From 99aa1b211ffa70f5d0dbb4b59373ae9ec8a83318 Mon Sep 17 00:00:00 2001 From: Vladimir Iliakov Date: Fri, 6 Nov 2026 08:54:45 +0100 Subject: [PATCH] feat(suse-observability): link monitor hints to the ingestion tuning docs The receiver budget hints still named the removed maxAgents/maxComponents/ maxConnections/maxRelations and hourly variables. The receiver now scales each budget by agent count from the *PerHost settings, and agents over the profile's node limit are rejected outright, so the hints check for limited agents first, then raise the per-agent value, including the HA split path. Hints for monitors covered by a runbook on the "Tune data ingestion for your workload" page now end with a link to that section. The rejected logs hint pointed at the retired docs.stackstate.com site. Refs: https://github.com/StackVista/helm-charts-internal/issues/394 Co-Authored-By: Claude Code --- .../sts-apps-overrun-cpu-request.md.hbs | 4 +- .../includes/generic/sts-java-long-gc.md.hbs | 4 +- ...lickhouse-delayed-insert-throttling.md.hbs | 4 +- .../clickhouse-rejected-insert.md.hbs | 4 +- .../services/correlate/latency.md.hbs | 4 +- .../services/health-sync/latency.md.hbs | 4 +- .../services/kafka-to-es/latency.md.hbs | 2 + ...tel-collector-metric-export-failure.md.hbs | 4 +- ...el-collector-metric-processor-drops.md.hbs | 4 +- ...l-collector-metric-refused-receiver.md.hbs | 4 +- .../otel-collector-span-export-failure.md.hbs | 4 +- ...otel-collector-span-processor-drops.md.hbs | 4 +- ...tel-collector-span-refused-receiver.md.hbs | 4 +- .../receiver/budget-saturation.md.hbs | 50 +++++++++++-------- .../receiver/hourly-budget-saturation.md.hbs | 45 +++++++++++------ .../receiver/http-growing-requests.md.hbs | 4 +- .../services/receiver/memory-limiter.md.hbs | 4 +- .../services/receiver/rejected-logs.md.hbs | 8 +-- .../services/topo-sync/blocked.md.hbs | 4 +- .../topo-sync/internal-latency.md.hbs | 4 +- .../services/topo-sync/latency.md.hbs | 4 +- .../victoria-metrics/slow-insert-rate.md.hbs | 4 +- .../persistentqueue-dropping-data.md.hbs | 4 +- .../remotewrite-samples-dropped.md.hbs | 2 + stackpacks/suse-observability/stackpack.yaml | 2 +- 25 files changed, 126 insertions(+), 59 deletions(-) diff --git a/stackpacks/suse-observability/includes/generic/sts-apps-overrun-cpu-request.md.hbs b/stackpacks/suse-observability/includes/generic/sts-apps-overrun-cpu-request.md.hbs index 46e2919..1f3dd8e 100644 --- a/stackpacks/suse-observability/includes/generic/sts-apps-overrun-cpu-request.md.hbs +++ b/stackpacks/suse-observability/includes/generic/sts-apps-overrun-cpu-request.md.hbs @@ -23,4 +23,6 @@ helm upgrade \ --values values.yaml \ suse-observability \ suse-observability/suse-observability -``` \ No newline at end of file +``` + +For more details, see [How much to add](https://documentation.suse.com/cloudnative/suse-observability/latest/en/setup/install-stackstate/data-ingestion-pipeline.html#_how_much_to_add). diff --git a/stackpacks/suse-observability/includes/generic/sts-java-long-gc.md.hbs b/stackpacks/suse-observability/includes/generic/sts-java-long-gc.md.hbs index b4edc6c..c51d4b3 100644 --- a/stackpacks/suse-observability/includes/generic/sts-java-long-gc.md.hbs +++ b/stackpacks/suse-observability/includes/generic/sts-java-long-gc.md.hbs @@ -19,4 +19,6 @@ helm upgrade \ --values values.yaml \ suse-observability \ suse-observability/suse-observability -``` \ No newline at end of file +``` + +For more details, see [How much to add](https://documentation.suse.com/cloudnative/suse-observability/latest/en/setup/install-stackstate/data-ingestion-pipeline.html#_how_much_to_add). diff --git a/stackpacks/suse-observability/includes/services/clickhouse/clickhouse-delayed-insert-throttling.md.hbs b/stackpacks/suse-observability/includes/services/clickhouse/clickhouse-delayed-insert-throttling.md.hbs index a7bb60d..0d871df 100644 --- a/stackpacks/suse-observability/includes/services/clickhouse/clickhouse-delayed-insert-throttling.md.hbs +++ b/stackpacks/suse-observability/includes/services/clickhouse/clickhouse-delayed-insert-throttling.md.hbs @@ -1,2 +1,4 @@ ClickHouse has INSERT statements that are throttled due to high number of active data parts for partition in a MergeTree, -please decrease INSERT frequency https://clickhouse.com/docs/en/development/architecture/#merge-tree \ No newline at end of file +please decrease INSERT frequency https://clickhouse.com/docs/en/development/architecture/#merge-tree + +For more details, see [Traces are missing](https://documentation.suse.com/cloudnative/suse-observability/latest/en/setup/install-stackstate/data-ingestion-pipeline.html#_traces_are_missing). diff --git a/stackpacks/suse-observability/includes/services/clickhouse/clickhouse-rejected-insert.md.hbs b/stackpacks/suse-observability/includes/services/clickhouse/clickhouse-rejected-insert.md.hbs index 48345fd..0b34ebe 100644 --- a/stackpacks/suse-observability/includes/services/clickhouse/clickhouse-rejected-insert.md.hbs +++ b/stackpacks/suse-observability/includes/services/clickhouse/clickhouse-rejected-insert.md.hbs @@ -2,4 +2,6 @@ ClickHouse has INSERT statements that are rejected due to high number of active please decrease INSERT frequency: - [MergeTreeArchitecture](https://clickhouse.com/docs/en/development/architecture/#merge-tree) - [system.part_log](https://clickhouse.com/docs/en/operations/system-tables/part_log) -- [system.merge_tree_settings](https://clickhouse.com/docs/en/operations/system-tables/merge_tree_settings) \ No newline at end of file +- [system.merge_tree_settings](https://clickhouse.com/docs/en/operations/system-tables/merge_tree_settings) + +For more details, see [Traces are missing](https://documentation.suse.com/cloudnative/suse-observability/latest/en/setup/install-stackstate/data-ingestion-pipeline.html#_traces_are_missing). diff --git a/stackpacks/suse-observability/includes/services/correlate/latency.md.hbs b/stackpacks/suse-observability/includes/services/correlate/latency.md.hbs index 18c2215..16cb752 100644 --- a/stackpacks/suse-observability/includes/services/correlate/latency.md.hbs +++ b/stackpacks/suse-observability/includes/services/correlate/latency.md.hbs @@ -3,4 +3,6 @@ When the latency of the transformation process is high we might have components not present or arriving late. ### Investigate -There are a few potential causes of the high latency. To identify the root cause, please contact SUSE Observability [support](https://www.stackstate.com/company/contact-us/). \ No newline at end of file +There are a few potential causes of the high latency. To identify the root cause, please contact SUSE Observability [support](https://www.stackstate.com/company/contact-us/). + +For more details, see [Process and connection data is delayed](https://documentation.suse.com/cloudnative/suse-observability/latest/en/setup/install-stackstate/data-ingestion-pipeline.html#_process_and_connection_data_is_delayed). diff --git a/stackpacks/suse-observability/includes/services/health-sync/latency.md.hbs b/stackpacks/suse-observability/includes/services/health-sync/latency.md.hbs index df11f62..651e949 100644 --- a/stackpacks/suse-observability/includes/services/health-sync/latency.md.hbs +++ b/stackpacks/suse-observability/includes/services/health-sync/latency.md.hbs @@ -48,4 +48,6 @@ helm upgrade \ --values values.yaml \ suse-observability \ suse-observability/suse-observability -``` \ No newline at end of file +``` + +For more details, see [Health states are delayed](https://documentation.suse.com/cloudnative/suse-observability/latest/en/setup/install-stackstate/data-ingestion-pipeline.html#_health_states_are_delayed). diff --git a/stackpacks/suse-observability/includes/services/kafka-to-es/latency.md.hbs b/stackpacks/suse-observability/includes/services/kafka-to-es/latency.md.hbs index 87609d0..b99afa3 100644 --- a/stackpacks/suse-observability/includes/services/kafka-to-es/latency.md.hbs +++ b/stackpacks/suse-observability/includes/services/kafka-to-es/latency.md.hbs @@ -49,3 +49,5 @@ helm upgrade \ suse-observability \ suse-observability/suse-observability ``` + +For more details, see [Events are delayed](https://documentation.suse.com/cloudnative/suse-observability/latest/en/setup/install-stackstate/data-ingestion-pipeline.html#_events_are_delayed). diff --git a/stackpacks/suse-observability/includes/services/otel-collector/otel-collector-metric-export-failure.md.hbs b/stackpacks/suse-observability/includes/services/otel-collector/otel-collector-metric-export-failure.md.hbs index e464b31..6986b82 100644 --- a/stackpacks/suse-observability/includes/services/otel-collector/otel-collector-metric-export-failure.md.hbs +++ b/stackpacks/suse-observability/includes/services/otel-collector/otel-collector-metric-export-failure.md.hbs @@ -14,4 +14,6 @@ Potential Reasons: - **Batch Size and Interval**: Adjust batch size and sending interval settings in your exporter configuration to manage data flow better. Smaller batches and shorter intervals might help with overloaded endpoints. - **Queue Management**: Monitor metrics like `stackstate_otelcol_exporter_queue_size` and `stackstate_otelcol_exporter_queue_capacity`. If the queue is often full, consider increasing its capacity or adjusting batch sizes/intervals. -You may find more details by checking [logs](/#/components/{{ componentUrnForUrl }}#logs). \ No newline at end of file +You may find more details by checking [logs](/#/components/{{ componentUrnForUrl }}#logs). + +For more details, see [Metrics are delayed or missing](https://documentation.suse.com/cloudnative/suse-observability/latest/en/setup/install-stackstate/data-ingestion-pipeline.html#_metrics_are_delayed_or_missing). diff --git a/stackpacks/suse-observability/includes/services/otel-collector/otel-collector-metric-processor-drops.md.hbs b/stackpacks/suse-observability/includes/services/otel-collector/otel-collector-metric-processor-drops.md.hbs index 12e7a34..eb59396 100644 --- a/stackpacks/suse-observability/includes/services/otel-collector/otel-collector-metric-processor-drops.md.hbs +++ b/stackpacks/suse-observability/includes/services/otel-collector/otel-collector-metric-processor-drops.md.hbs @@ -15,4 +15,6 @@ Potential Reasons: - Other Potential Causes: - **Bugs in the processor**: While less likely, consider checking for known issues or bugs in the specific processor you're using. -You may find more details by checking [logs](/#/components/{{ componentUrnForUrl }}#logs). \ No newline at end of file +You may find more details by checking [logs](/#/components/{{ componentUrnForUrl }}#logs). + +For more details, see [Metrics are delayed or missing](https://documentation.suse.com/cloudnative/suse-observability/latest/en/setup/install-stackstate/data-ingestion-pipeline.html#_metrics_are_delayed_or_missing). diff --git a/stackpacks/suse-observability/includes/services/otel-collector/otel-collector-metric-refused-receiver.md.hbs b/stackpacks/suse-observability/includes/services/otel-collector/otel-collector-metric-refused-receiver.md.hbs index bc00015..1f5ffa6 100644 --- a/stackpacks/suse-observability/includes/services/otel-collector/otel-collector-metric-refused-receiver.md.hbs +++ b/stackpacks/suse-observability/includes/services/otel-collector/otel-collector-metric-refused-receiver.md.hbs @@ -16,4 +16,6 @@ Common Reasons: - **Connectivity problems**: Ensure the collector can establish and maintain a connection to the receiving endpoint (e.g., backend). Connectivity issues might prevent metrics delivery. - **Firewall restrictions**: Check for any firewall rules that might block communication between the collector and the receiving endpoint. -You may find more details by checking [logs](/#/components/{{ componentUrnForUrl }}#logs). \ No newline at end of file +You may find more details by checking [logs](/#/components/{{ componentUrnForUrl }}#logs). + +For more details, see [Metrics are delayed or missing](https://documentation.suse.com/cloudnative/suse-observability/latest/en/setup/install-stackstate/data-ingestion-pipeline.html#_metrics_are_delayed_or_missing). diff --git a/stackpacks/suse-observability/includes/services/otel-collector/otel-collector-span-export-failure.md.hbs b/stackpacks/suse-observability/includes/services/otel-collector/otel-collector-span-export-failure.md.hbs index 884f881..0f87666 100644 --- a/stackpacks/suse-observability/includes/services/otel-collector/otel-collector-span-export-failure.md.hbs +++ b/stackpacks/suse-observability/includes/services/otel-collector/otel-collector-span-export-failure.md.hbs @@ -14,4 +14,6 @@ Potential Reasons: - **Batch Size and Interval**: Adjust batch size and sending interval settings in your exporter configuration to manage data flow better. Smaller batches and shorter intervals might help with overloaded backends. - **Queue Management**: Monitor metrics like `stackstate_otelcol_exporter_queue_size` and `stackstate_otelcol_exporter_queue_capacity`. If the queue is often full, consider increasing its capacity or adjusting batch sizes/intervals. -You may find more details by checking [logs](/#/components/{{ componentUrnForUrl }}#logs). \ No newline at end of file +You may find more details by checking [logs](/#/components/{{ componentUrnForUrl }}#logs). + +For more details, see [Traces are missing](https://documentation.suse.com/cloudnative/suse-observability/latest/en/setup/install-stackstate/data-ingestion-pipeline.html#_traces_are_missing). diff --git a/stackpacks/suse-observability/includes/services/otel-collector/otel-collector-span-processor-drops.md.hbs b/stackpacks/suse-observability/includes/services/otel-collector/otel-collector-span-processor-drops.md.hbs index 86cac12..cbd1867 100644 --- a/stackpacks/suse-observability/includes/services/otel-collector/otel-collector-span-processor-drops.md.hbs +++ b/stackpacks/suse-observability/includes/services/otel-collector/otel-collector-span-processor-drops.md.hbs @@ -15,4 +15,6 @@ Potential Reasons: - Other Potential Causes: - **Bugs in the processor**: While less likely, consider checking for known issues or bugs in the specific processor you're using. -You may find more details by checking [logs](/#/components/{{ componentUrnForUrl }}#logs). \ No newline at end of file +You may find more details by checking [logs](/#/components/{{ componentUrnForUrl }}#logs). + +For more details, see [Traces are missing](https://documentation.suse.com/cloudnative/suse-observability/latest/en/setup/install-stackstate/data-ingestion-pipeline.html#_traces_are_missing). diff --git a/stackpacks/suse-observability/includes/services/otel-collector/otel-collector-span-refused-receiver.md.hbs b/stackpacks/suse-observability/includes/services/otel-collector/otel-collector-span-refused-receiver.md.hbs index b4e3ba9..1716178 100644 --- a/stackpacks/suse-observability/includes/services/otel-collector/otel-collector-span-refused-receiver.md.hbs +++ b/stackpacks/suse-observability/includes/services/otel-collector/otel-collector-span-refused-receiver.md.hbs @@ -15,4 +15,6 @@ Common Reasons: - **Connectivity problems**: Ensure the collector can establish and maintain a connection to the receiving endpoint (e.g., backend). Connectivity issues might prevent span delivery. - **Firewall restrictions**: Check for any firewall rules that might block communication between the collector and the receiving endpoint. -You may find more details by checking [logs](/#/components/{{ componentUrnForUrl }}#logs). \ No newline at end of file +You may find more details by checking [logs](/#/components/{{ componentUrnForUrl }}#logs). + +For more details, see [Traces are missing](https://documentation.suse.com/cloudnative/suse-observability/latest/en/setup/install-stackstate/data-ingestion-pipeline.html#_traces_are_missing). diff --git a/stackpacks/suse-observability/includes/services/receiver/budget-saturation.md.hbs b/stackpacks/suse-observability/includes/services/receiver/budget-saturation.md.hbs index d3ba362..77643db 100644 --- a/stackpacks/suse-observability/includes/services/receiver/budget-saturation.md.hbs +++ b/stackpacks/suse-observability/includes/services/receiver/budget-saturation.md.hbs @@ -1,28 +1,34 @@ -Element budget **nearly saturated for `{{ labels.element_type }}`**, has high unique element budget saturation level. When the budget is saturated data starts being dropped which translates in missing topology or metrics. +The unique element budget for `{{ labels.element_type }}` is **nearly saturated**. When the budget is saturated, the receiver drops data for that element type, which shows up as missing topology or connections. -### Increase the budget of elements allowed -1. We can control the budget by setting extra environment variables for the receiver pod. -Here are the default settings: +Each budget is a value per agent multiplied by the number of agents, so it grows when you add agents. + +### Check for limited agents +The sizing profile limits how many nodes you can observe. Agents above that limit are marked as limited. The receiver rejects their process, container and connection data, and they do not add to the budgets. Raising a budget does not help limited agents. + +1. Run `sts agent list`. The last line shows how many agents are active, limited and stale. +2. If any agents are limited, move to the next sizing profile. A profile change can change volume sizes and the Kafka partition count, so it takes more than a `helm upgrade`. + +### Raise the budget per agent +If no agents are limited, the agents send more elements than the default budget per agent allows, for example because they run many short-lived pods or open many connections. + +1. Find the variable for the saturated element type: + +| element type | environment variable | +|--------------|----------------------| +| component | `CONFIG_FORCE_stackstate_receiver_processAgent_maxComponentsPerHost` | +| relation | `CONFIG_FORCE_stackstate_receiver_processAgent_maxRelationsPerHost` | +| connection | `CONFIG_FORCE_stackstate_receiver_processAgent_maxConnectionObservationsPerHost` | + +2. The current value per agent is `stackstate_stackstate_receiver_unique_element_passed_max` for this element type divided by `stackstate_stackstate_receiver_unique_element_passed_count{element_type="agent"}`. Raise it by 50% in your `values.yaml`, for example: ``` +stackstate: + components: receiver: extraEnv: open: - CONFIG_FORCE_stackstate_receiver_processAgent_maxAgents: "2000" - CONFIG_FORCE_stackstate_receiver_processAgent_maxComponents: "5000" - CONFIG_FORCE_stackstate_receiver_processAgent_maxConnections: "150000" - CONFIG_FORCE_stackstate_receiver_processAgent_maxRelations: "15000" + CONFIG_FORCE_stackstate_receiver_processAgent_maxComponentsPerHost: "450" ``` - -2. Identify which budget got saturated and increment the right environment variable to allow more elements to be passed: - -| element type | environment variable | -|--------------|--------------------------------------------------------------| -| agent | CONFIG_FORCE_stackstate_receiver_processAgent_maxAgents | -| component | CONFIG_FORCE_stackstate_receiver_processAgent_maxComponents | -| connection | CONFIG_FORCE_stackstate_receiver_processAgent_maxConnections | -| relation | CONFIG_FORCE_stackstate_receiver_processAgent_maxRelations | - -Keep in mind that allowing more elements to be processed will have an impact on downstream services such as the Correlator and the Topology Sync. +On HA profiles, set the variable under `stackstate.components.receiver.split.processAgent.extraEnv.open`. 3. Redeploy via a `helm upgrade` including any other values files or extra settings you applied previously ``` @@ -32,4 +38,8 @@ helm upgrade \ --values values.yaml \ suse-observability \ suse-observability/suse-observability -``` \ No newline at end of file +``` + +A higher budget increases the load on Correlate and Topology Sync, so watch their latency afterwards. + +For more details, see [Receiver element budget saturated](https://documentation.suse.com/cloudnative/suse-observability/latest/en/setup/install-stackstate/data-ingestion-pipeline.html#_receiver_element_budget_saturated). diff --git a/stackpacks/suse-observability/includes/services/receiver/hourly-budget-saturation.md.hbs b/stackpacks/suse-observability/includes/services/receiver/hourly-budget-saturation.md.hbs index d38f1a4..1323423 100644 --- a/stackpacks/suse-observability/includes/services/receiver/hourly-budget-saturation.md.hbs +++ b/stackpacks/suse-observability/includes/services/receiver/hourly-budget-saturation.md.hbs @@ -1,24 +1,33 @@ -Element budget **nearly saturated for `{{ labels.element_type }}`**, has high element hourly budget saturation level. When the budget is saturated data starts being dropped which translates in missing topology or metrics. +The hourly budget for new `{{ labels.element_type }}` elements is **nearly saturated**. When the budget is saturated, the receiver drops new elements of that type for the rest of the hour, which shows up as missing topology. -### Increase the budget of elements allowed -1. We can control the budget by setting extra environment variables for the receiver pod. -Here are the default settings: +Each budget is a value per agent multiplied by the number of agents, so it grows when you add agents. + +### Check for limited agents +The sizing profile limits how many nodes you can observe. Agents above that limit are marked as limited. The receiver rejects their process, container and connection data, and they do not add to the budgets. Raising a budget does not help limited agents. + +1. Run `sts agent list`. The last line shows how many agents are active, limited and stale. +2. If any agents are limited, move to the next sizing profile. A profile change can change volume sizes and the Kafka partition count, so it takes more than a `helm upgrade`. + +### Raise the budget per agent +If no agents are limited, the agents create more new elements per hour than the default budget per agent allows, for example because they run many short-lived pods. + +1. Find the variable for the saturated element type: + +| element type | environment variable | +|--------------|----------------------| +| component | `CONFIG_FORCE_stackstate_receiver_processAgent_maxNewComponentsHourlyPerHost` | +| relation | `CONFIG_FORCE_stackstate_receiver_processAgent_maxNewRelationsHourlyPerHost` | + +2. Raise the value by 50% in your `values.yaml`, for example: ``` +stackstate: + components: receiver: extraEnv: open: - CONFIG_FORCE_stackstate_receiver_processAgent_maxNewComponentsHourly: "2000" - CONFIG_FORCE_stackstate_receiver_processAgent_maxNewRelationsHourly: "5000" + CONFIG_FORCE_stackstate_receiver_processAgent_maxNewComponentsHourlyPerHost: "150" ``` - -2. Identify which budget got saturated and increment the right environment variable to allow more elements to be passed: - -| element type | environment variable | -|--------------|--------------------------------------------------------------| -| component | CONFIG_FORCE_stackstate_receiver_processAgent_maxNewComponentsHourly | -| relation | CONFIG_FORCE_stackstate_receiver_processAgent_maxNewRelationsHourly | - -Keep in mind that allowing more elements to be processed will have an impact on downstream services such as the Correlator and the Topology Sync. +On HA profiles, set the variable under `stackstate.components.receiver.split.processAgent.extraEnv.open`. 3. Redeploy via a `helm upgrade` including any other values files or extra settings you applied previously ``` @@ -28,4 +37,8 @@ helm upgrade \ --values values.yaml \ suse-observability \ suse-observability/suse-observability -``` \ No newline at end of file +``` + +A higher budget increases the load on Correlate and Topology Sync, so watch their latency afterwards. + +For more details, see [Receiver element budget saturated](https://documentation.suse.com/cloudnative/suse-observability/latest/en/setup/install-stackstate/data-ingestion-pipeline.html#_receiver_element_budget_saturated). diff --git a/stackpacks/suse-observability/includes/services/receiver/http-growing-requests.md.hbs b/stackpacks/suse-observability/includes/services/receiver/http-growing-requests.md.hbs index 20ce4f5..c8a8144 100644 --- a/stackpacks/suse-observability/includes/services/receiver/http-growing-requests.md.hbs +++ b/stackpacks/suse-observability/includes/services/receiver/http-growing-requests.md.hbs @@ -8,4 +8,6 @@ This either means that there is a huge and sudden increase in load but much more ``` kubectl delete pod {{ labels.pod_name }} -n {{ labels.namespace }} ``` -4. After restart check the same charts again for the next 10 minutes to make sure issue is fixed. \ No newline at end of file +4. After restart check the same charts again for the next 10 minutes to make sure issue is fixed. + +For more details, see [Receiver rejects data or requests time out](https://documentation.suse.com/cloudnative/suse-observability/latest/en/setup/install-stackstate/data-ingestion-pipeline.html#_receiver_rejects_data_or_requests_time_out). diff --git a/stackpacks/suse-observability/includes/services/receiver/memory-limiter.md.hbs b/stackpacks/suse-observability/includes/services/receiver/memory-limiter.md.hbs index e3bf7e1..6a6477b 100644 --- a/stackpacks/suse-observability/includes/services/receiver/memory-limiter.md.hbs +++ b/stackpacks/suse-observability/includes/services/receiver/memory-limiter.md.hbs @@ -34,4 +34,6 @@ helm upgrade \ --values values.yaml \ suse-observability \ suse-observability/suse-observability -``` \ No newline at end of file +``` + +For more details, see [Receiver rejects data or requests time out](https://documentation.suse.com/cloudnative/suse-observability/latest/en/setup/install-stackstate/data-ingestion-pipeline.html#_receiver_rejects_data_or_requests_time_out). diff --git a/stackpacks/suse-observability/includes/services/receiver/rejected-logs.md.hbs b/stackpacks/suse-observability/includes/services/receiver/rejected-logs.md.hbs index 801e7ab..8a72832 100644 --- a/stackpacks/suse-observability/includes/services/receiver/rejected-logs.md.hbs +++ b/stackpacks/suse-observability/includes/services/receiver/rejected-logs.md.hbs @@ -6,7 +6,7 @@ SUSE Observability logs are rejected when one or more log sources (for example p ### Increase Disk Space for ElasticSearch 1. Verify the current ElasticSearch disk space and inspect its configuration to check the current size. - * Verify that the used storage class can be resized. For that please follow our [resizing documentation] https://docs.stackstate.com/self-hosted-setup/data-management/data_retention#resizing-storage + * Verify that the used storage class can be resized. See [Resizing storage](https://documentation.suse.com/cloudnative/suse-observability/latest/en/setup/data-management/data_retention.html#_resizing_storage). 2. Update the values.yaml adding more ``` elasticsearch: @@ -26,7 +26,7 @@ suse-observability \ suse-observability/suse-observability ``` -For more detailed information visit our [data-retention](https://docs.stackstate.com/self-hosted-setup/data-management/data_retention) documentation. +For more detailed information, see [Data retention](https://documentation.suse.com/cloudnative/suse-observability/latest/en/setup/data-management/data_retention.html). ### Decrease retention for logs 1. By default, SUSE Observability sets a 7-day retention for logs @@ -47,4 +47,6 @@ helm upgrade \ --values values.yaml \ suse-observability \ suse-observability/suse-observability -``` \ No newline at end of file +``` + +For more details, see [Logs are missing](https://documentation.suse.com/cloudnative/suse-observability/latest/en/setup/install-stackstate/data-ingestion-pipeline.html#_logs_are_missing). diff --git a/stackpacks/suse-observability/includes/services/topo-sync/blocked.md.hbs b/stackpacks/suse-observability/includes/services/topo-sync/blocked.md.hbs index 8675478..1d5e7e5 100644 --- a/stackpacks/suse-observability/includes/services/topo-sync/blocked.md.hbs +++ b/stackpacks/suse-observability/includes/services/topo-sync/blocked.md.hbs @@ -7,4 +7,6 @@ kubectl delete pod {{ labels.pod_name }} -n {{ labels.namespace }} ``` `Restarting the pod can help by either unblocking the issue or making it more evident in the logs` -2. Inspect the [Logs](/#/components/{{ componentUrnForUrl }}#logs) of the pod in order to find the root cause of the blockage. \ No newline at end of file +2. Inspect the [Logs](/#/components/{{ componentUrnForUrl }}#logs) of the pod in order to find the root cause of the blockage. + +For more details, see [Topology is delayed or components are missing](https://documentation.suse.com/cloudnative/suse-observability/latest/en/setup/install-stackstate/data-ingestion-pipeline.html#_topology_is_delayed_or_components_are_missing). diff --git a/stackpacks/suse-observability/includes/services/topo-sync/internal-latency.md.hbs b/stackpacks/suse-observability/includes/services/topo-sync/internal-latency.md.hbs index bdbaff8..20fc142 100644 --- a/stackpacks/suse-observability/includes/services/topo-sync/internal-latency.md.hbs +++ b/stackpacks/suse-observability/includes/services/topo-sync/internal-latency.md.hbs @@ -53,4 +53,6 @@ suse-observability/suse-observability ### Reduce the frequency of the topology updates. Update the settings of the agent collection of data for integration: `{{ labels.integration_type }}`, -Reducing the frequency of updates will remove pressure on the Topology Synchronization but as well means that the topology data will be less up-to-date as we don't refresh it that often. \ No newline at end of file +Reducing the frequency of updates will remove pressure on the Topology Synchronization but as well means that the topology data will be less up-to-date as we don't refresh it that often. + +For more details, see [Topology is delayed or components are missing](https://documentation.suse.com/cloudnative/suse-observability/latest/en/setup/install-stackstate/data-ingestion-pipeline.html#_topology_is_delayed_or_components_are_missing). diff --git a/stackpacks/suse-observability/includes/services/topo-sync/latency.md.hbs b/stackpacks/suse-observability/includes/services/topo-sync/latency.md.hbs index bdbaff8..20fc142 100644 --- a/stackpacks/suse-observability/includes/services/topo-sync/latency.md.hbs +++ b/stackpacks/suse-observability/includes/services/topo-sync/latency.md.hbs @@ -53,4 +53,6 @@ suse-observability/suse-observability ### Reduce the frequency of the topology updates. Update the settings of the agent collection of data for integration: `{{ labels.integration_type }}`, -Reducing the frequency of updates will remove pressure on the Topology Synchronization but as well means that the topology data will be less up-to-date as we don't refresh it that often. \ No newline at end of file +Reducing the frequency of updates will remove pressure on the Topology Synchronization but as well means that the topology data will be less up-to-date as we don't refresh it that often. + +For more details, see [Topology is delayed or components are missing](https://documentation.suse.com/cloudnative/suse-observability/latest/en/setup/install-stackstate/data-ingestion-pipeline.html#_topology_is_delayed_or_components_are_missing). diff --git a/stackpacks/suse-observability/includes/services/victoria-metrics/slow-insert-rate.md.hbs b/stackpacks/suse-observability/includes/services/victoria-metrics/slow-insert-rate.md.hbs index 95d037d..8004685 100644 --- a/stackpacks/suse-observability/includes/services/victoria-metrics/slow-insert-rate.md.hbs +++ b/stackpacks/suse-observability/includes/services/victoria-metrics/slow-insert-rate.md.hbs @@ -31,4 +31,6 @@ helm upgrade \ --values values.yaml \ suse-observability \ suse-observability/suse-observability -``` \ No newline at end of file +``` + +For more details, see [Metrics are delayed or missing](https://documentation.suse.com/cloudnative/suse-observability/latest/en/setup/install-stackstate/data-ingestion-pipeline.html#_metrics_are_delayed_or_missing). diff --git a/stackpacks/suse-observability/includes/services/vmagent/persistentqueue-dropping-data.md.hbs b/stackpacks/suse-observability/includes/services/vmagent/persistentqueue-dropping-data.md.hbs index eb6356a..9256e34 100644 --- a/stackpacks/suse-observability/includes/services/vmagent/persistentqueue-dropping-data.md.hbs +++ b/stackpacks/suse-observability/includes/services/vmagent/persistentqueue-dropping-data.md.hbs @@ -26,4 +26,6 @@ suse-observability \ suse-observability/suse-observability ``` - 2b. Consider to limit the ingestion rate. \ No newline at end of file + 2b. Consider to limit the ingestion rate. + +For more details, see [Metrics are delayed or missing](https://documentation.suse.com/cloudnative/suse-observability/latest/en/setup/install-stackstate/data-ingestion-pipeline.html#_metrics_are_delayed_or_missing). diff --git a/stackpacks/suse-observability/includes/services/vmagent/remotewrite-samples-dropped.md.hbs b/stackpacks/suse-observability/includes/services/vmagent/remotewrite-samples-dropped.md.hbs index c7f548f..864370b 100644 --- a/stackpacks/suse-observability/includes/services/vmagent/remotewrite-samples-dropped.md.hbs +++ b/stackpacks/suse-observability/includes/services/vmagent/remotewrite-samples-dropped.md.hbs @@ -7,3 +7,5 @@ Check: - `stackstate_vmagent_remotewrite_rate_limit_reached_total` if a remote-write rate limit is configured Fix the downstream cause rather than growing the queue; a larger queue only delays the same loss. + +For more details, see [Metrics are delayed or missing](https://documentation.suse.com/cloudnative/suse-observability/latest/en/setup/install-stackstate/data-ingestion-pipeline.html#_metrics_are_delayed_or_missing). diff --git a/stackpacks/suse-observability/stackpack.yaml b/stackpacks/suse-observability/stackpack.yaml index ac929b9..f80d600 100644 --- a/stackpacks/suse-observability/stackpack.yaml +++ b/stackpacks/suse-observability/stackpack.yaml @@ -1,5 +1,5 @@ name: suse-observability -version: "0.0.10" +version: "0.0.11" schemaVersion: "2.0" displayName: "SUSE Observability" categories: [ "SUSE Observability" ]