drjones/gpu-program-swapper
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Stop the dashboard reporting things that are not true

Browse Source 
A screenshot of the running dashboard showed four claims that the backend does not
support. Each is the same failure the rest of this branch has been correcting:
displaying a number without checking what it measures.

"Models in RAM: 54.31 GB" was ram.cached_gb -- the entire Linux page cache, every
file the kernel has cached, not models. Measured model residency at the same moment
was 42.87 GB of a 331 GB catalogue. The two are different quantities that happened
to look similar. The legend now says "Page Cache (all files)" for what that number
is, and shows measured model residency separately beside it.

"LAST SWAP TIME 1.65 ms" and "RAM HIT STATUS: Cleaned" were read from history[0],
the most recent event of any type. Both tiles were describing a ComfyUI VRAM purge:
its duration under a swap-time label, its status under a cache-hit label. They now
select the most recent LLM Model Switch, and fall back to the persisted log when the
in-memory ring is empty, so a restart no longer blanks them.

"Host Pinned Memory: 53.6 GB Staging Buffer", "Async PCIe Offloading: Enabled (2
Streams)" and "Fast Disk RAM Mmap: Active" were hardcoded in the HTML and measured
from nothing at all. Replaced with values the service actually has: VRAM currently
held by ComfyUI, live PCIe throughput from NVML, measured checkpoint residency, and
the real idle-purge countdown.

Also: the VRAM legend's "System" bucket hid an 842 MB third-party process behind the
same label as a 3.9 MB compositor, so it is now split into Desktop and Unmanaged;
and the version badge read a hardcoded "v1.0-DEPLOY" while the API served 2.0.0, so
it now reads the version from /openapi.json.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
drjones
2026-09-05 23:48:37 -07:00
parent 2948b0b440
commit b53b026ced
2 changed files with 123 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

99
static/app.js
View File

@@ -154,6 +154,29 @@ function updateDashboard(data) {
document.getElementById('legend-ram-used').textContent = `${ram.used_gb || 0} GB`;
document.getElementById('legend-ram-cached').textContent = `${ram.cached_gb || 0} GB`;
// Split the old catch-all: desktop compositor vs VRAM we cannot reclaim.
const vbd = gpu.breakdown || {};
const unmanagedEl = document.getElementById('legend-vram-unmanaged');
if (unmanagedEl) unmanagedEl.textContent = `${vbd.unmanaged_gb ?? 0} GB`;
const sysEl = document.getElementById('legend-system');
if (sysEl) sysEl.textContent = `${vbd.desktop_gb ?? 0} GB`;
// Measured ComfyUI facts, replacing the panel's previously hardcoded ones.
const held = document.getElementById('comfy-vram-held');
if (held) held.textContent = `${vbd.comfyui_gb ?? 0} GB`;
const pcie = document.getElementById('comfy-pcie');
if (pcie) {
const tx = (gpu.pcie_tx_kbps || 0) / 1024, rx = (gpu.pcie_rx_kbps || 0) / 1024;
pcie.textContent = `${tx.toFixed(1)} / ${rx.toFixed(1)} MB/s`;
}
const purge = document.getElementById('comfy-purge-state');
if (purge && data.arbitrator) {
const a = data.arbitrator;
purge.textContent = a.pending_purge && a.comfy_idle_s != null
? `in ${Math.max((a.idle_purge_after_s || 0) - a.comfy_idle_s, 0).toFixed(0)}s`
: (a.comfy_active ? 'generating' : 'idle');
}
document.getElementById('legend-ram-free').textContent = `${ram.free_gb || 0} GB`;
}
@@ -225,9 +248,14 @@ function updateDashboard(data) {
const history = data.history || [];
const logContainer = document.getElementById('switch-log-container');
if (history.length > 0) {
const latest = history[0];
document.getElementById('ollama-last-swap').textContent = `${latest.duration_ms} ms`;
document.getElementById('ollama-cache-hit').textContent = latest.cache_status || 'OK';
// These tiles are labelled "last swap time" and "RAM hit status", so they must come
// from an actual model swap. Reading history[0] meant a ComfyUI purge showed its
// 1.65 ms duration as the swap time and its "Cleaned" status as a cache result.
const lastSwap = history.find(h => h.event_type === 'LLM Model Switch');
document.getElementById('ollama-last-swap').textContent =
lastSwap ? `${lastSwap.duration_ms} ms` : '\u2014';
document.getElementById('ollama-cache-hit').textContent =
lastSwap ? (lastSwap.cache_status || 'OK') : 'no swaps yet';
logContainer.innerHTML = history.slice(0, 10).map(item => {
const isHit = (item.cache_status || '').includes('RAM Cache Hit') || (item.cache_status || '').includes('RAM-Cached');
@@ -976,3 +1004,68 @@ document.addEventListener('DOMContentLoaded', () => {
fetchHealth(false);
setInterval(() => fetchHealth(false), 60000);
});
// ---------------------------------------------------------------- honest labels
async function fetchMeasuredResidency() {
const el = document.getElementById('legend-models-resident');
if (!el) return;
try {
const d = await (await fetch('/api/cache/report?files=false')).json();
// Deliberately distinct from the page-cache figure beside it: that is every file
// the kernel has cached; this is model weights, measured.
el.textContent = `${d.resident_total_gb} GB of ${d.catalog_total_gb} GB`;
const cr = document.getElementById('comfy-resident');
if (cr) cr.textContent = `${d.residency_pct}%`;
} catch (e) {
el.textContent = 'unavailable';
}
}
async function fetchVersion() {
const el = document.getElementById('app-version');
if (!el) return;
try {
const d = await (await fetch('/openapi.json')).json();
el.textContent = `v${d.info.version}`;
} catch (e) {
el.textContent = 'v?';
}
}
document.addEventListener('DOMContentLoaded', () => {
fetchVersion();
fetchMeasuredResidency();
setInterval(fetchMeasuredResidency, 30000);
});
// ---------------------------------------------------------------- durable swap stats
let lastSwapFromStore = null;
async function fetchLastSwapFromStore() {
// The in-memory ring empties on restart, which blanked the swap tiles even though
// every swap is on disk. Fall back to the persisted log so a restart does not erase
// what the dashboard knows.
try {
const rows = await (await fetch('/api/history?durable=true&limit=50')).json();
const swap = (rows || []).find(r => r.event_type === 'LLM Model Switch');
if (!swap) return;
lastSwapFromStore = swap;
const t = document.getElementById('ollama-last-swap');
const c = document.getElementById('ollama-cache-hit');
if (t && (!t.textContent || t.textContent.includes('\u2014') || t.textContent.includes('--'))) {
t.textContent = `${Math.round(swap.duration_ms)} ms`;
}
if (c && (!c.textContent || c.textContent.includes('\u2014') || c.textContent.includes('--')
|| c.textContent === 'no swaps yet')) {
c.textContent = swap.cache_status || 'OK';
}
} catch (e) { /* the live stream is the primary source; this is only a fallback */ }
}
document.addEventListener('DOMContentLoaded', () => {
setTimeout(fetchLastSwapFromStore, 1500);
});