grant/spark-control
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 3 Wiki Activity

v0.3.0:1 - hotfix: parallel SSH probes + longer timeout

Browse Source 
- Hardware probes for spark1 and spark2 now run via asyncio.gather (parallel) so the worst-case wall time is max(per-probe), not sum
- Bump per-probe SSH timeout from 8s to 12s to absorb first-call overhead (StrictHostKeyChecking=accept-new on first connect + nvidia-smi cold start)
- Unreachable Spark now shows up cleanly in the UI as a single 'unreachable' card with the error message
This commit is contained in:
Grant
2026-05-12 12:14:36 -05:00
parent 64ce0fca10
commit e88fdcfde4
2 changed files with 7 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
image/app/hardware.py
+6 -5
View File
@@ -96,10 +96,11 @@ class HardwareProbe:
return self._locks[key] return self._locks[key]
async def fetch(self) -> dict: async def fetch(self) -> dict:
return { s1, s2 = await asyncio.gather(
"spark1": await self._one("spark1", self.settings.spark1_host, self.settings.spark1_user), self._one("spark1", self.settings.spark1_host, self.settings.spark1_user),
"spark2": await self._one("spark2", self.settings.spark2_host, self.settings.spark2_user), self._one("spark2", self.settings.spark2_host, self.settings.spark2_user),
} )
return {"spark1": s1, "spark2": s2}
async def _one(self, key: str, host: str, user: str) -> dict: async def _one(self, key: str, host: str, user: str) -> dict:
if not host or not user: if not host or not user:
@@ -109,7 +110,7 @@ class HardwareProbe:
cached = self._cache.get(key) cached = self._cache.get(key)
if cached and (now - cached[0] < self.ttl_sec): if cached and (now - cached[0] < self.ttl_sec):
return cached[1] return cached[1]
rc, out, err = await ssh_run(host, user, _PROBE, self.settings, timeout=8) rc, out, err = await ssh_run(host, user, _PROBE, self.settings, timeout=12)
if rc != 0: if rc != 0:
result = {"reachable": False, "configured": True, "host": host, "error": err.strip() or out.strip() or f"rc={rc}"} result = {"reachable": False, "configured": True, "host": host, "error": err.strip() or out.strip() or f"rc={rc}"}
else: else:
package/startos/versions/v0_1_0.ts
+1 -1
View File
@@ -1,7 +1,7 @@
import { VersionInfo, IMPOSSIBLE } from '@start9labs/start-sdk' import { VersionInfo, IMPOSSIBLE } from '@start9labs/start-sdk'
export const v0_1_0 = VersionInfo.of({ export const v0_1_0 = VersionInfo.of({
version: '0.3.0:0', version: '0.3.0:1',
releaseNotes: { releaseNotes: {
en_US: en_US:
'v0.3: Spark hardware dashboard (RAM, disk, GPU memory + utilization, CPU load, uptime per Spark). Per-model Advanced settings now show plain-English hints tied to your actual GPU memory (e.g. "0.85 GPU util leaves ~18 GB free"). "Explain context" button on the update banner asks the loaded LLM to summarize pending commits in plain English. Optional Open WebUI URL in Configure Sparks shows a one-click "Open chat" button in the top bar. Downloads can now target Spark 1, Spark 2, or both. Each model card links out to its Hugging Face page.', 'v0.3: Spark hardware dashboard (RAM, disk, GPU memory + utilization, CPU load, uptime per Spark). Per-model Advanced settings now show plain-English hints tied to your actual GPU memory (e.g. "0.85 GPU util leaves ~18 GB free"). "Explain context" button on the update banner asks the loaded LLM to summarize pending commits in plain English. Optional Open WebUI URL in Configure Sparks shows a one-click "Open chat" button in the top bar. Downloads can now target Spark 1, Spark 2, or both. Each model card links out to its Hugging Face page.',