KVM_STAT(1)

💅 KVM_STAT(1) — the manual, but make it group chat

okay bestie, so this is kvm_stat, a page from the KVM_STAT(1) manual, and I'm about to tell you everything about it. no cap, every single flag. let's go 🎀

✨ NAME ✨

kvm_stat — reports KVM kernel module event counters. that's it, that's the whole job, and it does it beautifully. 💖

🌸 SYNOPSIS 🌸

kvm_stat [OPTION]...

🦋 DESCRIPTION 🦋

so kvm_stat prints counts of KVM kernel module trace events. these events are literally the receipts of state transitions — things like guest mode entry and exit. 👑

this tool is genuinely iconic for observing guest behavior from the host perspective. like, you're on the outside looking in, and ngl, a lot of conclusions about performance or buggy behavior can be drawn from the output. while you're running in regular mode, just press any of the keys listed in the Interactive Commands section below. and if you're scripting? use batch and logging modes, bestie. 🫶

heads up: the set of KVM kernel module trace events may be specific to your kernel version or architecture. it's best to check the KVM kernel module source code for the meaning of events. iykyk — the manpage can't do everything for you. 💀

---

🎀 INTERACTIVE COMMANDS 🎀

• b — toggle events by guests (debugfs only, honors filters)
• c — clear filter
• f — filter by regular expression

Note: Child events pull in their parents, and parents' stats summarize all child events, not just the filtered ones. so like, don't be surprised, okay?

• g — filter by guest name/PID
• h — display interactive commands reference
• o — toggle sorting order (Total vs CurAvg/s)
• p — filter by guest name/PID
• q — quit
• r — reset stats
• s — set delay between refreshs
• x — toggle reporting of stats for child trace events

Note: The stats for the parents summarize the respective child trace events

press any other key to refresh statistics immediately. yes, any other key. it's giving "surprise me." 😭

---

🔥 OPTIONS 🔥

• -1, --once, --batch — run in batch mode for one second
• -c, --csv — log in csv format. requires option -l/--log or -L/--log-to-file. when used with option -L/--log-to-file, the header is only ever written to start of file to preserve the format. (iconic restraint, honestly 💅)
• -d, --debugfs — retrieve statistics from debugfs
• -f<fields>, --fields=<fields> — fields to display (regex), -f help for a list of available events
• -g<guest>, --guest=<guest_name> — limit statistics to one virtual machine (guest name)
• -h, --help — show help message
• -i, --debugfs-include-past — include all available data on past events for debugfs
• -l, --log — run in logging mode (like vmstat)
• -L<file>, --log-to-file=<file> — like -l/--log, but logging to a file. appends to existing files. (no clobbering, we respect the data 🫶)
• -p<pid>, --pid=<pid> — limit statistics to one virtual machine (pid)
• -s, --set-delay — set delay between refreshs (value range: 0.1-25.5 secs)
• -t, --tracepoints — retrieve statistics from tracepoints
• -z, --skip-zero-records — omit records with all zeros in logging mode

---

🌈 SEE ALSO 🌈

perf(1), trace-cmd(1) — your other besties, go say hi 💜

👑 AUTHOR 👑

Stefan Hajnoczi <stefanha@redhat.com> — the main character who wrote this. respect. 🙈

---

and that's the whole page, bestie! 🦋 this was KVM_STAT(1), version KVM_STAT(1), dated 11/01/2026. bookmark it, screenshot it, send it to the group chat — it ate and left no crumbs. ✨💖🎀