2013-03-24 07:11:31 +08:00
|
|
|
/*
|
|
|
|
* Some low level IO code, and hacks for various block layer limitations
|
|
|
|
*
|
|
|
|
* Copyright 2010, 2011 Kent Overstreet <kent.overstreet@gmail.com>
|
|
|
|
* Copyright 2012 Google, Inc.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include "bcache.h"
|
|
|
|
#include "bset.h"
|
|
|
|
#include "debug.h"
|
|
|
|
|
2013-04-27 06:39:55 +08:00
|
|
|
#include <linux/blkdev.h>
|
|
|
|
|
2013-03-24 07:11:31 +08:00
|
|
|
/* Bios with headers */
|
|
|
|
|
|
|
|
void bch_bbio_free(struct bio *bio, struct cache_set *c)
|
|
|
|
{
|
|
|
|
struct bbio *b = container_of(bio, struct bbio, bio);
|
|
|
|
mempool_free(b, c->bio_meta);
|
|
|
|
}
|
|
|
|
|
|
|
|
struct bio *bch_bbio_alloc(struct cache_set *c)
|
|
|
|
{
|
|
|
|
struct bbio *b = mempool_alloc(c->bio_meta, GFP_NOIO);
|
|
|
|
struct bio *bio = &b->bio;
|
|
|
|
|
|
|
|
bio_init(bio);
|
|
|
|
bio->bi_flags |= BIO_POOL_NONE << BIO_POOL_OFFSET;
|
|
|
|
bio->bi_max_vecs = bucket_pages(c);
|
|
|
|
bio->bi_io_vec = bio->bi_inline_vecs;
|
|
|
|
|
|
|
|
return bio;
|
|
|
|
}
|
|
|
|
|
|
|
|
void __bch_submit_bbio(struct bio *bio, struct cache_set *c)
|
|
|
|
{
|
|
|
|
struct bbio *b = container_of(bio, struct bbio, bio);
|
|
|
|
|
2013-10-12 06:44:27 +08:00
|
|
|
bio->bi_iter.bi_sector = PTR_OFFSET(&b->key, 0);
|
|
|
|
bio->bi_bdev = PTR_CACHE(c, &b->key, 0)->bdev;
|
2013-03-24 07:11:31 +08:00
|
|
|
|
|
|
|
b->submit_time_us = local_clock_us();
|
2013-11-24 15:11:25 +08:00
|
|
|
closure_bio_submit(bio, bio->bi_private);
|
2013-03-24 07:11:31 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
void bch_submit_bbio(struct bio *bio, struct cache_set *c,
|
|
|
|
struct bkey *k, unsigned ptr)
|
|
|
|
{
|
|
|
|
struct bbio *b = container_of(bio, struct bbio, bio);
|
|
|
|
bch_bkey_copy_single_ptr(&b->key, k, ptr);
|
|
|
|
__bch_submit_bbio(bio, c);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* IO errors */
|
|
|
|
|
|
|
|
void bch_count_io_errors(struct cache *ca, int error, const char *m)
|
|
|
|
{
|
|
|
|
/*
|
|
|
|
* The halflife of an error is:
|
|
|
|
* log2(1/2)/log2(127/128) * refresh ~= 88 * refresh
|
|
|
|
*/
|
|
|
|
|
|
|
|
if (ca->set->error_decay) {
|
|
|
|
unsigned count = atomic_inc_return(&ca->io_count);
|
|
|
|
|
|
|
|
while (count > ca->set->error_decay) {
|
|
|
|
unsigned errors;
|
|
|
|
unsigned old = count;
|
|
|
|
unsigned new = count - ca->set->error_decay;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* First we subtract refresh from count; each time we
|
|
|
|
* succesfully do so, we rescale the errors once:
|
|
|
|
*/
|
|
|
|
|
|
|
|
count = atomic_cmpxchg(&ca->io_count, old, new);
|
|
|
|
|
|
|
|
if (count == old) {
|
|
|
|
count = new;
|
|
|
|
|
|
|
|
errors = atomic_read(&ca->io_errors);
|
|
|
|
do {
|
|
|
|
old = errors;
|
|
|
|
new = ((uint64_t) errors * 127) / 128;
|
|
|
|
errors = atomic_cmpxchg(&ca->io_errors,
|
|
|
|
old, new);
|
|
|
|
} while (old != errors);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (error) {
|
|
|
|
char buf[BDEVNAME_SIZE];
|
|
|
|
unsigned errors = atomic_add_return(1 << IO_ERROR_SHIFT,
|
|
|
|
&ca->io_errors);
|
|
|
|
errors >>= IO_ERROR_SHIFT;
|
|
|
|
|
|
|
|
if (errors < ca->set->error_limit)
|
|
|
|
pr_err("%s: IO error on %s, recovering",
|
|
|
|
bdevname(ca->bdev, buf), m);
|
|
|
|
else
|
|
|
|
bch_cache_set_error(ca->set,
|
|
|
|
"%s: too many IO errors %s",
|
|
|
|
bdevname(ca->bdev, buf), m);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
void bch_bbio_count_io_errors(struct cache_set *c, struct bio *bio,
|
|
|
|
int error, const char *m)
|
|
|
|
{
|
|
|
|
struct bbio *b = container_of(bio, struct bbio, bio);
|
|
|
|
struct cache *ca = PTR_CACHE(c, &b->key, 0);
|
|
|
|
|
|
|
|
unsigned threshold = bio->bi_rw & REQ_WRITE
|
|
|
|
? c->congested_write_threshold_us
|
|
|
|
: c->congested_read_threshold_us;
|
|
|
|
|
|
|
|
if (threshold) {
|
|
|
|
unsigned t = local_clock_us();
|
|
|
|
|
|
|
|
int us = t - b->submit_time_us;
|
|
|
|
int congested = atomic_read(&c->congested);
|
|
|
|
|
|
|
|
if (us > (int) threshold) {
|
|
|
|
int ms = us / 1024;
|
|
|
|
c->congested_last_us = t;
|
|
|
|
|
|
|
|
ms = min(ms, CONGESTED_MAX + congested);
|
|
|
|
atomic_sub(ms, &c->congested);
|
|
|
|
} else if (congested < 0)
|
|
|
|
atomic_inc(&c->congested);
|
|
|
|
}
|
|
|
|
|
|
|
|
bch_count_io_errors(ca, error, m);
|
|
|
|
}
|
|
|
|
|
|
|
|
void bch_bbio_endio(struct cache_set *c, struct bio *bio,
|
|
|
|
int error, const char *m)
|
|
|
|
{
|
|
|
|
struct closure *cl = bio->bi_private;
|
|
|
|
|
|
|
|
bch_bbio_count_io_errors(c, bio, error, m);
|
|
|
|
bio_put(bio);
|
|
|
|
closure_put(cl);
|
|
|
|
}
|