Develop bmc-log-collector

.github/workflows/main.yaml

@@ -26,6 +26,9 @@ jobs:
           - dir: "./bmc-reverse-proxy"
             container-image: "bmc-reverse-proxy"
             make-targets: "setup check-generate test"
+          - dir: "./bmc-log-collector"
+            container-image: "bmc-log-collector"
+            make-targets: "setup check-generate test"
           - dir: "./bpf-map-pressure-exporter"
             container-image: "bpf-map-pressure-exporter"
             make-targets: "check-generate test"

bmc-log-collector/BRANCH

@@ -0,0 +1 @@
+0.9

bmc-log-collector/Dockerfile

@@ -0,0 +1,18 @@
+# Stage1: build from source
+FROM ghcr.io/cybozu/golang:1.22-jammy AS build
+
+COPY . /work
+WORKDIR /work
+
+RUN CGO_ENABLED=0 go install -ldflags="-w -s"
+
+# Stage2: setup runtime container
+FROM scratch
+
+LABEL org.opencontainers.image.source="https://github.com/cybozu/neco-containers"
+
+COPY --from=build /go/bin /
+
+USER 10000:10000
+
+ENTRYPOINT ["/log-collector"]

bmc-log-collector/Makefile

@@ -0,0 +1,28 @@
+.PHONY: all
+all: check-generate test
+
+.PHONY: setup
+setup:
+	go install github.com/cybozu-go/golang-custom-analyzer/cmd/custom-checker@latest
+	go install honnef.co/go/tools/cmd/staticcheck@latest
+	go install github.com/onsi/ginkgo/v2/ginkgo
+
+.PHONY: check-generate
+check-generate:
+	go mod tidy
+	git diff --exit-code --name-only
+
+.PHONY: test
+test: clean
+	test -z "$$(gofmt -s -l . | tee /dev/stderr)"
+	staticcheck ./...
+	test -z "$$(custom-checker -restrictpkg.packages=html/template ./... 2>&1 | tee /dev/stderr)"
+	go vet ./...
+	ginkgo -v --race -p .
+
+.PHONY: clean
+clean:
+	rm -f testdata/output_main_test/*
+	rm -fr testdata/pointers_get_machines
+	rm -fr testdata/pointers_log_collector
+	rm -fr testdata/pointers_main_test

bmc-log-collector/README.md

@@ -0,0 +1,53 @@
+bmc-log-collector
+============================
+
+`bmc-log-collector` collects hardware logs from Baseboard Management Controller (BMC) and output own stdout.
+
+The following products are assumed as BMC.
+- DELL integrated Dell Remote Access Controller (iDRAC) 
+
+This program reads the "machineslist.json" and retrieves the System Event Log from each BMC. "bmc-log-collector" adds the serial and the node IP to own STD output.
+
+## Referenced file
+
+#### User and password of BMC
+
+```
+{
+  "USERID-TO-BE-REPLACE": {
+    "password": {
+      "raw": "PASSWORD-STRING-TO-BE-REPLACE"
+    }
+  },
+  // Repeat
+}
+```
+
+#### Target "machineslist.json" of log scraping
+
+```
+[
+    {
+        serial:    "ABC1234",     // Uniq serial ID of the server hardware
+        bmc_ipv4:  "192.168.1.1"  // BMC IP address
+        node_ipv4: "192.168.10.1" // Server IP address
+    },
+    // Repeat
+]
+```
+
+
+## Usage 
+
+bmc-log-collector command provides the usage in following.
+
+```
+$ bmc-log-collector --help
+
+Usage of ./bmc-log-collector:
+      --bmc-user-json string          User and password of BMC (default "/users/neco/bmc-user.json")
+      --machine-list-json string      Target machines list of log scraping (default "/config/machineslist.json")
+      --pointer-dir-path string       Data directory of pointer management (default "/data/pointers")
+      --scraping-interval-timer int   Timer(sec) of scraping interval time (default 300)
+      --user-id string                User ID of bmc-user-json JSON file (default "support")
+```

bmc-log-collector/TAG

@@ -0,0 +1 @@
+0.9.0

bmc-log-collector/bmc-user.go

@@ -0,0 +1,42 @@
+package main
+
+import (
+	"encoding/json"
+	"os"
+)
+
+// BMCPassword represents password for a BMC user.
+type BMCPassword struct {
+	Raw  string `json:"raw"`
+	Hash string `json:"hash"`
+	Salt string `json:"salt"`
+}
+
+// Credentials represents credentials of a BMC user.
+type Credentials struct {
+	Password BMCPassword `json:"password"`
+}
+
+// UserConfig represents a set of BMC user credentials in JSON format.
+type UserConfig struct {
+	Root    Credentials `json:"root"`
+	Repair  Credentials `json:"repair"`
+	Power   Credentials `json:"power"`
+	Support Credentials `json:"support"`
+}
+
+// LoadConfig loads UserConfig.
+func LoadBMCUserConfig(userFile string) (*UserConfig, error) {
+	fd, err := os.Open(userFile)
+	if err != nil {
+		return nil, err
+	}
+	defer fd.Close()
+
+	bmcUsers := new(UserConfig)
+	err = json.NewDecoder(fd).Decode(bmcUsers)
+	if err != nil {
+		return nil, err
+	}
+	return bmcUsers, nil
+}

bmc-log-collector/bmc-user_test.go

@@ -0,0 +1,28 @@
+package main
+
+import (
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+)
+
+var _ = Describe("Get User from bmc-user.json", Ordered, func() {
+	Context("Normal", func() {
+		It("Read JSON file", func() {
+			user, err := LoadBMCUserConfig("testdata/etc/bmc-user.json")
+			Expect(err).NotTo(HaveOccurred())
+			Expect(user.Support.Password.Raw).To(Equal(basicAuthPassword))
+		})
+	})
+
+	Context("Abnormal", func() {
+		It("Read no existing file", func() {
+			_, err := LoadBMCUserConfig("testdata/etc/no-exist.json")
+			Expect(err).To(HaveOccurred())
+		})
+
+		It("no support user in json file", func() {
+			_, err := LoadBMCUserConfig("testdata/etc/bmc-user-err.json")
+			Expect(err).To(HaveOccurred())
+		})
+	})
+})

bmc-log-collector/docs/design.md

@@ -0,0 +1,112 @@
+# BMC Log Collector Design
+
+“BMC Log Collector” collects Hareware Error from Baseboard Management Controller (BMC) and output to own stdout.
+In case of DELL hardware, “BMC Log Collector” collects System Event Log (SEL) from iDRAC.
+The first case of collecting is DELL.
+
+“BMC Log Collector” has the following features
+1. Retrieve the IP address and ID of the BMC to be collected from a JSON file
+2. Access the IP address of the BMC and retrieve a hardware error logs from the Redfish REST service
+3. Output the collected logs that eliminated duplication to STDOUT
+
+Redfish is a standard for server management and provides information as REST API service. 
+We can get the event of hardware in Server.
+
+## Architecture of BMC Log Collector
+
+The following figure shows an architectural diagram of BMC Log Collector.
+
+```mermaid
+flowchart TB
+  PS[(Pointer File Store)] <---> LC
+  CF[JSON File]-->LC[Log Collector]
+  BMC[BMC]-->LC
+  LC-->LS[Stdout]
+```
+
+1. "JSON File" has BMC IP list, server identity string, server's IP address.
+2. "Pointer File Store" has latest pointer information for each BMC.
+5. "BMC" is Baseboard Management Controller that has IP address and serves Redfish API.
+
+## How “BMC Log Collector” works
+
+1. Get a list of IP addresses of the BMC in a JSON file
+2. Access the Redfish path of the BMC's IP address to get the hardware event log
+3. Use `/redfish/v1/Managers/iDRAC.Embedded.1/LogServices/Sel/Entries` as the path to RedFish.
+4. Convert the received JSON data into a Go language structure and inspect for duplicates.
+5. Compare the ID of the log received last time with the ID of the log received this time. If the ID of the log received this time is larger, it is considered the latest event.
+6. If the ID is smaller than the previous one, the timestamp is compared, and if it is larger than the previous timestamp, it is considered as the latest log.
+7. Write ID, type stamp, and identification string in the file. The file name is the identification string, and a separate file is created for each BMC.
+8. The latest events in the event log are output in JSON format to standard output.
+9. Perform tasks 1 through 8 above, at intervals of a few minutes.
+10. Continue this cycle while the “BMC Log Collector” is running.
+
+
+## Architectural Decisions
+
+### ADR1. Obtaining the BMC machine list
+
+There are two ways to obtain the latest BMC listings.
+
+- Method 1: Get the BMC list from the server's database.
+- Method 2: Create a JSON file by adding to the existing functions.
+
+#### Advantages of using Method 1
+- Reduced risk of failure due to fewer dependent components
+
+#### Disadvantages of using Method 1
+- Complex processes to retrieve data from databases, serfs, etc. must be written.
+
+#### Advantages of adopting Method 2
+- Programming and testing can be reduced, and the construction period can be shortened.
+
+#### Disadvantages of adopting Method 2
+- If an existing function fails, the main function stops.
+
+### Decision and Reason
+Adopt method 2.
+As a countermeasure against failure, minimize the impact by using the last updated JSON file when the existing function stops.
+
+
+### ADR2. Control of processing load
+
+There are two possible methods to obtain event logs from the BMC.
+
+- Method 1: The list is stored in the processing queue and worker tasks retrieve it sequentially.
+
+- Method 2: Go routines are started in a number of BMCs, and they are all retrieved at the same time.
+
+
+#### Advantages of Method 1
+- Workload can be controlled by the number of worker tasks
+
+#### Disadvantages of Method 1
+- Management of queues and worker processes becomes complicated
+
+#### Advantages of Method 2
+- Simplifies Go programming
+
+#### Disadvantages of Method 2
+- Load surges occur at the beginning of each collection cycle when there are many target BMCs,Unable to control the load.
+
+### Decision and Reason
+Method 2
+With the current number of BMCs, load is not a problem.
+
+
+
+## Risks
+
+1. There is a concern that log output may be mixed under multi-threaded execution. There is a possibility that this is not thread-safe.
+  - Countermeasures
+    - Put exclusion control before and after the output to make it thread-safe.
+
+2. Concerns that workload surges will adversely affect others
+  - Countermeasures
+    - If a problem is discovered, initially limit the number of Go routines by semaphore. If the problem cannot be resolved, consider a queue.
+
+
+
+## Usage
+
+please refer [README.md](../README.md)

bmc-log-collector/go.mod

@@ -0,0 +1,32 @@
+module log-collector
+
+go 1.22.5
+
+require (
+	github.com/onsi/ginkgo/v2 v2.19.0
+	github.com/onsi/gomega v1.33.1
+	github.com/prometheus/client_golang v1.20.0
+	github.com/prometheus/common v0.55.0
+	github.com/spf13/pflag v1.0.5
+)
+
+require (
+	github.com/beorn7/perks v1.0.1 // indirect
+	github.com/cespare/xxhash/v2 v2.3.0 // indirect
+	github.com/go-logr/logr v1.4.1 // indirect
+	github.com/go-task/slim-sprig/v3 v3.0.0 // indirect
+	github.com/google/go-cmp v0.6.0 // indirect
+	github.com/google/pprof v0.0.0-20240424215950-a892ee059fd6 // indirect
+	github.com/klauspost/compress v1.17.9 // indirect
+	github.com/kr/text v0.2.0 // indirect
+	github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
+	github.com/prometheus/client_model v0.6.1 // indirect
+	github.com/prometheus/procfs v0.15.1 // indirect
+	github.com/rogpeppe/go-internal v1.12.0 // indirect
+	golang.org/x/net v0.27.0 // indirect
+	golang.org/x/sys v0.22.0 // indirect
+	golang.org/x/text v0.16.0 // indirect
+	golang.org/x/tools v0.23.0 // indirect
+	google.golang.org/protobuf v1.34.2 // indirect
+	gopkg.in/yaml.v3 v3.0.1 // indirect
+)

bmc-log-collector/go.sum

@@ -0,0 +1,60 @@
+github.com/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM=
+github.com/beorn7/perks v1.0.1/go.mod h1:G2ZrVWU2WbWT9wwq4/hrbKbnv/1ERSJQ0ibhJ6rlkpw=
+github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs=
+github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
+github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
+github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
+github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/go-logr/logr v1.4.1 h1:pKouT5E8xu9zeFC39JXRDukb6JFQPXM5p5I91188VAQ=
+github.com/go-logr/logr v1.4.1/go.mod h1:9T104GzyrTigFIr8wt5mBrctHMim0Nb2HLGrmQ40KvY=
+github.com/go-task/slim-sprig/v3 v3.0.0 h1:sUs3vkvUymDpBKi3qH1YSqBQk9+9D/8M2mN1vB6EwHI=
+github.com/go-task/slim-sprig/v3 v3.0.0/go.mod h1:W848ghGpv3Qj3dhTPRyJypKRiqCdHZiAzKg9hl15HA8=
+github.com/google/go-cmp v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI=
+github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
+github.com/google/pprof v0.0.0-20240424215950-a892ee059fd6 h1:k7nVchz72niMH6YLQNvHSdIE7iqsQxK1P41mySCvssg=
+github.com/google/pprof v0.0.0-20240424215950-a892ee059fd6/go.mod h1:kf6iHlnVGwgKolg33glAes7Yg/8iWP8ukqeldJSO7jw=
+github.com/klauspost/compress v1.17.9 h1:6KIumPrER1LHsvBVuDa0r5xaG0Es51mhhB9BQB2qeMA=
+github.com/klauspost/compress v1.17.9/go.mod h1:Di0epgTjJY877eYKx5yC51cX2A2Vl2ibi7bDH9ttBbw=
+github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
+github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk=
+github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
+github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
+github.com/kylelemons/godebug v1.1.0 h1:RPNrshWIDI6G2gRW9EHilWtl7Z6Sb1BR0xunSBf0SNc=
+github.com/kylelemons/godebug v1.1.0/go.mod h1:9/0rRGxNHcop5bhtWyNeEfOS8JIWk580+fNqagV/RAw=
+github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 h1:C3w9PqII01/Oq1c1nUAm88MOHcQC9l5mIlSMApZMrHA=
+github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822/go.mod h1:+n7T8mK8HuQTcFwEeznm/DIxMOiR9yIdICNftLE1DvQ=
+github.com/onsi/ginkgo/v2 v2.19.0 h1:9Cnnf7UHo57Hy3k6/m5k3dRfGTMXGvxhHFvkDTCTpvA=
+github.com/onsi/ginkgo/v2 v2.19.0/go.mod h1:rlwLi9PilAFJ8jCg9UE1QP6VBpd6/xj3SRC0d6TU0To=
+github.com/onsi/gomega v1.33.1 h1:dsYjIxxSR755MDmKVsaFQTE22ChNBcuuTWgkUDSubOk=
+github.com/onsi/gomega v1.33.1/go.mod h1:U4R44UsT+9eLIaYRB2a5qajjtQYn0hauxvRm16AVYg0=
+github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
+github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
+github.com/prometheus/client_golang v1.20.0 h1:jBzTZ7B099Rg24tny+qngoynol8LtVYlA2bqx3vEloI=
+github.com/prometheus/client_golang v1.20.0/go.mod h1:PIEt8X02hGcP8JWbeHyeZ53Y/jReSnHgO035n//V5WE=
+github.com/prometheus/client_model v0.6.1 h1:ZKSh/rekM+n3CeS952MLRAdFwIKqeY8b62p8ais2e9E=
+github.com/prometheus/client_model v0.6.1/go.mod h1:OrxVMOVHjw3lKMa8+x6HeMGkHMQyHDk9E3jmP2AmGiY=
+github.com/prometheus/common v0.55.0 h1:KEi6DK7lXW/m7Ig5i47x0vRzuBsHuvJdi5ee6Y3G1dc=
+github.com/prometheus/common v0.55.0/go.mod h1:2SECS4xJG1kd8XF9IcM1gMX6510RAEL65zxzNImwdc8=
+github.com/prometheus/procfs v0.15.1 h1:YagwOFzUgYfKKHX6Dr+sHT7km/hxC76UB0learggepc=
+github.com/prometheus/procfs v0.15.1/go.mod h1:fB45yRUv8NstnjriLhBQLuOUt+WW4BsoGhij/e3PBqk=
+github.com/rogpeppe/go-internal v1.12.0 h1:exVL4IDcn6na9z1rAb56Vxr+CgyK3nn3O+epU5NdKM8=
+github.com/rogpeppe/go-internal v1.12.0/go.mod h1:E+RYuTGaKKdloAfM02xzb0FW3Paa99yedzYV+kq4uf4=
+github.com/spf13/pflag v1.0.5 h1:iy+VFUOCP1a+8yFto/drg2CJ5u0yRoB7fZw3DKv/JXA=
+github.com/spf13/pflag v1.0.5/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg=
+github.com/stretchr/testify v1.9.0 h1:HtqpIVDClZ4nwg75+f6Lvsy/wHu+3BoSGCbBAcpTsTg=
+github.com/stretchr/testify v1.9.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
+golang.org/x/net v0.27.0 h1:5K3Njcw06/l2y9vpGCSdcxWOYHOUk3dVNGDXN+FvAys=
+golang.org/x/net v0.27.0/go.mod h1:dDi0PyhWNoiUOrAS8uXv/vnScO4wnHQO4mj9fn/RytE=
+golang.org/x/sys v0.22.0 h1:RI27ohtqKCnwULzJLqkv897zojh5/DwS/ENaMzUOaWI=
+golang.org/x/sys v0.22.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
+golang.org/x/text v0.16.0 h1:a94ExnEXNtEwYLGJSIUxnWoxoRz/ZcCsV63ROupILh4=
+golang.org/x/text v0.16.0/go.mod h1:GhwF1Be+LQoKShO3cGOHzqOgRrGaYc9AvblQOmPVHnI=
+golang.org/x/tools v0.23.0 h1:SGsXPZ+2l4JsgaCKkx+FQ9YZ5XEtA1GZYuoDjenLjvg=
+golang.org/x/tools v0.23.0/go.mod h1:pnu6ufv6vQkll6szChhK3C3L/ruaIv5eBeztNG8wtsI=
+google.golang.org/protobuf v1.34.2 h1:6xV6lTsCfpGD21XK49h7MhtcApnLqkfYgPcdHftf6hg=
+google.golang.org/protobuf v1.34.2/go.mod h1:qYOHts0dSfpeUzUFpOMr/WGzszTmLH+DiWniOlNbLDw=
+gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
+gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
+gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=
+gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
+gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=