mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-04 09:59:32 +00:00
![Omar Sandoval](/assets/img/avatar_default.png)
Currently, statistics are gathered in ~0.13s windows, and users grab the statistics whenever they need them. This is not ideal for both in-tree users: 1. Writeback throttling wants its own dynamically sized window of statistics. Since the blk-stats statistics are reset after every window and the wbt windows don't line up with the blk-stats windows, wbt doesn't see every I/O. 2. Polling currently grabs the statistics on every I/O. Again, depending on how the window lines up, we may miss some I/Os. It's also unnecessary overhead to get the statistics on every I/O; the hybrid polling heuristic would be just as happy with the statistics from the previous full window. This reworks the blk-stats infrastructure to be callback-based: users register a callback that they want called at a given time with all of the statistics from the window during which the callback was active. Users can dynamically bucketize the statistics. wbt and polling both currently use read vs. write, but polling can be extended to further subdivide based on request size. The callbacks are kept on an RCU list, and each callback has percpu stats buffers. There will only be a few users, so the overhead on the I/O completion side is low. The stats flushing is also simplified considerably: since the timer function is responsible for clearing the statistics, we don't have to worry about stale statistics. wbt is a trivial conversion. After the conversion, the windowing problem mentioned above is fixed. For polling, we register an extra callback that caches the previous window's statistics in the struct request_queue for the hybrid polling heuristic to use. Since we no longer have a single stats buffer for the request queue, this also removes the sysfs and debugfs stats entries. To replace those, we add a debugfs entry for the poll statistics. Signed-off-by: Omar Sandoval <osandov@fb.com> Signed-off-by: Jens Axboe <axboe@fb.com>
299 lines
7.8 KiB
C
299 lines
7.8 KiB
C
/*
|
|
* Block data types and constants. Directly include this file only to
|
|
* break include dependency loop.
|
|
*/
|
|
#ifndef __LINUX_BLK_TYPES_H
|
|
#define __LINUX_BLK_TYPES_H
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/bvec.h>
|
|
|
|
struct bio_set;
|
|
struct bio;
|
|
struct bio_integrity_payload;
|
|
struct page;
|
|
struct block_device;
|
|
struct io_context;
|
|
struct cgroup_subsys_state;
|
|
typedef void (bio_end_io_t) (struct bio *);
|
|
|
|
/*
|
|
* main unit of I/O for the block layer and lower layers (ie drivers and
|
|
* stacking drivers)
|
|
*/
|
|
struct bio {
|
|
struct bio *bi_next; /* request queue link */
|
|
struct block_device *bi_bdev;
|
|
int bi_error;
|
|
unsigned int bi_opf; /* bottom bits req flags,
|
|
* top bits REQ_OP. Use
|
|
* accessors.
|
|
*/
|
|
unsigned short bi_flags; /* status, command, etc */
|
|
unsigned short bi_ioprio;
|
|
|
|
struct bvec_iter bi_iter;
|
|
|
|
/* Number of segments in this BIO after
|
|
* physical address coalescing is performed.
|
|
*/
|
|
unsigned int bi_phys_segments;
|
|
|
|
/*
|
|
* To keep track of the max segment size, we account for the
|
|
* sizes of the first and last mergeable segments in this bio.
|
|
*/
|
|
unsigned int bi_seg_front_size;
|
|
unsigned int bi_seg_back_size;
|
|
|
|
atomic_t __bi_remaining;
|
|
|
|
bio_end_io_t *bi_end_io;
|
|
|
|
void *bi_private;
|
|
#ifdef CONFIG_BLK_CGROUP
|
|
/*
|
|
* Optional ioc and css associated with this bio. Put on bio
|
|
* release. Read comment on top of bio_associate_current().
|
|
*/
|
|
struct io_context *bi_ioc;
|
|
struct cgroup_subsys_state *bi_css;
|
|
#endif
|
|
union {
|
|
#if defined(CONFIG_BLK_DEV_INTEGRITY)
|
|
struct bio_integrity_payload *bi_integrity; /* data integrity */
|
|
#endif
|
|
};
|
|
|
|
unsigned short bi_vcnt; /* how many bio_vec's */
|
|
|
|
/*
|
|
* Everything starting with bi_max_vecs will be preserved by bio_reset()
|
|
*/
|
|
|
|
unsigned short bi_max_vecs; /* max bvl_vecs we can hold */
|
|
|
|
atomic_t __bi_cnt; /* pin count */
|
|
|
|
struct bio_vec *bi_io_vec; /* the actual vec list */
|
|
|
|
struct bio_set *bi_pool;
|
|
|
|
/*
|
|
* We can inline a number of vecs at the end of the bio, to avoid
|
|
* double allocations for a small number of bio_vecs. This member
|
|
* MUST obviously be kept at the very end of the bio.
|
|
*/
|
|
struct bio_vec bi_inline_vecs[0];
|
|
};
|
|
|
|
#define BIO_RESET_BYTES offsetof(struct bio, bi_max_vecs)
|
|
|
|
/*
|
|
* bio flags
|
|
*/
|
|
#define BIO_SEG_VALID 1 /* bi_phys_segments valid */
|
|
#define BIO_CLONED 2 /* doesn't own data */
|
|
#define BIO_BOUNCED 3 /* bio is a bounce bio */
|
|
#define BIO_USER_MAPPED 4 /* contains user pages */
|
|
#define BIO_NULL_MAPPED 5 /* contains invalid user pages */
|
|
#define BIO_QUIET 6 /* Make BIO Quiet */
|
|
#define BIO_CHAIN 7 /* chained bio, ->bi_remaining in effect */
|
|
#define BIO_REFFED 8 /* bio has elevated ->bi_cnt */
|
|
#define BIO_THROTTLED 9 /* This bio has already been subjected to
|
|
* throttling rules. Don't do it again. */
|
|
|
|
/*
|
|
* Flags starting here get preserved by bio_reset() - this includes
|
|
* BVEC_POOL_IDX()
|
|
*/
|
|
#define BIO_RESET_BITS 10
|
|
|
|
/*
|
|
* We support 6 different bvec pools, the last one is magic in that it
|
|
* is backed by a mempool.
|
|
*/
|
|
#define BVEC_POOL_NR 6
|
|
#define BVEC_POOL_MAX (BVEC_POOL_NR - 1)
|
|
|
|
/*
|
|
* Top 4 bits of bio flags indicate the pool the bvecs came from. We add
|
|
* 1 to the actual index so that 0 indicates that there are no bvecs to be
|
|
* freed.
|
|
*/
|
|
#define BVEC_POOL_BITS (4)
|
|
#define BVEC_POOL_OFFSET (16 - BVEC_POOL_BITS)
|
|
#define BVEC_POOL_IDX(bio) ((bio)->bi_flags >> BVEC_POOL_OFFSET)
|
|
|
|
/*
|
|
* Operations and flags common to the bio and request structures.
|
|
* We use 8 bits for encoding the operation, and the remaining 24 for flags.
|
|
*
|
|
* The least significant bit of the operation number indicates the data
|
|
* transfer direction:
|
|
*
|
|
* - if the least significant bit is set transfers are TO the device
|
|
* - if the least significant bit is not set transfers are FROM the device
|
|
*
|
|
* If a operation does not transfer data the least significant bit has no
|
|
* meaning.
|
|
*/
|
|
#define REQ_OP_BITS 8
|
|
#define REQ_OP_MASK ((1 << REQ_OP_BITS) - 1)
|
|
#define REQ_FLAG_BITS 24
|
|
|
|
enum req_opf {
|
|
/* read sectors from the device */
|
|
REQ_OP_READ = 0,
|
|
/* write sectors to the device */
|
|
REQ_OP_WRITE = 1,
|
|
/* flush the volatile write cache */
|
|
REQ_OP_FLUSH = 2,
|
|
/* discard sectors */
|
|
REQ_OP_DISCARD = 3,
|
|
/* get zone information */
|
|
REQ_OP_ZONE_REPORT = 4,
|
|
/* securely erase sectors */
|
|
REQ_OP_SECURE_ERASE = 5,
|
|
/* seset a zone write pointer */
|
|
REQ_OP_ZONE_RESET = 6,
|
|
/* write the same sector many times */
|
|
REQ_OP_WRITE_SAME = 7,
|
|
/* write the zero filled sector many times */
|
|
REQ_OP_WRITE_ZEROES = 8,
|
|
|
|
/* SCSI passthrough using struct scsi_request */
|
|
REQ_OP_SCSI_IN = 32,
|
|
REQ_OP_SCSI_OUT = 33,
|
|
/* Driver private requests */
|
|
REQ_OP_DRV_IN = 34,
|
|
REQ_OP_DRV_OUT = 35,
|
|
|
|
REQ_OP_LAST,
|
|
};
|
|
|
|
enum req_flag_bits {
|
|
__REQ_FAILFAST_DEV = /* no driver retries of device errors */
|
|
REQ_OP_BITS,
|
|
__REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */
|
|
__REQ_FAILFAST_DRIVER, /* no driver retries of driver errors */
|
|
__REQ_SYNC, /* request is sync (sync write or read) */
|
|
__REQ_META, /* metadata io request */
|
|
__REQ_PRIO, /* boost priority in cfq */
|
|
__REQ_NOMERGE, /* don't touch this for merging */
|
|
__REQ_IDLE, /* anticipate more IO after this one */
|
|
__REQ_INTEGRITY, /* I/O includes block integrity payload */
|
|
__REQ_FUA, /* forced unit access */
|
|
__REQ_PREFLUSH, /* request for cache flush */
|
|
__REQ_RAHEAD, /* read ahead, can fail anytime */
|
|
__REQ_BACKGROUND, /* background IO */
|
|
__REQ_NR_BITS, /* stops here */
|
|
};
|
|
|
|
#define REQ_FAILFAST_DEV (1ULL << __REQ_FAILFAST_DEV)
|
|
#define REQ_FAILFAST_TRANSPORT (1ULL << __REQ_FAILFAST_TRANSPORT)
|
|
#define REQ_FAILFAST_DRIVER (1ULL << __REQ_FAILFAST_DRIVER)
|
|
#define REQ_SYNC (1ULL << __REQ_SYNC)
|
|
#define REQ_META (1ULL << __REQ_META)
|
|
#define REQ_PRIO (1ULL << __REQ_PRIO)
|
|
#define REQ_NOMERGE (1ULL << __REQ_NOMERGE)
|
|
#define REQ_IDLE (1ULL << __REQ_IDLE)
|
|
#define REQ_INTEGRITY (1ULL << __REQ_INTEGRITY)
|
|
#define REQ_FUA (1ULL << __REQ_FUA)
|
|
#define REQ_PREFLUSH (1ULL << __REQ_PREFLUSH)
|
|
#define REQ_RAHEAD (1ULL << __REQ_RAHEAD)
|
|
#define REQ_BACKGROUND (1ULL << __REQ_BACKGROUND)
|
|
|
|
#define REQ_FAILFAST_MASK \
|
|
(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)
|
|
|
|
#define REQ_NOMERGE_FLAGS \
|
|
(REQ_NOMERGE | REQ_PREFLUSH | REQ_FUA)
|
|
|
|
#define bio_op(bio) \
|
|
((bio)->bi_opf & REQ_OP_MASK)
|
|
#define req_op(req) \
|
|
((req)->cmd_flags & REQ_OP_MASK)
|
|
|
|
/* obsolete, don't use in new code */
|
|
static inline void bio_set_op_attrs(struct bio *bio, unsigned op,
|
|
unsigned op_flags)
|
|
{
|
|
bio->bi_opf = op | op_flags;
|
|
}
|
|
|
|
static inline bool op_is_write(unsigned int op)
|
|
{
|
|
return (op & 1);
|
|
}
|
|
|
|
/*
|
|
* Check if the bio or request is one that needs special treatment in the
|
|
* flush state machine.
|
|
*/
|
|
static inline bool op_is_flush(unsigned int op)
|
|
{
|
|
return op & (REQ_FUA | REQ_PREFLUSH);
|
|
}
|
|
|
|
/*
|
|
* Reads are always treated as synchronous, as are requests with the FUA or
|
|
* PREFLUSH flag. Other operations may be marked as synchronous using the
|
|
* REQ_SYNC flag.
|
|
*/
|
|
static inline bool op_is_sync(unsigned int op)
|
|
{
|
|
return (op & REQ_OP_MASK) == REQ_OP_READ ||
|
|
(op & (REQ_SYNC | REQ_FUA | REQ_PREFLUSH));
|
|
}
|
|
|
|
typedef unsigned int blk_qc_t;
|
|
#define BLK_QC_T_NONE -1U
|
|
#define BLK_QC_T_SHIFT 16
|
|
#define BLK_QC_T_INTERNAL (1U << 31)
|
|
|
|
static inline bool blk_qc_t_valid(blk_qc_t cookie)
|
|
{
|
|
return cookie != BLK_QC_T_NONE;
|
|
}
|
|
|
|
static inline blk_qc_t blk_tag_to_qc_t(unsigned int tag, unsigned int queue_num,
|
|
bool internal)
|
|
{
|
|
blk_qc_t ret = tag | (queue_num << BLK_QC_T_SHIFT);
|
|
|
|
if (internal)
|
|
ret |= BLK_QC_T_INTERNAL;
|
|
|
|
return ret;
|
|
}
|
|
|
|
static inline unsigned int blk_qc_t_to_queue_num(blk_qc_t cookie)
|
|
{
|
|
return (cookie & ~BLK_QC_T_INTERNAL) >> BLK_QC_T_SHIFT;
|
|
}
|
|
|
|
static inline unsigned int blk_qc_t_to_tag(blk_qc_t cookie)
|
|
{
|
|
return cookie & ((1u << BLK_QC_T_SHIFT) - 1);
|
|
}
|
|
|
|
static inline bool blk_qc_t_is_internal(blk_qc_t cookie)
|
|
{
|
|
return (cookie & BLK_QC_T_INTERNAL) != 0;
|
|
}
|
|
|
|
struct blk_issue_stat {
|
|
u64 time;
|
|
};
|
|
|
|
struct blk_rq_stat {
|
|
s64 mean;
|
|
u64 min;
|
|
u64 max;
|
|
s32 nr_samples;
|
|
s32 nr_batch;
|
|
u64 batch;
|
|
};
|
|
|
|
#endif /* __LINUX_BLK_TYPES_H */
|