AWSDeadlineCloud Update: Added fields to track cumulative task retry attempts for steps and jobs

Author: AWS

.changes/next-release/feature-AWSDeadlineCloud-2f61f6f.json

@@ -0,0 +1,6 @@
+{
+    "type": "feature",
+    "category": "AWSDeadlineCloud",
+    "contributor": "",
+    "description": "Added fields to track cumulative task retry attempts for steps and jobs"
+}

services/deadline/src/main/resources/codegen-resources/service-2.json

@@ -2286,11 +2286,11 @@
       "members":{
         "name":{
           "shape":"AcceleratorName",
-          "documentation":"<p>The name of the chip used by the GPU accelerator.</p> <p>If you specify <code>l4</code> as the name of the accelerator, you must specify <code>latest</code> or <code>grid:r550</code> as the runtime.</p> <p>The available GPU accelerators are:</p> <ul> <li> <p> <code>t4</code> - NVIDIA T4 Tensor Core GPU</p> </li> <li> <p> <code>a10g</code> - NVIDIA A10G Tensor Core GPU</p> </li> <li> <p> <code>l4</code> - NVIDIA L4 Tensor Core GPU</p> </li> <li> <p> <code>l40s</code> - NVIDIA L40S Tensor Core GPU</p> </li> </ul>"
+          "documentation":"<p>The name of the chip used by the GPU accelerator.</p> <p>If you specify <code>l4</code> as the name of the accelerator, you must specify <code>latest</code> or <code>grid:r570</code> as the runtime.</p> <p>The available GPU accelerators are:</p> <ul> <li> <p> <code>t4</code> - NVIDIA T4 Tensor Core GPU</p> </li> <li> <p> <code>a10g</code> - NVIDIA A10G Tensor Core GPU</p> </li> <li> <p> <code>l4</code> - NVIDIA L4 Tensor Core GPU</p> </li> <li> <p> <code>l40s</code> - NVIDIA L40S Tensor Core GPU</p> </li> </ul>"
         },
         "runtime":{
           "shape":"AcceleratorRuntime",
-          "documentation":"<p>Specifies the runtime driver to use for the GPU accelerator. You must use the same runtime for all GPUs. </p> <p>You can choose from the following runtimes:</p> <ul> <li> <p> <code>latest</code> - Use the latest runtime available for the chip. If you specify <code>latest</code> and a new version of the runtime is released, the new version of the runtime is used.</p> </li> <li> <p> <code>grid:r550</code> - <a href=\"https://docs.nvidia.com/vgpu/17.0/index.html\">NVIDIA vGPU software 17</a> </p> </li> <li> <p> <code>grid:r535</code> - <a href=\"https://docs.nvidia.com/vgpu/16.0/index.html\">NVIDIA vGPU software 16</a> </p> </li> </ul> <p>If you don't specify a runtime, Deadline Cloud uses <code>latest</code> as the default. However, if you have multiple accelerators and specify <code>latest</code> for some and leave others blank, Deadline Cloud raises an exception.</p>"
+          "documentation":"<p>Specifies the runtime driver to use for the GPU accelerator. You must use the same runtime for all GPUs. </p> <p>You can choose from the following runtimes:</p> <ul> <li> <p> <code>latest</code> - Use the latest runtime available for the chip. If you specify <code>latest</code> and a new version of the runtime is released, the new version of the runtime is used.</p> </li> <li> <p> <code>grid:r570</code> - <a href=\"https://docs.nvidia.com/vgpu/18.0/index.html\">NVIDIA vGPU software 18</a> </p> </li> <li> <p> <code>grid:r535</code> - <a href=\"https://docs.nvidia.com/vgpu/16.0/index.html\">NVIDIA vGPU software 16</a> </p> </li> </ul> <p>If you don't specify a runtime, Deadline Cloud uses <code>latest</code> as the default. However, if you have multiple accelerators and specify <code>latest</code> for some and leave others blank, Deadline Cloud raises an exception.</p>"
         }
       },
       "documentation":"<p>Describes a specific GPU accelerator required for an Amazon Elastic Compute Cloud worker host.</p>"
@@ -5458,7 +5458,7 @@
         },
         "status":{
           "shape":"FleetStatus",
-          "documentation":"<p>The Auto Scaling status of the fleet.</p>"
+          "documentation":"<p>The status of the fleet.</p>"
         },
         "autoScalingStatus":{
           "shape":"AutoScalingStatus",
@@ -5633,6 +5633,10 @@
           "shape":"TaskRunStatusCounts",
           "documentation":"<p>The number of tasks running on the job.</p>"
         },
+        "taskFailureRetryCount":{
+          "shape":"TaskFailureRetryCount",
+          "documentation":"<p>The total number of times tasks from the job failed and were retried.</p>"
+        },
         "storageProfileId":{
           "shape":"StorageProfileId",
           "documentation":"<p>The storage profile ID associated with the job.</p>"
@@ -6506,6 +6510,10 @@
           "shape":"TaskRunStatusCounts",
           "documentation":"<p>The number of tasks running on the job.</p>"
         },
+        "taskFailureRetryCount":{
+          "shape":"TaskFailureRetryCount",
+          "documentation":"<p>The total number of times tasks from the step failed and were retried.</p>"
+        },
         "targetTaskRunStatus":{
           "shape":"StepTargetTaskRunStatus",
           "documentation":"<p>The task status with which the job started.</p>"
@@ -7410,6 +7418,10 @@
           "shape":"TaskRunStatusCounts",
           "documentation":"<p>The number of tasks running on the job.</p>"
         },
+        "taskFailureRetryCount":{
+          "shape":"TaskFailureRetryCount",
+          "documentation":"<p>The total number of times tasks from the job failed and were retried.</p>"
+        },
         "priority":{
           "shape":"JobPriority",
           "documentation":"<p>The job priority.</p>"
@@ -7525,6 +7537,10 @@
           "shape":"TaskRunStatusCounts",
           "documentation":"<p>The number of tasks running on the job.</p>"
         },
+        "taskFailureRetryCount":{
+          "shape":"TaskFailureRetryCount",
+          "documentation":"<p>The total number of times tasks from the job failed and were retried.</p>"
+        },
         "maxFailedTasksCount":{
           "shape":"MaxFailedTasksCount",
           "documentation":"<p>The number of task failures before the job stops running and is marked as <code>FAILED</code>.</p>"
@@ -11190,6 +11206,10 @@
           "shape":"TaskRunStatusCounts",
           "documentation":"<p>The number of tasks running on the job.</p>"
         },
+        "taskFailureRetryCount":{
+          "shape":"TaskFailureRetryCount",
+          "documentation":"<p>The total number of times tasks from the step failed and were retried.</p>"
+        },
         "createdAt":{
           "shape":"CreatedAt",
           "documentation":"<p>The date and time the resource was created.</p>"
@@ -11249,6 +11269,10 @@
           "shape":"TaskRunStatusCounts",
           "documentation":"<p>The number of tasks running on the job.</p>"
         },
+        "taskFailureRetryCount":{
+          "shape":"TaskFailureRetryCount",
+          "documentation":"<p>The total number of times tasks from the step failed and were retried.</p>"
+        },
         "targetTaskRunStatus":{
           "shape":"StepTargetTaskRunStatus",
           "documentation":"<p>The task status to start with on the job.</p>"
@@ -11434,6 +11458,12 @@
       "key":{"shape":"String"},
       "value":{"shape":"String"}
     },
+    "TaskFailureRetryCount":{
+      "type":"integer",
+      "box":true,
+      "max":2147483647,
+      "min":0
+    },
     "TaskId":{
       "type":"string",
       "pattern":"task-[0-9a-f]{32}-(0|([1-9][0-9]{0,9}))"