Add metrics

Cargo.toml

@@ -20,6 +20,7 @@ rand = "0.8.5"
 reqwest = { version = "0.11.23", features = ["blocking", "brotli", "deflate", "gzip", "rustls-tls", "json"] }
 rustls = { version = "0.21.10", default-features = false, features = ["quic"] }
 solana-core = "1.18.8"
+solana-ledger = "1.18.8"
 solana-logger = "1.18.8"
 solana-sdk = "1.18.8"
 strum = "0.26.2"

PROGRESS.md

@@ -15,33 +15,33 @@
 - [x] Create Genesis
     - [x] Generate faucet and bootstrap accounts
     - [x] Build genesis
-- [ ] Docker Build
-    - [ ] Build Bootstrap Image
-    - [ ] Push Image to registry
+- [x] Docker Build
+    - [x] Build Bootstrap Image
+    - [x] Push Image to registry
 - [ ] Create & Deploy Secrets
-    - [ ] Bootstrap
+    - [x] Bootstrap
     - [ ] Validator (regular)
     - [ ] RPC nodes
     - [ ] Client
 - [ ] Create & Deploy Selector
-    - [ ] Bootstrap
+    - [x] Bootstrap
     - [ ] Validator (regular)
     - [ ] RPC nodes
     - [ ] Client
 - [ ] Create & Deploy Replica Set
-    - [ ] Bootstrap
+    - [x] Bootstrap
     - [ ] Validator (regular)
     - [ ] RPC nodes
     - [ ] Client
 - [ ] Create & Deploy Services
-    - [ ] Bootstrap
+    - [x] Bootstrap
     - [ ] Validator (regular)
     - [ ] RPC nodes
     - [ ] Client
-- [ ] Check Bootstrap is deployed and running
-- [ ] Build and deploy Load Balancer (sits in front of bootstrap and RPC nodes)
+- [x] Check Bootstrap is deployed and running
+- [x] Build and deploy Load Balancer (sits in front of bootstrap and RPC nodes)
 - [ ] Add metrics
-    - [ ] Bootstrap
+    - [x] Bootstrap
     - [ ] Validator (regular)
     - [ ] RPC nodes
     - [ ] Client
@@ -69,7 +69,7 @@ Above, we start with bootstrap, and then we do validators (regular), and then we
     - Use command line flags to set type of client, tx-count, etc
 
 - [ ] Add in kubernetes deployment flags
-    - [ ] CPU/Memory Requests
+    - [x] CPU/Memory Requests
     - [ ] Node Affinity -> Regions
     - [ ] Node Affinity -> Node Type (Equinix/Lumen)
 

README.md

@@ -36,7 +36,7 @@ cargo run --bin cluster --
     --release-channel <agave-version: e.g. v1.17.28> # note: MUST include the "v" 
 ```
 
-#### Build from Local Repo and Configure Genesis
+#### Build from Local Repo and Configure Genesis and Bootstrap Validator Image
 Example:
 ```
 cargo run --bin cluster -- 
@@ -51,4 +51,57 @@ cargo run --bin cluster --
     --max-genesis-archive-unpacked-size <size in bytes>
     --target-lamports-per-signature <lamports-per-signature>
     --slots-per-epoch <slots-per-epoch>
+    # docker config
+    --registry <docker-registry>        # e.g. gregcusack 
+    --tag <docker-image-tag>            # e.g. v1
+    --base-image <base-image>           # e.g. ubuntu:20.04
+    --image-name <docker-image-name>    # e.g. cluster-image
+```
+
+## Metrics
+1) Setup metrics database:
+```
+cd scripts/
+./init-metrics -c <database-name> <metrics-username>
+# enter password when promted
+```
+2) add the following to your `cluster` command from above
+```
+--metrics-host https://internal-metrics.solana.com # need the `https://` here
+--metrics-port 8086
+--metrics-db <database-name>            # from (1)
+--metrics-username <metrics-username>   # from (1)
+--metrics-password <metrics-password>   # from (1)
+```
+
+
+## Kubernetes Cheatsheet
+Create namespace:
+```
+kubectl create ns <namespace>
+```
+
+Delete namespace:
+```
+kubectl delete ns <namespace>
+```
+
+Get running pods:
+```
+kubectl get pods -n <namespace>
+```
+
+Get pod logs:
+```
+kubectl logs -n <namespace> <pod-name>
+```
+
+Exec into pod:
+```
+kubectl exec -it -n <namespace> <pod-name> -- /bin/bash
+```
+
+Get information about pod:
+```
+kubectl describe pod -n <namespace> <pod-name>
 ```

scripts/init-metrics.sh

@@ -0,0 +1,87 @@
+#!/usr/bin/env bash
+set -e
+
+here=$(dirname "$0")
+# shellcheck source=net/common.sh
+source "$here"/common.sh
+
+usage() {
+  exitcode=0
+  if [[ -n "$1" ]]; then
+    exitcode=1
+    echo "Error: $*"
+  fi
+  cat <<EOF
+usage: $0 [-e] [-d] [-c database_name] [username]
+
+Creates a testnet dev metrics database
+
+  username        InfluxDB user with access to create a new database
+  -c              Manually specify a database to create, rather than read from config file
+  -d              Delete the database instead of creating it
+  -e              Assume database already exists and SOLANA_METRICS_CONFIG is
+                  defined in the environment already
+
+EOF
+  exit $exitcode
+}
+
+useEnv=false
+delete=false
+createWithoutConfig=false
+host="https://internal-metrics.solana.com:8086"
+while getopts ":hdec:" opt; do
+  case $opt in
+  h)
+    usage
+    exit 0
+    ;;
+  c)
+    createWithoutConfig=true
+    netBasename=$OPTARG
+    ;;
+  d)
+    delete=true
+    ;;
+  e)
+    useEnv=true
+    ;;
+  *)
+    usage "unhandled option: $OPTARG"
+    ;;
+  esac
+done
+shift $((OPTIND - 1))
+
+if $useEnv; then
+  [[ -n $SOLANA_METRICS_CONFIG ]] ||
+    usage "SOLANA_METRICS_CONFIG is not defined in the environment"
+else
+  username=$1
+  [[ -n "$username" ]] || usage "username not specified"
+
+  read -rs -p "InfluxDB password for $username: " password
+  [[ -n $password ]] || { echo "Password not specified"; exit 1; }
+  echo
+
+  password="$(urlencode "$password")"
+
+  query() {
+    echo "$*"
+    set -x
+    curl -XPOST \
+      "$host/query?u=${username}&p=${password}" \
+      --data-urlencode "q=$*"
+  }
+
+  query "DROP DATABASE \"$netBasename\""
+  ! $delete || exit 0
+  query "CREATE DATABASE \"$netBasename\""
+  query "ALTER RETENTION POLICY autogen ON \"$netBasename\" DURATION 7d"
+  query "GRANT READ ON \"$netBasename\" TO \"ro\""
+  query "GRANT WRITE ON \"$netBasename\" TO \"scratch_writer\""
+
+  SOLANA_METRICS_CONFIG="host=$host,db=$netBasename,u=scratch_writer,p=topsecret"
+fi
+
+exit 0