{"slug": "ramsleuth-ram-telemetry-memory-benchmark-for-linux", "title": "RamSleuth — RAM telemetry + memory benchmark for Linux", "summary": "A user testing RamSleuth, a Linux RAM telemetry and memory benchmark tool, found that the utility misreports memory channel mode and doubles MCLK to report 3600MT/s DDR4 as 7200MT/s. The user traced the channel-mode bug with DeepSeek V4.1 Flash to a collector that reads the DMI entry folder as a file, errors, and swallows the failure via a continue-on-error argument, reporting 0 and never triggering the override guard; a patched version now reports channel_mode: Some(DualSymmetric) and channel_trust: Some(Override) with dimm_count: 2. The user also reported UI bugs, including graphs and probe reports that fail to redraw the terminal region below them and a burn-in test elapsed counter that does not tick up.", "body_md": "Checking it out now:\n\nIt’s now picking up the vcore reading!\n\nStill thinks it’s single-channel though, digging into why now with DeepSeek. In the meantime, a couple UI notes:\n\nThe graph function doesn’t re-draw the rest of the terminal window section below it, so those values just sit there, makes it hard to read. The probe report option also does this, only over-writing the blue border and the consent buttons, so it’s nigh impossible to read:\n\nOn the burn-in test, the “#:## elapsed” counter doesn’t tick up. I think that’s all the UI bugs I can find so far.\n\nI can’t upload .md files, so here’s a paste of the probe report in a hide section, so it won’t make everyone scroll a million years .\n\nprobe-report\nAlright, DS figured it out. The collector looks at the dmi entry folder as a file, errors, the continue on error arg swallows it, so it reports 0. That way it never triggers the override guard. The test creates the mock entry as a file, so it passes. The parser is reading the wrong values on this system too. Here’s DS’s summary:\n\nDeepSeek V4.1 Flash’s Report\nThe patched version reads correctly:\n\n`channel_mode: Some(DualSymmetric)`\n\n`channel_trust: Some(Override)`\n\n`channel_annotation: \"[Override: MCHBAR decoded Single-Channel`\n\n`dimm_count: 2 }\"`\n\nAnd here’s the raw hex dumps and dmidecode:\n\n17-0/raw hex dump\nAnd the probe-report after the patch:\n\nprobe-report-2\nAnother small catch while reading the probe-report again, it doubles what it reads as MCLK and reports that as MT/s. So it thinks my 3600 “MHz” (1800Mhz, 3600MT/s) DDR4 is running at 7200MT/s.", "url": "https://wpnews.pro/news/ramsleuth-ram-telemetry-memory-benchmark-for-linux", "canonical_source": "https://forum.level1techs.com/t/ramsleuth-ram-telemetry-memory-benchmark-for-linux/256922#post_9", "published_at": "2026-10-10 02:09:48+00:00", "updated_at": "2026-10-10 02:27:40.170315+00:00", "lang": "en", "topics": ["ai-tools"], "entities": ["RamSleuth", "DeepSeek V4.1 Flash", "DeepSeek", "Linux"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/ramsleuth-ram-telemetry-memory-benchmark-for-linux", "markdown": "https://wpnews.pro/news/ramsleuth-ram-telemetry-memory-benchmark-for-linux.md", "text": "https://wpnews.pro/news/ramsleuth-ram-telemetry-memory-benchmark-for-linux.txt", "jsonld": "https://wpnews.pro/news/ramsleuth-ram-telemetry-memory-benchmark-for-linux.jsonld"}}