Compare commits

...
10 Commits
Author SHA1 Message Date
jialin e919b22d98 feat(gpu-service): restrict non-stopped instance edit, drop recreate
- non-stopped edit: only displayName and SSH public keys editable;
  type/template/storage sections disabled (stopped edit keeps all editable)
- remove recreate feature and the realAction prop it required:
  entry, delete-then-create submit path, warning banner, locale keys
2026-07-23 10:24:54 +08:00
jialin 89a74ed26a style(cluster): col width 2026-07-22 16:21:12 +08:00
jialin fe4dbf087f feat(gpu-service): align instance-type/flavor contract with status.detail API
- spec keeps definition fields only; observed hardware read from status.detail
- sliceable derived from slicedDetail (logical count / physical profiles)
- flat snapshot format isolated in instance-description for back-compat
- drop flavor.spec.sliceable; onceMaxRequest realigned (no ram/localStorage)
- lock compute ratio to memory ratio when coresPercentageOvercommit is false
- sliced mode submits whole cores / Gi; displayName-first type labels
2026-07-22 15:52:17 +08:00
jialin cbd9fc4946 fix: preset 10,20,30,50 for ratios 2026-07-22 15:52:17 +08:00
jialin 74f1399e3c feat(gpu-service): add sliced compute ratio, confirm activate/deactivate, watch instance types
- add configurable compute (cores) percentage in sliced mode (cores >= memory)
- confirm instance-type activate/deactivate via DeleteModal
- live-sync instance types list via chunked watch
2026-07-22 15:52:17 +08:00
jialin 96d194a4f4 feat(gpu-service): allow re-typing stopped instances on edit
- Add instance-type column to edit drawer for stopped instances
- Extract saveInstanceDataInDescription into shared util
- Floor sliced unit resources; keep CPU >= 1 core
- Expose applyInstanceType for both create and edit flows
2026-07-22 15:52:17 +08:00
jialin e9d585cc90 fix(gpu-service): only pick Active candidates for accelerator
Gate pickCandidateForAccelerator on phase === Active using
InstanceTypePhaseValueMap so a phase-value change stays in sync.
2026-07-22 15:52:17 +08:00
jialin 3fff1c10f2 feat(gpu-service): instance-type activate/deactivate, displayName, unified flavor display
- add activate/deactivate row actions (phase-driven) with new PUT APIs
- add displayName field; list shows displayName || name
- rename list OS column title to Platform
- share a two-line flavor renderer between the create dropdown and the list
- normalize 'CPU Only' label to 'CPU-only'
2026-07-22 15:52:17 +08:00
jialin 2763594ae3 feat(gpu-service): use grouped flavor select in instance type create drawer 2026-07-22 15:52:17 +08:00
jialin 1655549f31 feat(gpu-service): add sliceable tag and horizontal scroll to instance types table 2026-07-22 15:52:17 +08:00
38 changed files with 1328 additions and 673 deletions
+4
View File
@@ -98,6 +98,10 @@ Compose layout with Ant components, not hand-written `display: flex`.
Drive spacing with the theme scale (`Flex`/`Space` `gap`, or `var(--ant-*)` spacing tokens), not scattered `px` literals.
## Tables
- **Horizontally scrollable table**: set `scroll={{ x: 'max-content' }}` **and** add `className="scroll-table"` on the `Table`. The class styles the horizontal scroll to match the design; without it the scroll works but looks off.
# Naming conventions
A page module lives under `src/pages/{module}` with this sub-structure: `components/`, `config/`, `forms/`, `hooks/`, `services/`, `index.tsx`. File naming:
+6
View File
@@ -222,6 +222,12 @@ export default {
'common.title.delete.confirm': 'Confirm deletion',
'common.title.stop.confirm': 'Confirm stop',
'common.title.start.confirm': 'Confirm start',
'common.title.activate.confirm': 'Confirm activate',
'common.title.deactivate.confirm': 'Confirm deactivate',
'common.activate.single.confirm':
'Are you sure you want to activate? \n <span style="font-size: 13px;font-weight: 700">{name}</span>',
'common.deactivate.single.confirm':
'Are you sure you want to deactivate? \n <span style="font-size: 13px;font-weight: 700">{name}</span>',
'common.title.recreate.confirm': 'Confirm recreate',
'common.button.addLabel': 'Add Label',
'common.button.addSelector': 'Add Selector',
+12 -5
View File
@@ -122,6 +122,10 @@ export default {
'gpuservice.instance.mode.whole': 'Full GPU',
'gpuservice.instance.mode.sliced': 'By Ratio',
'gpuservice.instance.slice.memoryPercentage': 'VRAM Percentage (%)',
'gpuservice.instance.slice.percentage': 'Percentage (%)',
'gpuservice.instance.slice.coresPercentage': 'Compute Percentage (%)',
'gpuservice.instance.slice.cores.min':
'The compute ratio must be no less than the VRAM ratio ({count}%)',
'gpuservice.instance.slice.fullCores': '100% Compute',
'gpuservice.instance.slice.percentage.required':
'Please select or enter a percentage',
@@ -134,10 +138,16 @@ export default {
'gpuservice.instance.ram': 'RAM',
'gpuservice.instance.os': 'OS',
'gpuservice.instance.arch': 'Arch',
'gpuservice.instanceType': 'GPU Instance Type',
'gpuservice.instanceType': 'GPU Instance Type',
'gpuservice.instanceType.add': 'Add Instance Type',
'gpuservice.instanceType.flavor': 'Flavor',
'gpuservice.instanceType.flavor.required': 'Please select an instance type flavor',
'gpuservice.instanceType.flavor.required':
'Please select an instance type flavor',
'gpuservice.instanceType.flavor.gpuGroup': 'GPU Compute',
'gpuservice.instanceType.flavor.cpuGroup': 'CPU Compute',
'gpuservice.instanceType.activate': 'Activate',
'gpuservice.instanceType.deactivate': 'Deactivate',
'gpuservice.instanceType.platform': 'Platform',
'gpuservice.instanceType.product': 'Product',
'gpuservice.instanceType.unitCpu': 'Unit CPU',
'gpuservice.instanceType.unitCpu.tip': 'CPU allocated per GPU',
@@ -168,9 +178,6 @@ export default {
'Only events from the last hour are shown',
'gpuservice.instance.event.tab.instance': 'Instance Events',
'gpuservice.instance.event.tab.volume': 'Volume Events',
'gpuservice.instance.recreate.confirm.title': 'Confirm recreation',
'gpuservice.instance.recreate.confirm.content':
'The current instance will be deleted first, then recreated with the current configuration.\n <span style="font-size: 13px;font-weight: 700">{name}</span>',
'gpuservice.storage': 'Storage',
'gpuservice.storage.add': 'Add Storage',
'gpuservice.storage.edit': 'Edit Storage',
+6
View File
@@ -221,6 +221,12 @@ export default {
'common.title.delete.confirm': '削除を確認',
'common.title.stop.confirm': '停止を確認',
'common.title.start.confirm': '開始を確認',
'common.title.activate.confirm': '有効化を確認',
'common.title.deactivate.confirm': '無効化を確認',
'common.activate.single.confirm':
'<span style="font-size: 13px;font-weight: 700">{name}</span> を有効化してもよろしいですか?',
'common.deactivate.single.confirm':
'<span style="font-size: 13px;font-weight: 700">{name}</span> を無効化してもよろしいですか?',
'common.title.recreate.confirm': '再作成を確認',
'common.button.addLabel': 'ラベルを追加',
'common.button.addSelector': 'セレクターを追加',
+12 -5
View File
@@ -121,6 +121,10 @@ export default {
'gpuservice.instance.mode.whole': 'GPU 全体',
'gpuservice.instance.mode.sliced': '比率で',
'gpuservice.instance.slice.memoryPercentage': 'VRAM の割合(%',
'gpuservice.instance.slice.percentage': '割合(%',
'gpuservice.instance.slice.coresPercentage': '演算能力の割合(%',
'gpuservice.instance.slice.cores.min':
'演算能力の割合は VRAM の割合({count}%)以上である必要があります',
'gpuservice.instance.slice.fullCores': '100% コンピュート',
'gpuservice.instance.slice.percentage.required':
'パーセンテージを選択または入力してください',
@@ -133,10 +137,16 @@ export default {
'gpuservice.instance.ram': 'RAM',
'gpuservice.instance.os': 'OS',
'gpuservice.instance.arch': 'アーキテクチャ',
'gpuservice.instanceType': 'GPU Instance Type',
'gpuservice.instanceType': 'GPU Instance Type',
'gpuservice.instanceType.add': 'Add Instance Type',
'gpuservice.instanceType.flavor': 'Flavor',
'gpuservice.instanceType.flavor.required': 'Please select an instance type flavor',
'gpuservice.instanceType.flavor.required':
'Please select an instance type flavor',
'gpuservice.instanceType.flavor.gpuGroup': 'GPU Compute',
'gpuservice.instanceType.flavor.cpuGroup': 'CPU Compute',
'gpuservice.instanceType.activate': 'Activate',
'gpuservice.instanceType.deactivate': 'Deactivate',
'gpuservice.instanceType.platform': 'Platform',
'gpuservice.instanceType.product': 'Product',
'gpuservice.instanceType.unitCpu': 'Unit CPU',
'gpuservice.instanceType.unitCpu.tip': 'CPU allocated per GPU',
@@ -167,9 +177,6 @@ export default {
'直近 1 時間のイベントのみ表示されます',
'gpuservice.instance.event.tab.instance': 'インスタンスイベント',
'gpuservice.instance.event.tab.volume': 'ボリュームイベント',
'gpuservice.instance.recreate.confirm.title': '再作成を確認しますか',
'gpuservice.instance.recreate.confirm.content':
'現在のインスタンスを削除した後、現在の構成で再作成します。\n <span style="font-size: 13px;font-weight: 700">{name}</span>',
'gpuservice.storage': 'ストレージ',
'gpuservice.storage.add': 'ストレージを追加',
'gpuservice.storage.edit': 'ストレージを編集',
+6
View File
@@ -219,6 +219,12 @@ export default {
'common.title.delete.confirm': 'Подтверждение удаления',
'common.title.stop.confirm': 'Подтверждение остановки',
'common.title.start.confirm': 'Подтверждение запуска',
'common.title.activate.confirm': 'Подтверждение активации',
'common.title.deactivate.confirm': 'Подтверждение деактивации',
'common.activate.single.confirm':
'Вы уверены, что хотите активировать <span style="font-size: 13px;font-weight: 700">{name}</span>?',
'common.deactivate.single.confirm':
'Вы уверены, что хотите деактивировать <span style="font-size: 13px;font-weight: 700">{name}</span>?',
'common.title.recreate.confirm': 'Подтверждение пересоздания',
'common.button.addLabel': 'Добавить метку',
'common.button.addSelector': 'Добавить селектор',
+12 -5
View File
@@ -120,6 +120,10 @@ export default {
'gpuservice.instance.mode.whole': 'Весь GPU',
'gpuservice.instance.mode.sliced': 'По доле',
'gpuservice.instance.slice.memoryPercentage': 'Доля VRAM (%)',
'gpuservice.instance.slice.percentage': 'Доля (%)',
'gpuservice.instance.slice.coresPercentage': 'Доля вычислений (%)',
'gpuservice.instance.slice.cores.min':
'Доля вычислений должна быть не меньше доли VRAM ({count}%)',
'gpuservice.instance.slice.fullCores': '100% вычислений',
'gpuservice.instance.slice.percentage.required':
'Выберите или введите процент',
@@ -132,10 +136,16 @@ export default {
'gpuservice.instance.ram': 'RAM',
'gpuservice.instance.os': 'ОС',
'gpuservice.instance.arch': 'Архитектура',
'gpuservice.instanceType': 'GPU Instance Type',
'gpuservice.instanceType': 'GPU Instance Type',
'gpuservice.instanceType.add': 'Add Instance Type',
'gpuservice.instanceType.flavor': 'Flavor',
'gpuservice.instanceType.flavor.required': 'Please select an instance type flavor',
'gpuservice.instanceType.flavor.required':
'Please select an instance type flavor',
'gpuservice.instanceType.flavor.gpuGroup': 'GPU Compute',
'gpuservice.instanceType.flavor.cpuGroup': 'CPU Compute',
'gpuservice.instanceType.activate': 'Activate',
'gpuservice.instanceType.deactivate': 'Deactivate',
'gpuservice.instanceType.platform': 'Platform',
'gpuservice.instanceType.product': 'Product',
'gpuservice.instanceType.unitCpu': 'Unit CPU',
'gpuservice.instanceType.unitCpu.tip': 'CPU allocated per GPU',
@@ -166,9 +176,6 @@ export default {
'Отображаются только события за последний час',
'gpuservice.instance.event.tab.instance': 'События экземпляра',
'gpuservice.instance.event.tab.volume': 'События тома',
'gpuservice.instance.recreate.confirm.title': 'Подтвердить пересоздание',
'gpuservice.instance.recreate.confirm.content':
'Текущий экземпляр будет сначала удалён, а затем пересоздан с текущей конфигурацией.\n <span style="font-size: 13px;font-weight: 700">{name}</span>',
'gpuservice.storage': 'Хранилище',
'gpuservice.storage.add': 'Добавить хранилище',
'gpuservice.storage.edit': 'Редактировать хранилище',
+6
View File
@@ -224,6 +224,12 @@ export default {
'common.title.delete.confirm': 'Silme onayı',
'common.title.stop.confirm': 'Durdurma onayı',
'common.title.start.confirm': 'Başlatma onayı',
'common.title.activate.confirm': 'Etkinleştirme onayı',
'common.title.deactivate.confirm': 'Devre dışı bırakma onayı',
'common.activate.single.confirm':
'Etkinleştirmek istediğinizden emin misiniz? \n <span style="font-size: 13px;font-weight: 700">{name}</span>',
'common.deactivate.single.confirm':
'Devre dışı bırakmak istediğinizden emin misiniz? \n <span style="font-size: 13px;font-weight: 700">{name}</span>',
'common.title.recreate.confirm': 'Yeniden oluşturma onayı',
'common.button.addLabel': 'Etiket Ekle',
'common.button.addSelector': 'Seçici Ekle',
+12 -6
View File
@@ -116,6 +116,10 @@ export default {
'gpuservice.instance.mode.whole': 'Tam GPU',
'gpuservice.instance.mode.sliced': 'Orana Göre',
'gpuservice.instance.slice.memoryPercentage': 'VRAM Yüzdesi (%)',
'gpuservice.instance.slice.percentage': 'Yüzde (%)',
'gpuservice.instance.slice.coresPercentage': 'İşlem Gücü Yüzdesi (%)',
'gpuservice.instance.slice.cores.min':
'İşlem gücü oranı VRAM oranından ({count}%) küçük olamaz',
'gpuservice.instance.slice.fullCores': '%100 İşlem Gücü',
'gpuservice.instance.slice.percentage.required':
'Lütfen bir yüzde seçin veya girin',
@@ -128,10 +132,16 @@ export default {
'gpuservice.instance.ram': 'RAM',
'gpuservice.instance.os': 'OS',
'gpuservice.instance.arch': 'Mimari',
'gpuservice.instanceType': 'GPU Instance Type',
'gpuservice.instanceType': 'GPU Instance Type',
'gpuservice.instanceType.add': 'Add Instance Type',
'gpuservice.instanceType.flavor': 'Flavor',
'gpuservice.instanceType.flavor.required': 'Please select an instance type flavor',
'gpuservice.instanceType.flavor.required':
'Please select an instance type flavor',
'gpuservice.instanceType.flavor.gpuGroup': 'GPU Compute',
'gpuservice.instanceType.flavor.cpuGroup': 'CPU Compute',
'gpuservice.instanceType.activate': 'Activate',
'gpuservice.instanceType.deactivate': 'Deactivate',
'gpuservice.instanceType.platform': 'Platform',
'gpuservice.instanceType.product': 'Product',
'gpuservice.instanceType.unitCpu': 'Unit CPU',
'gpuservice.instanceType.unitCpu.tip': 'CPU allocated per GPU',
@@ -162,10 +172,6 @@ export default {
'Yalnızca son bir saatteki olaylar gösterilir',
'gpuservice.instance.event.tab.instance': 'Örnek Olayları',
'gpuservice.instance.event.tab.volume': 'Birim Olayları',
'gpuservice.instance.recreate.confirm.title':
'Yeniden oluşturma onaylansın mı',
'gpuservice.instance.recreate.confirm.content':
'Mevcut örnek önce silinecek, ardından mevcut yapılandırmayla yeniden oluşturulacaktır.\n <span style="font-size: 13px;font-weight: 700">{name}</span>',
'gpuservice.storage': 'Depolama',
'gpuservice.storage.add': 'Depolama Ekle',
'gpuservice.storage.edit': 'Depolamayı Düzenle',
+6
View File
@@ -212,6 +212,12 @@ export default {
'common.title.delete.confirm': '确认删除',
'common.title.stop.confirm': '确认停止',
'common.title.start.confirm': '确认启动',
'common.title.activate.confirm': '确认启用',
'common.title.deactivate.confirm': '确认停用',
'common.activate.single.confirm':
'确定启用 <span style="font-size: 13px;font-weight: 700">{name}</span>',
'common.deactivate.single.confirm':
'确定停用 <span style="font-size: 13px;font-weight: 700">{name}</span>',
'common.title.recreate.confirm': '确认重新创建',
'common.button.addLabel': '添加标签',
'common.button.addSelector': '添加选择器',
+9 -4
View File
@@ -111,6 +111,9 @@ export default {
'gpuservice.instance.mode.whole': '整卡',
'gpuservice.instance.mode.sliced': '按比例',
'gpuservice.instance.slice.memoryPercentage': '显存占比(%',
'gpuservice.instance.slice.percentage': '占比(%',
'gpuservice.instance.slice.coresPercentage': '算力占比(%',
'gpuservice.instance.slice.cores.min': '算力占比需不小于显存占比 {count}%',
'gpuservice.instance.slice.fullCores': '100% 算力',
'gpuservice.instance.slice.percentage.required': '请选择或输入百分比',
'gpuservice.instance.slice.percentage.max': '比例需在 1% 到 {count}% 之间',
@@ -121,10 +124,15 @@ export default {
'gpuservice.instance.ram': '内存',
'gpuservice.instance.os': '系统',
'gpuservice.instance.arch': '架构',
'gpuservice.instanceType': 'GPU 实例类型',
'gpuservice.instanceType': 'GPU 实例类型',
'gpuservice.instanceType.add': '添加实例类型',
'gpuservice.instanceType.flavor': '规格',
'gpuservice.instanceType.flavor.required': '请选择实例类型规格',
'gpuservice.instanceType.flavor.gpuGroup': 'GPU 算力',
'gpuservice.instanceType.flavor.cpuGroup': 'CPU 算力',
'gpuservice.instanceType.activate': '启用',
'gpuservice.instanceType.deactivate': '停用',
'gpuservice.instanceType.platform': '平台',
'gpuservice.instanceType.product': '商品',
'gpuservice.instanceType.unitCpu': '单位 CPU',
'gpuservice.instanceType.unitCpu.tip': '每 GPU 对应多少 CPU',
@@ -154,9 +162,6 @@ export default {
'gpuservice.instance.event.recentHourTip': '仅显示最近一小时的事件。',
'gpuservice.instance.event.tab.instance': '实例事件',
'gpuservice.instance.event.tab.volume': '存储卷事件',
'gpuservice.instance.recreate.confirm.title': '确认重新创建',
'gpuservice.instance.recreate.confirm.content':
'系统将先删除当前实例,然后使用当前配置重新创建。\n <span style="font-size: 13px;font-weight: 700">{name}</span>',
'gpuservice.storage': '存储',
'gpuservice.storage.add': '添加存储',
'gpuservice.storage.edit': '编辑存储',
@@ -153,7 +153,7 @@ const useClusterColumns = (
span: 3,
render: (text: string, record: ClusterListItem) => (
<>
<AutoTooltip ghost title={text}>
<AutoTooltip ghost title={text} minWidth={20}>
<span className="text-primary">{record.name}</span>
</AutoTooltip>
{record.is_default && (
@@ -186,23 +186,24 @@ const useClusterColumns = (
{
title: intl.formatMessage({ id: 'dashboard.totalgpus' }),
dataIndex: 'gpus',
span: 2,
sorter: tableSorter(3),
width: 100,
sorter: tableSorter(3),
render: (value: number) => <span>{value}</span>
},
{
title: intl.formatMessage({ id: 'clusters.table.deployments' }),
dataIndex: 'models',
sorter: tableSorter(4),
width: 100,
span: spans.deployments,
maxWidth: 150,
render: (value: number) => <span>{value}</span>
},
{
title: intl.formatMessage({ id: 'resources.nodes' }),
dataIndex: 'workers',
minWidth: 100,
maxWidth: 120,
sorter: tableSorter(5),
width: 100,
render: (value: number, record: ClusterListItem) => (
<span>
{record.ready_workers} / {record.workers}
@@ -213,6 +214,7 @@ const useClusterColumns = (
title: intl.formatMessage({ id: 'common.table.status' }),
dataIndex: 'state',
span: spans.status,
minWidth: 80,
align: 'center',
render: (value: number, record: ClusterListItem) => (
<StatusTag
@@ -52,3 +52,25 @@ export async function deleteGPUInstanceType(params: {
params: { cluster_id: params.cluster_id }
});
}
// PUT /gpu-instance-types/{name}/activate?cluster_id — activate an instance type.
export async function activateGPUInstanceType(params: {
name: string;
cluster_id: number;
}) {
return request(`${GPU_INSTANCE_TYPES_API}/${params.name}/activate`, {
method: 'PUT',
params: { cluster_id: params.cluster_id }
});
}
// PUT /gpu-instance-types/{name}/deactivate?cluster_id — deactivate an instance type.
export async function deactivateGPUInstanceType(params: {
name: string;
cluster_id: number;
}) {
return request(`${GPU_INSTANCE_TYPES_API}/${params.name}/deactivate`, {
method: 'PUT',
params: { cluster_id: params.cluster_id }
});
}
@@ -1,14 +1,11 @@
import useSubmitLock from '@/hooks/use-submit-lock';
import Separator from '@/pages/llmodels/components/separator';
import { ColumnWrapper, GSDrawer, ModalFooter } from '@gpustack/core-ui';
import { useIntl } from '@umijs/max';
import { Typography, message } from 'antd';
import { message } from 'antd';
import { useEffect, useRef, useState } from 'react';
import { FlavorItem, FormData } from '../config/types';
import GPUServiceInstanceTypeForm from '../forms';
import useQueryFlavors from '../services/use-query-flavors';
import styles from '../styles/instance-types.module.less';
import FlavorList from './flavor-list';
type AddInstanceTypeModalProps = {
title: string;
@@ -18,28 +15,6 @@ type AddInstanceTypeModalProps = {
onCancel: () => void;
};
const ColTitle: React.FC<{
children: React.ReactNode;
style?: React.CSSProperties;
}> = ({ children, style }) => (
<Typography.Title
level={3}
style={{
fontSize: 14,
paddingTop: 10,
paddingBottom: 16,
margin: 0,
position: 'sticky',
top: 0,
zIndex: 100,
backgroundColor: 'var(--ant-color-bg-elevated)',
...style
}}
>
{children}
</Typography.Title>
);
const AddInstanceTypeModal: React.FC<AddInstanceTypeModalProps> = ({
title,
open,
@@ -101,63 +76,37 @@ const AddInstanceTypeModal: React.FC<AddInstanceTypeModalProps> = ({
mask={{ closable: false }}
keyboard={false}
styles={{
wrapper: { width: 'min(900px, calc(100vw - 220px))' },
wrapper: { width: 'min(600px, calc(100vw - 220px))' },
body: { overflowY: 'hidden' }
}}
footer={false}
>
<div className={styles.container}>
<div className={styles.colWrapper}>
<ColumnWrapper styles={{ container: { paddingBlock: 0 } }}>
<div className={styles.panelBody}>
<div className={styles.stickyHead}>
<ColTitle
style={{
paddingBottom: 0
}}
>
{intl.formatMessage({ id: 'gpuservice.instanceType.flavor' })}
</ColTitle>
</div>
<FlavorList
value={selectedFlavor?.name}
dataList={flavorList}
loading={flavorLoading}
onChange={setSelectedFlavor}
/>
</div>
</ColumnWrapper>
<Separator />
</div>
<div className={styles.formWrapper}>
<ColumnWrapper
styles={{ container: { paddingBlock: 0 } }}
footer={
<ModalFooter
onOk={handleSubmit}
onCancel={handleCancel}
loading={loading}
style={{
padding: '16px 24px 8px',
display: 'flex',
justifyContent: 'flex-end'
}}
/>
}
>
<ColTitle>
{intl.formatMessage({ id: 'common.title.config' })}
</ColTitle>
<GPUServiceInstanceTypeForm
ref={form}
open={open}
selectedFlavor={selectedFlavor}
onFinish={onFinish}
onFinishFailed={release}
/>
</ColumnWrapper>
</div>
</div>
<ColumnWrapper
styles={{ container: { paddingBlock: 0 } }}
footer={
<ModalFooter
onOk={handleSubmit}
onCancel={handleCancel}
loading={loading}
style={{
padding: '16px 24px 8px',
display: 'flex',
justifyContent: 'flex-end'
}}
/>
}
>
<GPUServiceInstanceTypeForm
ref={form}
open={open}
selectedFlavor={selectedFlavor}
flavorList={flavorList}
flavorLoading={flavorLoading}
onFlavorChange={setSelectedFlavor}
onFinish={onFinish}
onFinishFailed={release}
/>
</ColumnWrapper>
</GSDrawer>
);
};
@@ -0,0 +1,118 @@
import { AutoTooltip, ThemeTag } from '@gpustack/core-ui';
import { useIntl } from '@umijs/max';
import { Flex } from 'antd';
import { formatMemoryDisplay } from '../../instances/config';
import { manufactureColorMap } from '../../templates/config';
import { formatManufacturer } from '../../utils';
// The subset of a flavor / instance-type display shape the flavor renderers
// read. Flavor specs satisfy it directly (minus sliceable, which the API
// removed from flavors); the management list builds it from spec.acceleratable
// + status.detail, deriving sliceable from slicedDetail.
interface FlavorSpecLike {
manufacturer?: string | null;
product?: string | null;
memory?: string | null;
sliceable?: boolean;
acceleratable?: boolean;
}
// A flavor's title mirrors the flavor card: a generic (no product, no/`generic`
// manufacturer, non-acceleratable) flavor reads as "CPU-only".
export const getFlavorTitle = (
spec: FlavorSpecLike = {},
fallbackName?: string | null
) => {
const manufacturer = spec.manufacturer || '';
const isCpuOnly =
!spec.acceleratable &&
!spec.product &&
(!manufacturer || manufacturer.toLowerCase() === 'generic');
return isCpuOnly ? 'CPU-only' : spec.product || fallbackName || '-';
};
// Secondary line, dot-separated: manufacturer · memory · sliceable. memory and
// sliceable apply to accelerator (GPU) flavors only; sliceable stays a tag.
// Returns null when a (generic) flavor has nothing to show.
export const FlavorMeta: React.FC<{ spec?: FlavorSpecLike }> = ({
spec = {}
}) => {
const intl = useIntl();
const manufacturer = spec.manufacturer || '';
const color = manufactureColorMap[manufacturer] ?? 'purple';
const memory = spec.acceleratable
? formatMemoryDisplay(spec.memory ?? undefined)
: '';
const pieces: React.ReactNode[] = [];
if (manufacturer) {
pieces.push(
<ThemeTag
key="vendor"
color={color}
style={{ fontWeight: 400, marginInlineEnd: 0 }}
>
{formatManufacturer(manufacturer)}
</ThemeTag>
);
}
if (memory) {
pieces.push(<span key="memory">{memory}</span>);
}
if (!pieces.length) return null;
return (
<Flex
align="center"
gap={8}
style={{
minWidth: 0,
color: 'var(--ant-color-text-tertiary)',
fontSize: 12
}}
>
{pieces.flatMap((piece, index) =>
index === 0
? [piece]
: [
<span
key={`dot-${index}`}
style={{ color: 'var(--ant-color-text-quaternary)' }}
>
·
</span>,
piece
]
)}
</Flex>
);
};
// Two-line flavor display: title on top, meta row below. Shared by the create
// drawer's dropdown option and the management list's flavor cell.
export const FlavorOption: React.FC<{
spec?: FlavorSpecLike;
fallbackName?: string | null;
maxWidth?: number | string;
}> = ({ spec = {}, fallbackName, maxWidth = '100%' }) => (
<Flex vertical gap={4} style={{ minWidth: 0, padding: '2px 0' }}>
<AutoTooltip ghost minWidth={20} maxWidth={maxWidth}>
{getFlavorTitle(spec, fallbackName)}
</AutoTooltip>
<FlavorMeta spec={spec} />
</Flex>
);
// Single-line flavor display: title then meta inline. Used for the collapsed
// selected value in the create drawer's Select.
export const FlavorSelected: React.FC<{
spec?: FlavorSpecLike;
fallbackName?: string | null;
}> = ({ spec = {}, fallbackName }) => (
<Flex align="center" gap={8} style={{ minWidth: 0 }}>
<AutoTooltip ghost minWidth={20} maxWidth={200}>
{getFlavorTitle(spec, fallbackName)}
</AutoTooltip>
<FlavorMeta spec={spec} />
</Flex>
);
@@ -94,8 +94,10 @@ const FlavorList: React.FC<FlavorListProps> = ({
</ThemeTag>
)}
</Flex>
{/* Memory / sliceable only apply to accelerator (GPU) flavors;
a non-acceleratable (generic) flavor has neither. */}
{/* Memory only applies to accelerator (GPU) flavors; a
non-acceleratable (generic) flavor has none. (Sliceable is no
longer a flavor field — it is observed per instance type on
status.detail.slicedDetail.) */}
{spec.acceleratable && (
<Flex wrap gap={16}>
<MetaItem
@@ -105,17 +107,6 @@ const FlavorList: React.FC<FlavorListProps> = ({
})}
value={formatMemoryDisplay(spec.memory ?? undefined) ?? '-'}
/>
<MetaItem
icon="icon-sliced"
label={intl.formatMessage({
id: 'gpuservice.instance.sliceable'
})}
value={
spec.sliceable
? intl.formatMessage({ id: 'common.table.yes' })
: intl.formatMessage({ id: 'common.table.no' })
}
/>
</Flex>
)}
</Flex>
@@ -9,7 +9,7 @@ import {
import { useIntl } from '@umijs/max';
import { Button } from 'antd';
import _ from 'lodash';
import { formatMemoryDisplay } from '../../instances/config';
import { formatMemoryDisplay, isSliceableDetail } from '../../instances/config';
import { manufactureColorMap } from '../../templates/config';
import { ceilMilliToCore, parseQuantityToGi } from '../../utils';
import {
@@ -31,12 +31,16 @@ const InstanceTypeCard: React.FC<InstanceTypeCardProps> = ({
}) => {
const intl = useIntl();
const spec = data.spec || {};
// Observed hardware (manufacturer / memory / sliced capability, …) comes
// from status.detail and may be absent until the operator backfills status.
const detail = data.status?.detail || {};
const unit = spec.unitResources || {};
const phase = data.status?.phase || '';
const manufacturer = spec.manufacturer || '';
const manufacturer = detail.manufacturer || '';
const manufacturerColor = manufactureColorMap[manufacturer] ?? 'purple';
const sliceable = isSliceableDetail(detail.slicedDetail);
const memoryText = formatMemoryDisplay(spec.memory ?? undefined);
const memoryText = formatMemoryDisplay(detail.memory ?? undefined);
// Base resources, formatted into a single "·"-separated line. Falsy parts
// (e.g. a CPU-only type without VRAM) drop out rather than showing "-".
@@ -71,7 +75,7 @@ const InstanceTypeCard: React.FC<InstanceTypeCardProps> = ({
<div className={styles.header}>
<span className={styles.product}>
<AutoTooltip ghost minWidth={20}>
{spec.product || data.name || '-'}
{detail.product || data.name || '-'}
</AutoTooltip>
</span>
<span className={styles.headerRight}>
@@ -115,13 +119,13 @@ const InstanceTypeCard: React.FC<InstanceTypeCardProps> = ({
}}
/>
) : null}
{spec.clockSpeed ? <span>{spec.clockSpeed}</span> : null}
{detail.clockSpeed ? <span>{detail.clockSpeed}</span> : null}
<span
className={`${styles.tag} ${
spec.sliceable ? styles.tagSliceable : styles.tagPlain
sliceable ? styles.tagSliceable : styles.tagPlain
}`}
>
{spec.sliceable
{sliceable
? intl.formatMessage({ id: 'gpuservice.instance.sliceable' })
: intl.formatMessage({
id: 'gpuservice.instanceType.notSliceable'
@@ -8,24 +8,24 @@ export const GPU_INSTANCE_TYPE_OS = 'linux';
export const InstanceTypePhaseValueMap = {
Active: 'Active',
Inactive: 'Inactive',
Preparing: 'Preparing'
Draining: 'Draining'
};
export const InstanceTypePhaseLabelMap: Record<string, string> = {
[InstanceTypePhaseValueMap.Active]: 'Active',
[InstanceTypePhaseValueMap.Inactive]: 'Inactive',
[InstanceTypePhaseValueMap.Preparing]: 'Preparing'
[InstanceTypePhaseValueMap.Draining]: 'Draining'
};
export const status: Record<string, StatusType> = {
[InstanceTypePhaseValueMap.Active]: StatusMaps.success,
[InstanceTypePhaseValueMap.Inactive]: StatusMaps.inactive,
[InstanceTypePhaseValueMap.Preparing]: StatusMaps.transitioning
[InstanceTypePhaseValueMap.Draining]: StatusMaps.transitioning
};
export const ArchOptions = [
{ label: 'amd64', value: 'amd64' },
{ label: 'arm64', value: 'arm64' }
{ label: 'AMD64', value: 'amd64' },
{ label: 'ARM64', value: 'arm64' }
];
// ``icon`` is narrowed to ``any`` so the inferred type doesn't reach into
@@ -1,16 +1,17 @@
import {
InstanceTypeDetail,
InstanceTypeResource
} from '../../instances/config/types';
export interface UnitResources {
cpu?: string | null;
ram?: string | null;
}
// spec carries user-defined fields only; observed hardware (manufacturer,
// memory, sliced capability, …) lives on status.detail.
export interface InstanceTypeSpec {
manufacturer?: string | null;
product?: string | null;
family?: string | null;
memory?: string | null;
cores?: string | null;
clockSpeed?: string | null;
sliceable?: boolean;
displayName?: string | null;
os?: string | null;
arch?: string | null;
acceleratable?: boolean;
@@ -21,8 +22,15 @@ export interface InstanceTypeSpec {
}
export interface InstanceTypeStatus {
// Observed hardware descriptor; absent until the operator backfills status.
detail?: InstanceTypeDetail | null;
phase?: string | null;
phaseMessage?: string | null;
// Per-mode resource accounting ({onceMaxRequest, remaining, capacity}).
accelerator?: InstanceTypeResource | null;
acceleratorShared?: InstanceTypeResource | null;
acceleratorSliced?: InstanceTypeResource | null;
cpu?: InstanceTypeResource | null;
}
// Row shape for the management list (GET /gpu-instance-types).
@@ -43,7 +51,6 @@ export interface FlavorItem {
family?: string | null;
memory?: string | null;
cores?: string | null;
sliceable?: boolean;
acceleratable?: boolean;
acceleratorGroup?: string | null;
generalGroup?: string | null;
@@ -54,6 +61,7 @@ export interface FlavorItem {
export interface FormData {
name: string;
spec: {
displayName?: string | null;
acceleratorGroup?: string | null;
generalGroup?: string | null;
acceleratable?: boolean;
@@ -8,8 +8,14 @@ import {
import { useIntl } from '@umijs/max';
import { Form } from 'antd';
import { forwardRef, useEffect, useImperativeHandle } from 'react';
import {
FlavorOption,
FlavorSelected,
getFlavorTitle
} from '../components/flavor-display';
import { ArchOptions, GPU_INSTANCE_TYPE_OS } from '../config';
import { FlavorItem, FormData } from '../config/types';
import styles from '../styles/instance-types.module.less';
// RAM / storage are entered as a plain number in GB but stored/submitted as a
// "Gi" quantity string. These drive the FormItem's submit (`normalize`) and
@@ -23,16 +29,27 @@ const giValueProps = (value?: string | null) => ({
interface InstanceTypeFormProps {
ref?: any;
open: boolean;
// The flavor picked in the drawer's first column. Its acceleratorGroup /
// The flavor picked from the flavor Select. Its acceleratorGroup /
// generalGroup / acceleratable are copied into the created instance type.
selectedFlavor?: FlavorItem | null;
flavorList: FlavorItem[];
flavorLoading?: boolean;
onFlavorChange: (flavor: FlavorItem | null) => void;
onFinish: (values: FormData) => Promise<void>;
onFinishFailed?: (errorInfo: any) => void;
}
const GPUServiceInstanceTypeForm: React.FC<InstanceTypeFormProps> = forwardRef(
(props, ref) => {
const { open, selectedFlavor, onFinish, onFinishFailed } = props;
const {
open,
selectedFlavor,
flavorList,
flavorLoading,
onFlavorChange,
onFinish,
onFinishFailed
} = props;
const intl = useIntl();
const { getRuleMessage } = useAppUtils();
const [form] = Form.useForm<FormData>();
@@ -68,6 +85,36 @@ const GPUServiceInstanceTypeForm: React.FC<InstanceTypeFormProps> = forwardRef(
}
}));
// Split flavors into two groups: CPU compute (generic) and GPU compute
// (accelerator). Groups render as labeled sections in the dropdown.
const toFlavorOption = (flavor: FlavorItem) => ({
value: flavor.name,
label: getFlavorTitle(flavor.spec, flavor.name),
flavor
});
const cpuFlavors = flavorList.filter(
(flavor) => !flavor.spec?.acceleratable
);
const gpuFlavors = flavorList.filter(
(flavor) => flavor.spec?.acceleratable
);
const flavorOptions = [
cpuFlavors.length && {
label: intl.formatMessage({
id: 'gpuservice.instanceType.flavor.cpuGroup'
}),
title: 'cpu',
options: cpuFlavors.map(toFlavorOption)
},
gpuFlavors.length && {
label: intl.formatMessage({
id: 'gpuservice.instanceType.flavor.gpuGroup'
}),
title: 'gpu',
options: gpuFlavors.map(toFlavorOption)
}
].filter(Boolean) as any;
const handleFinish = async (values: FormData) => {
// The hardware group / acceleratable flags are not user-editable; they
// come from the chosen flavor. os is fixed to lowercase "linux". ram /
@@ -76,6 +123,7 @@ const GPUServiceInstanceTypeForm: React.FC<InstanceTypeFormProps> = forwardRef(
await onFinish({
name: values.name,
spec: {
displayName: values.spec?.displayName?.trim() || null,
acceleratorGroup: selectedFlavor?.spec?.acceleratorGroup ?? null,
generalGroup: selectedFlavor?.spec?.generalGroup ?? null,
acceleratable: selectedFlavor?.spec?.acceleratable ?? false,
@@ -117,6 +165,57 @@ const GPUServiceInstanceTypeForm: React.FC<InstanceTypeFormProps> = forwardRef(
/>
</Form.Item>
<Form.Item<FormData>
name={['spec', 'displayName']}
rules={[
{
max: 63,
message: intl.formatMessage({
id: 'gpuservice.template.displayName.max'
})
}
]}
>
<CInput.Input
trim={false}
label={intl.formatMessage({
id: 'gpuservice.template.displayName'
})}
/>
</Form.Item>
<Form.Item>
<SealSelect
label={intl.formatMessage({ id: 'gpuservice.instanceType.flavor' })}
required
showSearch
optionFilterProp="label"
classNames={{ popup: { root: styles.flavorDropdown } }}
loading={flavorLoading}
value={selectedFlavor?.name}
options={flavorOptions}
onChange={(val: string) =>
onFlavorChange(
flavorList.find((flavor) => flavor.name === val) ?? null
)
}
optionRender={(option: any) => {
const flavor: FlavorItem = option.data.flavor;
return (
<FlavorOption spec={flavor.spec} fallbackName={flavor.name} />
);
}}
labelRender={({ value }) => {
const flavor = flavorList.find((item) => item.name === value);
return flavor ? (
<FlavorSelected spec={flavor.spec} fallbackName={flavor.name} />
) : (
((value ?? '') as React.ReactNode)
);
}}
/>
</Form.Item>
<Form.Item>
<CInput.Input
disabled
@@ -3,22 +3,21 @@ import {
AutoTooltip,
DropdownButtons,
icons,
StatusTag,
ThemeTag
StatusTag
} from '@gpustack/core-ui';
import { useIntl } from '@umijs/max';
import { Space, Tooltip } from 'antd';
import type { ColumnsType } from 'antd/lib/table';
import _ from 'lodash';
import { useMemo } from 'react';
import { formatMemoryDisplay } from '../../instances/config';
import { manufactureColorMap } from '../../templates/config';
import { isSliceableDetail } from '../../instances/config';
import { ceilMilliToCore, parseQuantityToGi } from '../../utils';
import { FlavorOption } from '../components/flavor-display';
import {
ceilMilliToCore,
formatManufacturer,
parseQuantityToGi
} from '../../utils';
import { InstanceTypePhaseLabelMap, status as phaseStatusMap } from '../config';
InstanceTypePhaseLabelMap,
InstanceTypePhaseValueMap,
status as phaseStatusMap
} from '../config';
import { ListItem } from '../config/types';
interface ColumnsHookProps {
@@ -26,16 +25,36 @@ interface ColumnsHookProps {
}
// DropdownButtons reads `locale` / `props` at runtime; its `items` prop is
// typed as antd's MenuProps['items'], so cast the config to satisfy it.
const rowActions = [
{
// typed as antd's MenuProps['items'], so cast the config to satisfy it. The
// activate / deactivate action is chosen from the row's current phase: Active
// types can be deactivated, Inactive ones activated (none while Preparing).
const buildRowActions = (record: ListItem) => {
const phase = record.status?.phase;
const actions: any[] = [];
if (phase === InstanceTypePhaseValueMap.Active) {
actions.push({
label: 'gpuservice.instanceType.deactivate',
key: 'deactivate',
locale: true,
icon: icons.Disabled
});
} else if (phase === InstanceTypePhaseValueMap.Inactive) {
actions.push({
label: 'gpuservice.instanceType.activate',
key: 'activate',
locale: true,
icon: icons.Charger
});
}
actions.push({
label: 'common.button.delete',
key: 'delete',
locale: true,
icon: icons.DeleteOutlined,
props: { danger: true }
}
] as any;
});
return actions;
};
// Column header with an info tooltip (used for the per-GPU resource columns).
const TitleWithTip: React.FC<{ title: string; tip: string }> = ({
@@ -64,61 +83,42 @@ const useInstanceTypeColumns = ({
dataIndex: 'name',
key: 'name',
ellipsis: { showTitle: false },
render: (text: string) => (
<AutoTooltip ghost maxWidth={240} title={text}>
<span className="text-primary">{text || '-'}</span>
</AutoTooltip>
)
// Prefer the friendly display name, fall back to the resource name.
render: (text: string, record: ListItem) => {
const label = record.spec?.displayName || text;
return (
<AutoTooltip ghost minWidth={20} maxWidth={200} title={label}>
<span className="text-primary">{label || '-'}</span>
</AutoTooltip>
);
}
},
{
title: intl.formatMessage({ id: 'gpuservice.instanceType.product' }),
dataIndex: ['spec', 'product'],
// Flavor cell mirrors the create drawer's dropdown: product name on
// top, manufacturer · memory · sliceable on the meta line below.
// Observed hardware comes from status.detail (absent until the
// operator backfills status); sliceable is derived from slicedDetail.
title: intl.formatMessage({ id: 'gpuservice.instanceType.flavor' }),
dataIndex: ['status', 'detail', 'product'],
key: 'product',
ellipsis: { showTitle: false },
render: (text: string) => (
<AutoTooltip ghost maxWidth={200}>
{text || '-'}
</AutoTooltip>
)
render: (_text: string, record: ListItem) => {
const detail = record.status?.detail;
return (
<FlavorOption
spec={{
acceleratable: record.spec?.acceleratable,
manufacturer: detail?.manufacturer,
product: detail?.product,
memory: detail?.memory,
sliceable: isSliceableDetail(detail?.slicedDetail)
}}
fallbackName={record.name}
maxWidth={200}
/>
);
}
},
{
title: intl.formatMessage({ id: 'resources.table.vendor' }),
dataIndex: ['spec', 'manufacturer'],
key: 'manufacturer',
ellipsis: { showTitle: false },
render: (value: string) =>
value ? (
<ThemeTag
color={manufactureColorMap[value] ?? 'purple'}
style={{ fontWeight: 400, width: 'fit-content' }}
>
{formatManufacturer(value)}
</ThemeTag>
) : (
'-'
)
},
{
title: intl.formatMessage({ id: 'gpuservice.instance.memory' }),
dataIndex: ['spec', 'memory'],
key: 'memory',
ellipsis: { showTitle: false },
// Non-acceleratable (generic) types have no VRAM concept → N/A.
render: (value: string, record: ListItem) =>
record.spec?.acceleratable
? formatMemoryDisplay(value ?? undefined) || '-'
: 'N/A'
},
// {
// title: intl.formatMessage({ id: 'gpuservice.instance.sliceable' }),
// dataIndex: ['spec', 'sliceable'],
// key: 'sliceable',
// ellipsis: { showTitle: false },
// render: (value: boolean) =>
// value
// ? intl.formatMessage({ id: 'common.table.yes' })
// : intl.formatMessage({ id: 'common.table.no' })
// },
{
title: (
<TitleWithTip
@@ -177,14 +177,22 @@ const useInstanceTypeColumns = ({
}
},
{
title: intl.formatMessage({ id: 'gpuservice.instance.os' }),
title: intl.formatMessage({ id: 'gpuservice.instanceType.platform' }),
key: 'os',
ellipsis: { showTitle: false },
render: (_text, record: ListItem) => {
const os = _.capitalize(record.spec?.os || '');
const arch = _.toUpper(record.spec?.arch || '');
if (!os) return '-';
return arch ? `${os} (${arch})` : os;
return (
<AutoTooltip
ghost
maxWidth={240}
title={arch ? `${os}/${arch}` : os}
>
{arch ? `${os}/${arch}` : os}
</AutoTooltip>
);
}
},
{
@@ -212,7 +220,7 @@ const useInstanceTypeColumns = ({
ellipsis: { showTitle: false },
render: (_text, record: ListItem) => (
<DropdownButtons
items={rowActions}
items={buildRowActions(record)}
onSelect={(val: string) => handleSelect(val, record)}
/>
)
+44 -4
View File
@@ -12,7 +12,11 @@ import { useMemoizedFn } from 'ahooks';
import { ConfigProvider, Divider, Flex, Table, message } from 'antd';
import { useEffect, useMemo, useRef, useState } from 'react';
import PageBox, { HeaderLeft } from '../../_components/page-box';
import { deleteGPUInstanceType } from './apis';
import {
activateGPUInstanceType,
deactivateGPUInstanceType,
deleteGPUInstanceType
} from './apis';
import AddInstanceTypeModal from './components/add-instance-type-modal';
import { FormData, ListItem } from './config/types';
import useCreateInstanceTypeModal from './hooks/use-create-instance-type-modal';
@@ -35,7 +39,8 @@ const GPUServiceInstanceTypes: React.FC = () => {
const {
dataList,
loading: instanceTypesLoading,
fetchInstanceTypes
fetchInstanceTypes,
startWatch
} = useQueryInstanceTypes();
const { fetchData: createInstanceType } = useCreateInstanceType();
const {
@@ -62,16 +67,18 @@ const GPUServiceInstanceTypes: React.FC = () => {
if (firstK8s?.id != null) {
setClusterId(firstK8s.id);
await fetchInstanceTypes(firstK8s.id);
startWatch(firstK8s.id);
}
setLoaded(true);
};
init();
}, []);
const handleClusterChange = useMemoizedFn((value: number) => {
const handleClusterChange = useMemoizedFn(async (value: number) => {
setClusterId(value);
setKeyword('');
fetchInstanceTypes(value);
await fetchInstanceTypes(value);
startWatch(value);
});
const handleRefresh = useMemoizedFn(() => {
@@ -120,9 +127,40 @@ const GPUServiceInstanceTypes: React.FC = () => {
});
});
const handleToggleActive = useMemoizedFn(
(record: ListItem, activate: boolean) => {
if (clusterId == null) return;
const action = activate
? activateGPUInstanceType
: deactivateGPUInstanceType;
deleteModalRef.current?.show({
content: intl.formatMessage({ id: 'gpuservice.instanceType' }),
title: activate
? 'common.title.activate.confirm'
: 'common.title.deactivate.confirm',
okText: activate
? 'gpuservice.instanceType.activate'
: 'gpuservice.instanceType.deactivate',
operation: activate
? 'common.activate.single.confirm'
: 'common.deactivate.single.confirm',
name: record.spec?.displayName || record.name,
async onOk() {
await action({ name: record.name, cluster_id: clusterId });
message.success(intl.formatMessage({ id: 'common.message.success' }));
fetchInstanceTypes(clusterId);
}
});
}
);
const handleSelect = useMemoizedFn((val: string, record: ListItem) => {
if (val === 'delete') {
handleDelete(record);
} else if (val === 'activate') {
handleToggleActive(record, true);
} else if (val === 'deactivate') {
handleToggleActive(record, false);
}
});
@@ -207,6 +245,8 @@ const GPUServiceInstanceTypes: React.FC = () => {
<Table
columns={columns}
dataSource={filteredList}
scroll={{ x: 'max-content' }}
className={'scroll-table'}
loading={{
spinning: instanceTypesLoading || clusterLoading,
size: 'middle'
@@ -1,15 +1,49 @@
import { createAxiosToken } from '@/hooks/use-chunk-request';
import { WatchEventType } from '@/config';
import useSetChunkRequest, {
createAxiosToken
} from '@/hooks/use-chunk-request';
import { useRequest } from 'ahooks';
import { CancelTokenSource } from 'axios';
import qs from 'query-string';
import { useEffect, useRef, useState } from 'react';
import { queryGPUInstanceTypes } from '../apis';
import { GPU_INSTANCE_TYPES_API, queryGPUInstanceTypes } from '../apis';
import { ListItem } from '../config/types';
// Merge a batch of watch events into the current name-keyed list. Instance
// types have no numeric id, so we upsert / remove by `name` rather than reuse
// the shared id-based chunked-list helper.
const mergeWatchEvents = (current: ListItem[], events: any[]) => {
let list = [...current];
events.forEach((event: any) => {
const collection: ListItem[] = event?.collection || [];
if (event?.type === WatchEventType.DELETE) {
const names = collection.map((item) => item.name);
list = list.filter((item) => !names.includes(item.name));
} else if (
event?.type === WatchEventType.CREATE ||
event?.type === WatchEventType.UPDATE
) {
collection.forEach((item) => {
const index = list.findIndex((it) => it.name === item.name);
if (index > -1) {
list[index] = item;
} else {
list = [item, ...list];
}
});
}
});
return list;
};
// Cluster-scoped instance types for the management list. Action-driven:
// call fetchInstanceTypes(clusterId) from the cluster picker / refresh, not
// via an effect dependency.
// via an effect dependency. startWatch(clusterId) opens a chunked watch that
// keeps the list in sync with live create/update/delete events.
export default function useQueryInstanceTypes() {
const tokenRef = useRef<CancelTokenSource | null>(null);
const chunkRequestRef = useRef<any>(null);
const { setChunkRequest } = useSetChunkRequest();
const [dataList, setDataList] = useState<ListItem[]>([]);
const {
@@ -43,10 +77,27 @@ export default function useQueryInstanceTypes() {
tokenRef.current?.cancel('CANCEL_PREVIOUS_REQUEST');
};
const stopWatch = () => {
chunkRequestRef.current?.current?.cancel?.();
};
const startWatch = (clusterId: number) => {
stopWatch();
chunkRequestRef.current = setChunkRequest({
url: `${GPU_INSTANCE_TYPES_API}?${qs.stringify({
cluster_id: clusterId
})}`,
handler: (events: any[]) => {
setDataList((pre) => mergeWatchEvents(pre, events));
}
});
};
useEffect(() => {
return () => {
cancel();
tokenRef.current?.cancel();
stopWatch();
};
}, []);
@@ -55,6 +106,8 @@ export default function useQueryInstanceTypes() {
loading,
fetchInstanceTypes,
cancelRequest,
startWatch,
stopWatch,
setDataList
};
}
@@ -42,6 +42,24 @@
min-height: 96px;
}
// ============ flavor select dropdown ============
.flavorDropdown {
:global {
// tighten the indent of grouped options
.ant-select-item-option-grouped {
padding-inline-start: 12px;
}
// divider between options
.ant-select-item-option {
border-block-end: 1px solid var(--ant-color-border-secondary);
&:last-child {
border-block-end: none;
}
}
}
}
// ============ list card (Linear-style, minimal) ============
.listCard {
height: auto !important;
@@ -5,23 +5,19 @@ import useUserDirectory from '@/pages/gpu-service/hooks/use-user-directory';
import Separator from '@/pages/llmodels/components/separator';
import { getGPUStackPlugin } from '@/plugins';
import { SearchOutlined } from '@ant-design/icons';
import {
AlertBlockInfo,
ColumnWrapper,
GSDrawer,
ModalFooter
} from '@gpustack/core-ui';
import { ColumnWrapper, GSDrawer, ModalFooter } from '@gpustack/core-ui';
import { useIntl, useModel } from '@umijs/max';
import { Input, Typography } from 'antd';
import _ from 'lodash';
import { useEffect, useMemo, useRef, useState } from 'react';
import { ListItem as TemplateItem } from '../../templates/config/types';
import useQueryTemplates from '../../templates/services/use-query-templates';
import { InstanceStatusValueMap } from '../config';
import { FormData, InstanceTypeItem, ListItem } from '../config/types';
import GPUServiceInstanceForm from '../forms';
import TemplateSelector, { TemplateGroup } from '../forms/template-selector';
import useQueryInstanceTypes from '../services/use-query-instance-types';
import styles from '../styles/instances.module.less';
import { saveInstanceDataInDescription } from '../utils/instance-description';
import InstanceTypeList from './instance-type-list';
type AddModalProps = {
@@ -29,7 +25,6 @@ type AddModalProps = {
action: PageActionType;
open: boolean;
width?: number | string;
realAction?: string;
clusterList?: Array<{
label: string;
value: number;
@@ -83,8 +78,7 @@ const AddModal: React.FC<AddModalProps> = ({
data,
onCancel,
width,
clusterList = [],
realAction
clusterList = []
}) => {
const intl = useIntl();
const { initialState } = useModel('@@initialState') || {};
@@ -103,6 +97,12 @@ const AddModal: React.FC<AddModalProps> = ({
manufacturer: undefined
});
const [templateId, setTemplateId] = useState<number | undefined>();
// Re-selected instance type on a stopped-instance edit. Kept separate from
// `instanceTypeSelection` (the create card selection) so the two flows don't
// couple; starts empty each open (no default highlight).
const [editSelectedType, setEditSelectedType] = useState<string | undefined>(
undefined
);
const [instanceKeyword, setInstanceKeyword] = useState('');
const [templateKeyword, setTemplateKeyword] = useState('');
const { loading, guard, run, release } = useSubmitLock();
@@ -166,9 +166,18 @@ const AddModal: React.FC<AddModalProps> = ({
);
// const readonly = action === PageAction.VIEW;
const readonly = false;
const isRecreate = realAction === PageAction.CREATE;
const showResourceSelectors = action === PageAction.CREATE || isRecreate;
const shouldAutoSelectResource = action === PageAction.CREATE && !isRecreate;
const showResourceSelectors = action === PageAction.CREATE;
// Only a stopped instance can be re-typed on edit. It shows the instance-type
// column (but not the template column) beside the form; the create card
// columns render for CREATE.
const isStoppedEdit =
action === PageAction.EDIT &&
data?.status?.phase === InstanceStatusValueMap.Stopped;
const showInstanceTypeColumn = showResourceSelectors || isStoppedEdit;
// Editing a non-stopped instance is restricted: only displayName and the
// SSH public keys stay editable; the type / template / storage sections
// render disabled. A stopped instance edits everything.
const isRestrictedEdit = action === PageAction.EDIT && !isStoppedEdit;
const findTemplateByManufacturer = (
manufacturer: string | undefined,
@@ -179,24 +188,13 @@ const AddModal: React.FC<AddModalProps> = ({
: undefined;
};
const saveInstanceDataInDescription = (instanceType: InstanceTypeItem) => {
return JSON.stringify({
name: instanceType.name,
spec: {
..._.omit(instanceType.spec, ['cache', 'cpu']),
cpu: _.pick(instanceType.spec?.cpu, [
'manufacturer',
'product',
'family'
])
}
});
};
// GPU types carry their accelerator vendor; non-acceleratable (CPU) types
// all map to the single 'cpu' bucket used to match templates.
// GPU types carry their accelerator vendor on status.detail (observed — may
// be absent until the operator backfills status); non-acceleratable (CPU)
// types all map to the single 'cpu' bucket used to match templates.
const manufacturerOf = (instanceType: InstanceTypeItem) =>
instanceType.spec.acceleratable ? instanceType.spec?.manufacturer : 'cpu';
instanceType.spec.acceleratable
? (instanceType.status?.detail?.manufacturer ?? undefined)
: 'cpu';
// apply the selection of instance type and template
const applySelection = (
@@ -263,43 +261,12 @@ const AddModal: React.FC<AddModalProps> = ({
);
};
const findAggregateOf = (
candidateName: string | undefined,
clusterId: number | null | undefined,
instanceTypes: InstanceTypeItem[]
): InstanceTypeItem | undefined => {
if (!candidateName) return undefined;
return instanceTypes.find((item) =>
(item.status?.tiers ?? []).some((tier) =>
(tier.candidates ?? []).some(
(c) => c.name === candidateName && Number(c.cluster) === clusterId
)
)
);
};
// initial for first
const applyAutoSelection = (
instanceTypes: InstanceTypeItem[],
templates: TemplateItem[],
orgId?: number | null
) => {
// On edit / view, surface the persisted selection in the card list.
if (!shouldAutoSelectResource) {
const aggregate = findAggregateOf(
data?.spec?.type,
data?.clusterId,
instanceTypes
);
if (aggregate) {
setInstanceTypeSelection({
instanceType: aggregate.name,
manufacturer: manufacturerOf(aggregate)
});
}
return;
}
// Scope to clusters the chosen org owns (admin "All" view).
const owned = filterTypesByOwner(instanceTypes, orgId);
@@ -359,6 +326,7 @@ const AddModal: React.FC<AddModalProps> = ({
manufacturer: undefined
});
setTemplateId(undefined);
setEditSelectedType(undefined);
setInstanceKeyword('');
setTemplateKeyword('');
setScopeOrgId(undefined);
@@ -367,8 +335,12 @@ const AddModal: React.FC<AddModalProps> = ({
if (action === PageAction.CREATE) {
loadCreateResources();
} else if (action === PageAction.EDIT) {
// Edit has no card columns, but the change-type overlay still needs the
// full instance-type list to re-type a stopped instance.
fetchData({ page: -1 });
}
}, [open, shouldAutoSelectResource, action]);
}, [open, action]);
// filter instance types (already scoped to the chosen org's clusters)
const filteredInstanceTypes = ownedInstanceTypes.filter((item) =>
@@ -506,6 +478,17 @@ const AddModal: React.FC<AddModalProps> = ({
applySelection(item, template);
};
// Stopped-edit re-type. Decoupled from applySelection (the create flow): it
// only snapshots the type into `description` and applies it to the form — no
// template selection or filtering.
const handleEditInstanceTypeChange = (item: InstanceTypeItem) => {
setEditSelectedType(item.name);
form.current?.setFieldsValue({
description: saveInstanceDataInDescription(item)
});
form.current?.applyInstanceType?.(item);
};
const handleTemplateChange = (id: number, item: TemplateItem) => {
setTemplateId(id);
const formValues = form.current?.getFieldsValue();
@@ -543,104 +526,108 @@ const AddModal: React.FC<AddModalProps> = ({
footer={false}
>
<div className={styles.container}>
{showInstanceTypeColumn && (
<div
className={styles.colWrapper}
// The 33% cap suits the 3-column create layout; in the 2-column
// stopped-edit layout, split the space evenly with the form column.
style={isStoppedEdit ? { flex: 1, maxWidth: 'none' } : undefined}
>
<ColumnWrapper styles={{ container: { paddingBlock: 0 } }}>
<div className={styles.panelBody}>
<div
style={{
display: 'flex',
flexDirection: 'column',
gap: 16,
position: 'sticky',
top: 0,
zIndex: 10,
backgroundColor: 'var(--ant-color-bg-elevated)'
}}
>
<ColTitle style={{ paddingBottom: 0 }}>
{intl.formatMessage({
id: 'gpuservice.instance.types'
})}
</ColTitle>
<Input
allowClear
prefix={<SearchOutlined className="text-tertiary" />}
placeholder={intl.formatMessage({
id: 'gpuservice.instance.search.type.placeholder'
})}
value={instanceKeyword}
onChange={(e) => setInstanceKeyword(e.target.value)}
/>
</div>
<InstanceTypeList
// Edit (stopped) re-selection is decoupled from create's
// card selection: separate highlight state + apply handler.
value={
isStoppedEdit
? editSelectedType
: instanceTypeSelection.instanceType
}
dataList={filteredInstanceTypes}
loading={instanceTypesLoading}
onChange={
isStoppedEdit
? handleEditInstanceTypeChange
: handleInstanceTypeChange
}
/>
</div>
</ColumnWrapper>
<Separator></Separator>
</div>
)}
{showResourceSelectors && (
<>
<div className={styles.colWrapper}>
<ColumnWrapper styles={{ container: { paddingBlock: 0 } }}>
<div className={styles.panelBody}>
<div
style={{
display: 'flex',
flexDirection: 'column',
gap: 16,
position: 'sticky',
top: 0,
zIndex: 10,
backgroundColor: 'var(--ant-color-bg-elevated)'
}}
>
<ColTitle style={{ paddingBottom: 0 }}>
{intl.formatMessage({
id: 'gpuservice.instance.types'
})}
</ColTitle>
<Input
allowClear
prefix={<SearchOutlined className="text-tertiary" />}
placeholder={intl.formatMessage({
id: 'gpuservice.instance.search.type.placeholder'
})}
value={instanceKeyword}
onChange={(e) => setInstanceKeyword(e.target.value)}
/>
</div>
<InstanceTypeList
value={instanceTypeSelection.instanceType}
dataList={filteredInstanceTypes}
loading={instanceTypesLoading}
onChange={handleInstanceTypeChange}
<div className={styles.colWrapper}>
<ColumnWrapper styles={{ container: { paddingBlock: 0 } }}>
<div className={styles.panelBody}>
<div
style={{
display: 'flex',
flexDirection: 'column',
gap: 16,
position: 'sticky',
top: 0,
zIndex: 10,
backgroundColor: 'var(--ant-color-bg-elevated)'
}}
>
<ColTitle style={{ paddingBottom: 0 }}>
{intl.formatMessage({
id: 'gpuservice.instance.templates'
})}
</ColTitle>
<Input
allowClear
prefix={<SearchOutlined className="text-tertiary" />}
placeholder={intl.formatMessage({
id: 'gpuservice.instance.search.template.placeholder'
})}
value={templateKeyword}
onChange={(e) => setTemplateKeyword(e.target.value)}
/>
</div>
</ColumnWrapper>
<Separator></Separator>
</div>
<div className={styles.colWrapper}>
<ColumnWrapper styles={{ container: { paddingBlock: 0 } }}>
<div className={styles.panelBody}>
<div
style={{
display: 'flex',
flexDirection: 'column',
gap: 16,
position: 'sticky',
top: 0,
zIndex: 10,
backgroundColor: 'var(--ant-color-bg-elevated)'
}}
>
<ColTitle style={{ paddingBottom: 0 }}>
{intl.formatMessage({
id: 'gpuservice.instance.templates'
})}
</ColTitle>
<Input
allowClear
prefix={<SearchOutlined className="text-tertiary" />}
placeholder={intl.formatMessage({
id: 'gpuservice.instance.search.template.placeholder'
})}
value={templateKeyword}
onChange={(e) => setTemplateKeyword(e.target.value)}
/>
</div>
<TemplateSelector
value={templateId}
loading={templateLoading || !initialized}
groups={templateGroups}
onChange={handleTemplateChange}
/>
</div>
</ColumnWrapper>
<Separator></Separator>
</div>
</>
<TemplateSelector
value={templateId}
loading={templateLoading || !initialized}
groups={templateGroups}
onChange={handleTemplateChange}
/>
</div>
</ColumnWrapper>
<Separator></Separator>
</div>
)}
<div className={styles.formWrapper}>
<ColumnWrapper
styles={{ container: { paddingBlock: 0 } }}
footer={
<>
{isRecreate && open && (
<div style={{ marginInline: 24, paddingTop: 8 }}>
<AlertBlockInfo
type="warning"
contentStyle={{ paddingInline: 0 }}
message={intl.formatMessage({
id: 'gpuservice.instance.recreate.confirm.content'
})}
/>
</div>
)}
<ModalFooter
onOk={handleSubmit}
onCancel={handleCancel}
@@ -664,9 +651,9 @@ const AddModal: React.FC<AddModalProps> = ({
<GPUServiceInstanceForm
ref={form}
action={action}
realAction={realAction}
currentData={data}
disabled={readonly}
restrictedEdit={isRestrictedEdit}
onFinish={onFinish}
onFinishFailed={release}
onScopeChange={handleScopeChange}
@@ -7,7 +7,11 @@ import styled from 'styled-components';
import { manufactureColorMap } from '../../templates/config';
import { formatManufacturer } from '../../utils';
import { formatMemoryDisplay } from '../config';
import { InstanceTypeItem as InstanceTypeItemModel } from '../config/types';
import {
InstanceTypeItem as InstanceTypeItemModel,
InstanceTypeSnapshotSpec
} from '../config/types';
import { buildInstanceTypeSnapshotSpec } from '../utils/instance-description';
const Title = styled.div`
display: flex;
@@ -54,10 +58,14 @@ const Meta = styled.div<{ $columns?: number }>`
interface InstanceTypeItemProps {
item: InstanceTypeItemModel;
action?: React.ReactNode;
}
interface MetadataSectionProps {
spec: InstanceTypeItemModel['spec'];
// The flat snapshot / display model — built from a live item with
// buildInstanceTypeSnapshotSpec, or parsed back from a persisted
// `description` snapshot (readonly edit card).
spec: InstanceTypeSnapshotSpec;
// status.onceMaxRequest.acceleratorSliced (max sliceable percentage). Shown
// next to Max for sliceable types.
slicedMaxPercentage?: number;
@@ -103,8 +111,14 @@ const CPUManufacturerTag: React.FC<{ manufacturer?: string }> = ({
);
};
function getInstanceDerived(item: InstanceTypeItemModel) {
const spec = item.spec || {};
// Derives the display fields from the flat snapshot spec (the UI document
// format — built from a live item with buildInstanceTypeSnapshotSpec, or
// parsed back from a persisted `description` snapshot). Observed hardware
// (manufacturer / product / memory / cpu) originates from status.detail.
function getInstanceDerived(
spec: InstanceTypeSnapshotSpec = {},
fallbackName?: string
) {
const acceleratable = spec.acceleratable;
const cpuManufacturer = acceleratable
@@ -115,7 +129,9 @@ function getInstanceDerived(item: InstanceTypeItemModel) {
acceleratable,
isGPU: acceleratable,
manufacturer: acceleratable ? spec.manufacturer || '' : 'cpu', // GPU manufacturer or 'cpu' for non-acceleratable types
displayName: acceleratable ? spec.product || item.name : 'CPU Only',
displayName: acceleratable
? spec.displayName || spec.product || fallbackName
: spec.displayName || 'CPU-only',
ramUnit: spec.unitResourcesParsed?.ram?.value,
os: _.capitalize(spec.os) || '',
arch: spec.arch,
@@ -158,9 +174,7 @@ export const InstanceMetadataSection: React.FC<MetadataSectionProps> = ({
}) => {
const intl = useIntl();
const { ramUnit, cpuUnitCores, isGPU, arch } = getInstanceDerived({
spec
} as InstanceTypeItemModel);
const { ramUnit, cpuUnitCores, isGPU, arch } = getInstanceDerived(spec);
// Sliceable types append a "Sliceable {n}%" cell to the second row.
const showSliceable = !!spec.sliceable && (slicedMaxPercentage ?? 0) > 0;
@@ -212,11 +226,16 @@ export const InstanceMetadataSection: React.FC<MetadataSectionProps> = ({
);
};
const InstanceTypeItem: React.FC<InstanceTypeItemProps> = ({ item }) => {
const specData = item.spec || {};
const InstanceTypeItem: React.FC<InstanceTypeItemProps> = ({
item,
action
}) => {
// Fold the live (API-shaped) item into the flat display model: definition
// fields from spec, observed hardware from status.detail.
const specData = buildInstanceTypeSnapshotSpec(item);
const { acceleratable, manufacturer, displayName, cpuManufacturer } =
getInstanceDerived(item);
getInstanceDerived(specData, item.name);
const manufacturerColor = manufactureColorMap[manufacturer] ?? 'purple';
const showManufacturerTag = acceleratable && !!manufacturer;
@@ -264,6 +283,7 @@ const InstanceTypeItem: React.FC<InstanceTypeItemProps> = ({ item }) => {
name="InstanceTypeBillingBadge"
context={{ instanceType: item }}
/>
{action && <div style={{ marginLeft: 8 }}>{action}</div>}
</Flex>
</Title>
<InstanceMetadataSection
@@ -3,7 +3,15 @@ import { StatusType } from '@/config/types';
import { IconFont, icons } from '@gpustack/core-ui';
import _ from 'lodash';
import React from 'react';
import { ListItem } from '../config/types';
import { AcceleratorSlicedDetail, ListItem } from '../config/types';
// Whether a type can be sliced, per the API contract (replaces the removed
// `spec.sliceable` boolean): logical (soft) slicing reports per-card capacity
// or physical (e.g. MIG) profiles exist. Every level of slicedDetail may be
// absent (exclude_none responses).
export const isSliceableDetail = (detail?: AcceleratorSlicedDetail | null) =>
(detail?.logical?.count ?? 0) > 0 ||
(detail?.physical?.profiles?.length ?? 0) > 0;
export const InstanceStatusValueMap = {
Scheduling: 'Scheduling',
@@ -251,7 +259,7 @@ const parseQuantity = (value?: string | null): number => {
// Returns the slider max for the accelerator count: the largest
// tier.onceMaxRequest.accelerator across all tiers (not from candidates).
export const getAcceleratorMax = (
tiers?: { onceMaxRequest: { accelerator?: string } }[] | null
tiers?: { onceMaxRequest: { accelerator?: string | null } }[] | null
) => {
if (!tiers?.length) return 0;
return tiers.reduce((acc, tier) => {
@@ -262,20 +270,25 @@ export const getAcceleratorMax = (
// Picks the candidate (cluster + type name) that should fulfill a requested
// accelerator count: the first candidate of the smallest tier whose
// onceMaxRequest.accelerator is >= the requested count. Accelerated types are
// not gated on CPU remaining (only CPU-only types are); in sliced mode the
// candidate's acceleratorSliced remaining must also be > 0.
// onceMaxRequest.accelerator is >= the requested count. Only Active candidates
// are eligible. Accelerated types are not gated on CPU remaining (only CPU-only
// types are); in sliced mode the candidate's acceleratorSliced remaining must
// also be > 0.
export const pickCandidateForAccelerator = <
C extends {
cluster: string;
name: string;
phase?: string | null;
cpu?: { remaining?: string | null } | null;
acceleratorSliced?: { remaining?: string | null } | null;
}
>(
tiers:
| {
onceMaxRequest: { accelerator?: string; acceleratorSliced?: string };
onceMaxRequest: {
accelerator?: string | null;
acceleratorSliced?: string | null;
};
candidates?: C[] | null;
}[]
| undefined
@@ -289,6 +302,8 @@ export const pickCandidateForAccelerator = <
if (!tiers?.length) return null;
const hasResources = (c: C) => {
// Only Active candidates can serve new instances.
if (c.phase !== InstanceTypePhaseValueMap.Active) return false;
// Accelerated types are not gated on CPU remaining; CPU-only types are.
if (!acceleratable && parseQuantity(c.cpu?.remaining) <= 0) return false;
if (sliced && parseQuantity(c.acceleratorSliced?.remaining) <= 0)
+121 -47
View File
@@ -131,76 +131,129 @@ export interface InstanceTypeResource {
export interface InstanceTypeCandidate {
cluster: string;
name: string;
accelerator: InstanceTypeResource;
cpu: InstanceTypeResource;
accelerator?: InstanceTypeResource | null;
cpu?: InstanceTypeResource | null;
// Shared-mode available resource (not shown in the GPU Instance form).
acceleratorShared: InstanceTypeResource;
acceleratorShared?: InstanceTypeResource | null;
// Sliced-mode available resource.
acceleratorSliced: InstanceTypeResource;
acceleratorSliced?: InstanceTypeResource | null;
// This candidate's sliced (partitioning) capability.
acceleratorSlicedDetail?: AcceleratorSlicedDetail | null;
phase?: 'Active' | 'Inactive' | 'Draining' | null;
}
export interface InstanceTypeTierOnceMaxRequestResource {
accelerator?: string;
cpu: QuanityCPU;
ram: QuanityMemory;
localStorage: QuanityLocalStorage;
// Per-mode maxima as plain number strings — the shape of the aggregated
// status.onceMaxRequest / status.remaining AND of tier onceMaxRequest /
// remaining (they are identical in the API). accelerator counts whole cards,
// acceleratorShared / acceleratorSliced are percentages, cpu is cores. The
// API carries no ram / localStorage here — RAM caps derive from
// spec.unitResources, disk from spec.localStorage.
export interface InstanceTypeOverviewResource {
accelerator?: `${number}` | null;
acceleratorShared?: `${number}` | null;
acceleratorSliced?: `${number}` | null;
cpu?: QuanityCPU | null;
}
export interface InstanceTypeTier {
onceMaxRequest: InstanceTypeTierOnceMaxRequestResource;
onceMaxRequest: InstanceTypeOverviewResource;
remaining?: InstanceTypeOverviewResource | null;
// The tier's aggregated sliced (partitioning) capability.
acceleratorSlicedDetail?: AcceleratorSlicedDetail | null;
candidates?: InstanceTypeCandidate[] | null;
}
export interface InstanceTypeOnceMaxRequestResource {
accelerator?: `${number}` | null;
cpu: QuanityCPU;
ram: QuanityMemory;
localStorage: QuanityLocalStorage;
acceleratorShared: `${number}` | null;
acceleratorSliced: `${number}` | null;
}
export interface CPUCache {
l1i: string;
l1d: string;
l2: string;
l3: string;
l1i?: string | null;
l1d?: string | null;
l2?: string | null;
l3?: string | null;
}
export interface CPUInfo {
physicalCores: string;
threadsPerPhysicalCore: string;
logicalCores: string;
stepping: string | null;
clockSpeed: string | null;
maxClockSpeed: string | null;
cacheLine: string;
cache: CPUCache;
manufacturer: string;
product: string;
family: string;
physicalCores?: string | null;
threadsPerPhysicalCore?: string | null;
logicalCores?: string | null;
stepping?: string | null;
clockSpeed?: string | null;
maxClockSpeed?: string | null;
cacheLine?: string | null;
cache?: CPUCache | null;
manufacturer?: string | null;
product?: string | null;
family?: string | null;
}
export interface InstanceTypeSpec {
group: string;
acceleratable: boolean;
manufacturer: string;
// Sliced (partitioning) capability descriptor. Replaces the removed
// `spec.sliceable` boolean: a type is sliceable when logical (soft) slicing
// reports capacity or physical (e.g. MIG) profiles exist — see
// isSliceableDetail in ./index. Appears as status.detail.slicedDetail and as
// tier / candidate `acceleratorSlicedDetail` in the aggregated view.
export interface AcceleratorSlicedLogicalDetail {
coresPercentageOvercommit?: boolean;
// Max soft slices per card; 0 → soft slicing unsupported.
count?: number | null;
}
export interface AcceleratorSlicedPhysicalDetailProfile {
name?: string | null;
count?: number | null;
}
export interface AcceleratorSlicedPhysicalDetail {
profiles?: AcceleratorSlicedPhysicalDetailProfile[] | null;
count?: number | null;
}
export interface AcceleratorSlicedDetail {
logical?: AcceleratorSlicedLogicalDetail | null;
physical?: AcceleratorSlicedPhysicalDetail | null;
}
// status.detail — the observed hardware descriptor. The API moved these off
// spec (spec keeps user-defined fields only). The whole object is absent until
// the operator backfills status, and every response is exclude_none — treat
// every key as possibly missing.
export interface InstanceTypeDetail {
// Device identity.
manufacturer?: string | null;
product?: string | null;
memory?: string | null;
family?: string | null;
// Host node CPU (flat fields, as opposed to the nested `cpu` below).
physicalCores?: string | null;
threadsPerPhysicalCore?: string | null;
logicalCores?: string | null;
stepping?: string | null;
clockSpeed?: string | null;
maxClockSpeed?: string | null;
cacheLine?: string | null;
cache?: CPUCache | null;
// Accelerator hardware.
memory?: string | null;
cores?: string | null;
computeCapability?: string | null;
sliced?: string | null;
sliceable?: boolean;
slicedDetail?: AcceleratorSlicedDetail | null;
// The accelerator's own CPU (distinct from the flat host CPU fields above).
cpu?: CPUInfo | null;
}
// Mirrors the API spec object exactly (user-defined fields only — observed
// hardware lives on status.detail), plus two UI-computed enrichments filled by
// use-query-instance-types whose names exist nowhere in the API.
export interface InstanceTypeSpec {
displayName?: string | null;
acceleratorGroup?: string | null;
generalGroup?: string | null;
acceleratable?: boolean;
os?: string;
arch?: string;
localStorage?: QuanityLocalStorage;
maxComputeUnitCount?: number;
unitResources?: {
cpu: QuanityCPU;
ram: QuanityMemory;
};
os?: string;
arch?: string;
cpu?: CPUInfo;
cache?: Record<string, string>;
// ---- UI-computed (not part of the API contract) ----
// spec.unitResources parsed to numbers.
unitResourcesParsed?: {
cpu: {
cores?: number;
@@ -213,10 +266,31 @@ export interface InstanceTypeSpec {
num: number;
} | null;
};
// Max requestable unit (card / core) count, derived from status.
maxComputeUnitCount?: number;
}
// Flat spec snapshot persisted in a GPU instance's `description` field at
// create time (see utils/instance-description.ts) and reused as the display
// model of the type card / metadata section. It merges the definition spec
// with the observed hardware from status.detail and the derived `sliceable`.
// The flat shape is a UI document format — do NOT confuse it with the API
// InstanceTypeSpec; it stays flat for compatibility with snapshots persisted
// by older instances.
export interface InstanceTypeSnapshotSpec extends InstanceTypeSpec {
manufacturer?: string | null;
product?: string | null;
family?: string | null;
memory?: string | null;
sliceable?: boolean;
// Accelerator CPU identity only (from status.detail.cpu).
cpu?: Pick<CPUInfo, 'manufacturer' | 'product' | 'family'> | null;
}
export interface InstanceTypeStatus {
onceMaxRequest: InstanceTypeOnceMaxRequestResource;
detail?: InstanceTypeDetail | null;
onceMaxRequest: InstanceTypeOverviewResource;
remaining?: InstanceTypeOverviewResource | null;
tiers?: InstanceTypeTier[] | null;
}
+127 -75
View File
@@ -35,7 +35,11 @@ import { DefaultImagePullPolicy } from '../../templates/config';
import TemplateBasicForm, {
BasicResourceMax
} from '../../templates/forms/basic';
import { pickCandidateForAccelerator, StorageModeValueMap } from '../config';
import {
isSliceableDetail,
pickCandidateForAccelerator,
StorageModeValueMap
} from '../config';
import { FormContext } from '../config/form-context';
import { FormData, InstanceTypeItem, ListItem } from '../config/types';
import instanceStyles from '../styles/instances.module.less';
@@ -55,7 +59,7 @@ interface InstanceFormProps {
ref?: any;
open: boolean;
action: PageActionType;
realAction?: PageActionType | string;
// Present on edit / view.
currentData?: ListItem | null;
namespace?: string;
instanceTypeList?: InstanceTypeItem[];
@@ -63,6 +67,9 @@ interface InstanceFormProps {
// surfaces a "no available instance type" message in the scheduling tab.
noAvailableInstanceTypes?: boolean;
disabled?: boolean;
// Editing a non-stopped instance: only displayName and the SSH public keys
// stay editable; the type / template / storage sections render disabled.
restrictedEdit?: boolean;
// Fired when the create-scope picker retargets the form to another
// org (or Global). Only emitted on genuine changes — never on the
// initial mount, and never in builds where the picker isn't mounted
@@ -107,9 +114,9 @@ const GPUServiceInstanceForm: React.FC<InstanceFormProps> = forwardRef(
(props, ref) => {
const {
action,
realAction,
currentData,
disabled,
restrictedEdit,
open,
instanceTypeList = [],
noAvailableInstanceTypes,
@@ -121,8 +128,9 @@ const GPUServiceInstanceForm: React.FC<InstanceFormProps> = forwardRef(
const { getRuleMessage } = useAppUtils();
const [form] = Form.useForm<InstanceFormValues>();
const scrollTabsRef = useRef<any>(null);
const formAction =
realAction === PageAction.CREATE ? PageAction.CREATE : action;
// Restricted (non-stopped) edit disables the type / template / storage
// sections; displayName and the SSH public keys keep following `disabled`.
const sectionDisabled = disabled || restrictedEdit;
const sshEnabled = Form.useWatch('enable_ssh', form);
const description = Form.useWatch(['description'], form);
// `organization_id` is owned by the create-scope picker slot; it only
@@ -289,15 +297,15 @@ const GPUServiceInstanceForm: React.FC<InstanceFormProps> = forwardRef(
const wholeFactor = isGPUType ? accelerator : cpuCount;
// Sliced mode: scale a single card's unit resources by the chosen
// percentage. Scale CPU in millicores and RAM in MiB so fractional
// slices stay precise and k8s-valid (integers) — e.g. 10% of a 4-core /
// 16Gi card → 400m / 1638Mi, not a rounded-up 1 core / 1Gi.
// percentage, submitted as whole cores / whole Gi (floored, min 1) so
// the payload matches what the disabled CPU / RAM inputs display —
// e.g. 10% of a 4-core / 16Gi card → "1" / "1Gi".
if (sliced && unitResourcesParsed) {
const cpuCores = unitResourcesParsed.cpu?.cores ?? 0;
const ramValue = unitResourcesParsed.ram?.value ?? 0;
return {
cpu: `${Math.max(1, _.floor((cpuCores * 1000 * percentage) / 100))}m`,
ram: `${Math.max(1, _.floor((ramValue * 1024 * percentage) / 100))}Mi`
cpu: `${Math.max(1, _.floor((cpuCores * percentage) / 100))}`,
ram: `${Math.max(1, _.floor((ramValue * percentage) / 100))}Gi`
};
}
@@ -335,37 +343,66 @@ const GPUServiceInstanceForm: React.FC<InstanceFormProps> = forwardRef(
form.setFieldsValue({
spec: {
resources: {
// Display the precise (rounded) fractional values — the inputs are
// disabled, so decimals are fine and match the submitted
// millicore / MiB allocation better than a floored integer.
// Floor the scaled unit resources to whole units, never below 1 —
// a small slice (e.g. 8 GB × 10%) still shows a usable 1 vCPU /
// 1 GB instead of 0. Display-only: the submit path recomputes
// both precisely in millicores / Mi.
cpu:
cpuCores != null && percentage > 0
? _.round((cpuCores * percentage) / 100, 2)
? Math.max(1, _.floor((cpuCores * percentage) / 100))
: null,
ram:
ramValue != null && percentage > 0
? _.round((ramValue * percentage) / 100, 2)
? Math.max(1, _.floor((ramValue * percentage) / 100))
: null
}
}
} as any);
};
// Single entry point for the sliced memory ratio: write the ratio (compute
// stays pinned at 100%) and rescale CPU / RAM off it. Reused by the slider
// onChange and by the sliced-mode defaults so both share one path.
// Whether the selected type allows the compute (cores) ratio to exceed
// the memory ratio. Without overcommit there is no cores selector and the
// cores ratio is locked to (mirrors) the memory ratio.
const coresOvercommit =
!!selectedInstanceType?.status?.detail?.slicedDetail?.logical
?.coresPercentageOvercommit;
// Single entry point for the sliced memory ratio: write the ratio and
// rescale CPU / RAM off it. With cores overcommit the compute ratio must
// stay >= memory (bump it up when memory overtakes it); without it the
// compute ratio always mirrors memory. Reused by the slider onChange.
const applySliceMemoryPercentage = (value: number) => {
const currentCores = _.toNumber(
form.getFieldValue([
'spec',
'resources',
'acceleratorSlicedCoresPercentage'
])
);
const coresPercentage = coresOvercommit
? Math.max(currentCores, value)
: value;
form.setFieldsValue({
spec: {
resources: {
acceleratorSlicedMemoryPercentage: value,
acceleratorSlicedCoresPercentage: 100
acceleratorSlicedCoresPercentage: coresPercentage
}
}
} as any);
applySlicedResourceScaling();
};
// Compute (cores) ratio — a GPU-slice-only parameter that rides along on
// submit. It does not scale CPU / RAM (those track the memory ratio), so
// just write the field.
const applySliceCoresPercentage = (value: number) => {
form.setFieldValue(
['spec', 'resources', 'acceleratorSlicedCoresPercentage'],
value
);
};
const resolveAndApply = (
instanceType: InstanceTypeItem | undefined,
count: number,
@@ -405,12 +442,14 @@ const GPUServiceInstanceForm: React.FC<InstanceFormProps> = forwardRef(
console.log('picked candidate', candidate, instanceType, count);
// The API carries no RAM max on onceMaxRequest — derive it from the
// per-unit RAM × the max requestable unit count (RAM always scales with
// the unit count). Disk max comes from spec.localStorage (UI-only cap).
const unitRamGi = instanceType.spec?.unitResourcesParsed?.ram?.value;
const maxUnits = instanceType.spec?.maxComputeUnitCount || 0;
setOnceMaxRequest({
cpu: ceilMilliToCore(candidate?.cpu?.onceMaxRequest)?.cores,
// candidate no longer carries ram/localStorage: memory max comes from
// the type-level onceMaxRequest.ram (already parsed to a Gi number by
// the query hook), disk max from spec.localStorage (UI-only cap).
memory: _.toNumber(instanceType.status?.onceMaxRequest?.ram) || null,
memory: unitRamGi && maxUnits ? unitRamGi * maxUnits : null,
localStorage:
parseQuantityToGi(instanceType.spec?.localStorage)?.value ?? null
});
@@ -429,22 +468,33 @@ const GPUServiceInstanceForm: React.FC<InstanceFormProps> = forwardRef(
};
// Whole-card (exclusive) vs sliced (percentage) mode. Only meaningful for
// sliceable accelerator types; derived (no persisted field) — on edit/
// recreate it is inferred from acceleratorSlicedMemoryPercentage > 0.
// sliceable accelerator types; derived (no persisted field) — on edit it
// is inferred from acceleratorSlicedMemoryPercentage > 0.
const [sliceMode, setSliceMode] = useState<'whole' | 'sliced'>('whole');
const handleAcceleratorChange = (count: number) => {
resolveAndApply(selectedInstanceType, count, false);
};
// Seed the sliced-mode default ratio for an instance type: 10% but never
// above the type's max sliceable ratio (status.onceMaxRequest
// .acceleratorSliced). Shares applySliceMemoryPercentage with the slider.
// Seed the sliced-mode defaults for an instance type: memory ratio at 10%
// (never above the type's max sliceable ratio, status.onceMaxRequest
// .acceleratorSliced), and the cores ratio defaulting to the same value
// (cores >= memory). Set both together so a fresh selection doesn't carry a
// stale cores value from a previous type.
const applySlicedDefaults = (instanceType?: InstanceTypeItem) => {
const slicedMax =
_.toNumber(instanceType?.status?.onceMaxRequest?.acceleratorSliced) ||
0;
applySliceMemoryPercentage(slicedMax ? Math.min(10, slicedMax) : 10);
const memoryPercentage = slicedMax ? Math.min(10, slicedMax) : 10;
form.setFieldsValue({
spec: {
resources: {
acceleratorSlicedMemoryPercentage: memoryPercentage,
acceleratorSlicedCoresPercentage: memoryPercentage
}
}
} as any);
applySlicedResourceScaling();
};
// Toggle between whole-card and sliced mode. Sliced fixes the accelerator
@@ -468,6 +518,40 @@ const GPUServiceInstanceForm: React.FC<InstanceFormProps> = forwardRef(
}
};
// Apply a chosen instance type to the form: default to sliced mode for a
// sliceable type with no whole-card capacity, otherwise whole-card with a
// count of 1. Shared by the create card selection (imperative handle) and
// the edit change-type overlay.
const applyInstanceType = (instanceType?: InstanceTypeItem) => {
if (!instanceType) {
setSliceMode('whole');
resolveAndApply(undefined, 0);
return;
}
// A sliceable type with no whole-card capacity (Max < 1) defaults to
// sliced mode — whole mode would have nothing selectable.
const wholeMax = instanceType.spec?.maxComputeUnitCount ?? 0;
const slicedMax =
_.toNumber(instanceType.status?.onceMaxRequest?.acceleratorSliced) || 0;
const defaultSliced =
isSliceableDetail(instanceType.status?.detail?.slicedDetail) &&
wholeMax < 1 &&
slicedMax > 0;
if (defaultSliced) {
setSliceMode('sliced');
resolveAndApply(instanceType, 1, true);
applySlicedDefaults(instanceType);
return;
}
// Otherwise default to whole-card mode (a new type may not be
// sliceable); set count to 1 for all instance types: GPU or non-GPU.
setSliceMode('whole');
resolveAndApply(instanceType, 1);
};
const onTargetChange = (key: string) => {
scrollTabsRef.current?.handleTargetChange(key);
};
@@ -502,11 +586,8 @@ const GPUServiceInstanceForm: React.FC<InstanceFormProps> = forwardRef(
return;
}
if (
action === PageAction.EDIT ||
action === PageAction.VIEW ||
realAction === PageAction.CREATE
) {
// Prefill from the source row on edit / view.
if (currentData) {
console.log('currentData', currentData);
const currentSpec = parseJsonSafe(
currentData?.description || '{}',
@@ -517,8 +598,8 @@ const GPUServiceInstanceForm: React.FC<InstanceFormProps> = forwardRef(
? _.toNumber(currentData?.spec?.resources?.accelerator)
: _.toNumber(currentData?.spec?.resources?.cpu) || 0;
// Infer the mode from the persisted slice percentage (recreate keeps
// the section editable; edit/view render a readonly card).
// Infer the mode from the persisted slice percentage (edit/view
// render a readonly card).
const persistedSliced =
_.toNumber(
currentData?.spec?.resources?.acceleratorSlicedMemoryPercentage
@@ -544,12 +625,12 @@ const GPUServiceInstanceForm: React.FC<InstanceFormProps> = forwardRef(
});
// buildResourcesData above filled CPU / RAM for the whole card; rescale
// them off the persisted percentages when recreating a sliced instance.
// them off the persisted percentages for a sliced instance.
if (persistedSliced) {
applySlicedResourceScaling();
}
}
}, [action, currentData, form, open, realAction, instanceTypeList]);
}, [action, currentData, form, open, instanceTypeList]);
const getUnitResources = () => {
if (selectedInstanceType?.spec?.unitResourcesParsed) {
@@ -614,34 +695,7 @@ const GPUServiceInstanceForm: React.FC<InstanceFormProps> = forwardRef(
form.setFieldsValue(values as any);
},
getFieldsValue: () => form.getFieldsValue(),
applyInstanceType: (instanceType?: InstanceTypeItem) => {
if (!instanceType) {
setSliceMode('whole');
resolveAndApply(undefined, 0);
return;
}
// A sliceable type with no whole-card capacity (Max < 1) defaults to
// sliced mode — whole mode would have nothing selectable.
const wholeMax = instanceType.spec?.maxComputeUnitCount ?? 0;
const slicedMax =
_.toNumber(instanceType.status?.onceMaxRequest?.acceleratorSliced) ||
0;
const defaultSliced =
!!instanceType.spec?.sliceable && wholeMax < 1 && slicedMax > 0;
if (defaultSliced) {
setSliceMode('sliced');
resolveAndApply(instanceType, 1, true);
applySlicedDefaults(instanceType);
return;
}
// Otherwise default to whole-card mode (a new type may not be
// sliceable); set count to 1 for all instance types: GPU or non-GPU.
setSliceMode('whole');
resolveAndApply(instanceType, 1);
}
applyInstanceType
}));
const handleAddSSHKey = () => {
@@ -683,7 +737,7 @@ const GPUServiceInstanceForm: React.FC<InstanceFormProps> = forwardRef(
>
<FormContext.Provider
value={{
action: formAction,
action: action,
currentData: currentData,
isGPUType: isGPUType
}}
@@ -727,7 +781,7 @@ const GPUServiceInstanceForm: React.FC<InstanceFormProps> = forwardRef(
storageMode: StorageModeValueMap.Temporary
}}
>
<Basic action={formAction} disabled={disabled} />
<Basic action={action} disabled={disabled} />
<Form.Item name="clusterId" hidden>
<CInput.Input />
</Form.Item>
@@ -744,8 +798,8 @@ const GPUServiceInstanceForm: React.FC<InstanceFormProps> = forwardRef(
forceRender: true,
children: (
<InstanceTypeFormItem
action={formAction}
disabled={disabled}
action={action}
disabled={sectionDisabled}
selectedInstanceType={selectedInstanceType}
currentData={currentData as any}
onceMaxRequest={onceMaxRequest}
@@ -753,6 +807,7 @@ const GPUServiceInstanceForm: React.FC<InstanceFormProps> = forwardRef(
sliceMode={sliceMode}
onSliceModeChange={handleSliceModeChange}
onSliceMemoryPercentageChange={applySliceMemoryPercentage}
onSliceCoresPercentageChange={applySliceCoresPercentage}
onGPUCountChange={handleAcceleratorChange}
/>
)
@@ -766,7 +821,7 @@ const GPUServiceInstanceForm: React.FC<InstanceFormProps> = forwardRef(
children: (
<TemplateBasicForm
page="instance"
disabled={disabled || formAction === PageAction.EDIT}
disabled={sectionDisabled}
onceMaxRequest={onceMaxRequest}
/>
)
@@ -778,10 +833,7 @@ const GPUServiceInstanceForm: React.FC<InstanceFormProps> = forwardRef(
}),
forceRender: true,
children: (
<StorageVolume
disabled={disabled || formAction === PageAction.EDIT}
action={formAction}
/>
<StorageVolume disabled={sectionDisabled} action={action} />
)
}
]}
@@ -12,6 +12,7 @@ import { parseJsonSafe } from '../../utils';
import InstanceTypeItem, {
InstanceMetadataSection
} from '../components/instance-type-item';
import { isSliceableDetail } from '../config';
import { FormContext } from '../config/form-context';
import {
FormData,
@@ -58,7 +59,22 @@ const InstanceTypePicker: React.FC<InstanceTypePickerProps> = ({
};
// Fixed 10-tick percentage scale (10..100) for the sliced (percentage) mode.
const SLICE_PERCENT_TICKS = [10, 20, 30, 40, 50, 60, 70, 80, 90, 100];
const SLICE_PERCENT_TICKS = [10, 20, 30, 50];
// The paired VRAM + Compute selectors (cores overcommit) are grouped in a
// bordered card; a lone "Percentage" selector (no overcommit) renders bare so
// it matches the whole-card GPU Count block's styling.
const SliceFieldWrapper: React.FC<{
withCard: boolean;
children: React.ReactNode;
}> = ({ withCard, children }) =>
withCard ? (
<FieldBlock>
<SelectedCard style={{ padding: 0 }}>{children}</SelectedCard>
</FieldBlock>
) : (
<>{children}</>
);
interface InstanceTypeFormItemProps {
action: PageActionType;
@@ -76,6 +92,8 @@ interface InstanceTypeFormItemProps {
onSliceModeChange?: (mode: 'whole' | 'sliced') => void;
// Commit a new sliced memory ratio (writes the field + rescales CPU / RAM).
onSliceMemoryPercentageChange?: (value: number) => void;
// Commit a new sliced compute (cores) ratio (writes the field only).
onSliceCoresPercentageChange?: (value: number) => void;
onGPUCountChange?: (value: number) => void;
}
@@ -89,14 +107,21 @@ const InstanceTypeFormItem: React.FC<InstanceTypeFormItemProps> = ({
sliceMode = 'whole',
onSliceModeChange,
onSliceMemoryPercentageChange,
onSliceCoresPercentageChange,
onGPUCountChange
}) => {
const intl = useIntl();
const form = Form.useFormInstance();
const { isGPUType } = useContext(FormContext);
// In edit mode the type card is read-only until a type is re-picked from the
// instance-type column (stopped instances only); once selected the section
// behaves like create (editable count / slice controls, live capacity
// labels).
const readonlyType = action === PageAction.EDIT && !selectedInstanceType;
const maxComputeUnitCount = useMemo(() => {
if (action === PageAction.EDIT) {
if (readonlyType) {
const description = parseJsonSafe(
currentData?.description || '{}',
{} as any
@@ -104,25 +129,19 @@ const InstanceTypeFormItem: React.FC<InstanceTypeFormItemProps> = ({
return description.spec?.maxComputeUnitCount || 0;
}
return selectedInstanceType?.spec?.maxComputeUnitCount || 0;
}, [action, currentData, selectedInstanceType]);
const isGPU = useMemo(() => {
if (action === PageAction.EDIT) {
return _.toNumber(currentData?.spec?.resources?.accelerator) > 0;
}
return selectedInstanceType?.spec?.acceleratable;
}, [selectedInstanceType, action]);
}, [readonlyType, currentData, selectedInstanceType]);
const handleOnGPUCountChange = (value: number) => {
onGPUCountChange?.(value);
};
// Sliced mode is only offered for sliceable accelerator types, and only when
// the section is editable (create / recreate; edit renders a readonly card).
// the section is editable (create, or edit after re-picking a type; a
// not-yet-re-typed edit renders a readonly card).
const showModeSwitch =
action !== PageAction.EDIT &&
!readonlyType &&
isGPUType &&
!!selectedInstanceType?.spec?.sliceable;
isSliceableDetail(selectedInstanceType?.status?.detail?.slicedDetail);
const handleModeChange = (value: string) => {
onSliceModeChange?.(value as 'whole' | 'sliced');
@@ -134,6 +153,21 @@ const InstanceTypeFormItem: React.FC<InstanceTypeFormItemProps> = ({
onSliceMemoryPercentageChange?.(value);
};
// Compute (cores) percentage changed — forward the new value.
const handleCoresPercentageChange = (value: number) => {
onSliceCoresPercentageChange?.(value);
};
// The cores ratio must be >= the memory ratio, so ticks below the current
// memory percentage are disabled (min). Cores range is a fixed 10..100.
const slicedMemoryPercentage =
_.toNumber(
Form.useWatch(
['spec', 'resources', 'acceleratorSlicedMemoryPercentage'],
form
)
) || 1;
// Max selectable ratio in sliced mode: status.onceMaxRequest.acceleratorSliced
// (a percentage). Ticks above it stay visible but disabled.
const slicedMaxPercentage =
@@ -141,10 +175,17 @@ const InstanceTypeFormItem: React.FC<InstanceTypeFormItemProps> = ({
selectedInstanceType?.status?.onceMaxRequest?.acceleratorSliced
) || 0;
// Whether the compute (cores) ratio may exceed the memory ratio. When the
// type doesn't support overcommit, cores are locked to the memory ratio —
// no cores selector, and the memory selector reads as a plain "Percentage".
const coresOvercommit =
!!selectedInstanceType?.status?.detail?.slicedDetail?.logical
?.coresPercentageOvercommit;
const modeSegmented = showModeSwitch ? (
<Segmented
size="small"
shape="round"
size="middle"
type="rounded"
style={{ fontSize: 12 }}
value={sliceMode}
disabled={disabled}
@@ -168,7 +209,7 @@ const InstanceTypeFormItem: React.FC<InstanceTypeFormItemProps> = ({
// When the max ratio is below 10%, switch the ticks to a finer 1..10 scale
// so small slices are still selectable; otherwise use the 10..100 scale.
const sliceTicks =
const sliceTicks: number[] =
slicedMaxPercentage < 10
? [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
: SLICE_PERCENT_TICKS;
@@ -191,7 +232,7 @@ const InstanceTypeFormItem: React.FC<InstanceTypeFormItemProps> = ({
};
const renderMemoryLabel = (): React.ReactNode => {
if (isGPUType || action === PageAction.EDIT || !onceMaxRequest?.memory) {
if (isGPUType || readonlyType || !onceMaxRequest?.memory) {
return intl.formatMessage({ id: 'gpuservice.template.memory' });
}
@@ -223,8 +264,8 @@ const InstanceTypeFormItem: React.FC<InstanceTypeFormItemProps> = ({
}}
>
{description.acceleratable
? `${description.product} x ${currentData?.spec?.resources?.accelerator}`
: 'CPU'}
? `${description.displayName || description.product} x ${currentData?.spec?.resources?.accelerator}`
: description.displayName || 'CPU'}
</span>
<InstanceMetadataSection spec={description}></InstanceMetadataSection>
</Flex>
@@ -257,15 +298,21 @@ const InstanceTypeFormItem: React.FC<InstanceTypeFormItemProps> = ({
}
]}
>
{action === PageAction.CREATE && (
{readonlyType ? (
renderInstanceType()
) : (
<InstanceTypePicker
selectedInstanceType={selectedInstanceType}
noAvailable={noAvailableTypes}
/>
)}
{action === PageAction.EDIT && renderInstanceType()}
</Form.Item>
</FieldBlock>
{showModeSwitch && (
<div>
<div style={{ marginBlock: 8 }}>{modeSegmented}</div>
</div>
)}
{!noAvailableTypes && (
<Form.Item<FormData>
key={isGPUType ? 'accelerator' : 'cpu'}
@@ -275,7 +322,7 @@ const InstanceTypeFormItem: React.FC<InstanceTypeFormItemProps> = ({
: ['spec', 'resources', 'cpu']
}
preserve
hidden={action === PageAction.EDIT || isSliced}
hidden={readonlyType || isSliced}
normalize={(value) => (value != null ? _.toString(value) : undefined)}
getValueProps={(value) => ({
value: value != null ? _.toNumber(value) : undefined
@@ -316,8 +363,7 @@ const InstanceTypeFormItem: React.FC<InstanceTypeFormItemProps> = ({
max={maxComputeUnitCount}
step={1}
required
labelExtra={sliceMode === 'whole' ? modeSegmented : undefined}
disabled={disabled || action === PageAction.EDIT}
disabled={disabled || readonlyType}
label={`${intl.formatMessage({ id: 'common.max.count' }, { label: numberSelectionLabel.label })} (${intl.formatMessage(
{
id: 'common.max'
@@ -328,73 +374,142 @@ const InstanceTypeFormItem: React.FC<InstanceTypeFormItemProps> = ({
</Form.Item>
)}
{!noAvailableTypes && isSliced && (
<FieldBlock>
<Form.Item<FormData>
name={['spec', 'resources', 'acceleratorSlicedMemoryPercentage']}
getValueProps={(value) => ({
value: value != null ? _.toNumber(value) : undefined
})}
rules={[
{
required: true,
validator: (_, value) => {
const num = Number(value);
if (value == null || value === '' || Number.isNaN(num)) {
return Promise.reject(
new Error(
intl.formatMessage({
id: 'gpuservice.instance.slice.percentage.required'
})
)
);
}
if (num > slicedMaxPercentage || num <= 0) {
return Promise.reject(
new Error(
intl.formatMessage(
{
id: 'gpuservice.instance.slice.percentage.max'
},
{ count: slicedMaxPercentage }
)
)
);
}
return Promise.resolve();
}
}
]}
>
<NumberSelection
min={1}
max={slicedMaxPercentage}
step={1}
maxCount={sliceTicks.length}
presetValues={sliceTicks}
alwaysShowInput
required
disabled={disabled}
onChange={handleMemoryPercentageChange}
labelExtra={modeSegmented}
label={intl.formatMessage({
id: 'gpuservice.instance.slice.memoryPercentage'
<SliceFieldWrapper withCard={coresOvercommit}>
<>
<Form.Item<FormData>
name={['spec', 'resources', 'acceleratorSlicedMemoryPercentage']}
// Grouped with the compute selector inside one card — tighten
// the default 24px gap between the pair.
style={coresOvercommit ? { marginBottom: 0 } : undefined}
getValueProps={(value) => ({
value: value != null ? _.toNumber(value) : undefined
})}
/>
</Form.Item>
{/* Compute (cores) percentage is fixed at 100. Kept in the form via a
hidden item so it rides along on submit. */}
<Form.Item<FormData>
name={['spec', 'resources', 'acceleratorSlicedCoresPercentage']}
hidden
>
<InputNumber />
</Form.Item>
</FieldBlock>
rules={[
{
required: true,
validator: (_, value) => {
const num = Number(value);
if (value == null || value === '' || Number.isNaN(num)) {
return Promise.reject(
new Error(
intl.formatMessage({
id: 'gpuservice.instance.slice.percentage.required'
})
)
);
}
if (num > slicedMaxPercentage || num <= 0) {
return Promise.reject(
new Error(
intl.formatMessage(
{
id: 'gpuservice.instance.slice.percentage.max'
},
{ count: slicedMaxPercentage }
)
)
);
}
return Promise.resolve();
}
}
]}
>
<NumberSelection
min={1}
max={slicedMaxPercentage}
step={1}
maxCount={sliceTicks.length}
presetValues={sliceTicks}
alwaysShowInput
required
disabled={disabled}
// Inside the card the selector drops its own border; the bare
// (no-overcommit) variant keeps it, like the GPU Count block.
style={coresOvercommit ? { border: 'none' } : undefined}
onChange={handleMemoryPercentageChange}
label={intl.formatMessage({
// Without cores overcommit this single ratio drives both
// VRAM and compute, so drop the "VRAM" qualifier.
id: coresOvercommit
? 'gpuservice.instance.slice.memoryPercentage'
: 'gpuservice.instance.slice.percentage'
})}
/>
</Form.Item>
{/* Compute (cores) percentage. Fixed 10..100 ticks; ticks below the
chosen memory ratio are disabled (cores must be >= memory). Only
types with cores overcommit get the selector — without it the
ratio is locked to the memory percentage (the parent mirrors it),
carried by a hidden field so it still rides the submit. */}
{coresOvercommit ? (
<Form.Item<FormData>
name={['spec', 'resources', 'acceleratorSlicedCoresPercentage']}
style={{ marginBottom: 0 }}
getValueProps={(value) => ({
value: value != null ? _.toNumber(value) : undefined
})}
rules={[
{
required: true,
validator: (_, value) => {
const num = Number(value);
if (value == null || value === '' || Number.isNaN(num)) {
return Promise.reject(
new Error(
intl.formatMessage({
id: 'gpuservice.instance.slice.percentage.required'
})
)
);
}
if (num < slicedMemoryPercentage || num > 100) {
return Promise.reject(
new Error(
intl.formatMessage(
{ id: 'gpuservice.instance.slice.cores.min' },
{ count: slicedMemoryPercentage }
)
)
);
}
return Promise.resolve();
}
}
]}
>
<NumberSelection
min={slicedMemoryPercentage}
max={100}
step={10}
maxCount={SLICE_PERCENT_TICKS.length}
presetValues={SLICE_PERCENT_TICKS}
alwaysShowInput
required
disabled={disabled}
onChange={handleCoresPercentageChange}
style={{ border: 'none' }}
label={intl.formatMessage({
id: 'gpuservice.instance.slice.coresPercentage'
})}
/>
</Form.Item>
) : (
<Form.Item<FormData>
name={['spec', 'resources', 'acceleratorSlicedCoresPercentage']}
style={{ marginBottom: 0 }}
hidden
>
<InputNumber />
</Form.Item>
)}
</>
</SliceFieldWrapper>
)}
{/* Edit renders a readonly card (no sliced UI), so register the slice
percentages as hidden fields — otherwise their persisted values are
dropped from the submit payload. */}
{action === PageAction.EDIT && (
{/* A not-yet-re-typed edit renders a readonly card (no sliced UI), so
register the slice percentages as hidden fields — otherwise their
persisted values are dropped from the submit payload. */}
{readonlyType && (
<>
<Form.Item<FormData>
name={['spec', 'resources', 'acceleratorSlicedMemoryPercentage']}
@@ -3,6 +3,7 @@ import type { PageActionType } from '@/config/types';
import useBodyScroll from '@/hooks/use-body-scroll';
import { useIntl } from '@umijs/max';
import { useState } from 'react';
import { InstanceStatusValueMap } from '../config';
import type { ListItem } from '../config/types';
const useCreateInstance = () => {
@@ -14,30 +15,26 @@ const useCreateInstance = () => {
title: string;
currentData?: ListItem | null;
width?: number | string;
realAction?: string;
}>({
action: PageAction.CREATE,
title: '',
open: false,
width: undefined,
currentData: null,
realAction: undefined
currentData: null
});
const openModal = (
action: PageActionType,
title: string,
currentData?: ListItem | null,
width?: number | string,
realAction?: string
width?: number | string
) => {
setOpenModalStatus({
action,
title,
open: true,
currentData,
width,
realAction
width
});
saveScrollHeight();
};
@@ -52,11 +49,14 @@ const useCreateInstance = () => {
};
const openEditInstanceModal = (row: ListItem) => {
// A stopped instance can be re-typed, so it needs the two-column layout
// (instance-type list + form); other statuses edit in a single column.
const isStopped = row.status?.phase === InstanceStatusValueMap.Stopped;
openModal(
PageAction.EDIT,
intl.formatMessage({ id: 'gpuservice.instance.edit' }),
row,
600
isStopped ? 'min(1040px, calc(100vw - 220px))' : 600
);
};
@@ -69,23 +69,12 @@ const useCreateInstance = () => {
);
};
const openRecreateInstanceModal = (row: ListItem) => {
openModal(
PageAction.EDIT,
intl.formatMessage({ id: 'common.button.recreate' }),
row,
'calc(100vw - 220px)',
PageAction.CREATE
);
};
const closeModal = () => {
setOpenModalStatus({
...openModalStatus,
title: '',
open: false,
currentData: null,
realAction: undefined
currentData: null
});
restoreScrollHeight();
};
@@ -97,7 +86,6 @@ const useCreateInstance = () => {
openCreateInstanceModal,
openEditInstanceModal,
openViewInstanceModal,
openRecreateInstanceModal,
closeInstanceModal: closeModal
};
};
+1 -11
View File
@@ -86,7 +86,6 @@ const GPUService: React.FC = () => {
openCreateInstanceModal,
openEditInstanceModal,
openViewInstanceModal,
openRecreateInstanceModal,
closeInstanceModal
} = useCreateInstance();
const { openViewLogsModal, closeViewLogsModal, openViewLogsModalStatus } =
@@ -136,13 +135,7 @@ const GPUService: React.FC = () => {
const handleModalOk = async (data: FormData) => {
try {
if (openInstanceModalStatus.realAction === PageAction.CREATE) {
await deleteGPUServiceInstance(openInstanceModalStatus.currentData!.id);
await new Promise((resolve) => {
setTimeout(resolve, 300);
});
await createInstance({ data });
} else if (openInstanceModalStatus.action === PageAction.EDIT) {
if (openInstanceModalStatus.action === PageAction.EDIT) {
await updateInstance({
id: openInstanceModalStatus.currentData!.id,
data
@@ -243,8 +236,6 @@ const GPUService: React.FC = () => {
openEditInstanceModal(row);
} else if (val === 'delete') {
handleDelete({ ...row });
} else if (val === 'recreate') {
openRecreateInstanceModal(row);
} else if (val === 'viewlog') {
openViewLogsModal(row);
} else if (val === 'viewevent') {
@@ -391,7 +382,6 @@ const GPUService: React.FC = () => {
title={openInstanceModalStatus.title}
data={openInstanceModalStatus.currentData}
width={openInstanceModalStatus.width}
realAction={openInstanceModalStatus.realAction}
clusterList={clusterList}
onCancel={closeInstanceModal}
onOk={handleModalOk}
@@ -2,7 +2,7 @@ import { useQueryData } from '@gpustack/core-ui';
import React from 'react';
import { ceilMilliToCore, parseQuantityToGi } from '../../utils';
import { queryGPUServiceInstanceTypes } from '../apis';
import { getAcceleratorMax } from '../config';
import { getAcceleratorMax, isSliceableDetail } from '../config';
import { InstanceTypeItem } from '../config/types';
type InstanceType = InstanceTypeItem & {
@@ -40,7 +40,7 @@ export default function useQueryInstanceTypes() {
// Sliceable types stay selectable as long as either whole-card or sliced
// capacity remains; unavailable only when both status.onceMaxRequest
// .accelerator and .acceleratorSliced are 0.
if (item.spec?.sliceable) {
if (isSliceableDetail(item.status?.detail?.slicedDetail)) {
const wholeMax = Number(item.status?.onceMaxRequest?.accelerator) || 0;
const slicedMax =
Number(item.status?.onceMaxRequest?.acceleratorSliced) || 0;
@@ -77,17 +77,11 @@ export default function useQueryInstanceTypes() {
},
status: {
...item.status,
// Normalize cpu (possibly millicores) to a whole-core count string;
// the other onceMaxRequest fields are plain number strings already.
onceMaxRequest: {
...rawMax,
cpu: rawMax?.cpu
? `${ceilMilliToCore(rawMax.cpu)?.cores || 0}`
: '',
ram: rawMax?.ram
? `${parseQuantityToGi(rawMax.ram)?.value || 0}`
: '',
localStorage: rawMax?.localStorage
? `${parseQuantityToGi(rawMax.localStorage)?.value || 0}`
: ''
cpu: rawMax?.cpu ? `${ceilMilliToCore(rawMax.cpu)?.cores || 0}` : ''
}
},
@@ -0,0 +1,35 @@
import _ from 'lodash';
import { isSliceableDetail } from '../config';
import { InstanceTypeItem, InstanceTypeSnapshotSpec } from '../config/types';
// Build the flat snapshot spec from a live (API-shaped) instance type:
// definition fields from spec, observed hardware from status.detail, plus the
// derived `sliceable`. This flat shape is the UI document format persisted in
// the instance's `description` (older instances already carry it flat) and
// doubles as the display model of the type card / metadata section.
export const buildInstanceTypeSnapshotSpec = (
instanceType: InstanceTypeItem
): InstanceTypeSnapshotSpec => {
const detail = instanceType.status?.detail;
return {
...instanceType.spec,
..._.pick(detail, ['manufacturer', 'product', 'family', 'memory']),
sliceable: isSliceableDetail(detail?.slicedDetail),
// Accelerator CPU identity only — the full CPU descriptor is too bulky to
// persist and the UI only shows who made it.
cpu: _.pick(detail?.cpu, ['manufacturer', 'product', 'family'])
};
};
// Serialize the chosen instance type into the instance's `description` field —
// a persisted spec snapshot the form reads back to render the type card and
// derive unit resources. Shared by the create flow (card selection) and the
// edit flow (change-type overlay).
export const saveInstanceDataInDescription = (
instanceType: InstanceTypeItem
): string => {
return JSON.stringify({
name: instanceType.name,
spec: buildInstanceTypeSnapshotSpec(instanceType)
});
};
@@ -11,10 +11,10 @@
* with ``buildInstanceTypeRecordFromMiB`` and feed it here.
*/
import _ from 'lodash';
import { parseJsonSafe, parseQuantityToGi } from '../../utils';
import { ceilMilliToCore, parseJsonSafe, parseQuantityToGi } from '../../utils';
import InstanceTypeCell from '../components/instance-type-cell';
import { formatMemoryDisplay } from '../config';
import { InstanceTypeSpec, ListItem } from '../config/types';
import { InstanceTypeSnapshotSpec, ListItem } from '../config/types';
// Minimal shape of the ``useIntl()`` result we depend on — keeps this module
// free of an intl package import.
@@ -25,7 +25,7 @@ const toGB = (v?: string | number) =>
const buildResourcesData = (
instanceType: {
spec: InstanceTypeSpec;
spec: InstanceTypeSnapshotSpec;
},
options: {
count: number;
@@ -54,7 +54,7 @@ const getSliceMemoryPercentage = (record: ListItem) =>
_.toNumber(record.spec?.resources?.acceleratorSlicedMemoryPercentage) || 0;
const formatResources = (
instanceTypeSpec: { spec: InstanceTypeSpec },
instanceTypeSpec: { spec: InstanceTypeSnapshotSpec },
record: ListItem
) => {
const resources = buildResourcesData(instanceTypeSpec, {
@@ -77,25 +77,28 @@ const formatResources = (
const sliceMemoryPercentage = getSliceMemoryPercentage(record);
// Sliced: CPU / RAM carry the already-scaled values on spec.resources, and
// VRAM is the per-card memory scaled by the memory percentage (floored,
// min 1) — not the whole card's size.
// Sliced: CPU / RAM carry the already-scaled values on spec.resources
// whole cores / whole Gi for instances created by the current form; parse
// (instead of echoing the raw quantity) so legacy instances persisted as
// millicores / Mi (e.g. "400m" / "1638Mi") render as whole units too. VRAM
// is the per-card memory scaled by the memory percentage (floored, min 1) —
// not the whole card's size.
if (sliceMemoryPercentage > 0) {
const vramGi = parseQuantityToGi(
(instanceTypeSpec.spec as any)?.memory
)?.value;
const vramGi = parseQuantityToGi(instanceTypeSpec.spec?.memory)?.value;
const vram =
vramGi != null
? `${Math.max(1, _.floor((vramGi * sliceMemoryPercentage) / 100))} GB`
: undefined;
const cpuCores = ceilMilliToCore(
_.toString(record.spec?.resources?.cpu) || null
)?.cores;
const ramGi = parseQuantityToGi(
_.toString(record.spec?.resources?.ram) || null
)?.value;
return {
cpu: record.spec?.resources?.cpu
? `${record.spec?.resources?.cpu} vCPU`
: '-',
ram: record.spec?.resources?.ram
? toGB(record.spec?.resources?.ram)
: '-',
cpu: cpuCores != null ? `${Math.max(1, cpuCores)} vCPU` : '-',
ram: ramGi != null ? `${Math.max(1, ramGi)} GB` : '-',
vram,
localStorage: record.spec?.resources?.localStorage
? toGB(record.spec?.resources?.localStorage)
@@ -105,7 +108,7 @@ const formatResources = (
// VRAM = per-card GPU memory (a single card's size; not aggregated across
// cards — the model's marquee spec).
const vram = formatMemoryDisplay((instanceTypeSpec.spec as any)?.memory);
const vram = formatMemoryDisplay(instanceTypeSpec.spec?.memory ?? undefined);
return {
cpu: resources.cpu ? `${resources.cpu} vCPU` : '-',
@@ -131,7 +134,7 @@ export const renderInstanceType = (
// Types breakdown only wants CPU + RAM, for example.
categories?: SpecCategory[];
// Override the primary label (default: derived "<product> x <count>" /
// "CPU Only"). The Instance Types breakdown keeps its plain product name.
// "CPU-only"). The Instance Types breakdown keeps its plain product name.
title?: string;
}
) => {
@@ -142,13 +145,17 @@ export const renderInstanceType = (
const accelerator = record.spec?.resources?.accelerator;
const sliceMemoryPercentage = getSliceMemoryPercentage(record);
const isSliced = description.acceleratable && sliceMemoryPercentage > 0;
// Type label (primary cell label and the popover's "Type" row) prefers the
// user-defined displayName persisted in the description snapshot, falling
// back to the hardware product.
const typeLabel = description.displayName || description.product;
const title =
options.title ??
(description.acceleratable
? isSliced
? `${description.product} (${sliceMemoryPercentage}%)`
: `${description.product} x ${accelerator}`
: 'CPU Only');
? `${typeLabel} (${sliceMemoryPercentage}%)`
: `${typeLabel} x ${accelerator}`
: description.displayName || 'CPU-only');
const volume = (record.spec as any)?.volume;
// Spec popover grouped by category (GPU / CPU / Memory / Disk), mirroring
@@ -179,7 +186,7 @@ export const renderInstanceType = (
],
[
intl.formatMessage({ id: 'gpuservice.instance.section.type' }),
description.product
typeLabel
],
[
intl.formatMessage({ id: 'gpuservice.instance.memory' }),
@@ -251,7 +258,7 @@ const mibToGiQuantity = (mib?: number): string | undefined =>
export interface InstanceTypeMiB {
name?: string;
product?: string;
// accelerator (GPU card) count; 0/undefined → CPU-only ("CPU Only").
// accelerator (GPU card) count; 0/undefined → CPU-only.
gpuCount?: number;
// Per-card values.
unitCpuMilli?: number;
+2 -2
View File
@@ -93,7 +93,7 @@ export interface ResourceBreakdownItem extends ResourceBreakdownSummary {
unit_memory_mib?: number;
vram_mib?: number;
// Instance totals (requested cpu/ram) — the real size, so CPU instance types
// show "CPU Only · 2 vCPU · 4 GB" instead of just the per-unit spec.
// show "CPU-only · 2 vCPU · 4 GB" instead of just the per-unit spec.
cpu_milli?: number;
memory_mib?: number;
// Per-instance rows also carry the card count + ephemeral disk so the
@@ -382,7 +382,7 @@ function flattenItem(
if (it.creator_deleted != null) flat.user_deleted = !!it.creator_deleted;
// Instance-type grouped trend: the series label (``group``) defaults to the
// raw flavor slug. Instance Types are grouped by actual shape, so label each
// series by that shape — "<product> x <cards>" / "CPU Only · 3 vCPU · 6 GB" —
// series by that shape — "<product> x <cards>" / "CPU-only · 3 vCPU · 6 GB" —
// matching the table and keeping every shape a distinct series (#5700).
// ``groupBy`` is the unmapped frontend dimension; the instance-type axis is
// ``gpu_type`` (→ backend ``instance_type`` via GROUP_BY_MAP).
@@ -39,7 +39,7 @@ const useInstancesColumns = (groupKey: GroupKey) => {
}
];
// Instance Types breakdown: the pretty product name (or flavor slug for
// older rows; "CPU Only" when no GPU cards) plus a CPU + RAM spec popover —
// older rows; "CPU-only" when no GPU cards) plus a CPU + RAM spec popover —
// rendered through the canonical renderer so the formatting matches the GPU
// Instances list, but limited to the CPU/RAM categories.
const instanceTypeColType = {
@@ -64,7 +64,7 @@ const useInstancesColumns = (groupKey: GroupKey) => {
intl,
categories: ['cpu', 'ram'],
// Each row is one shape: GPU "<product> x <cards>", CPU
// "CPU Only · <spec>".
// "CPU-only · <spec>".
title: instanceTypeSeriesLabel(row)
}
);
@@ -95,7 +95,7 @@ const useInstancesColumns = (groupKey: GroupKey) => {
persistentMib: row.persistent_mib
}),
// Label by shape directly (consistent with the Instance Types
// column); avoids renderInstanceType's "CPU Only" fallback when a
// column); avoids renderInstanceType's "CPU-only" fallback when a
// GPU row has vram but a missing/zero gpu_count.
{ intl, title: instanceTypeSeriesLabel(row) }
);
@@ -32,16 +32,16 @@ export const formatCpuSpec = (
return parts.join(' · ');
};
// CPU instance-type label: "CPU Only" plus its real size when known, e.g.
// "CPU Only · 2 vCPU · 4 GB". Used by both the table column and the trend
// CPU instance-type label: "CPU-only" plus its real size when known, e.g.
// "CPU-only · 2 vCPU · 4 GB". Used by both the table column and the trend
// legend so they read identically.
export const cpuOnlyLabel = (row?: Partial<ResourceBreakdownItem>): string => {
const spec = formatCpuSpec(row?.cpu_milli, row?.memory_mib);
return spec ? `CPU Only · ${spec}` : 'CPU Only';
return spec ? `CPU-only · ${spec}` : 'CPU-only';
};
// Instance Types are grouped by actual shape, so each row is one concrete
// type: a GPU shows "<product> x <cards>", a CPU shows "CPU Only · <spec>".
// type: a GPU shows "<product> x <cards>", a CPU shows "CPU-only · <spec>".
// One label for the table column and the trend legend so they read the same
// and each shape is a distinct series. (" x " matches the GPU Instances list.)
export const instanceTypeSeriesLabel = (