Files
UnrealEngineUWP/Engine/Source/Developer/Virtualization/Private/VirtualizationDDCBackend.cpp

177 lines
5.1 KiB
C++
Raw Normal View History

// Copyright Epic Games, Inc. All Rights Reserved.
#include "VirtualizationDDCBackend.h"
#include "Misc/Parse.h"
#include "DerivedDataCache.h"
#include "DerivedDataCacheRecord.h"
#include "DerivedDataRequestOwner.h"
#include "DerivedDataValue.h"
namespace UE::Virtualization
{
/** Utility function to help convert from UE::Virtualization::FIoHash to UE::DerivedData::FValueId */
static UE::DerivedData::FValueId ToDerivedDataValueId(const FIoHash& Id)
{
return UE::DerivedData::FValueId::FromHash(Id);
}
FDDCBackend::FDDCBackend(FStringView ProjectName, FStringView ConfigName, FStringView InDebugName)
: IVirtualizationBackend(ConfigName, InDebugName, EOperations::Push | EOperations::Pull)
, BucketName(TEXT("BulkData"))
, TransferPolicy(UE::DerivedData::ECachePolicy::None)
, QueryPolicy(UE::DerivedData::ECachePolicy::None)
{
}
bool FDDCBackend::Initialize(const FString& ConfigEntry)
{
TRACE_CPUPROFILER_EVENT_SCOPE(Initialize::Initialize);
if (!FParse::Value(*ConfigEntry, TEXT("Bucket="), BucketName))
{
UE_LOG(LogVirtualization, Fatal, TEXT("[%s] 'Bucket=' not found in the config file"), *GetDebugName());
}
bool bAllowLocal = true;
if (FParse::Bool(*ConfigEntry, TEXT("LocalStorage="), bAllowLocal))
{
UE_LOG(LogVirtualization, Display, TEXT("[%s] Use of local storage set to '%s"), *GetDebugName(), bAllowLocal ? TEXT("true") : TEXT("false"));
}
bool bAllowRemote = true;
if (FParse::Bool(*ConfigEntry, TEXT("RemoteStorage="), bAllowRemote))
{
UE_LOG(LogVirtualization, Display, TEXT("[%s] Use of remote storage set to '%s"), *GetDebugName(), bAllowRemote ? TEXT("true") : TEXT("false"));
}
if (!bAllowLocal && !bAllowRemote)
{
UE_LOG(LogVirtualization, Fatal, TEXT("[%s] LocalStorage and RemoteStorage cannot both be disabled"), *GetDebugName());
return false;
}
if (bAllowLocal)
{
TransferPolicy |= UE::DerivedData::ECachePolicy::Local;
QueryPolicy |= UE::DerivedData::ECachePolicy::QueryLocal;
}
if (bAllowRemote)
{
TransferPolicy |= UE::DerivedData::ECachePolicy::Remote;
QueryPolicy |= UE::DerivedData::ECachePolicy::QueryRemote;
}
Bucket = UE::DerivedData::FCacheBucket(BucketName);
return true;
}
EPushResult FDDCBackend::PushData(const FIoHash& Id, const FCompressedBuffer& Payload, const FString& PackageContext)
{
TRACE_CPUPROFILER_EVENT_SCOPE(FDDCBackend::PushData);
Submitting packages on projects with virtualization enabled is much faster when none of the payloads actually needs to be virtualized. #rb PJ.Kack #rnx #preflight 61a795773c29b3cf13cd8250 ### PackageSubmissionChecks - Under the old model submitting a large number of packages could be very slow as each package would check each payload that it owns and is currently stored locally one at a time. For the source control backend this created quite a large overhead even when all of the payloads were already virtualized. - Now we do a pass over the submitted files to find all valid packages that have package trailers with locally stored payloads, gather the payloads into a single list and then query that in one large batch. - Once we find which payloads are not in permanent storage (note that in the case where a project is using multiple permanent storage solutions, if a payload is missing in one backend it counts as not being in permanent storage) we then attempt to virtualized them. - Only after all of this is done will we create the truncated copy of each package and then append the updated trailer to each one. In theory doing it in this order this might slightly increase the change of submit failures that occur after virtualization that result in a package never being submitted and orphaned payloads being added to permanent storage, but this will always be a risk. - Added an assert to fire if we detect a trailer with some virtualized and some local payloads. This should be a supported feature but needs proper testing first before we can allow it. With out current project settings no project should actually encounter this scenario. - To make the code easier to follow we now early out of the entire check when errors are encountered. - Added logging at various stages in the process to help show the user that something is happening and make problems easier to identify in the future. - Notes -- There is a lot of handling of invalid FPayloads. This is because it is currently possible to add empty payloads to the trailer which is inefficient and wastes space. The trailer will be modified to reject empty payloads in a future update at which point a lot of this handling can be removed. -- This could've also been solved by not fully rehydrating a package on save by the end user, which will be added as a project setting in a future piece of work, but this approach will solve the edge case when the user does have a large amount of hydrated packages which contain payloads that are already virtualized so it was better to fix that now while we have good test cases for it. -- We still have scaling problems with large number of package being submitted that do have payloads that need to be virtualized, this will be fixed by extending IVirtualizationSystem::Push to also accept batches of payloads in future work. -- OnPrePackageSubmission could be broken up into smaller chunks to make the code easier to follow. This will be done after the batch payload submission work is done. ### VirtualizationSystem - EStorageType has been promoted to enum class. - Added a new enum FPayloadStatus to be used when querying if a payload exists in a backend storage system or not. - Add a new method ::DoPayloadsExist which allows the caller to query if one or more payloads exists in the given backend storage system. ### VirtualizationManager - Implemented ::DoPayloadsExist. First we get the results from each backend in the storage system (which return as true or false from each backend) then total how many backends found the payload in order to set the correct status. ### IVirtualizationBackend - ::DoesPayloadExist which queries the existence of a single payload has been added to the interface. Most backends already implemented this for private use and if so have had their implementation renamed to match this. - Also added ::DoPayloadsExist which takes a batch of FpayloadIdsto query. Some backends can deal with a batch of payload ids much more efficiently than one at a time, although the default implementation does call ::DoesPayloadExist for each requested payload. -- The default implementation prevents every backend from needing to implement the same for loop but does allow backends that can gain from batching to override it. ### VirtualizationSourceControlBackend - This backend does override ::DoPayloadsExist and implements it's own version as it tends to perform very poorly when not operating on larger batches. - In this case ::DoesPayloadExist calls back to ::DoPayloadsExist to check each payload rather than implement as specific version. ### PackageTrailer - The trailer can now be queries to request how many payloads of a given type it contains #ROBOMERGE-AUTHOR: paul.chipchase #ROBOMERGE-SOURCE: CL 18339847 in //UE5/Release-5.0/... via CL 18339852 #ROBOMERGE-BOT: STARSHIP (Release-Engine-Staging -> Release-Engine-Test) (v895-18170469) [CL 18339859 by paul chipchase in ue5-release-engine-test branch]
2021-12-01 11:13:31 -05:00
if (DoesPayloadExist(Id))
{
UE_LOG(LogVirtualization, Verbose, TEXT("[%s] Already has a copy of the payload '%s'."), *GetDebugName(), *LexToString(Id));
return EPushResult::PayloadAlreadyExisted;
}
UE::DerivedData::ICache& Cache = UE::DerivedData::GetCache();
UE::DerivedData::FCacheKey Key;
Key.Bucket = Bucket;
Key.Hash = Id;
UE::DerivedData::FValue DerivedDataValue(Payload);
check(DerivedDataValue.GetRawHash() == Id);
UE::DerivedData::FCacheRecordBuilder RecordBuilder(Key);
RecordBuilder.AddValue(ToDerivedDataValueId(Id), DerivedDataValue);
UE::DerivedData::FRequestOwner Owner(UE::DerivedData::EPriority::Blocking);
UE::DerivedData::FCachePutResponse Result;
auto Callback = [&Result](UE::DerivedData::FCachePutResponse&& Response)
{
Result = Response;
};
// TODO: Improve the name when we start passing more context to this function
Cache.Put({{{TEXT("Mirage")}, RecordBuilder.Build(), TransferPolicy}}, Owner, MoveTemp(Callback));
Owner.Wait();
if (Result.Status == UE::DerivedData::EStatus::Ok)
{
return EPushResult::Success;
}
else
{
return EPushResult::Failed;
}
}
FCompressedBuffer FDDCBackend::PullData(const FIoHash& Id)
{
TRACE_CPUPROFILER_EVENT_SCOPE(FDDCBackend::PullData);
UE::DerivedData::ICache& Cache = UE::DerivedData::GetCache();
UE::DerivedData::FCacheKey Key;
Key.Bucket = Bucket;
Key.Hash = Id;
UE::DerivedData::FRequestOwner Owner(UE::DerivedData::EPriority::Blocking);
FCompressedBuffer ResultData;
UE::DerivedData::EStatus ResultStatus;
auto Callback = [&Id, &ResultData, &ResultStatus](UE::DerivedData::FCacheGetResponse&& Response)
{
ResultStatus = Response.Status;
if (ResultStatus == UE::DerivedData::EStatus::Ok)
{
ResultData = Response.Record.GetValue(ToDerivedDataValueId(Id)).GetData();
}
};
// TODO: Improve the name when we start passing more context to this function
Cache.Get({{{TEXT("Mirage")}, Key, TransferPolicy}}, Owner, MoveTemp(Callback));
Owner.Wait();
return ResultData;
}
bool FDDCBackend::DoesPayloadExist(const FIoHash& Id)
{
Submitting packages on projects with virtualization enabled is much faster when none of the payloads actually needs to be virtualized. #rb PJ.Kack #rnx #preflight 61a795773c29b3cf13cd8250 ### PackageSubmissionChecks - Under the old model submitting a large number of packages could be very slow as each package would check each payload that it owns and is currently stored locally one at a time. For the source control backend this created quite a large overhead even when all of the payloads were already virtualized. - Now we do a pass over the submitted files to find all valid packages that have package trailers with locally stored payloads, gather the payloads into a single list and then query that in one large batch. - Once we find which payloads are not in permanent storage (note that in the case where a project is using multiple permanent storage solutions, if a payload is missing in one backend it counts as not being in permanent storage) we then attempt to virtualized them. - Only after all of this is done will we create the truncated copy of each package and then append the updated trailer to each one. In theory doing it in this order this might slightly increase the change of submit failures that occur after virtualization that result in a package never being submitted and orphaned payloads being added to permanent storage, but this will always be a risk. - Added an assert to fire if we detect a trailer with some virtualized and some local payloads. This should be a supported feature but needs proper testing first before we can allow it. With out current project settings no project should actually encounter this scenario. - To make the code easier to follow we now early out of the entire check when errors are encountered. - Added logging at various stages in the process to help show the user that something is happening and make problems easier to identify in the future. - Notes -- There is a lot of handling of invalid FPayloads. This is because it is currently possible to add empty payloads to the trailer which is inefficient and wastes space. The trailer will be modified to reject empty payloads in a future update at which point a lot of this handling can be removed. -- This could've also been solved by not fully rehydrating a package on save by the end user, which will be added as a project setting in a future piece of work, but this approach will solve the edge case when the user does have a large amount of hydrated packages which contain payloads that are already virtualized so it was better to fix that now while we have good test cases for it. -- We still have scaling problems with large number of package being submitted that do have payloads that need to be virtualized, this will be fixed by extending IVirtualizationSystem::Push to also accept batches of payloads in future work. -- OnPrePackageSubmission could be broken up into smaller chunks to make the code easier to follow. This will be done after the batch payload submission work is done. ### VirtualizationSystem - EStorageType has been promoted to enum class. - Added a new enum FPayloadStatus to be used when querying if a payload exists in a backend storage system or not. - Add a new method ::DoPayloadsExist which allows the caller to query if one or more payloads exists in the given backend storage system. ### VirtualizationManager - Implemented ::DoPayloadsExist. First we get the results from each backend in the storage system (which return as true or false from each backend) then total how many backends found the payload in order to set the correct status. ### IVirtualizationBackend - ::DoesPayloadExist which queries the existence of a single payload has been added to the interface. Most backends already implemented this for private use and if so have had their implementation renamed to match this. - Also added ::DoPayloadsExist which takes a batch of FpayloadIdsto query. Some backends can deal with a batch of payload ids much more efficiently than one at a time, although the default implementation does call ::DoesPayloadExist for each requested payload. -- The default implementation prevents every backend from needing to implement the same for loop but does allow backends that can gain from batching to override it. ### VirtualizationSourceControlBackend - This backend does override ::DoPayloadsExist and implements it's own version as it tends to perform very poorly when not operating on larger batches. - In this case ::DoesPayloadExist calls back to ::DoPayloadsExist to check each payload rather than implement as specific version. ### PackageTrailer - The trailer can now be queries to request how many payloads of a given type it contains #ROBOMERGE-AUTHOR: paul.chipchase #ROBOMERGE-SOURCE: CL 18339847 in //UE5/Release-5.0/... via CL 18339852 #ROBOMERGE-BOT: STARSHIP (Release-Engine-Staging -> Release-Engine-Test) (v895-18170469) [CL 18339859 by paul chipchase in ue5-release-engine-test branch]
2021-12-01 11:13:31 -05:00
TRACE_CPUPROFILER_EVENT_SCOPE(FDDCBackend::DoesPayloadExist);
UE::DerivedData::ICache& Cache = UE::DerivedData::GetCache();
UE::DerivedData::FCacheKey Key;
Key.Bucket = Bucket;
Key.Hash = Id;
UE::DerivedData::FRequestOwner Owner(UE::DerivedData::EPriority::Blocking);
UE::DerivedData::EStatus ResultStatus;
auto Callback = [&ResultStatus](UE::DerivedData::FCacheGetResponse&& Response)
{
ResultStatus = Response.Status;
};
// TODO: Improve the name when we start passing more context to this function
Cache.Get({{{TEXT("Mirage")}, Key, QueryPolicy | UE::DerivedData::ECachePolicy::SkipData}}, Owner, MoveTemp(Callback));
Owner.Wait();
return ResultStatus == UE::DerivedData::EStatus::Ok;
}
UE_REGISTER_VIRTUALIZATION_BACKEND_FACTORY(FDDCBackend, DDCBackend);
} // namespace UE::Virtualization