Skip to content

Commit

Permalink
Merge pull request influxdata#141 from richwilbert/richnetworktest
Browse files Browse the repository at this point in the history 
Added alert for network errors
  • Loading branch information
@russorat
russorat authored Jul 7, 2020
2 parents 65d3943 + 90852f8 commit 96c3bcc
Showing 1 changed file with 28 additions and 33 deletions.
61 changes: 28 additions & 33 deletions network_interface_performance/network_interface_performance.yml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -61,17 +61,14 @@ spec:
- query: |-
import "system"
import "influxdata/influxdb/v1"
data = from(bucket: v.bucket)
|> range(start: v.timeRangeStart, stop: v.timeRangeStop)
|> filter(fn: (r) => r._measurement == "net")
|> filter(fn: (r) => r._field =~ /^bytes_/)
|> filter(fn: (r) => r.host == v.network_host)
|> filter(fn: (r) => r.interface == v.network_interface)
last = data |> last() |> v1.fieldsAsCols()
first = data |> first() |> v1.fieldsAsCols()
join(tables: {l: last, f: first}, on: ["host","interface","_measurement"], method: "inner")
|> drop(columns: ["_time_f", "_time_l","_stop_f","_stop_l","_start_f","_start_l"])
|> map(fn: (r) => ({ r with _value: ((r.bytes_recv_l - r.bytes_recv_f) + (r.bytes_sent_l - r.bytes_sent_f)) }))
Expand Down Expand Up @@ -250,7 +247,6 @@ spec:
- query: |-
import "system"
import "influxdata/influxdb/v1"
data =from(bucket: v.bucket)
|> range(start: v.timeRangeStart, stop:v.timeRangeStop)
|> filter(fn: (r) => r._measurement == "net")
Expand All @@ -260,7 +256,6 @@ spec:
last = data |> last() |> v1.fieldsAsCols()
first= data |> first() |> v1.fieldsAsCols()
join(tables: {l: last, f:first}, on: ["host","interface","_measurement"], method: "inner")
|> drop(columns: ["_time_f", "_time_l","_stop_f","_stop_l","_start_f","_start_l"])
|> map(fn: (r) => ({ r with _value: ((r.packets_recv_l - r.packets_recv_f)+ (r.packets_sent_l - r.packets_sent_f)) }))
Expand All @@ -280,17 +275,14 @@ spec:
- query: |-
import "system"
import "influxdata/influxdb/v1"
data = from(bucket: v.bucket)
|> range(start: v.timeRangeStart, stop: v.timeRangeStop)
|> filter(fn: (r) => r._measurement == "net")
|> filter(fn: (r) => r._field =~ /^drop_/)
|> filter(fn: (r) => r.host == v.network_host)
|> filter(fn: (r) => r.interface == v.network_interface)
last = data |> last() |> v1.fieldsAsCols()
first = data |> first() |> v1.fieldsAsCols()
join(tables: {l: last, f: first}, on: ["host","interface","_measurement"], method: "inner")
|> drop(columns: ["_time_f", "_time_l","_stop_f","_stop_l","_start_f","_start_l"])
|> map(fn: (r) => ({ r with _value: ((r.drop_in_l - r.drop_in_f) + (r.drop_out_l - r.drop_out_f)) }))
Expand All @@ -310,17 +302,14 @@ spec:
- query: |-
import "system"
import "influxdata/influxdb/v1"
data = from(bucket: v.bucket)
|> range(start: v.timeRangeStart, stop: v.timeRangeStop)
|> filter(fn: (r) => r._measurement == "net")
|> filter(fn: (r) => r._field =~ /^err_/)
|> filter(fn: (r) => r.host == v.network_host)
|> filter(fn: (r) => r.interface == v.network_interface)
last = data |> last() |> v1.fieldsAsCols()
first = data |> first() |> v1.fieldsAsCols()
join(tables: {l: last, f: first}, on: ["host","interface","_measurement"], method: "inner")
|> drop(columns: ["_time_f", "_time_l","_stop_f","_stop_l","_start_f","_start_l"])
|> map(fn: (r) => ({ r with _value: ((r.err_in_l - r.err_in_f) + (r.err_out_l - r.err_out_f)) }))
Expand Down Expand Up @@ -408,48 +397,39 @@ spec:
# Environment variables can be used anywhere in this config file, simply surround
# them with ${}. For strings the variable must be within quotes (ie, "${STR_VAR}"),
# for numbers and booleans they should be plain (ie, ${INT_VAR}, ${BOOL_VAR})
# Global tags can be specified here in key="value" format.
[global_tags]
# dc = "us-east-1" # will tag all metrics with dc=us-east-1
# rack = "1a"
## Environment variables can be used as tags, and throughout the config file
# user = "$USER"
# Configuration for telegraf agent
[agent]
## Default data collection interval for all inputs
interval = "10s"
## Rounds collection interval to 'interval'
## ie, if interval="10s" then always collect on :00, :10, :20, etc.
round_interval = true
## Telegraf will send metrics to outputs in batches of at most
## metric_batch_size metrics.
## This controls the size of writes that Telegraf sends to output plugins.
metric_batch_size = 1000
## Maximum number of unwritten metrics per output. Increasing this value
## allows for longer periods of output downtime without dropping metrics at the
## cost of higher maximum memory usage.
metric_buffer_limit = 10000
## Collection jitter is used to jitter the collection by a random amount.
## Each plugin will sleep for a random time within jitter before collecting.
## This can be used to avoid many plugins querying things like sysfs at the
## same time, which can have a measurable effect on the system.
collection_jitter = "0s"
## Default flushing interval for all outputs. Maximum flush_interval will be
## flush_interval + flush_jitter
flush_interval = "10s"
## Jitter the flush interval by a random amount. This is primarily to avoid
## large write spikes for users running a large number of telegraf instances.
## ie, a jitter of 5s and interval 10s means flushes will happen every 10-15s
flush_jitter = "0s"
## By default or when set to "0s", precision will be set to the same
## timestamp order as the collection interval, with the maximum being 1s.
## ie, when interval = "10s", precision will be "1s"
Expand All @@ -458,44 +438,34 @@ spec:
## service input to set the timestamp at the appropriate precision.
## Valid time units are "ns", "us" (or "µs"), "ms", "s".
precision = ""
## Log at debug level.
# debug = false
## Log only error level messages.
# quiet = false
## Log target controls the destination for logs and can be one of "file",
## "stderr" or, on Windows, "eventlog". When set to "file", the output file
## is determined by the "logfile" setting.
# logtarget = "file"
## Name of the file to be logged to when using the "file" logtarget. If set to
## the empty string then logs are written to stderr.
# logfile = ""
## The logfile will be rotated after the time interval specified. When set
## to 0 no time based rotation is performed. Logs are rotated only when
## written to, if there is no log activity rotation may be delayed.
# logfile_rotation_interval = "0d"
## The logfile will be rotated when it becomes larger than the specified
## size. When set to 0 no size based rotation is performed.
# logfile_rotation_max_size = "0MB"
## Maximum number of rotated archives to keep, any older logs are deleted.
## If set to -1, no archives are removed.
# logfile_rotation_max_archives = 5
## Override default hostname, if empty use os.Hostname()
hostname = ""
## If set to true, do no set the "host" tag in the telegraf agent.
omit_hostname = false
###############################################################################
# OUTPUT PLUGINS #
###############################################################################
# Configuration for sending metrics to InfluxDB
[[outputs.influxdb_v2]]
## The URLs of the InfluxDB cluster nodes.
Expand Down Expand Up @@ -534,12 +504,9 @@ spec:
# tls_key = "/etc/telegraf/key.pem"
## Use TLS but skip chain & host verification
# insecure_skip_verify = false
###############################################################################
# INPUT PLUGINS #
###############################################################################
# Gather metrics about network interfaces
[[inputs.net]]
## By default, telegraf gathers stats from any up interface (excluding loopback)
Expand All @@ -566,3 +533,31 @@ spec:
retentionRules:
- everySeconds: 604800
type: expire
########################################################################################
# Network Error Check #
########################################################################################
apiVersion: influxdata.com/v2alpha1
kind: CheckThreshold
metadata:
name: relaxed-lewin-e50001
spec:
every: 10m0s
name: Network errors
query: |-
from(bucket: "network_data")
|> range(start: v.timeRangeStart, stop: v.timeRangeStop)
|> filter(fn: (r) => r["_measurement"] == "net")
|> filter(fn: (r) => r["_field"] == "err_in")
|> filter(fn: (r) => r["host"] == "Richards-MacBook-Pro.local")
|> aggregateWindow(every: 1m, fn: mean)
|> yield(name: "mean")
status: active
statusMessageTemplate: 'Check: ${ r._check_name } is: ${ r._level }'
thresholds:
- level: CRIT
type: greater
value: 20
- level: WARN
type: greater
value: 10

0 comments on commit 96c3bcc

Please sign in to comment.