mirror of https://github.com/grafana/loki
Flag categorize labels on streams response (#10419)
We recently introduced support for ingesting and querying structured metadata in Loki. This adds a new dimension to Loki's labels since now we arguably have three categories of labels: _stream_, _structured metadata_, and _parsed_ labels. Depending on the origin of the labels, they should be used in LogQL expressions differently to achieve optimal performance. _stream_ labels should be added to stream matchers, _structured metadata_ labels should be used in a filter expression before any parsing expression, and _parsed_ labels should be placed after the parser expression extracting them. The Grafana UI has a hard time dealing with this same problem. Before https://github.com/grafana/grafana/pull/73955, the filtering functionality in Grafana was broken since it was not able to distinguish between _stream_ and _structured metadata_ labels. Also, as soon as a parser expression was added to the query, filters added by Grafana would be appended to the end of the query regardless of the label category. The PR above implements a workaround for this problem but needs a better API on Loki's end to mitigate all corner cases. Loki currently returns the following JSON for log queries: ```json ... { "stream": { "cluster": "us-central", "container": "query-frontend", "namespace": "loki", "level": "info", "traceID": "68810cf0c94bfcca" }, "values": [ [ "1693996529000222496", "1693996529000222496 aaaaaaaaa.....\n" ], ... }, { "stream": { "cluster": "us-central", "container": "query-frontend", "namespace": "loki", "level": "debug", "traceID": "a7116cj54c4bjz8s" }, "values": [ [ "1693996529000222497", "1693996529000222497 bbbbbbbbb.....\n" ], ... }, ... ``` As can be seen, there is no way we can distinguish the category of each label. This PR introduces a new flag `X-Loki-Response-Encoding-Flags: categorize-labels` that makes Loki return categorized labels as follows: ```json ... { "stream": { "cluster": "us-central", "container": "query-frontend", "namespace": "loki", }, "values": [ [ "1693996529000222496", "1693996529000222496 aaaaaaaaa.....\n", { "structuredMetadata": { "traceID": "68810cf0c94bfcca" }, "parsed": { "level": "info" } } ], [ "1693996529000222497", "1693996529000222497 bbbbbbbbb.....\n", { "structuredMetadata": { "traceID": "a7116cj54c4bjz8s" }, "parsed": { "level": "debug" } } ], ... }, ... ``` Note that this PR only supports log queries, not metric queries. From a UX perspective, being able to categorize labels in metric queries doesn't have any benefit yet. Having said that, supporting this for metric queries would require some minor refactoring on top of what has been implemented here. If we decide to do that, I think we should do it on a separate PR to avoid making this PR even larger. I also decided to leave out support for Tail queries to avoid making this PR even larger. Once this one gets merged, we can work to support tailing. --- **Note to reviewers** This PR is huge since we need to forward categorized all over the codebase (from parsing logs all the way to marshaling), fortunately, many of the changes come from updating tests and refactoring iterators. Tested out in a dev cell with query `'{stream="stdout"} | label_format new="text"`. - Without the new flag: ``` $ http http://127.0.0.1:3100/loki/api/v1/query_range\?direction\=BACKWARD\&end\=1693996529322486000\&limit\=30\&query\=%7Bstream%3D%22stdout%22%7D+%7C+label_format+new%3D%22text%22\&start\=1693992929322486000 X-Scope-Orgid:REDACTED { "data": { "result": [ { "stream": { "new": "text", "pod": "loki-canary-986bd6f4b-xqmb7", "stream": "stdout" }, "values": [ [ "1693996529000222496", "1693996529000222496 pppppppppppp...\n" ], [ "1693996528499160852", "1693996528499160852 pppppppppppp...\n" ], ... ``` - With the new flag ``` $ http http://127.0.0.1:3100/loki/api/v1/query_range\?direction\=BACKWARD\&end\=1693996529322486000\&limit\=30\&query\=%7Bstream%3D%22stdout%22%7D+%7C+label_format+new%3D%22text%22\&start\=1693992929322486000 X-Scope-Orgid:REDACTED X-Loki-Response-Encoding-Flags:categorize-labels { "data": { "encodingFlags": [ "categorize-labels" ], "result": [ { "stream": { "pod": "loki-canary-986bd6f4b-xqmb7", "stream": "stdout" }, "values": [ [ "1693996529000222496", "1693996529000222496 pppppppppppp...\n", { "parsed": { "new": "text" } } ], [ "1693996528499160852", "1693996528499160852 pppppppppppp...\n", { "parsed": { "new": "text" } } ], ... ```pull/10996/head^2
Salva Corts
3 years ago
committed by
GitHub
parent
60ea954f5d
commit
52a3f16039
@ -0,0 +1,113 @@ |
||||
package httpreq |
||||
|
||||
import ( |
||||
"context" |
||||
"net/http" |
||||
"strings" |
||||
|
||||
"github.com/grafana/dskit/httpgrpc" |
||||
) |
||||
|
||||
type EncodingFlag string |
||||
|
||||
type EncodingFlags map[EncodingFlag]struct{} |
||||
|
||||
func NewEncodingFlags(flags ...EncodingFlag) EncodingFlags { |
||||
var ef EncodingFlags |
||||
ef.Set(flags...) |
||||
return ef |
||||
} |
||||
|
||||
func (ef *EncodingFlags) Set(flags ...EncodingFlag) { |
||||
if *ef == nil { |
||||
*ef = make(EncodingFlags, len(flags)) |
||||
} |
||||
|
||||
for _, flag := range flags { |
||||
(*ef)[flag] = struct{}{} |
||||
} |
||||
} |
||||
|
||||
func (ef *EncodingFlags) Has(flag EncodingFlag) bool { |
||||
_, ok := (*ef)[flag] |
||||
return ok |
||||
} |
||||
|
||||
func (ef *EncodingFlags) String() string { |
||||
var sb strings.Builder |
||||
var i int |
||||
for flag := range *ef { |
||||
if i > 0 { |
||||
sb.WriteString(EncodeFlagsDelimiter) |
||||
} |
||||
sb.WriteString(string(flag)) |
||||
i++ |
||||
} |
||||
return sb.String() |
||||
} |
||||
|
||||
const ( |
||||
LokiEncodingFlagsHeader = "X-Loki-Response-Encoding-Flags" |
||||
FlagCategorizeLabels EncodingFlag = "categorize-labels" |
||||
|
||||
EncodeFlagsDelimiter = "," |
||||
) |
||||
|
||||
func AddEncodingFlags(req *http.Request, flags EncodingFlags) { |
||||
if len(flags) == 0 { |
||||
return |
||||
} |
||||
|
||||
req.Header.Set(LokiEncodingFlagsHeader, flags.String()) |
||||
} |
||||
|
||||
func AddEncodingFlagsToContext(ctx context.Context, flags EncodingFlags) context.Context { |
||||
if len(flags) == 0 { |
||||
return ctx |
||||
} |
||||
|
||||
return context.WithValue(ctx, headerContextKey(LokiEncodingFlagsHeader), flags.String()) |
||||
} |
||||
|
||||
func ExtractEncodingFlags(req *http.Request) EncodingFlags { |
||||
rawValue := req.Header.Get(LokiEncodingFlagsHeader) |
||||
if rawValue == "" { |
||||
return nil |
||||
} |
||||
|
||||
return parseEncodingFlags(rawValue) |
||||
} |
||||
|
||||
func ExtractEncodingFlagsFromProto(req *httpgrpc.HTTPRequest) EncodingFlags { |
||||
var rawValue string |
||||
for _, header := range req.GetHeaders() { |
||||
if header.GetKey() == LokiEncodingFlagsHeader { |
||||
rawValue = header.GetValues()[0] |
||||
if rawValue == "" { |
||||
return nil |
||||
} |
||||
|
||||
return parseEncodingFlags(rawValue) |
||||
} |
||||
} |
||||
|
||||
return nil |
||||
} |
||||
|
||||
func ExtractEncodingFlagsFromCtx(ctx context.Context) EncodingFlags { |
||||
rawValue := ExtractHeader(ctx, LokiEncodingFlagsHeader) |
||||
if rawValue == "" { |
||||
return nil |
||||
} |
||||
|
||||
return parseEncodingFlags(rawValue) |
||||
} |
||||
|
||||
func parseEncodingFlags(rawFlags string) EncodingFlags { |
||||
split := strings.Split(rawFlags, EncodeFlagsDelimiter) |
||||
flags := make(EncodingFlags, len(split)) |
||||
for _, rawFlag := range split { |
||||
flags.Set(EncodingFlag(rawFlag)) |
||||
} |
||||
return flags |
||||
} |
||||
Loading…
Reference in new issue