Thanks — good info. You’re already in Slax and the transcript shows two things we expected: Slax doesn’t have sudo/libinput installed (so the sudo attempts failed) and you successfully started dmesg capture as root. That’s fine — being root means sudo isn’t needed. I’ll give a short fallback plan (exact commands) so you can monitor the mouse input events directly and capture everything we need. This follows the Slax flow we discussed earlier.
First — quick summary of your current state (based on your paste)
- dmesg capture started (you launched it as root).
- libinput was not found so libinput debug-events didn’t run.
- lsusb and /proc/bus/input/devices were saved to /tmp files.
If the mouse hasn’t dropped yet, continue using it now until it does; if it already dropped, stop the captures immediately (commands below).
If the mouse has already dropped — stop dmesg now and produce lsusb/input snapshots:
Run these two commands now (you’re root so no sudo):
sh -c "kill $(cat /tmp/dmesg_dmesg_pid.txt) || true"
lsusb > /tmp/lsusb_after.txt
cat /proc/bus/input/devices > /tmp/inputdev_after.txt
Then run the packaging step near the end of this message to create the .tgz and attach it.
If the mouse has NOT yet dropped — set up direct input monitoring and continue using it
1) Find which /dev/input/eventN is the mouse
Run (paste the output here):
awk '/^N: Name=/{name=$0} /^H: Handlers=/{print name \" -> \" $0}' /tmp/inputdev_before.txt
From that output, copy the line that shows the Logitech / HID‑compliant mouse (it will show the device Name and its Handlers including an eventX value). Paste that line here if you want me to pick the event number for you.
2) Start a raw event monitor on the event node (replace eventN with the event number from step 1)
If hexdump exists:
stdbuf -oL hexdump -C /dev/input/eventN > /tmp/mouse_event_hexdump.log & echo $! > /tmp/mouse_event_pid.txt
If hexdump is not present, fallback to a raw capture (binary):
cat /dev/input/eventN > /tmp/mouse_event_raw & echo $! > /tmp/mouse_event_pid.txt
Leave that running while you use the mouse. It will record activity; when the mouse stops sending events you’ll see the hexdump/ raw file stop growing.
3) When (and only when) the mouse drops — stop the captures
(sh -c is not needed since you are root)
kill $(cat /tmp/dmesg_dmesg_pid.txt) || true
kill $(cat /tmp/mouse_event_pid.txt) || true
lsusb > /tmp/lsusb_after.txt
cat /proc/bus/input/devices > /tmp/inputdev_after.txt
4) Package whatever files exist into a tarball for upload
START=$(date --iso-8601=seconds)
tar -czf /tmp/mouselinuxlogs_${START}.tgz $(ls /tmp/dmesg_live.log /tmp/lsusb_before.txt /tmp/lsusb_after.txt /tmp/lsusb_tree_before.txt /tmp/inputdev_before.txt /tmp/inputdev_after.txt /tmp/libinput_events.log /tmp/mouse_event_hexdump.log /tmp/mouse_event
raw 2>/dev/null) && echo "/tmp/mouselinuxlogs${START}.tgz created"
5) Copy the tarball to a USB stick or a location you can attach from the forum UI (example — adjust mount point):
cp /tmp/mouselinuxlogs_${START}.tgz /media/$(ls /media | head -n1)/
What I’ll check when you attach the .tgz (or paste key outputs)
- dmesg around the drop for USB disconnects / xhci_hcd / ehci_hcd / “USB disconnect” / “reset high-speed USB device” lines (host/controller reset).
- lsusb before/after: did the Unifying receiver disappear from the bus at drop time?
- input event log (hexdump): did input events stop while the receiver still shows in lsusb? If so, that points to an RF/session loss (device side).
These are exactly the diagnostics we planned for Slax.
If you want me to keep it very small, do this now:
- Run the awk command from step 1 and paste its output here (I’ll tell you the event number and the exact hexdump/capture command to run).
OR
- If the mouse already dropped, run the three stop + package commands I listed in the “already dropped” block and attach the tarball.
I’ll parse the logs immediately as soon as you attach them and tell you whether this isolates the problem to Windows (host/driver) or to the mouse/receiver (RF/hardware).
) [Get-WinEvent], Exception
