feat(asap-tools): validate recommended sketch configs end to end on cluster traces

asap-tools/experiments/config/experiment_type/recommended_sketch_configs/alibaba_v2022_ms_cpu_by_msname_5m_default.yaml

@@ -0,0 +1,50 @@
+# @package _global_
+# Generated by recommended_sketch_configs.py; do not edit.
+experiment_params:
+  experiment:
+  - mode: sketchdb
+    server: sketchdb
+    query_prometheus_too: true
+  monitoring:
+    tool: prometheus
+    deployment_mode: bare_metal
+  servers:
+  - name: prometheus
+    url: http://localhost:9090
+  - name: sketchdb
+    url: http://localhost:8088
+  exporters:
+    only_start_if_queries_exist: true
+    exporter_list:
+      cluster_data_exporter:
+        provider: alibaba
+        port: 40000
+        data_type: msresource
+        data_year: 2022
+        parts_mode: part-index
+        part_index: 0
+        scrape_timeout: 10s
+  query_groups:
+  - id: 1
+    queries:
+    - sum by (ms_name) (sum_over_time(alibaba_microservice_cpu_usage[5m]))
+    repetition_delay_ms: 10000
+    client_options:
+      repetitions: 20
+      query_time_offset: 10
+      starting_delay: 390
+    controller_options:
+      accuracy_sla: 0.99
+      latency_sla: 1
+  metrics:
+  - metric: alibaba_microservice_cpu_usage
+    labels:
+    - instance
+    - job
+    - ms_name
+    - ms_instance_id
+    - node_id
+    exporter: cluster_data_exporter
+cluster_data_directory: /data/cluster_traces/alibaba_msmetrics
+prometheus:
+  scrape_interval: 10s

asap-tools/experiments/config/experiment_type/recommended_sketch_configs/alibaba_v2022_ms_cpu_by_msname_5m_recommended.yaml

@@ -0,0 +1,54 @@
+# @package _global_
+# Generated by recommended_sketch_configs.py; do not edit.
+experiment_params:
+  experiment:
+  - mode: sketchdb
+    server: sketchdb
+    query_prometheus_too: true
+  monitoring:
+    tool: prometheus
+    deployment_mode: bare_metal
+  servers:
+  - name: prometheus
+    url: http://localhost:9090
+  - name: sketchdb
+    url: http://localhost:8088
+  exporters:
+    only_start_if_queries_exist: true
+    exporter_list:
+      cluster_data_exporter:
+        provider: alibaba
+        port: 40000
+        data_type: msresource
+        data_year: 2022
+        parts_mode: part-index
+        part_index: 0
+        scrape_timeout: 10s
+  query_groups:
+  - id: 1
+    queries:
+    - sum by (ms_name) (sum_over_time(alibaba_microservice_cpu_usage[5m]))
+    repetition_delay_ms: 10000
+    client_options:
+      repetitions: 20
+      query_time_offset: 10
+      starting_delay: 390
+    controller_options:
+      accuracy_sla: 0.99
+      latency_sla: 1
+  metrics:
+  - metric: alibaba_microservice_cpu_usage
+    labels:
+    - instance
+    - job
+    - ms_name
+    - ms_instance_id
+    - node_id
+    exporter: cluster_data_exporter
+cluster_data_directory: /data/cluster_traces/alibaba_msmetrics
+prometheus:
+  scrape_interval: 10s
+sketch_parameters:
+  CountMinSketch:
+    depth: 3
+    width: 16384

asap-tools/experiments/config/experiment_type/recommended_sketch_configs/alibaba_v2022_ms_cpu_by_msname_instant_default.yaml

@@ -0,0 +1,50 @@
+# @package _global_
+# Generated by recommended_sketch_configs.py; do not edit.
+experiment_params:
+  experiment:
+  - mode: sketchdb
+    server: sketchdb
+    query_prometheus_too: true
+  monitoring:
+    tool: prometheus
+    deployment_mode: bare_metal
+  servers:
+  - name: prometheus
+    url: http://localhost:9090
+  - name: sketchdb
+    url: http://localhost:8088
+  exporters:
+    only_start_if_queries_exist: true
+    exporter_list:
+      cluster_data_exporter:
+        provider: alibaba
+        port: 40000
+        data_type: msresource
+        data_year: 2022
+        parts_mode: part-index
+        part_index: 0
+        scrape_timeout: 10s
+  query_groups:
+  - id: 1
+    queries:
+    - sum by (ms_name) (alibaba_microservice_cpu_usage)
+    repetition_delay_ms: 10000
+    client_options:
+      repetitions: 20
+      query_time_offset: 10
+      starting_delay: 90
+    controller_options:
+      accuracy_sla: 0.99
+      latency_sla: 1
+  metrics:
+  - metric: alibaba_microservice_cpu_usage
+    labels:
+    - instance
+    - job
+    - ms_name
+    - ms_instance_id
+    - node_id
+    exporter: cluster_data_exporter
+cluster_data_directory: /data/cluster_traces/alibaba_msmetrics
+prometheus:
+  scrape_interval: 10s

asap-tools/experiments/config/experiment_type/recommended_sketch_configs/alibaba_v2022_ms_cpu_by_msname_instant_recommended.yaml

@@ -0,0 +1,54 @@
+# @package _global_
+# Generated by recommended_sketch_configs.py; do not edit.
+experiment_params:
+  experiment:
+  - mode: sketchdb
+    server: sketchdb
+    query_prometheus_too: true
+  monitoring:
+    tool: prometheus
+    deployment_mode: bare_metal
+  servers:
+  - name: prometheus
+    url: http://localhost:9090
+  - name: sketchdb
+    url: http://localhost:8088
+  exporters:
+    only_start_if_queries_exist: true
+    exporter_list:
+      cluster_data_exporter:
+        provider: alibaba
+        port: 40000
+        data_type: msresource
+        data_year: 2022
+        parts_mode: part-index
+        part_index: 0
+        scrape_timeout: 10s
+  query_groups:
+  - id: 1
+    queries:
+    - sum by (ms_name) (alibaba_microservice_cpu_usage)
+    repetition_delay_ms: 10000
+    client_options:
+      repetitions: 20
+      query_time_offset: 10
+      starting_delay: 90
+    controller_options:
+      accuracy_sla: 0.99
+      latency_sla: 1
+  metrics:
+  - metric: alibaba_microservice_cpu_usage
+    labels:
+    - instance
+    - job
+    - ms_name
+    - ms_instance_id
+    - node_id
+    exporter: cluster_data_exporter
+cluster_data_directory: /data/cluster_traces/alibaba_msmetrics
+prometheus:
+  scrape_interval: 10s
+sketch_parameters:
+  CountMinSketch:
+    depth: 3
+    width: 16384

asap-tools/experiments/config/experiment_type/recommended_sketch_configs/google_2011_cpu_by_job_id_5m_default.yaml

@@ -0,0 +1,47 @@
+# @package _global_
+# Generated by recommended_sketch_configs.py; do not edit.
+experiment_params:
+  experiment:
+  - mode: sketchdb
+    server: sketchdb
+    query_prometheus_too: true
+  monitoring:
+    tool: prometheus
+    deployment_mode: bare_metal
+  servers:
+  - name: prometheus
+    url: http://localhost:9090
+  - name: sketchdb
+    url: http://localhost:8088
+  exporters:
+    only_start_if_queries_exist: true
+    exporter_list:
+      cluster_data_exporter:
+        provider: google
+        port: 40000
+        metrics: mean-cpu-usage-rate
+        parts_mode: part-index
+        part_index: 0
+        scrape_timeout: 1s
+  query_groups:
+  - id: 1
+    queries:
+    - sum by (job_id) (sum_over_time(google_mean_cpu_usage_rate_0[5m]))
+    repetition_delay_ms: 5000
+    client_options:
+      repetitions: 20
+      query_time_offset: 10
+      starting_delay: 390
+    controller_options:
+      accuracy_sla: 0.99
+      latency_sla: 1
+  metrics:
+  - metric: google_mean_cpu_usage_rate_0
+    labels:
+    - instance
+    - job
+    - job_id
+    - task_index
+    - machine_id
+    exporter: cluster_data_exporter
+cluster_data_directory: /data/cluster_traces/google

asap-tools/experiments/config/experiment_type/recommended_sketch_configs/google_2011_cpu_by_job_id_5m_recommended.yaml

@@ -0,0 +1,51 @@
+# @package _global_
+# Generated by recommended_sketch_configs.py; do not edit.
+experiment_params:
+  experiment:
+  - mode: sketchdb
+    server: sketchdb
+    query_prometheus_too: true
+  monitoring:
+    tool: prometheus
+    deployment_mode: bare_metal
+  servers:
+  - name: prometheus
+    url: http://localhost:9090
+  - name: sketchdb
+    url: http://localhost:8088
+  exporters:
+    only_start_if_queries_exist: true
+    exporter_list:
+      cluster_data_exporter:
+        provider: google
+        port: 40000
+        metrics: mean-cpu-usage-rate
+        parts_mode: part-index
+        part_index: 0
+        scrape_timeout: 1s
+  query_groups:
+  - id: 1
+    queries:
+    - sum by (job_id) (sum_over_time(google_mean_cpu_usage_rate_0[5m]))
+    repetition_delay_ms: 5000
+    client_options:
+      repetitions: 20
+      query_time_offset: 10
+      starting_delay: 390
+    controller_options:
+      accuracy_sla: 0.99
+      latency_sla: 1
+  metrics:
+  - metric: google_mean_cpu_usage_rate_0
+    labels:
+    - instance
+    - job
+    - job_id
+    - task_index
+    - machine_id
+    exporter: cluster_data_exporter
+cluster_data_directory: /data/cluster_traces/google
+sketch_parameters:
+  CountMinSketch:
+    depth: 3
+    width: 4096

asap-tools/experiments/config/experiment_type/recommended_sketch_configs/google_2011_cpu_by_job_id_instant_default.yaml

@@ -0,0 +1,47 @@
+# @package _global_
+# Generated by recommended_sketch_configs.py; do not edit.
+experiment_params:
+  experiment:
+  - mode: sketchdb
+    server: sketchdb
+    query_prometheus_too: true
+  monitoring:
+    tool: prometheus
+    deployment_mode: bare_metal
+  servers:
+  - name: prometheus
+    url: http://localhost:9090
+  - name: sketchdb
+    url: http://localhost:8088
+  exporters:
+    only_start_if_queries_exist: true
+    exporter_list:
+      cluster_data_exporter:
+        provider: google
+        port: 40000
+        metrics: mean-cpu-usage-rate
+        parts_mode: part-index
+        part_index: 0
+        scrape_timeout: 1s
+  query_groups:
+  - id: 1
+    queries:
+    - sum by (job_id) (google_mean_cpu_usage_rate_0)
+    repetition_delay_ms: 5000
+    client_options:
+      repetitions: 20
+      query_time_offset: 10
+      starting_delay: 90
+    controller_options:
+      accuracy_sla: 0.99
+      latency_sla: 1
+  metrics:
+  - metric: google_mean_cpu_usage_rate_0
+    labels:
+    - instance
+    - job
+    - job_id
+    - task_index
+    - machine_id
+    exporter: cluster_data_exporter
+cluster_data_directory: /data/cluster_traces/google