fix: allocation csv: gpu_hours -> slot_hours, add resource_pool [DET-10408]

docs/manage/historical-cluster-usage-data.rst

@@ -6,7 +6,7 @@
 
 Determined provides insights into the usage of your cluster, measured in compute hours allocated.
 Note that this is based on allocation, not resource utilization. For example, if a user has 1 GPU
-allocated but uses only 20% of it, we still report one GPU hour.
+allocated but uses only 20% of it, we still report one slot-hour.
 
 .. warning::
 
@@ -23,11 +23,11 @@ allocated but uses only 20% of it, we still report one GPU hour.
 
 .. note::
 
-   When using the export to CSV functionality, ``gpu_hours`` reflects only the GPU hours used during
-   the export time window. This means that allocations overlapping the export window have their GPU
-   hours calculated only for the time within the window. As a result, allocations not starting and
-   ending within the export window may appear to have incorrect GPU hours when calculated manually
-   from their start and end times.
+   When using the export to CSV functionality, ``slot_hours`` reflects only the slot hours used
+   during the export time window. This means that allocations overlapping the export window have
+   their slot-hours calculated only for the time within the window. As a result, allocations not
+   starting and ending within the export window may appear to have incorrect slot-hours when
+   calculated manually from their start and end times.
 
 *********************
  WebUI Visualization

docs/reference/experiment-config-reference.rst

@@ -1174,6 +1174,13 @@ multiple GPUs is done using data parallelism. Configuring ``slots_per_trial`` to
    certain models, as described in the `PyTorch documentation
    <https://pytorch.org/docs/stable/generated/torch.nn.DataParallel.html#torch.nn.DataParallel>`__.
 
+``slots``
+=========
+
+For historical reasons, this field usually passes config validation steps, but has no practical
+effect when present in experiment config. Use :ref:`slots_per_trial
+<exp-config-resources-slots-per-trial>` instead.
+
 ``max_slots``
 =============
 

docs/release-notes/relabel-allocation-csv.rst

@@ -0,0 +1,7 @@
+:orphan:
+
+**Breaking Changes**
+
+-  Tasks: The :ref:`historical usage <historical-cluster-usage-data>` CSV header row for slot-hours
+   is now named ``slot_hours`` as it may also track allocation time for resource pools without GPUs.
+   Also, this CSV now has an additional column providing the ``resource_pool`` for each allocation.

master/internal/core.go

@@ -362,12 +362,13 @@ type AllocationMetadata struct {
 	TaskType         model.TaskType
 	Username         string
 	WorkspaceName    string
+	ResourcePool     string
 	ExperimentID     int
 	Slots            int
 	StartTime        time.Time
 	EndTime          time.Time
 	ImagepullingTime float64
-	GPUHours         float64
+	SlotHours        float64
 }
 
 // canGetUsageDetails checks if the user has permission to get cluster usage details.
@@ -438,7 +439,8 @@ func (m *Master) getResourceAllocations(c echo.Context) error {
 		ColumnExpr("a.start_time").
 		ColumnExpr("a.end_time").
 		ColumnExpr("a.slots").
-		ColumnExpr("CASE WHEN a.start_time is NULL THEN 0.0 ELSE extract(epoch FROM (LEAST(GREATEST(coalesce(a.end_time, now()), a.start_time), ? :: timestamptz) - GREATEST(a.start_time, ? :: timestamptz))) * a.slots END AS gpu_seconds", end, start).
+		ColumnExpr("a.resource_pool").
+		ColumnExpr("CASE WHEN a.start_time is NULL THEN 0.0 ELSE extract(epoch FROM (LEAST(GREATEST(coalesce(a.end_time, now()), a.start_time), ? :: timestamptz) - GREATEST(a.start_time, ? :: timestamptz))) * a.slots END AS slot_seconds", end, start).
 		TableExpr("allocations a").
 		Where("tstzrange(start_time - interval '1 microsecond', greatest(start_time, coalesce(end_time, now()))) && tstzrange(? :: timestamptz, ? :: timestamptz)", start, end)
 
@@ -470,7 +472,8 @@ func (m *Master) getResourceAllocations(c echo.Context) error {
 		ColumnExpr("a.start_time").
 		ColumnExpr("a.end_time").
 		ColumnExpr("ip.imagepulling_time").
-		ColumnExpr("a.gpu_seconds / 3600.0 AS gpu_hours").
+		ColumnExpr("a.slot_seconds / 3600.0 AS slot_hours").
+		ColumnExpr("a.resource_pool").
 		With("tasks_in_range", tasksInRange).
 		With("allocations_in_range", allocationsInRange).
 		With("task_owners", taskOwners).
@@ -500,7 +503,8 @@ func (m *Master) getResourceAllocations(c echo.Context) error {
 		"start_time",
 		"end_time",
 		"imagepulling_time",
-		"gpu_hours",
+		"slot_hours",
+		"resource_pool",
 	}
 
 	formatTimestamp := func(t time.Time) string {
@@ -545,7 +549,8 @@ func (m *Master) getResourceAllocations(c echo.Context) error {
 			formatTimestamp(allocationMetadata.StartTime),
 			formatTimestamp(allocationMetadata.EndTime),
 			formatDuration(allocationMetadata.ImagepullingTime),
-			formatDuration(allocationMetadata.GPUHours),
+			formatDuration(allocationMetadata.SlotHours),
+			allocationMetadata.ResourcePool,
 		}
 		if err := csvWriter.Write(fields); err != nil {
 			return err