mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-27 20:05:14 +07:00
ca1136c99b
Currently blktrace isn't cgroup aware. blktrace prints out task name of current context, but the task of current context isn't always in the cgroup where the BIO comes from. We can't use task name to find out IO cgroup. For example, Writeback BIOs always comes from flusher thread but the BIOs are for different blk cgroups. Request could be requeued and dispatched from completely different tasks. MD/DM are another examples. This patch tries to fix the gap. We print out cgroup fhandle info in blktrace. Userspace can use open_by_handle_at() syscall to find the cgroup by fhandle. Or userspace can use name_to_handle_at() syscall to find fhandle for a cgroup and use a BPF program to filter out blktrace for a specific cgroup. We add a new 'blk_cgroup' trace option for blk tracer. It's default off. Application which doesn't know the new option isn't affected. When it's on, we output fhandle info right after blk_io_trace with an extra bit set in event action. So from application point of view, blktrace with the option will output new actions. I didn't change blk trace event yet, since I'm not sure if changing the trace event output is an ABI issue. If not, I'll do it later. Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Signed-off-by: Shaohua Li <shli@fb.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
146 lines
4.5 KiB
C
146 lines
4.5 KiB
C
#ifndef _UAPIBLKTRACE_H
|
|
#define _UAPIBLKTRACE_H
|
|
|
|
#include <linux/types.h>
|
|
|
|
/*
|
|
* Trace categories
|
|
*/
|
|
enum blktrace_cat {
|
|
BLK_TC_READ = 1 << 0, /* reads */
|
|
BLK_TC_WRITE = 1 << 1, /* writes */
|
|
BLK_TC_FLUSH = 1 << 2, /* flush */
|
|
BLK_TC_SYNC = 1 << 3, /* sync IO */
|
|
BLK_TC_SYNCIO = BLK_TC_SYNC,
|
|
BLK_TC_QUEUE = 1 << 4, /* queueing/merging */
|
|
BLK_TC_REQUEUE = 1 << 5, /* requeueing */
|
|
BLK_TC_ISSUE = 1 << 6, /* issue */
|
|
BLK_TC_COMPLETE = 1 << 7, /* completions */
|
|
BLK_TC_FS = 1 << 8, /* fs requests */
|
|
BLK_TC_PC = 1 << 9, /* pc requests */
|
|
BLK_TC_NOTIFY = 1 << 10, /* special message */
|
|
BLK_TC_AHEAD = 1 << 11, /* readahead */
|
|
BLK_TC_META = 1 << 12, /* metadata */
|
|
BLK_TC_DISCARD = 1 << 13, /* discard requests */
|
|
BLK_TC_DRV_DATA = 1 << 14, /* binary per-driver data */
|
|
BLK_TC_FUA = 1 << 15, /* fua requests */
|
|
|
|
BLK_TC_END = 1 << 15, /* we've run out of bits! */
|
|
};
|
|
|
|
#define BLK_TC_SHIFT (16)
|
|
#define BLK_TC_ACT(act) ((act) << BLK_TC_SHIFT)
|
|
|
|
/*
|
|
* Basic trace actions
|
|
*/
|
|
enum blktrace_act {
|
|
__BLK_TA_QUEUE = 1, /* queued */
|
|
__BLK_TA_BACKMERGE, /* back merged to existing rq */
|
|
__BLK_TA_FRONTMERGE, /* front merge to existing rq */
|
|
__BLK_TA_GETRQ, /* allocated new request */
|
|
__BLK_TA_SLEEPRQ, /* sleeping on rq allocation */
|
|
__BLK_TA_REQUEUE, /* request requeued */
|
|
__BLK_TA_ISSUE, /* sent to driver */
|
|
__BLK_TA_COMPLETE, /* completed by driver */
|
|
__BLK_TA_PLUG, /* queue was plugged */
|
|
__BLK_TA_UNPLUG_IO, /* queue was unplugged by io */
|
|
__BLK_TA_UNPLUG_TIMER, /* queue was unplugged by timer */
|
|
__BLK_TA_INSERT, /* insert request */
|
|
__BLK_TA_SPLIT, /* bio was split */
|
|
__BLK_TA_BOUNCE, /* bio was bounced */
|
|
__BLK_TA_REMAP, /* bio was remapped */
|
|
__BLK_TA_ABORT, /* request aborted */
|
|
__BLK_TA_DRV_DATA, /* driver-specific binary data */
|
|
__BLK_TA_CGROUP = 1 << 8, /* from a cgroup*/
|
|
};
|
|
|
|
/*
|
|
* Notify events.
|
|
*/
|
|
enum blktrace_notify {
|
|
__BLK_TN_PROCESS = 0, /* establish pid/name mapping */
|
|
__BLK_TN_TIMESTAMP, /* include system clock */
|
|
__BLK_TN_MESSAGE, /* Character string message */
|
|
__BLK_TN_CGROUP = __BLK_TA_CGROUP, /* from a cgroup */
|
|
};
|
|
|
|
|
|
/*
|
|
* Trace actions in full. Additionally, read or write is masked
|
|
*/
|
|
#define BLK_TA_QUEUE (__BLK_TA_QUEUE | BLK_TC_ACT(BLK_TC_QUEUE))
|
|
#define BLK_TA_BACKMERGE (__BLK_TA_BACKMERGE | BLK_TC_ACT(BLK_TC_QUEUE))
|
|
#define BLK_TA_FRONTMERGE (__BLK_TA_FRONTMERGE | BLK_TC_ACT(BLK_TC_QUEUE))
|
|
#define BLK_TA_GETRQ (__BLK_TA_GETRQ | BLK_TC_ACT(BLK_TC_QUEUE))
|
|
#define BLK_TA_SLEEPRQ (__BLK_TA_SLEEPRQ | BLK_TC_ACT(BLK_TC_QUEUE))
|
|
#define BLK_TA_REQUEUE (__BLK_TA_REQUEUE | BLK_TC_ACT(BLK_TC_REQUEUE))
|
|
#define BLK_TA_ISSUE (__BLK_TA_ISSUE | BLK_TC_ACT(BLK_TC_ISSUE))
|
|
#define BLK_TA_COMPLETE (__BLK_TA_COMPLETE| BLK_TC_ACT(BLK_TC_COMPLETE))
|
|
#define BLK_TA_PLUG (__BLK_TA_PLUG | BLK_TC_ACT(BLK_TC_QUEUE))
|
|
#define BLK_TA_UNPLUG_IO (__BLK_TA_UNPLUG_IO | BLK_TC_ACT(BLK_TC_QUEUE))
|
|
#define BLK_TA_UNPLUG_TIMER (__BLK_TA_UNPLUG_TIMER | BLK_TC_ACT(BLK_TC_QUEUE))
|
|
#define BLK_TA_INSERT (__BLK_TA_INSERT | BLK_TC_ACT(BLK_TC_QUEUE))
|
|
#define BLK_TA_SPLIT (__BLK_TA_SPLIT)
|
|
#define BLK_TA_BOUNCE (__BLK_TA_BOUNCE)
|
|
#define BLK_TA_REMAP (__BLK_TA_REMAP | BLK_TC_ACT(BLK_TC_QUEUE))
|
|
#define BLK_TA_ABORT (__BLK_TA_ABORT | BLK_TC_ACT(BLK_TC_QUEUE))
|
|
#define BLK_TA_DRV_DATA (__BLK_TA_DRV_DATA | BLK_TC_ACT(BLK_TC_DRV_DATA))
|
|
|
|
#define BLK_TN_PROCESS (__BLK_TN_PROCESS | BLK_TC_ACT(BLK_TC_NOTIFY))
|
|
#define BLK_TN_TIMESTAMP (__BLK_TN_TIMESTAMP | BLK_TC_ACT(BLK_TC_NOTIFY))
|
|
#define BLK_TN_MESSAGE (__BLK_TN_MESSAGE | BLK_TC_ACT(BLK_TC_NOTIFY))
|
|
|
|
#define BLK_IO_TRACE_MAGIC 0x65617400
|
|
#define BLK_IO_TRACE_VERSION 0x07
|
|
|
|
/*
|
|
* The trace itself
|
|
*/
|
|
struct blk_io_trace {
|
|
__u32 magic; /* MAGIC << 8 | version */
|
|
__u32 sequence; /* event number */
|
|
__u64 time; /* in microseconds */
|
|
__u64 sector; /* disk offset */
|
|
__u32 bytes; /* transfer length */
|
|
__u32 action; /* what happened */
|
|
__u32 pid; /* who did it */
|
|
__u32 device; /* device number */
|
|
__u32 cpu; /* on what cpu did it happen */
|
|
__u16 error; /* completion error */
|
|
__u16 pdu_len; /* length of data after this trace */
|
|
/* cgroup id will be stored here if exists */
|
|
};
|
|
|
|
/*
|
|
* The remap event
|
|
*/
|
|
struct blk_io_trace_remap {
|
|
__be32 device_from;
|
|
__be32 device_to;
|
|
__be64 sector_from;
|
|
};
|
|
|
|
enum {
|
|
Blktrace_setup = 1,
|
|
Blktrace_running,
|
|
Blktrace_stopped,
|
|
};
|
|
|
|
#define BLKTRACE_BDEV_SIZE 32
|
|
|
|
/*
|
|
* User setup structure passed with BLKTRACESTART
|
|
*/
|
|
struct blk_user_trace_setup {
|
|
char name[BLKTRACE_BDEV_SIZE]; /* output */
|
|
__u16 act_mask; /* input */
|
|
__u32 buf_size; /* input */
|
|
__u32 buf_nr; /* input */
|
|
__u64 start_lba;
|
|
__u64 end_lba;
|
|
__u32 pid;
|
|
};
|
|
|
|
#endif /* _UAPIBLKTRACE_H */
|