biopattern(8)

✨ biopattern(8) — System Manager's Manual ✨

💖 NAME

biopattern - Identify random/sequential disk access patterns. 🦋

📝 SYNOPSIS

biopattern [-h] [-d DISK] [interval] [count]

🌸 DESCRIPTION

okay so bestie, this one traces block device I/O (aka disk I/O) and spits out the ratio of random vs sequential I/O 💅 for each disk, or just the specified disk if you ask for one. You get the summary either when you hit Ctrl-C or after a given interval in seconds ✨

this works by tracing the kernel tracepoint block:block_rq_complete 🔥

heads up 💀 since this uses BPF, only the root user can use this tool. no cap, you need to be root.

🎀 REQUIREMENTS

you'll need CONFIG_BPF and bcc 🫶

✨ OPTIONS ✨

• -h — show the help message and exit 💜
• -d — trace this disk only 🎯
• interval — print output every interval seconds, if any 🌈
• count — number of interval summaries 🍓

🧚 EXAMPLES

trace access patterns of all disks, and print a summary on Ctrl-C:

# biopattern

trace disk sdb only:

# biopattern -d sdb

print 1 second summaries, 10 times:

# biopattern 1 10

👑 FIELDS

• TIME — time of the output, in HH:MM:SS format ⭐
• DISK — disk device name 💖
• %RND — ratio of random I/O 🌸
• %SEQ — ratio of sequential I/O 🦋
• COUNT — number of I/O during the interval 🔥
• KBYTES — total Kbytes for these I/O, during the interval 💅

🫧 OVERHEAD

block device I/O usually has a relatively low frequency (< 10,000/s), so the overhead for this tool is expected to be low or negligible. ngl, for high IOPS storage systems, test and quantify before use 🙈

🌈 SOURCE

this is from bcc 💜

https://github.com/iovisor/bcc

also look in the bcc distribution for a companion _examples.txt file containing example usage, output, and commentary for this tool 🎀

💅 OS

Linux 🐧

⚠️ STABILITY

Unstable - in development 🙈

💫 AUTHOR

Rocky Xing ✨

🦋 SEE ALSO

biosnoop(8), biolatency(8), iostat(1) 🫶

---

bye bestie, that's the whole tea ☕🌸 biopattern(8) from the bcc crew, last updated 2022-02-21, under USER COMMANDS 💖 stay iconic 🧚✨