#!/usr/bin/python3
#
# disksnoop.py	Trace block device I/O: basic version of iosnoop.
#		For Linux, uses BCC, eBPF. Embedded C.
#
# Written as a basic example of tracing latency.
#
# Copyright (c) 2015 Brendan Gregg.
# Licensed under the Apache License, Version 2.0 (the "License")
#
# 11-Aug-2015	Brendan Gregg	Created this.

from __future__ import print_function
from bcc import BPF
from bcc.utils import printb

REQ_WRITE = 1		# from include/linux/blk_types.h

# load BPF program
b = BPF(text="""
#include <uapi/linux/ptrace.h>
#include <linux/blkdev.h>

BPF_HASH(start, struct request *);

void trace_start(struct pt_regs *ctx, struct request *req) {
	// stash start timestamp by request ptr
	u64 ts = bpf_ktime_get_ns();

	start.update(&req, &ts);
}

void trace_completion(struct pt_regs *ctx, struct request *req) {
	u64 *tsp, delta;

	tsp = start.lookup(&req);
	if (tsp != 0) {
		delta = bpf_ktime_get_ns() - *tsp;
		bpf_trace_printk("%d %x %d\\n", req->__data_len,
		    req->cmd_flags, delta / 1000);
		start.delete(&req);
	}
}
""")

b.attach_kprobe(event="blk_start_request", fn_name="trace_start")
b.attach_kprobe(event="blk_mq_start_request", fn_name="trace_start")
b.attach_kprobe(event="blk_account_io_completion", fn_name="trace_completion")

# header
print("%-18s %-2s %-7s %8s" % ("TIME(s)", "T", "BYTES", "LAT(ms)"))

# format output
while 1:
	try:
		(task, pid, cpu, flags, ts, msg) = b.trace_fields()
		(bytes_s, bflags_s, us_s) = msg.split()

		if int(bflags_s, 16) & REQ_WRITE:
			type_s = b"W"
		elif bytes_s == "0":	# see blk_fill_rwbs() for logic
			type_s = b"M"
		else:
			type_s = b"R"
		ms = float(int(us_s, 10)) / 1000

		printb(b"%-18.9f %-2s %-7s %8.2f" % (ts, type_s, bytes_s, ms))
	except KeyboardInterrupt:
		exit()