Add statistics to query_range and instant_query API. (#1615)

* Refactor stats package to use proto. Signed-off-by: Cyril Tovena <[email protected]> * Merge statistics in the frontend. Signed-off-by: Cyril Tovena <[email protected]> * Improve engine logging. Signed-off-by: Cyril Tovena <[email protected]> * Fixes GRPC by rolling back Signed-off-by: Cyril Tovena <[email protected]> * Add a test to verify stats in the LogQL engine. Signed-off-by: Cyril Tovena <[email protected]> * Set circle ci build image to 0.9.1 which contains protobuf regression Signed-off-by: Cyril Tovena <[email protected]> * Fix drone CI. Signed-off-by: Cyril Tovena <[email protected]> * Change timing data from nanoseconds to seconds like Prometheus. Signed-off-by: Cyril Tovena <[email protected]> * Improve naming of stats Signed-off-by: Cyril Tovena <[email protected]> * Move stats property under data property like Prometheus. Signed-off-by: Cyril Tovena <[email protected]> * Adjust queryrange frontend to use the new stats property Signed-off-by: Cyril Tovena <[email protected]> * Cleanup unused structs. Signed-off-by: Cyril Tovena <[email protected]> * Add documentation for stats API. Signed-off-by: Cyril Tovena <[email protected]> * Format proto file. Signed-off-by: Cyril Tovena <[email protected]> * Adds missing godoc on logql.Result Signed-off-by: Cyril Tovena <[email protected]>
grafana · Feb 4, 2020 · 93eb4ad · 93eb4ad
1 parent 1773900
commit 93eb4ad
Show file tree

Hide file tree

Showing 32 changed files with 3,595 additions and 917 deletions.
diff --git a/.circleci/config.yml b/.circleci/config.yml
@@ -47,7 +47,7 @@ workflows:
 # https://circleci.com/blog/circleci-hacks-reuse-yaml-in-your-circleci-config-with-yaml/
 .defaults: &defaults
   docker:
-    - image: grafana/loki-build-image:0.9.0
+    - image: grafana/loki-build-image:0.9.1
   working_directory: /src/loki
 
 jobs:

diff --git a/.drone/drone.yml b/.drone/drone.yml
@@ -12,28 +12,28 @@ workspace:
 
 steps:
 - name: test
-  image: grafana/loki-build-image:0.9.0
+  image: grafana/loki-build-image:0.9.1
   commands:
   - make BUILD_IN_CONTAINER=false test
   depends_on:
   - clone
 
 - name: lint
-  image: grafana/loki-build-image:0.9.0
+  image: grafana/loki-build-image:0.9.1
   commands:
   - make BUILD_IN_CONTAINER=false lint
   depends_on:
   - clone
 
 - name: check-generated-files
-  image: grafana/loki-build-image:0.9.0
+  image: grafana/loki-build-image:0.9.1
   commands:
   - make BUILD_IN_CONTAINER=false check-generated-files
   depends_on:
   - clone
 
 - name: check-mod
-  image: grafana/loki-build-image:0.9.0
+  image: grafana/loki-build-image:0.9.1
   commands:
   - make BUILD_IN_CONTAINER=false check-mod
   depends_on:
@@ -562,7 +562,7 @@ platform:
 
 steps:
 - name: trigger
-  image: grafana/loki-build-image:0.9.0
+  image: grafana/loki-build-image:0.9.1
   commands:
   - ./tools/deploy.sh
   environment:

diff --git a/Makefile b/Makefile
@@ -38,7 +38,7 @@ IMAGE_NAMES := $(foreach dir,$(DOCKER_IMAGE_DIRS),$(patsubst %,$(IMAGE_PREFIX)%,
 # make BUILD_IN_CONTAINER=false target
 # or you can override this with an environment variable
 BUILD_IN_CONTAINER ?= true
-BUILD_IMAGE_VERSION := 0.9.0
+BUILD_IMAGE_VERSION := 0.9.1
 
 # Docker image info
 IMAGE_PREFIX ?= grafana

diff --git a/cmd/docker-driver/Dockerfile b/cmd/docker-driver/Dockerfile
@@ -1,4 +1,4 @@
-ARG BUILD_IMAGE=grafana/loki-build-image:0.9.0
+ARG BUILD_IMAGE=grafana/loki-build-image:0.9.1
 # Directories in this file are referenced from the root of the project not this folder
 # This file is intended to be called from the root like so:
 # docker build -t grafana/loki -f cmd/loki/Dockerfile .

diff --git a/cmd/loki-canary/Dockerfile.cross b/cmd/loki-canary/Dockerfile.cross
@@ -1,4 +1,4 @@
-ARG BUILD_IMAGE=grafana/loki-build-image:0.9.0
+ARG BUILD_IMAGE=grafana/loki-build-image:0.9.1
 # Directories in this file are referenced from the root of the project not this folder
 # This file is intended to be called from the root like so:
 # docker build -t grafana/promtail -f cmd/promtail/Dockerfile .

diff --git a/cmd/loki/Dockerfile.cross b/cmd/loki/Dockerfile.cross
@@ -1,4 +1,4 @@
-ARG BUILD_IMAGE=grafana/loki-build-image:0.9.0
+ARG BUILD_IMAGE=grafana/loki-build-image:0.9.1
 # Directories in this file are referenced from the root of the project not this folder
 # This file is intended to be called from the root like so:
 # docker build -t grafana/loki -f cmd/loki/Dockerfile .

diff --git a/cmd/promtail/Dockerfile.cross b/cmd/promtail/Dockerfile.cross
@@ -1,4 +1,4 @@
-ARG BUILD_IMAGE=grafana/loki-build-image:0.9.0
+ARG BUILD_IMAGE=grafana/loki-build-image:0.9.1
 # Directories in this file are referenced from the root of the project not this folder
 # This file is intended to be called from the root like so:
 # docker build -t grafana/promtail -f cmd/promtail/Dockerfile .
@@ -23,4 +23,3 @@ COPY --from=build /src/loki/cmd/promtail/promtail /usr/bin/promtail
 COPY cmd/promtail/promtail-local-config.yaml /etc/promtail/local-config.yaml
 COPY cmd/promtail/promtail-docker-config.yaml /etc/promtail/docker-config.yaml
 ENTRYPOINT ["/usr/bin/promtail"]
-
diff --git a/docs/api.md b/docs/api.md
@@ -35,7 +35,7 @@ These endpoints are exposed by all components:
 - [`GET /ready`](#get-ready)
 - [`GET /metrics`](#get-metrics)
 
-These endpoints are exposed by just the querier:
+These endpoints are exposed by the querier and the frontend:
 
 - [`GET /loki/api/v1/query`](#get-lokiapiv1query)
 - [`GET /loki/api/v1/query_range`](#get-lokiapiv1query_range)
@@ -86,7 +86,7 @@ query parameters support the following values:
 - `time`: The evaluation time for the query as a nanosecond Unix epoch. Defaults to now.
 - `direction`: Determines the sort order of logs. Supported values are `forward` or `backward`. Defaults to `backward.`
 
-In microservices mode, `/loki/api/v1/query` is exposed by the querier.
+In microservices mode, `/loki/api/v1/query` is exposed by the querier and the frontend.
 
 Response:
 
@@ -95,7 +95,8 @@ Response:
   "status": "success",
   "data": {
     "resultType": "vector" | "streams",
-    "result": [<vector value>] | [<stream value>]
+    "result": [<vector value>] | [<stream value>].
+    "stats" : [<statistics>]
   }
 }
 ```
@@ -131,6 +132,8 @@ And `<stream value>` is:
 }
 ```
 
+See [statistics](#Statistics) for information about the statistics returned by Loki.
+
 ### Examples
 
 ```bash
@@ -165,7 +168,10 @@ $ curl -G -s  "http://localhost:3100/loki/api/v1/query" --data-urlencode 'query=
           "37.69"
         ]
       }
-    ]
+    ],
+    "stats": {
+      ...
+    }
   }
 }
 ```
@@ -192,9 +198,12 @@ $ curl -G -s  "http://localhost:3100/loki/api/v1/query" --data-urlencode 'query=
             "1568234269716526880",
             "bar"
           ]
-        ]
+        ],
       }
-    ]
+    ],
+    "stats": {
+      ...
+    }
   }
 }
 ```
@@ -216,7 +225,7 @@ find log streams for particular labels. Because the index store is spread out by
 time, the time span covered by `start` and `end`, if large, may cause additional
 load against the index server and result in a slow query.
 
-In microservices mode, `/loki/api/v1/query_range` is exposed by the querier.
+In microservices mode, `/loki/api/v1/query_range` is exposed by the querier and the frontend.
 
 Response:
 
@@ -226,6 +235,7 @@ Response:
   "data": {
     "resultType": "matrix" | "streams",
     "result": [<matrix value>] | [<stream value>]
+    "stats" : [<statistics>]
   }
 }
 ```
@@ -261,6 +271,8 @@ And `<stream value>` is:
 }
 ```
 
+See [statistics](#Statistics) for information about the statistics returned by Loki.
+
 ### Examples
 
 ```bash
@@ -308,7 +320,10 @@ $ curl -G -s  "http://localhost:3100/loki/api/v1/query_range" --data-urlencode '
           ]
         ]
       }
-    ]
+    ],
+    "stats": {
+      ...
+    }
   }
 }
 ```
@@ -337,7 +352,10 @@ $ curl -G -s  "http://localhost:3100/loki/api/v1/query_range" --data-urlencode '
           ]
         ]
       }
-    ]
+    ],
+    "stats": {
+      ...
+    }
   }
 }
 ```
@@ -564,7 +582,7 @@ support the following values:
 - `direction`: Determines the sort order of logs. Supported values are `forward` or `backward`. Defaults to `backward.`
 - `regexp`: a regex to filter the returned results
 
-In microservices mode, `/api/prom/query` is exposed by the querier.
+In microservices mode, `/api/prom/query` is exposed by the querier and the frontend.
 
 Note that the larger the time span between `start` and `end` will cause
 additional load on Loki and the index store, resulting in slower queries.
@@ -585,10 +603,13 @@ Response:
       ],
     },
     ...
-  ]
+  ],
+  "stats": [<statistics>]
 }
 ```
 
+See [statistics](#Statistics) for information about the statistics returned by Loki.
+
 ### Examples
 
 ```bash
@@ -608,7 +629,10 @@ $ curl -G -s  "http://localhost:3100/api/prom/query" --data-urlencode '{foo="bar
         }
       ]
     }
-  ]
+  ],
+  "stats": {
+    ...
+  }
 }
 ```
 
@@ -822,3 +846,49 @@ $ curl -s "http://localhost:3100/loki/api/v1/series" --data-urlencode 'match={co
   ]
 }
 ```
+
+## Statistics
+
+Query endpoints such as `/api/prom/query`, `/loki/api/v1/query` and `/loki/api/v1/query_range` return a set of statistics about the query execution. Those statistics allow users to understand the amount of data processed and at which speed.
+
+The example belows show all possible statistics returned with their respective description.
+
+```json
+{
+  "status": "success",
+  "data": {
+    "resultType": "streams",
+    "result": [],
+    "stats": {
+     "ingester" : {
+        "compressedBytes": 0, // Total bytes of compressed chunks (blocks) processed by ingesters
+        "decompressedBytes": 0, // Total bytes decompressed and processed by ingesters
+        "decompressedLines": 0, // Total lines decompressed and processed by ingesters
+        "headChunkBytes": 0, // Total bytes read from ingesters head chunks
+        "headChunkLines": 0, // Total lines read from ingesters head chunks
+        "totalBatches": 0, // Total batches sent by ingesters
+        "totalChunksMatched": 0, // Total chunks matched by ingesters
+        "totalDuplicates": 0, // Total of duplicates found by ingesters
+        "totalLinesSent": 0, // Total lines sent by ingesters
+        "totalReached": 0 // Amount of ingesters reached.
+      },
+      "store": {
+        "compressedBytes": 0, // Total bytes of compressed chunks (blocks) processed by the store
+        "decompressedBytes": 0,  // Total bytes decompressed and processed by the store
+        "decompressedLines": 0, // Total lines decompressed and processed by the store
+        "chunksDownloadTime": 0, // Total time spent downloading chunks in seconds (float)
+        "totalChunksRef": 0, // Total chunks found in the index for the current query
+        "totalChunksDownloaded": 0, // Total of chunks downloaded
+        "totalDuplicates": 0 // Total of duplicates removed from replication
+      },
+      "summary": {
+        "bytesProcessedPerSeconds": 0, // Total of bytes processed per seconds
+        "execTime": 0, // Total execution time in seconds (float)
+        "linesProcessedPerSeconds": 0, // Total lines processed per second
+        "totalBytesProcessed":0, // Total amount of bytes processed overall for this request
+        "totalLinesProcessed":0 // Total amount of lines processed overall for this request
+      }
+    }
+  }
+}
+```
diff --git a/loki-build-image/Dockerfile b/loki-build-image/Dockerfile
@@ -41,8 +41,8 @@ COPY --from=drone /go/bin/drone /usr/bin/drone
 # It's possible this can be revisited in newer versions of Go if the behavior around GOPATH vs GO111MODULES changes
 RUN GO111MODULE=on go get \
     github.com/golang/protobuf/[email protected] \
-    github.com/gogo/protobuf/protoc-gen-gogoslick@v1.3.0 \
-    github.com/gogo/protobuf/gogoproto@v1.3.0 \
+    github.com/gogo/protobuf/protoc-gen-gogoslick@v1.2.1 \
+    github.com/gogo/protobuf/gogoproto@v1.2.1 \
     github.com/go-delve/delve/cmd/dlv \
     # Due to the lack of a proper release tag, we use the commit hash of
     # https://github.com/golang/tools/releases v0.1.7

diff --git a/pkg/iter/iterator.go b/pkg/iter/iterator.go
@@ -21,6 +21,16 @@ type EntryIterator interface {
 	Close() error
 }
 
+type noOpIterator struct{}
+
+var NoopIterator = noOpIterator{}
+
+func (noOpIterator) Next() bool            { return false }
+func (noOpIterator) Error() error          { return nil }
+func (noOpIterator) Labels() string        { return "" }
+func (noOpIterator) Entry() logproto.Entry { return logproto.Entry{} }
+func (noOpIterator) Close() error          { return nil }
+
 // streamIterator iterates over entries in a stream.
 type streamIterator struct {
 	i       int

diff --git a/pkg/loghttp/query.go b/pkg/loghttp/query.go
@@ -9,6 +9,7 @@ import (
 	"unsafe"
 
 	"github.com/grafana/loki/pkg/logproto"
+	"github.com/grafana/loki/pkg/logql/stats"
 	json "github.com/json-iterator/go"
 	"github.com/prometheus/common/model"
 )
@@ -55,8 +56,9 @@ type ResultValue interface {
 
 //QueryResponseData represents the http json response to a label query
 type QueryResponseData struct {
-	ResultType ResultType  `json:"resultType"`
-	Result     ResultValue `json:"result"`
+	ResultType ResultType   `json:"resultType"`
+	Result     ResultValue  `json:"result"`
+	Statistics stats.Result `json:"stats"`
 }
 
 // Type implements the promql.Value interface
@@ -98,8 +100,9 @@ type Entry struct {
 // UnmarshalJSON implements the json.Unmarshaler interface.
 func (q *QueryResponseData) UnmarshalJSON(data []byte) error {
 	unmarshal := struct {
-		Type   ResultType      `json:"resultType"`
-		Result json.RawMessage `json:"result"`
+		Type       ResultType      `json:"resultType"`
+		Result     json.RawMessage `json:"result"`
+		Statistics stats.Result    `json:"stats"`
 	}{}
 
 	err := json.Unmarshal(data, &unmarshal)
@@ -133,6 +136,7 @@ func (q *QueryResponseData) UnmarshalJSON(data []byte) error {
 
 	q.ResultType = unmarshal.Type
 	q.Result = value
+	q.Statistics = unmarshal.Statistics
 
 	return nil
 }