IntersectMBO · mgmeier · Sep 25, 2024 · Aug 20, 2024
@@ -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.
-
@@ -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

@@ -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,
@@ -155,11 +155,12 @@ library
                         cardano-git-rev ^>=0.2.2
                       , cassava
                       , threepenny-gui
+                      , utf8-string
                       , vector
 
   build-depends:        aeson
                       , async
-                      , async-extras
+                      , auto-update
                       , bimap
                       , blaze-html
                       , bytestring
@@ -168,21 +169,20 @@ library
                       , containers
                       , contra-tracer
                       , directory
-                      , ekg
                       , ekg-core
-                      , ekg-forward ^>= 0.5
+                      , 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 +191,8 @@ library
                       , trace-forward
                       , trace-resources
                       , unordered-containers
+                      , 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

@@ -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

@@ -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

@@ -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

@@ -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

@@ -337,72 +337,135 @@ The fields `rpMaxAgeMinutes`, `rpMaxAgeHours` specify the lifetime of the log fi
 
 ## Prometheus
 
-The optional field `hasPrometheus` specifies the host and port of the web page with metrics. For example:
+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,
+depending on desired content type (`Accept:` header of the request).
+
+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 Prometheus metrics. For example:
 
 ```
 "hasPrometheus": {
   "epHost": "127.0.0.1",
-  "epPort": 3000
+  "epPort": 3200
 }
 ```
 
-Here the web page is available at `http://127.0.0.1:3000`. Please note that if you skip this field, the web page will not be available.
+With this example, the list of clickable identifiers of connected
+nodes will be available at `http://127.0.0.1:3200`, such as:
+
+```
+* 127.0.0.1:30004
+* 127.0.0.1:30001
+* 127.0.0.1:30005
+* 127.0.0.1:30000
+* 127.0.0.1:30003
+* 127.0.0.1:30002
+* TxGenerator
+```
+
+Clicking an identifier will take you to its monitoring page. For
+example clicking on `127.0.0.1:30004` displays the monitoring metrics
+at `http://localhost:3200/12700130004`.
 
-After you open `http://127.0.0.1:3000` in your browser, you will see the list of identifiers of connected nodes (or the warning message, if there are no connected nodes yet), for example:
+Sending a HTTP GET request with a JSON Accept header gives the metrics
+of the top-level route, or identifier as JSON. `jq '.'` pretty-prints
+the JSON object.
 
 ```
-* tmp-forwarder.sock@0
-* tmp-forwarder.sock@1
-* tmp-forwarder.sock@2
+$ curl --silent -H "Accept: application/json" '127.0.0.1:3200' | jq '.'
+{
+  "127.0.0.1:30000": "/12700130000",
+  "127.0.0.1:30001": "/12700130001",
+  "127.0.0.1:30002": "/12700130002",
+  "127.0.0.1:30003": "/12700130003",
+  "127.0.0.1:30004": "/12700130004",
+  "127.0.0.1:30005": "/12700130005",
+  "TxGenerator": "/txgenerator"
+}
 ```
 
-Each identifier is a hyperlink to the page where you will see the **current** list of metrics received from the corresponding node, in such a format:
+The Promethus output is a map from Prometheus metric to value:
 
 ```
+$ curl '127.0.0.1:3200/12700130004'
+blockNum_int 35
+rts_gc_init_cpu_ms 5
 rts_gc_par_tot_bytes_copied 0
-rts_gc_num_gcs 2
-rts_gc_max_bytes_slop 15880
-rts_gc_num_bytes_usage_samples 1
-rts_gc_wall_ms 4005
-...
-rts_gc_par_max_bytes_copied 0
-rts_gc_mutator_cpu_ms 57
-rts_gc_mutator_wall_ms 4004
-rts_gc_gc_cpu_ms 1
-rts_gc_cumulative_bytes_used 184824
+served_block_counter 31
+submissions_accepted_counter 2771
+density_real 5.7692307692307696e-2
+blocksForged_int 6
+
 ```
 
 ## 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.
+
+The responses are either human-readable names (HTML) with clickable
+links, or JSON mapping from connected node names to relative URLs,
+depending on desired content type (`Accept:` header of the request).
 
-1. the list of identifiers of connected nodes,
-2. EKG monitoring page.
+The routes dynamically depend on the connected nodes, the node names
+are [sluggified](https://hackage.haskell.org/package/slugify).
 
-For example, if you use JSON configuration file:
+The optional field `hasEKG` specifies the host and port of the web
+page with EKG 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:
+With this example, the list of clickable identifiers of connected
+nodes will be available at `http://127.0.0.1:3100`, such as:
 
 ```
-* tmp-forwarder.sock@0
-* tmp-forwarder.sock@1
-* tmp-forwarder.sock@2
+* 127.0.0.1:30004
+* 127.0.0.1:30001
+* 127.0.0.1:30005
+* 127.0.0.1:30000
+* 127.0.0.1:30003
+* 127.0.0.1:30002
+* TxGenerator
 ```
 
-Each identifier is a hyperlink, after clicking to it you will be redirected to `http://127.0.0.1:3101` where you will see EKG monitoring page for corresponding node.
+Clicking an identifier will take you to its monitoring page. For
+example clicking on `127.0.0.1:30004` displays the monitoring metrics
+at `http://localhost:3100/12700130004`.
+
+Sending a HTTP GET request with a JSON Accept header gives the metrics
+of an identifier as JSON. `jq '.'` pretty-prints the JSON object.
+
+```
+$ curl --silent -H 'Accept: application/json' '127.0.0.1:3100/12700130004' | jq '.'
+{
+  "ChainSync": {
+    "HeadersServed_counter": {
+      "type": "c",
+      "val": 24
+    }
+  },
+  "Mem": {
+    "resident_int": {
+      "type": "g",
+      "val": 91877376
+    }
+  },
+  "RTS": {
+    "alloc_int": {
+      "type": "g",
+      "val": 1014189896
+    },
+```
 
 ## Verbosity
 

@@ -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