Skip to content

Commit

Permalink
Merge pull request #598 from momoXD007/enable_fluentbit_healthcheck
Browse files Browse the repository at this point in the history 
feat: Enable fluentbit healthcheck
  • Loading branch information
@benjaminhuo
benjaminhuo committed Mar 7, 2023
2 parents e012507 + 9be6645 commit 1fb6689
Show file tree
Hide file tree
Showing 9 changed files with 180 additions and 2 deletions.
23 changes: 23 additions & 0 deletions apis/fluentbit/v1alpha2/clusterfluentbitconfig_types.go
View file
Original file line number Diff line number Diff line change
Expand Up @@ -53,6 +53,17 @@ type Service struct {
FlushSeconds *int64 `json:"flushSeconds,omitempty"`
// Wait time on exit
GraceSeconds *int64 `json:"graceSeconds,omitempty"`
// the error count to meet the unhealthy requirement, this is a sum for all output plugins in a defined HC_Period, example for output error: [2022/02/16 10:44:10] [ warn] [engine] failed to flush chunk '1-1645008245.491540684.flb', retry in 7 seconds: task_id=0, input=forward.1 > output=cloudwatch_logs.3 (out_id=3)
// +kubebuilder:validation:Minimum:=1
HcErrorsCount *int64 `json:"hcErrorsCount,omitempty"`
// the retry failure count to meet the unhealthy requirement, this is a sum for all output plugins in a defined HC_Period, example for retry failure: [2022/02/16 20:11:36] [ warn] [engine] chunk '1-1645042288.260516436.flb' cannot be retried: task_id=0, input=tcp.3 > output=cloudwatch_logs.1
// +kubebuilder:validation:Minimum:=1
HcRetryFailureCount *int64 `json:"hcRetryFailureCount,omitempty"`
// The time period by second to count the error and retry failure data point
// +kubebuilder:validation:Minimum:=1
HcPeriod *int64 `json:"hcPeriod,omitempty"`
// enable Health check feature at http://127.0.0.1:2020/api/v1/health Note: Enabling this will not automatically configure kubernetes to use fluentbit's healthcheck endpoint
HealthCheck *bool `json:"healthCheck,omitempty"`
// Address to listen
// +kubebuilder:validation:Pattern:="^\\d{1,3}.\\d{1,3}.\\d{1,3}.\\d{1,3}$"
HttpListen string `json:"httpListen,omitempty"`
Expand Down Expand Up @@ -108,6 +119,18 @@ func (s *Service) Params() *params.KVs {
if s.GraceSeconds != nil {
m.Insert("Grace", fmt.Sprint(*s.GraceSeconds))
}
if s.HcErrorsCount != nil {
m.Insert("HC_Errors_Count", fmt.Sprint(*s.HcErrorsCount))
}
if s.HcRetryFailureCount != nil {
m.Insert("HC_Retry_Failure_Count", fmt.Sprint(*s.HcRetryFailureCount))
}
if s.HcPeriod != nil {
m.Insert("HC_Period", fmt.Sprint(*s.HcPeriod))
}
if s.HealthCheck != nil {
m.Insert("Health_Check", fmt.Sprint(*s.HealthCheck))
}
if s.HttpListen != "" {
m.Insert("Http_Listen", s.HttpListen)
}
Expand Down
20 changes: 20 additions & 0 deletions apis/fluentbit/v1alpha2/zz_generated.deepcopy.go
View file

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

3 changes: 1 addition & 2 deletions apis/generated/clientset/versioned/clientset.go
View file

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

30 changes: 30 additions & 0 deletions charts/fluent-operator/crds/fluentbit.fluent.io_clusterfluentbitconfigs.yaml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -235,6 +235,36 @@ spec:
description: Wait time on exit
format: int64
type: integer
hcErrorsCount:
description: 'the error count to meet the unhealthy requirement,
this is a sum for all output plugins in a defined HC_Period,
example for output error: [2022/02/16 10:44:10] [ warn] [engine]
failed to flush chunk ''1-1645008245.491540684.flb'', retry
in 7 seconds: task_id=0, input=forward.1 > output=cloudwatch_logs.3
(out_id=3)'
format: int64
minimum: 1
type: integer
hcPeriod:
description: The time period by second to count the error and
retry failure data point
format: int64
minimum: 1
type: integer
hcRetryFailureCount:
description: 'the retry failure count to meet the unhealthy requirement,
this is a sum for all output plugins in a defined HC_Period,
example for retry failure: [2022/02/16 20:11:36] [ warn] [engine]
chunk ''1-1645042288.260516436.flb'' cannot be retried: task_id=0,
input=tcp.3 > output=cloudwatch_logs.1'
format: int64
minimum: 1
type: integer
healthCheck:
description: 'enable Health check feature at http://127.0.0.1:2020/api/v1/health
Note: Enabling this will not automatically configure kubernetes
to use fluentbit''s healthcheck endpoint'
type: boolean
httpListen:
description: Address to listen
pattern: ^\d{1,3}.\d{1,3}.\d{1,3}.\d{1,3}$
Expand Down
30 changes: 30 additions & 0 deletions config/crd/bases/fluentbit.fluent.io_clusterfluentbitconfigs.yaml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -235,6 +235,36 @@ spec:
description: Wait time on exit
format: int64
type: integer
hcErrorsCount:
description: 'the error count to meet the unhealthy requirement,
this is a sum for all output plugins in a defined HC_Period,
example for output error: [2022/02/16 10:44:10] [ warn] [engine]
failed to flush chunk ''1-1645008245.491540684.flb'', retry
in 7 seconds: task_id=0, input=forward.1 > output=cloudwatch_logs.3
(out_id=3)'
format: int64
minimum: 1
type: integer
hcPeriod:
description: The time period by second to count the error and
retry failure data point
format: int64
minimum: 1
type: integer
hcRetryFailureCount:
description: 'the retry failure count to meet the unhealthy requirement,
this is a sum for all output plugins in a defined HC_Period,
example for retry failure: [2022/02/16 20:11:36] [ warn] [engine]
chunk ''1-1645042288.260516436.flb'' cannot be retried: task_id=0,
input=tcp.3 > output=cloudwatch_logs.1'
format: int64
minimum: 1
type: integer
healthCheck:
description: 'enable Health check feature at http://127.0.0.1:2020/api/v1/health
Note: Enabling this will not automatically configure kubernetes
to use fluentbit''s healthcheck endpoint'
type: boolean
httpListen:
description: Address to listen
pattern: ^\d{1,3}.\d{1,3}.\d{1,3}.\d{1,3}$
Expand Down
4 changes: 4 additions & 0 deletions go.mod
View file
Original file line number Diff line number Diff line change
Expand Up @@ -57,12 +57,14 @@ require (
go.uber.org/atomic v1.9.0 // indirect
go.uber.org/multierr v1.7.0 // indirect
go.uber.org/zap v1.24.0 // indirect
golang.org/x/mod v0.6.0 // indirect
golang.org/x/net v0.5.0 // indirect
golang.org/x/oauth2 v0.0.0-20220223155221-ee480838109b // indirect
golang.org/x/sys v0.4.0 // indirect
golang.org/x/term v0.4.0 // indirect
golang.org/x/text v0.6.0 // indirect
golang.org/x/time v0.3.0 // indirect
golang.org/x/tools v0.2.0 // indirect
gomodules.xyz/jsonpatch/v2 v2.2.0 // indirect
google.golang.org/appengine v1.6.7 // indirect
google.golang.org/protobuf v1.28.1 // indirect
Expand All @@ -71,7 +73,9 @@ require (
gopkg.in/yaml.v2 v2.4.0 // indirect
gopkg.in/yaml.v3 v3.0.1 // indirect
k8s.io/apiextensions-apiserver v0.26.1 // indirect
k8s.io/code-generator v0.26.1 // indirect
k8s.io/component-base v0.26.1 // indirect
k8s.io/gengo v0.0.0-20220902162205-c0856e24416d // indirect
k8s.io/kube-openapi v0.0.0-20221012153701-172d655c2280 // indirect
k8s.io/utils v0.0.0-20221128185143-99ec85e7a448 // indirect
sigs.k8s.io/json v0.0.0-20220713155537-f223a00ba0e2 // indirect
Expand Down
12 changes: 12 additions & 0 deletions go.sum
View file
Original file line number Diff line number Diff line change
Expand Up @@ -89,6 +89,7 @@ github.com/go-logfmt/logfmt v0.4.0/go.mod h1:3RMwSq7FuexP4Kalkev3ejPJsZTpXXBr9+V
github.com/go-logfmt/logfmt v0.5.0/go.mod h1:wCYkCAKZfumFQihp8CzCvQ3paCTfi41vtzG1KdI/P7A=
github.com/go-logfmt/logfmt v0.5.1 h1:otpy5pqBCBZ1ng9RQ0dPu4PN7ba75Y/aA+UpowDyNVA=
github.com/go-logfmt/logfmt v0.5.1/go.mod h1:WYhtIu8zTZfxdn5+rREduYbwxfcBr/Vr6KEVveWlfTs=
github.com/go-logr/logr v0.2.0/go.mod h1:z6/tIYblkpsD+a4lm/fGIIU9mZ+XfAiaFtq7xTgseGU=
github.com/go-logr/logr v1.2.0/go.mod h1:jdQByPbusPIv2/zmleS9BjJVeZ6kBagPoEUsqbVz/1A=
github.com/go-logr/logr v1.2.2/go.mod h1:jdQByPbusPIv2/zmleS9BjJVeZ6kBagPoEUsqbVz/1A=
github.com/go-logr/logr v1.2.3 h1:2DntVwHkVopvECVRSlL5PSo9eG+cAkDCuckLubN+rq0=
Expand Down Expand Up @@ -342,6 +343,8 @@ golang.org/x/mod v0.1.1-0.20191105210325-c90efee705ee/go.mod h1:QqPTAvyqsEbceGzB
golang.org/x/mod v0.1.1-0.20191107180719-034126e5016b/go.mod h1:QqPTAvyqsEbceGzBzNggFXnrqF1CaUcvgkdR5Ot7KZg=
golang.org/x/mod v0.2.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
golang.org/x/mod v0.3.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
golang.org/x/mod v0.6.0 h1:b9gGHsz9/HhJ3HF5DHQytPpuwocVTChQJK3AvoLRD5I=
golang.org/x/mod v0.6.0/go.mod h1:4mET923SAdbXp2ki8ey+zGs1SLqsuM2Y0uvdZR/fUNI=
golang.org/x/net v0.0.0-20180724234803-3673e40ba225/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
golang.org/x/net v0.0.0-20180826012351-8a410e7b638d/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
golang.org/x/net v0.0.0-20180906233101-161cd47e91fd/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
Expand Down Expand Up @@ -496,6 +499,7 @@ golang.org/x/tools v0.0.0-20200304193943-95d2e580d8eb/go.mod h1:o4KQGtdN14AW+yjs
golang.org/x/tools v0.0.0-20200312045724-11d5b4c81c7d/go.mod h1:o4KQGtdN14AW+yjsvvwRTJJuXz8XRtIHtEnmAXLyFUw=
golang.org/x/tools v0.0.0-20200331025713-a30bf2db82d4/go.mod h1:Sl4aGygMT6LrqrWclx+PTx3U+LnKx/seiNR+3G19Ar8=
golang.org/x/tools v0.0.0-20200501065659-ab2804fb9c9d/go.mod h1:EkVYQZoAsY45+roYkvgYkIh4xh/qjgUK9TdY2XT94GE=
golang.org/x/tools v0.0.0-20200505023115-26f46d2f7ef8/go.mod h1:EkVYQZoAsY45+roYkvgYkIh4xh/qjgUK9TdY2XT94GE=
golang.org/x/tools v0.0.0-20200512131952-2bc93b1c0c88/go.mod h1:EkVYQZoAsY45+roYkvgYkIh4xh/qjgUK9TdY2XT94GE=
golang.org/x/tools v0.0.0-20200515010526-7d3b6ebf133d/go.mod h1:EkVYQZoAsY45+roYkvgYkIh4xh/qjgUK9TdY2XT94GE=
golang.org/x/tools v0.0.0-20200618134242-20370b0cb4b2/go.mod h1:EkVYQZoAsY45+roYkvgYkIh4xh/qjgUK9TdY2XT94GE=
Expand All @@ -505,6 +509,8 @@ golang.org/x/tools v0.0.0-20200804011535-6c149bb5ef0d/go.mod h1:njjCfa9FT2d7l9Bc
golang.org/x/tools v0.0.0-20200825202427-b303f430e36d/go.mod h1:njjCfa9FT2d7l9Bc6FUM5FLjQPp3cFF28FI3qnDFljA=
golang.org/x/tools v0.0.0-20201224043029-2b0845dc783e/go.mod h1:emZCQorbCU4vsT4fOWvOPXz4eW1wZW4PmDk9uLelYpA=
golang.org/x/tools v0.0.0-20210106214847-113979e3529a/go.mod h1:emZCQorbCU4vsT4fOWvOPXz4eW1wZW4PmDk9uLelYpA=
golang.org/x/tools v0.2.0 h1:G6AHpWxTMGY1KyEYoAQ5WTtIekUUvDNjan3ugu60JvE=
golang.org/x/tools v0.2.0/go.mod h1:y4OqIKeOV/fWJetJ8bXPU1sEVniLMIyDAZWeHdV+NTA=
golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
golang.org/x/xerrors v0.0.0-20191011141410-1b5146add898/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
Expand Down Expand Up @@ -631,8 +637,13 @@ k8s.io/apimachinery v0.26.1 h1:8EZ/eGJL+hY/MYCNwhmDzVqq2lPl3N3Bo8rvweJwXUQ=
k8s.io/apimachinery v0.26.1/go.mod h1:tnPmbONNJ7ByJNz9+n9kMjNP8ON+1qoAIIC70lztu74=
k8s.io/client-go v0.26.1 h1:87CXzYJnAMGaa/IDDfRdhTzxk/wzGZ+/HUQpqgVSZXU=
k8s.io/client-go v0.26.1/go.mod h1:IWNSglg+rQ3OcvDkhY6+QLeasV4OYHDjdqeWkDQZwGE=
k8s.io/code-generator v0.26.1 h1:dusFDsnNSKlMFYhzIM0jAO1OlnTN5WYwQQ+Ai12IIlo=
k8s.io/code-generator v0.26.1/go.mod h1:OMoJ5Dqx1wgaQzKgc+ZWaZPfGjdRq/Y3WubFrZmeI3I=
k8s.io/component-base v0.26.1 h1:4ahudpeQXHZL5kko+iDHqLj/FSGAEUnSVO0EBbgDd+4=
k8s.io/component-base v0.26.1/go.mod h1:VHrLR0b58oC035w6YQiBSbtsf0ThuSwXP+p5dD/kAWU=
k8s.io/gengo v0.0.0-20220902162205-c0856e24416d h1:U9tB195lKdzwqicbJvyJeOXV7Klv+wNAWENRnXEGi08=
k8s.io/gengo v0.0.0-20220902162205-c0856e24416d/go.mod h1:FiNAH4ZV3gBg2Kwh89tzAEV2be7d5xI0vBa/VySYy3E=
k8s.io/klog/v2 v2.2.0/go.mod h1:Od+F08eJP+W3HUb4pSrPpgp9DGU4GzlpG/TmITuYh/Y=
k8s.io/klog/v2 v2.90.0 h1:VkTxIV/FjRXn1fgNNcKGM8cfmL1Z33ZjXRTVxKCoF5M=
k8s.io/klog/v2 v2.90.0/go.mod h1:y1WjHnz7Dj687irZUWR/WLkLc5N1YHtjLdmgWjndZn0=
k8s.io/kube-openapi v0.0.0-20221012153701-172d655c2280 h1:+70TFaan3hfJzs+7VK2o+OGxg8HsuBr/5f6tVAjDu6E=
Expand All @@ -648,5 +659,6 @@ sigs.k8s.io/json v0.0.0-20220713155537-f223a00ba0e2 h1:iXTIw73aPyC+oRdyqqvVJuloN
sigs.k8s.io/json v0.0.0-20220713155537-f223a00ba0e2/go.mod h1:B8JuhiUyNFVKdsE8h686QcCxMaH6HrOAZj4vswFpcB0=
sigs.k8s.io/structured-merge-diff/v4 v4.2.3 h1:PRbqxJClWWYMNV1dhaG4NsibJbArud9kFxnAMREiWFE=
sigs.k8s.io/structured-merge-diff/v4 v4.2.3/go.mod h1:qjx8mGObPmV2aSZepjQjbmb2ihdVs8cGKBraizNC69E=
sigs.k8s.io/yaml v1.2.0/go.mod h1:yfXDCHCao9+ENCvLSE62v9VSji2MKu5jeNfTrofGhJc=
sigs.k8s.io/yaml v1.3.0 h1:a2VclLzOGrwOHDiV8EfBGhvjHvP46CtW5j6POvhYGGo=
sigs.k8s.io/yaml v1.3.0/go.mod h1:GeOyir5tyXNByN85N/dRIT9es5UQNerPYEKK56eTBm8=
30 changes: 30 additions & 0 deletions manifests/setup/fluent-operator-crd.yaml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -1387,6 +1387,36 @@ spec:
description: Wait time on exit
format: int64
type: integer
hcErrorsCount:
description: 'the error count to meet the unhealthy requirement,
this is a sum for all output plugins in a defined HC_Period,
example for output error: [2022/02/16 10:44:10] [ warn] [engine]
failed to flush chunk ''1-1645008245.491540684.flb'', retry
in 7 seconds: task_id=0, input=forward.1 > output=cloudwatch_logs.3
(out_id=3)'
format: int64
minimum: 1
type: integer
hcPeriod:
description: The time period by second to count the error and
retry failure data point
format: int64
minimum: 1
type: integer
hcRetryFailureCount:
description: 'the retry failure count to meet the unhealthy requirement,
this is a sum for all output plugins in a defined HC_Period,
example for retry failure: [2022/02/16 20:11:36] [ warn] [engine]
chunk ''1-1645042288.260516436.flb'' cannot be retried: task_id=0,
input=tcp.3 > output=cloudwatch_logs.1'
format: int64
minimum: 1
type: integer
healthCheck:
description: 'enable Health check feature at http://127.0.0.1:2020/api/v1/health
Note: Enabling this will not automatically configure kubernetes
to use fluentbit''s healthcheck endpoint'
type: boolean
httpListen:
description: Address to listen
pattern: ^\d{1,3}.\d{1,3}.\d{1,3}.\d{1,3}$
Expand Down
30 changes: 30 additions & 0 deletions manifests/setup/setup.yaml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -1387,6 +1387,36 @@ spec:
description: Wait time on exit
format: int64
type: integer
hcErrorsCount:
description: 'the error count to meet the unhealthy requirement,
this is a sum for all output plugins in a defined HC_Period,
example for output error: [2022/02/16 10:44:10] [ warn] [engine]
failed to flush chunk ''1-1645008245.491540684.flb'', retry
in 7 seconds: task_id=0, input=forward.1 > output=cloudwatch_logs.3
(out_id=3)'
format: int64
minimum: 1
type: integer
hcPeriod:
description: The time period by second to count the error and
retry failure data point
format: int64
minimum: 1
type: integer
hcRetryFailureCount:
description: 'the retry failure count to meet the unhealthy requirement,
this is a sum for all output plugins in a defined HC_Period,
example for retry failure: [2022/02/16 20:11:36] [ warn] [engine]
chunk ''1-1645042288.260516436.flb'' cannot be retried: task_id=0,
input=tcp.3 > output=cloudwatch_logs.1'
format: int64
minimum: 1
type: integer
healthCheck:
description: 'enable Health check feature at http://127.0.0.1:2020/api/v1/health
Note: Enabling this will not automatically configure kubernetes
to use fluentbit''s healthcheck endpoint'
type: boolean
httpListen:
description: Address to listen
pattern: ^\d{1,3}.\d{1,3}.\d{1,3}.\d{1,3}$
Expand Down

0 comments on commit 1fb6689

Please sign in to comment.