[BlobAsync] Disk support for blob storage

content/browser/service_worker/service_worker_url_request_job.cc

 // Copyright 2014 The Chromium Authors. All rights reserved.
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file.
 
 #include "content/browser/service_worker/service_worker_url_request_job.h"
 
 #include <stddef.h>
 #include <stdint.h>
 
-#include <limits>
 #include <map>
 #include <memory>
 #include <string>
 #include <utility>
 #include <vector>
 
 #include "base/bind.h"
+#include "base/files/file.h"
 #include "base/guid.h"
 #include "base/location.h"
 #include "base/single_thread_task_runner.h"
 #include "base/strings/stringprintf.h"
+#include "base/task_runner.h"
+#include "base/task_runner_util.h"
 #include "base/threading/thread_task_runner_handle.h"
 #include "base/time/time.h"
 #include "content/browser/resource_context_impl.h"
 #include "content/browser/service_worker/embedded_worker_instance.h"
 #include "content/browser/service_worker/service_worker_fetch_dispatcher.h"
 #include "content/browser/service_worker/service_worker_provider_host.h"
 #include "content/browser/service_worker/service_worker_response_info.h"
 #include "content/browser/streams/stream.h"
 #include "content/browser/streams/stream_context.h"
 #include "content/browser/streams/stream_registry.h"
 #include "content/common/resource_request_body_impl.h"
 #include "content/common/service_worker/service_worker_types.h"
 #include "content/common/service_worker/service_worker_utils.h"
 #include "content/public/browser/blob_handle.h"
+#include "content/public/browser/browser_thread.h"
 #include "content/public/browser/resource_request_info.h"
 #include "content/public/browser/service_worker_context.h"
 #include "content/public/common/referrer.h"
 #include "net/base/net_errors.h"
 #include "net/http/http_request_headers.h"
 #include "net/http/http_response_headers.h"
 #include "net/http/http_response_info.h"
 #include "net/http/http_util.h"
 #include "net/log/net_log.h"
 #include "storage/browser/blob/blob_data_builder.h"
@@ skipping 52 matching lines @@
     case m::REQUEST_JOB_ERROR_DESTROYED_WITH_BLOB:
     case m::REQUEST_JOB_ERROR_DESTROYED_WITH_STREAM:
     // Invalid type.
     case m::NUM_REQUEST_JOB_RESULT_TYPES:
       NOTREACHED() << result;
   }
   NOTREACHED() << result;
   return n::TYPE_FAILED;
 }
 
+bool PopulateUnknownFileLengths(
+    std::vector<ResourceRequestBodyImpl::Element>* elements) {
+  for (ResourceRequestBodyImpl::Element& element : *elements) {
+    if (element.type() == ResourceRequestBodyImpl::Element::TYPE_FILE &&
+        element.length() == ResourceRequestBodyImpl::Element::kUnknownSize) {
+      // Try to open our file.
+      base::File file(element.path(),
+                      base::File::FLAG_OPEN | base::File::FLAG_READ);
+      if (file.error_details() != base::File::FILE_OK)

[michaeln, 2016/08/15 22:44:43]

base:: has a nice utility to GetFileInfo given just a path. so i don't think we
need a base::File instance here.

[dmurph, 2016/08/19 00:18:31]

Done.

+        return false;
+
+      base::File::Info file_info;
+      if (!file.GetInfo(&file_info))
+        return false;
+
+      element.SetToFilePathRange(element.path(), element.offset(),
+                                 file_info.size,
+                                 element.expected_modification_time());
+    }
+  }
+  return true;
+}
+
 }  // namespace
 
-class ServiceWorkerURLRequestJob::BlobConstructionWaiter {
+class ServiceWorkerURLRequestJob::BlobFilesWaiter {

[michaeln, 2016/08/15 22:44:43]

Oh, the purpose of this class is now completely different.

We used to have to wait for constituent blob elements in the RequestBody to
complete prior to "resolving" it into a RequestBlob.

But now we have to get the size of any constituent file elements in the
RequestBody because we have to know the size in order to create the RequestBlob.

A larger name change might be good since it doesn't really 'wait' for an
external agency to complete something.

class FileSizeResolver?

The impl might be easier to compose with a helper function like...

int64_t GetFileSizeOnBlockingPool(const base::FilePath& file_path) {
  int64_t size = 0;
  bool success = base::GetFileSize(file_path, &size);
  return success ? size : -1;
}

++num_pending_file_size_tasks_;
PostTaskAndReplyWithResult(
    runner,
    base::Bind(&GetFileSizeOnBlockingPool, path),
    base::Bind(&OnGotFileSize, GetWeakPtr(), element_index));

[dmurph, 2016/08/19 00:18:31]

Done.

  public:
-  explicit BlobConstructionWaiter(ServiceWorkerURLRequestJob* owner)
+  explicit BlobFilesWaiter(ServiceWorkerURLRequestJob* owner)
       : owner_(owner), weak_factory_(this) {
-    TRACE_EVENT_ASYNC_BEGIN1("ServiceWorker", "BlobConstructionWaiter", this,
-                             "URL", owner_->request()->url().spec());
+    TRACE_EVENT_ASYNC_BEGIN1("ServiceWorker", "BlobFilesWaiter", this, "URL",
+                             owner_->request()->url().spec());
     owner_->request()->net_log().BeginEvent(
-        net::NetLog::TYPE_SERVICE_WORKER_WAITING_FOR_REQUEST_BODY_BLOB);
+        net::NetLog::TYPE_SERVICE_WORKER_WAITING_FOR_REQUEST_BODY_FILES);
   }
 
-  ~BlobConstructionWaiter() {
+  ~BlobFilesWaiter() {
     owner_->request()->net_log().EndEvent(
-        net::NetLog::TYPE_SERVICE_WORKER_WAITING_FOR_REQUEST_BODY_BLOB,
+        net::NetLog::TYPE_SERVICE_WORKER_WAITING_FOR_REQUEST_BODY_FILES,
         net::NetLog::BoolCallback("success", phase_ == Phase::SUCCESS));
-    TRACE_EVENT_ASYNC_END1("ServiceWorker", "BlobConstructionWaiter", this,
-                           "Success", phase_ == Phase::SUCCESS);
+    TRACE_EVENT_ASYNC_END1("ServiceWorker", "BlobFilesWaiter", this, "Success",
+                           phase_ == Phase::SUCCESS);
   }
 
-  void RunOnComplete(const base::Callback<void(bool)>& callback) {
+  void RunOnComplete(base::TaskRunner* file_runner,
+                     const base::Callback<void(bool)>& callback) {
     DCHECK_EQ(static_cast<int>(Phase::INITIAL), static_cast<int>(phase_));
     phase_ = Phase::WAITING;
-    num_pending_request_body_blobs_ = 0;
+    body_ = owner_->body_;
     callback_ = callback;
 
-    for (const ResourceRequestBodyImpl::Element& element :
-         *(owner_->body_->elements())) {
-      if (element.type() != ResourceRequestBodyImpl::Element::TYPE_BLOB)
-        continue;
-
-      std::unique_ptr<storage::BlobDataHandle> handle =
-          owner_->blob_storage_context_->GetBlobDataFromUUID(
-              element.blob_uuid());
-      if (handle->IsBroken()) {
-        Complete(false);
-        return;
-      }
-      if (handle->IsBeingBuilt()) {
-        ++num_pending_request_body_blobs_;
-        handle->RunOnConstructionComplete(
-            base::Bind(&BlobConstructionWaiter::OneRequestBodyBlobCompleted,
-                       weak_factory_.GetWeakPtr()));
+    bool needs_file_stats = false;
+    for (const ResourceRequestBodyImpl::Element& element : *body_->elements()) {

[michaeln, 2016/08/15 22:44:42]

might be good place for const auto&

[dmurph, 2016/08/19 00:18:32]

Done.

+      if (element.type() == ResourceRequestBodyImpl::Element::TYPE_FILE &&
+          element.length() == ResourceRequestBodyImpl::Element::kUnknownSize) {
+        needs_file_stats = true;
       }
     }
 
-    if (num_pending_request_body_blobs_ == 0)
+    if (!needs_file_stats) {
       Complete(true);
+      return;
+    }
+
+    PostTaskAndReplyWithResult(
+        file_runner, FROM_HERE,
+        base::Bind(&PopulateUnknownFileLengths, body_->elements_mutable()),

[Marijn Kruisselbrink, 2016/08/05 23:23:54]

Is this safe? body_->elements_mutable() is just a raw pointer, so you're
seemingly relying on something else to keep body_ alive. But on the next
callback you're using a weak pointer to |this|, so it can't be the reference
this holds to body_ that keeps body_ alive.

[michaeln, 2016/08/15 22:44:43]

what he said

[dmurph, 2016/08/19 00:18:31]

Now we protect this by accessing the elements only in this class.

+        base::Bind(&ServiceWorkerURLRequestJob::BlobFilesWaiter::Complete,
+                   weak_factory_.GetWeakPtr()));
   }
 
  private:
   enum class Phase { INITIAL, WAITING, SUCCESS, FAIL };
 
-  void OneRequestBodyBlobCompleted(
-      bool success,
-      storage::IPCBlobCreationCancelCode cancel_code) {
-    DCHECK_GT(num_pending_request_body_blobs_, 0UL);
-
-    if (success)
-      --num_pending_request_body_blobs_;
-    else
-      num_pending_request_body_blobs_ = 0;
-
-    if (num_pending_request_body_blobs_ == 0)
-      Complete(success);
-  }
-
   void Complete(bool success) {
     DCHECK_EQ(static_cast<int>(Phase::WAITING), static_cast<int>(phase_));
     phase_ = success ? Phase::SUCCESS : Phase::FAIL;
     // Destroys |this|.
     callback_.Run(success);
   }
 
   // Owns and must outlive |this|.
   ServiceWorkerURLRequestJob* owner_;
 
   scoped_refptr<ResourceRequestBodyImpl> body_;
   base::Callback<void(bool)> callback_;
-  size_t num_pending_request_body_blobs_ = 0;
   Phase phase_ = Phase::INITIAL;
-  base::WeakPtrFactory<BlobConstructionWaiter> weak_factory_;
+  base::WeakPtrFactory<BlobFilesWaiter> weak_factory_;
 
-  DISALLOW_COPY_AND_ASSIGN(BlobConstructionWaiter);
+  DISALLOW_COPY_AND_ASSIGN(BlobFilesWaiter);
 };
 
 bool ServiceWorkerURLRequestJob::Delegate::RequestStillValid(
     ServiceWorkerMetrics::URLRequestJobResult* result) {
   return true;
 }
 
 ServiceWorkerURLRequestJob::ServiceWorkerURLRequestJob(
     net::URLRequest* request,
     net::NetworkDelegate* network_delegate,
@@ skipping 314 matching lines @@
       FinalizeFallbackToNetwork();
       return;
 
     case FALLBACK_TO_RENDERER:
       FinalizeFallbackToRenderer();
       return;
 
     case FORWARD_TO_SERVICE_WORKER:
       if (HasRequestBody()) {
         DCHECK(!blob_construction_waiter_);
-        blob_construction_waiter_.reset(new BlobConstructionWaiter(this));
+        blob_construction_waiter_.reset(new BlobFilesWaiter(this));
         blob_construction_waiter_->RunOnComplete(
+            BrowserThread::GetBlockingPool(),
             base::Bind(&ServiceWorkerURLRequestJob::RequestBodyBlobsCompleted,
                        GetWeakPtr()));
         return;
       }
 
       RequestBodyBlobsCompleted(true);
       return;
   }
 
   NOTREACHED();
@@ skipping 37 matching lines @@
     request->referrer =
         Referrer(GURL(request_->referrer()), blink::WebReferrerPolicyDefault);
   }
   request->fetch_type = fetch_type_;
   return request;
 }
 
 void ServiceWorkerURLRequestJob::CreateRequestBodyBlob(std::string* blob_uuid,
                                                        uint64_t* blob_size) {
   DCHECK(HasRequestBody());
-  // To ensure the blobs stick around until the end of the reading.
-  std::vector<std::unique_ptr<storage::BlobDataHandle>> handles;
-  std::vector<std::unique_ptr<storage::BlobDataSnapshot>> snapshots;
-  // TODO(dmurph): Allow blobs to be added below, so that the context can
-  // efficiently re-use blob items for the new blob.
-  std::vector<const ResourceRequestBodyImpl::Element*> resolved_elements;
+  const std::string uuid(base::GenerateGUID());
+  storage::BlobDataBuilder blob_builder(uuid);

[michaeln, 2016/08/15 22:44:43]

you could get rid of the uuid local and a line of code

[dmurph, 2016/08/19 00:18:31]

Done.

   for (const ResourceRequestBodyImpl::Element& element : (*body_->elements())) {
-    if (element.type() != ResourceRequestBodyImpl::Element::TYPE_BLOB) {
-      resolved_elements.push_back(&element);
-      continue;
-    }
-    std::unique_ptr<storage::BlobDataHandle> handle =
-        blob_storage_context_->GetBlobDataFromUUID(element.blob_uuid());
-    std::unique_ptr<storage::BlobDataSnapshot> snapshot =
-        handle->CreateSnapshot();
-    if (snapshot->items().empty())
-      continue;
-    const auto& items = snapshot->items();
-    for (const auto& item : items) {
-      DCHECK_NE(storage::DataElement::TYPE_BLOB, item->type());
-      resolved_elements.push_back(item->data_element_ptr());
-    }
-    handles.push_back(std::move(handle));
-    snapshots.push_back(std::move(snapshot));
-  }
-
-  const std::string uuid(base::GenerateGUID());
-  uint64_t total_size = 0;
-
-  storage::BlobDataBuilder blob_builder(uuid);
-  for (size_t i = 0; i < resolved_elements.size(); ++i) {
-    const ResourceRequestBodyImpl::Element& element = *resolved_elements[i];
-    if (total_size != std::numeric_limits<uint64_t>::max() &&
-        element.length() != std::numeric_limits<uint64_t>::max())
-      total_size += element.length();
-    else
-      total_size = std::numeric_limits<uint64_t>::max();
-    switch (element.type()) {
-      case ResourceRequestBodyImpl::Element::TYPE_BYTES:
-        blob_builder.AppendData(element.bytes(), element.length());
-        break;
-      case ResourceRequestBodyImpl::Element::TYPE_FILE:
-        blob_builder.AppendFile(element.path(), element.offset(),
-                                element.length(),
-                                element.expected_modification_time());
-        break;
-      case ResourceRequestBodyImpl::Element::TYPE_BLOB:
-        // Blob elements should be resolved beforehand.
-        NOTREACHED();
-        break;
-      case ResourceRequestBodyImpl::Element::TYPE_FILE_FILESYSTEM:
-        blob_builder.AppendFileSystemFile(element.filesystem_url(),
-                                          element.offset(), element.length(),
-                                          element.expected_modification_time());
-        break;
-      default:
-        NOTIMPLEMENTED();
-    }
+    blob_builder.AppendIPCDataElement(element);
   }
 
   request_body_blob_data_handle_ =
       blob_storage_context_->AddFinishedBlob(&blob_builder);
   *blob_uuid = uuid;
-  *blob_size = total_size;
+  *blob_size = request_body_blob_data_handle_->size();
 }
 
 void ServiceWorkerURLRequestJob::DidPrepareFetchEvent(
     scoped_refptr<ServiceWorkerVersion> version) {
   worker_ready_time_ = base::TimeTicks::Now();
   load_timing_info_.send_start = worker_ready_time_;
 
   // Record the time taken for the browser to find and possibly start an active
   // worker to which to dispatch a FetchEvent for a main frame resource request.
   // For context, a FetchEvent can only be dispatched to an ACTIVATED worker
@@ skipping 379 matching lines @@
       CreateFetchRequest(), active_worker, resource_type_, request()->net_log(),
       base::Bind(&ServiceWorkerURLRequestJob::DidPrepareFetchEvent,
                  weak_factory_.GetWeakPtr(), active_worker),
       base::Bind(&ServiceWorkerURLRequestJob::DidDispatchFetchEvent,
                  weak_factory_.GetWeakPtr())));
   worker_start_time_ = base::TimeTicks::Now();
   fetch_dispatcher_->Run();
 }
 
 }  // namespace content