cardano-tracer: Allow switching EKG service between different nodes.

cabal.project

@@ -48,7 +48,7 @@ package cryptonite
   flags: -support_rdrand
 
 package snap-server
-  flags: +openssl
+  flags: -openssl
 
 package bitvec
   flags: -simd
@@ -62,8 +62,8 @@ constraints:
 
 allow-newer:
   , katip:Win32
+  , ekg-wai:time
 
 -- IMPORTANT
 -- Do NOT add more source-repository-package stanzas here unless they are strictly
 -- temporary! Please read the section in CONTRIBUTING about updating dependencies.
-

cardano-tracer/CHANGELOG.md

@@ -1,5 +1,16 @@
 # ChangeLog
 
+## 0.3 (September 20, 2024)
+
+* Abondon `snap` webserver in favour of `wai`/`warp` for Prometheus and EKG Monitoring.
+* Add dynamic routing to EKG stores of all connected nodes.
+* Derive URL compliant routes from connected node names (instead of plain node names).
+* Remove the requirement of two distinct ports for the EKG backend (changing `hasEKG` config type).
+* For optional RTView component only: Disable SSL/https connections. Force `snap-server`
+  dependency to build with `-flag -openssl`.
+* Add JSON responses when listing connected nodes for both Prometheus and EKG Monitoring.
+* Add consistency check for redundant port values in the config.
+
 ## 0.2.4 (August 13, 2024)
 
 * `systemd` is enabled by default. To disable it use the cabal

cardano-tracer/cardano-tracer.cabal

@@ -1,7 +1,7 @@
 cabal-version: 3.0
 
 name:                   cardano-tracer
-version:                0.2.4
+version:                0.3
 synopsis:               A service for logging and monitoring over Cardano nodes
 description:            A service for logging and monitoring over Cardano nodes.
 category:               Cardano,
@@ -18,7 +18,7 @@ extra-doc-files:        README.md
 
 flag rtview
   description:          Enable RTView. False by default. Enable with `-f +rtview`.
-  default:              False
+  default:              True
   manual:               True
 
 flag systemd
@@ -159,7 +159,7 @@ library
 
   build-depends:        aeson
                       , async
-                      , async-extras
+                      , auto-update
                       , bimap
                       , blaze-html
                       , bytestring
@@ -168,21 +168,20 @@ library
                       , containers
                       , contra-tracer
                       , directory
-                      , ekg
                       , ekg-core
                       , ekg-forward ^>= 0.5
+                      , ekg-wai
                       , extra
                       , filepath
+                      , http-types
                       , mime-mail
                       , optparse-applicative
                       , ouroboros-network ^>= 0.17
                       , ouroboros-network-api
                       , ouroboros-network-framework
                       , signal
+                      , slugify
                       , smtp-mail ^>= 0.5
-                      , snap-blaze
-                      , snap-core
-                      , snap-server
                       , stm
                       , string-qq
                       , text
@@ -191,6 +190,9 @@ library
                       , trace-forward
                       , trace-resources
                       , unordered-containers
+                      , utf8-string
+                      , wai ^>= 3.2
+                      , warp ^>= 3.4
                       , yaml
 
   if flag(systemd) && os(linux)
@@ -281,8 +283,7 @@ library demo-acceptor-lib
 
   exposed-modules:      Cardano.Tracer.Test.Acceptor
 
-  build-depends:        async-extras
-                      , bytestring
+  build-depends:        bytestring
                       , cardano-tracer
                       , containers
                       , extra

cardano-tracer/configuration/complete-example.json

@@ -6,16 +6,10 @@
   },
   "loRequestNum": 100,
   "ekgRequestFreq": 2,
-  "hasEKG": [
-    {
-      "epHost": "127.0.0.1",
-      "epPort": 3100
-    },
-    {
-      "epHost": "127.0.0.1",
-      "epPort": 3101
-    }
-  ],
+  "hasEKG": {
+    "epHost": "127.0.0.1",
+    "epPort": 3100
+  },
   "hasPrometheus": {
     "epHost": "127.0.0.1",
     "epPort": 3000

cardano-tracer/configuration/complete-example.yaml

@@ -7,10 +7,8 @@ network:
 loRequestNum: 100
 ekgRequestFreq: 2
 hasEKG:
-- epHost: 127.0.0.1
+  epHost: 127.0.0.1
   epPort: 3100
-- epHost: 127.0.0.1
-  epPort: 3101
 hasPrometheus:
   epHost: 127.0.0.1
   epPort: 3000

cardano-tracer/demo/multi/active-tracer-config.json

@@ -8,16 +8,10 @@
       "/run/user/1000/cardano-tracer-demo-3.sock"
     ]
   },
-  "hasEKG": [
-    {
+  "hasEKG": {
       "epHost": "127.0.0.1",
       "epPort": 3100
-    },
-    {
-      "epHost": "127.0.0.1",
-      "epPort": 3101
-    }
-  ],
+  },
   "hasPrometheus": {
     "epHost": "127.0.0.1",
     "epPort": 3000

cardano-tracer/demo/multi/passive-tracer-config.json

@@ -4,16 +4,10 @@
     "tag": "AcceptAt",
     "contents": "/run/user/1000/cardano-tracer-demo-1.sock"
   },
-  "hasEKG": [
-    {
-      "epHost": "127.0.0.1",
-      "epPort": 3100
-    },
-    {
-      "epHost": "127.0.0.1",
-      "epPort": 3101
-    }
-  ],
+  "hasEKG": {
+    "epHost": "127.0.0.1",
+    "epPort": 3100
+  },
   "hasPrometheus": {
     "epHost": "127.0.0.1",
     "epPort": 3000

cardano-tracer/docs/cardano-tracer.md

@@ -337,6 +337,14 @@ The fields `rpMaxAgeMinutes`, `rpMaxAgeHours` specify the lifetime of the log fi
 
 ## Prometheus
 
+At top-level route `/` Promtheus gives a list of connected nodes.
+
+The responses are either human-readable names (HTML) with clickable
+links, or JSON mapping from connected node names to relative URLs.
+
+The routes dynamically depend on the connected nodes, the node names
+are [sluggified](https://hackage.haskell.org/package/slugify).
+
 The optional field `hasPrometheus` specifies the host and port of the web page with metrics. For example:
 
 ```
@@ -374,24 +382,22 @@ rts_gc_cumulative_bytes_used 184824
 
 ## EKG Monitoring
 
-The optional field `hasEKG` specifies the hosts and ports of two web pages:
+At top-level route `/` EKG gives a list of connected nodes.
 
-1. the list of identifiers of connected nodes,
-2. EKG monitoring page.
+The responses are either human-readable names (HTML) with clickable
+links, or JSON mapping from connected node names to relative URLs.
 
-For example, if you use JSON configuration file:
+The routes dynamically depend on the connected nodes, the node names
+are [sluggified](https://hackage.haskell.org/package/slugify).
+
+The optional field `hasEKG` specifies the host and port of the web
+page with metrics. For example:
 
 ```
-"hasEKG": [
-  {
-    "epHost": "127.0.0.1",
-    "epPort": 3100
-  },
-  {
-    "epHost": "127.0.0.1",
-    "epPort": 3101
-  }
-]
+"hasEKG": {
+  "epHost": "127.0.0.1",
+  "epPort": 3100
+}
 ```
 
 The page with the list of identifiers of connected nodes will be available at `http://127.0.0.1:3100`, for example:

cardano-tracer/src/Cardano/Tracer/Acceptors/Utils.hs

@@ -1,7 +1,6 @@
 {-# LANGUAGE NamedFieldPuns #-}
-#if RTVIEW
 {-# LANGUAGE OverloadedStrings #-}
-#endif
+{-# LANGUAGE TupleSections #-}
 
 module Cardano.Tracer.Acceptors.Utils
   ( prepareDataPointRequestor
@@ -26,6 +25,7 @@ import           Control.Concurrent.STM.TVar (TVar, modifyTVar', newTVarIO)
 import qualified Data.Bimap as BM
 import qualified Data.Map.Strict as M
 import qualified Data.Set as S
+import           Data.Time.Clock.POSIX (getPOSIXTime)
 #if RTVIEW
 import           Data.Time.Clock.System (getSystemTime, systemToUTCTime)
 #endif
@@ -51,12 +51,26 @@ prepareMetricsStores
   -> IO (EKG.Store, TVar MetricsLocalStore)
 prepareMetricsStores TracerEnv{teConnectedNodes, teAcceptedMetrics} connId = do
   addConnectedNode teConnectedNodes connId
-  storesForNewNode <- (,) <$> EKG.newStore
-                          <*> newTVarIO emptyMetricsLocalStore
-  atomically $
-    modifyTVar' teAcceptedMetrics $ M.insert (connIdToNodeId connId) storesForNewNode
+  store <- EKG.newStore
+
+  EKG.registerCounter "ekg.server_timestamp_ms" getTimeMs store
+  storesForNewNode <- (store ,) <$> newTVarIO emptyMetricsLocalStore
+
+  atomically do
+    modifyTVar' teAcceptedMetrics do
+      M.insert (connIdToNodeId connId) storesForNewNode
+
   return storesForNewNode
 
+  where
+    -- forkServer definition of `getTimeMs'. The ekg frontend relies
+    -- on the "ekg.server_timestamp_ms" metric being in every
+    -- store. While forkServer adds that that automatically we must
+    -- manually add it.
+    -- url
+    --  + https://github.com/tvh/ekg-wai/blob/master/System/Remote/Monitoring/Wai.hs#L237-L238
+    getTimeMs = (round . (* 1000)) `fmap` getPOSIXTime
+
 addConnectedNode
   :: ConnectedNodes
   -> ConnectionId LocalAddress