Sha256: 0c8e8d57a36ddce9b8734d8073bf68b1f26a695fa313f3d504f7a5e19a3d3d71
Contents?: true
Size: 1.63 KB
Versions: 42
Compression:
Stored size: 1.63 KB
Contents
ALERT FluentdNodeDown
IF up{job="fluentd"} == 0
FOR 10m
LABELS {
service = "fluentd",
severity = "warning"
}
ANNOTATIONS {
summary = "fluentd cannot be scraped",
description = "Prometheus could not scrape {{ $labels.job }} for more than 10 minutes",
}
ALERT FluentdNodeDown
IF up{job="fluentd"} == 0
FOR 30m
LABELS {
service = "fluentd",
severity = "critical"
}
ANNOTATIONS {
summary = "fluentd cannot be scraped",
description = "Prometheus could not scrape {{ $labels.job }} for more than 30 minutes",
}
ALERT FluentdQueueLength
IF rate(fluentd_status_buffer_queue_length[5m]) > 0.3
FOR 1m
LABELS {
service = "fluentd",
severity = "warning"
}
ANNOTATIONS {
summary = "fluentd node are failing",
description = "In the last 5 minutes, fluentd queues increased 30%. Current value is {{ $value }} ",
}
ALERT FluentdQueueLength
IF rate(fluentd_status_buffer_queue_length[5m]) > 0.5
FOR 1m
LABELS {
service = "fluentd",
severity = "critical"
}
ANNOTATIONS {
summary = "fluentd node are critical",
description = "In the last 5 minutes, fluentd queues increased 50%. Current value is {{ $value }} ",
}
ALERT FluentdRecordsCountsHigh
IF sum(rate(fluentd_output_status_emit_records{job="fluentd"}[5m])) BY (instance) > (3 * sum(rate(fluentd_output_status_emit_records{job="fluentd"}[15m])) BY (instance))
FOR 1m
LABELS {
service = "fluentd",
severity = "critical"
}
ANNOTATIONS {
summary = "fluentd records count are critical",
description = "In the last 5m, records counts increased 3 times, comparing to the latest 15 min.",
}
Version data entries
42 entries across 42 versions & 4 rubygems