feat(test-tooling): containers pull image retries exp. back-off hyper…

…ledger-cacti#656

Potentially fixing hyperledger-cacti#656. Definitely improves the situation but it
is impossible to tell in advance if this will make all the other-
wise non-reproducible issues go away. Fingers crossed.

This change makes it so that the pullImage(...) method of the Containers
utility class will now - by default - retry 6 times if the docker
image pulling has failed. The internval between retries is
increasing exponentially (power of two) starting from one
second as the delay then proceeding to be 2^6 seconds
for the final retry (which if also fails then an AbortError
is thrown by the underlying pRetry library that is powering
the retry mechanism.)

For reference, here is a randomly failed CI test execution
where the logs show that DockerHub is randomly in-
accessible over the network and that's another thing that
makes our tests flaky, hence this commit to fix this.

https://github.com/hyperledger/cactus/runs/2178802580?check_suite_focus=true#step:8:2448

In case that link goes dead in the future, here's also the actual logs:

not ok 60 - packages/cactus-test-cmd-api-server/src/test/typescript/integration/remote-plugin-imports.test.ts # time=25389.665ms
  ---
  env:
    TS_NODE_COMPILER_OPTIONS: '{"jsx":"react"}'
  file: packages/cactus-test-cmd-api-server/src/test/typescript/integration/remote-plugin-imports.test.ts
  timeout: 1800000
  command: /opt/hostedtoolcache/node/12.13.0/x64/bin/node
  args:
    - -r
    - /home/runner/work/cactus/cactus/node_modules/ts-node/register/index.js
    - --max-old-space-size=4096
    - packages/cactus-test-cmd-api-server/src/test/typescript/integration/remote-plugin-imports.test.ts
  stdio:
    - 0
    - pipe
    - 2
  cwd: /home/runner/work/cactus/cactus
  exitCode: 1
  ...
{
    # NodeJS API server + Rust plugin work together
    [2021-03-23T20:45:51.458Z] INFO (VaultTestServer): Created VaultTestServer OK. Image FQN: vault:1.6.1
    not ok 1 Error: (HTTP code 500) server error - Get https://registry-1.docker.io/v2/: net/http: request canceled while waiting for connection (Client.Timeout exceeded while awaiting headers)
      ---
        operator: error
        at: bound (/home/runner/work/cactus/cactus/node_modules/onetime/index.js:30:12)
        stack: |-
          Error: (HTTP code 500) server error - Get https://registry-1.docker.io/v2/: net/http: request canceled while waiting for connection (Client.Timeout exceeded while awaiting headers)
              at /home/runner/work/cactus/cactus/packages/cactus-test-tooling/node_modules/docker-modem/lib/modem.js:301:17
              at IncomingMessage.<anonymous> (/home/runner/work/cactus/cactus/packages/cactus-test-tooling/node_modules/docker-modem/lib/modem.js:328:9)
              at IncomingMessage.emit (events.js:215:7)
              at endReadableNT (_stream_readable.js:1183:12)
              at processTicksAndRejections (internal/process/task_queues.js:80:21)
      ...

    Bail out! Error: (HTTP code 500) server error - Get https://registry-1.docker.io/v2/: net/http: request canceled while waiting for connection (Client.Timeout exceeded while awaiting headers)
}
Bail out! Error: (HTTP code 500) server error - Get https://registry-1.docker.io/v2/: net/http: request canceled while waiting for connection (Client.Timeout exceeded while awaiting headers)

Signed-off-by: Peter Somogyvari <peter.somogyvari@accenture.com>

packages/cactus-test-tooling/package.json

@@ -31,7 +31,10 @@
       "ignore": [
         "src/**/generated/*"
       ],
-      "extensions": ["ts", "json"],
+      "extensions": [
+        "ts",
+        "json"
+      ],
       "quiet": true,
       "verbose": false,
       "runOnChangeOnly": true
@@ -91,6 +94,7 @@
     "loglevel": "1.6.7",
     "loglevel-plugin-prefix": "0.8.4",
     "node-ssh": "11.1.1",
+    "p-retry": "4.4.0",
     "tar-stream": "2.1.2",
     "typescript-optional": "2.0.1",
     "web3": "1.2.7"
@@ -100,8 +104,8 @@
     "@types/extract-zip": "1.6.2",
     "@types/fs-extra": "8.1.0",
     "@types/joi": "14.3.4",
-    "@types/ssh2": "0.5.44",
     "@types/node-ssh": "7.0.0",
+    "@types/ssh2": "0.5.44",
     "@types/tar-stream": "2.1.0"
   }
 }

packages/cactus-test-tooling/src/main/typescript/common/containers.ts

@@ -5,9 +5,15 @@ import { Container, ContainerInfo } from "dockerode";
 import Dockerode from "dockerode";
 import tar from "tar-stream";
 import fs from "fs-extra";
+import pRetry from "p-retry";
 import { Streams } from "../common/streams";
-import { Checks, LoggerProvider, Strings } from "@hyperledger/cactus-common";
-import { LogLevelDesc } from "loglevel";
+import {
+  Checks,
+  LogLevelDesc,
+  LoggerProvider,
+  Strings,
+  ILoggerOptions,
+} from "@hyperledger/cactus-common";
 
 export interface IPruneDockerResourcesRequest {
   logLevel?: LogLevelDesc;
@@ -297,33 +303,62 @@ export class Containers {
       return NetworkSettings.Networks[networkNames[0]].IPAddress;
     }
   }
-
   public static pullImage(
-    containerNameAndTag: string,
-    pullOptions: any = {},
+    imageFqn: string,
+    options: any = {},
+    logLevel?: LogLevelDesc,
+  ): Promise<any[]> {
+    const defualtLoggerOptions: ILoggerOptions = {
+      label: "containers#pullImage()",
+      level: logLevel || "INFO",
+    };
+    const log = LoggerProvider.getOrCreate(defualtLoggerOptions);
+    const task = () => Containers.tryPullImage(imageFqn, options, logLevel);
+    const retryOptions: pRetry.Options = {
+      retries: 6,
+      onFailedAttempt: async (ex) => {
+        log.debug(`Failed attempt at pulling container image ${imageFqn}`, ex);
+      },
+    };
+    return pRetry(task, retryOptions);
+  }
+
+  public static tryPullImage(
+    imageFqn: string,
+    options: any = {},
+    logLevel?: LogLevelDesc,
   ): Promise<any[]> {
     return new Promise((resolve, reject) => {
+      const loggerOptions: ILoggerOptions = {
+        label: "containers#tryPullImage()",
+        level: logLevel || "INFO",
+      };
+      const log = LoggerProvider.getOrCreate(loggerOptions);
+
       const docker = new Dockerode();
-      docker.pull(
-        containerNameAndTag,
-        pullOptions,
-        (pullError: any, stream: any) => {
-          if (pullError) {
-            reject(pullError);
-          } else {
-            docker.modem.followProgress(
-              stream,
-              (progressError: any, output: any[]) => {
-                if (progressError) {
-                  reject(progressError);
-                } else {
-                  resolve(output);
-                }
-              },
-            );
-          }
-        },
-      );
+
+      const pullStreamStartedHandler = (pullError: any, stream: any) => {
+        if (pullError) {
+          log.error(`Could not even start ${imageFqn} pull:`, pullError);
+          reject(pullError);
+        } else {
+          log.debug(`Started ${imageFqn} pull progress stream OK`);
+          docker.modem.followProgress(
+            stream,
+            (progressError: any, output: any[]) => {
+              if (progressError) {
+                log.error(`Failed to finish ${imageFqn} pull:`, progressError);
+                reject(progressError);
+              } else {
+                log.debug(`Finished ${imageFqn} pull completely OK`);
+                resolve(output);
+              }
+            },
+          );
+        }
+      };
+
+      docker.pull(imageFqn, options, pullStreamStartedHandler);
     });
   }