fix: retry transient RM allocation failures so power control block doesn't vanish
GSP transiently rejects NV0080 object allocation with status 0x1f when busy — reliably on the first probe in a fresh server process and intermittently right after RM operations (e.g. a power-limit write). The probe surfaced that transient rejection as rm_power_supported=false, making the Experimental Power Control block disappear in the UI until a reload re-probed successfully. - hal/rm_power: RmHandle.open() now retries the handle allocation (3 attempts, 100 ms apart) before reporting the interface unavailable; covers probe, set, and enable-check paths. Each attempt cleans up its own fds, so retries are safe and idempotent. - PerformancePanel: confirm a negative rm_power_supported reading with one follow-up fetch before rendering it, so a single flaky probe can't hide the block or flip it into "interface unavailable"; the confirm has its own error boundary so a failed second request keeps the first (valid) read. Also added a monotonic fetch-seq guard so a slow response for a previously selected GPU cannot clobber fresher state. - tests: cover transient-failure-retry and persistent-failure paths for RmHandle.open. Verified live: first probe after restart 5/5 (was 0/3), 150 rapid set+get cycles with 0 probe flips and 0 set failures.
This commit is contained in:
1 parent
6afdd15d2a
commit
2e8e580d79
3 files changed
+137
-4
No files matched your search
@@ -1,4 +1,4 @@
|
||||
import { useState, useEffect } from "react";
|
||||
import { useState, useEffect, useRef } from "react";
|
||||
import { Check, X, RotateCcw } from "lucide-react";
|
||||
import { api } from "../../api/client.js";
|
||||
import { useCurveStore } from "../../store/curveStore.js";
|
||||
@@ -17,15 +17,45 @@ export function PerformancePanel() {
|
||||
const [error, setError] = useState<string | null>(null);
|
||||
const [confirmApply, setConfirmApply] = useState(false);
|
||||
const [confirmReset, setConfirmReset] = useState(false);
|
||||
// Monotonic fetch counter: a response may only commit state (or toast /
|
||||
// clear loading) if it is still the latest fetch for this panel, so a slow
|
||||
// response for a previously selected GPU cannot clobber fresher results.
|
||||
const fetchSeq = useRef(0);
|
||||
|
||||
async function fetchLimits() {
|
||||
const seq = ++fetchSeq.current;
|
||||
try {
|
||||
setLoading(true);
|
||||
setLimits(await api.limits(selectedGpuIndex));
|
||||
let next = await api.limits(selectedGpuIndex);
|
||||
// The RM support probe can flake transiently (the driver briefly
|
||||
// rejects RM object allocation when busy) and report
|
||||
// rm_power_supported=false for one read. A single failed read must not
|
||||
// make the Experimental Power Control block vanish — or flip it into
|
||||
// "interface unavailable" — so confirm a negative reading with one
|
||||
// follow-up fetch before trusting it. The confirm has its own error
|
||||
// boundary: if it throws (network blip), keep the first result, which
|
||||
// is still a valid read, rather than discarding it into the outer catch.
|
||||
if (!next.rm_power_supported) {
|
||||
try {
|
||||
const again = await api.limits(selectedGpuIndex);
|
||||
if (again.rm_power_supported) {
|
||||
next = again;
|
||||
}
|
||||
} catch {
|
||||
// keep first result
|
||||
}
|
||||
}
|
||||
if (seq === fetchSeq.current) {
|
||||
setLimits(next);
|
||||
}
|
||||
} catch {
|
||||
toast.error("Failed to load performance limits");
|
||||
if (seq === fetchSeq.current) {
|
||||
toast.error("Failed to load performance limits");
|
||||
}
|
||||
} finally {
|
||||
setLoading(false);
|
||||
if (seq === fetchSeq.current) {
|
||||
setLoading(false);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
Reference in new issue
Block a user