2020-06-16 18:23:06 +03:00
|
|
|
-- | Execution of GraphQL queries over HTTP transport
|
2018-07-20 10:22:46 +03:00
|
|
|
module Hasura.GraphQL.Transport.HTTP
|
2021-09-24 01:56:37 +03:00
|
|
|
( QueryCacheKey (..),
|
|
|
|
MonadExecuteQuery (..),
|
|
|
|
CachedDirective (..),
|
|
|
|
runGQ,
|
|
|
|
runGQBatched,
|
|
|
|
coalescePostgresMutations,
|
|
|
|
extractFieldFromResponse,
|
|
|
|
buildRaw,
|
2021-10-29 17:42:07 +03:00
|
|
|
encodeAnnotatedResponseParts,
|
|
|
|
encodeEncJSONResults,
|
2021-09-24 01:56:37 +03:00
|
|
|
|
|
|
|
-- * imported from HTTP.Protocol; required by pro
|
|
|
|
GQLReq (..),
|
|
|
|
GQLReqUnparsed,
|
|
|
|
GQLReqParsed,
|
|
|
|
GQLExecDoc (..),
|
|
|
|
OperationName (..),
|
|
|
|
GQLQueryText (..),
|
2021-10-26 14:44:18 +03:00
|
|
|
AnnotatedResponsePart (..),
|
2021-09-24 01:56:37 +03:00
|
|
|
CacheStoreSuccess (..),
|
|
|
|
CacheStoreFailure (..),
|
Rewrite `Tracing` to allow for only one `TraceT` in the entire stack.
This PR is on top of #7789.
### Description
This PR entirely rewrites the API of the Tracing library, to make `interpTraceT` a thing of the past. Before this change, we ran traces by sticking a `TraceT` on top of whatever we were doing. This had several major drawbacks:
- we were carrying a bunch of `TraceT` across the codebase, and the entire codebase had to know about it
- we needed to carry a second class constraint around (`HasReporterM`) to be able to run all of those traces
- we kept having to do stack rewriting with `interpTraceT`, which went from inconvenient to horrible
- we had to declare several behavioral instances on `TraceT m`
This PR rewrite all of `Tracing` using a more conventional model: there is ONE `TraceT` at the bottom of the stack, and there is an associated class constraint `MonadTrace`: any part of the code that happens to satisfy `MonadTrace` is able to create new traces. We NEVER have to do stack rewriting, `interpTraceT` is gone, and `TraceT` and `Reporter` become implementation details that 99% of the code is blissfully unaware of: code that needs to do tracing only needs to declare that the monad in which it operates implements `MonadTrace`.
In doing so, this PR revealed **several bugs in the codebase**: places where we were expecting to trace something, but due to the default instance of `HasReporterM IO` we would actually not do anything. This PR also splits the code of `Tracing` in more byte-sized modules, with the goal of potentially moving to `server/lib` down the line.
### Remaining work
This PR is a draft; what's left to do is:
- [x] make Pro compile; i haven't updated `HasuraPro/Main` yet
- [x] document Tracing by writing a note that explains how to use the library, and the meaning of "reporter", "trace" and "span", as well as the pitfalls
- [x] discuss some of the trade-offs in the implementation, which is why i'm opening this PR already despite it not fully building yet
- [x] it depends on #7789 being merged first
PR-URL: https://github.com/hasura/graphql-engine-mono/pull/7791
GitOrigin-RevId: cadd32d039134c93ddbf364599a2f4dd988adea8
2023-03-13 20:37:16 +03:00
|
|
|
CacheStoreResponse,
|
2021-09-24 01:56:37 +03:00
|
|
|
SessVarPred,
|
|
|
|
filterVariablesFromQuery,
|
|
|
|
runSessVarPred,
|
|
|
|
)
|
|
|
|
where
|
|
|
|
|
2022-03-08 11:22:20 +03:00
|
|
|
import Control.Lens (Traversal', foldOf, to)
|
2021-09-24 01:56:37 +03:00
|
|
|
import Control.Monad.Trans.Control (MonadBaseControl)
|
|
|
|
import Data.Aeson qualified as J
|
|
|
|
import Data.Aeson.Ordered qualified as JO
|
2022-03-08 11:22:20 +03:00
|
|
|
import Data.Bifoldable
|
2021-09-24 01:56:37 +03:00
|
|
|
import Data.ByteString.Lazy qualified as LBS
|
|
|
|
import Data.Dependent.Map qualified as DM
|
|
|
|
import Data.Environment qualified as Env
|
2023-04-27 10:41:55 +03:00
|
|
|
import Data.HashMap.Strict.InsOrd qualified as InsOrdHashMap
|
2022-02-18 17:57:09 +03:00
|
|
|
import Data.Monoid (Any (..))
|
2021-09-24 01:56:37 +03:00
|
|
|
import Data.Text qualified as T
|
2023-04-05 11:57:19 +03:00
|
|
|
import Hasura.Backends.DataConnector.Agent.Client (AgentLicenseKey)
|
2021-09-24 01:56:37 +03:00
|
|
|
import Hasura.Backends.Postgres.Instances.Transport (runPGMutationTransaction)
|
|
|
|
import Hasura.Base.Error
|
2023-04-05 11:57:19 +03:00
|
|
|
import Hasura.CredentialCache
|
2021-09-24 01:56:37 +03:00
|
|
|
import Hasura.EncJSON
|
|
|
|
import Hasura.GraphQL.Execute qualified as E
|
|
|
|
import Hasura.GraphQL.Execute.Action qualified as EA
|
|
|
|
import Hasura.GraphQL.Execute.Backend qualified as EB
|
|
|
|
import Hasura.GraphQL.Execute.RemoteJoin qualified as RJ
|
|
|
|
import Hasura.GraphQL.Logging
|
2023-03-15 16:05:17 +03:00
|
|
|
( MonadExecutionLog,
|
|
|
|
MonadQueryLog (logQueryLog),
|
2021-09-24 01:56:37 +03:00
|
|
|
QueryLog (..),
|
|
|
|
QueryLogKind (..),
|
2023-03-14 14:32:20 +03:00
|
|
|
statsToAnyBackend,
|
2021-09-24 01:56:37 +03:00
|
|
|
)
|
2021-10-29 17:42:07 +03:00
|
|
|
import Hasura.GraphQL.Namespace
|
2021-09-24 01:56:37 +03:00
|
|
|
import Hasura.GraphQL.ParameterizedQueryHash
|
2023-03-21 15:35:46 +03:00
|
|
|
import Hasura.GraphQL.Parser.Directives hiding (cachedDirective)
|
2021-09-24 01:56:37 +03:00
|
|
|
import Hasura.GraphQL.Transport.Backend
|
|
|
|
import Hasura.GraphQL.Transport.HTTP.Protocol
|
|
|
|
import Hasura.GraphQL.Transport.Instances ()
|
|
|
|
import Hasura.HTTP
|
2023-01-25 10:12:53 +03:00
|
|
|
( HttpResponse (HttpResponse, _hrBody),
|
|
|
|
addHttpResponseHeaders,
|
|
|
|
)
|
2021-09-24 01:56:37 +03:00
|
|
|
import Hasura.Logging qualified as L
|
|
|
|
import Hasura.Metadata.Class
|
|
|
|
import Hasura.Prelude
|
2023-03-31 00:18:11 +03:00
|
|
|
import Hasura.QueryTags
|
2021-09-24 01:56:37 +03:00
|
|
|
import Hasura.RQL.IR
|
2022-04-27 16:57:28 +03:00
|
|
|
import Hasura.RQL.Types.Action
|
|
|
|
import Hasura.RQL.Types.Backend
|
2023-04-24 21:35:48 +03:00
|
|
|
import Hasura.RQL.Types.BackendType
|
2023-03-21 15:35:46 +03:00
|
|
|
import Hasura.RQL.Types.Common
|
2022-04-27 16:57:28 +03:00
|
|
|
import Hasura.RQL.Types.ResultCustomization
|
2023-04-24 11:50:29 +03:00
|
|
|
import Hasura.RQL.Types.Roles (RoleName)
|
2022-04-27 16:57:28 +03:00
|
|
|
import Hasura.RQL.Types.SchemaCache
|
scaffolding for remote-schemas module
The main aim of the PR is:
1. To set up a module structure for 'remote-schemas' package.
2. Move parts by the remote schema codebase into the new module structure to validate it.
## Notes to the reviewer
Why a PR with large-ish diff?
1. We've been making progress on the MM project but we don't yet know long it is going to take us to get to the first milestone. To understand this better, we need to figure out the unknowns as soon as possible. Hence I've taken a stab at the first two items in the [end-state](https://gist.github.com/0x777/ca2bdc4284d21c3eec153b51dea255c9) document to figure out the unknowns. Unsurprisingly, there are a bunch of issues that we haven't discussed earlier. These are documented in the 'open questions' section.
1. The diff is large but that is only code moved around and I've added a section that documents how things are moved. In addition, there are fair number of PR comments to help with the review process.
## Changes in the PR
### Module structure
Sets up the module structure as follows:
```
Hasura/
RemoteSchema/
Metadata/
Types.hs
SchemaCache/
Types.hs
Permission.hs
RemoteRelationship.hs
Build.hs
MetadataAPI/
Types.hs
Execute.hs
```
### 1. Types representing metadata are moved
Types that capture metadata information (currently scattered across several RQL modules) are moved into `Hasura.RemoteSchema.Metadata.Types`.
- This new module only depends on very 'core' modules such as
`Hasura.Session` for the notion of roles and `Hasura.Incremental` for `Cacheable` typeclass.
- The requirement on database modules is avoided by generalizing the remote schemas metadata to accept an arbitrary 'r' for a remote relationship
definition.
### 2. SchemaCache related types and build logic have been moved
Types that represent remote schemas information in SchemaCache are moved into `Hasura.RemoteSchema.SchemaCache.Types`.
Similar to `H.RS.Metadata.Types`, this module depends on 'core' modules except for `Hasura.GraphQL.Parser.Variable`. It has something to do with remote relationships but I haven't spent time looking into it. The validation of 'remote relationships to remote schema' is also something that needs to be looked at.
Rips out the logic that builds remote schema's SchemaCache information from the monolithic `buildSchemaCacheRule` and moves it into `Hasura.RemoteSchema.SchemaCache.Build`. Further, the `.SchemaCache.Permission` and `.SchemaCache.RemoteRelationship` have been created from existing modules that capture schema cache building logic for those two components.
This was a fair amount of work. On main, currently remote schema's SchemaCache information is built in two phases - in the first phase, 'permissions' and 'remote relationships' are ignored and in the second phase they are filled in.
While remote relationships can only be resolved after partially resolving sources and other remote schemas, the same isn't true for permissions. Further, most of the work that is done to resolve remote relationships can be moved to the first phase so that the second phase can be a very simple traversal.
This is the approach that was taken - resolve permissions and as much as remote relationships information in the first phase.
### 3. Metadata APIs related types and build logic have been moved
The types that represent remote schema related metadata APIs and the execution logic have been moved to `Hasura.RemoteSchema.MetadataAPI.Types` and `.Execute` modules respectively.
## Open questions:
1. `Hasura.RemoteSchema.Metadata.Types` is so called because I was hoping that all of the metadata related APIs of remote schema can be brought in at `Hasura.RemoteSchema.Metadata.API`. However, as metadata APIs depended on functions from `SchemaCache` module (see [1](https://github.com/hasura/graphql-engine-mono/blob/ceba6d62264603ee5d279814677b29bcc43ecaea/server/src-lib/Hasura/RQL/DDL/RemoteSchema.hs#L55) and [2](https://github.com/hasura/graphql-engine-mono/blob/ceba6d62264603ee5d279814677b29bcc43ecaea/server/src-lib/Hasura/RQL/DDL/RemoteSchema.hs#L91), it made more sense to create a separate top-level module for `MetadataAPI`s.
Maybe we can just have `Hasura.RemoteSchema.Metadata` and get rid of the extra nesting or have `Hasura.RemoteSchema.Metadata.{Core,Permission,RemoteRelationship}` if we want to break them down further.
1. `buildRemoteSchemas` in `H.RS.SchemaCache.Build` has the following type:
```haskell
buildRemoteSchemas ::
( ArrowChoice arr,
Inc.ArrowDistribute arr,
ArrowWriter (Seq CollectedInfo) arr,
Inc.ArrowCache m arr,
MonadIO m,
HasHttpManagerM m,
Inc.Cacheable remoteRelationshipDefinition,
ToJSON remoteRelationshipDefinition,
MonadError QErr m
) =>
Env.Environment ->
( (Inc.Dependency (HashMap RemoteSchemaName Inc.InvalidationKey), OrderedRoles),
[RemoteSchemaMetadataG remoteRelationshipDefinition]
)
`arr` HashMap RemoteSchemaName (PartiallyResolvedRemoteSchemaCtxG remoteRelationshipDefinition, MetadataObject)
```
Note the dependence on `CollectedInfo` which is defined as
```haskell
data CollectedInfo
= CIInconsistency InconsistentMetadata
| CIDependency
MetadataObject
-- ^ for error reporting on missing dependencies
SchemaObjId
SchemaDependency
deriving (Eq)
```
this pretty much means that remote schemas is dependent on types from databases, actions, ....
How do we fix this? Maybe introduce a typeclass such as `ArrowCollectRemoteSchemaDependencies` which is defined in `Hasura.RemoteSchema` and then implemented in graphql-engine?
1. The dependency on `buildSchemaCacheFor` in `.MetadataAPI.Execute` which has the following signature:
```haskell
buildSchemaCacheFor ::
(QErrM m, CacheRWM m, MetadataM m) =>
MetadataObjId ->
MetadataModifier ->
```
This can be easily resolved if we restrict what the metadata APIs are allowed to do. Currently, they operate in an unfettered access to modify SchemaCache (the `CacheRWM` constraint):
```haskell
runAddRemoteSchema ::
( QErrM m,
CacheRWM m,
MonadIO m,
HasHttpManagerM m,
MetadataM m,
Tracing.MonadTrace m
) =>
Env.Environment ->
AddRemoteSchemaQuery ->
m EncJSON
```
This should instead be changed to restrict remote schema APIs to only modify remote schema metadata (but has access to the remote schemas part of the schema cache), this dependency is completely removed.
```haskell
runAddRemoteSchema ::
( QErrM m,
MonadIO m,
HasHttpManagerM m,
MonadReader RemoteSchemasSchemaCache m,
MonadState RemoteSchemaMetadata m,
Tracing.MonadTrace m
) =>
Env.Environment ->
AddRemoteSchemaQuery ->
m RemoteSchemeMetadataObjId
```
The idea is that the core graphql-engine would call these functions and then call
`buildSchemaCacheFor`.
PR-URL: https://github.com/hasura/graphql-engine-mono/pull/6291
GitOrigin-RevId: 51357148c6404afe70219afa71bd1d59bdf4ffc6
2022-10-21 06:13:07 +03:00
|
|
|
import Hasura.RemoteSchema.SchemaCache
|
2021-09-24 01:56:37 +03:00
|
|
|
import Hasura.SQL.AnyBackend qualified as AB
|
2023-03-21 15:35:46 +03:00
|
|
|
import Hasura.Server.Init qualified as Init
|
2021-09-24 01:56:37 +03:00
|
|
|
import Hasura.Server.Init.Config
|
2021-09-29 19:20:06 +03:00
|
|
|
import Hasura.Server.Limits
|
2021-09-24 01:56:37 +03:00
|
|
|
import Hasura.Server.Logging
|
|
|
|
import Hasura.Server.Logging qualified as L
|
2022-07-24 00:18:01 +03:00
|
|
|
import Hasura.Server.Prometheus
|
|
|
|
( GraphQLRequestMetrics (..),
|
|
|
|
PrometheusMetrics (..),
|
|
|
|
)
|
2021-09-24 01:56:37 +03:00
|
|
|
import Hasura.Server.Telemetry.Counters qualified as Telem
|
2023-03-21 15:35:46 +03:00
|
|
|
import Hasura.Server.Types (ReadOnlyMode (..), RequestId (..))
|
|
|
|
import Hasura.Services
|
2023-04-24 11:50:29 +03:00
|
|
|
import Hasura.Session (SessionVariable, SessionVariableValue, SessionVariables, UserInfo (..), filterSessionVariables)
|
2023-04-26 19:19:58 +03:00
|
|
|
import Hasura.Tracing (MonadTrace, TraceT, attachMetadata)
|
2021-09-24 01:56:37 +03:00
|
|
|
import Language.GraphQL.Draft.Syntax qualified as G
|
|
|
|
import Network.HTTP.Types qualified as HTTP
|
|
|
|
import Network.Wai.Extended qualified as Wai
|
2022-07-24 00:18:01 +03:00
|
|
|
import System.Metrics.Prometheus.Counter qualified as Prometheus.Counter
|
|
|
|
import System.Metrics.Prometheus.Histogram qualified as Prometheus.Histogram
|
2020-06-16 18:23:06 +03:00
|
|
|
|
2020-10-07 11:55:39 +03:00
|
|
|
data QueryCacheKey = QueryCacheKey
|
2021-09-24 01:56:37 +03:00
|
|
|
{ qckQueryString :: !GQLReqParsed,
|
|
|
|
qckUserRole :: !RoleName,
|
|
|
|
qckSession :: !SessionVariables
|
2020-10-07 11:55:39 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
instance J.ToJSON QueryCacheKey where
|
2021-02-13 03:05:23 +03:00
|
|
|
toJSON (QueryCacheKey qs ur sess) =
|
|
|
|
J.object ["query_string" J..= qs, "user_role" J..= ur, "session" J..= sess]
|
2020-10-07 11:55:39 +03:00
|
|
|
|
2021-08-25 04:52:38 +03:00
|
|
|
type CacheStoreResponse = Either CacheStoreFailure CacheStoreSuccess
|
|
|
|
|
|
|
|
data CacheStoreSuccess
|
|
|
|
= CacheStoreSkipped
|
|
|
|
| CacheStoreHit
|
|
|
|
deriving (Eq, Show)
|
|
|
|
|
|
|
|
data CacheStoreFailure
|
|
|
|
= CacheStoreLimitReached
|
|
|
|
| CacheStoreNotEnoughCapacity
|
|
|
|
| CacheStoreBackendError String
|
|
|
|
deriving (Eq, Show)
|
|
|
|
|
2020-07-15 13:40:48 +03:00
|
|
|
class Monad m => MonadExecuteQuery m where
|
2020-10-07 11:55:39 +03:00
|
|
|
-- | This method does two things: it looks up a query result in the
|
|
|
|
-- server-side cache, if a cache is used, and it additionally returns HTTP
|
|
|
|
-- headers that can instruct a client how long a response can be cached
|
|
|
|
-- locally (i.e. client-side).
|
2021-09-24 01:56:37 +03:00
|
|
|
cacheLookup ::
|
|
|
|
-- | Used to check if the elaborated query supports caching
|
|
|
|
[RemoteSchemaInfo] ->
|
|
|
|
-- | Used to check if actions query supports caching (unsupported if `forward_client_headers` is set)
|
|
|
|
[ActionsInfo] ->
|
|
|
|
-- | Key that uniquely identifies the result of a query execution
|
|
|
|
QueryCacheKey ->
|
|
|
|
-- | Cached Directive from GraphQL query AST
|
|
|
|
Maybe CachedDirective ->
|
|
|
|
-- | HTTP headers to be sent back to the caller for this GraphQL request,
|
2020-10-07 11:55:39 +03:00
|
|
|
-- containing e.g. time-to-live information, and a cached value if found and
|
|
|
|
-- within time-to-live. So a return value (non-empty-ttl-headers, Nothing)
|
|
|
|
-- represents that we don't have a server-side cache of the query, but that
|
|
|
|
-- the client should store it locally. The value ([], Just json) represents
|
|
|
|
-- that the client should not store the response locally, but we do have a
|
|
|
|
-- server-side cache value that can be used to avoid query execution.
|
Rewrite `Tracing` to allow for only one `TraceT` in the entire stack.
This PR is on top of #7789.
### Description
This PR entirely rewrites the API of the Tracing library, to make `interpTraceT` a thing of the past. Before this change, we ran traces by sticking a `TraceT` on top of whatever we were doing. This had several major drawbacks:
- we were carrying a bunch of `TraceT` across the codebase, and the entire codebase had to know about it
- we needed to carry a second class constraint around (`HasReporterM`) to be able to run all of those traces
- we kept having to do stack rewriting with `interpTraceT`, which went from inconvenient to horrible
- we had to declare several behavioral instances on `TraceT m`
This PR rewrite all of `Tracing` using a more conventional model: there is ONE `TraceT` at the bottom of the stack, and there is an associated class constraint `MonadTrace`: any part of the code that happens to satisfy `MonadTrace` is able to create new traces. We NEVER have to do stack rewriting, `interpTraceT` is gone, and `TraceT` and `Reporter` become implementation details that 99% of the code is blissfully unaware of: code that needs to do tracing only needs to declare that the monad in which it operates implements `MonadTrace`.
In doing so, this PR revealed **several bugs in the codebase**: places where we were expecting to trace something, but due to the default instance of `HasReporterM IO` we would actually not do anything. This PR also splits the code of `Tracing` in more byte-sized modules, with the goal of potentially moving to `server/lib` down the line.
### Remaining work
This PR is a draft; what's left to do is:
- [x] make Pro compile; i haven't updated `HasuraPro/Main` yet
- [x] document Tracing by writing a note that explains how to use the library, and the meaning of "reporter", "trace" and "span", as well as the pitfalls
- [x] discuss some of the trade-offs in the implementation, which is why i'm opening this PR already despite it not fully building yet
- [x] it depends on #7789 being merged first
PR-URL: https://github.com/hasura/graphql-engine-mono/pull/7791
GitOrigin-RevId: cadd32d039134c93ddbf364599a2f4dd988adea8
2023-03-13 20:37:16 +03:00
|
|
|
m (Either QErr (HTTP.ResponseHeaders, Maybe EncJSON))
|
2020-10-07 11:55:39 +03:00
|
|
|
|
|
|
|
-- | Store a json response for a query that we've executed in the cache. Note
|
|
|
|
-- that, as part of this, 'cacheStore' has to decide whether the response is
|
|
|
|
-- cacheable. A very similar decision is also made in 'cacheLookup', since it
|
|
|
|
-- has to construct corresponding cache-enabling headers that are sent to the
|
|
|
|
-- client. But note that the HTTP headers influence client-side caching,
|
|
|
|
-- whereas 'cacheStore' changes the server-side cache.
|
2021-09-24 01:56:37 +03:00
|
|
|
cacheStore ::
|
|
|
|
-- | Key under which to store the result of a query execution
|
|
|
|
QueryCacheKey ->
|
|
|
|
-- | Cached Directive from GraphQL query AST
|
|
|
|
Maybe CachedDirective ->
|
|
|
|
-- | Result of a query execution
|
|
|
|
EncJSON ->
|
|
|
|
-- | Always succeeds
|
Rewrite `Tracing` to allow for only one `TraceT` in the entire stack.
This PR is on top of #7789.
### Description
This PR entirely rewrites the API of the Tracing library, to make `interpTraceT` a thing of the past. Before this change, we ran traces by sticking a `TraceT` on top of whatever we were doing. This had several major drawbacks:
- we were carrying a bunch of `TraceT` across the codebase, and the entire codebase had to know about it
- we needed to carry a second class constraint around (`HasReporterM`) to be able to run all of those traces
- we kept having to do stack rewriting with `interpTraceT`, which went from inconvenient to horrible
- we had to declare several behavioral instances on `TraceT m`
This PR rewrite all of `Tracing` using a more conventional model: there is ONE `TraceT` at the bottom of the stack, and there is an associated class constraint `MonadTrace`: any part of the code that happens to satisfy `MonadTrace` is able to create new traces. We NEVER have to do stack rewriting, `interpTraceT` is gone, and `TraceT` and `Reporter` become implementation details that 99% of the code is blissfully unaware of: code that needs to do tracing only needs to declare that the monad in which it operates implements `MonadTrace`.
In doing so, this PR revealed **several bugs in the codebase**: places where we were expecting to trace something, but due to the default instance of `HasReporterM IO` we would actually not do anything. This PR also splits the code of `Tracing` in more byte-sized modules, with the goal of potentially moving to `server/lib` down the line.
### Remaining work
This PR is a draft; what's left to do is:
- [x] make Pro compile; i haven't updated `HasuraPro/Main` yet
- [x] document Tracing by writing a note that explains how to use the library, and the meaning of "reporter", "trace" and "span", as well as the pitfalls
- [x] discuss some of the trade-offs in the implementation, which is why i'm opening this PR already despite it not fully building yet
- [x] it depends on #7789 being merged first
PR-URL: https://github.com/hasura/graphql-engine-mono/pull/7791
GitOrigin-RevId: cadd32d039134c93ddbf364599a2f4dd988adea8
2023-03-13 20:37:16 +03:00
|
|
|
m (Either QErr CacheStoreResponse)
|
2021-09-24 01:56:37 +03:00
|
|
|
|
|
|
|
default cacheLookup ::
|
|
|
|
(m ~ t n, MonadTrans t, MonadExecuteQuery n) =>
|
|
|
|
[RemoteSchemaInfo] ->
|
|
|
|
[ActionsInfo] ->
|
|
|
|
QueryCacheKey ->
|
|
|
|
Maybe CachedDirective ->
|
Rewrite `Tracing` to allow for only one `TraceT` in the entire stack.
This PR is on top of #7789.
### Description
This PR entirely rewrites the API of the Tracing library, to make `interpTraceT` a thing of the past. Before this change, we ran traces by sticking a `TraceT` on top of whatever we were doing. This had several major drawbacks:
- we were carrying a bunch of `TraceT` across the codebase, and the entire codebase had to know about it
- we needed to carry a second class constraint around (`HasReporterM`) to be able to run all of those traces
- we kept having to do stack rewriting with `interpTraceT`, which went from inconvenient to horrible
- we had to declare several behavioral instances on `TraceT m`
This PR rewrite all of `Tracing` using a more conventional model: there is ONE `TraceT` at the bottom of the stack, and there is an associated class constraint `MonadTrace`: any part of the code that happens to satisfy `MonadTrace` is able to create new traces. We NEVER have to do stack rewriting, `interpTraceT` is gone, and `TraceT` and `Reporter` become implementation details that 99% of the code is blissfully unaware of: code that needs to do tracing only needs to declare that the monad in which it operates implements `MonadTrace`.
In doing so, this PR revealed **several bugs in the codebase**: places where we were expecting to trace something, but due to the default instance of `HasReporterM IO` we would actually not do anything. This PR also splits the code of `Tracing` in more byte-sized modules, with the goal of potentially moving to `server/lib` down the line.
### Remaining work
This PR is a draft; what's left to do is:
- [x] make Pro compile; i haven't updated `HasuraPro/Main` yet
- [x] document Tracing by writing a note that explains how to use the library, and the meaning of "reporter", "trace" and "span", as well as the pitfalls
- [x] discuss some of the trade-offs in the implementation, which is why i'm opening this PR already despite it not fully building yet
- [x] it depends on #7789 being merged first
PR-URL: https://github.com/hasura/graphql-engine-mono/pull/7791
GitOrigin-RevId: cadd32d039134c93ddbf364599a2f4dd988adea8
2023-03-13 20:37:16 +03:00
|
|
|
m (Either QErr (HTTP.ResponseHeaders, Maybe EncJSON))
|
|
|
|
cacheLookup a b c d = lift $ cacheLookup a b c d
|
2020-07-15 13:40:48 +03:00
|
|
|
|
2021-09-24 01:56:37 +03:00
|
|
|
default cacheStore ::
|
|
|
|
(m ~ t n, MonadTrans t, MonadExecuteQuery n) =>
|
|
|
|
QueryCacheKey ->
|
|
|
|
Maybe CachedDirective ->
|
|
|
|
EncJSON ->
|
Rewrite `Tracing` to allow for only one `TraceT` in the entire stack.
This PR is on top of #7789.
### Description
This PR entirely rewrites the API of the Tracing library, to make `interpTraceT` a thing of the past. Before this change, we ran traces by sticking a `TraceT` on top of whatever we were doing. This had several major drawbacks:
- we were carrying a bunch of `TraceT` across the codebase, and the entire codebase had to know about it
- we needed to carry a second class constraint around (`HasReporterM`) to be able to run all of those traces
- we kept having to do stack rewriting with `interpTraceT`, which went from inconvenient to horrible
- we had to declare several behavioral instances on `TraceT m`
This PR rewrite all of `Tracing` using a more conventional model: there is ONE `TraceT` at the bottom of the stack, and there is an associated class constraint `MonadTrace`: any part of the code that happens to satisfy `MonadTrace` is able to create new traces. We NEVER have to do stack rewriting, `interpTraceT` is gone, and `TraceT` and `Reporter` become implementation details that 99% of the code is blissfully unaware of: code that needs to do tracing only needs to declare that the monad in which it operates implements `MonadTrace`.
In doing so, this PR revealed **several bugs in the codebase**: places where we were expecting to trace something, but due to the default instance of `HasReporterM IO` we would actually not do anything. This PR also splits the code of `Tracing` in more byte-sized modules, with the goal of potentially moving to `server/lib` down the line.
### Remaining work
This PR is a draft; what's left to do is:
- [x] make Pro compile; i haven't updated `HasuraPro/Main` yet
- [x] document Tracing by writing a note that explains how to use the library, and the meaning of "reporter", "trace" and "span", as well as the pitfalls
- [x] discuss some of the trade-offs in the implementation, which is why i'm opening this PR already despite it not fully building yet
- [x] it depends on #7789 being merged first
PR-URL: https://github.com/hasura/graphql-engine-mono/pull/7791
GitOrigin-RevId: cadd32d039134c93ddbf364599a2f4dd988adea8
2023-03-13 20:37:16 +03:00
|
|
|
m (Either QErr CacheStoreResponse)
|
|
|
|
cacheStore a b c = lift $ cacheStore a b c
|
2020-07-15 13:40:48 +03:00
|
|
|
|
2021-06-17 09:27:58 +03:00
|
|
|
instance MonadExecuteQuery m => MonadExecuteQuery (ReaderT r m)
|
2021-09-24 01:56:37 +03:00
|
|
|
|
Rewrite `Tracing` to allow for only one `TraceT` in the entire stack.
This PR is on top of #7789.
### Description
This PR entirely rewrites the API of the Tracing library, to make `interpTraceT` a thing of the past. Before this change, we ran traces by sticking a `TraceT` on top of whatever we were doing. This had several major drawbacks:
- we were carrying a bunch of `TraceT` across the codebase, and the entire codebase had to know about it
- we needed to carry a second class constraint around (`HasReporterM`) to be able to run all of those traces
- we kept having to do stack rewriting with `interpTraceT`, which went from inconvenient to horrible
- we had to declare several behavioral instances on `TraceT m`
This PR rewrite all of `Tracing` using a more conventional model: there is ONE `TraceT` at the bottom of the stack, and there is an associated class constraint `MonadTrace`: any part of the code that happens to satisfy `MonadTrace` is able to create new traces. We NEVER have to do stack rewriting, `interpTraceT` is gone, and `TraceT` and `Reporter` become implementation details that 99% of the code is blissfully unaware of: code that needs to do tracing only needs to declare that the monad in which it operates implements `MonadTrace`.
In doing so, this PR revealed **several bugs in the codebase**: places where we were expecting to trace something, but due to the default instance of `HasReporterM IO` we would actually not do anything. This PR also splits the code of `Tracing` in more byte-sized modules, with the goal of potentially moving to `server/lib` down the line.
### Remaining work
This PR is a draft; what's left to do is:
- [x] make Pro compile; i haven't updated `HasuraPro/Main` yet
- [x] document Tracing by writing a note that explains how to use the library, and the meaning of "reporter", "trace" and "span", as well as the pitfalls
- [x] discuss some of the trade-offs in the implementation, which is why i'm opening this PR already despite it not fully building yet
- [x] it depends on #7789 being merged first
PR-URL: https://github.com/hasura/graphql-engine-mono/pull/7791
GitOrigin-RevId: cadd32d039134c93ddbf364599a2f4dd988adea8
2023-03-13 20:37:16 +03:00
|
|
|
instance MonadExecuteQuery m => MonadExecuteQuery (ExceptT e m)
|
2021-09-24 01:56:37 +03:00
|
|
|
|
Rewrite `Tracing` to allow for only one `TraceT` in the entire stack.
This PR is on top of #7789.
### Description
This PR entirely rewrites the API of the Tracing library, to make `interpTraceT` a thing of the past. Before this change, we ran traces by sticking a `TraceT` on top of whatever we were doing. This had several major drawbacks:
- we were carrying a bunch of `TraceT` across the codebase, and the entire codebase had to know about it
- we needed to carry a second class constraint around (`HasReporterM`) to be able to run all of those traces
- we kept having to do stack rewriting with `interpTraceT`, which went from inconvenient to horrible
- we had to declare several behavioral instances on `TraceT m`
This PR rewrite all of `Tracing` using a more conventional model: there is ONE `TraceT` at the bottom of the stack, and there is an associated class constraint `MonadTrace`: any part of the code that happens to satisfy `MonadTrace` is able to create new traces. We NEVER have to do stack rewriting, `interpTraceT` is gone, and `TraceT` and `Reporter` become implementation details that 99% of the code is blissfully unaware of: code that needs to do tracing only needs to declare that the monad in which it operates implements `MonadTrace`.
In doing so, this PR revealed **several bugs in the codebase**: places where we were expecting to trace something, but due to the default instance of `HasReporterM IO` we would actually not do anything. This PR also splits the code of `Tracing` in more byte-sized modules, with the goal of potentially moving to `server/lib` down the line.
### Remaining work
This PR is a draft; what's left to do is:
- [x] make Pro compile; i haven't updated `HasuraPro/Main` yet
- [x] document Tracing by writing a note that explains how to use the library, and the meaning of "reporter", "trace" and "span", as well as the pitfalls
- [x] discuss some of the trade-offs in the implementation, which is why i'm opening this PR already despite it not fully building yet
- [x] it depends on #7789 being merged first
PR-URL: https://github.com/hasura/graphql-engine-mono/pull/7791
GitOrigin-RevId: cadd32d039134c93ddbf364599a2f4dd988adea8
2023-03-13 20:37:16 +03:00
|
|
|
instance (MonadExecuteQuery m, MonadIO m) => MonadExecuteQuery (TraceT m)
|
2021-09-24 01:56:37 +03:00
|
|
|
|
2021-10-26 14:44:18 +03:00
|
|
|
-- | A partial response, e.g. from a remote schema call or postgres
|
|
|
|
-- postgres query, which we'll assemble into the final response for
|
|
|
|
-- the client. It is annotated with timing metadata.
|
|
|
|
data AnnotatedResponsePart = AnnotatedResponsePart
|
|
|
|
{ arpTimeIO :: DiffTime,
|
|
|
|
arpLocality :: Telem.Locality,
|
|
|
|
arpResponse :: EncJSON,
|
|
|
|
arpHeaders :: HTTP.ResponseHeaders
|
2020-10-07 13:23:17 +03:00
|
|
|
}
|
2020-07-15 13:40:48 +03:00
|
|
|
|
2021-10-26 14:44:18 +03:00
|
|
|
-- | A full response, annotated with timing metadata.
|
|
|
|
data AnnotatedResponse = AnnotatedResponse
|
|
|
|
{ arQueryType :: Telem.QueryType,
|
|
|
|
arTimeIO :: DiffTime,
|
|
|
|
arLocality :: Telem.Locality,
|
|
|
|
arResponse :: HttpResponse (Maybe GQResponse, EncJSON)
|
|
|
|
}
|
|
|
|
|
|
|
|
-- | Merge response parts into a full response.
|
|
|
|
buildResponseFromParts ::
|
|
|
|
(MonadError QErr m) =>
|
|
|
|
Telem.QueryType ->
|
2021-10-29 17:42:07 +03:00
|
|
|
Either (Either GQExecError QErr) (RootFieldMap AnnotatedResponsePart) ->
|
2021-10-26 14:44:18 +03:00
|
|
|
m AnnotatedResponse
|
2023-04-16 22:31:59 +03:00
|
|
|
buildResponseFromParts telemType partsErr =
|
2021-10-26 14:44:18 +03:00
|
|
|
buildResponse telemType partsErr \parts ->
|
2021-10-29 17:42:07 +03:00
|
|
|
let responseData = Right $ encJToLBS $ encodeAnnotatedResponseParts parts
|
2021-10-26 14:44:18 +03:00
|
|
|
in AnnotatedResponse
|
|
|
|
{ arQueryType = telemType,
|
|
|
|
arTimeIO = sum (fmap arpTimeIO parts),
|
|
|
|
arLocality = foldMap arpLocality parts,
|
|
|
|
arResponse =
|
|
|
|
HttpResponse
|
|
|
|
(Just responseData, encodeGQResp responseData)
|
2023-04-16 22:31:59 +03:00
|
|
|
(foldMap arpHeaders parts)
|
2021-10-26 14:44:18 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
buildResponse ::
|
|
|
|
(MonadError QErr m) =>
|
|
|
|
Telem.QueryType ->
|
|
|
|
Either (Either GQExecError QErr) a ->
|
|
|
|
(a -> AnnotatedResponse) ->
|
|
|
|
m AnnotatedResponse
|
|
|
|
buildResponse telemType res f = case res of
|
|
|
|
Right a -> pure $ f a
|
|
|
|
Left (Right err) -> throwError err
|
|
|
|
Left (Left err) ->
|
|
|
|
pure $
|
|
|
|
AnnotatedResponse
|
|
|
|
{ arQueryType = telemType,
|
|
|
|
arTimeIO = 0,
|
|
|
|
arLocality = Telem.Remote,
|
|
|
|
arResponse =
|
|
|
|
HttpResponse
|
|
|
|
(Just (Left err), encodeGQResp $ Left err)
|
|
|
|
[]
|
|
|
|
}
|
|
|
|
|
2021-02-13 03:05:23 +03:00
|
|
|
-- | A predicate on session variables. The 'Monoid' instance makes it simple
|
|
|
|
-- to combine several predicates disjunctively.
|
2022-03-08 11:22:20 +03:00
|
|
|
-- | The definition includes `Maybe` which allows us to short-circuit calls like @mempty <> m@ and @m <> mempty@, which
|
|
|
|
-- otherwise might build up long repeated chains of calls to @\_ _ -> False@.
|
|
|
|
newtype SessVarPred = SessVarPred {unSessVarPred :: Maybe (SessionVariable -> SessionVariableValue -> Bool)}
|
|
|
|
deriving (Semigroup, Monoid) via (Maybe (SessionVariable -> SessionVariableValue -> Any))
|
2021-02-13 03:05:23 +03:00
|
|
|
|
|
|
|
keepAllSessionVariables :: SessVarPred
|
2022-03-08 11:22:20 +03:00
|
|
|
keepAllSessionVariables = SessVarPred $ Just $ \_ _ -> True
|
2021-02-13 03:05:23 +03:00
|
|
|
|
|
|
|
runSessVarPred :: SessVarPred -> SessionVariables -> SessionVariables
|
2022-03-08 11:22:20 +03:00
|
|
|
runSessVarPred = filterSessionVariables . fromMaybe (\_ _ -> False) . unSessVarPred
|
2021-02-13 03:05:23 +03:00
|
|
|
|
|
|
|
-- | Filter out only those session variables used by the query AST provided
|
2021-09-24 01:56:37 +03:00
|
|
|
filterVariablesFromQuery ::
|
2022-02-25 23:37:32 +03:00
|
|
|
[ RootField
|
|
|
|
(QueryDBRoot (RemoteRelationshipField UnpreparedValue) UnpreparedValue)
|
Enable remote joins from remote schemas in the execution engine.
### Description
This PR adds the ability to perform remote joins from remote schemas in the engine. To do so, we alter the definition of an `ExecutionStep` targeting a remote schema: the `ExecStepRemote` constructor now expects a `Maybe RemoteJoins`. This new argument is used when processing the execution step, in the transport layer (either `Transport.HTTP` or `Transport.WebSocket`).
For this `Maybe RemoteJoins` to be extracted from a parsed query, this PR also extends the `Execute.RemoteJoin.Collect` module, to implement "collection" from a selection set. Not only do those new functions extract the remote joins, but they also apply all necessary transformations to the selection sets (such as inserting the necessary "phantom" fields used as join keys).
Finally in `Execute.RemoteJoin.Join`, we make two changes. First, we now always look for nested remote joins, regardless of whether the join we just performed went to a source or a remote schema; and second we adapt our join tree logic according to the special cases that were added to deal with remote server edge cases.
Additionally, this PR refactors / cleans / documents `Execute.RemoteJoin.RemoteServer`. This is not required as part of this change and could be moved to a separate PR if needed (a similar cleanup of `Join` is done independently in #3894). It also introduces a draft of a new documentation page for this project, that will be refined in the release PR that ships the feature (either #3069 or a copy of it).
While this PR extends the engine, it doesn't plug such relationships in the schema, meaning that, as of this PR, the new code paths in `Join` are technically unreachable. Adding the corresponding schema code and, ultimately, enabling the metadata API will be done in subsequent PRs.
### Keeping track of concrete type names
The main change this PR makes to the existing `Join` code is to handle a new reserved field we sometimes use when targeting remote servers: the `__hasura_internal_typename` field. In short, a GraphQL selection set can sometimes "branch" based on the concrete "runtime type" of the object on which the selection happens:
```graphql
query {
author(id: 53478) {
... on Writer {
name
articles {
title
}
}
... on Artist {
name
articles {
title
}
}
}
}
```
If both of those `articles` are remote joins, we need to be able, when we get the answer, to differentiate between the two different cases. We do this by asking for `__typename`, to be able to decide if we're in the `Writer` or the `Artist` branch of the query.
To avoid further processing / customization of results, we only insert this `__hasura_internal_typename: __typename` field in the query in the case of unions of interfaces AND if we have the guarantee that we will processing the request as part of the remote joins "folding": that is, if there's any remote join in this branch in the tree. Otherwise, we don't insert the field, and we leave that part of the response untouched.
PR-URL: https://github.com/hasura/graphql-engine-mono/pull/3810
GitOrigin-RevId: 89aaf16274d68e26ad3730b80c2d2fdc2896b96c
2022-03-09 06:17:28 +03:00
|
|
|
(RemoteSchemaRootField (RemoteRelationshipField UnpreparedValue) RemoteSchemaVariable)
|
2022-03-03 06:43:27 +03:00
|
|
|
(ActionQuery (RemoteRelationshipField UnpreparedValue))
|
2022-02-25 23:37:32 +03:00
|
|
|
d
|
|
|
|
] ->
|
2021-09-24 01:56:37 +03:00
|
|
|
SessVarPred
|
2022-03-08 11:22:20 +03:00
|
|
|
filterVariablesFromQuery = foldMap \case
|
|
|
|
RFDB _ exists ->
|
|
|
|
AB.dispatchAnyBackend @Backend exists \case
|
|
|
|
SourceConfigWith _ _ (QDBR db) -> bifoldMap remoteFieldPred toPred db
|
|
|
|
RFRemote remote -> foldOf (traverse . _SessionPresetVariable . to match) remote
|
|
|
|
RFAction actionQ -> foldMap remoteFieldPred actionQ
|
|
|
|
RFRaw {} -> mempty
|
2022-07-25 18:53:25 +03:00
|
|
|
RFMulti {} -> mempty
|
2021-02-13 03:05:23 +03:00
|
|
|
where
|
2021-06-17 22:16:11 +03:00
|
|
|
_SessionPresetVariable :: Traversal' RemoteSchemaVariable SessionVariable
|
|
|
|
_SessionPresetVariable f (SessionPresetVariable a b c) =
|
|
|
|
(\a' -> SessionPresetVariable a' b c) <$> f a
|
|
|
|
_SessionPresetVariable _ x = pure x
|
|
|
|
|
2021-02-13 03:05:23 +03:00
|
|
|
toPred :: UnpreparedValue bet -> SessVarPred
|
|
|
|
-- if we see a reference to the whole session variables object,
|
|
|
|
-- then we need to keep everything:
|
2021-09-24 01:56:37 +03:00
|
|
|
toPred UVSession = keepAllSessionVariables
|
2021-02-13 03:05:23 +03:00
|
|
|
-- if we only see a specific session variable, we only need to keep that one:
|
2021-06-17 22:16:11 +03:00
|
|
|
toPred (UVSessionVar _type sv) = match sv
|
2021-09-24 01:56:37 +03:00
|
|
|
toPred _ = mempty
|
2021-02-12 06:04:09 +03:00
|
|
|
|
2021-06-17 22:16:11 +03:00
|
|
|
match :: SessionVariable -> SessVarPred
|
2022-03-08 11:22:20 +03:00
|
|
|
match sv = SessVarPred $ Just $ \sv' _ -> sv == sv'
|
|
|
|
|
|
|
|
remoteFieldPred :: RemoteRelationshipField UnpreparedValue -> SessVarPred
|
|
|
|
remoteFieldPred = \case
|
|
|
|
RemoteSchemaField RemoteSchemaSelect {..} ->
|
|
|
|
foldOf (traverse . _SessionPresetVariable . to match) _rselSelection
|
|
|
|
RemoteSourceField exists ->
|
|
|
|
AB.dispatchAnyBackend @Backend exists \RemoteSourceSelect {..} ->
|
|
|
|
case _rssSelection of
|
|
|
|
SourceRelationshipObject obj -> foldMap toPred obj
|
|
|
|
SourceRelationshipArray arr -> foldMap toPred arr
|
|
|
|
SourceRelationshipArrayAggregate agg -> foldMap toPred agg
|
2021-06-17 22:16:11 +03:00
|
|
|
|
2020-06-16 18:23:06 +03:00
|
|
|
-- | Run (execute) a single GraphQL query
|
2021-09-24 01:56:37 +03:00
|
|
|
runGQ ::
|
|
|
|
forall m.
|
2021-10-13 19:38:56 +03:00
|
|
|
( MonadIO m,
|
2021-09-24 01:56:37 +03:00
|
|
|
MonadBaseControl IO m,
|
|
|
|
MonadError QErr m,
|
|
|
|
E.MonadGQLExecutionCheck m,
|
|
|
|
MonadQueryLog m,
|
2023-03-15 16:05:17 +03:00
|
|
|
MonadExecutionLog m,
|
2021-09-24 01:56:37 +03:00
|
|
|
MonadTrace m,
|
|
|
|
MonadExecuteQuery m,
|
2023-02-03 04:03:23 +03:00
|
|
|
MonadMetadataStorage m,
|
2023-03-31 00:18:11 +03:00
|
|
|
MonadQueryTags m,
|
harmonize network manager handling
## Description
### I want to speak to the `Manager`
Oh boy. This PR is both fairly straightforward and overreaching, so let's break it down.
For most network access, we need a [`HTTP.Manager`](https://hackage.haskell.org/package/http-client-0.1.0.0/docs/Network-HTTP-Client-Manager.html). It is created only once, at the top level, when starting the engine, and is then threaded through the application to wherever we need to make a network call. As of main, the way we do this is not standardized: most of the GraphQL execution code passes it "manually" as a function argument throughout the code. We also have a custom monad constraint, `HasHttpManagerM`, that describes a monad's ability to provide a manager. And, finally, several parts of the code store the manager in some kind of argument structure, such as `RunT`'s `RunCtx`.
This PR's first goal is to harmonize all of this: we always create the manager at the root, and we already have it when we do our very first `runReaderT`. Wouldn't it make sense for the rest of the code to not manually pass it anywhere, to not store it anywhere, but to always rely on the current monad providing it? This is, in short, what this PR does: it implements a constraint on the base monads, so that they provide the manager, and removes most explicit passing from the code.
### First come, first served
One way this PR goes a tiny bit further than "just" doing the aforementioned harmonization is that it starts the process of implementing the "Services oriented architecture" roughly outlined in this [draft document](https://docs.google.com/document/d/1FAigqrST0juU1WcT4HIxJxe1iEBwTuBZodTaeUvsKqQ/edit?usp=sharing). Instead of using the existing `HasHTTPManagerM`, this PR revamps it into the `ProvidesNetwork` service.
The idea is, again, that we should make all "external" dependencies of the engine, all things that the core of the engine doesn't care about, a "service". This allows us to define clear APIs for features, to choose different implementations based on which version of the engine we're running, harmonizes our many scattered monadic constraints... Which is why this service is called "Network": we can refine it, moving forward, to be the constraint that defines how all network communication is to operate, instead of relying on disparate classes constraint or hardcoded decisions. A comment in the code clarifies this intent.
### Side-effects? In my Haskell?
This PR also unavoidably touches some other aspects of the codebase. One such example: it introduces `Hasura.App.AppContext`, named after `HasuraPro.Context.AppContext`: a name for the reader structure at the base level. It also transforms `Handler` from a type alias to a newtype, as `Handler` is where we actually enforce HTTP limits; but without `Handler` being a distinct type, any code path could simply do a `runExceptT $ runReader` and forget to enforce them.
(As a rule of thumb, i am starting to consider any straggling `runReaderT` or `runExceptT` as a code smell: we should not stack / unstack monads haphazardly, and every layer should be an opaque `newtype` with a corresponding run function.)
## Further work
In several places, i have left TODOs when i have encountered things that suggest that we should do further unrelated cleanups. I'll write down the follow-up steps, either in the aforementioned document or on slack. But, in short, at a glance, in approximate order, we could:
- delete `ExecutionCtx` as it is only a subset of `ServerCtx`, and remove one more `runReaderT` call
- delete `ServerConfigCtx` as it is only a subset of `ServerCtx`, and remove it from `RunCtx`
- remove `ServerCtx` from `HandlerCtx`, and make it part of `AppContext`, or even make it the `AppContext` altogether (since, at least for the OSS version, `AppContext` is there again only a subset)
- remove `CacheBuildParams` and `CacheBuild` altogether, as they're just a distinct stack that is a `ReaderT` on top of `IO` that contains, you guessed it, the same thing as `ServerCtx`
- move `RunT` out of `RQL.Types` and rename it, since after the previous cleanups **it only contains `UserInfo`**; it could be bundled with the authentication service, made a small implementation detail in `Hasura.Server.Auth`
- rename `PGMetadaStorageT` to something a bit more accurate, such as `App`, and enforce its IO base
This would significantly simply our complex stack. From there, or in parallel, we can start moving existing dependencies as Services. For the purpose of supporting read replicas entitlement, we could move `MonadResolveSource` to a `SourceResolver` service, as attempted in #7653, and transform `UserAuthenticationM` into a `Authentication` service.
PR-URL: https://github.com/hasura/graphql-engine-mono/pull/7736
GitOrigin-RevId: 68cce710eb9e7d752bda1ba0c49541d24df8209f
2023-02-22 18:53:52 +03:00
|
|
|
HasResourceLimits m,
|
|
|
|
ProvidesNetwork m
|
2021-09-24 01:56:37 +03:00
|
|
|
) =>
|
2023-03-21 15:35:46 +03:00
|
|
|
-- TODO: almost all of those arguments come from `AppEnv` and `HandlerCtx`
|
|
|
|
-- (including `AppContext`). We could refactor this function to make use of
|
|
|
|
-- `HasAppEnv` and `MonadReader HandlerCtx` if the direct dependency is ok.
|
|
|
|
-- In turn, cleaning this list of arguments would allow for a cleanup of
|
|
|
|
-- `runGQBatched` and `runCustomEndpoint`.
|
2021-09-24 01:56:37 +03:00
|
|
|
Env.Environment ->
|
2023-03-21 15:35:46 +03:00
|
|
|
SQLGenCtx ->
|
|
|
|
SchemaCache ->
|
|
|
|
SchemaCacheVer ->
|
|
|
|
Init.AllowListStatus ->
|
|
|
|
ReadOnlyMode ->
|
|
|
|
PrometheusMetrics ->
|
2021-09-24 01:56:37 +03:00
|
|
|
L.Logger L.Hasura ->
|
2023-04-05 11:57:19 +03:00
|
|
|
Maybe (CredentialCache AgentLicenseKey) ->
|
2021-09-24 01:56:37 +03:00
|
|
|
RequestId ->
|
|
|
|
UserInfo ->
|
|
|
|
Wai.IpAddress ->
|
|
|
|
[HTTP.Header] ->
|
|
|
|
E.GraphQLQueryType ->
|
|
|
|
GQLReqUnparsed ->
|
|
|
|
m (GQLQueryOperationSuccessLog, HttpResponse (Maybe GQResponse, EncJSON))
|
2023-04-05 11:57:19 +03:00
|
|
|
runGQ env sqlGenCtx sc scVer enableAL readOnlyMode prometheusMetrics logger agentLicenseKey reqId userInfo ipAddress reqHeaders queryType reqUnparsed = do
|
2022-07-24 00:18:01 +03:00
|
|
|
let gqlMetrics = pmGraphQLRequestMetrics prometheusMetrics
|
|
|
|
|
|
|
|
(totalTime, (response, parameterizedQueryHash, gqlOpType)) <- withElapsedTime $ do
|
|
|
|
(reqParsed, runLimits, queryParts) <- observeGQLQueryError gqlMetrics Nothing $ do
|
|
|
|
-- 1. Run system authorization on the 'reqUnparsed :: GQLReqUnparsed' query.
|
|
|
|
reqParsed <-
|
|
|
|
E.checkGQLExecution userInfo (reqHeaders, ipAddress) enableAL sc reqUnparsed reqId
|
|
|
|
>>= flip onLeft throwError
|
|
|
|
|
2022-10-27 18:34:43 +03:00
|
|
|
operationLimit <- askGraphqlOperationLimit reqId userInfo (scApiLimits sc)
|
|
|
|
let runLimits = runResourceLimits operationLimit
|
2022-07-24 00:18:01 +03:00
|
|
|
|
|
|
|
-- 2. Construct the first step of the execution plan from 'reqParsed :: GQLParsed'.
|
|
|
|
queryParts <- getSingleOperation reqParsed
|
|
|
|
return (reqParsed, runLimits, queryParts)
|
|
|
|
|
|
|
|
let gqlOpType = G._todType queryParts
|
|
|
|
observeGQLQueryError gqlMetrics (Just gqlOpType) $ do
|
|
|
|
-- 3. Construct the remainder of the execution plan.
|
|
|
|
let maybeOperationName = _unOperationName <$> _grOperationName reqParsed
|
2023-04-26 19:19:58 +03:00
|
|
|
for_ maybeOperationName $ \nm ->
|
|
|
|
-- https://opentelemetry.io/docs/reference/specification/trace/semantic_conventions/instrumentation/graphql/
|
|
|
|
attachMetadata [("graphql.operation.name", G.unName nm)]
|
2022-07-24 00:18:01 +03:00
|
|
|
(parameterizedQueryHash, execPlan) <-
|
|
|
|
E.getResolvedExecPlan
|
|
|
|
env
|
|
|
|
logger
|
2022-12-28 06:47:42 +03:00
|
|
|
prometheusMetrics
|
2022-07-24 00:18:01 +03:00
|
|
|
userInfo
|
|
|
|
sqlGenCtx
|
|
|
|
readOnlyMode
|
|
|
|
sc
|
|
|
|
scVer
|
|
|
|
queryType
|
|
|
|
reqHeaders
|
|
|
|
reqUnparsed
|
|
|
|
queryParts
|
|
|
|
maybeOperationName
|
|
|
|
reqId
|
|
|
|
|
|
|
|
-- 4. Execute the execution plan producing a 'AnnotatedResponse'.
|
harmonize network manager handling
## Description
### I want to speak to the `Manager`
Oh boy. This PR is both fairly straightforward and overreaching, so let's break it down.
For most network access, we need a [`HTTP.Manager`](https://hackage.haskell.org/package/http-client-0.1.0.0/docs/Network-HTTP-Client-Manager.html). It is created only once, at the top level, when starting the engine, and is then threaded through the application to wherever we need to make a network call. As of main, the way we do this is not standardized: most of the GraphQL execution code passes it "manually" as a function argument throughout the code. We also have a custom monad constraint, `HasHttpManagerM`, that describes a monad's ability to provide a manager. And, finally, several parts of the code store the manager in some kind of argument structure, such as `RunT`'s `RunCtx`.
This PR's first goal is to harmonize all of this: we always create the manager at the root, and we already have it when we do our very first `runReaderT`. Wouldn't it make sense for the rest of the code to not manually pass it anywhere, to not store it anywhere, but to always rely on the current monad providing it? This is, in short, what this PR does: it implements a constraint on the base monads, so that they provide the manager, and removes most explicit passing from the code.
### First come, first served
One way this PR goes a tiny bit further than "just" doing the aforementioned harmonization is that it starts the process of implementing the "Services oriented architecture" roughly outlined in this [draft document](https://docs.google.com/document/d/1FAigqrST0juU1WcT4HIxJxe1iEBwTuBZodTaeUvsKqQ/edit?usp=sharing). Instead of using the existing `HasHTTPManagerM`, this PR revamps it into the `ProvidesNetwork` service.
The idea is, again, that we should make all "external" dependencies of the engine, all things that the core of the engine doesn't care about, a "service". This allows us to define clear APIs for features, to choose different implementations based on which version of the engine we're running, harmonizes our many scattered monadic constraints... Which is why this service is called "Network": we can refine it, moving forward, to be the constraint that defines how all network communication is to operate, instead of relying on disparate classes constraint or hardcoded decisions. A comment in the code clarifies this intent.
### Side-effects? In my Haskell?
This PR also unavoidably touches some other aspects of the codebase. One such example: it introduces `Hasura.App.AppContext`, named after `HasuraPro.Context.AppContext`: a name for the reader structure at the base level. It also transforms `Handler` from a type alias to a newtype, as `Handler` is where we actually enforce HTTP limits; but without `Handler` being a distinct type, any code path could simply do a `runExceptT $ runReader` and forget to enforce them.
(As a rule of thumb, i am starting to consider any straggling `runReaderT` or `runExceptT` as a code smell: we should not stack / unstack monads haphazardly, and every layer should be an opaque `newtype` with a corresponding run function.)
## Further work
In several places, i have left TODOs when i have encountered things that suggest that we should do further unrelated cleanups. I'll write down the follow-up steps, either in the aforementioned document or on slack. But, in short, at a glance, in approximate order, we could:
- delete `ExecutionCtx` as it is only a subset of `ServerCtx`, and remove one more `runReaderT` call
- delete `ServerConfigCtx` as it is only a subset of `ServerCtx`, and remove it from `RunCtx`
- remove `ServerCtx` from `HandlerCtx`, and make it part of `AppContext`, or even make it the `AppContext` altogether (since, at least for the OSS version, `AppContext` is there again only a subset)
- remove `CacheBuildParams` and `CacheBuild` altogether, as they're just a distinct stack that is a `ReaderT` on top of `IO` that contains, you guessed it, the same thing as `ServerCtx`
- move `RunT` out of `RQL.Types` and rename it, since after the previous cleanups **it only contains `UserInfo`**; it could be bundled with the authentication service, made a small implementation detail in `Hasura.Server.Auth`
- rename `PGMetadaStorageT` to something a bit more accurate, such as `App`, and enforce its IO base
This would significantly simply our complex stack. From there, or in parallel, we can start moving existing dependencies as Services. For the purpose of supporting read replicas entitlement, we could move `MonadResolveSource` to a `SourceResolver` service, as attempted in #7653, and transform `UserAuthenticationM` into a `Authentication` service.
PR-URL: https://github.com/hasura/graphql-engine-mono/pull/7736
GitOrigin-RevId: 68cce710eb9e7d752bda1ba0c49541d24df8209f
2023-02-22 18:53:52 +03:00
|
|
|
response <- executePlan reqParsed runLimits execPlan
|
2022-07-24 00:18:01 +03:00
|
|
|
return (response, parameterizedQueryHash, gqlOpType)
|
|
|
|
|
|
|
|
-- 5. Record telemetry
|
2021-10-26 14:44:18 +03:00
|
|
|
recordTimings totalTime response
|
2022-07-24 00:18:01 +03:00
|
|
|
|
|
|
|
-- 6. Record Prometheus metrics (query successes)
|
|
|
|
liftIO $ recordGQLQuerySuccess gqlMetrics totalTime gqlOpType
|
|
|
|
|
|
|
|
-- 7. Return the response along with logging metadata.
|
2021-10-26 14:44:18 +03:00
|
|
|
let requestSize = LBS.length $ J.encode reqUnparsed
|
|
|
|
responseSize = LBS.length $ encJToLBS $ snd $ _hrBody $ arResponse $ response
|
|
|
|
return
|
|
|
|
( GQLQueryOperationSuccessLog reqUnparsed totalTime responseSize requestSize parameterizedQueryHash,
|
|
|
|
arResponse response
|
|
|
|
)
|
|
|
|
where
|
|
|
|
doQErr :: ExceptT QErr m a -> ExceptT (Either GQExecError QErr) m a
|
|
|
|
doQErr = withExceptT Right
|
|
|
|
|
2023-04-27 10:41:55 +03:00
|
|
|
forWithKey = flip InsOrdHashMap.traverseWithKey
|
2021-10-26 14:44:18 +03:00
|
|
|
|
|
|
|
executePlan ::
|
|
|
|
GQLReqParsed ->
|
|
|
|
(m AnnotatedResponse -> m AnnotatedResponse) ->
|
|
|
|
E.ResolvedExecutionPlan ->
|
|
|
|
m AnnotatedResponse
|
harmonize network manager handling
## Description
### I want to speak to the `Manager`
Oh boy. This PR is both fairly straightforward and overreaching, so let's break it down.
For most network access, we need a [`HTTP.Manager`](https://hackage.haskell.org/package/http-client-0.1.0.0/docs/Network-HTTP-Client-Manager.html). It is created only once, at the top level, when starting the engine, and is then threaded through the application to wherever we need to make a network call. As of main, the way we do this is not standardized: most of the GraphQL execution code passes it "manually" as a function argument throughout the code. We also have a custom monad constraint, `HasHttpManagerM`, that describes a monad's ability to provide a manager. And, finally, several parts of the code store the manager in some kind of argument structure, such as `RunT`'s `RunCtx`.
This PR's first goal is to harmonize all of this: we always create the manager at the root, and we already have it when we do our very first `runReaderT`. Wouldn't it make sense for the rest of the code to not manually pass it anywhere, to not store it anywhere, but to always rely on the current monad providing it? This is, in short, what this PR does: it implements a constraint on the base monads, so that they provide the manager, and removes most explicit passing from the code.
### First come, first served
One way this PR goes a tiny bit further than "just" doing the aforementioned harmonization is that it starts the process of implementing the "Services oriented architecture" roughly outlined in this [draft document](https://docs.google.com/document/d/1FAigqrST0juU1WcT4HIxJxe1iEBwTuBZodTaeUvsKqQ/edit?usp=sharing). Instead of using the existing `HasHTTPManagerM`, this PR revamps it into the `ProvidesNetwork` service.
The idea is, again, that we should make all "external" dependencies of the engine, all things that the core of the engine doesn't care about, a "service". This allows us to define clear APIs for features, to choose different implementations based on which version of the engine we're running, harmonizes our many scattered monadic constraints... Which is why this service is called "Network": we can refine it, moving forward, to be the constraint that defines how all network communication is to operate, instead of relying on disparate classes constraint or hardcoded decisions. A comment in the code clarifies this intent.
### Side-effects? In my Haskell?
This PR also unavoidably touches some other aspects of the codebase. One such example: it introduces `Hasura.App.AppContext`, named after `HasuraPro.Context.AppContext`: a name for the reader structure at the base level. It also transforms `Handler` from a type alias to a newtype, as `Handler` is where we actually enforce HTTP limits; but without `Handler` being a distinct type, any code path could simply do a `runExceptT $ runReader` and forget to enforce them.
(As a rule of thumb, i am starting to consider any straggling `runReaderT` or `runExceptT` as a code smell: we should not stack / unstack monads haphazardly, and every layer should be an opaque `newtype` with a corresponding run function.)
## Further work
In several places, i have left TODOs when i have encountered things that suggest that we should do further unrelated cleanups. I'll write down the follow-up steps, either in the aforementioned document or on slack. But, in short, at a glance, in approximate order, we could:
- delete `ExecutionCtx` as it is only a subset of `ServerCtx`, and remove one more `runReaderT` call
- delete `ServerConfigCtx` as it is only a subset of `ServerCtx`, and remove it from `RunCtx`
- remove `ServerCtx` from `HandlerCtx`, and make it part of `AppContext`, or even make it the `AppContext` altogether (since, at least for the OSS version, `AppContext` is there again only a subset)
- remove `CacheBuildParams` and `CacheBuild` altogether, as they're just a distinct stack that is a `ReaderT` on top of `IO` that contains, you guessed it, the same thing as `ServerCtx`
- move `RunT` out of `RQL.Types` and rename it, since after the previous cleanups **it only contains `UserInfo`**; it could be bundled with the authentication service, made a small implementation detail in `Hasura.Server.Auth`
- rename `PGMetadaStorageT` to something a bit more accurate, such as `App`, and enforce its IO base
This would significantly simply our complex stack. From there, or in parallel, we can start moving existing dependencies as Services. For the purpose of supporting read replicas entitlement, we could move `MonadResolveSource` to a `SourceResolver` service, as attempted in #7653, and transform `UserAuthenticationM` into a `Authentication` service.
PR-URL: https://github.com/hasura/graphql-engine-mono/pull/7736
GitOrigin-RevId: 68cce710eb9e7d752bda1ba0c49541d24df8209f
2023-02-22 18:53:52 +03:00
|
|
|
executePlan reqParsed runLimits execPlan = case execPlan of
|
2023-04-26 19:19:58 +03:00
|
|
|
E.QueryExecutionPlan queryPlans asts dirMap -> do
|
|
|
|
-- https://opentelemetry.io/docs/reference/specification/trace/semantic_conventions/instrumentation/graphql/
|
|
|
|
attachMetadata [("graphql.operation.type", "query")]
|
2022-04-08 09:48:37 +03:00
|
|
|
-- Attempt to lookup a cached response in the query cache.
|
|
|
|
-- 'keyedLookup' is a monadic action possibly returning a cache hit.
|
|
|
|
-- 'keyedStore' is a function to write a new response to the cache.
|
2021-10-26 14:44:18 +03:00
|
|
|
let (keyedLookup, keyedStore) = cacheAccess reqParsed queryPlans asts dirMap
|
|
|
|
(cachingHeaders, cachedValue) <- keyedLookup
|
2021-01-29 04:02:34 +03:00
|
|
|
case fmap decodeGQResp cachedValue of
|
2022-04-08 09:48:37 +03:00
|
|
|
-- If we get a cache hit, annotate the response with metadata and return it.
|
2021-04-19 04:21:34 +03:00
|
|
|
Just cachedResponseData -> do
|
2023-03-15 16:05:17 +03:00
|
|
|
logQueryLog logger $ QueryLog reqUnparsed Nothing reqId QueryLogKindCached
|
2021-10-26 14:44:18 +03:00
|
|
|
pure $
|
|
|
|
AnnotatedResponse
|
|
|
|
{ arQueryType = Telem.Query,
|
|
|
|
arTimeIO = 0,
|
|
|
|
arLocality = Telem.Local,
|
|
|
|
arResponse = HttpResponse cachedResponseData cachingHeaders
|
|
|
|
}
|
2022-04-08 09:48:37 +03:00
|
|
|
-- If we get a cache miss, we must run the query against the graphql engine.
|
2021-09-29 19:20:06 +03:00
|
|
|
Nothing -> runLimits $ do
|
2022-04-08 09:48:37 +03:00
|
|
|
-- 1. 'traverse' the 'ExecutionPlan' executing every step.
|
harmonize network manager handling
## Description
### I want to speak to the `Manager`
Oh boy. This PR is both fairly straightforward and overreaching, so let's break it down.
For most network access, we need a [`HTTP.Manager`](https://hackage.haskell.org/package/http-client-0.1.0.0/docs/Network-HTTP-Client-Manager.html). It is created only once, at the top level, when starting the engine, and is then threaded through the application to wherever we need to make a network call. As of main, the way we do this is not standardized: most of the GraphQL execution code passes it "manually" as a function argument throughout the code. We also have a custom monad constraint, `HasHttpManagerM`, that describes a monad's ability to provide a manager. And, finally, several parts of the code store the manager in some kind of argument structure, such as `RunT`'s `RunCtx`.
This PR's first goal is to harmonize all of this: we always create the manager at the root, and we already have it when we do our very first `runReaderT`. Wouldn't it make sense for the rest of the code to not manually pass it anywhere, to not store it anywhere, but to always rely on the current monad providing it? This is, in short, what this PR does: it implements a constraint on the base monads, so that they provide the manager, and removes most explicit passing from the code.
### First come, first served
One way this PR goes a tiny bit further than "just" doing the aforementioned harmonization is that it starts the process of implementing the "Services oriented architecture" roughly outlined in this [draft document](https://docs.google.com/document/d/1FAigqrST0juU1WcT4HIxJxe1iEBwTuBZodTaeUvsKqQ/edit?usp=sharing). Instead of using the existing `HasHTTPManagerM`, this PR revamps it into the `ProvidesNetwork` service.
The idea is, again, that we should make all "external" dependencies of the engine, all things that the core of the engine doesn't care about, a "service". This allows us to define clear APIs for features, to choose different implementations based on which version of the engine we're running, harmonizes our many scattered monadic constraints... Which is why this service is called "Network": we can refine it, moving forward, to be the constraint that defines how all network communication is to operate, instead of relying on disparate classes constraint or hardcoded decisions. A comment in the code clarifies this intent.
### Side-effects? In my Haskell?
This PR also unavoidably touches some other aspects of the codebase. One such example: it introduces `Hasura.App.AppContext`, named after `HasuraPro.Context.AppContext`: a name for the reader structure at the base level. It also transforms `Handler` from a type alias to a newtype, as `Handler` is where we actually enforce HTTP limits; but without `Handler` being a distinct type, any code path could simply do a `runExceptT $ runReader` and forget to enforce them.
(As a rule of thumb, i am starting to consider any straggling `runReaderT` or `runExceptT` as a code smell: we should not stack / unstack monads haphazardly, and every layer should be an opaque `newtype` with a corresponding run function.)
## Further work
In several places, i have left TODOs when i have encountered things that suggest that we should do further unrelated cleanups. I'll write down the follow-up steps, either in the aforementioned document or on slack. But, in short, at a glance, in approximate order, we could:
- delete `ExecutionCtx` as it is only a subset of `ServerCtx`, and remove one more `runReaderT` call
- delete `ServerConfigCtx` as it is only a subset of `ServerCtx`, and remove it from `RunCtx`
- remove `ServerCtx` from `HandlerCtx`, and make it part of `AppContext`, or even make it the `AppContext` altogether (since, at least for the OSS version, `AppContext` is there again only a subset)
- remove `CacheBuildParams` and `CacheBuild` altogether, as they're just a distinct stack that is a `ReaderT` on top of `IO` that contains, you guessed it, the same thing as `ServerCtx`
- move `RunT` out of `RQL.Types` and rename it, since after the previous cleanups **it only contains `UserInfo`**; it could be bundled with the authentication service, made a small implementation detail in `Hasura.Server.Auth`
- rename `PGMetadaStorageT` to something a bit more accurate, such as `App`, and enforce its IO base
This would significantly simply our complex stack. From there, or in parallel, we can start moving existing dependencies as Services. For the purpose of supporting read replicas entitlement, we could move `MonadResolveSource` to a `SourceResolver` service, as attempted in #7653, and transform `UserAuthenticationM` into a `Authentication` service.
PR-URL: https://github.com/hasura/graphql-engine-mono/pull/7736
GitOrigin-RevId: 68cce710eb9e7d752bda1ba0c49541d24df8209f
2023-02-22 18:53:52 +03:00
|
|
|
-- TODO: can this be a `catch` rather than a `runExceptT`?
|
|
|
|
conclusion <- runExceptT $ forWithKey queryPlans executeQueryStep
|
2022-04-08 09:48:37 +03:00
|
|
|
-- 2. Construct an 'AnnotatedResponse' from the results of all steps in the 'ExecutionPlan'.
|
2023-04-16 22:31:59 +03:00
|
|
|
result <- buildResponseFromParts Telem.Query conclusion
|
2021-10-26 14:44:18 +03:00
|
|
|
let response@(HttpResponse responseData _) = arResponse result
|
2022-04-08 09:48:37 +03:00
|
|
|
-- 3. Cache the 'AnnotatedResponse'.
|
2021-10-26 14:44:18 +03:00
|
|
|
cacheStoreRes <- keyedStore (snd responseData)
|
|
|
|
let headers = case cacheStoreRes of
|
|
|
|
-- Note: Warning header format: "Warning: <warn-code> <warn-agent> <warn-text> [warn-date]"
|
|
|
|
-- See: https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Warning
|
2023-04-16 22:31:59 +03:00
|
|
|
Right _ -> cachingHeaders
|
2021-10-26 14:44:18 +03:00
|
|
|
(Left CacheStoreLimitReached) -> [("warning", "199 - cache-store-size-limit-exceeded")]
|
|
|
|
(Left CacheStoreNotEnoughCapacity) -> [("warning", "199 - cache-store-capacity-exceeded")]
|
|
|
|
(Left (CacheStoreBackendError _)) -> [("warning", "199 - cache-store-error")]
|
2022-04-08 09:48:37 +03:00
|
|
|
in -- 4. Return the response.
|
|
|
|
pure $ result {arResponse = addHttpResponseHeaders headers response}
|
2021-09-29 19:20:06 +03:00
|
|
|
E.MutationExecutionPlan mutationPlans -> runLimits $ do
|
2023-04-26 19:19:58 +03:00
|
|
|
-- https://opentelemetry.io/docs/reference/specification/trace/semantic_conventions/instrumentation/graphql/
|
|
|
|
attachMetadata [("graphql.operation.type", "mutation")]
|
2021-04-01 23:40:31 +03:00
|
|
|
{- Note [Backwards-compatible transaction optimisation]
|
|
|
|
|
|
|
|
For backwards compatibility, we perform the following optimisation: if all mutation steps
|
|
|
|
are going to the same source, and that source is Postgres, we group all mutations as a
|
|
|
|
transaction. This is a somewhat dangerous beaviour, and we would prefer, in the future,
|
|
|
|
to make transactionality explicit rather than implicit and context-dependent.
|
|
|
|
-}
|
|
|
|
case coalescePostgresMutations mutationPlans of
|
|
|
|
-- we are in the aforementioned case; we circumvent the normal process
|
2023-01-25 10:12:53 +03:00
|
|
|
Just (sourceConfig, resolvedConnectionTemplate, pgMutations) -> do
|
2021-10-26 14:44:18 +03:00
|
|
|
res <-
|
harmonize network manager handling
## Description
### I want to speak to the `Manager`
Oh boy. This PR is both fairly straightforward and overreaching, so let's break it down.
For most network access, we need a [`HTTP.Manager`](https://hackage.haskell.org/package/http-client-0.1.0.0/docs/Network-HTTP-Client-Manager.html). It is created only once, at the top level, when starting the engine, and is then threaded through the application to wherever we need to make a network call. As of main, the way we do this is not standardized: most of the GraphQL execution code passes it "manually" as a function argument throughout the code. We also have a custom monad constraint, `HasHttpManagerM`, that describes a monad's ability to provide a manager. And, finally, several parts of the code store the manager in some kind of argument structure, such as `RunT`'s `RunCtx`.
This PR's first goal is to harmonize all of this: we always create the manager at the root, and we already have it when we do our very first `runReaderT`. Wouldn't it make sense for the rest of the code to not manually pass it anywhere, to not store it anywhere, but to always rely on the current monad providing it? This is, in short, what this PR does: it implements a constraint on the base monads, so that they provide the manager, and removes most explicit passing from the code.
### First come, first served
One way this PR goes a tiny bit further than "just" doing the aforementioned harmonization is that it starts the process of implementing the "Services oriented architecture" roughly outlined in this [draft document](https://docs.google.com/document/d/1FAigqrST0juU1WcT4HIxJxe1iEBwTuBZodTaeUvsKqQ/edit?usp=sharing). Instead of using the existing `HasHTTPManagerM`, this PR revamps it into the `ProvidesNetwork` service.
The idea is, again, that we should make all "external" dependencies of the engine, all things that the core of the engine doesn't care about, a "service". This allows us to define clear APIs for features, to choose different implementations based on which version of the engine we're running, harmonizes our many scattered monadic constraints... Which is why this service is called "Network": we can refine it, moving forward, to be the constraint that defines how all network communication is to operate, instead of relying on disparate classes constraint or hardcoded decisions. A comment in the code clarifies this intent.
### Side-effects? In my Haskell?
This PR also unavoidably touches some other aspects of the codebase. One such example: it introduces `Hasura.App.AppContext`, named after `HasuraPro.Context.AppContext`: a name for the reader structure at the base level. It also transforms `Handler` from a type alias to a newtype, as `Handler` is where we actually enforce HTTP limits; but without `Handler` being a distinct type, any code path could simply do a `runExceptT $ runReader` and forget to enforce them.
(As a rule of thumb, i am starting to consider any straggling `runReaderT` or `runExceptT` as a code smell: we should not stack / unstack monads haphazardly, and every layer should be an opaque `newtype` with a corresponding run function.)
## Further work
In several places, i have left TODOs when i have encountered things that suggest that we should do further unrelated cleanups. I'll write down the follow-up steps, either in the aforementioned document or on slack. But, in short, at a glance, in approximate order, we could:
- delete `ExecutionCtx` as it is only a subset of `ServerCtx`, and remove one more `runReaderT` call
- delete `ServerConfigCtx` as it is only a subset of `ServerCtx`, and remove it from `RunCtx`
- remove `ServerCtx` from `HandlerCtx`, and make it part of `AppContext`, or even make it the `AppContext` altogether (since, at least for the OSS version, `AppContext` is there again only a subset)
- remove `CacheBuildParams` and `CacheBuild` altogether, as they're just a distinct stack that is a `ReaderT` on top of `IO` that contains, you guessed it, the same thing as `ServerCtx`
- move `RunT` out of `RQL.Types` and rename it, since after the previous cleanups **it only contains `UserInfo`**; it could be bundled with the authentication service, made a small implementation detail in `Hasura.Server.Auth`
- rename `PGMetadaStorageT` to something a bit more accurate, such as `App`, and enforce its IO base
This would significantly simply our complex stack. From there, or in parallel, we can start moving existing dependencies as Services. For the purpose of supporting read replicas entitlement, we could move `MonadResolveSource` to a `SourceResolver` service, as attempted in #7653, and transform `UserAuthenticationM` into a `Authentication` service.
PR-URL: https://github.com/hasura/graphql-engine-mono/pull/7736
GitOrigin-RevId: 68cce710eb9e7d752bda1ba0c49541d24df8209f
2023-02-22 18:53:52 +03:00
|
|
|
-- TODO: can this be a `catch` rather than a `runExceptT`?
|
2021-09-24 01:56:37 +03:00
|
|
|
runExceptT $
|
|
|
|
doQErr $
|
2023-01-25 10:12:53 +03:00
|
|
|
runPGMutationTransaction reqId reqUnparsed userInfo logger sourceConfig resolvedConnectionTemplate pgMutations
|
2021-10-26 14:44:18 +03:00
|
|
|
-- we do not construct response parts since we have only one part
|
|
|
|
buildResponse Telem.Mutation res \(telemTimeIO_DT, parts) ->
|
2021-10-29 17:42:07 +03:00
|
|
|
let responseData = Right $ encJToLBS $ encodeEncJSONResults parts
|
2021-10-26 14:44:18 +03:00
|
|
|
in AnnotatedResponse
|
|
|
|
{ arQueryType = Telem.Mutation,
|
|
|
|
arTimeIO = telemTimeIO_DT,
|
|
|
|
arLocality = Telem.Local,
|
|
|
|
arResponse =
|
|
|
|
HttpResponse
|
|
|
|
(Just responseData, encodeGQResp responseData)
|
|
|
|
[]
|
|
|
|
}
|
2021-04-01 23:40:31 +03:00
|
|
|
|
|
|
|
-- we are not in the transaction case; proceeding normally
|
|
|
|
Nothing -> do
|
harmonize network manager handling
## Description
### I want to speak to the `Manager`
Oh boy. This PR is both fairly straightforward and overreaching, so let's break it down.
For most network access, we need a [`HTTP.Manager`](https://hackage.haskell.org/package/http-client-0.1.0.0/docs/Network-HTTP-Client-Manager.html). It is created only once, at the top level, when starting the engine, and is then threaded through the application to wherever we need to make a network call. As of main, the way we do this is not standardized: most of the GraphQL execution code passes it "manually" as a function argument throughout the code. We also have a custom monad constraint, `HasHttpManagerM`, that describes a monad's ability to provide a manager. And, finally, several parts of the code store the manager in some kind of argument structure, such as `RunT`'s `RunCtx`.
This PR's first goal is to harmonize all of this: we always create the manager at the root, and we already have it when we do our very first `runReaderT`. Wouldn't it make sense for the rest of the code to not manually pass it anywhere, to not store it anywhere, but to always rely on the current monad providing it? This is, in short, what this PR does: it implements a constraint on the base monads, so that they provide the manager, and removes most explicit passing from the code.
### First come, first served
One way this PR goes a tiny bit further than "just" doing the aforementioned harmonization is that it starts the process of implementing the "Services oriented architecture" roughly outlined in this [draft document](https://docs.google.com/document/d/1FAigqrST0juU1WcT4HIxJxe1iEBwTuBZodTaeUvsKqQ/edit?usp=sharing). Instead of using the existing `HasHTTPManagerM`, this PR revamps it into the `ProvidesNetwork` service.
The idea is, again, that we should make all "external" dependencies of the engine, all things that the core of the engine doesn't care about, a "service". This allows us to define clear APIs for features, to choose different implementations based on which version of the engine we're running, harmonizes our many scattered monadic constraints... Which is why this service is called "Network": we can refine it, moving forward, to be the constraint that defines how all network communication is to operate, instead of relying on disparate classes constraint or hardcoded decisions. A comment in the code clarifies this intent.
### Side-effects? In my Haskell?
This PR also unavoidably touches some other aspects of the codebase. One such example: it introduces `Hasura.App.AppContext`, named after `HasuraPro.Context.AppContext`: a name for the reader structure at the base level. It also transforms `Handler` from a type alias to a newtype, as `Handler` is where we actually enforce HTTP limits; but without `Handler` being a distinct type, any code path could simply do a `runExceptT $ runReader` and forget to enforce them.
(As a rule of thumb, i am starting to consider any straggling `runReaderT` or `runExceptT` as a code smell: we should not stack / unstack monads haphazardly, and every layer should be an opaque `newtype` with a corresponding run function.)
## Further work
In several places, i have left TODOs when i have encountered things that suggest that we should do further unrelated cleanups. I'll write down the follow-up steps, either in the aforementioned document or on slack. But, in short, at a glance, in approximate order, we could:
- delete `ExecutionCtx` as it is only a subset of `ServerCtx`, and remove one more `runReaderT` call
- delete `ServerConfigCtx` as it is only a subset of `ServerCtx`, and remove it from `RunCtx`
- remove `ServerCtx` from `HandlerCtx`, and make it part of `AppContext`, or even make it the `AppContext` altogether (since, at least for the OSS version, `AppContext` is there again only a subset)
- remove `CacheBuildParams` and `CacheBuild` altogether, as they're just a distinct stack that is a `ReaderT` on top of `IO` that contains, you guessed it, the same thing as `ServerCtx`
- move `RunT` out of `RQL.Types` and rename it, since after the previous cleanups **it only contains `UserInfo`**; it could be bundled with the authentication service, made a small implementation detail in `Hasura.Server.Auth`
- rename `PGMetadaStorageT` to something a bit more accurate, such as `App`, and enforce its IO base
This would significantly simply our complex stack. From there, or in parallel, we can start moving existing dependencies as Services. For the purpose of supporting read replicas entitlement, we could move `MonadResolveSource` to a `SourceResolver` service, as attempted in #7653, and transform `UserAuthenticationM` into a `Authentication` service.
PR-URL: https://github.com/hasura/graphql-engine-mono/pull/7736
GitOrigin-RevId: 68cce710eb9e7d752bda1ba0c49541d24df8209f
2023-02-22 18:53:52 +03:00
|
|
|
-- TODO: can this be a `catch` rather than a `runExceptT`?
|
|
|
|
conclusion <- runExceptT $ forWithKey mutationPlans executeMutationStep
|
2023-04-16 22:31:59 +03:00
|
|
|
buildResponseFromParts Telem.Mutation conclusion
|
2021-03-31 13:39:01 +03:00
|
|
|
E.SubscriptionExecutionPlan _sub ->
|
Rewrite GraphQL schema generation and query parsing (close #2801) (#4111)
Aka “the PDV refactor.” History is preserved on the branch 2801-graphql-schema-parser-refactor.
* [skip ci] remove stale benchmark commit from commit_diff
* [skip ci] Check for root field name conflicts between remotes
* [skip ci] Additionally check for conflicts between remotes and DB
* [skip ci] Check for conflicts in schema when tracking a table
* [skip ci] Fix equality checking in GraphQL AST
* server: fix mishandling of GeoJSON inputs in subscriptions (fix #3239) (#4551)
* Add support for multiple top-level fields in a subscription to improve testability of subscriptions
* Add an internal flag to enable multiple subscriptions
* Add missing call to withConstructorFn in live queries (fix #3239)
Co-authored-by: Alexis King <lexi.lambda@gmail.com>
* Scheduled triggers (close #1914) (#3553)
server: add scheduled triggers
Co-authored-by: Alexis King <lexi.lambda@gmail.com>
Co-authored-by: Marion Schleifer <marion@hasura.io>
Co-authored-by: Karthikeyan Chinnakonda <karthikeyan@hasura.io>
Co-authored-by: Aleksandra Sikora <ola.zxcvbnm@gmail.com>
* dev.sh: bump version due to addition of croniter python dependency
* server: fix an introspection query caching issue (fix #4547) (#4661)
Introspection queries accept variables, but we need to make sure to
also touch the variables that we ignore, so that an introspection
query is marked not reusable if we are not able to build a correct
query plan for it.
A better solution here would be to deal with such unused variables
correctly, so that more introspection queries become reusable.
An even better solution would be to type-safely track *how* to reuse
which variables, rather than to split the reusage marking from the
planning.
Co-authored-by: Tirumarai Selvan <tiru@hasura.io>
* flush log buffer on exception in mkWaiApp ( fix #4772 ) (#4801)
* flush log buffer on exception in mkWaiApp
* add comment to explain the introduced change
* add changelog
* allow logging details of a live query polling thread (#4959)
* changes for poller-log
add various multiplexed query info in poller-log
* minor cleanup, also fixes a bug which will return duplicate data
* Live query poller stats can now be logged
This also removes in-memory stats that are collected about batched
query execution as the log lines when piped into an monitoring tool
will give us better insights.
* allow poller-log to be configurable
* log minimal information in the livequery-poller-log
Other information can be retrieved from /dev/subscriptions/extended
* fix few review comments
* avoid marshalling and unmarshalling from ByteString to EncJSON
* separate out SubscriberId and SubscriberMetadata
Co-authored-by: Anon Ray <rayanon004@gmail.com>
* Don't compile in developer APIs by default
* Tighten up handling of admin secret, more docs
Store the admin secret only as a hash to prevent leaking the secret
inadvertently, and to prevent timing attacks on the secret.
NOTE: best practice for stored user passwords is a function with a
tunable cost like bcrypt, but our threat model is quite different (even
if we thought we could reasonably protect the secret from an attacker
who could read arbitrary regions of memory), and bcrypt is far too slow
(by design) to perform on each request. We'd have to rely on our
(technically savvy) users to choose high entropy passwords in any case.
Referencing #4736
* server/docs: add instructions to fix loss of float precision in PostgreSQL <= 11 (#5187)
This adds a server flag, --pg-connection-options, that can be used to set a PostgreSQL connection parameter, extra_float_digits, that needs to be used to avoid loss of data on older versions of PostgreSQL, which have odd default behavior when returning float values. (fixes #5092)
* [skip ci] Add new commits from master to the commit diff
* [skip ci] serve default directives (skip & include) over introspection
* [skip ci] Update non-Haskell assets with the version on master
* server: refactor GQL execution check and config API (#5094)
Co-authored-by: Vamshi Surabhi <vamshi@hasura.io>
Co-authored-by: Vamshi Surabhi <0x777@users.noreply.github.com>
* [skip ci] fix js issues in tests by pinning dependencies version
* [skip ci] bump graphql version
* [skip ci] Add note about memory usage
* generalize query execution logic on Postgres (#5110)
* generalize PGExecCtx to support specialized functions for various operations
* fix tests compilation
* allow customising PGExecCtx when starting the web server
* server: changes catalog initialization and logging for pro customization (#5139)
* new typeclass to abstract the logic of QueryLog-ing
* abstract the logic of logging websocket-server logs
introduce a MonadWSLog typeclass
* move catalog initialization to init step
expose a helper function to migrate catalog
create schema cache in initialiseCtx
* expose various modules and functions for pro
* [skip ci] cosmetic change
* [skip ci] fix test calling a mutation that does not exist
* [skip ci] minor text change
* [skip ci] refactored input values
* [skip ci] remove VString Origin
* server: fix updating of headers behaviour in the update cron trigger API and create future events immediately (#5151)
* server: fix bug to update headers in an existing cron trigger and create future events
Co-authored-by: Tirumarai Selvan <tiru@hasura.io>
* Lower stack chunk size in RTS to reduce thread STACK memory (closes #5190)
This reduces memory consumption for new idle subscriptions significantly
(see linked ticket).
The hypothesis is: we fork a lot of threads per websocket, and some of
these use slightly more than the initial 1K stack size, so the first
overflow balloons to 32K, when significantly less is required.
However: running with `+RTS -K1K -xc` did not seem to show evidence of
any overflows! So it's a mystery why this improves things.
GHC should probably also be doubling the stack buffer at each overflow
or doing something even smarter; the knobs we have aren't so helpful.
* [skip ci] fix todo and schema generation for aggregate fields
* 5087 libpq pool leak (#5089)
Shrink libpq buffers to 1MB before returning connection to pool. Closes #5087
See: https://github.com/hasura/pg-client-hs/pull/19
Also related: #3388 #4077
* bump pg-client-hs version (fixes a build issue on some environments) (#5267)
* do not use prepared statements for mutations
* server: unlock scheduled events on graceful shutdown (#4928)
* Fix buggy parsing of new --conn-lifetime flag in 2b0e3774
* [skip ci] remove cherry-picked commit from commit_diff.txt
* server: include additional fields in scheduled trigger webhook payload (#5262)
* include scheduled triggers metadata in the webhook body
Co-authored-by: Tirumarai Selvan <tiru@hasura.io>
* server: call the webhook asynchronously in event triggers (#5352)
* server: call the webhook asynchronosly in event triggers
* Expose all modules in Cabal file (#5371)
* [skip ci] update commit_diff.txt
* [skip ci] fix cast exp parser & few TODOs
* [skip ci] fix remote fields arguments
* [skip ci] fix few more TODO, no-op refactor, move resolve/action.hs to execute/action.hs
* Pass environment variables around as a data structure, via @sordina (#5374)
* Pass environment variables around as a data structure, via @sordina
* Resolving build error
* Adding Environment passing note to changelog
* Removing references to ILTPollerLog as this seems to have been reintroduced from a bad merge
* removing commented-out imports
* Language pragmas already set by project
* Linking async thread
* Apply suggestions from code review
Use `runQueryTx` instead of `runLazyTx` for queries.
* remove the non-user facing entry in the changelog
Co-authored-by: Phil Freeman <paf31@cantab.net>
Co-authored-by: Phil Freeman <phil@hasura.io>
Co-authored-by: Vamshi Surabhi <0x777@users.noreply.github.com>
* [skip ci] fix: restrict remote relationship field generation for hasura queries
* [skip ci] no-op refactor; move insert execution code from schema parser module
* server: call the webhook asynchronously in event triggers (#5352)
* server: call the webhook asynchronosly in event triggers
* Expose all modules in Cabal file (#5371)
* [skip ci] update commit_diff.txt
* Pass environment variables around as a data structure, via @sordina (#5374)
* Pass environment variables around as a data structure, via @sordina
* Resolving build error
* Adding Environment passing note to changelog
* Removing references to ILTPollerLog as this seems to have been reintroduced from a bad merge
* removing commented-out imports
* Language pragmas already set by project
* Linking async thread
* Apply suggestions from code review
Use `runQueryTx` instead of `runLazyTx` for queries.
* remove the non-user facing entry in the changelog
Co-authored-by: Phil Freeman <paf31@cantab.net>
Co-authored-by: Phil Freeman <phil@hasura.io>
Co-authored-by: Vamshi Surabhi <0x777@users.noreply.github.com>
* [skip ci] implement header checking
Probably closes #14 and #3659.
* server: refactor 'pollQuery' to have a hook to process 'PollDetails' (#5391)
Co-authored-by: Vamshi Surabhi <0x777@users.noreply.github.com>
* update pg-client (#5421)
* [skip ci] update commit_diff
* Fix latency buckets for telemetry data
These must have gotten messed up during a refactor. As a consequence
almost all samples received so far fall into the single erroneous 0 to
1K seconds (originally supposed to be 1ms?) bucket.
I also re-thought what the numbers should be, but these are still
arbitrary and might want adjusting in the future.
* [skip ci] include the latest commit compared against master in commit_diff
* [skip ci] include new commits from master in commit_diff
* [skip ci] improve description generation
* [skip ci] sort all introspect arrays
* [skip ci] allow parsers to specify error codes
* [skip ci] fix integer and float parsing error code
* [skip ci] scalar from json errors are now parse errors
* [skip ci] fixed negative integer error message and code
* [skip ci] Re-fix nullability in relationships
* [skip ci] no-op refactor and removed couple of FIXMEs
* [skip ci] uncomment code in 'deleteMetadataObject'
* [skip ci] Fix re-fix of nullability for relationships
* [skip ci] fix default arguments error code
* [skip ci] updated test error message
!!! WARNING !!!
Since all fields accept `null`, they all are technically optional in
the new schema. Meaning there's no such thing as a missing mandatory
field anymore: a field that doesn't have a default value, and which
therefore isn't labelled as "optional" in the schema, will be assumed
to be null if it's missing, meaning it isn't possible anymore to have
an error for a missing mandatory field. The only possible error is now
when a optional positional argument is omitted but is not the last
positional argument.
* [skip ci] cleanup of int scalar parser
* [skip ci] retro-compatibility of offset as string
* [skip ci] Remove commit from commit_diff.txt
Although strictly speaking we don't know if this will work correctly in PDV
if we would implement query plan caching, the fact is that in the theoretical
case that we would have the same issue in PDV, it would probably apply not just
to introspection, and the fix would be written completely differently. So this
old commit is of no value to us other than the heads-up "make sure query plan
caching works correctly even in the presence of unused variables", which is
already part of the test suite.
* Add MonadTrace and MonadExecuteQuery abstractions (#5383)
* [skip ci] Fix accumulation of input object types
Just like object types, interface types, and union types, we have to avoid
circularities when collecting input types from the GraphQL AST.
Additionally, this fixes equality checks for input object types (whose fields
are unordered, and hence should be compared as sets) and enum types (ditto).
* [skip ci] fix fragment error path
* [skip ci] fix node error code
* [skip ci] fix paths in insert queries
* [skip ci] fix path in objects
* [skip ci] manually alter node id path for consistency
* [skip ci] more node error fixups
* [skip ci] one last relay error message fix
* [skip ci] update commit_diff
* Propagate the trace context to event triggers (#5409)
* Propagate the trace context to event triggers
* Handle missing trace and span IDs
* Store trace context as one LOCAL
* Add migrations
* Documentation
* changelog
* Fix warnings
* Respond to code review suggestions
* Respond to code review
* Undo changelog
* Update CHANGELOG.md
Co-authored-by: Vamshi Surabhi <0x777@users.noreply.github.com>
* server: log request/response sizes for event triggers (#5463)
* server: log request/response sizes for event triggers
event triggers (and scheduled triggers) now have request/response size
in their logs.
* add changelog entry
* Tracing: Simplify HTTP traced request (#5451)
Remove the Inversion of Control (SuspendRequest) and simplify
the tracing of HTTP Requests.
Co-authored-by: Phil Freeman <phil@hasura.io>
* Attach request ID as tracing metadata (#5456)
* Propagate the trace context to event triggers
* Handle missing trace and span IDs
* Store trace context as one LOCAL
* Add migrations
* Documentation
* Include the request ID as trace metadata
* changelog
* Fix warnings
* Respond to code review suggestions
* Respond to code review
* Undo changelog
* Update CHANGELOG.md
* Typo
Co-authored-by: Vamshi Surabhi <0x777@users.noreply.github.com>
* server: add logging for action handlers (#5471)
* server: add logging for action handlers
* add changelog entry
* change action-handler log type from internal to non-internal
* fix action-handler-log name
* server: pass http and websocket request to logging context (#5470)
* pass request body to logging context in all cases
* add message size logging on the websocket API
this is required by graphql-engine-pro/#416
* message size logging on websocket API
As we need to log all messages recieved/sent by the websocket server,
it makes sense to log them as part of the websocket server event logs.
Previously message recieved were logged inside the onMessage handler,
and messages sent were logged only for "data" messages (as a server event log)
* fix review comments
Co-authored-by: Phil Freeman <phil@hasura.io>
* server: stop eventing subsystem threads when shutting down (#5479)
* server: stop eventing subsystem threads when shutting down
* Apply suggestions from code review
Co-authored-by: Karthikeyan Chinnakonda <chkarthikeyan95@gmail.com>
Co-authored-by: Phil Freeman <phil@hasura.io>
Co-authored-by: Phil Freeman <paf31@cantab.net>
Co-authored-by: Karthikeyan Chinnakonda <chkarthikeyan95@gmail.com>
* [skip ci] update commit_diff with new commits added in master
* Bugfix to support 0-size HASURA_GRAPHQL_QUERY_PLAN_CACHE_SIZE
Also some minor refactoring of bounded cache module:
- the maxBound check in `trim` was confusing and unnecessary
- consequently trim was unnecessary for lookupPure
Also add some basic tests
* Support only the bounded cache, with default HASURA_GRAPHQL_QUERY_PLAN_CACHE_SIZE of 4000. Closes #5363
* [skip ci] remove merge commit from commit_diff
* server: Fix compiler warning caused by GHC upgrade (#5489)
Co-authored-by: Vamshi Surabhi <0x777@users.noreply.github.com>
* [skip ci] update all non server code from master
* [skip ci] aligned object field error message with master
* [skip ci] fix remaining undefined?
* [skip ci] remove unused import
* [skip ci] revert to previous error message, fix tests
* Move nullableType/nonNullableType to Schema.hs
These are functions on Types, not on Parsers.
* [skip ci] fix setup to fix backend only test
the order in which permission checks are performed on the branch is
slightly different than on master, resulting in a slightly different
error if there are no other mutations the user has access to. By
adding update permissions, we go back to the expected case.
* [skip ci] fix insert geojson tests to reflect new paths
* [skip ci] fix enum test for better error message
* [skip ci] fix header test for better error message
* [skip ci] fix fragment cycle test for better error message
* [skip ci] fix error message for type mismatch
* [skip ci] fix variable path in test
* [skip ci] adjust tests after bug fix
* [skip ci] more tests fixing
* Add hdb_catalog.current_setting abstraction for reading Hasura settings
As the comment in the function’s definition explains, this is needed to
work around an awkward Postgres behavior.
* [skip ci] Update CONTRIBUTING.md to mention Node setup for Python tests
* [skip ci] Add missing Python tests env var to CONTRIBUTING.md
* [skip ci] fix order of result when subscription is run with multiple nodes
* [skip ci] no-op refactor: fix a warning in Internal/Parser.hs
* [skip ci] throw error when a subscription contains remote joins
* [skip ci] Enable easier profiling by hiding AssertNF behind a flag
In order to compile a profiling build, run:
$ cabal new-build -f profiling --enable-profiling
* [skip ci] Fix two warnings
We used to lookup the objects that implement a given interface by filtering all
objects in the schema document. However, one of the tests expects us to
generate a warning if the provided `implements` field of an introspection query
specifies an object not implementing some interface. So we use that field
instead.
* [skip ci] Fix warnings by commenting out query plan caching
* [skip ci] improve masking/commenting query caching related code & few warning fixes
* [skip ci] Fixed compiler warnings in graphql-parser-hs
* Sync non-Haskell assets with master
* [skip ci] add a test inserting invalid GraphQL but valid JSON value in a jsonb column
* [skip ci] Avoid converting to/from Map
* [skip ci] Apply some hlint suggestions
* [skip ci] remove redundant constraints from buildLiveQueryPlan and explainGQLQuery
* [skip ci] add NOTEs about missing Tracing constraints in PDV from master
* Remove -fdefer-typed-holes, fix warnings
* Update cabal.project.freeze
* Limit GHC’s heap size to 8GB in CI to avoid the OOM killer
* Commit package-lock.json for Python tests’ remote schema server
* restrict env variables start with HASURA_GRAPHQL_ for headers configuration in actions, event triggers & remote schemas (#5519)
* restrict env variables start with HASURA_GRAPHQL_ for headers definition in actions & event triggers
* update CHANGELOG.md
* Apply suggestions from code review
Co-authored-by: Vamshi Surabhi <0x777@users.noreply.github.com>
* add test for table_by_pk node when roles doesn't have permission to PK
* [skip ci] fix introspection query if any enum column present in primary key (fix #5200) (#5522)
* [skip ci] test case fix for a6450e126bc2d98bcfd3791501986e4627ce6c6f
* [skip ci] add tests to agg queries when role doesn't have access to any cols
* fix backend test
* Simplify subscription execution
* [skip ci] add test to check if required headers are present while querying
* Suppose, table B is related to table A and to query B certain headers are
necessary, then the test checks that we are throwing error when the header
is not set when B is queried through A
* fix mutations not checking for view mutability
* [skip ci] add variable type checking and corresponding tests
* [skip ci] add test to check if update headers are present while doing an upsert
* [skip ci] add positive counterparts to some of the negative permission tests
* fix args missing their description in introspect
* [skip ci] Remove unused function; insert missing markNotReusable call
* [skip ci] Add a Note about InputValue
* [skip ci] Delete LegacySchema/ 🎉
* [skip ci] Delete GraphQL/{Resolve,Validate}/ 🎉
* [skip ci] Delete top-level Resolve/Validate modules; tidy .cabal file
* [skip ci] Delete LegacySchema top-level module
Somehow I missed this one.
* fix input value to json
* [skip ci] elaborate on JSON objects in GraphQL
* [skip ci] add missing file
* [skip ci] add a test with subscription containing remote joins
* add a test with remote joins in mutation output
* [skip ci] Add some comments to Schema/Mutation.hs
* [skip ci] Remove no longer needed code from RemoteServer.hs
* [skip ci] Use a helper function to generate conflict clause parsers
* [skip ci] fix type checker error in fields with default value
* capitalize the header keys in select_articles_without_required_headers
* Somehow, this was the reason the tests were failing. I have no idea, why!
* [skip ci] Add a long Note about optional fields and nullability
* Improve comments a bit; simplify Schema/Common.hs a bit
* [skip ci] full implementation of 5.8.5 type checking.
* [skip ci] fix validation test teardown
* [skip ci] fix schema stitching test
* fix remote schema ignoring enum nullability
* [skip ci] fix fieldOptional to not discard nullability
* revert nullability of use_spheroid
* fix comment
* add required remote fields with arguments for tests
* [skip ci] add missing docstrings
* [skip ci] fixed description of remote fields
* [skip ci] change docstring for consistency
* fix several schema inconsistencies
* revert behaviour change in function arguments parsing
* fix remaining nullability issues in new schema
* minor no-op refactor; use isListType from graphql-parser-hs
* use nullability of remote schema node, while creating a Remote reln
* fix 'ID' input coercing & action 'ID' type relationship mapping
* include ASTs in MonadExecuteQuery
* needed for PRO code-base
* Delete code for "interfaces implementing ifaces" (draft GraphQL spec)
Previously I started writing some code that adds support for a future GraphQL
feature where interfaces may themselves be sub-types of other interfaces.
However, this code was incomplete, and partially incorrect. So this commit
deletes support for that entirely.
* Ignore a remote schema test during the upgrade/downgrade test
The PDV refactor does a better job at exposing a minimal set of types through
introspection. In particular, not every type that is present in a remote schema
is re-exposed by Hasura. The test
test_schema_stitching.py::TestRemoteSchemaBasic::test_introspection assumed that
all types were re-exposed, which is not required for GraphQL compatibility, in
order to test some aspect of our support for remote schemas.
So while this particular test has been updated on PDV, the PDV branch now does
not pass the old test, which we argue to be incorrect. Hence this test is
disabled while we await a release, after which we can re-enable it.
This also re-enables a test that was previously disabled for similar, though
unrelated, reasons.
* add haddock documentation to the action's field parsers
* Deslecting some tests in server-upgrade
Some tests with current build are failing on server upgrade
which it should not. The response is more accurate than
what it was.
Also the upgrade tests were not throwing errors when the test is
expected to return an error, but succeeds. The test framework is
patched to catch this case.
* [skip ci] Add a long Note about interfaces and object types
* send the response headers back to client after running a query
* Deselect a few more tests during upgrade/downgrade test
* Update commit_diff.txt
* change log kind from db_migrate to catalog_migrate (#5531)
* Show method and complete URI in traced HTTP calls (#5525)
Co-authored-by: Vamshi Surabhi <0x777@users.noreply.github.com>
* restrict env variables start with HASURA_GRAPHQL_ for headers configuration in actions, event triggers & remote schemas (#5519)
* restrict env variables start with HASURA_GRAPHQL_ for headers definition in actions & event triggers
* update CHANGELOG.md
* Apply suggestions from code review
Co-authored-by: Vamshi Surabhi <0x777@users.noreply.github.com>
* fix introspection query if any enum column present in primary key (fix #5200) (#5522)
* Fix telemetry reporting of transport (websocket was reported as http)
* add log kinds in cli-migrations image (#5529)
* add log kinds in cli-migrations image
* give hint to resolve timeout error
* minor changes and CHANGELOG
* server: set hasura.tracecontext in RQL mutations [#5542] (#5555)
* server: set hasura.tracecontext in RQL mutations [#5542]
* Update test suite
Co-authored-by: Tirumarai Selvan <tiru@hasura.io>
* Add bulldozer auto-merge and -update configuration
We still need to add the github app (as of time of opening this PR)
Afterwards devs should be able to allow bulldozer to automatically
"update" the branch, merging in parent when it changes, as well as
automatically merge when all checks pass.
This is opt-in by adding the `auto-update-auto-merge` label to the PR.
* Remove 'bulldozer' config, try 'kodiak' for auto-merge
see: https://github.com/chdsbd/kodiak
The main issue that bit us was not being able to auto update forked
branches, also:
https://github.com/palantir/bulldozer/issues/66
https://github.com/palantir/bulldozer/issues/145
* Cherry-picked all commits
* [skip ci] Slightly improve formatting
* Revert "fix introspection query if any enum column present in primary key (fix #5200) (#5522)"
This reverts commit 0f9a5afa59a88f6824f4d63d58db246a5ba3fb03.
This undoes a cherry-pick of 34288e1eb5f2c5dad9e6d1e05453dd52397dc970 that was
already done previously in a6450e126bc2d98bcfd3791501986e4627ce6c6f, and
subsequently fixed for PDV in 70e89dc250f8ddc6e2b7930bbe2b3eeaa6dbe1db
* Do a small bit of tidying in Hasura.GraphQL.Parser.Collect
* Fix cherry-picking work
Some previous cherry-picks ended up modifying code that is commented out
* [skip ci] clarified comment regarding insert representation
* [skip ci] removed obsolete todos
* cosmetic change
* fix action error message
* [skip ci] remove obsolete comment
* [skip ci] synchronize stylish haskell extensions list
* use previously defined scalar names in parsers rather than ad-hoc literals
* Apply most syntax hlint hints.
* Clarify comment on update mutation.
* [skip ci] Clarify what fields should be specified for objects
* Update "_inc" description.
* Use record types rather than tuples fo IntrospectionResult and ParsedIntrospection
* Get rid of checkFieldNamesUnique (use Data.List.Extended.duplicates)
* Throw more errors when collecting query root names
* [skip ci] clean column parser comment
* Remove dead code inserted in ab65b39
* avoid converting to non-empty list where not needed
* add note and TODO about the disabled checks in PDV
* minor refactor in remoteField' function
* Unify two getObject methods
* Nitpicks in Remote.hs
* Update CHANGELOG.md
* Revert "Unify two getObject methods"
This reverts commit bd6bb40355b3d189a46c0312eb52225e18be57b3.
We do need two different getObject functions as the corresponding error message is different
* Fix error message in Remote.hs
* Update CHANGELOG.md
Co-authored-by: Auke Booij <auke@tulcod.com>
* Apply suggested Changelog fix.
Co-authored-by: Auke Booij <auke@tulcod.com>
* Fix typo in Changelog.
* [skip ci] Update changelog.
* reuse type names to avoid duplication
* Fix Hashable instance for Definition
The presence of `Maybe Unique`, and an optional description, as part of
`Definition`s, means that `Definition`s that are considered `Eq`ual may get
different hashes. This can happen, for instance, when one object is memoized
but another is not.
* [skip ci] Update commit_diff.txt
* Bump parser version.
* Bump freeze file after changes in parser.
* [skip ci] Incorporate commits from master
* Fix developer flag in server/cabal.project.freeze
Co-authored-by: Auke Booij <auke@tulcod.com>
* Deselect a changed ENUM test for upgrade/downgrade CI
* Deselect test here as well
* [skip ci] remove dead code
* Disable more tests for upgrade/downgrade
* Fix which test gets deselected
* Revert "Add hdb_catalog.current_setting abstraction for reading Hasura settings"
This reverts commit 66e85ab9fbd56cca2c28a80201f6604fbe811b85.
* Remove circular reference in cabal.project.freeze
Co-authored-by: Karthikeyan Chinnakonda <karthikeyan@hasura.io>
Co-authored-by: Auke Booij <auke@hasura.io>
Co-authored-by: Tirumarai Selvan <tiru@hasura.io>
Co-authored-by: Marion Schleifer <marion@hasura.io>
Co-authored-by: Aleksandra Sikora <ola.zxcvbnm@gmail.com>
Co-authored-by: Brandon Simmons <brandon.m.simmons@gmail.com>
Co-authored-by: Vamshi Surabhi <0x777@users.noreply.github.com>
Co-authored-by: Anon Ray <rayanon004@gmail.com>
Co-authored-by: rakeshkky <12475069+rakeshkky@users.noreply.github.com>
Co-authored-by: Anon Ray <ecthiender@users.noreply.github.com>
Co-authored-by: Vamshi Surabhi <vamshi@hasura.io>
Co-authored-by: Antoine Leblanc <antoine@hasura.io>
Co-authored-by: Brandon Simmons <brandon@hasura.io>
Co-authored-by: Phil Freeman <phil@hasura.io>
Co-authored-by: Lyndon Maydwell <lyndon@sordina.net>
Co-authored-by: Phil Freeman <paf31@cantab.net>
Co-authored-by: Naveen Naidu <naveennaidu479@gmail.com>
Co-authored-by: Karthikeyan Chinnakonda <chkarthikeyan95@gmail.com>
Co-authored-by: Nizar Malangadan <nizar-m@users.noreply.github.com>
Co-authored-by: Antoine Leblanc <crucuny@gmail.com>
Co-authored-by: Auke Booij <auke@tulcod.com>
2020-08-21 20:27:01 +03:00
|
|
|
throw400 UnexpectedPayload "subscriptions are not supported over HTTP, use websockets instead"
|
2021-04-13 10:00:43 +03:00
|
|
|
|
2021-10-26 14:44:18 +03:00
|
|
|
executeQueryStep ::
|
2021-10-29 17:42:07 +03:00
|
|
|
RootFieldAlias ->
|
2021-10-26 14:44:18 +03:00
|
|
|
EB.ExecutionStep ->
|
|
|
|
ExceptT (Either GQExecError QErr) m AnnotatedResponsePart
|
harmonize network manager handling
## Description
### I want to speak to the `Manager`
Oh boy. This PR is both fairly straightforward and overreaching, so let's break it down.
For most network access, we need a [`HTTP.Manager`](https://hackage.haskell.org/package/http-client-0.1.0.0/docs/Network-HTTP-Client-Manager.html). It is created only once, at the top level, when starting the engine, and is then threaded through the application to wherever we need to make a network call. As of main, the way we do this is not standardized: most of the GraphQL execution code passes it "manually" as a function argument throughout the code. We also have a custom monad constraint, `HasHttpManagerM`, that describes a monad's ability to provide a manager. And, finally, several parts of the code store the manager in some kind of argument structure, such as `RunT`'s `RunCtx`.
This PR's first goal is to harmonize all of this: we always create the manager at the root, and we already have it when we do our very first `runReaderT`. Wouldn't it make sense for the rest of the code to not manually pass it anywhere, to not store it anywhere, but to always rely on the current monad providing it? This is, in short, what this PR does: it implements a constraint on the base monads, so that they provide the manager, and removes most explicit passing from the code.
### First come, first served
One way this PR goes a tiny bit further than "just" doing the aforementioned harmonization is that it starts the process of implementing the "Services oriented architecture" roughly outlined in this [draft document](https://docs.google.com/document/d/1FAigqrST0juU1WcT4HIxJxe1iEBwTuBZodTaeUvsKqQ/edit?usp=sharing). Instead of using the existing `HasHTTPManagerM`, this PR revamps it into the `ProvidesNetwork` service.
The idea is, again, that we should make all "external" dependencies of the engine, all things that the core of the engine doesn't care about, a "service". This allows us to define clear APIs for features, to choose different implementations based on which version of the engine we're running, harmonizes our many scattered monadic constraints... Which is why this service is called "Network": we can refine it, moving forward, to be the constraint that defines how all network communication is to operate, instead of relying on disparate classes constraint or hardcoded decisions. A comment in the code clarifies this intent.
### Side-effects? In my Haskell?
This PR also unavoidably touches some other aspects of the codebase. One such example: it introduces `Hasura.App.AppContext`, named after `HasuraPro.Context.AppContext`: a name for the reader structure at the base level. It also transforms `Handler` from a type alias to a newtype, as `Handler` is where we actually enforce HTTP limits; but without `Handler` being a distinct type, any code path could simply do a `runExceptT $ runReader` and forget to enforce them.
(As a rule of thumb, i am starting to consider any straggling `runReaderT` or `runExceptT` as a code smell: we should not stack / unstack monads haphazardly, and every layer should be an opaque `newtype` with a corresponding run function.)
## Further work
In several places, i have left TODOs when i have encountered things that suggest that we should do further unrelated cleanups. I'll write down the follow-up steps, either in the aforementioned document or on slack. But, in short, at a glance, in approximate order, we could:
- delete `ExecutionCtx` as it is only a subset of `ServerCtx`, and remove one more `runReaderT` call
- delete `ServerConfigCtx` as it is only a subset of `ServerCtx`, and remove it from `RunCtx`
- remove `ServerCtx` from `HandlerCtx`, and make it part of `AppContext`, or even make it the `AppContext` altogether (since, at least for the OSS version, `AppContext` is there again only a subset)
- remove `CacheBuildParams` and `CacheBuild` altogether, as they're just a distinct stack that is a `ReaderT` on top of `IO` that contains, you guessed it, the same thing as `ServerCtx`
- move `RunT` out of `RQL.Types` and rename it, since after the previous cleanups **it only contains `UserInfo`**; it could be bundled with the authentication service, made a small implementation detail in `Hasura.Server.Auth`
- rename `PGMetadaStorageT` to something a bit more accurate, such as `App`, and enforce its IO base
This would significantly simply our complex stack. From there, or in parallel, we can start moving existing dependencies as Services. For the purpose of supporting read replicas entitlement, we could move `MonadResolveSource` to a `SourceResolver` service, as attempted in #7653, and transform `UserAuthenticationM` into a `Authentication` service.
PR-URL: https://github.com/hasura/graphql-engine-mono/pull/7736
GitOrigin-RevId: 68cce710eb9e7d752bda1ba0c49541d24df8209f
2023-02-22 18:53:52 +03:00
|
|
|
executeQueryStep fieldName = \case
|
2021-10-26 14:44:18 +03:00
|
|
|
E.ExecStepDB _headers exists remoteJoins -> doQErr $ do
|
|
|
|
(telemTimeIO_DT, resp) <-
|
|
|
|
AB.dispatchAnyBackend @BackendTransport
|
|
|
|
exists
|
2023-01-25 10:12:53 +03:00
|
|
|
\(EB.DBStepInfo _ sourceConfig genSql tx resolvedConnectionTemplate :: EB.DBStepInfo b) ->
|
2023-04-05 11:57:19 +03:00
|
|
|
runDBQuery @b reqId reqUnparsed fieldName userInfo logger agentLicenseKey sourceConfig (fmap (statsToAnyBackend @b) tx) genSql resolvedConnectionTemplate
|
2021-10-26 14:44:18 +03:00
|
|
|
finalResponse <-
|
2023-04-05 11:57:19 +03:00
|
|
|
RJ.processRemoteJoins reqId logger agentLicenseKey env reqHeaders userInfo resp remoteJoins reqUnparsed
|
2021-10-26 14:44:18 +03:00
|
|
|
pure $ AnnotatedResponsePart telemTimeIO_DT Telem.Local finalResponse []
|
Enable remote joins from remote schemas in the execution engine.
### Description
This PR adds the ability to perform remote joins from remote schemas in the engine. To do so, we alter the definition of an `ExecutionStep` targeting a remote schema: the `ExecStepRemote` constructor now expects a `Maybe RemoteJoins`. This new argument is used when processing the execution step, in the transport layer (either `Transport.HTTP` or `Transport.WebSocket`).
For this `Maybe RemoteJoins` to be extracted from a parsed query, this PR also extends the `Execute.RemoteJoin.Collect` module, to implement "collection" from a selection set. Not only do those new functions extract the remote joins, but they also apply all necessary transformations to the selection sets (such as inserting the necessary "phantom" fields used as join keys).
Finally in `Execute.RemoteJoin.Join`, we make two changes. First, we now always look for nested remote joins, regardless of whether the join we just performed went to a source or a remote schema; and second we adapt our join tree logic according to the special cases that were added to deal with remote server edge cases.
Additionally, this PR refactors / cleans / documents `Execute.RemoteJoin.RemoteServer`. This is not required as part of this change and could be moved to a separate PR if needed (a similar cleanup of `Join` is done independently in #3894). It also introduces a draft of a new documentation page for this project, that will be refined in the release PR that ships the feature (either #3069 or a copy of it).
While this PR extends the engine, it doesn't plug such relationships in the schema, meaning that, as of this PR, the new code paths in `Join` are technically unreachable. Adding the corresponding schema code and, ultimately, enabling the metadata API will be done in subsequent PRs.
### Keeping track of concrete type names
The main change this PR makes to the existing `Join` code is to handle a new reserved field we sometimes use when targeting remote servers: the `__hasura_internal_typename` field. In short, a GraphQL selection set can sometimes "branch" based on the concrete "runtime type" of the object on which the selection happens:
```graphql
query {
author(id: 53478) {
... on Writer {
name
articles {
title
}
}
... on Artist {
name
articles {
title
}
}
}
}
```
If both of those `articles` are remote joins, we need to be able, when we get the answer, to differentiate between the two different cases. We do this by asking for `__typename`, to be able to decide if we're in the `Writer` or the `Artist` branch of the query.
To avoid further processing / customization of results, we only insert this `__hasura_internal_typename: __typename` field in the query in the case of unions of interfaces AND if we have the guarantee that we will processing the request as part of the remote joins "folding": that is, if there's any remote join in this branch in the tree. Otherwise, we don't insert the field, and we leave that part of the response untouched.
PR-URL: https://github.com/hasura/graphql-engine-mono/pull/3810
GitOrigin-RevId: 89aaf16274d68e26ad3730b80c2d2fdc2896b96c
2022-03-09 06:17:28 +03:00
|
|
|
E.ExecStepRemote rsi resultCustomizer gqlReq remoteJoins -> do
|
2023-03-15 16:05:17 +03:00
|
|
|
logQueryLog logger $ QueryLog reqUnparsed Nothing reqId QueryLogKindRemoteSchema
|
harmonize network manager handling
## Description
### I want to speak to the `Manager`
Oh boy. This PR is both fairly straightforward and overreaching, so let's break it down.
For most network access, we need a [`HTTP.Manager`](https://hackage.haskell.org/package/http-client-0.1.0.0/docs/Network-HTTP-Client-Manager.html). It is created only once, at the top level, when starting the engine, and is then threaded through the application to wherever we need to make a network call. As of main, the way we do this is not standardized: most of the GraphQL execution code passes it "manually" as a function argument throughout the code. We also have a custom monad constraint, `HasHttpManagerM`, that describes a monad's ability to provide a manager. And, finally, several parts of the code store the manager in some kind of argument structure, such as `RunT`'s `RunCtx`.
This PR's first goal is to harmonize all of this: we always create the manager at the root, and we already have it when we do our very first `runReaderT`. Wouldn't it make sense for the rest of the code to not manually pass it anywhere, to not store it anywhere, but to always rely on the current monad providing it? This is, in short, what this PR does: it implements a constraint on the base monads, so that they provide the manager, and removes most explicit passing from the code.
### First come, first served
One way this PR goes a tiny bit further than "just" doing the aforementioned harmonization is that it starts the process of implementing the "Services oriented architecture" roughly outlined in this [draft document](https://docs.google.com/document/d/1FAigqrST0juU1WcT4HIxJxe1iEBwTuBZodTaeUvsKqQ/edit?usp=sharing). Instead of using the existing `HasHTTPManagerM`, this PR revamps it into the `ProvidesNetwork` service.
The idea is, again, that we should make all "external" dependencies of the engine, all things that the core of the engine doesn't care about, a "service". This allows us to define clear APIs for features, to choose different implementations based on which version of the engine we're running, harmonizes our many scattered monadic constraints... Which is why this service is called "Network": we can refine it, moving forward, to be the constraint that defines how all network communication is to operate, instead of relying on disparate classes constraint or hardcoded decisions. A comment in the code clarifies this intent.
### Side-effects? In my Haskell?
This PR also unavoidably touches some other aspects of the codebase. One such example: it introduces `Hasura.App.AppContext`, named after `HasuraPro.Context.AppContext`: a name for the reader structure at the base level. It also transforms `Handler` from a type alias to a newtype, as `Handler` is where we actually enforce HTTP limits; but without `Handler` being a distinct type, any code path could simply do a `runExceptT $ runReader` and forget to enforce them.
(As a rule of thumb, i am starting to consider any straggling `runReaderT` or `runExceptT` as a code smell: we should not stack / unstack monads haphazardly, and every layer should be an opaque `newtype` with a corresponding run function.)
## Further work
In several places, i have left TODOs when i have encountered things that suggest that we should do further unrelated cleanups. I'll write down the follow-up steps, either in the aforementioned document or on slack. But, in short, at a glance, in approximate order, we could:
- delete `ExecutionCtx` as it is only a subset of `ServerCtx`, and remove one more `runReaderT` call
- delete `ServerConfigCtx` as it is only a subset of `ServerCtx`, and remove it from `RunCtx`
- remove `ServerCtx` from `HandlerCtx`, and make it part of `AppContext`, or even make it the `AppContext` altogether (since, at least for the OSS version, `AppContext` is there again only a subset)
- remove `CacheBuildParams` and `CacheBuild` altogether, as they're just a distinct stack that is a `ReaderT` on top of `IO` that contains, you guessed it, the same thing as `ServerCtx`
- move `RunT` out of `RQL.Types` and rename it, since after the previous cleanups **it only contains `UserInfo`**; it could be bundled with the authentication service, made a small implementation detail in `Hasura.Server.Auth`
- rename `PGMetadaStorageT` to something a bit more accurate, such as `App`, and enforce its IO base
This would significantly simply our complex stack. From there, or in parallel, we can start moving existing dependencies as Services. For the purpose of supporting read replicas entitlement, we could move `MonadResolveSource` to a `SourceResolver` service, as attempted in #7653, and transform `UserAuthenticationM` into a `Authentication` service.
PR-URL: https://github.com/hasura/graphql-engine-mono/pull/7736
GitOrigin-RevId: 68cce710eb9e7d752bda1ba0c49541d24df8209f
2023-02-22 18:53:52 +03:00
|
|
|
runRemoteGQ fieldName rsi resultCustomizer gqlReq remoteJoins
|
2021-10-26 14:44:18 +03:00
|
|
|
E.ExecStepAction aep _ remoteJoins -> do
|
2023-03-15 16:05:17 +03:00
|
|
|
logQueryLog logger $ QueryLog reqUnparsed Nothing reqId QueryLogKindAction
|
2021-10-26 14:44:18 +03:00
|
|
|
(time, resp) <- doQErr $ do
|
|
|
|
(time, (resp, _)) <- EA.runActionExecution userInfo aep
|
|
|
|
finalResponse <-
|
2023-04-05 11:57:19 +03:00
|
|
|
RJ.processRemoteJoins reqId logger agentLicenseKey env reqHeaders userInfo resp remoteJoins reqUnparsed
|
2021-10-26 14:44:18 +03:00
|
|
|
pure (time, finalResponse)
|
|
|
|
pure $ AnnotatedResponsePart time Telem.Empty resp []
|
|
|
|
E.ExecStepRaw json -> do
|
2023-03-15 16:05:17 +03:00
|
|
|
logQueryLog logger $ QueryLog reqUnparsed Nothing reqId QueryLogKindIntrospection
|
2021-10-26 14:44:18 +03:00
|
|
|
buildRaw json
|
2022-07-25 18:53:25 +03:00
|
|
|
-- For `ExecStepMulti`, execute all steps and then concat them in a list
|
|
|
|
E.ExecStepMulti lst -> do
|
harmonize network manager handling
## Description
### I want to speak to the `Manager`
Oh boy. This PR is both fairly straightforward and overreaching, so let's break it down.
For most network access, we need a [`HTTP.Manager`](https://hackage.haskell.org/package/http-client-0.1.0.0/docs/Network-HTTP-Client-Manager.html). It is created only once, at the top level, when starting the engine, and is then threaded through the application to wherever we need to make a network call. As of main, the way we do this is not standardized: most of the GraphQL execution code passes it "manually" as a function argument throughout the code. We also have a custom monad constraint, `HasHttpManagerM`, that describes a monad's ability to provide a manager. And, finally, several parts of the code store the manager in some kind of argument structure, such as `RunT`'s `RunCtx`.
This PR's first goal is to harmonize all of this: we always create the manager at the root, and we already have it when we do our very first `runReaderT`. Wouldn't it make sense for the rest of the code to not manually pass it anywhere, to not store it anywhere, but to always rely on the current monad providing it? This is, in short, what this PR does: it implements a constraint on the base monads, so that they provide the manager, and removes most explicit passing from the code.
### First come, first served
One way this PR goes a tiny bit further than "just" doing the aforementioned harmonization is that it starts the process of implementing the "Services oriented architecture" roughly outlined in this [draft document](https://docs.google.com/document/d/1FAigqrST0juU1WcT4HIxJxe1iEBwTuBZodTaeUvsKqQ/edit?usp=sharing). Instead of using the existing `HasHTTPManagerM`, this PR revamps it into the `ProvidesNetwork` service.
The idea is, again, that we should make all "external" dependencies of the engine, all things that the core of the engine doesn't care about, a "service". This allows us to define clear APIs for features, to choose different implementations based on which version of the engine we're running, harmonizes our many scattered monadic constraints... Which is why this service is called "Network": we can refine it, moving forward, to be the constraint that defines how all network communication is to operate, instead of relying on disparate classes constraint or hardcoded decisions. A comment in the code clarifies this intent.
### Side-effects? In my Haskell?
This PR also unavoidably touches some other aspects of the codebase. One such example: it introduces `Hasura.App.AppContext`, named after `HasuraPro.Context.AppContext`: a name for the reader structure at the base level. It also transforms `Handler` from a type alias to a newtype, as `Handler` is where we actually enforce HTTP limits; but without `Handler` being a distinct type, any code path could simply do a `runExceptT $ runReader` and forget to enforce them.
(As a rule of thumb, i am starting to consider any straggling `runReaderT` or `runExceptT` as a code smell: we should not stack / unstack monads haphazardly, and every layer should be an opaque `newtype` with a corresponding run function.)
## Further work
In several places, i have left TODOs when i have encountered things that suggest that we should do further unrelated cleanups. I'll write down the follow-up steps, either in the aforementioned document or on slack. But, in short, at a glance, in approximate order, we could:
- delete `ExecutionCtx` as it is only a subset of `ServerCtx`, and remove one more `runReaderT` call
- delete `ServerConfigCtx` as it is only a subset of `ServerCtx`, and remove it from `RunCtx`
- remove `ServerCtx` from `HandlerCtx`, and make it part of `AppContext`, or even make it the `AppContext` altogether (since, at least for the OSS version, `AppContext` is there again only a subset)
- remove `CacheBuildParams` and `CacheBuild` altogether, as they're just a distinct stack that is a `ReaderT` on top of `IO` that contains, you guessed it, the same thing as `ServerCtx`
- move `RunT` out of `RQL.Types` and rename it, since after the previous cleanups **it only contains `UserInfo`**; it could be bundled with the authentication service, made a small implementation detail in `Hasura.Server.Auth`
- rename `PGMetadaStorageT` to something a bit more accurate, such as `App`, and enforce its IO base
This would significantly simply our complex stack. From there, or in parallel, we can start moving existing dependencies as Services. For the purpose of supporting read replicas entitlement, we could move `MonadResolveSource` to a `SourceResolver` service, as attempted in #7653, and transform `UserAuthenticationM` into a `Authentication` service.
PR-URL: https://github.com/hasura/graphql-engine-mono/pull/7736
GitOrigin-RevId: 68cce710eb9e7d752bda1ba0c49541d24df8209f
2023-02-22 18:53:52 +03:00
|
|
|
_all <- traverse (executeQueryStep fieldName) lst
|
2022-07-25 18:53:25 +03:00
|
|
|
pure $ AnnotatedResponsePart 0 Telem.Local (encJFromList (map arpResponse _all)) []
|
2021-10-26 14:44:18 +03:00
|
|
|
|
|
|
|
executeMutationStep ::
|
2021-10-29 17:42:07 +03:00
|
|
|
RootFieldAlias ->
|
2021-10-26 14:44:18 +03:00
|
|
|
EB.ExecutionStep ->
|
|
|
|
ExceptT (Either GQExecError QErr) m AnnotatedResponsePart
|
harmonize network manager handling
## Description
### I want to speak to the `Manager`
Oh boy. This PR is both fairly straightforward and overreaching, so let's break it down.
For most network access, we need a [`HTTP.Manager`](https://hackage.haskell.org/package/http-client-0.1.0.0/docs/Network-HTTP-Client-Manager.html). It is created only once, at the top level, when starting the engine, and is then threaded through the application to wherever we need to make a network call. As of main, the way we do this is not standardized: most of the GraphQL execution code passes it "manually" as a function argument throughout the code. We also have a custom monad constraint, `HasHttpManagerM`, that describes a monad's ability to provide a manager. And, finally, several parts of the code store the manager in some kind of argument structure, such as `RunT`'s `RunCtx`.
This PR's first goal is to harmonize all of this: we always create the manager at the root, and we already have it when we do our very first `runReaderT`. Wouldn't it make sense for the rest of the code to not manually pass it anywhere, to not store it anywhere, but to always rely on the current monad providing it? This is, in short, what this PR does: it implements a constraint on the base monads, so that they provide the manager, and removes most explicit passing from the code.
### First come, first served
One way this PR goes a tiny bit further than "just" doing the aforementioned harmonization is that it starts the process of implementing the "Services oriented architecture" roughly outlined in this [draft document](https://docs.google.com/document/d/1FAigqrST0juU1WcT4HIxJxe1iEBwTuBZodTaeUvsKqQ/edit?usp=sharing). Instead of using the existing `HasHTTPManagerM`, this PR revamps it into the `ProvidesNetwork` service.
The idea is, again, that we should make all "external" dependencies of the engine, all things that the core of the engine doesn't care about, a "service". This allows us to define clear APIs for features, to choose different implementations based on which version of the engine we're running, harmonizes our many scattered monadic constraints... Which is why this service is called "Network": we can refine it, moving forward, to be the constraint that defines how all network communication is to operate, instead of relying on disparate classes constraint or hardcoded decisions. A comment in the code clarifies this intent.
### Side-effects? In my Haskell?
This PR also unavoidably touches some other aspects of the codebase. One such example: it introduces `Hasura.App.AppContext`, named after `HasuraPro.Context.AppContext`: a name for the reader structure at the base level. It also transforms `Handler` from a type alias to a newtype, as `Handler` is where we actually enforce HTTP limits; but without `Handler` being a distinct type, any code path could simply do a `runExceptT $ runReader` and forget to enforce them.
(As a rule of thumb, i am starting to consider any straggling `runReaderT` or `runExceptT` as a code smell: we should not stack / unstack monads haphazardly, and every layer should be an opaque `newtype` with a corresponding run function.)
## Further work
In several places, i have left TODOs when i have encountered things that suggest that we should do further unrelated cleanups. I'll write down the follow-up steps, either in the aforementioned document or on slack. But, in short, at a glance, in approximate order, we could:
- delete `ExecutionCtx` as it is only a subset of `ServerCtx`, and remove one more `runReaderT` call
- delete `ServerConfigCtx` as it is only a subset of `ServerCtx`, and remove it from `RunCtx`
- remove `ServerCtx` from `HandlerCtx`, and make it part of `AppContext`, or even make it the `AppContext` altogether (since, at least for the OSS version, `AppContext` is there again only a subset)
- remove `CacheBuildParams` and `CacheBuild` altogether, as they're just a distinct stack that is a `ReaderT` on top of `IO` that contains, you guessed it, the same thing as `ServerCtx`
- move `RunT` out of `RQL.Types` and rename it, since after the previous cleanups **it only contains `UserInfo`**; it could be bundled with the authentication service, made a small implementation detail in `Hasura.Server.Auth`
- rename `PGMetadaStorageT` to something a bit more accurate, such as `App`, and enforce its IO base
This would significantly simply our complex stack. From there, or in parallel, we can start moving existing dependencies as Services. For the purpose of supporting read replicas entitlement, we could move `MonadResolveSource` to a `SourceResolver` service, as attempted in #7653, and transform `UserAuthenticationM` into a `Authentication` service.
PR-URL: https://github.com/hasura/graphql-engine-mono/pull/7736
GitOrigin-RevId: 68cce710eb9e7d752bda1ba0c49541d24df8209f
2023-02-22 18:53:52 +03:00
|
|
|
executeMutationStep fieldName = \case
|
2021-10-26 14:44:18 +03:00
|
|
|
E.ExecStepDB responseHeaders exists remoteJoins -> doQErr $ do
|
|
|
|
(telemTimeIO_DT, resp) <-
|
|
|
|
AB.dispatchAnyBackend @BackendTransport
|
|
|
|
exists
|
2023-01-25 10:12:53 +03:00
|
|
|
\(EB.DBStepInfo _ sourceConfig genSql tx resolvedConnectionTemplate :: EB.DBStepInfo b) ->
|
2023-04-05 11:57:19 +03:00
|
|
|
runDBMutation @b reqId reqUnparsed fieldName userInfo logger agentLicenseKey sourceConfig (fmap EB.arResult tx) genSql resolvedConnectionTemplate
|
2021-10-26 14:44:18 +03:00
|
|
|
finalResponse <-
|
2023-04-05 11:57:19 +03:00
|
|
|
RJ.processRemoteJoins reqId logger agentLicenseKey env reqHeaders userInfo resp remoteJoins reqUnparsed
|
2021-10-26 14:44:18 +03:00
|
|
|
pure $ AnnotatedResponsePart telemTimeIO_DT Telem.Local finalResponse responseHeaders
|
Enable remote joins from remote schemas in the execution engine.
### Description
This PR adds the ability to perform remote joins from remote schemas in the engine. To do so, we alter the definition of an `ExecutionStep` targeting a remote schema: the `ExecStepRemote` constructor now expects a `Maybe RemoteJoins`. This new argument is used when processing the execution step, in the transport layer (either `Transport.HTTP` or `Transport.WebSocket`).
For this `Maybe RemoteJoins` to be extracted from a parsed query, this PR also extends the `Execute.RemoteJoin.Collect` module, to implement "collection" from a selection set. Not only do those new functions extract the remote joins, but they also apply all necessary transformations to the selection sets (such as inserting the necessary "phantom" fields used as join keys).
Finally in `Execute.RemoteJoin.Join`, we make two changes. First, we now always look for nested remote joins, regardless of whether the join we just performed went to a source or a remote schema; and second we adapt our join tree logic according to the special cases that were added to deal with remote server edge cases.
Additionally, this PR refactors / cleans / documents `Execute.RemoteJoin.RemoteServer`. This is not required as part of this change and could be moved to a separate PR if needed (a similar cleanup of `Join` is done independently in #3894). It also introduces a draft of a new documentation page for this project, that will be refined in the release PR that ships the feature (either #3069 or a copy of it).
While this PR extends the engine, it doesn't plug such relationships in the schema, meaning that, as of this PR, the new code paths in `Join` are technically unreachable. Adding the corresponding schema code and, ultimately, enabling the metadata API will be done in subsequent PRs.
### Keeping track of concrete type names
The main change this PR makes to the existing `Join` code is to handle a new reserved field we sometimes use when targeting remote servers: the `__hasura_internal_typename` field. In short, a GraphQL selection set can sometimes "branch" based on the concrete "runtime type" of the object on which the selection happens:
```graphql
query {
author(id: 53478) {
... on Writer {
name
articles {
title
}
}
... on Artist {
name
articles {
title
}
}
}
}
```
If both of those `articles` are remote joins, we need to be able, when we get the answer, to differentiate between the two different cases. We do this by asking for `__typename`, to be able to decide if we're in the `Writer` or the `Artist` branch of the query.
To avoid further processing / customization of results, we only insert this `__hasura_internal_typename: __typename` field in the query in the case of unions of interfaces AND if we have the guarantee that we will processing the request as part of the remote joins "folding": that is, if there's any remote join in this branch in the tree. Otherwise, we don't insert the field, and we leave that part of the response untouched.
PR-URL: https://github.com/hasura/graphql-engine-mono/pull/3810
GitOrigin-RevId: 89aaf16274d68e26ad3730b80c2d2fdc2896b96c
2022-03-09 06:17:28 +03:00
|
|
|
E.ExecStepRemote rsi resultCustomizer gqlReq remoteJoins -> do
|
2023-03-15 16:05:17 +03:00
|
|
|
logQueryLog logger $ QueryLog reqUnparsed Nothing reqId QueryLogKindRemoteSchema
|
harmonize network manager handling
## Description
### I want to speak to the `Manager`
Oh boy. This PR is both fairly straightforward and overreaching, so let's break it down.
For most network access, we need a [`HTTP.Manager`](https://hackage.haskell.org/package/http-client-0.1.0.0/docs/Network-HTTP-Client-Manager.html). It is created only once, at the top level, when starting the engine, and is then threaded through the application to wherever we need to make a network call. As of main, the way we do this is not standardized: most of the GraphQL execution code passes it "manually" as a function argument throughout the code. We also have a custom monad constraint, `HasHttpManagerM`, that describes a monad's ability to provide a manager. And, finally, several parts of the code store the manager in some kind of argument structure, such as `RunT`'s `RunCtx`.
This PR's first goal is to harmonize all of this: we always create the manager at the root, and we already have it when we do our very first `runReaderT`. Wouldn't it make sense for the rest of the code to not manually pass it anywhere, to not store it anywhere, but to always rely on the current monad providing it? This is, in short, what this PR does: it implements a constraint on the base monads, so that they provide the manager, and removes most explicit passing from the code.
### First come, first served
One way this PR goes a tiny bit further than "just" doing the aforementioned harmonization is that it starts the process of implementing the "Services oriented architecture" roughly outlined in this [draft document](https://docs.google.com/document/d/1FAigqrST0juU1WcT4HIxJxe1iEBwTuBZodTaeUvsKqQ/edit?usp=sharing). Instead of using the existing `HasHTTPManagerM`, this PR revamps it into the `ProvidesNetwork` service.
The idea is, again, that we should make all "external" dependencies of the engine, all things that the core of the engine doesn't care about, a "service". This allows us to define clear APIs for features, to choose different implementations based on which version of the engine we're running, harmonizes our many scattered monadic constraints... Which is why this service is called "Network": we can refine it, moving forward, to be the constraint that defines how all network communication is to operate, instead of relying on disparate classes constraint or hardcoded decisions. A comment in the code clarifies this intent.
### Side-effects? In my Haskell?
This PR also unavoidably touches some other aspects of the codebase. One such example: it introduces `Hasura.App.AppContext`, named after `HasuraPro.Context.AppContext`: a name for the reader structure at the base level. It also transforms `Handler` from a type alias to a newtype, as `Handler` is where we actually enforce HTTP limits; but without `Handler` being a distinct type, any code path could simply do a `runExceptT $ runReader` and forget to enforce them.
(As a rule of thumb, i am starting to consider any straggling `runReaderT` or `runExceptT` as a code smell: we should not stack / unstack monads haphazardly, and every layer should be an opaque `newtype` with a corresponding run function.)
## Further work
In several places, i have left TODOs when i have encountered things that suggest that we should do further unrelated cleanups. I'll write down the follow-up steps, either in the aforementioned document or on slack. But, in short, at a glance, in approximate order, we could:
- delete `ExecutionCtx` as it is only a subset of `ServerCtx`, and remove one more `runReaderT` call
- delete `ServerConfigCtx` as it is only a subset of `ServerCtx`, and remove it from `RunCtx`
- remove `ServerCtx` from `HandlerCtx`, and make it part of `AppContext`, or even make it the `AppContext` altogether (since, at least for the OSS version, `AppContext` is there again only a subset)
- remove `CacheBuildParams` and `CacheBuild` altogether, as they're just a distinct stack that is a `ReaderT` on top of `IO` that contains, you guessed it, the same thing as `ServerCtx`
- move `RunT` out of `RQL.Types` and rename it, since after the previous cleanups **it only contains `UserInfo`**; it could be bundled with the authentication service, made a small implementation detail in `Hasura.Server.Auth`
- rename `PGMetadaStorageT` to something a bit more accurate, such as `App`, and enforce its IO base
This would significantly simply our complex stack. From there, or in parallel, we can start moving existing dependencies as Services. For the purpose of supporting read replicas entitlement, we could move `MonadResolveSource` to a `SourceResolver` service, as attempted in #7653, and transform `UserAuthenticationM` into a `Authentication` service.
PR-URL: https://github.com/hasura/graphql-engine-mono/pull/7736
GitOrigin-RevId: 68cce710eb9e7d752bda1ba0c49541d24df8209f
2023-02-22 18:53:52 +03:00
|
|
|
runRemoteGQ fieldName rsi resultCustomizer gqlReq remoteJoins
|
2021-10-26 14:44:18 +03:00
|
|
|
E.ExecStepAction aep _ remoteJoins -> do
|
2023-03-15 16:05:17 +03:00
|
|
|
logQueryLog logger $ QueryLog reqUnparsed Nothing reqId QueryLogKindAction
|
2021-10-26 14:44:18 +03:00
|
|
|
(time, (resp, hdrs)) <- doQErr $ do
|
|
|
|
(time, (resp, hdrs)) <- EA.runActionExecution userInfo aep
|
|
|
|
finalResponse <-
|
2023-04-05 11:57:19 +03:00
|
|
|
RJ.processRemoteJoins reqId logger agentLicenseKey env reqHeaders userInfo resp remoteJoins reqUnparsed
|
2021-10-26 14:44:18 +03:00
|
|
|
pure (time, (finalResponse, hdrs))
|
|
|
|
pure $ AnnotatedResponsePart time Telem.Empty resp $ fromMaybe [] hdrs
|
|
|
|
E.ExecStepRaw json -> do
|
2023-03-15 16:05:17 +03:00
|
|
|
logQueryLog logger $ QueryLog reqUnparsed Nothing reqId QueryLogKindIntrospection
|
2021-10-26 14:44:18 +03:00
|
|
|
buildRaw json
|
2022-07-25 18:53:25 +03:00
|
|
|
-- For `ExecStepMulti`, execute all steps and then concat them in a list
|
|
|
|
E.ExecStepMulti lst -> do
|
harmonize network manager handling
## Description
### I want to speak to the `Manager`
Oh boy. This PR is both fairly straightforward and overreaching, so let's break it down.
For most network access, we need a [`HTTP.Manager`](https://hackage.haskell.org/package/http-client-0.1.0.0/docs/Network-HTTP-Client-Manager.html). It is created only once, at the top level, when starting the engine, and is then threaded through the application to wherever we need to make a network call. As of main, the way we do this is not standardized: most of the GraphQL execution code passes it "manually" as a function argument throughout the code. We also have a custom monad constraint, `HasHttpManagerM`, that describes a monad's ability to provide a manager. And, finally, several parts of the code store the manager in some kind of argument structure, such as `RunT`'s `RunCtx`.
This PR's first goal is to harmonize all of this: we always create the manager at the root, and we already have it when we do our very first `runReaderT`. Wouldn't it make sense for the rest of the code to not manually pass it anywhere, to not store it anywhere, but to always rely on the current monad providing it? This is, in short, what this PR does: it implements a constraint on the base monads, so that they provide the manager, and removes most explicit passing from the code.
### First come, first served
One way this PR goes a tiny bit further than "just" doing the aforementioned harmonization is that it starts the process of implementing the "Services oriented architecture" roughly outlined in this [draft document](https://docs.google.com/document/d/1FAigqrST0juU1WcT4HIxJxe1iEBwTuBZodTaeUvsKqQ/edit?usp=sharing). Instead of using the existing `HasHTTPManagerM`, this PR revamps it into the `ProvidesNetwork` service.
The idea is, again, that we should make all "external" dependencies of the engine, all things that the core of the engine doesn't care about, a "service". This allows us to define clear APIs for features, to choose different implementations based on which version of the engine we're running, harmonizes our many scattered monadic constraints... Which is why this service is called "Network": we can refine it, moving forward, to be the constraint that defines how all network communication is to operate, instead of relying on disparate classes constraint or hardcoded decisions. A comment in the code clarifies this intent.
### Side-effects? In my Haskell?
This PR also unavoidably touches some other aspects of the codebase. One such example: it introduces `Hasura.App.AppContext`, named after `HasuraPro.Context.AppContext`: a name for the reader structure at the base level. It also transforms `Handler` from a type alias to a newtype, as `Handler` is where we actually enforce HTTP limits; but without `Handler` being a distinct type, any code path could simply do a `runExceptT $ runReader` and forget to enforce them.
(As a rule of thumb, i am starting to consider any straggling `runReaderT` or `runExceptT` as a code smell: we should not stack / unstack monads haphazardly, and every layer should be an opaque `newtype` with a corresponding run function.)
## Further work
In several places, i have left TODOs when i have encountered things that suggest that we should do further unrelated cleanups. I'll write down the follow-up steps, either in the aforementioned document or on slack. But, in short, at a glance, in approximate order, we could:
- delete `ExecutionCtx` as it is only a subset of `ServerCtx`, and remove one more `runReaderT` call
- delete `ServerConfigCtx` as it is only a subset of `ServerCtx`, and remove it from `RunCtx`
- remove `ServerCtx` from `HandlerCtx`, and make it part of `AppContext`, or even make it the `AppContext` altogether (since, at least for the OSS version, `AppContext` is there again only a subset)
- remove `CacheBuildParams` and `CacheBuild` altogether, as they're just a distinct stack that is a `ReaderT` on top of `IO` that contains, you guessed it, the same thing as `ServerCtx`
- move `RunT` out of `RQL.Types` and rename it, since after the previous cleanups **it only contains `UserInfo`**; it could be bundled with the authentication service, made a small implementation detail in `Hasura.Server.Auth`
- rename `PGMetadaStorageT` to something a bit more accurate, such as `App`, and enforce its IO base
This would significantly simply our complex stack. From there, or in parallel, we can start moving existing dependencies as Services. For the purpose of supporting read replicas entitlement, we could move `MonadResolveSource` to a `SourceResolver` service, as attempted in #7653, and transform `UserAuthenticationM` into a `Authentication` service.
PR-URL: https://github.com/hasura/graphql-engine-mono/pull/7736
GitOrigin-RevId: 68cce710eb9e7d752bda1ba0c49541d24df8209f
2023-02-22 18:53:52 +03:00
|
|
|
_all <- traverse (executeQueryStep fieldName) lst
|
2022-07-25 18:53:25 +03:00
|
|
|
pure $ AnnotatedResponsePart 0 Telem.Local (encJFromList (map arpResponse _all)) []
|
2020-10-07 13:23:17 +03:00
|
|
|
|
harmonize network manager handling
## Description
### I want to speak to the `Manager`
Oh boy. This PR is both fairly straightforward and overreaching, so let's break it down.
For most network access, we need a [`HTTP.Manager`](https://hackage.haskell.org/package/http-client-0.1.0.0/docs/Network-HTTP-Client-Manager.html). It is created only once, at the top level, when starting the engine, and is then threaded through the application to wherever we need to make a network call. As of main, the way we do this is not standardized: most of the GraphQL execution code passes it "manually" as a function argument throughout the code. We also have a custom monad constraint, `HasHttpManagerM`, that describes a monad's ability to provide a manager. And, finally, several parts of the code store the manager in some kind of argument structure, such as `RunT`'s `RunCtx`.
This PR's first goal is to harmonize all of this: we always create the manager at the root, and we already have it when we do our very first `runReaderT`. Wouldn't it make sense for the rest of the code to not manually pass it anywhere, to not store it anywhere, but to always rely on the current monad providing it? This is, in short, what this PR does: it implements a constraint on the base monads, so that they provide the manager, and removes most explicit passing from the code.
### First come, first served
One way this PR goes a tiny bit further than "just" doing the aforementioned harmonization is that it starts the process of implementing the "Services oriented architecture" roughly outlined in this [draft document](https://docs.google.com/document/d/1FAigqrST0juU1WcT4HIxJxe1iEBwTuBZodTaeUvsKqQ/edit?usp=sharing). Instead of using the existing `HasHTTPManagerM`, this PR revamps it into the `ProvidesNetwork` service.
The idea is, again, that we should make all "external" dependencies of the engine, all things that the core of the engine doesn't care about, a "service". This allows us to define clear APIs for features, to choose different implementations based on which version of the engine we're running, harmonizes our many scattered monadic constraints... Which is why this service is called "Network": we can refine it, moving forward, to be the constraint that defines how all network communication is to operate, instead of relying on disparate classes constraint or hardcoded decisions. A comment in the code clarifies this intent.
### Side-effects? In my Haskell?
This PR also unavoidably touches some other aspects of the codebase. One such example: it introduces `Hasura.App.AppContext`, named after `HasuraPro.Context.AppContext`: a name for the reader structure at the base level. It also transforms `Handler` from a type alias to a newtype, as `Handler` is where we actually enforce HTTP limits; but without `Handler` being a distinct type, any code path could simply do a `runExceptT $ runReader` and forget to enforce them.
(As a rule of thumb, i am starting to consider any straggling `runReaderT` or `runExceptT` as a code smell: we should not stack / unstack monads haphazardly, and every layer should be an opaque `newtype` with a corresponding run function.)
## Further work
In several places, i have left TODOs when i have encountered things that suggest that we should do further unrelated cleanups. I'll write down the follow-up steps, either in the aforementioned document or on slack. But, in short, at a glance, in approximate order, we could:
- delete `ExecutionCtx` as it is only a subset of `ServerCtx`, and remove one more `runReaderT` call
- delete `ServerConfigCtx` as it is only a subset of `ServerCtx`, and remove it from `RunCtx`
- remove `ServerCtx` from `HandlerCtx`, and make it part of `AppContext`, or even make it the `AppContext` altogether (since, at least for the OSS version, `AppContext` is there again only a subset)
- remove `CacheBuildParams` and `CacheBuild` altogether, as they're just a distinct stack that is a `ReaderT` on top of `IO` that contains, you guessed it, the same thing as `ServerCtx`
- move `RunT` out of `RQL.Types` and rename it, since after the previous cleanups **it only contains `UserInfo`**; it could be bundled with the authentication service, made a small implementation detail in `Hasura.Server.Auth`
- rename `PGMetadaStorageT` to something a bit more accurate, such as `App`, and enforce its IO base
This would significantly simply our complex stack. From there, or in parallel, we can start moving existing dependencies as Services. For the purpose of supporting read replicas entitlement, we could move `MonadResolveSource` to a `SourceResolver` service, as attempted in #7653, and transform `UserAuthenticationM` into a `Authentication` service.
PR-URL: https://github.com/hasura/graphql-engine-mono/pull/7736
GitOrigin-RevId: 68cce710eb9e7d752bda1ba0c49541d24df8209f
2023-02-22 18:53:52 +03:00
|
|
|
runRemoteGQ fieldName rsi resultCustomizer gqlReq remoteJoins = do
|
2020-12-20 09:52:43 +03:00
|
|
|
(telemTimeIO_DT, remoteResponseHeaders, resp) <-
|
harmonize network manager handling
## Description
### I want to speak to the `Manager`
Oh boy. This PR is both fairly straightforward and overreaching, so let's break it down.
For most network access, we need a [`HTTP.Manager`](https://hackage.haskell.org/package/http-client-0.1.0.0/docs/Network-HTTP-Client-Manager.html). It is created only once, at the top level, when starting the engine, and is then threaded through the application to wherever we need to make a network call. As of main, the way we do this is not standardized: most of the GraphQL execution code passes it "manually" as a function argument throughout the code. We also have a custom monad constraint, `HasHttpManagerM`, that describes a monad's ability to provide a manager. And, finally, several parts of the code store the manager in some kind of argument structure, such as `RunT`'s `RunCtx`.
This PR's first goal is to harmonize all of this: we always create the manager at the root, and we already have it when we do our very first `runReaderT`. Wouldn't it make sense for the rest of the code to not manually pass it anywhere, to not store it anywhere, but to always rely on the current monad providing it? This is, in short, what this PR does: it implements a constraint on the base monads, so that they provide the manager, and removes most explicit passing from the code.
### First come, first served
One way this PR goes a tiny bit further than "just" doing the aforementioned harmonization is that it starts the process of implementing the "Services oriented architecture" roughly outlined in this [draft document](https://docs.google.com/document/d/1FAigqrST0juU1WcT4HIxJxe1iEBwTuBZodTaeUvsKqQ/edit?usp=sharing). Instead of using the existing `HasHTTPManagerM`, this PR revamps it into the `ProvidesNetwork` service.
The idea is, again, that we should make all "external" dependencies of the engine, all things that the core of the engine doesn't care about, a "service". This allows us to define clear APIs for features, to choose different implementations based on which version of the engine we're running, harmonizes our many scattered monadic constraints... Which is why this service is called "Network": we can refine it, moving forward, to be the constraint that defines how all network communication is to operate, instead of relying on disparate classes constraint or hardcoded decisions. A comment in the code clarifies this intent.
### Side-effects? In my Haskell?
This PR also unavoidably touches some other aspects of the codebase. One such example: it introduces `Hasura.App.AppContext`, named after `HasuraPro.Context.AppContext`: a name for the reader structure at the base level. It also transforms `Handler` from a type alias to a newtype, as `Handler` is where we actually enforce HTTP limits; but without `Handler` being a distinct type, any code path could simply do a `runExceptT $ runReader` and forget to enforce them.
(As a rule of thumb, i am starting to consider any straggling `runReaderT` or `runExceptT` as a code smell: we should not stack / unstack monads haphazardly, and every layer should be an opaque `newtype` with a corresponding run function.)
## Further work
In several places, i have left TODOs when i have encountered things that suggest that we should do further unrelated cleanups. I'll write down the follow-up steps, either in the aforementioned document or on slack. But, in short, at a glance, in approximate order, we could:
- delete `ExecutionCtx` as it is only a subset of `ServerCtx`, and remove one more `runReaderT` call
- delete `ServerConfigCtx` as it is only a subset of `ServerCtx`, and remove it from `RunCtx`
- remove `ServerCtx` from `HandlerCtx`, and make it part of `AppContext`, or even make it the `AppContext` altogether (since, at least for the OSS version, `AppContext` is there again only a subset)
- remove `CacheBuildParams` and `CacheBuild` altogether, as they're just a distinct stack that is a `ReaderT` on top of `IO` that contains, you guessed it, the same thing as `ServerCtx`
- move `RunT` out of `RQL.Types` and rename it, since after the previous cleanups **it only contains `UserInfo`**; it could be bundled with the authentication service, made a small implementation detail in `Hasura.Server.Auth`
- rename `PGMetadaStorageT` to something a bit more accurate, such as `App`, and enforce its IO base
This would significantly simply our complex stack. From there, or in parallel, we can start moving existing dependencies as Services. For the purpose of supporting read replicas entitlement, we could move `MonadResolveSource` to a `SourceResolver` service, as attempted in #7653, and transform `UserAuthenticationM` into a `Authentication` service.
PR-URL: https://github.com/hasura/graphql-engine-mono/pull/7736
GitOrigin-RevId: 68cce710eb9e7d752bda1ba0c49541d24df8209f
2023-02-22 18:53:52 +03:00
|
|
|
doQErr $ E.execRemoteGQ env userInfo reqHeaders (rsDef rsi) gqlReq
|
2021-11-30 03:37:14 +03:00
|
|
|
value <- extractFieldFromResponse fieldName resultCustomizer resp
|
Enable remote joins from remote schemas in the execution engine.
### Description
This PR adds the ability to perform remote joins from remote schemas in the engine. To do so, we alter the definition of an `ExecutionStep` targeting a remote schema: the `ExecStepRemote` constructor now expects a `Maybe RemoteJoins`. This new argument is used when processing the execution step, in the transport layer (either `Transport.HTTP` or `Transport.WebSocket`).
For this `Maybe RemoteJoins` to be extracted from a parsed query, this PR also extends the `Execute.RemoteJoin.Collect` module, to implement "collection" from a selection set. Not only do those new functions extract the remote joins, but they also apply all necessary transformations to the selection sets (such as inserting the necessary "phantom" fields used as join keys).
Finally in `Execute.RemoteJoin.Join`, we make two changes. First, we now always look for nested remote joins, regardless of whether the join we just performed went to a source or a remote schema; and second we adapt our join tree logic according to the special cases that were added to deal with remote server edge cases.
Additionally, this PR refactors / cleans / documents `Execute.RemoteJoin.RemoteServer`. This is not required as part of this change and could be moved to a separate PR if needed (a similar cleanup of `Join` is done independently in #3894). It also introduces a draft of a new documentation page for this project, that will be refined in the release PR that ships the feature (either #3069 or a copy of it).
While this PR extends the engine, it doesn't plug such relationships in the schema, meaning that, as of this PR, the new code paths in `Join` are technically unreachable. Adding the corresponding schema code and, ultimately, enabling the metadata API will be done in subsequent PRs.
### Keeping track of concrete type names
The main change this PR makes to the existing `Join` code is to handle a new reserved field we sometimes use when targeting remote servers: the `__hasura_internal_typename` field. In short, a GraphQL selection set can sometimes "branch" based on the concrete "runtime type" of the object on which the selection happens:
```graphql
query {
author(id: 53478) {
... on Writer {
name
articles {
title
}
}
... on Artist {
name
articles {
title
}
}
}
}
```
If both of those `articles` are remote joins, we need to be able, when we get the answer, to differentiate between the two different cases. We do this by asking for `__typename`, to be able to decide if we're in the `Writer` or the `Artist` branch of the query.
To avoid further processing / customization of results, we only insert this `__hasura_internal_typename: __typename` field in the query in the case of unions of interfaces AND if we have the guarantee that we will processing the request as part of the remote joins "folding": that is, if there's any remote join in this branch in the tree. Otherwise, we don't insert the field, and we leave that part of the response untouched.
PR-URL: https://github.com/hasura/graphql-engine-mono/pull/3810
GitOrigin-RevId: 89aaf16274d68e26ad3730b80c2d2fdc2896b96c
2022-03-09 06:17:28 +03:00
|
|
|
finalResponse <-
|
|
|
|
doQErr $
|
|
|
|
RJ.processRemoteJoins
|
|
|
|
reqId
|
|
|
|
logger
|
2023-04-05 11:57:19 +03:00
|
|
|
agentLicenseKey
|
Enable remote joins from remote schemas in the execution engine.
### Description
This PR adds the ability to perform remote joins from remote schemas in the engine. To do so, we alter the definition of an `ExecutionStep` targeting a remote schema: the `ExecStepRemote` constructor now expects a `Maybe RemoteJoins`. This new argument is used when processing the execution step, in the transport layer (either `Transport.HTTP` or `Transport.WebSocket`).
For this `Maybe RemoteJoins` to be extracted from a parsed query, this PR also extends the `Execute.RemoteJoin.Collect` module, to implement "collection" from a selection set. Not only do those new functions extract the remote joins, but they also apply all necessary transformations to the selection sets (such as inserting the necessary "phantom" fields used as join keys).
Finally in `Execute.RemoteJoin.Join`, we make two changes. First, we now always look for nested remote joins, regardless of whether the join we just performed went to a source or a remote schema; and second we adapt our join tree logic according to the special cases that were added to deal with remote server edge cases.
Additionally, this PR refactors / cleans / documents `Execute.RemoteJoin.RemoteServer`. This is not required as part of this change and could be moved to a separate PR if needed (a similar cleanup of `Join` is done independently in #3894). It also introduces a draft of a new documentation page for this project, that will be refined in the release PR that ships the feature (either #3069 or a copy of it).
While this PR extends the engine, it doesn't plug such relationships in the schema, meaning that, as of this PR, the new code paths in `Join` are technically unreachable. Adding the corresponding schema code and, ultimately, enabling the metadata API will be done in subsequent PRs.
### Keeping track of concrete type names
The main change this PR makes to the existing `Join` code is to handle a new reserved field we sometimes use when targeting remote servers: the `__hasura_internal_typename` field. In short, a GraphQL selection set can sometimes "branch" based on the concrete "runtime type" of the object on which the selection happens:
```graphql
query {
author(id: 53478) {
... on Writer {
name
articles {
title
}
}
... on Artist {
name
articles {
title
}
}
}
}
```
If both of those `articles` are remote joins, we need to be able, when we get the answer, to differentiate between the two different cases. We do this by asking for `__typename`, to be able to decide if we're in the `Writer` or the `Artist` branch of the query.
To avoid further processing / customization of results, we only insert this `__hasura_internal_typename: __typename` field in the query in the case of unions of interfaces AND if we have the guarantee that we will processing the request as part of the remote joins "folding": that is, if there's any remote join in this branch in the tree. Otherwise, we don't insert the field, and we leave that part of the response untouched.
PR-URL: https://github.com/hasura/graphql-engine-mono/pull/3810
GitOrigin-RevId: 89aaf16274d68e26ad3730b80c2d2fdc2896b96c
2022-03-09 06:17:28 +03:00
|
|
|
env
|
|
|
|
reqHeaders
|
|
|
|
userInfo
|
|
|
|
-- TODO: avoid encode and decode here
|
|
|
|
(encJFromOrderedValue value)
|
|
|
|
remoteJoins
|
|
|
|
reqUnparsed
|
2020-10-07 13:23:17 +03:00
|
|
|
let filteredHeaders = filter ((== "Set-Cookie") . fst) remoteResponseHeaders
|
Enable remote joins from remote schemas in the execution engine.
### Description
This PR adds the ability to perform remote joins from remote schemas in the engine. To do so, we alter the definition of an `ExecutionStep` targeting a remote schema: the `ExecStepRemote` constructor now expects a `Maybe RemoteJoins`. This new argument is used when processing the execution step, in the transport layer (either `Transport.HTTP` or `Transport.WebSocket`).
For this `Maybe RemoteJoins` to be extracted from a parsed query, this PR also extends the `Execute.RemoteJoin.Collect` module, to implement "collection" from a selection set. Not only do those new functions extract the remote joins, but they also apply all necessary transformations to the selection sets (such as inserting the necessary "phantom" fields used as join keys).
Finally in `Execute.RemoteJoin.Join`, we make two changes. First, we now always look for nested remote joins, regardless of whether the join we just performed went to a source or a remote schema; and second we adapt our join tree logic according to the special cases that were added to deal with remote server edge cases.
Additionally, this PR refactors / cleans / documents `Execute.RemoteJoin.RemoteServer`. This is not required as part of this change and could be moved to a separate PR if needed (a similar cleanup of `Join` is done independently in #3894). It also introduces a draft of a new documentation page for this project, that will be refined in the release PR that ships the feature (either #3069 or a copy of it).
While this PR extends the engine, it doesn't plug such relationships in the schema, meaning that, as of this PR, the new code paths in `Join` are technically unreachable. Adding the corresponding schema code and, ultimately, enabling the metadata API will be done in subsequent PRs.
### Keeping track of concrete type names
The main change this PR makes to the existing `Join` code is to handle a new reserved field we sometimes use when targeting remote servers: the `__hasura_internal_typename` field. In short, a GraphQL selection set can sometimes "branch" based on the concrete "runtime type" of the object on which the selection happens:
```graphql
query {
author(id: 53478) {
... on Writer {
name
articles {
title
}
}
... on Artist {
name
articles {
title
}
}
}
}
```
If both of those `articles` are remote joins, we need to be able, when we get the answer, to differentiate between the two different cases. We do this by asking for `__typename`, to be able to decide if we're in the `Writer` or the `Artist` branch of the query.
To avoid further processing / customization of results, we only insert this `__hasura_internal_typename: __typename` field in the query in the case of unions of interfaces AND if we have the guarantee that we will processing the request as part of the remote joins "folding": that is, if there's any remote join in this branch in the tree. Otherwise, we don't insert the field, and we leave that part of the response untouched.
PR-URL: https://github.com/hasura/graphql-engine-mono/pull/3810
GitOrigin-RevId: 89aaf16274d68e26ad3730b80c2d2fdc2896b96c
2022-03-09 06:17:28 +03:00
|
|
|
pure $ AnnotatedResponsePart telemTimeIO_DT Telem.Remote finalResponse filteredHeaders
|
2021-10-26 14:44:18 +03:00
|
|
|
|
|
|
|
cacheAccess ::
|
|
|
|
GQLReqParsed ->
|
|
|
|
EB.ExecutionPlan ->
|
|
|
|
[QueryRootField UnpreparedValue] ->
|
|
|
|
DirectiveMap ->
|
|
|
|
( m (HTTP.ResponseHeaders, Maybe EncJSON),
|
|
|
|
EncJSON -> m CacheStoreResponse
|
|
|
|
)
|
|
|
|
cacheAccess reqParsed queryPlans asts dirMap =
|
|
|
|
let filteredSessionVars = runSessVarPred (filterVariablesFromQuery asts) (_uiSession userInfo)
|
|
|
|
remoteSchemas =
|
2023-04-27 10:41:55 +03:00
|
|
|
InsOrdHashMap.elems queryPlans >>= \case
|
2021-10-26 14:44:18 +03:00
|
|
|
E.ExecStepDB _headers _dbAST remoteJoins -> do
|
|
|
|
maybe [] (map RJ._rsjRemoteSchema . RJ.getRemoteSchemaJoins) remoteJoins
|
2023-04-19 14:12:07 +03:00
|
|
|
E.ExecStepRemote remoteSchemaInfo _ _ _ -> [remoteSchemaInfo]
|
2021-10-26 14:44:18 +03:00
|
|
|
_ -> []
|
|
|
|
getExecStepActionWithActionInfo acc execStep = case execStep of
|
|
|
|
EB.ExecStepAction _ actionInfo _remoteJoins -> (actionInfo : acc)
|
|
|
|
_ -> acc
|
|
|
|
actionsInfo =
|
|
|
|
foldl getExecStepActionWithActionInfo [] $
|
2023-04-27 10:41:55 +03:00
|
|
|
InsOrdHashMap.elems $
|
|
|
|
InsOrdHashMap.filter
|
2021-10-26 14:44:18 +03:00
|
|
|
( \case
|
|
|
|
E.ExecStepAction _ _ _remoteJoins -> True
|
|
|
|
_ -> False
|
|
|
|
)
|
|
|
|
queryPlans
|
|
|
|
cacheKey = QueryCacheKey reqParsed (_uiRole userInfo) filteredSessionVars
|
|
|
|
cachedDirective = runIdentity <$> DM.lookup cached dirMap
|
Rewrite `Tracing` to allow for only one `TraceT` in the entire stack.
This PR is on top of #7789.
### Description
This PR entirely rewrites the API of the Tracing library, to make `interpTraceT` a thing of the past. Before this change, we ran traces by sticking a `TraceT` on top of whatever we were doing. This had several major drawbacks:
- we were carrying a bunch of `TraceT` across the codebase, and the entire codebase had to know about it
- we needed to carry a second class constraint around (`HasReporterM`) to be able to run all of those traces
- we kept having to do stack rewriting with `interpTraceT`, which went from inconvenient to horrible
- we had to declare several behavioral instances on `TraceT m`
This PR rewrite all of `Tracing` using a more conventional model: there is ONE `TraceT` at the bottom of the stack, and there is an associated class constraint `MonadTrace`: any part of the code that happens to satisfy `MonadTrace` is able to create new traces. We NEVER have to do stack rewriting, `interpTraceT` is gone, and `TraceT` and `Reporter` become implementation details that 99% of the code is blissfully unaware of: code that needs to do tracing only needs to declare that the monad in which it operates implements `MonadTrace`.
In doing so, this PR revealed **several bugs in the codebase**: places where we were expecting to trace something, but due to the default instance of `HasReporterM IO` we would actually not do anything. This PR also splits the code of `Tracing` in more byte-sized modules, with the goal of potentially moving to `server/lib` down the line.
### Remaining work
This PR is a draft; what's left to do is:
- [x] make Pro compile; i haven't updated `HasuraPro/Main` yet
- [x] document Tracing by writing a note that explains how to use the library, and the meaning of "reporter", "trace" and "span", as well as the pitfalls
- [x] discuss some of the trade-offs in the implementation, which is why i'm opening this PR already despite it not fully building yet
- [x] it depends on #7789 being merged first
PR-URL: https://github.com/hasura/graphql-engine-mono/pull/7791
GitOrigin-RevId: cadd32d039134c93ddbf364599a2f4dd988adea8
2023-03-13 20:37:16 +03:00
|
|
|
in ( liftEitherM $ cacheLookup remoteSchemas actionsInfo cacheKey cachedDirective,
|
|
|
|
liftEitherM . cacheStore cacheKey cachedDirective
|
2021-09-24 01:56:37 +03:00
|
|
|
)
|
|
|
|
|
2021-10-26 14:44:18 +03:00
|
|
|
recordTimings :: DiffTime -> AnnotatedResponse -> m ()
|
|
|
|
recordTimings totalTime result = do
|
|
|
|
Telem.recordTimingMetric
|
|
|
|
Telem.RequestDimensions
|
|
|
|
{ telemTransport = Telem.HTTP,
|
|
|
|
telemQueryType = arQueryType result,
|
|
|
|
telemLocality = arLocality result
|
|
|
|
}
|
|
|
|
Telem.RequestTimings
|
|
|
|
{ telemTimeIO = convertDuration $ arTimeIO result,
|
|
|
|
telemTimeTot = convertDuration totalTime
|
|
|
|
}
|
|
|
|
|
2022-07-24 00:18:01 +03:00
|
|
|
-- Catch, record, and re-throw errors.
|
|
|
|
observeGQLQueryError ::
|
|
|
|
forall n e a.
|
|
|
|
( MonadIO n,
|
|
|
|
MonadError e n
|
|
|
|
) =>
|
|
|
|
GraphQLRequestMetrics ->
|
|
|
|
Maybe G.OperationType ->
|
|
|
|
n a ->
|
|
|
|
n a
|
|
|
|
observeGQLQueryError gqlMetrics mOpType action =
|
|
|
|
catchError (fmap Right action) (pure . Left) >>= \case
|
|
|
|
Right result ->
|
|
|
|
pure result
|
|
|
|
Left err -> do
|
|
|
|
case mOpType of
|
|
|
|
Nothing ->
|
|
|
|
liftIO $ Prometheus.Counter.inc (gqlRequestsUnknownFailure gqlMetrics)
|
|
|
|
Just opType -> case opType of
|
|
|
|
G.OperationTypeQuery ->
|
|
|
|
liftIO $ Prometheus.Counter.inc (gqlRequestsQueryFailure gqlMetrics)
|
|
|
|
G.OperationTypeMutation ->
|
|
|
|
liftIO $ Prometheus.Counter.inc (gqlRequestsMutationFailure gqlMetrics)
|
|
|
|
G.OperationTypeSubscription ->
|
|
|
|
-- We do not collect metrics for subscriptions at the request level.
|
|
|
|
pure ()
|
|
|
|
throwError err
|
|
|
|
|
|
|
|
-- Tally and record execution times for successful GraphQL requests.
|
|
|
|
recordGQLQuerySuccess ::
|
|
|
|
GraphQLRequestMetrics -> DiffTime -> G.OperationType -> IO ()
|
|
|
|
recordGQLQuerySuccess gqlMetrics totalTime = \case
|
|
|
|
G.OperationTypeQuery -> liftIO $ do
|
|
|
|
Prometheus.Counter.inc (gqlRequestsQuerySuccess gqlMetrics)
|
|
|
|
Prometheus.Histogram.observe (gqlExecutionTimeSecondsQuery gqlMetrics) (realToFrac totalTime)
|
|
|
|
G.OperationTypeMutation -> liftIO $ do
|
|
|
|
Prometheus.Counter.inc (gqlRequestsMutationSuccess gqlMetrics)
|
|
|
|
Prometheus.Histogram.observe (gqlExecutionTimeSecondsMutation gqlMetrics) (realToFrac totalTime)
|
|
|
|
G.OperationTypeSubscription ->
|
|
|
|
-- We do not collect metrics for subscriptions at the request level.
|
|
|
|
-- Furthermore, we do not serve GraphQL subscriptions over HTTP.
|
|
|
|
pure ()
|
|
|
|
|
2021-09-24 01:56:37 +03:00
|
|
|
coalescePostgresMutations ::
|
|
|
|
EB.ExecutionPlan ->
|
|
|
|
Maybe
|
|
|
|
( SourceConfig ('Postgres 'Vanilla),
|
2023-01-25 10:12:53 +03:00
|
|
|
ResolvedConnectionTemplate ('Postgres 'Vanilla),
|
2021-10-29 17:42:07 +03:00
|
|
|
InsOrdHashMap RootFieldAlias (EB.DBStepInfo ('Postgres 'Vanilla))
|
2021-09-24 01:56:37 +03:00
|
|
|
)
|
2021-04-01 23:40:31 +03:00
|
|
|
coalescePostgresMutations plan = do
|
|
|
|
-- we extract the name and config of the first mutation root, if any
|
2023-01-25 10:12:53 +03:00
|
|
|
(oneSourceName, oneResolvedConnectionTemplate, oneSourceConfig) <- case toList plan of
|
2021-09-24 01:56:37 +03:00
|
|
|
(E.ExecStepDB _ exists _remoteJoins : _) ->
|
|
|
|
AB.unpackAnyBackend @('Postgres 'Vanilla) exists <&> \dbsi ->
|
|
|
|
( EB.dbsiSourceName dbsi,
|
2023-01-25 10:12:53 +03:00
|
|
|
EB.dbsiResolvedConnectionTemplate dbsi,
|
2021-09-24 01:56:37 +03:00
|
|
|
EB.dbsiSourceConfig dbsi
|
|
|
|
)
|
|
|
|
_ -> Nothing
|
2021-04-01 23:40:31 +03:00
|
|
|
-- we then test whether all mutations are going to that same first source
|
|
|
|
-- and that it is Postgres
|
|
|
|
mutations <- for plan \case
|
2021-06-11 06:26:50 +03:00
|
|
|
E.ExecStepDB _ exists remoteJoins -> do
|
2021-04-22 00:44:37 +03:00
|
|
|
dbStepInfo <- AB.unpackAnyBackend @('Postgres 'Vanilla) exists
|
2023-01-25 10:12:53 +03:00
|
|
|
guard $
|
|
|
|
oneSourceName == EB.dbsiSourceName dbStepInfo
|
|
|
|
&& isNothing remoteJoins
|
|
|
|
&& oneResolvedConnectionTemplate == EB.dbsiResolvedConnectionTemplate dbStepInfo
|
2021-04-01 23:40:31 +03:00
|
|
|
Just dbStepInfo
|
|
|
|
_ -> Nothing
|
2023-01-25 10:12:53 +03:00
|
|
|
Just (oneSourceConfig, oneResolvedConnectionTemplate, mutations)
|
2020-10-07 13:23:17 +03:00
|
|
|
|
2021-11-10 05:33:58 +03:00
|
|
|
data GraphQLResponse
|
|
|
|
= GraphQLResponseErrors [J.Value]
|
|
|
|
| GraphQLResponseData JO.Value
|
|
|
|
|
|
|
|
decodeGraphQLResponse :: LBS.ByteString -> Either Text GraphQLResponse
|
|
|
|
decodeGraphQLResponse bs = do
|
|
|
|
val <- mapLeft T.pack $ JO.eitherDecode bs
|
|
|
|
valObj <- JO.asObject val
|
|
|
|
case JO.lookup "errors" valObj of
|
|
|
|
Just (JO.Array errs) -> Right $ GraphQLResponseErrors (toList $ JO.fromOrdered <$> errs)
|
|
|
|
Just _ -> Left "Invalid \"errors\" field in response from remote"
|
|
|
|
Nothing -> do
|
|
|
|
dataVal <- JO.lookup "data" valObj `onNothing` Left "Missing \"data\" field in response from remote"
|
|
|
|
Right $ GraphQLResponseData dataVal
|
|
|
|
|
2021-09-24 01:56:37 +03:00
|
|
|
extractFieldFromResponse ::
|
|
|
|
forall m.
|
|
|
|
Monad m =>
|
2021-10-29 17:42:07 +03:00
|
|
|
RootFieldAlias ->
|
|
|
|
ResultCustomizer ->
|
2021-09-24 01:56:37 +03:00
|
|
|
LBS.ByteString ->
|
|
|
|
ExceptT (Either GQExecError QErr) m JO.Value
|
2021-11-30 03:37:14 +03:00
|
|
|
extractFieldFromResponse fieldName resultCustomizer resp = do
|
|
|
|
let fieldName' = G.unName $ _rfaAlias fieldName
|
2021-09-24 01:56:37 +03:00
|
|
|
dataVal <-
|
2021-11-10 05:33:58 +03:00
|
|
|
applyResultCustomizer resultCustomizer
|
|
|
|
<$> do
|
|
|
|
graphQLResponse <- decodeGraphQLResponse resp `onLeft` do400
|
|
|
|
case graphQLResponse of
|
|
|
|
GraphQLResponseErrors errs -> doGQExecError errs
|
|
|
|
GraphQLResponseData d -> pure d
|
2021-11-30 03:37:14 +03:00
|
|
|
dataObj <- onLeft (JO.asObject dataVal) do400
|
|
|
|
fieldVal <-
|
|
|
|
onNothing (JO.lookup fieldName' dataObj) $
|
2022-11-02 23:53:23 +03:00
|
|
|
do400 $
|
|
|
|
"expecting key " <> fieldName'
|
2021-11-30 03:37:14 +03:00
|
|
|
return fieldVal
|
2020-10-07 13:23:17 +03:00
|
|
|
where
|
|
|
|
do400 = withExceptT Right . throw400 RemoteSchemaError
|
|
|
|
doGQExecError = withExceptT Left . throwError . GQExecError
|
|
|
|
|
2021-10-26 14:44:18 +03:00
|
|
|
buildRaw :: Applicative m => JO.Value -> m AnnotatedResponsePart
|
2020-10-07 13:23:17 +03:00
|
|
|
buildRaw json = do
|
2021-08-06 16:39:00 +03:00
|
|
|
let obj = encJFromOrderedValue json
|
2020-10-07 13:23:17 +03:00
|
|
|
telemTimeIO_DT = 0
|
2021-10-26 14:44:18 +03:00
|
|
|
pure $ AnnotatedResponsePart telemTimeIO_DT Telem.Local obj []
|
2018-11-23 16:02:46 +03:00
|
|
|
|
2021-10-29 17:42:07 +03:00
|
|
|
encodeAnnotatedResponseParts :: RootFieldMap AnnotatedResponsePart -> EncJSON
|
|
|
|
encodeAnnotatedResponseParts = encodeEncJSONResults . fmap arpResponse
|
|
|
|
|
|
|
|
encodeEncJSONResults :: RootFieldMap EncJSON -> EncJSON
|
|
|
|
encodeEncJSONResults =
|
|
|
|
encNameMap . fmap (namespacedField id encNameMap) . unflattenNamespaces
|
|
|
|
where
|
2023-04-27 10:41:55 +03:00
|
|
|
encNameMap = encJFromInsOrdHashMap . InsOrdHashMap.mapKeys G.unName
|
2021-10-29 17:42:07 +03:00
|
|
|
|
2021-06-17 09:27:58 +03:00
|
|
|
-- | Run (execute) a batched GraphQL query (see 'GQLBatchedReqs').
|
2021-09-24 01:56:37 +03:00
|
|
|
runGQBatched ::
|
|
|
|
forall m.
|
2021-10-13 19:38:56 +03:00
|
|
|
( MonadIO m,
|
2021-09-24 01:56:37 +03:00
|
|
|
MonadBaseControl IO m,
|
|
|
|
MonadError QErr m,
|
|
|
|
E.MonadGQLExecutionCheck m,
|
|
|
|
MonadQueryLog m,
|
2023-03-15 16:05:17 +03:00
|
|
|
MonadExecutionLog m,
|
2021-09-24 01:56:37 +03:00
|
|
|
MonadTrace m,
|
|
|
|
MonadExecuteQuery m,
|
2023-02-03 04:03:23 +03:00
|
|
|
MonadMetadataStorage m,
|
2023-03-31 00:18:11 +03:00
|
|
|
MonadQueryTags m,
|
harmonize network manager handling
## Description
### I want to speak to the `Manager`
Oh boy. This PR is both fairly straightforward and overreaching, so let's break it down.
For most network access, we need a [`HTTP.Manager`](https://hackage.haskell.org/package/http-client-0.1.0.0/docs/Network-HTTP-Client-Manager.html). It is created only once, at the top level, when starting the engine, and is then threaded through the application to wherever we need to make a network call. As of main, the way we do this is not standardized: most of the GraphQL execution code passes it "manually" as a function argument throughout the code. We also have a custom monad constraint, `HasHttpManagerM`, that describes a monad's ability to provide a manager. And, finally, several parts of the code store the manager in some kind of argument structure, such as `RunT`'s `RunCtx`.
This PR's first goal is to harmonize all of this: we always create the manager at the root, and we already have it when we do our very first `runReaderT`. Wouldn't it make sense for the rest of the code to not manually pass it anywhere, to not store it anywhere, but to always rely on the current monad providing it? This is, in short, what this PR does: it implements a constraint on the base monads, so that they provide the manager, and removes most explicit passing from the code.
### First come, first served
One way this PR goes a tiny bit further than "just" doing the aforementioned harmonization is that it starts the process of implementing the "Services oriented architecture" roughly outlined in this [draft document](https://docs.google.com/document/d/1FAigqrST0juU1WcT4HIxJxe1iEBwTuBZodTaeUvsKqQ/edit?usp=sharing). Instead of using the existing `HasHTTPManagerM`, this PR revamps it into the `ProvidesNetwork` service.
The idea is, again, that we should make all "external" dependencies of the engine, all things that the core of the engine doesn't care about, a "service". This allows us to define clear APIs for features, to choose different implementations based on which version of the engine we're running, harmonizes our many scattered monadic constraints... Which is why this service is called "Network": we can refine it, moving forward, to be the constraint that defines how all network communication is to operate, instead of relying on disparate classes constraint or hardcoded decisions. A comment in the code clarifies this intent.
### Side-effects? In my Haskell?
This PR also unavoidably touches some other aspects of the codebase. One such example: it introduces `Hasura.App.AppContext`, named after `HasuraPro.Context.AppContext`: a name for the reader structure at the base level. It also transforms `Handler` from a type alias to a newtype, as `Handler` is where we actually enforce HTTP limits; but without `Handler` being a distinct type, any code path could simply do a `runExceptT $ runReader` and forget to enforce them.
(As a rule of thumb, i am starting to consider any straggling `runReaderT` or `runExceptT` as a code smell: we should not stack / unstack monads haphazardly, and every layer should be an opaque `newtype` with a corresponding run function.)
## Further work
In several places, i have left TODOs when i have encountered things that suggest that we should do further unrelated cleanups. I'll write down the follow-up steps, either in the aforementioned document or on slack. But, in short, at a glance, in approximate order, we could:
- delete `ExecutionCtx` as it is only a subset of `ServerCtx`, and remove one more `runReaderT` call
- delete `ServerConfigCtx` as it is only a subset of `ServerCtx`, and remove it from `RunCtx`
- remove `ServerCtx` from `HandlerCtx`, and make it part of `AppContext`, or even make it the `AppContext` altogether (since, at least for the OSS version, `AppContext` is there again only a subset)
- remove `CacheBuildParams` and `CacheBuild` altogether, as they're just a distinct stack that is a `ReaderT` on top of `IO` that contains, you guessed it, the same thing as `ServerCtx`
- move `RunT` out of `RQL.Types` and rename it, since after the previous cleanups **it only contains `UserInfo`**; it could be bundled with the authentication service, made a small implementation detail in `Hasura.Server.Auth`
- rename `PGMetadaStorageT` to something a bit more accurate, such as `App`, and enforce its IO base
This would significantly simply our complex stack. From there, or in parallel, we can start moving existing dependencies as Services. For the purpose of supporting read replicas entitlement, we could move `MonadResolveSource` to a `SourceResolver` service, as attempted in #7653, and transform `UserAuthenticationM` into a `Authentication` service.
PR-URL: https://github.com/hasura/graphql-engine-mono/pull/7736
GitOrigin-RevId: 68cce710eb9e7d752bda1ba0c49541d24df8209f
2023-02-22 18:53:52 +03:00
|
|
|
HasResourceLimits m,
|
|
|
|
ProvidesNetwork m
|
2021-09-24 01:56:37 +03:00
|
|
|
) =>
|
|
|
|
Env.Environment ->
|
2023-03-21 15:35:46 +03:00
|
|
|
SQLGenCtx ->
|
|
|
|
SchemaCache ->
|
|
|
|
SchemaCacheVer ->
|
|
|
|
Init.AllowListStatus ->
|
|
|
|
ReadOnlyMode ->
|
|
|
|
PrometheusMetrics ->
|
2021-09-24 01:56:37 +03:00
|
|
|
L.Logger L.Hasura ->
|
2023-04-05 11:57:19 +03:00
|
|
|
Maybe (CredentialCache AgentLicenseKey) ->
|
2021-09-24 01:56:37 +03:00
|
|
|
RequestId ->
|
|
|
|
ResponseInternalErrorsConfig ->
|
|
|
|
UserInfo ->
|
|
|
|
Wai.IpAddress ->
|
|
|
|
[HTTP.Header] ->
|
|
|
|
E.GraphQLQueryType ->
|
|
|
|
-- | the batched request with unparsed GraphQL query
|
|
|
|
GQLBatchedReqs (GQLReq GQLQueryText) ->
|
2022-12-15 10:48:18 +03:00
|
|
|
m (HttpLogGraphQLInfo, HttpResponse EncJSON)
|
2023-04-05 11:57:19 +03:00
|
|
|
runGQBatched env sqlGenCtx sc scVer enableAL readOnlyMode prometheusMetrics logger agentLicenseKey reqId responseErrorsConfig userInfo ipAddress reqHdrs queryType query =
|
2020-06-16 18:23:06 +03:00
|
|
|
case query of
|
2021-04-06 20:52:55 +03:00
|
|
|
GQLSingleRequest req -> do
|
2023-04-05 11:57:19 +03:00
|
|
|
(gqlQueryOperationLog, httpResp) <- runGQ env sqlGenCtx sc scVer enableAL readOnlyMode prometheusMetrics logger agentLicenseKey reqId userInfo ipAddress reqHdrs queryType req
|
2022-12-15 10:48:18 +03:00
|
|
|
let httpLoggingGQInfo = (CommonHttpLogMetadata L.RequestModeSingle (Just (GQLSingleRequest (GQLQueryOperationSuccess gqlQueryOperationLog))), (PQHSetSingleton (gqolParameterizedQueryHash gqlQueryOperationLog)))
|
|
|
|
pure (httpLoggingGQInfo, snd <$> httpResp)
|
2020-06-16 18:23:06 +03:00
|
|
|
GQLBatchedReqs reqs -> do
|
2019-12-20 19:04:02 +03:00
|
|
|
-- It's unclear what we should do if we receive multiple
|
|
|
|
-- responses with distinct headers, so just do the simplest thing
|
|
|
|
-- in this case, and don't forward any.
|
2023-03-21 15:35:46 +03:00
|
|
|
E.checkGQLBatchedReqs userInfo reqId reqs sc >>= flip onLeft throwError
|
2020-04-24 12:10:53 +03:00
|
|
|
let includeInternal = shouldIncludeInternal (_uiRole userInfo) responseErrorsConfig
|
2020-04-24 10:55:51 +03:00
|
|
|
removeHeaders =
|
2020-03-20 09:46:45 +03:00
|
|
|
flip HttpResponse []
|
2021-09-24 01:56:37 +03:00
|
|
|
. encJFromList
|
|
|
|
. map (either (encJFromJValue . encodeGQErr includeInternal) _hrBody)
|
2023-04-05 11:57:19 +03:00
|
|
|
responses <- for reqs \req -> fmap (req,) $ try $ (fmap . fmap . fmap) snd $ runGQ env sqlGenCtx sc scVer enableAL readOnlyMode prometheusMetrics logger agentLicenseKey reqId userInfo ipAddress reqHdrs queryType req
|
2021-09-15 11:29:34 +03:00
|
|
|
let requestsOperationLogs = map fst $ rights $ map snd responses
|
2021-09-24 01:56:37 +03:00
|
|
|
batchOperationLogs =
|
|
|
|
map
|
|
|
|
( \(req, resp) ->
|
|
|
|
case resp of
|
|
|
|
Left err -> GQLQueryOperationError $ GQLQueryOperationErrorLog req err
|
|
|
|
Right (successOpLog, _) -> GQLQueryOperationSuccess successOpLog
|
|
|
|
)
|
|
|
|
responses
|
2021-09-15 11:29:34 +03:00
|
|
|
parameterizedQueryHashes = map gqolParameterizedQueryHash requestsOperationLogs
|
2022-12-15 10:48:18 +03:00
|
|
|
httpLoggingGQInfo = (CommonHttpLogMetadata L.RequestModeBatched ((Just (GQLBatchedReqs batchOperationLogs))), PQHSetBatched parameterizedQueryHashes)
|
|
|
|
pure (httpLoggingGQInfo, removeHeaders (map ((fmap snd) . snd) responses))
|
2020-06-16 18:23:06 +03:00
|
|
|
where
|
|
|
|
try = flip catchError (pure . Left) . fmap Right
|