mirror of
https://github.com/torvalds/linux.git
synced 2024-11-10 14:11:52 +00:00
92632115fb
Recently, a new tracepoint for the block layer, specifically the block_io_start/done tracepoints, was introduced in commit5a80bd075f("block: introduce block_io_start/block_io_done tracepoints"). Previously, the kprobe entry used for this purpose was quite unstable and inherently broke relevant probes [1]. Now that a stable tracepoint is available, this commit replaces the bio latency check with it. One of the changes made during this replacement is the key used for the hash table. Since 'struct request' cannot be used as a hash key, the approach taken follows that which was implemented in bcc/biolatency [2]. (uses dev:sector for the key) [1]: https://github.com/iovisor/bcc/issues/4261 [2]: https://github.com/iovisor/bcc/pull/4691 Fixes:450b7879e3("block: move blk_account_io_{start,done} to blk-mq.c") Signed-off-by: Daniel T. Lee <danieltimlee@gmail.com> Link: https://lore.kernel.org/r/20230818090119.477441-7-danieltimlee@gmail.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
101 lines
2.2 KiB
C
101 lines
2.2 KiB
C
/* Copyright (c) 2013-2015 PLUMgrid, http://plumgrid.com
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of version 2 of the GNU General Public
|
|
* License as published by the Free Software Foundation.
|
|
*/
|
|
#include "vmlinux.h"
|
|
#include <linux/version.h>
|
|
#include <bpf/bpf_helpers.h>
|
|
#include <bpf/bpf_tracing.h>
|
|
|
|
struct start_key {
|
|
dev_t dev;
|
|
u32 _pad;
|
|
sector_t sector;
|
|
};
|
|
|
|
struct {
|
|
__uint(type, BPF_MAP_TYPE_HASH);
|
|
__type(key, long);
|
|
__type(value, u64);
|
|
__uint(max_entries, 4096);
|
|
} my_map SEC(".maps");
|
|
|
|
/* from /sys/kernel/tracing/events/block/block_io_start/format */
|
|
SEC("tracepoint/block/block_io_start")
|
|
int bpf_prog1(struct trace_event_raw_block_rq *ctx)
|
|
{
|
|
u64 val = bpf_ktime_get_ns();
|
|
struct start_key key = {
|
|
.dev = ctx->dev,
|
|
.sector = ctx->sector
|
|
};
|
|
|
|
bpf_map_update_elem(&my_map, &key, &val, BPF_ANY);
|
|
return 0;
|
|
}
|
|
|
|
static unsigned int log2l(unsigned long long n)
|
|
{
|
|
#define S(k) if (n >= (1ull << k)) { i += k; n >>= k; }
|
|
int i = -(n == 0);
|
|
S(32); S(16); S(8); S(4); S(2); S(1);
|
|
return i;
|
|
#undef S
|
|
}
|
|
|
|
#define SLOTS 100
|
|
|
|
struct {
|
|
__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
|
|
__uint(key_size, sizeof(u32));
|
|
__uint(value_size, sizeof(u64));
|
|
__uint(max_entries, SLOTS);
|
|
} lat_map SEC(".maps");
|
|
|
|
/* from /sys/kernel/tracing/events/block/block_io_done/format */
|
|
SEC("tracepoint/block/block_io_done")
|
|
int bpf_prog2(struct trace_event_raw_block_rq *ctx)
|
|
{
|
|
struct start_key key = {
|
|
.dev = ctx->dev,
|
|
.sector = ctx->sector
|
|
};
|
|
|
|
u64 *value, l, base;
|
|
u32 index;
|
|
|
|
value = bpf_map_lookup_elem(&my_map, &key);
|
|
if (!value)
|
|
return 0;
|
|
|
|
u64 cur_time = bpf_ktime_get_ns();
|
|
u64 delta = cur_time - *value;
|
|
|
|
bpf_map_delete_elem(&my_map, &key);
|
|
|
|
/* the lines below are computing index = log10(delta)*10
|
|
* using integer arithmetic
|
|
* index = 29 ~ 1 usec
|
|
* index = 59 ~ 1 msec
|
|
* index = 89 ~ 1 sec
|
|
* index = 99 ~ 10sec or more
|
|
* log10(x)*10 = log2(x)*10/log2(10) = log2(x)*3
|
|
*/
|
|
l = log2l(delta);
|
|
base = 1ll << l;
|
|
index = (l * 64 + (delta - base) * 64 / base) * 3 / 64;
|
|
|
|
if (index >= SLOTS)
|
|
index = SLOTS - 1;
|
|
|
|
value = bpf_map_lookup_elem(&lat_map, &index);
|
|
if (value)
|
|
*value += 1;
|
|
|
|
return 0;
|
|
}
|
|
char _license[] SEC("license") = "GPL";
|
|
u32 _version SEC("version") = LINUX_VERSION_CODE;
|