kernel_optimize_test/include/linux/blktrace_api.h

238 lines
7.3 KiB
C
Raw Normal View History

#ifndef BLKTRACE_H
#define BLKTRACE_H
#include <linux/types.h>
#ifdef __KERNEL__
#include <linux/blkdev.h>
#include <linux/relay.h>
#endif
/*
* Trace categories
*/
enum blktrace_cat {
BLK_TC_READ = 1 << 0, /* reads */
BLK_TC_WRITE = 1 << 1, /* writes */
BLK_TC_BARRIER = 1 << 2, /* barrier */
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_END = 1 << 15, /* only 16-bits, reminder */
};
#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 */
};
/*
* 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 */
};
/*
* 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 */
};
/*
* 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;
};
#ifdef __KERNEL__
#if defined(CONFIG_BLK_DEV_IO_TRACE)
#include <linux/sysfs.h>
struct blk_trace {
int trace_state;
struct rchan *rchan;
unsigned long *sequence;
unsigned char *msg_data;
u16 act_mask;
u64 start_lba;
u64 end_lba;
u32 pid;
u32 dev;
struct dentry *dir;
struct dentry *dropped_file;
struct dentry *msg_file;
atomic_t dropped;
};
extern int blk_trace_ioctl(struct block_device *, unsigned, char __user *);
extern void blk_trace_shutdown(struct request_queue *);
extern int do_blk_trace_setup(struct request_queue *q, char *name,
dev_t dev, struct block_device *bdev,
struct blk_user_trace_setup *buts);
extern void __trace_note_message(struct blk_trace *, const char *fmt, ...);
/**
* blk_add_trace_msg - Add a (simple) message to the blktrace stream
* @q: queue the io is for
* @fmt: format to print message in
* args... Variable argument list for format
*
* Description:
* Records a (simple) message onto the blktrace stream.
*
* NOTE: BLK_TN_MAX_MSG characters are output at most.
* NOTE: Can not use 'static inline' due to presence of var args...
*
**/
#define blk_add_trace_msg(q, fmt, ...) \
do { \
struct blk_trace *bt = (q)->blk_trace; \
if (unlikely(bt)) \
__trace_note_message(bt, fmt, ##__VA_ARGS__); \
} while (0)
#define BLK_TN_MAX_MSG 128
extern void blk_add_driver_data(struct request_queue *q, struct request *rq,
void *data, size_t len);
extern int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
struct block_device *bdev,
char __user *arg);
extern int blk_trace_startstop(struct request_queue *q, int start);
extern int blk_trace_remove(struct request_queue *q);
Add missing blk_trace_remove_sysfs to be in pair with blk_trace_init_sysfs Add missing blk_trace_remove_sysfs to be in pair with blk_trace_init_sysfs introduced in commit 1d54ad6da9192fed5dd3b60224d9f2dfea0dcd82. Release kobject also in case the request_fn is NULL. Problem was noticed via kmemleak backtrace when some sysfs entries were note properly destroyed during device removal: unreferenced object 0xffff88001aa76640 (size 80): comm "lvcreate", pid 2120, jiffies 4294885144 hex dump (first 32 bytes): 01 00 00 00 00 00 00 00 f0 65 a7 1a 00 88 ff ff .........e...... 90 66 a7 1a 00 88 ff ff 86 1d 53 81 ff ff ff ff .f........S..... backtrace: [<ffffffff813f9cc6>] kmemleak_alloc+0x26/0x60 [<ffffffff8111d693>] kmem_cache_alloc+0x133/0x1c0 [<ffffffff81195891>] sysfs_new_dirent+0x41/0x120 [<ffffffff81194b0c>] sysfs_add_file_mode+0x3c/0xb0 [<ffffffff81197c81>] internal_create_group+0xc1/0x1a0 [<ffffffff81197d93>] sysfs_create_group+0x13/0x20 [<ffffffff810d8004>] blk_trace_init_sysfs+0x14/0x20 [<ffffffff8123f45c>] blk_register_queue+0x3c/0xf0 [<ffffffff812447e4>] add_disk+0x94/0x160 [<ffffffffa00d8b08>] dm_create+0x598/0x6e0 [dm_mod] [<ffffffffa00de951>] dev_create+0x51/0x350 [dm_mod] [<ffffffffa00de823>] ctl_ioctl+0x1a3/0x240 [dm_mod] [<ffffffffa00de8f2>] dm_compat_ctl_ioctl+0x12/0x20 [dm_mod] [<ffffffff81177bfd>] compat_sys_ioctl+0xcd/0x4f0 [<ffffffff81036ed8>] sysenter_dispatch+0x7/0x2c [<ffffffffffffffff>] 0xffffffffffffffff Signed-off-by: Zdenek Kabelac <zkabelac@redhat.com> Reviewed-by: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-09-25 12:19:26 +08:00
extern void blk_trace_remove_sysfs(struct device *dev);
extern int blk_trace_init_sysfs(struct device *dev);
extern struct attribute_group blk_trace_attr_group;
#else /* !CONFIG_BLK_DEV_IO_TRACE */
# define blk_trace_ioctl(bdev, cmd, arg) (-ENOTTY)
# define blk_trace_shutdown(q) do { } while (0)
# define do_blk_trace_setup(q, name, dev, bdev, buts) (-ENOTTY)
# define blk_add_driver_data(q, rq, data, len) do {} while (0)
# define blk_trace_setup(q, name, dev, bdev, arg) (-ENOTTY)
# define blk_trace_startstop(q, start) (-ENOTTY)
# define blk_trace_remove(q) (-ENOTTY)
# define blk_add_trace_msg(q, fmt, ...) do { } while (0)
# define blk_trace_remove_sysfs(dev) do { } while (0)
static inline int blk_trace_init_sysfs(struct device *dev)
{
return 0;
}
#endif /* CONFIG_BLK_DEV_IO_TRACE */
#if defined(CONFIG_EVENT_TRACING) && defined(CONFIG_BLOCK)
tracing/events: convert block trace points to TRACE_EVENT() TRACE_EVENT is a more generic way to define tracepoints. Doing so adds these new capabilities to this tracepoint: - zero-copy and per-cpu splice() tracing - binary tracing without printf overhead - structured logging records exposed under /debug/tracing/events - trace events embedded in function tracer output and other plugins - user-defined, per tracepoint filter expressions ... Cons: - no dev_t info for the output of plug, unplug_timer and unplug_io events. no dev_t info for getrq and sleeprq events if bio == NULL. no dev_t info for rq_abort,...,rq_requeue events if rq->rq_disk == NULL. This is mainly because we can't get the deivce from a request queue. But this may change in the future. - A packet command is converted to a string in TP_assign, not TP_print. While blktrace do the convertion just before output. Since pc requests should be rather rare, this is not a big issue. - In blktrace, an event can have 2 different print formats, but a TRACE_EVENT has a unique format, which means we have some unused data in a trace entry. The overhead is minimized by using __dynamic_array() instead of __array(). I've benchmarked the ioctl blktrace vs the splice based TRACE_EVENT tracing: dd dd + ioctl blktrace dd + TRACE_EVENT (splice) 1 7.36s, 42.7 MB/s 7.50s, 42.0 MB/s 7.41s, 42.5 MB/s 2 7.43s, 42.3 MB/s 7.48s, 42.1 MB/s 7.43s, 42.4 MB/s 3 7.38s, 42.6 MB/s 7.45s, 42.2 MB/s 7.41s, 42.5 MB/s So the overhead of tracing is very small, and no regression when using those trace events vs blktrace. And the binary output of TRACE_EVENT is much smaller than blktrace: # ls -l -h -rw-r--r-- 1 root root 8.8M 06-09 13:24 sda.blktrace.0 -rw-r--r-- 1 root root 195K 06-09 13:24 sda.blktrace.1 -rw-r--r-- 1 root root 2.7M 06-09 13:25 trace_splice.out Following are some comparisons between TRACE_EVENT and blktrace: plug: kjournald-480 [000] 303.084981: block_plug: [kjournald] kjournald-480 [000] 303.084981: 8,0 P N [kjournald] unplug_io: kblockd/0-118 [000] 300.052973: block_unplug_io: [kblockd/0] 1 kblockd/0-118 [000] 300.052974: 8,0 U N [kblockd/0] 1 remap: kjournald-480 [000] 303.085042: block_remap: 8,0 W 102736992 + 8 <- (8,8) 33384 kjournald-480 [000] 303.085043: 8,0 A W 102736992 + 8 <- (8,8) 33384 bio_backmerge: kjournald-480 [000] 303.085086: block_bio_backmerge: 8,0 W 102737032 + 8 [kjournald] kjournald-480 [000] 303.085086: 8,0 M W 102737032 + 8 [kjournald] getrq: kjournald-480 [000] 303.084974: block_getrq: 8,0 W 102736984 + 8 [kjournald] kjournald-480 [000] 303.084975: 8,0 G W 102736984 + 8 [kjournald] bash-2066 [001] 1072.953770: 8,0 G N [bash] bash-2066 [001] 1072.953773: block_getrq: 0,0 N 0 + 0 [bash] rq_complete: konsole-2065 [001] 300.053184: block_rq_complete: 8,0 W () 103669040 + 16 [0] konsole-2065 [001] 300.053191: 8,0 C W 103669040 + 16 [0] ksoftirqd/1-7 [001] 1072.953811: 8,0 C N (5a 00 08 00 00 00 00 00 24 00) [0] ksoftirqd/1-7 [001] 1072.953813: block_rq_complete: 0,0 N (5a 00 08 00 00 00 00 00 24 00) 0 + 0 [0] rq_insert: kjournald-480 [000] 303.084985: block_rq_insert: 8,0 W 0 () 102736984 + 8 [kjournald] kjournald-480 [000] 303.084986: 8,0 I W 102736984 + 8 [kjournald] Changelog from v2 -> v3: - use the newly introduced __dynamic_array(). Changelog from v1 -> v2: - use __string() instead of __array() to minimize the memory required to store hex dump of rq->cmd(). - support large pc requests. - add missing blk_fill_rwbs_rq() in block_rq_requeue TRACE_EVENT. - some cleanups. Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> LKML-Reference: <4A2DF669.5070905@cn.fujitsu.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-09 13:43:05 +08:00
static inline int blk_cmd_buf_len(struct request *rq)
{
return blk_pc_request(rq) ? rq->cmd_len * 3 : 1;
}
extern void blk_dump_cmd(char *buf, struct request *rq);
extern void blk_fill_rwbs(char *rwbs, u32 rw, int bytes);
extern void blk_fill_rwbs_rq(char *rwbs, struct request *rq);
#endif /* CONFIG_EVENT_TRACING && CONFIG_BLOCK */
tracing/events: convert block trace points to TRACE_EVENT() TRACE_EVENT is a more generic way to define tracepoints. Doing so adds these new capabilities to this tracepoint: - zero-copy and per-cpu splice() tracing - binary tracing without printf overhead - structured logging records exposed under /debug/tracing/events - trace events embedded in function tracer output and other plugins - user-defined, per tracepoint filter expressions ... Cons: - no dev_t info for the output of plug, unplug_timer and unplug_io events. no dev_t info for getrq and sleeprq events if bio == NULL. no dev_t info for rq_abort,...,rq_requeue events if rq->rq_disk == NULL. This is mainly because we can't get the deivce from a request queue. But this may change in the future. - A packet command is converted to a string in TP_assign, not TP_print. While blktrace do the convertion just before output. Since pc requests should be rather rare, this is not a big issue. - In blktrace, an event can have 2 different print formats, but a TRACE_EVENT has a unique format, which means we have some unused data in a trace entry. The overhead is minimized by using __dynamic_array() instead of __array(). I've benchmarked the ioctl blktrace vs the splice based TRACE_EVENT tracing: dd dd + ioctl blktrace dd + TRACE_EVENT (splice) 1 7.36s, 42.7 MB/s 7.50s, 42.0 MB/s 7.41s, 42.5 MB/s 2 7.43s, 42.3 MB/s 7.48s, 42.1 MB/s 7.43s, 42.4 MB/s 3 7.38s, 42.6 MB/s 7.45s, 42.2 MB/s 7.41s, 42.5 MB/s So the overhead of tracing is very small, and no regression when using those trace events vs blktrace. And the binary output of TRACE_EVENT is much smaller than blktrace: # ls -l -h -rw-r--r-- 1 root root 8.8M 06-09 13:24 sda.blktrace.0 -rw-r--r-- 1 root root 195K 06-09 13:24 sda.blktrace.1 -rw-r--r-- 1 root root 2.7M 06-09 13:25 trace_splice.out Following are some comparisons between TRACE_EVENT and blktrace: plug: kjournald-480 [000] 303.084981: block_plug: [kjournald] kjournald-480 [000] 303.084981: 8,0 P N [kjournald] unplug_io: kblockd/0-118 [000] 300.052973: block_unplug_io: [kblockd/0] 1 kblockd/0-118 [000] 300.052974: 8,0 U N [kblockd/0] 1 remap: kjournald-480 [000] 303.085042: block_remap: 8,0 W 102736992 + 8 <- (8,8) 33384 kjournald-480 [000] 303.085043: 8,0 A W 102736992 + 8 <- (8,8) 33384 bio_backmerge: kjournald-480 [000] 303.085086: block_bio_backmerge: 8,0 W 102737032 + 8 [kjournald] kjournald-480 [000] 303.085086: 8,0 M W 102737032 + 8 [kjournald] getrq: kjournald-480 [000] 303.084974: block_getrq: 8,0 W 102736984 + 8 [kjournald] kjournald-480 [000] 303.084975: 8,0 G W 102736984 + 8 [kjournald] bash-2066 [001] 1072.953770: 8,0 G N [bash] bash-2066 [001] 1072.953773: block_getrq: 0,0 N 0 + 0 [bash] rq_complete: konsole-2065 [001] 300.053184: block_rq_complete: 8,0 W () 103669040 + 16 [0] konsole-2065 [001] 300.053191: 8,0 C W 103669040 + 16 [0] ksoftirqd/1-7 [001] 1072.953811: 8,0 C N (5a 00 08 00 00 00 00 00 24 00) [0] ksoftirqd/1-7 [001] 1072.953813: block_rq_complete: 0,0 N (5a 00 08 00 00 00 00 00 24 00) 0 + 0 [0] rq_insert: kjournald-480 [000] 303.084985: block_rq_insert: 8,0 W 0 () 102736984 + 8 [kjournald] kjournald-480 [000] 303.084986: 8,0 I W 102736984 + 8 [kjournald] Changelog from v2 -> v3: - use the newly introduced __dynamic_array(). Changelog from v1 -> v2: - use __string() instead of __array() to minimize the memory required to store hex dump of rq->cmd(). - support large pc requests. - add missing blk_fill_rwbs_rq() in block_rq_requeue TRACE_EVENT. - some cleanups. Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> LKML-Reference: <4A2DF669.5070905@cn.fujitsu.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-09 13:43:05 +08:00
#endif /* __KERNEL__ */
#endif