Skip to content

Add pmax threshold check #288

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Tzvonimir merged 1 commit into from
Feb 19, 2026
Merged

Add pmax threshold check #288

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
79 changes: 50 additions & 29 deletions gen/api/v1/mpa.pb.go
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

27 changes: 27 additions & 0 deletions internal/collector/historical_metrics_collector.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -187,6 +187,31 @@ func (c *HistoricalMetricsCollector) fetchContainerPercentiles(ctx context.Conte
sampleCount = int32(countVal)
}

// Pmax queries: max observed value over 24h for spike protection
var cpuPmax, memPmax int64

cpuPmaxQuery := fmt.Sprintf(
`max_over_time(rate(container_cpu_usage_seconds_total{namespace="%s", pod=~"%s", container="%s"}[5m])[24h:%s])`,
workload.Namespace, workload.PodRegex, containerName, historicalStepInterval,
)
cpuPmaxVal, err := c.queryScalar(ctx, cpuPmaxQuery, now)
if err != nil {
c.logger.V(1).Info("CPU pmax query failed", "error", err)
} else {
cpuPmax = int64(cpuPmaxVal * 1000) // Convert cores to millicores
}

memPmaxQuery := fmt.Sprintf(
`max_over_time(container_memory_working_set_bytes{namespace="%s", pod=~"%s", container="%s"}[24h])`,
workload.Namespace, workload.PodRegex, containerName,
)
memPmaxVal, err := c.queryScalar(ctx, memPmaxQuery, now)
if err != nil {
c.logger.V(1).Info("Memory pmax query failed", "error", err)
} else {
memPmax = int64(memPmaxVal)
}

return &gen.ContainerHistoricalMetrics{
ContainerName: containerName,
CpuP50: cpuValues[0.50],
Expand All @@ -199,6 +224,8 @@ func (c *HistoricalMetricsCollector) fetchContainerPercentiles(ctx context.Conte
MemP80: memValues[0.80],
MemP90: memValues[0.90],
MemP99: memValues[0.99],
CpuPmax: cpuPmax,
MemPmax: memPmax,
}, sampleCount
}

Expand Down
3 changes: 3 additions & 0 deletions internal/proto/mpa.proto
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -102,6 +102,9 @@ message ContainerHistoricalMetrics {
int64 disk_p90 = 21;
int64 disk_p95 = 22;
int64 disk_p99 = 23;
// Pmax (max observed over 24h window) for spike protection
int64 cpu_pmax = 24; // max CPU over 24h window (millicores)
int64 mem_pmax = 25; // max memory over 24h window (bytes)
}

// MpaStreamResponse wraps both real-time and historical data on the same stream
Expand Down
3 changes: 3 additions & 0 deletions proto/api/v1/mpa.proto
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -102,6 +102,9 @@ message ContainerHistoricalMetrics {
int64 disk_p90 = 21;
int64 disk_p95 = 22;
int64 disk_p99 = 23;
// Pmax (max observed over 24h window) for spike protection
int64 cpu_pmax = 24; // max CPU over 24h window (millicores)
int64 mem_pmax = 25; // max memory over 24h window (bytes)
}

// MpaStreamResponse wraps both real-time and historical data on the same stream
Expand Down