAllData, MinimalAllPayload, MinimalDcPathData, MinimalMeRuntimeData,
ClassCount, DcEndpointWriters, DcStatus, DcStatusData, MeWriterStatus, MeWritersData,
MeWritersSummary, MinimalAllData, MinimalAllPayload, MinimalDcPathData, MinimalMeRuntimeData,
MinimalQuarantineData, UpstreamDcStatus, UpstreamStatus, UpstreamSummaryData, UpstreamsData,
ZeroAllData, ZeroCodeCount, ZeroCoreData, ZeroDesyncData, ZeroMiddleProxyData, ZeroPoolData,
ZeroUpstreamData,
@@ -26,6 +26,16 @@ pub(crate) struct MinimalCacheEntry {
pub(super) fn build_zero_all_data(stats: &Stats, configured_users: usize) -> ZeroAllData {
let telemetry = stats.telemetry_policy();
let bad_connection_classes = stats
.get_connects_bad_class_counts()
.into_iter()
.map(|(class, total)| ClassCount { class, total })
.collect();
let handshake_failure_classes = stats
.get_handshake_failure_class_counts()
.into_iter()
.map(|(class, total)| ClassCount { class, total })
.collect();
let handshake_error_codes = stats
.get_me_handshake_error_code_counts()
.into_iter()
@@ -38,6 +48,8 @@ pub(super) fn build_zero_all_data(stats: &Stats, configured_users: usize) -> Zer
uptime_seconds: stats.uptime_secs(),
connections_total: stats.get_connects_all(),
connections_bad_total: stats.get_connects_bad(),
connections_bad_by_class: bad_connection_classes,
handshake_failures_by_class: handshake_failure_classes,
handshake_timeouts_total: stats.get_handshake_timeouts(),
accept_permit_timeout_total: stats.get_accept_permit_timeout_total(),
configured_users,