AIToday
Large Language ModelsZenn AI/MLPublished: Nov 21, 2026, 16:00 JST

TerminalHub heavy jobs: 30/30 finish, 11MB free, no SSD lockup

Send on LINE
TerminalHub heavy jobs: 30/30 finish, 11MB free, no SSD lockup

3 Key Points

  1. What happened

    Running Claude Code sessions via TerminalHub on one 32GB Windows PC, the user logged 33 heavy jobs over three days and summarized 30; all finished, including 9 that dropped free memory under 1GB, and the disk-saturation watcher never fired.

  2. Why it matters

    The old rule (stop when free memory falls below 1GB) would have halted 9 of those 30 jobs unnecessarily, since low free memory did not by itself predict the SSD stalling as the author had assumed.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, every morning.

Context & Analysis

The author had previously managed heavy jobs by reserving memory before starting them and stopping when free memory fell below 1GB. That approach assumed low free memory was a proxy for the two problems that actually matter: the PC becoming sluggish due to disk paging, and processes crashing when the commit limit (the total memory plus page file Windows will guarantee, 47.5GB on this machine) is reached. The three-day log shows free memory was a poor proxy for the first problem: a 40-minute ComfyUI generation that bottomed out at 11MB free memory averaged only 14% disk usage and raised page file usage by just 3.8 points. The distinction between the two problems appears in the one job that stopped, a roughly 57-minute ComfyUI run with no other reservations: disk usage averaged 30% and never met the saturation condition, but commit reached 46.1GB and the script's own line halted generation. The author also found the watcher's cadence (one 60-second window every 10 seconds) could miss short stalls, and fixed it to examine every window. The thresholds (90%, 60 seconds, +0.3 points) were derived from a single 24-image test, and the author notes they would likely differ on other SSDs or page file sizes. The rules were built for this specific PC with an integrated GPU sharing the same 32GB, not for a machine with dedicated GPU memory, and the watcher relies on Windows typeperf counters.

FAQ
What two conditions must be met for the watcher to flag disk saturation?
The 60-second average disk usage must exceed 90%, and the paging file usage must rise by more than 0.3 percentage points within the same 60 seconds. The first 2 minutes (model loading) are ignored.
What stopped the 57-minute ComfyUI run that had only 5MB free?
The image-generation script's own commit limit of 46.1GB halted it, and Claude Code also stopped the background scripts for low memory. The disk-saturation watcher did not fire because saturation never occurred.
Did the author find any gaps in the watcher's detection?
Yes, a re-analysis of all intervals found one 13-minute job with about 8 seconds that met the stop condition but was missed. The watcher only checked the single most recent 60-second window every 10 seconds; it was fixed to check every complete window since the last check.
Send on LINE

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.

Questions and answers are published on this page.

Related Articles

Next articleContra Pace: Ben Pace's one-graph case for LessWrong's writer decline