Correctly reset chunk during artifact upload on retry (#458)

* Correctly reset chunk during artifact upload on retry

* Update workflow

* Implementation details around the passthrough stream

.github/workflows/artifact-tests.yml

@@ -1,5 +1,13 @@
 name: artifact-unit-tests
-on: push
+on:
+  push:
+    branches:
+      - master
+    paths-ignore:
+      - '**.md'
+  pull_request:
+    paths-ignore:
+      - '**.md'
 
 jobs:
   build:
@@ -7,7 +15,7 @@ jobs:
 
     strategy:
       matrix:
-        runs-on: [ubuntu-latest, windows-latest, macOS-latest]
+        runs-on: [ubuntu-latest, windows-latest, macos-latest]
       fail-fast: false
 
     runs-on: ${{ matrix.runs-on }}

packages/artifact/docs/implementation-details.md

@@ -6,6 +6,10 @@ Warning: Implementation details may change at any time without notice. This is m
 
 ![image](https://user-images.githubusercontent.com/16109154/79765587-19522b00-8327-11ea-9679-410bb10e1b13.png)
 
+During artifact upload, gzip is used to compress individual files that then get uploaded. This is used to minimize the amount of data that gets uploaded which reduces the total amount of HTTP calls (upload happens in 4MB chunks). This results in considerably faster uploads with huge performance implications especially on self-hosted runners.
+
+If a file is less than 64KB in size, a passthrough stream (readable and writable) is used to convert an in-memory buffer into a readable stream without any extra streams or pipping.
+
 ## Retry Logic when downloading an individual file
 
 ![image](https://user-images.githubusercontent.com/16109154/78555461-5be71400-780d-11ea-9abd-b05b77a95a3f.png)

packages/artifact/src/internal/upload-http-client.ts

@@ -208,25 +208,30 @@ export class UploadHttpClient {
     // for creating a new GZip file, an in-memory buffer is used for compression
     if (totalFileSize < 65536) {
       const buffer = await createGZipFileInBuffer(parameters.file)
-      let uploadStream: NodeJS.ReadableStream
+
+      //An open stream is needed in the event of a failure and we need to retry. If a NodeJS.ReadableStream is directly passed in,
+      // it will not properly get reset to the start of the stream if a chunk upload needs to be retried
+      let openUploadStream: () => NodeJS.ReadableStream
 
       if (totalFileSize < buffer.byteLength) {
         // compression did not help with reducing the size, use a readable stream from the original file for upload
-        uploadStream = fs.createReadStream(parameters.file)
+        openUploadStream = () => fs.createReadStream(parameters.file)
         isGzip = false
         uploadFileSize = totalFileSize
       } else {
         // create a readable stream using a PassThrough stream that is both readable and writable
+        openUploadStream = () => {
           const passThrough = new stream.PassThrough()
           passThrough.end(buffer)
-        uploadStream = passThrough
+          return passThrough
+        }
         uploadFileSize = buffer.byteLength
       }
 
       const result = await this.uploadChunk(
         httpClientIndex,
         parameters.resourceUrl,
-        uploadStream,
+        openUploadStream,
         0,
         uploadFileSize - 1,
         uploadFileSize,
@@ -296,6 +301,7 @@ export class UploadHttpClient {
         const result = await this.uploadChunk(
           httpClientIndex,
           parameters.resourceUrl,
+          () =>
             fs.createReadStream(uploadFilePath, {
               start,
               end,
@@ -335,7 +341,7 @@ export class UploadHttpClient {
    * indicates a retryable status, we try to upload the chunk as well
    * @param {number} httpClientIndex The index of the httpClient being used to make all the necessary calls
    * @param {string} resourceUrl Url of the resource that the chunk will be uploaded to
-   * @param {NodeJS.ReadableStream} data Stream of the file that will be uploaded
+   * @param {NodeJS.ReadableStream} openStream Stream of the file that will be uploaded
    * @param {number} start Starting byte index of file that the chunk belongs to
    * @param {number} end Ending byte index of file that the chunk belongs to
    * @param {number} uploadFileSize Total size of the file in bytes that is being uploaded
@@ -346,7 +352,7 @@ export class UploadHttpClient {
   private async uploadChunk(
     httpClientIndex: number,
     resourceUrl: string,
-    data: NodeJS.ReadableStream,
+    openStream: () => NodeJS.ReadableStream,
     start: number,
     end: number,
     uploadFileSize: number,
@@ -365,7 +371,7 @@ export class UploadHttpClient {
 
     const uploadChunkRequest = async (): Promise<IHttpClientResponse> => {
       const client = this.uploadHttpManager.getClient(httpClientIndex)
-      return await client.sendStream('PUT', resourceUrl, data, headers)
+      return await client.sendStream('PUT', resourceUrl, openStream(), headers)
     }
 
     let retryCount = 0