Restructure web UI navigation into 7 numbered workflow stages
Replace the flat menu (Dashboard, Audit, Validate, Burn, Benchmark, Tasks, Tools) with a numbered progression that guides engineers through a logical acceptance workflow: Dashboard (landing) → 1. Audit → 2. Check → 3. Load → 4. Speed → 5. Endurance → 6. Tools → 7. Settings Key changes: - layout.go: numbered nav labels, new hrefs, Tasks removed from nav and replaced with a persistent sidebar badge (polls /api/tasks every 5 s, highlights amber when tasks are active) - server.go: 301 redirects from /validate→/check, /burn→/load, /benchmark→/speed for backward compatibility - pages.go: dispatch cases for all new routes; old routes kept as fallbacks - page_validate.go: add renderCheck() — non-destructive check page with validate-mode tests only (no stress toggle, no targeted-stress/ targeted-power/pulse cards) - page_burn.go: add renderLoad() wrapper; update scope alert to reference /check instead of /validate - page_benchmark.go: add renderSpeed() (performance focus) and renderEndurance() (stability/overnight focus) wrappers - page_settings.go: new Settings page with blackbox logging toggle, NVIDIA driver reset, and build info - server_test.go: update five tests to use new route names and content expectations Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Mikhail Chusavitin
@@ -656,6 +656,292 @@ func validateIsVendorGPU(dev schema.HardwarePCIeDevice, vendor string) bool {
|
||||
}
|
||||
}
|
||||
|
||||
// renderCheck renders the non-destructive Check page (step 2).
|
||||
// Shows validate-mode tests only: CPU, Memory, Storage, NVIDIA L2, NCCL, NVBandwidth, AMD.
|
||||
// Stress-mode tests (targeted-stress, targeted-power, pulse) are on the Load page.
|
||||
func renderCheck(opts HandlerOptions) string {
|
||||
inv := loadValidateInventory(opts)
|
||||
n := inv.NvidiaGPUCount
|
||||
validateTotalStr := validateFmtDur(validateTotalValidateSec(n))
|
||||
gpuNote := ""
|
||||
if n > 0 {
|
||||
gpuNote = fmt.Sprintf(" (%d GPU)", n)
|
||||
}
|
||||
return `<div class="alert alert-info" style="margin-bottom:16px"><strong>Non-destructive:</strong> Check tests collect diagnostics only — no writes to disks, no sustained load, no hardware wear counters incremented. For stress testing, go to <a href="/load">3. Load</a>.</div>
|
||||
<div style="display:flex;align-items:center;gap:12px;margin-bottom:16px">
|
||||
<button type="button" class="btn btn-primary" onclick="runAllCheckSAT()">Run All Checks</button>
|
||||
<span id="sat-all-status" style="font-size:12px;color:var(--muted)"></span>
|
||||
<span style="font-size:12px;color:var(--muted)">est. ` + validateTotalStr + gpuNote + `</span>
|
||||
</div>
|
||||
|
||||
<div class="grid3">
|
||||
` + renderSATCard("cpu", "CPU", "runSAT('cpu')", "", renderValidateCardBody(
|
||||
inv.CPU,
|
||||
`Collects CPU inventory and temperatures, then runs a bounded CPU stress pass.`,
|
||||
`<code>lscpu</code>, <code>sensors</code>, <code>stress-ng</code>`,
|
||||
validateFmtDur(platform.SATEstimatedCPUValidateSec)+` (stress-ng 60 s).`,
|
||||
)) +
|
||||
renderSATCard("memory", "Memory", "runSAT('memory')", "", renderValidateCardBody(
|
||||
inv.Memory,
|
||||
`Runs a RAM validation pass and records memory state around the test.`,
|
||||
`<code>free</code>, <code>memtester</code>`,
|
||||
validateFmtDur(platform.SATEstimatedMemoryValidateSec)+` (256 MB × 1 pass).`,
|
||||
)) +
|
||||
renderSATCard("storage", "Storage", "runSAT('storage')", "", renderValidateCardBody(
|
||||
inv.Storage,
|
||||
`Scans all storage devices and runs the matching health or self-test path for each.`,
|
||||
`<code>lsblk</code>; NVMe: <code>nvme</code>; SATA/SAS: <code>smartctl</code>`,
|
||||
`Seconds (NVMe: instant device query; SATA/SAS: short self-test).`,
|
||||
)) +
|
||||
`</div>
|
||||
<div style="height:1px;background:var(--border);margin:16px 0"></div>
|
||||
<div class="card" style="margin-bottom:16px">
|
||||
<div class="card-head">NVIDIA GPU Selection</div>
|
||||
<div class="card-body">
|
||||
<p style="font-size:12px;color:var(--muted);margin:0 0 8px">` + inv.NVIDIA + `</p>
|
||||
<div style="display:flex;gap:8px;flex-wrap:wrap;margin-bottom:8px">
|
||||
<button class="btn btn-sm btn-secondary" type="button" onclick="satSelectAllGPUs()">Select All</button>
|
||||
<button class="btn btn-sm btn-secondary" type="button" onclick="satSelectNoGPUs()">Clear</button>
|
||||
</div>
|
||||
<div id="sat-gpu-list" style="border:1px solid var(--border);border-radius:4px;padding:12px;min-height:88px">
|
||||
<p style="color:var(--muted);font-size:13px">Loading NVIDIA GPUs...</p>
|
||||
</div>
|
||||
<p id="sat-gpu-selection-note" style="font-size:12px;color:var(--muted);margin:10px 0 0">Select at least one NVIDIA GPU to enable NVIDIA check tasks.</p>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="grid3">
|
||||
` + renderSATCard("nvidia", "NVIDIA GPU", "runNvidiaValidateSet('nvidia')", "", renderValidateCardBody(
|
||||
inv.NVIDIA,
|
||||
`Runs NVIDIA diagnostics and board inventory checks (DCGM Level 2).`,
|
||||
`<code>nvidia-smi</code>, <code>dmidecode</code>, <code>dcgmi diag</code>`,
|
||||
validateFmtDur(platform.SATEstimatedNvidiaGPUValidateSec)+` (Level 2, all GPUs simultaneously).`,
|
||||
)) +
|
||||
renderSATCard("nvidia-interconnect", "NVIDIA Interconnect (NCCL)", "runNvidiaFabricValidate('nvidia-interconnect')", "", renderValidateCardBody(
|
||||
inv.NVIDIA,
|
||||
`Verifies NVLink/NVSwitch fabric bandwidth using NCCL all_reduce_perf across all selected GPUs.`,
|
||||
`<code>all_reduce_perf</code> (NCCL tests)`,
|
||||
validateFmtDur(platform.SATEstimatedNvidiaInterconnectSec)+` (all GPUs simultaneously, requires ≥2).`,
|
||||
)) +
|
||||
renderSATCard("nvidia-bandwidth", "NVIDIA Bandwidth (NVBandwidth)", "runNvidiaFabricValidate('nvidia-bandwidth')", "", renderValidateCardBody(
|
||||
inv.NVIDIA,
|
||||
`Validates GPU memory copy and peer-to-peer bandwidth paths using NVBandwidth.`,
|
||||
`<code>nvbandwidth</code>`,
|
||||
validateFmtDur(platform.SATEstimatedNvidiaBandwidthSec)+` (all GPUs simultaneously).`,
|
||||
)) +
|
||||
`</div>
|
||||
<div class="grid3" style="margin-top:16px">
|
||||
` + renderSATCard("amd", "AMD GPU", "runAMDValidateSet()", "", renderValidateCardBody(
|
||||
inv.AMD,
|
||||
`Runs AMD GPU inventory, MEM integrity, and MEM bandwidth checks.`,
|
||||
`GPU Validate: <code>rocm-smi</code>, <code>dmidecode</code>; MEM Integrity: <code>rvs mem</code>; MEM Bandwidth: <code>rocm-bandwidth-test</code>, <code>rvs babel</code>`,
|
||||
`<div style="display:flex;flex-direction:column;gap:4px"><label class="cb-row"><input type="checkbox" id="sat-amd-target" checked><span>GPU Validate</span></label><label class="cb-row"><input type="checkbox" id="sat-amd-mem-target" checked><span>MEM Integrity</span></label><label class="cb-row"><input type="checkbox" id="sat-amd-bandwidth-target" checked><span>MEM Bandwidth</span></label></div>`,
|
||||
)) +
|
||||
`</div>
|
||||
<div id="sat-output" style="display:none;margin-top:16px" class="card">
|
||||
<div class="card-head">Test Output <span id="sat-title"></span></div>
|
||||
<div class="card-body"><div id="sat-terminal" class="terminal"></div></div>
|
||||
</div>
|
||||
<style>
|
||||
.validate-card-body { padding:0; }
|
||||
.validate-card-section { padding:12px 16px 0; }
|
||||
.validate-card-section:last-child { padding-bottom:16px; }
|
||||
.sat-gpu-row { display:flex; align-items:flex-start; gap:8px; padding:6px 0; cursor:pointer; font-size:13px; }
|
||||
.sat-gpu-row input[type=checkbox] { width:16px; height:16px; margin-top:2px; flex-shrink:0; }
|
||||
.cb-row { display:flex; align-items:flex-start; gap:8px; padding:4px 0; cursor:pointer; font-size:13px; }
|
||||
.cb-row input[type=checkbox] { width:16px; height:16px; margin-top:2px; flex-shrink:0; }
|
||||
</style>
|
||||
<script>
|
||||
let satES = null;
|
||||
function satLabels() {
|
||||
return {nvidia:'Check GPU (DCGM L2)', 'nvidia-interconnect':'NVIDIA Interconnect (NCCL)', 'nvidia-bandwidth':'NVIDIA Bandwidth (NVBandwidth)', memory:'Check Memory', storage:'Check Storage', cpu:'Check CPU', amd:'Check AMD GPU', 'amd-mem':'AMD GPU MEM Integrity', 'amd-bandwidth':'AMD GPU MEM Bandwidth'};
|
||||
}
|
||||
let satNvidiaGPUsPromise = null;
|
||||
function loadSatNvidiaGPUs() {
|
||||
if (!satNvidiaGPUsPromise) {
|
||||
satNvidiaGPUsPromise = fetch('/api/gpu/nvidia').then(r => {
|
||||
if (!r.ok) throw new Error('Failed to load NVIDIA GPUs.');
|
||||
return r.json();
|
||||
}).then(list => Array.isArray(list) ? list : []);
|
||||
}
|
||||
return satNvidiaGPUsPromise;
|
||||
}
|
||||
function satSelectedGPUIndices() {
|
||||
return Array.from(document.querySelectorAll('.sat-nvidia-checkbox'))
|
||||
.filter(el => el.checked && !el.disabled)
|
||||
.map(el => parseInt(el.value, 10))
|
||||
.filter(v => !Number.isNaN(v))
|
||||
.sort((a, b) => a - b);
|
||||
}
|
||||
function satUpdateGPUSelectionNote() {
|
||||
const note = document.getElementById('sat-gpu-selection-note');
|
||||
if (!note) return;
|
||||
const sel = satSelectedGPUIndices();
|
||||
note.textContent = sel.length
|
||||
? 'Selected GPUs: ' + sel.join(', ') + '. Multi-GPU tests will use all selected GPUs.'
|
||||
: 'Select at least one NVIDIA GPU to enable NVIDIA check tasks.';
|
||||
}
|
||||
function satRenderGPUList(gpus) {
|
||||
const root = document.getElementById('sat-gpu-list');
|
||||
if (!root) return;
|
||||
if (!gpus || !gpus.length) {
|
||||
root.innerHTML = '<p style="color:var(--muted);font-size:13px">No NVIDIA GPUs detected.</p>';
|
||||
satUpdateGPUSelectionNote(); return;
|
||||
}
|
||||
root.innerHTML = gpus.map(gpu => {
|
||||
const mem = gpu.memory_mb > 0 ? ' · ' + gpu.memory_mb + ' MiB' : '';
|
||||
return '<label class="sat-gpu-row"><input class="sat-nvidia-checkbox" type="checkbox" value="' + gpu.index + '" checked onchange="satUpdateGPUSelectionNote()"><span><strong>GPU ' + gpu.index + '</strong> — ' + gpu.name + mem + '</span></label>';
|
||||
}).join('');
|
||||
satUpdateGPUSelectionNote();
|
||||
}
|
||||
function satSelectAllGPUs() { document.querySelectorAll('.sat-nvidia-checkbox').forEach(el => { el.checked = true; }); satUpdateGPUSelectionNote(); }
|
||||
function satSelectNoGPUs() { document.querySelectorAll('.sat-nvidia-checkbox').forEach(el => { el.checked = false; }); satUpdateGPUSelectionNote(); }
|
||||
function satGPULoadInit() {
|
||||
loadSatNvidiaGPUs().then(satRenderGPUList).catch(err => {
|
||||
const root = document.getElementById('sat-gpu-list');
|
||||
if (root) root.innerHTML = '<p style="color:var(--crit-fg);font-size:13px">Error: ' + err.message + '</p>';
|
||||
satUpdateGPUSelectionNote();
|
||||
});
|
||||
}
|
||||
function satRequestBody(target, overrides) {
|
||||
const body = {};
|
||||
const labels = satLabels();
|
||||
body.display_name = labels[target] || ('Check ' + target);
|
||||
body.stress_mode = false;
|
||||
if (target === 'cpu') body.duration = 60;
|
||||
if (overrides) Object.keys(overrides).forEach(k => { body[k] = overrides[k]; });
|
||||
return body;
|
||||
}
|
||||
function enqueueSATTarget(target, overrides) {
|
||||
return fetch('/api/sat/' + target + '/run', {method:'POST', headers:{'Content-Type':'application/json'}, body:JSON.stringify(satRequestBody(target, overrides))}).then(r => r.json());
|
||||
}
|
||||
function streamSATTask(taskId, title, resetTerminal) {
|
||||
if (satES) { satES.close(); satES = null; }
|
||||
document.getElementById('sat-output').style.display = 'block';
|
||||
document.getElementById('sat-title').textContent = '— ' + title;
|
||||
const term = document.getElementById('sat-terminal');
|
||||
if (resetTerminal) term.textContent = '';
|
||||
term.textContent += 'Task ' + taskId + ' queued. Streaming log...\n';
|
||||
return new Promise(resolve => {
|
||||
satES = new EventSource('/api/tasks/' + taskId + '/stream');
|
||||
satES.onmessage = e => { term.textContent += e.data + '\n'; term.scrollTop = term.scrollHeight; };
|
||||
satES.addEventListener('done', e => {
|
||||
satES.close(); satES = null;
|
||||
term.textContent += (e.data ? '\nERROR: ' + e.data : '\nCompleted.') + '\n';
|
||||
term.scrollTop = term.scrollHeight;
|
||||
resolve({ok: !e.data, error: e.data || ''});
|
||||
});
|
||||
satES.onerror = () => {
|
||||
if (satES) { satES.close(); satES = null; }
|
||||
term.textContent += '\nERROR: stream disconnected.\n';
|
||||
term.scrollTop = term.scrollHeight;
|
||||
resolve({ok: false, error: 'stream disconnected'});
|
||||
};
|
||||
});
|
||||
}
|
||||
function selectedAMDValidateTargets() {
|
||||
const targets = [];
|
||||
const gpu = document.getElementById('sat-amd-target');
|
||||
const mem = document.getElementById('sat-amd-mem-target');
|
||||
const bw = document.getElementById('sat-amd-bandwidth-target');
|
||||
if (gpu && gpu.checked && !gpu.disabled) targets.push('amd');
|
||||
if (mem && mem.checked && !mem.disabled) targets.push('amd-mem');
|
||||
if (bw && bw.checked && !bw.disabled) targets.push('amd-bandwidth');
|
||||
return targets;
|
||||
}
|
||||
function runSAT(target) { return runSATWithOverrides(target, null); }
|
||||
function runSATWithOverrides(target, overrides) {
|
||||
const title = (overrides && overrides.display_name) || target;
|
||||
document.getElementById('sat-output').style.display = 'block';
|
||||
document.getElementById('sat-title').textContent = '— ' + title;
|
||||
const term = document.getElementById('sat-terminal');
|
||||
term.textContent = 'Enqueuing ' + title + ' test...\n';
|
||||
return enqueueSATTarget(target, overrides).then(d => streamSATTask(d.task_id, title, false));
|
||||
}
|
||||
function runNvidiaFabricValidate(target) {
|
||||
const indices = satSelectedGPUIndices();
|
||||
if (!indices.length) { alert('No NVIDIA GPUs available.'); return; }
|
||||
runSATWithOverrides(target, {gpu_indices: indices, display_name: satLabels()[target] || target});
|
||||
}
|
||||
function runNvidiaValidateSet(target) {
|
||||
const sel = satSelectedGPUIndices();
|
||||
if (!sel.length) { alert('Select at least one NVIDIA GPU.'); return; }
|
||||
return runSATWithOverrides(target, {gpu_indices: sel, display_name: satLabels()[target] || target});
|
||||
}
|
||||
function runAMDValidateSet() {
|
||||
const targets = selectedAMDValidateTargets();
|
||||
if (!targets.length) return;
|
||||
if (targets.length === 1) return runSAT(targets[0]);
|
||||
const term = document.getElementById('sat-terminal');
|
||||
document.getElementById('sat-output').style.display = 'block';
|
||||
document.getElementById('sat-title').textContent = '— amd';
|
||||
term.textContent = 'Running AMD check set...\n';
|
||||
const labels = satLabels();
|
||||
const runNext = idx => {
|
||||
if (idx >= targets.length) return Promise.resolve();
|
||||
const t = targets[idx];
|
||||
term.textContent += '\n[' + (idx + 1) + '/' + targets.length + '] ' + labels[t] + '\n';
|
||||
return enqueueSATTarget(t).then(d => streamSATTask(d.task_id, labels[t], false)).then(() => runNext(idx + 1));
|
||||
};
|
||||
return runNext(0);
|
||||
}
|
||||
function runAllCheckSAT() {
|
||||
const status = document.getElementById('sat-all-status');
|
||||
status.textContent = 'Enqueuing...';
|
||||
const nvidiaIndices = satSelectedGPUIndices();
|
||||
const nvidiaAllTargets = ['nvidia', 'nvidia-interconnect', 'nvidia-bandwidth'];
|
||||
const baseTargets = ['cpu', 'memory', 'storage'];
|
||||
const amdTargets = selectedAMDValidateTargets();
|
||||
const expanded = [];
|
||||
baseTargets.forEach(t => expanded.push({target: t}));
|
||||
if (nvidiaIndices.length) {
|
||||
nvidiaAllTargets.forEach(t => {
|
||||
const btn = document.getElementById('sat-btn-' + t);
|
||||
if (!(btn && btn.disabled)) expanded.push({target: t, overrides: {gpu_indices: nvidiaIndices, display_name: satLabels()[t] || t}});
|
||||
});
|
||||
}
|
||||
amdTargets.forEach(t => expanded.push({target: t}));
|
||||
if (!expanded.length) { status.textContent = 'No tasks selected.'; return; }
|
||||
const total = expanded.length;
|
||||
const runNext = idx => {
|
||||
if (idx >= expanded.length) { status.textContent = 'Completed ' + total + ' task(s).'; return Promise.resolve(); }
|
||||
const item = expanded[idx];
|
||||
status.textContent = 'Running ' + (idx + 1) + '/' + total + '...';
|
||||
return enqueueSATTarget(item.target, item.overrides).then(() => runNext(idx + 1));
|
||||
};
|
||||
runNext(0).catch(err => { status.textContent = 'Error: ' + err.message; });
|
||||
}
|
||||
function disableSATCard(id, reason) {
|
||||
const btn = document.getElementById('sat-btn-' + id);
|
||||
if (!btn) return;
|
||||
btn.disabled = true; btn.title = reason; btn.style.opacity = '0.4';
|
||||
const card = btn.closest('.card');
|
||||
if (card) {
|
||||
let note = card.querySelector('.sat-unavail');
|
||||
if (!note) {
|
||||
note = document.createElement('p');
|
||||
note.className = 'sat-unavail';
|
||||
note.style.cssText = 'color:var(--muted);font-size:12px;margin:0 0 8px';
|
||||
const body = card.querySelector('.card-body');
|
||||
if (body) body.insertBefore(note, body.firstChild);
|
||||
}
|
||||
note.textContent = reason;
|
||||
}
|
||||
}
|
||||
fetch('/api/gpu/presence').then(r => r.json()).then(gp => {
|
||||
if (!gp.nvidia) ['nvidia','nvidia-interconnect','nvidia-bandwidth'].forEach(t => disableSATCard(t, 'No NVIDIA GPU detected'));
|
||||
if (!gp.amd) {
|
||||
disableSATCard('amd', 'No AMD GPU detected');
|
||||
['sat-amd-target','sat-amd-mem-target','sat-amd-bandwidth-target'].forEach(id => {
|
||||
const cb = document.getElementById(id);
|
||||
if (cb) { cb.disabled = true; cb.checked = false; }
|
||||
});
|
||||
}
|
||||
});
|
||||
satGPULoadInit();
|
||||
</script>`
|
||||
}
|
||||
|
||||
func renderSATCard(id, label, runAction, headerActions, body string) string {
|
||||
actions := `<button id="sat-btn-` + id + `" class="btn btn-primary btn-sm" onclick="` + runAction + `">Run</button>`
|
||||
if strings.TrimSpace(headerActions) != "" {
|
||||
|
||||
Reference in New Issue
Block a user