Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
2 changes: 1 addition & 1 deletion src/compute-plane-services/byoo-otel-collector/VERSION
Original file line number Diff line number Diff line change
@@ -1 +1 @@
0.157.9
0.157.11
Original file line number Diff line number Diff line change
Expand Up @@ -57,7 +57,7 @@ receivers:
metrics_path: /federate
params:
match[]:
- '{job=~"kubelet", namespace="nvcf-backend", pod=~".*fake-instance-id.*", container=~"inference|task|", __name__=~"(container_cpu_cfs_throttled_periods_total|container_cpu_cfs_throttled_seconds_total|container_cpu_usage_seconds_total|container_memory_cache|container_memory_rss|container_memory_swap|container_memory_usage_bytes|container_memory_working_set_bytes|container_fs_limit_bytes|container_fs_usage_bytes|container_fs_reads_bytes_total|container_fs_reads_total|container_fs_writes_bytes_total|container_fs_writes_total|container_network_receive_bytes_total|container_network_receive_errors_total|container_network_receive_packets_dropped_total|container_network_receive_packets_total|container_network_transmit_bytes_total|container_network_transmit_errors_total|container_network_transmit_packets_dropped_total|container_network_transmit_packets_total)"}'
- '{job=~"kubelet", namespace="nvcf-backend", pod=~".*fake-instance-id.*", container=~"inference|task|POD|", __name__=~"(container_cpu_cfs_throttled_periods_total|container_cpu_cfs_throttled_seconds_total|container_cpu_usage_seconds_total|container_memory_cache|container_memory_rss|container_memory_swap|container_memory_usage_bytes|container_memory_working_set_bytes|container_fs_limit_bytes|container_fs_usage_bytes|container_fs_reads_bytes_total|container_fs_reads_total|container_fs_writes_bytes_total|container_fs_writes_total|container_network_receive_bytes_total|container_network_receive_errors_total|container_network_receive_packets_dropped_total|container_network_receive_packets_total|container_network_transmit_bytes_total|container_network_transmit_errors_total|container_network_transmit_packets_dropped_total|container_network_transmit_packets_total)"}'
scrape_interval: 30s
scrape_timeout: 25s
static_configs:
Expand Down Expand Up @@ -97,7 +97,7 @@ receivers:
- job_name: opentelemetry-collector
metric_relabel_configs:
- action: keep
regex: (otelcol_receiver_refused_metric_points_total|otelcol_receiver_refused_spans_total|otelcol_receiver_refused_log_records_total|otelcol_receiver_accepted_metric_points_total|otelcol_receiver_accepted_spans_total|otelcol_receiver_accepted_log_records_total|otelcol_exporter_sent_metric_points_total|otelcol_exporter_sent_spans_total|otelcol_exporter_sent_log_records_total|otelcol_exporter_send_failed_metric_points_total|otelcol_exporter_send_failed_spans_total|otelcol_exporter_send_failed_log_records_total|otelcol_exporter_enqueue_failed_metric_points_total|otelcol_exporter_enqueue_failed_spans_total|otelcol_exporter_enqueue_failed_log_records_total|otelcol_exporter_queue_size|otelcol_exporter_queue_capacity|otelcol_http_client_request_duration_seconds.*|otelcol_rpc_client_call_duration_seconds.*|otelcol_processor_incoming_items_total|otelcol_processor_outgoing_items_total)
regex: (otelcol_.*)
source_labels:
- __name__
scrape_interval: 30s
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -57,7 +57,7 @@ receivers:
metrics_path: /federate
params:
match[]:
- '{job=~"kubelet", namespace="nvcf-backend", pod=~".*fake-instance-id.*", container=~"inference|task|", __name__=~"(container_cpu_cfs_throttled_periods_total|container_cpu_cfs_throttled_seconds_total|container_cpu_usage_seconds_total|container_memory_cache|container_memory_rss|container_memory_swap|container_memory_usage_bytes|container_memory_working_set_bytes|container_fs_limit_bytes|container_fs_usage_bytes|container_fs_reads_bytes_total|container_fs_reads_total|container_fs_writes_bytes_total|container_fs_writes_total|container_network_receive_bytes_total|container_network_receive_errors_total|container_network_receive_packets_dropped_total|container_network_receive_packets_total|container_network_transmit_bytes_total|container_network_transmit_errors_total|container_network_transmit_packets_dropped_total|container_network_transmit_packets_total)"}'
- '{job=~"kubelet", namespace="nvcf-backend", pod=~".*fake-instance-id.*", container=~"inference|task|POD|", __name__=~"(container_cpu_cfs_throttled_periods_total|container_cpu_cfs_throttled_seconds_total|container_cpu_usage_seconds_total|container_memory_cache|container_memory_rss|container_memory_swap|container_memory_usage_bytes|container_memory_working_set_bytes|container_fs_limit_bytes|container_fs_usage_bytes|container_fs_reads_bytes_total|container_fs_reads_total|container_fs_writes_bytes_total|container_fs_writes_total|container_network_receive_bytes_total|container_network_receive_errors_total|container_network_receive_packets_dropped_total|container_network_receive_packets_total|container_network_transmit_bytes_total|container_network_transmit_errors_total|container_network_transmit_packets_dropped_total|container_network_transmit_packets_total)"}'
scrape_interval: 30s
scrape_timeout: 25s
static_configs:
Expand Down Expand Up @@ -97,7 +97,7 @@ receivers:
- job_name: opentelemetry-collector
metric_relabel_configs:
- action: keep
regex: (otelcol_receiver_refused_metric_points_total|otelcol_receiver_refused_spans_total|otelcol_receiver_refused_log_records_total|otelcol_receiver_accepted_metric_points_total|otelcol_receiver_accepted_spans_total|otelcol_receiver_accepted_log_records_total|otelcol_exporter_sent_metric_points_total|otelcol_exporter_sent_spans_total|otelcol_exporter_sent_log_records_total|otelcol_exporter_send_failed_metric_points_total|otelcol_exporter_send_failed_spans_total|otelcol_exporter_send_failed_log_records_total|otelcol_exporter_enqueue_failed_metric_points_total|otelcol_exporter_enqueue_failed_spans_total|otelcol_exporter_enqueue_failed_log_records_total|otelcol_exporter_queue_size|otelcol_exporter_queue_capacity|otelcol_http_client_request_duration_seconds.*|otelcol_rpc_client_call_duration_seconds.*|otelcol_processor_incoming_items_total|otelcol_processor_outgoing_items_total)
regex: (otelcol_.*)
source_labels:
- __name__
scrape_interval: 30s
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -57,7 +57,7 @@ receivers:
metrics_path: /federate
params:
match[]:
- '{job=~"kubelet", namespace="nvcf-backend", pod=~".*fake-instance-id.*", container=~"inference|task|", __name__=~"(container_cpu_cfs_throttled_periods_total|container_cpu_cfs_throttled_seconds_total|container_cpu_usage_seconds_total|container_memory_cache|container_memory_rss|container_memory_swap|container_memory_usage_bytes|container_memory_working_set_bytes|container_fs_limit_bytes|container_fs_usage_bytes|container_fs_reads_bytes_total|container_fs_reads_total|container_fs_writes_bytes_total|container_fs_writes_total|container_network_receive_bytes_total|container_network_receive_errors_total|container_network_receive_packets_dropped_total|container_network_receive_packets_total|container_network_transmit_bytes_total|container_network_transmit_errors_total|container_network_transmit_packets_dropped_total|container_network_transmit_packets_total)"}'
- '{job=~"kubelet", namespace="nvcf-backend", pod=~".*fake-instance-id.*", container=~"inference|task|POD|", __name__=~"(container_cpu_cfs_throttled_periods_total|container_cpu_cfs_throttled_seconds_total|container_cpu_usage_seconds_total|container_memory_cache|container_memory_rss|container_memory_swap|container_memory_usage_bytes|container_memory_working_set_bytes|container_fs_limit_bytes|container_fs_usage_bytes|container_fs_reads_bytes_total|container_fs_reads_total|container_fs_writes_bytes_total|container_fs_writes_total|container_network_receive_bytes_total|container_network_receive_errors_total|container_network_receive_packets_dropped_total|container_network_receive_packets_total|container_network_transmit_bytes_total|container_network_transmit_errors_total|container_network_transmit_packets_dropped_total|container_network_transmit_packets_total)"}'
scrape_interval: 30s
scrape_timeout: 25s
static_configs:
Expand Down Expand Up @@ -97,7 +97,7 @@ receivers:
- job_name: opentelemetry-collector
metric_relabel_configs:
- action: keep
regex: (otelcol_receiver_refused_metric_points_total|otelcol_receiver_refused_spans_total|otelcol_receiver_refused_log_records_total|otelcol_receiver_accepted_metric_points_total|otelcol_receiver_accepted_spans_total|otelcol_receiver_accepted_log_records_total|otelcol_exporter_sent_metric_points_total|otelcol_exporter_sent_spans_total|otelcol_exporter_sent_log_records_total|otelcol_exporter_send_failed_metric_points_total|otelcol_exporter_send_failed_spans_total|otelcol_exporter_send_failed_log_records_total|otelcol_exporter_enqueue_failed_metric_points_total|otelcol_exporter_enqueue_failed_spans_total|otelcol_exporter_enqueue_failed_log_records_total|otelcol_exporter_queue_size|otelcol_exporter_queue_capacity|otelcol_http_client_request_duration_seconds.*|otelcol_rpc_client_call_duration_seconds.*|otelcol_processor_incoming_items_total|otelcol_processor_outgoing_items_total)
regex: (otelcol_.*)
source_labels:
- __name__
scrape_interval: 30s
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -57,7 +57,7 @@ receivers:
metrics_path: /federate
params:
match[]:
- '{job=~"kubelet", namespace="nvcf-backend", pod=~".*fake-instance-id.*", container=~"inference|task|", __name__=~"(container_cpu_cfs_throttled_periods_total|container_cpu_cfs_throttled_seconds_total|container_cpu_usage_seconds_total|container_memory_cache|container_memory_rss|container_memory_swap|container_memory_usage_bytes|container_memory_working_set_bytes|container_fs_limit_bytes|container_fs_usage_bytes|container_fs_reads_bytes_total|container_fs_reads_total|container_fs_writes_bytes_total|container_fs_writes_total|container_network_receive_bytes_total|container_network_receive_errors_total|container_network_receive_packets_dropped_total|container_network_receive_packets_total|container_network_transmit_bytes_total|container_network_transmit_errors_total|container_network_transmit_packets_dropped_total|container_network_transmit_packets_total)"}'
- '{job=~"kubelet", namespace="nvcf-backend", pod=~".*fake-instance-id.*", container=~"inference|task|POD|", __name__=~"(container_cpu_cfs_throttled_periods_total|container_cpu_cfs_throttled_seconds_total|container_cpu_usage_seconds_total|container_memory_cache|container_memory_rss|container_memory_swap|container_memory_usage_bytes|container_memory_working_set_bytes|container_fs_limit_bytes|container_fs_usage_bytes|container_fs_reads_bytes_total|container_fs_reads_total|container_fs_writes_bytes_total|container_fs_writes_total|container_network_receive_bytes_total|container_network_receive_errors_total|container_network_receive_packets_dropped_total|container_network_receive_packets_total|container_network_transmit_bytes_total|container_network_transmit_errors_total|container_network_transmit_packets_dropped_total|container_network_transmit_packets_total)"}'
scrape_interval: 30s
scrape_timeout: 25s
static_configs:
Expand Down Expand Up @@ -97,7 +97,7 @@ receivers:
- job_name: opentelemetry-collector
metric_relabel_configs:
- action: keep
regex: (otelcol_receiver_refused_metric_points_total|otelcol_receiver_refused_spans_total|otelcol_receiver_refused_log_records_total|otelcol_receiver_accepted_metric_points_total|otelcol_receiver_accepted_spans_total|otelcol_receiver_accepted_log_records_total|otelcol_exporter_sent_metric_points_total|otelcol_exporter_sent_spans_total|otelcol_exporter_sent_log_records_total|otelcol_exporter_send_failed_metric_points_total|otelcol_exporter_send_failed_spans_total|otelcol_exporter_send_failed_log_records_total|otelcol_exporter_enqueue_failed_metric_points_total|otelcol_exporter_enqueue_failed_spans_total|otelcol_exporter_enqueue_failed_log_records_total|otelcol_exporter_queue_size|otelcol_exporter_queue_capacity|otelcol_http_client_request_duration_seconds.*|otelcol_rpc_client_call_duration_seconds.*|otelcol_processor_incoming_items_total|otelcol_processor_outgoing_items_total)
regex: (otelcol_.*)
source_labels:
- __name__
scrape_interval: 30s
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -57,7 +57,7 @@ receivers:
metrics_path: /federate
params:
match[]:
- '{job=~"kubelet", namespace="nvcf-backend", pod=~".*fake-instance-id.*", container=~"inference|task|", __name__=~"(container_cpu_cfs_throttled_periods_total|container_cpu_cfs_throttled_seconds_total|container_cpu_usage_seconds_total|container_memory_cache|container_memory_rss|container_memory_swap|container_memory_usage_bytes|container_memory_working_set_bytes|container_fs_limit_bytes|container_fs_usage_bytes|container_fs_reads_bytes_total|container_fs_reads_total|container_fs_writes_bytes_total|container_fs_writes_total|container_network_receive_bytes_total|container_network_receive_errors_total|container_network_receive_packets_dropped_total|container_network_receive_packets_total|container_network_transmit_bytes_total|container_network_transmit_errors_total|container_network_transmit_packets_dropped_total|container_network_transmit_packets_total)"}'
- '{job=~"kubelet", namespace="nvcf-backend", pod=~".*fake-instance-id.*", container=~"inference|task|POD|", __name__=~"(container_cpu_cfs_throttled_periods_total|container_cpu_cfs_throttled_seconds_total|container_cpu_usage_seconds_total|container_memory_cache|container_memory_rss|container_memory_swap|container_memory_usage_bytes|container_memory_working_set_bytes|container_fs_limit_bytes|container_fs_usage_bytes|container_fs_reads_bytes_total|container_fs_reads_total|container_fs_writes_bytes_total|container_fs_writes_total|container_network_receive_bytes_total|container_network_receive_errors_total|container_network_receive_packets_dropped_total|container_network_receive_packets_total|container_network_transmit_bytes_total|container_network_transmit_errors_total|container_network_transmit_packets_dropped_total|container_network_transmit_packets_total)"}'
scrape_interval: 30s
scrape_timeout: 25s
static_configs:
Expand Down Expand Up @@ -97,7 +97,7 @@ receivers:
- job_name: opentelemetry-collector
metric_relabel_configs:
- action: keep
regex: (otelcol_receiver_refused_metric_points_total|otelcol_receiver_refused_spans_total|otelcol_receiver_refused_log_records_total|otelcol_receiver_accepted_metric_points_total|otelcol_receiver_accepted_spans_total|otelcol_receiver_accepted_log_records_total|otelcol_exporter_sent_metric_points_total|otelcol_exporter_sent_spans_total|otelcol_exporter_sent_log_records_total|otelcol_exporter_send_failed_metric_points_total|otelcol_exporter_send_failed_spans_total|otelcol_exporter_send_failed_log_records_total|otelcol_exporter_enqueue_failed_metric_points_total|otelcol_exporter_enqueue_failed_spans_total|otelcol_exporter_enqueue_failed_log_records_total|otelcol_exporter_queue_size|otelcol_exporter_queue_capacity|otelcol_http_client_request_duration_seconds.*|otelcol_rpc_client_call_duration_seconds.*|otelcol_processor_incoming_items_total|otelcol_processor_outgoing_items_total)
regex: (otelcol_.*)
source_labels:
- __name__
scrape_interval: 30s
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -57,7 +57,7 @@ receivers:
metrics_path: /federate
params:
match[]:
- '{job=~"kubelet", namespace="nvcf-backend", pod=~".*fake-instance-id.*", container=~"inference|task|", __name__=~"(container_cpu_cfs_throttled_periods_total|container_cpu_cfs_throttled_seconds_total|container_cpu_usage_seconds_total|container_memory_cache|container_memory_rss|container_memory_swap|container_memory_usage_bytes|container_memory_working_set_bytes|container_fs_limit_bytes|container_fs_usage_bytes|container_fs_reads_bytes_total|container_fs_reads_total|container_fs_writes_bytes_total|container_fs_writes_total|container_network_receive_bytes_total|container_network_receive_errors_total|container_network_receive_packets_dropped_total|container_network_receive_packets_total|container_network_transmit_bytes_total|container_network_transmit_errors_total|container_network_transmit_packets_dropped_total|container_network_transmit_packets_total)"}'
- '{job=~"kubelet", namespace="nvcf-backend", pod=~".*fake-instance-id.*", container=~"inference|task|POD|", __name__=~"(container_cpu_cfs_throttled_periods_total|container_cpu_cfs_throttled_seconds_total|container_cpu_usage_seconds_total|container_memory_cache|container_memory_rss|container_memory_swap|container_memory_usage_bytes|container_memory_working_set_bytes|container_fs_limit_bytes|container_fs_usage_bytes|container_fs_reads_bytes_total|container_fs_reads_total|container_fs_writes_bytes_total|container_fs_writes_total|container_network_receive_bytes_total|container_network_receive_errors_total|container_network_receive_packets_dropped_total|container_network_receive_packets_total|container_network_transmit_bytes_total|container_network_transmit_errors_total|container_network_transmit_packets_dropped_total|container_network_transmit_packets_total)"}'
scrape_interval: 30s
scrape_timeout: 25s
static_configs:
Expand Down Expand Up @@ -97,7 +97,7 @@ receivers:
- job_name: opentelemetry-collector
metric_relabel_configs:
- action: keep
regex: (otelcol_receiver_refused_metric_points_total|otelcol_receiver_refused_spans_total|otelcol_receiver_refused_log_records_total|otelcol_receiver_accepted_metric_points_total|otelcol_receiver_accepted_spans_total|otelcol_receiver_accepted_log_records_total|otelcol_exporter_sent_metric_points_total|otelcol_exporter_sent_spans_total|otelcol_exporter_sent_log_records_total|otelcol_exporter_send_failed_metric_points_total|otelcol_exporter_send_failed_spans_total|otelcol_exporter_send_failed_log_records_total|otelcol_exporter_enqueue_failed_metric_points_total|otelcol_exporter_enqueue_failed_spans_total|otelcol_exporter_enqueue_failed_log_records_total|otelcol_exporter_queue_size|otelcol_exporter_queue_capacity|otelcol_http_client_request_duration_seconds.*|otelcol_rpc_client_call_duration_seconds.*|otelcol_processor_incoming_items_total|otelcol_processor_outgoing_items_total)
regex: (otelcol_.*)
source_labels:
- __name__
scrape_interval: 30s
Expand Down
Loading
Loading