Some checks failed
go: build dev binaries / cleanup (push) Successful in 4s
Codespell / Check for spelling errors (push) Failing after 3s
docker: build dev containers / build-rust-binaries (amd64, x86_64-unknown-linux-musl) (push) Failing after 3s
docker: build dev containers / build-dev-containers (push) Has been skipped
docker: build dev containers / build-rust-binaries (arm64, true, aarch64-unknown-linux-musl) (push) Failing after 3s
End to End / FUSE Mount (push) Failing after 2s
EC Integration Tests / EC Integration Tests (push) Failing after 30s
FUSE DLM Integration Tests / FUSE DLM Integration Tests (push) Failing after 3s
FUSE Volume Server Failover Tests / FUSE Volume Server Failover (push) Failing after 3s
FUSE Integration Tests / FUSE Integration Testing (push) Failing after 2s
FUSE P2P Peer Chunk Sharing Integration Tests / FUSE P2P Peer Chunk Sharing (push) Failing after 3s
go: build binary / Go Vet (push) Failing after 2s
go: build binary / Go Vet 32-bit (push) Failing after 3s
go: build binary / Build (push) Failing after 4s
go: build binary / Build cross-platform (freebsd/amd64) (push) Failing after 3s
go: build binary / Build cross-platform (windows/amd64) (push) Failing after 3s
go: build binary / Build cross-platform (darwin/arm64) (push) Failing after 3s
go: build binary / Build cross-platform (windows/arm64) (push) Failing after 3s
go: build binary / Test (push) Failing after 2s
go: build binary / Test 32-bit (push) Failing after 3s
helm: lint and test charts / lint-test (push) Failing after 3s
Java Client Integration Tests / Java Integration Tests (11) (push) Failing after 3s
Java Client Integration Tests / Java Integration Tests (17) (push) Failing after 3s
go: build dev binaries / build_dev_linux_windows (amd64, linux) (push) Failing after 2s
go: build dev binaries / build_dev_linux_windows (amd64, windows) (push) Failing after 3s
go: build dev binaries / build_dev_darwin (amd64, darwin) (push) Has been skipped
go: build dev binaries / build_dev_darwin (arm64, darwin) (push) Has been skipped
Java Client Unit Tests / Java Unit Tests (11) (push) Failing after 3s
Java Client Unit Tests / Java Unit Tests (17) (push) Failing after 2s
Java Client Unit Tests / Java Unit Tests (21) (push) Failing after 3s
Java Client Unit Tests / Java Unit Tests (8) (push) Failing after 3s
Kafka Quick Test (Load Test with Schema Registry) / Kafka Client Load Test (Quick) (push) Failing after 3s
Kafka Gateway Tests / Kafka Unit Tests (unit-tests-1) (push) Failing after 11s
Kafka Gateway Tests / Kafka Integration Tests (Critical) (integration-1) (push) Failing after 3s
Kafka Gateway Tests / Kafka End-to-End Tests (with SMQ) (e2e-1) (push) Failing after 3s
Kafka Gateway Tests / Kafka Consumer Group Tests (Highly Isolated) (consumer-group-1) (push) Failing after 2s
Kafka Gateway Tests / Kafka Client Compatibility (with SMQ) (client-compat-1) (push) Failing after 3s
Kafka Gateway Tests / Kafka SMQ Integration Tests (Full Stack) (smq-integration-1) (push) Failing after 3s
Kafka Gateway Tests / Kafka Protocol Tests (Isolated) (protocol-1) (push) Failing after 3s
KMS Tests / KMS Provider Integration Tests (push) Failing after 2s
KMS Tests / S3 KMS End-to-End Tests (push) Failing after 3s
Master Cold Start Tests / Master Cold Start Tests (push) Failing after 4s
Metadata Subscribe Integration Tests / Metadata Subscribe Integration Tests (push) Failing after 3s
Multi-Master Tests / Multi-Master Failover Tests (push) Failing after 3s
Performance / CPU and Heap Profile (push) Failing after 2s
Performance / S3 Read/Write Benchmark (rust volume) (push) Failing after 3s
pjdfstest POSIX Compliance / pjdfstest (push) Failing after 2s
Plugin Worker Integration Tests / Plugin Worker: erasure_coding (push) Failing after 3s
Plugin Worker Integration Tests / Plugin Worker: vacuum (push) Failing after 3s
Rust Volume Server Tests / Rust Integration Tests (push) Failing after 3s
Rust Volume Server Tests / Go Tests with Rust Volume (grpc - Shard 1) (push) Failing after 2s
Rust Volume Server Tests / Go Tests with Rust Volume (http - Shard 1) (push) Failing after 3s
Rust Volume Server Tests / Go Tests with Rust Volume (grpc - Shard 2) (push) Failing after 3s
Rust Volume Server Tests / Go Tests with Rust Volume (http - Shard 2) (push) Failing after 3s
Rust Volume Server Tests / Go Tests with Rust Volume (grpc - Shard 3) (push) Failing after 3s
S3 IAM Integration Tests / S3 IAM Distributed Tests (push) Failing after 2s
S3 IAM Integration Tests / S3 IAM Performance Tests (push) Failing after 3s
Performance / Throughput Benchmark (go volume) (push) Failing after 3s
Performance / Throughput Benchmark (rust volume) (push) Failing after 2s
Performance / S3 Read/Write Benchmark (go volume) (push) Failing after 3s
Plugin Worker Integration Tests / Plugin Worker: volume_balance (push) Failing after 3s
PostgreSQL Gateway Tests / PostgreSQL Basic Tests (push) Failing after 3s
Rust Volume Server Tests / Rust Unit Tests (push) Failing after 2s
Rust Volume Server Tests / Go Tests with Rust Volume (http - Shard 3) (push) Failing after 3s
Rust Plugin Worker Tests / Rust Plugin Worker Build and Unit Tests (push) Failing after 3s
rust: build dev volume server binaries / cleanup (push) Successful in 3s
S3 ETag and ACL Tests / S3 ETag + ACL Integration Tests (push) Failing after 3s
S3 IAM Integration Tests / IAM Unit Tests (push) Failing after 3s
S3 IAM Integration Tests / S3 IAM Integration Tests (advanced) (push) Failing after 3s
S3 IAM Integration Tests / S3 IAM Integration Tests (basic) (push) Failing after 2s
S3 IAM Integration Tests / S3 IAM Integration Tests (group) (push) Failing after 3s
S3 IAM Integration Tests / S3 IAM Integration Tests (policy-enforcement) (push) Failing after 2s
S3 IAM Integration Tests / S3 IAM Integration Tests (sts) (push) Failing after 4s
S3 Keycloak Integration Tests / S3 Keycloak Integration Tests (push) Failing after 3s
S3 PyArrow Parquet Tests / PyArrow Parquet Tests (Python 3.11) (push) Failing after 3s
S3 PyArrow Parquet Tests / Go Unit Tests (Implicit Directory) (push) Has been cancelled
S3 PyArrow Parquet Tests / PyArrow Parquet Tests (Python 3.12) (push) Has been cancelled
rust: build dev volume server binaries / build-rust-volume-dev-darwin (darwin-amd64, x86_64-apple-darwin) (push) Has been cancelled
rust: build dev volume server binaries / build-rust-volume-dev-darwin (darwin-arm64, aarch64-apple-darwin) (push) Has been cancelled
rust: build dev volume server binaries / build-rust-volume-dev-linux (linux-amd64, x86_64-unknown-linux-gnu) (push) Has been cancelled
S3 PyArrow Parquet Tests / PyArrow Parquet Tests (Python 3.9) (push) Has been cancelled
S3 Proxy Signature Tests / S3 Proxy Signature Verification Tests (push) Has been cancelled
S3 SDK V2 Route Disambiguation Tests / S3 SDK V2 Routing Tests (push) Has been cancelled
S3 SSE Tests / S3 SSE Integration Tests (quick) (push) Has been cancelled
S3 SSE Tests / S3 SSE Compatibility Test (push) Has been cancelled
S3 SSE Tests / S3 SSE Metadata Persistence Test (push) Has been cancelled
S3 SSE Tests / S3 SSE Copy Operations Test (push) Has been cancelled
S3 SSE Tests / S3 SSE Multipart Upload Test (push) Has been cancelled
S3 SSE Tests / S3 SSE Performance Test (push) Has been cancelled
S3 SSE Tests / S3 Volume Encryption Test (push) Has been cancelled
S3 SSE Tests / S3 SSE Integration Tests (comprehensive) (push) Has been cancelled
Spark Integration Tests / Spark Integration Tests (push) Failing after 2s
Telemetry Integration Tests / telemetry-integration-test (push) Failing after 3s
Volume Server Integration Tests / Volume Server Integration Tests (grpc - Shard 1) (push) Failing after 3s
Volume Server Integration Tests / Volume Server Integration Tests (http - Shard 1) (push) Failing after 3s
Ceph S3 tests / Basic S3 tests (KV store) (push) Has been cancelled
Ceph S3 tests / S3 Versioning & Object Lock tests (push) Has been cancelled
S3 Policy Integration Tests / S3 Policy Unit Tests (push) Failing after 3s
Ceph S3 tests / S3 CORS tests (push) Has been cancelled
Ceph S3 tests / SeaweedFS Custom S3 Copy tests (push) Has been cancelled
Ceph S3 tests / Basic S3 tests (SQL store) (push) Has been cancelled
test s3 over https using aws-cli / awscli-tests (push) Has been cancelled
TLS Rotation Integration Tests / TLS Rotation Integration Tests (push) Has been cancelled
Vacuum Integration Tests / Vacuum Integration Tests (push) Has been cancelled
S3 Policy Integration Tests / S3 Policy Variables Integration Tests (push) Failing after 3s
S3 Policy Integration Tests / S3 Policy Enforcement Integration Tests (advanced-policy) (push) Failing after 3s
S3 Policy Integration Tests / S3 Policy Enforcement Integration Tests (basic-policy) (push) Failing after 2s
S3 Policy Integration Tests / S3 Policy Enforcement Integration Tests (contextual-policy) (push) Failing after 4s
S3 Policy Integration Tests / Trusted Proxy Detection Tests (push) Failing after 2s
S3 Policy Integration Tests / S3 Policy Shell Integration Tests (push) Failing after 3s
Samba on FUSE Integration / samba-integration (push) Failing after 2s
SFTP Integration Tests / SFTP Integration Testing (push) Failing after 3s
terraform: validate and test modules / fmt, validate, plan-level tests (push) Failing after 3s
terraform: validate and test modules / local cluster smoke test (real weed) (push) Failing after 2s
Volume Server Integration Tests / Volume Server Integration Tests (grpc - Shard 3) (push) Failing after 3s
Volume Server Integration Tests / Volume Server Integration Tests (grpc - Shard 2) (push) Failing after 3s
Volume Server Integration Tests / Volume Server Integration Tests (http - Shard 2) (push) Failing after 2s
Volume Server Integration Tests / Volume Server Integration Tests (http - Shard 3) (push) Failing after 5s
mount: windows conformance / WinFsp conformance (push) Has been cancelled
mount: windows / Mount on Windows (push) Has been cancelled
183 lines
5.8 KiB
Go
183 lines
5.8 KiB
Go
package dash
|
|
|
|
import (
|
|
"fmt"
|
|
"strings"
|
|
"time"
|
|
)
|
|
|
|
// dashMaxSamples bounds the in-memory trend ring buffer. At the 15s sample
|
|
// cadence (piggy-backed on publishMaintenanceMetrics) this is ~15 minutes.
|
|
const dashMaxSamples = 60
|
|
|
|
// dashSample is one point-in-time snapshot of a few headline cluster numbers,
|
|
// derived from data the admin already holds (cluster topology + the in-process
|
|
// maintenance queue) — no Prometheus scrape required.
|
|
type dashSample struct {
|
|
t time.Time
|
|
volumes float64
|
|
ecShards float64
|
|
diskUsed float64
|
|
chunks float64
|
|
tasks float64 // pending/assigned/in-progress maintenance tasks
|
|
workers float64
|
|
}
|
|
|
|
// DashboardTrends carries inline-SVG sparklines of recent cluster history,
|
|
// keyed to the dashboard's existing summary cards so each card shows a value
|
|
// plus its trend (rather than a separate, duplicate row). Maintenance metrics
|
|
// that have no existing card carry their current value too, and fill the
|
|
// previously-empty columns of the EC row.
|
|
type DashboardTrends struct {
|
|
Samples int `json:"samples"`
|
|
|
|
// Sparklines (raw <svg>) for the existing summary cards.
|
|
Volumes string `json:"-"`
|
|
Chunks string `json:"-"`
|
|
DiskUsed string `json:"-"`
|
|
EcShards string `json:"-"`
|
|
|
|
// Maintenance cards: value + sparkline.
|
|
Tasks string `json:"-"`
|
|
TasksValue string `json:"tasks"`
|
|
Workers string `json:"-"`
|
|
WorkersValue string `json:"workers"`
|
|
}
|
|
|
|
// recordDashboardSample snapshots headline cluster numbers into the ring
|
|
// buffer. Cheap: topology is already cached, and the maintenance stats are
|
|
// in-memory. Called on the existing maintenance-metrics ticker.
|
|
func (s *AdminServer) recordDashboardSample() {
|
|
topology, err := s.GetClusterTopology()
|
|
if err != nil || topology == nil {
|
|
return
|
|
}
|
|
ecShards := 0
|
|
for _, vs := range topology.VolumeServers {
|
|
ecShards += vs.EcShards
|
|
}
|
|
sample := dashSample{
|
|
t: time.Now(),
|
|
volumes: float64(topology.TotalVolumes),
|
|
ecShards: float64(ecShards),
|
|
diskUsed: float64(topology.TotalSize),
|
|
chunks: float64(topology.TotalChunks),
|
|
}
|
|
if s.maintenanceManager != nil {
|
|
if stats := s.maintenanceManager.GetStats(); stats != nil {
|
|
active := 0
|
|
for status, n := range stats.TasksByStatus {
|
|
switch string(status) {
|
|
case "pending", "assigned", "in_progress":
|
|
active += n
|
|
}
|
|
}
|
|
sample.tasks = float64(active)
|
|
}
|
|
}
|
|
// Counted across both worker registries, same as the Prometheus gauge, so
|
|
// the card isn't stuck at 0 on clusters that only run plugin workers.
|
|
workers, _, _ := s.workerFleetTotals()
|
|
sample.workers = float64(workers)
|
|
|
|
s.dashSamplesMu.Lock()
|
|
s.dashSamples = append(s.dashSamples, sample)
|
|
if len(s.dashSamples) > dashMaxSamples {
|
|
s.dashSamples = s.dashSamples[len(s.dashSamples)-dashMaxSamples:]
|
|
}
|
|
s.dashSamplesMu.Unlock()
|
|
}
|
|
|
|
// GetDashboardTrends builds the trend cards from the current ring buffer.
|
|
func (s *AdminServer) GetDashboardTrends() DashboardTrends {
|
|
s.dashSamplesMu.Lock()
|
|
samples := make([]dashSample, len(s.dashSamples))
|
|
copy(samples, s.dashSamples)
|
|
s.dashSamplesMu.Unlock()
|
|
|
|
series := func(pick func(dashSample) float64) []float64 {
|
|
out := make([]float64, len(samples))
|
|
for i, smp := range samples {
|
|
out[i] = pick(smp)
|
|
}
|
|
return out
|
|
}
|
|
tasks := series(func(s dashSample) float64 { return s.tasks })
|
|
workers := series(func(s dashSample) float64 { return s.workers })
|
|
|
|
// Sparkline colors match the existing cards' border colors.
|
|
return DashboardTrends{
|
|
Samples: len(samples),
|
|
Volumes: sparklineSVG(series(func(s dashSample) float64 { return s.volumes }), "#1cc88a"), // success
|
|
Chunks: sparklineSVG(series(func(s dashSample) float64 { return s.chunks }), "#36b9cc"), // info
|
|
DiskUsed: sparklineSVG(series(func(s dashSample) float64 { return s.diskUsed }), "#f6c23e"), // warning
|
|
EcShards: sparklineSVG(series(func(s dashSample) float64 { return s.ecShards }), "#5a5c69"), // dark
|
|
Tasks: sparklineSVG(tasks, "#36b9cc"),
|
|
TasksValue: trendCount(last(tasks)),
|
|
Workers: sparklineSVG(workers, "#4e73df"),
|
|
WorkersValue: trendCount(last(workers)),
|
|
}
|
|
}
|
|
|
|
func last(v []float64) float64 {
|
|
if len(v) == 0 {
|
|
return 0
|
|
}
|
|
return v[len(v)-1]
|
|
}
|
|
|
|
// sparklineSVG renders a fixed-viewBox, width-responsive inline SVG line of the
|
|
// given points. Self-contained (no JS/chart lib); safe to inline in the page.
|
|
func sparklineSVG(pts []float64, color string) string {
|
|
const w, h = 240.0, 48.0
|
|
if len(pts) < 2 {
|
|
// Not enough history yet — draw a flat baseline so the card isn't empty.
|
|
return fmt.Sprintf(`<svg viewBox="0 0 %g %g" preserveAspectRatio="none" style="width:100%%;height:48px"><line x1="0" y1="%g" x2="%g" y2="%g" stroke="%s" stroke-width="2" opacity="0.4"/></svg>`, w, h, h/2, w, h/2, color)
|
|
}
|
|
minV, maxV := pts[0], pts[0]
|
|
for _, v := range pts {
|
|
if v < minV {
|
|
minV = v
|
|
}
|
|
if v > maxV {
|
|
maxV = v
|
|
}
|
|
}
|
|
span := maxV - minV
|
|
if span == 0 {
|
|
span = 1
|
|
}
|
|
dx := w / float64(len(pts)-1)
|
|
var line strings.Builder
|
|
for i, v := range pts {
|
|
x := float64(i) * dx
|
|
y := h - 3 - (v-minV)/span*(h-6) // 3px padding top/bottom; SVG y grows down
|
|
if i == 0 {
|
|
fmt.Fprintf(&line, "M%.1f %.1f", x, y)
|
|
} else {
|
|
fmt.Fprintf(&line, " L%.1f %.1f", x, y)
|
|
}
|
|
}
|
|
// Area path closes back along the baseline for a subtle fill.
|
|
area := fmt.Sprintf("%s L%.1f %.1f L0 %.1f Z", line.String(), w, h, h)
|
|
return fmt.Sprintf(`<svg viewBox="0 0 %g %g" preserveAspectRatio="none" style="width:100%%;height:48px"><path d="%s" fill="%s" opacity="0.12"/><path d="%s" fill="none" stroke="%s" stroke-width="2"/></svg>`,
|
|
w, h, area, color, line.String(), color)
|
|
}
|
|
|
|
// trendCount formats a count with thousands separators.
|
|
func trendCount(v float64) string {
|
|
n := int64(v)
|
|
s := fmt.Sprintf("%d", n)
|
|
if n < 0 {
|
|
return s
|
|
}
|
|
var out []byte
|
|
for i, c := range []byte(s) {
|
|
if i > 0 && (len(s)-i)%3 == 0 {
|
|
out = append(out, ',')
|
|
}
|
|
out = append(out, c)
|
|
}
|
|
return string(out)
|
|
}
|