From 24a2255c477b2b63bca16fc30ca32eb465ff6df1 Mon Sep 17 00:00:00 2001 From: Vladislav Polyakov Date: Fri, 25 Oct 2024 23:21:33 +0300 Subject: [PATCH 1/4] ci: run slo on push master --- .github/workflows/slo.yml | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/.github/workflows/slo.yml b/.github/workflows/slo.yml index 70c635451..483985d92 100644 --- a/.github/workflows/slo.yml +++ b/.github/workflows/slo.yml @@ -1,6 +1,9 @@ name: slo on: + push: + branches: + - master pull_request: branches: - master @@ -81,8 +84,11 @@ jobs: ./tests/slo/.bin/${{matrix.sdk.id}}_linux_amd64 create grpc://localhost:2135 /Root/testdb ./tests/slo/.bin/${{matrix.sdk.id}}_linux_amd64 run grpc://localhost:2135 /Root/testdb \ -prom-pgw localhost:9091 \ - -report-period 500 \ + -report-period 250 \ -time ${{inputs.slo_workload_duration_seconds || 600}} \ -read-rps ${{inputs.slo_workload_read_max_rps || 1000}} \ - -write-rps ${{inputs.slo_workload_write_max_rps || 100}} + -write-rps ${{inputs.slo_workload_write_max_rps || 100}} \ + -read-timeout 10000 \ + -write-timeout 10000 \ + -shutdown-time 30 ./tests/slo/.bin/${{matrix.sdk.id}}_linux_amd64 cleanup grpc://localhost:2135 /Root/testdb From 3c7d625f24cad891a07b9cbff6c2ceb9d52a0d68 Mon Sep 17 00:00:00 2001 From: Vladislav Polyakov Date: Fri, 25 Oct 2024 23:29:46 +0300 Subject: [PATCH 2/4] style: remove unused promlint comments --- tests/slo/internal/metrics/metrics.go | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) diff --git a/tests/slo/internal/metrics/metrics.go b/tests/slo/internal/metrics/metrics.go index 27029e6f2..4e79923ef 100644 --- a/tests/slo/internal/metrics/metrics.go +++ b/tests/slo/internal/metrics/metrics.go @@ -32,7 +32,6 @@ type ( retriesFailureTotal *prometheus.CounterVec pendingOperations *prometheus.GaugeVec - // TODO: // sdk_cpu_usage_seconds_total *prometheus.CounterVec // sdk_memory_usage_bytes *prometheus.GaugeVec // sdk_connections_open *prometheus.GaugeVec @@ -54,7 +53,7 @@ func New(url, ref, label, jobName string) (*Metrics, error) { } m.errorsTotal = prometheus.NewCounterVec( - prometheus.CounterOpts{ //nolint:promlinter + prometheus.CounterOpts{ Name: "sdk_errors_total", Help: "Total number of errors encountered, categorized by error type.", }, @@ -62,7 +61,7 @@ func New(url, ref, label, jobName string) (*Metrics, error) { ) m.operationsTotal = prometheus.NewCounterVec( - prometheus.CounterOpts{ //nolint:promlinter + prometheus.CounterOpts{ Name: "sdk_operations_total", Help: "Total number of operations, categorized by type attempted by the SDK.", }, @@ -70,7 +69,7 @@ func New(url, ref, label, jobName string) (*Metrics, error) { ) m.operationsSuccessTotal = prometheus.NewCounterVec( - prometheus.CounterOpts{ //nolint:promlinter + prometheus.CounterOpts{ Name: "sdk_operations_success_total", Help: "Total number of successful operations, categorized by type.", }, @@ -78,7 +77,7 @@ func New(url, ref, label, jobName string) (*Metrics, error) { ) m.operationsFailureTotal = prometheus.NewCounterVec( - prometheus.CounterOpts{ //nolint:promlinter + prometheus.CounterOpts{ Name: "sdk_operations_failure_total", Help: "Total number of failed operations, categorized by type.", }, @@ -86,7 +85,7 @@ func New(url, ref, label, jobName string) (*Metrics, error) { ) m.operationLatencySeconds = prometheus.NewHistogramVec( - prometheus.HistogramOpts{ //nolint:promlinter + prometheus.HistogramOpts{ Name: "sdk_operation_latency_seconds", Help: "Latency of operations performed by the SDK in seconds, categorized by type and status.", Buckets: []float64{ @@ -109,7 +108,7 @@ func New(url, ref, label, jobName string) (*Metrics, error) { ) m.retryAttemptsTotal = prometheus.NewCounterVec( - prometheus.CounterOpts{ //nolint:promlinter + prometheus.CounterOpts{ Name: "sdk_retry_attempts_total", Help: "Total number of retry attempts, categorized by operation type.", }, @@ -117,7 +116,7 @@ func New(url, ref, label, jobName string) (*Metrics, error) { ) m.retriesSuccessTotal = prometheus.NewCounterVec( - prometheus.CounterOpts{ //nolint:promlinter + prometheus.CounterOpts{ Name: "sdk_retries_success_total", Help: "Total number of successful retries, categorized by operation type.", }, @@ -125,7 +124,7 @@ func New(url, ref, label, jobName string) (*Metrics, error) { ) m.retriesFailureTotal = prometheus.NewCounterVec( - prometheus.CounterOpts{ //nolint:promlinter + prometheus.CounterOpts{ Name: "sdk_retries_failure_total", Help: "Total number of failed retries, categorized by operation type.", }, @@ -133,7 +132,7 @@ func New(url, ref, label, jobName string) (*Metrics, error) { ) m.pendingOperations = prometheus.NewGaugeVec( - prometheus.GaugeOpts{ //nolint:promlinter + prometheus.GaugeOpts{ Name: "sdk_pending_operations", Help: "Current number of pending operations, categorized by type.", }, From f48a61dbc514be971e561d7a920a7a17fab4d179 Mon Sep 17 00:00:00 2001 From: Vladislav Polyakov Date: Fri, 25 Oct 2024 23:38:04 +0300 Subject: [PATCH 3/4] ci: set default slo workload duration to 1 minute --- .github/workflows/slo.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/slo.yml b/.github/workflows/slo.yml index 483985d92..603415a15 100644 --- a/.github/workflows/slo.yml +++ b/.github/workflows/slo.yml @@ -85,7 +85,7 @@ jobs: ./tests/slo/.bin/${{matrix.sdk.id}}_linux_amd64 run grpc://localhost:2135 /Root/testdb \ -prom-pgw localhost:9091 \ -report-period 250 \ - -time ${{inputs.slo_workload_duration_seconds || 600}} \ + -time ${{inputs.slo_workload_duration_seconds || 60}} \ -read-rps ${{inputs.slo_workload_read_max_rps || 1000}} \ -write-rps ${{inputs.slo_workload_write_max_rps || 100}} \ -read-timeout 10000 \ From 238cd6a2fb8a08907fa5c26bd591dca9d578fd92 Mon Sep 17 00:00:00 2001 From: Vladislav Polyakov Date: Sat, 26 Oct 2024 00:14:06 +0300 Subject: [PATCH 4/4] ci: increase slo duration to 10 min --- .github/workflows/slo.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/slo.yml b/.github/workflows/slo.yml index 603415a15..483985d92 100644 --- a/.github/workflows/slo.yml +++ b/.github/workflows/slo.yml @@ -85,7 +85,7 @@ jobs: ./tests/slo/.bin/${{matrix.sdk.id}}_linux_amd64 run grpc://localhost:2135 /Root/testdb \ -prom-pgw localhost:9091 \ -report-period 250 \ - -time ${{inputs.slo_workload_duration_seconds || 60}} \ + -time ${{inputs.slo_workload_duration_seconds || 600}} \ -read-rps ${{inputs.slo_workload_read_max_rps || 1000}} \ -write-rps ${{inputs.slo_workload_write_max_rps || 100}} \ -read-timeout 10000 \