Merge branch 'for-linus' into test
* for-linus: block, bfq: add requeue-request hook bcache: fix for data collapse after re-attaching an attached device bcache: return attach error when no cache set exist bcache: set writeback_rate_update_seconds in range [1, 60] seconds bcache: fix for allocator and register thread race bcache: set error_limit correctly bcache: properly set task state in bch_writeback_thread() bcache: fix high CPU occupancy during journal bcache: add journal statistic block: Add should_fail_bio() for bpf error injection blk-wbt: account flush requests correctly
This commit is contained in:
commit
8525e5ff45
|
@ -3823,24 +3823,26 @@ static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
|
|||
}
|
||||
|
||||
/*
|
||||
* We exploit the bfq_finish_request hook to decrement
|
||||
* rq_in_driver, but bfq_finish_request will not be
|
||||
* invoked on this request. So, to avoid unbalance,
|
||||
* just start this request, without incrementing
|
||||
* rq_in_driver. As a negative consequence,
|
||||
* rq_in_driver is deceptively lower than it should be
|
||||
* while this request is in service. This may cause
|
||||
* bfq_schedule_dispatch to be invoked uselessly.
|
||||
* We exploit the bfq_finish_requeue_request hook to
|
||||
* decrement rq_in_driver, but
|
||||
* bfq_finish_requeue_request will not be invoked on
|
||||
* this request. So, to avoid unbalance, just start
|
||||
* this request, without incrementing rq_in_driver. As
|
||||
* a negative consequence, rq_in_driver is deceptively
|
||||
* lower than it should be while this request is in
|
||||
* service. This may cause bfq_schedule_dispatch to be
|
||||
* invoked uselessly.
|
||||
*
|
||||
* As for implementing an exact solution, the
|
||||
* bfq_finish_request hook, if defined, is probably
|
||||
* invoked also on this request. So, by exploiting
|
||||
* this hook, we could 1) increment rq_in_driver here,
|
||||
* and 2) decrement it in bfq_finish_request. Such a
|
||||
* solution would let the value of the counter be
|
||||
* always accurate, but it would entail using an extra
|
||||
* interface function. This cost seems higher than the
|
||||
* benefit, being the frequency of non-elevator-private
|
||||
* bfq_finish_requeue_request hook, if defined, is
|
||||
* probably invoked also on this request. So, by
|
||||
* exploiting this hook, we could 1) increment
|
||||
* rq_in_driver here, and 2) decrement it in
|
||||
* bfq_finish_requeue_request. Such a solution would
|
||||
* let the value of the counter be always accurate,
|
||||
* but it would entail using an extra interface
|
||||
* function. This cost seems higher than the benefit,
|
||||
* being the frequency of non-elevator-private
|
||||
* requests very low.
|
||||
*/
|
||||
goto start_rq;
|
||||
|
@ -4515,6 +4517,8 @@ static inline void bfq_update_insert_stats(struct request_queue *q,
|
|||
unsigned int cmd_flags) {}
|
||||
#endif
|
||||
|
||||
static void bfq_prepare_request(struct request *rq, struct bio *bio);
|
||||
|
||||
static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
|
||||
bool at_head)
|
||||
{
|
||||
|
@ -4541,6 +4545,18 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
|
|||
else
|
||||
list_add_tail(&rq->queuelist, &bfqd->dispatch);
|
||||
} else {
|
||||
if (WARN_ON_ONCE(!bfqq)) {
|
||||
/*
|
||||
* This should never happen. Most likely rq is
|
||||
* a requeued regular request, being
|
||||
* re-inserted without being first
|
||||
* re-prepared. Do a prepare, to avoid
|
||||
* failure.
|
||||
*/
|
||||
bfq_prepare_request(rq, rq->bio);
|
||||
bfqq = RQ_BFQQ(rq);
|
||||
}
|
||||
|
||||
idle_timer_disabled = __bfq_insert_request(bfqd, rq);
|
||||
/*
|
||||
* Update bfqq, because, if a queue merge has occurred
|
||||
|
@ -4697,22 +4713,44 @@ static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd)
|
|||
bfq_schedule_dispatch(bfqd);
|
||||
}
|
||||
|
||||
static void bfq_finish_request_body(struct bfq_queue *bfqq)
|
||||
static void bfq_finish_requeue_request_body(struct bfq_queue *bfqq)
|
||||
{
|
||||
bfqq->allocated--;
|
||||
|
||||
bfq_put_queue(bfqq);
|
||||
}
|
||||
|
||||
static void bfq_finish_request(struct request *rq)
|
||||
/*
|
||||
* Handle either a requeue or a finish for rq. The things to do are
|
||||
* the same in both cases: all references to rq are to be dropped. In
|
||||
* particular, rq is considered completed from the point of view of
|
||||
* the scheduler.
|
||||
*/
|
||||
static void bfq_finish_requeue_request(struct request *rq)
|
||||
{
|
||||
struct bfq_queue *bfqq;
|
||||
struct bfq_queue *bfqq = RQ_BFQQ(rq);
|
||||
struct bfq_data *bfqd;
|
||||
|
||||
if (!rq->elv.icq)
|
||||
/*
|
||||
* Requeue and finish hooks are invoked in blk-mq without
|
||||
* checking whether the involved request is actually still
|
||||
* referenced in the scheduler. To handle this fact, the
|
||||
* following two checks make this function exit in case of
|
||||
* spurious invocations, for which there is nothing to do.
|
||||
*
|
||||
* First, check whether rq has nothing to do with an elevator.
|
||||
*/
|
||||
if (unlikely(!(rq->rq_flags & RQF_ELVPRIV)))
|
||||
return;
|
||||
|
||||
/*
|
||||
* rq either is not associated with any icq, or is an already
|
||||
* requeued request that has not (yet) been re-inserted into
|
||||
* a bfq_queue.
|
||||
*/
|
||||
if (!rq->elv.icq || !bfqq)
|
||||
return;
|
||||
|
||||
bfqq = RQ_BFQQ(rq);
|
||||
bfqd = bfqq->bfqd;
|
||||
|
||||
if (rq->rq_flags & RQF_STARTED)
|
||||
|
@ -4727,13 +4765,14 @@ static void bfq_finish_request(struct request *rq)
|
|||
spin_lock_irqsave(&bfqd->lock, flags);
|
||||
|
||||
bfq_completed_request(bfqq, bfqd);
|
||||
bfq_finish_request_body(bfqq);
|
||||
bfq_finish_requeue_request_body(bfqq);
|
||||
|
||||
spin_unlock_irqrestore(&bfqd->lock, flags);
|
||||
} else {
|
||||
/*
|
||||
* Request rq may be still/already in the scheduler,
|
||||
* in which case we need to remove it. And we cannot
|
||||
* in which case we need to remove it (this should
|
||||
* never happen in case of requeue). And we cannot
|
||||
* defer such a check and removal, to avoid
|
||||
* inconsistencies in the time interval from the end
|
||||
* of this function to the start of the deferred work.
|
||||
|
@ -4748,9 +4787,26 @@ static void bfq_finish_request(struct request *rq)
|
|||
bfqg_stats_update_io_remove(bfqq_group(bfqq),
|
||||
rq->cmd_flags);
|
||||
}
|
||||
bfq_finish_request_body(bfqq);
|
||||
bfq_finish_requeue_request_body(bfqq);
|
||||
}
|
||||
|
||||
/*
|
||||
* Reset private fields. In case of a requeue, this allows
|
||||
* this function to correctly do nothing if it is spuriously
|
||||
* invoked again on this same request (see the check at the
|
||||
* beginning of the function). Probably, a better general
|
||||
* design would be to prevent blk-mq from invoking the requeue
|
||||
* or finish hooks of an elevator, for a request that is not
|
||||
* referred by that elevator.
|
||||
*
|
||||
* Resetting the following fields would break the
|
||||
* request-insertion logic if rq is re-inserted into a bfq
|
||||
* internal queue, without a re-preparation. Here we assume
|
||||
* that re-insertions of requeued requests, without
|
||||
* re-preparation, can happen only for pass_through or at_head
|
||||
* requests (which are not re-inserted into bfq internal
|
||||
* queues).
|
||||
*/
|
||||
rq->elv.priv[0] = NULL;
|
||||
rq->elv.priv[1] = NULL;
|
||||
}
|
||||
|
@ -5426,7 +5482,8 @@ static struct elevator_type iosched_bfq_mq = {
|
|||
.ops.mq = {
|
||||
.limit_depth = bfq_limit_depth,
|
||||
.prepare_request = bfq_prepare_request,
|
||||
.finish_request = bfq_finish_request,
|
||||
.requeue_request = bfq_finish_requeue_request,
|
||||
.finish_request = bfq_finish_requeue_request,
|
||||
.exit_icq = bfq_exit_icq,
|
||||
.insert_requests = bfq_insert_requests,
|
||||
.dispatch_request = bfq_dispatch_request,
|
||||
|
|
|
@ -34,6 +34,7 @@
|
|||
#include <linux/pm_runtime.h>
|
||||
#include <linux/blk-cgroup.h>
|
||||
#include <linux/debugfs.h>
|
||||
#include <linux/bpf.h>
|
||||
|
||||
#define CREATE_TRACE_POINTS
|
||||
#include <trace/events/block.h>
|
||||
|
@ -2083,6 +2084,14 @@ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part)
|
|||
return false;
|
||||
}
|
||||
|
||||
static noinline int should_fail_bio(struct bio *bio)
|
||||
{
|
||||
if (should_fail_request(&bio->bi_disk->part0, bio->bi_iter.bi_size))
|
||||
return -EIO;
|
||||
return 0;
|
||||
}
|
||||
ALLOW_ERROR_INJECTION(should_fail_bio, ERRNO);
|
||||
|
||||
/*
|
||||
* Remap block n of partition p to block n+start(p) of the disk.
|
||||
*/
|
||||
|
@ -2174,7 +2183,7 @@ generic_make_request_checks(struct bio *bio)
|
|||
if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_rq_based(q))
|
||||
goto not_supported;
|
||||
|
||||
if (should_fail_request(&bio->bi_disk->part0, bio->bi_iter.bi_size))
|
||||
if (should_fail_bio(bio))
|
||||
goto end_io;
|
||||
|
||||
if (!bio->bi_partno) {
|
||||
|
|
|
@ -697,7 +697,15 @@ u64 wbt_default_latency_nsec(struct request_queue *q)
|
|||
|
||||
static int wbt_data_dir(const struct request *rq)
|
||||
{
|
||||
return rq_data_dir(rq);
|
||||
const int op = req_op(rq);
|
||||
|
||||
if (op == REQ_OP_READ)
|
||||
return READ;
|
||||
else if (op == REQ_OP_WRITE || op == REQ_OP_FLUSH)
|
||||
return WRITE;
|
||||
|
||||
/* don't account */
|
||||
return -1;
|
||||
}
|
||||
|
||||
int wbt_init(struct request_queue *q)
|
||||
|
|
|
@ -287,8 +287,10 @@ do { \
|
|||
break; \
|
||||
\
|
||||
mutex_unlock(&(ca)->set->bucket_lock); \
|
||||
if (kthread_should_stop()) \
|
||||
if (kthread_should_stop()) { \
|
||||
set_current_state(TASK_RUNNING); \
|
||||
return 0; \
|
||||
} \
|
||||
\
|
||||
schedule(); \
|
||||
mutex_lock(&(ca)->set->bucket_lock); \
|
||||
|
|
|
@ -658,10 +658,15 @@ struct cache_set {
|
|||
atomic_long_t writeback_keys_done;
|
||||
atomic_long_t writeback_keys_failed;
|
||||
|
||||
atomic_long_t reclaim;
|
||||
atomic_long_t flush_write;
|
||||
atomic_long_t retry_flush_write;
|
||||
|
||||
enum {
|
||||
ON_ERROR_UNREGISTER,
|
||||
ON_ERROR_PANIC,
|
||||
} on_error;
|
||||
#define DEFAULT_IO_ERROR_LIMIT 8
|
||||
unsigned error_limit;
|
||||
unsigned error_decay;
|
||||
|
||||
|
@ -675,6 +680,8 @@ struct cache_set {
|
|||
|
||||
#define BUCKET_HASH_BITS 12
|
||||
struct hlist_head bucket_hash[1 << BUCKET_HASH_BITS];
|
||||
|
||||
DECLARE_HEAP(struct btree *, flush_btree);
|
||||
};
|
||||
|
||||
struct bbio {
|
||||
|
@ -917,7 +924,7 @@ void bcache_write_super(struct cache_set *);
|
|||
|
||||
int bch_flash_dev_create(struct cache_set *c, uint64_t size);
|
||||
|
||||
int bch_cached_dev_attach(struct cached_dev *, struct cache_set *);
|
||||
int bch_cached_dev_attach(struct cached_dev *, struct cache_set *, uint8_t *);
|
||||
void bch_cached_dev_detach(struct cached_dev *);
|
||||
void bch_cached_dev_run(struct cached_dev *);
|
||||
void bcache_device_stop(struct bcache_device *);
|
||||
|
|
|
@ -1869,14 +1869,17 @@ void bch_initial_gc_finish(struct cache_set *c)
|
|||
*/
|
||||
for_each_cache(ca, c, i) {
|
||||
for_each_bucket(b, ca) {
|
||||
if (fifo_full(&ca->free[RESERVE_PRIO]))
|
||||
if (fifo_full(&ca->free[RESERVE_PRIO]) &&
|
||||
fifo_full(&ca->free[RESERVE_BTREE]))
|
||||
break;
|
||||
|
||||
if (bch_can_invalidate_bucket(ca, b) &&
|
||||
!GC_MARK(b)) {
|
||||
__bch_invalidate_one_bucket(ca, b);
|
||||
fifo_push(&ca->free[RESERVE_PRIO],
|
||||
b - ca->buckets);
|
||||
if (!fifo_push(&ca->free[RESERVE_PRIO],
|
||||
b - ca->buckets))
|
||||
fifo_push(&ca->free[RESERVE_BTREE],
|
||||
b - ca->buckets);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
|
@ -368,6 +368,12 @@ err:
|
|||
}
|
||||
|
||||
/* Journalling */
|
||||
#define journal_max_cmp(l, r) \
|
||||
(fifo_idx(&c->journal.pin, btree_current_write(l)->journal) < \
|
||||
fifo_idx(&(c)->journal.pin, btree_current_write(r)->journal))
|
||||
#define journal_min_cmp(l, r) \
|
||||
(fifo_idx(&c->journal.pin, btree_current_write(l)->journal) > \
|
||||
fifo_idx(&(c)->journal.pin, btree_current_write(r)->journal))
|
||||
|
||||
static void btree_flush_write(struct cache_set *c)
|
||||
{
|
||||
|
@ -375,28 +381,41 @@ static void btree_flush_write(struct cache_set *c)
|
|||
* Try to find the btree node with that references the oldest journal
|
||||
* entry, best is our current candidate and is locked if non NULL:
|
||||
*/
|
||||
struct btree *b, *best;
|
||||
unsigned i;
|
||||
struct btree *b;
|
||||
int i;
|
||||
|
||||
atomic_long_inc(&c->flush_write);
|
||||
|
||||
retry:
|
||||
best = NULL;
|
||||
|
||||
for_each_cached_btree(b, c, i)
|
||||
if (btree_current_write(b)->journal) {
|
||||
if (!best)
|
||||
best = b;
|
||||
else if (journal_pin_cmp(c,
|
||||
btree_current_write(best)->journal,
|
||||
btree_current_write(b)->journal)) {
|
||||
best = b;
|
||||
spin_lock(&c->journal.lock);
|
||||
if (heap_empty(&c->flush_btree)) {
|
||||
for_each_cached_btree(b, c, i)
|
||||
if (btree_current_write(b)->journal) {
|
||||
if (!heap_full(&c->flush_btree))
|
||||
heap_add(&c->flush_btree, b,
|
||||
journal_max_cmp);
|
||||
else if (journal_max_cmp(b,
|
||||
heap_peek(&c->flush_btree))) {
|
||||
c->flush_btree.data[0] = b;
|
||||
heap_sift(&c->flush_btree, 0,
|
||||
journal_max_cmp);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
b = best;
|
||||
for (i = c->flush_btree.used / 2 - 1; i >= 0; --i)
|
||||
heap_sift(&c->flush_btree, i, journal_min_cmp);
|
||||
}
|
||||
|
||||
b = NULL;
|
||||
heap_pop(&c->flush_btree, b, journal_min_cmp);
|
||||
spin_unlock(&c->journal.lock);
|
||||
|
||||
if (b) {
|
||||
mutex_lock(&b->write_lock);
|
||||
if (!btree_current_write(b)->journal) {
|
||||
mutex_unlock(&b->write_lock);
|
||||
/* We raced */
|
||||
atomic_long_inc(&c->retry_flush_write);
|
||||
goto retry;
|
||||
}
|
||||
|
||||
|
@ -476,6 +495,8 @@ static void journal_reclaim(struct cache_set *c)
|
|||
unsigned iter, n = 0;
|
||||
atomic_t p;
|
||||
|
||||
atomic_long_inc(&c->reclaim);
|
||||
|
||||
while (!atomic_read(&fifo_front(&c->journal.pin)))
|
||||
fifo_pop(&c->journal.pin, p);
|
||||
|
||||
|
@ -819,7 +840,8 @@ int bch_journal_alloc(struct cache_set *c)
|
|||
j->w[0].c = c;
|
||||
j->w[1].c = c;
|
||||
|
||||
if (!(init_fifo(&j->pin, JOURNAL_PIN, GFP_KERNEL)) ||
|
||||
if (!(init_heap(&c->flush_btree, 128, GFP_KERNEL)) ||
|
||||
!(init_fifo(&j->pin, JOURNAL_PIN, GFP_KERNEL)) ||
|
||||
!(j->w[0].data = (void *) __get_free_pages(GFP_KERNEL, JSET_BITS)) ||
|
||||
!(j->w[1].data = (void *) __get_free_pages(GFP_KERNEL, JSET_BITS)))
|
||||
return -ENOMEM;
|
||||
|
|
|
@ -957,7 +957,8 @@ void bch_cached_dev_detach(struct cached_dev *dc)
|
|||
cached_dev_put(dc);
|
||||
}
|
||||
|
||||
int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c)
|
||||
int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
|
||||
uint8_t *set_uuid)
|
||||
{
|
||||
uint32_t rtime = cpu_to_le32(get_seconds());
|
||||
struct uuid_entry *u;
|
||||
|
@ -965,7 +966,8 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c)
|
|||
|
||||
bdevname(dc->bdev, buf);
|
||||
|
||||
if (memcmp(dc->sb.set_uuid, c->sb.set_uuid, 16))
|
||||
if ((set_uuid && memcmp(set_uuid, c->sb.set_uuid, 16)) ||
|
||||
(!set_uuid && memcmp(dc->sb.set_uuid, c->sb.set_uuid, 16)))
|
||||
return -ENOENT;
|
||||
|
||||
if (dc->disk.c) {
|
||||
|
@ -1194,7 +1196,7 @@ static void register_bdev(struct cache_sb *sb, struct page *sb_page,
|
|||
|
||||
list_add(&dc->list, &uncached_devices);
|
||||
list_for_each_entry(c, &bch_cache_sets, list)
|
||||
bch_cached_dev_attach(dc, c);
|
||||
bch_cached_dev_attach(dc, c, NULL);
|
||||
|
||||
if (BDEV_STATE(&dc->sb) == BDEV_STATE_NONE ||
|
||||
BDEV_STATE(&dc->sb) == BDEV_STATE_STALE)
|
||||
|
@ -1553,7 +1555,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
|
|||
|
||||
c->congested_read_threshold_us = 2000;
|
||||
c->congested_write_threshold_us = 20000;
|
||||
c->error_limit = 8 << IO_ERROR_SHIFT;
|
||||
c->error_limit = DEFAULT_IO_ERROR_LIMIT;
|
||||
|
||||
return c;
|
||||
err:
|
||||
|
@ -1716,7 +1718,7 @@ static void run_cache_set(struct cache_set *c)
|
|||
bcache_write_super(c);
|
||||
|
||||
list_for_each_entry_safe(dc, t, &uncached_devices, list)
|
||||
bch_cached_dev_attach(dc, c);
|
||||
bch_cached_dev_attach(dc, c, NULL);
|
||||
|
||||
flash_devs_run(c);
|
||||
|
||||
|
@ -1833,6 +1835,7 @@ void bch_cache_release(struct kobject *kobj)
|
|||
static int cache_alloc(struct cache *ca)
|
||||
{
|
||||
size_t free;
|
||||
size_t btree_buckets;
|
||||
struct bucket *b;
|
||||
|
||||
__module_get(THIS_MODULE);
|
||||
|
@ -1840,9 +1843,19 @@ static int cache_alloc(struct cache *ca)
|
|||
|
||||
bio_init(&ca->journal.bio, ca->journal.bio.bi_inline_vecs, 8);
|
||||
|
||||
/*
|
||||
* when ca->sb.njournal_buckets is not zero, journal exists,
|
||||
* and in bch_journal_replay(), tree node may split,
|
||||
* so bucket of RESERVE_BTREE type is needed,
|
||||
* the worst situation is all journal buckets are valid journal,
|
||||
* and all the keys need to replay,
|
||||
* so the number of RESERVE_BTREE type buckets should be as much
|
||||
* as journal buckets
|
||||
*/
|
||||
btree_buckets = ca->sb.njournal_buckets ?: 8;
|
||||
free = roundup_pow_of_two(ca->sb.nbuckets) >> 10;
|
||||
|
||||
if (!init_fifo(&ca->free[RESERVE_BTREE], 8, GFP_KERNEL) ||
|
||||
if (!init_fifo(&ca->free[RESERVE_BTREE], btree_buckets, GFP_KERNEL) ||
|
||||
!init_fifo_exact(&ca->free[RESERVE_PRIO], prio_buckets(ca), GFP_KERNEL) ||
|
||||
!init_fifo(&ca->free[RESERVE_MOVINGGC], free, GFP_KERNEL) ||
|
||||
!init_fifo(&ca->free[RESERVE_NONE], free, GFP_KERNEL) ||
|
||||
|
|
|
@ -65,6 +65,9 @@ read_attribute(bset_tree_stats);
|
|||
|
||||
read_attribute(state);
|
||||
read_attribute(cache_read_races);
|
||||
read_attribute(reclaim);
|
||||
read_attribute(flush_write);
|
||||
read_attribute(retry_flush_write);
|
||||
read_attribute(writeback_keys_done);
|
||||
read_attribute(writeback_keys_failed);
|
||||
read_attribute(io_errors);
|
||||
|
@ -195,7 +198,7 @@ STORE(__cached_dev)
|
|||
{
|
||||
struct cached_dev *dc = container_of(kobj, struct cached_dev,
|
||||
disk.kobj);
|
||||
ssize_t v = size;
|
||||
ssize_t v;
|
||||
struct cache_set *c;
|
||||
struct kobj_uevent_env *env;
|
||||
|
||||
|
@ -215,7 +218,9 @@ STORE(__cached_dev)
|
|||
sysfs_strtoul_clamp(writeback_rate,
|
||||
dc->writeback_rate.rate, 1, INT_MAX);
|
||||
|
||||
d_strtoul_nonzero(writeback_rate_update_seconds);
|
||||
sysfs_strtoul_clamp(writeback_rate_update_seconds,
|
||||
dc->writeback_rate_update_seconds,
|
||||
1, WRITEBACK_RATE_UPDATE_SECS_MAX);
|
||||
d_strtoul(writeback_rate_i_term_inverse);
|
||||
d_strtoul_nonzero(writeback_rate_p_term_inverse);
|
||||
|
||||
|
@ -267,17 +272,20 @@ STORE(__cached_dev)
|
|||
}
|
||||
|
||||
if (attr == &sysfs_attach) {
|
||||
if (bch_parse_uuid(buf, dc->sb.set_uuid) < 16)
|
||||
uint8_t set_uuid[16];
|
||||
|
||||
if (bch_parse_uuid(buf, set_uuid) < 16)
|
||||
return -EINVAL;
|
||||
|
||||
v = -ENOENT;
|
||||
list_for_each_entry(c, &bch_cache_sets, list) {
|
||||
v = bch_cached_dev_attach(dc, c);
|
||||
v = bch_cached_dev_attach(dc, c, set_uuid);
|
||||
if (!v)
|
||||
return size;
|
||||
}
|
||||
|
||||
pr_err("Can't attach %s: cache set not found", buf);
|
||||
size = v;
|
||||
return v;
|
||||
}
|
||||
|
||||
if (attr == &sysfs_detach && dc->disk.c)
|
||||
|
@ -545,6 +553,15 @@ SHOW(__bch_cache_set)
|
|||
sysfs_print(cache_read_races,
|
||||
atomic_long_read(&c->cache_read_races));
|
||||
|
||||
sysfs_print(reclaim,
|
||||
atomic_long_read(&c->reclaim));
|
||||
|
||||
sysfs_print(flush_write,
|
||||
atomic_long_read(&c->flush_write));
|
||||
|
||||
sysfs_print(retry_flush_write,
|
||||
atomic_long_read(&c->retry_flush_write));
|
||||
|
||||
sysfs_print(writeback_keys_done,
|
||||
atomic_long_read(&c->writeback_keys_done));
|
||||
sysfs_print(writeback_keys_failed,
|
||||
|
@ -556,7 +573,7 @@ SHOW(__bch_cache_set)
|
|||
|
||||
/* See count_io_errors for why 88 */
|
||||
sysfs_print(io_error_halflife, c->error_decay * 88);
|
||||
sysfs_print(io_error_limit, c->error_limit >> IO_ERROR_SHIFT);
|
||||
sysfs_print(io_error_limit, c->error_limit);
|
||||
|
||||
sysfs_hprint(congested,
|
||||
((uint64_t) bch_get_congested(c)) << 9);
|
||||
|
@ -656,7 +673,7 @@ STORE(__bch_cache_set)
|
|||
}
|
||||
|
||||
if (attr == &sysfs_io_error_limit)
|
||||
c->error_limit = strtoul_or_return(buf) << IO_ERROR_SHIFT;
|
||||
c->error_limit = strtoul_or_return(buf);
|
||||
|
||||
/* See count_io_errors() for why 88 */
|
||||
if (attr == &sysfs_io_error_halflife)
|
||||
|
@ -731,6 +748,9 @@ static struct attribute *bch_cache_set_internal_files[] = {
|
|||
|
||||
&sysfs_bset_tree_stats,
|
||||
&sysfs_cache_read_races,
|
||||
&sysfs_reclaim,
|
||||
&sysfs_flush_write,
|
||||
&sysfs_retry_flush_write,
|
||||
&sysfs_writeback_keys_done,
|
||||
&sysfs_writeback_keys_failed,
|
||||
|
||||
|
|
|
@ -112,6 +112,8 @@ do { \
|
|||
|
||||
#define heap_full(h) ((h)->used == (h)->size)
|
||||
|
||||
#define heap_empty(h) ((h)->used == 0)
|
||||
|
||||
#define DECLARE_FIFO(type, name) \
|
||||
struct { \
|
||||
size_t front, back, size, mask; \
|
||||
|
|
|
@ -564,18 +564,21 @@ static int bch_writeback_thread(void *arg)
|
|||
|
||||
while (!kthread_should_stop()) {
|
||||
down_write(&dc->writeback_lock);
|
||||
set_current_state(TASK_INTERRUPTIBLE);
|
||||
if (!atomic_read(&dc->has_dirty) ||
|
||||
(!test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags) &&
|
||||
!dc->writeback_running)) {
|
||||
up_write(&dc->writeback_lock);
|
||||
set_current_state(TASK_INTERRUPTIBLE);
|
||||
|
||||
if (kthread_should_stop())
|
||||
if (kthread_should_stop()) {
|
||||
set_current_state(TASK_RUNNING);
|
||||
return 0;
|
||||
}
|
||||
|
||||
schedule();
|
||||
continue;
|
||||
}
|
||||
set_current_state(TASK_RUNNING);
|
||||
|
||||
searched_full_index = refill_dirty(dc);
|
||||
|
||||
|
@ -652,7 +655,7 @@ void bch_cached_dev_writeback_init(struct cached_dev *dc)
|
|||
dc->writeback_rate.rate = 1024;
|
||||
dc->writeback_rate_minimum = 8;
|
||||
|
||||
dc->writeback_rate_update_seconds = 5;
|
||||
dc->writeback_rate_update_seconds = WRITEBACK_RATE_UPDATE_SECS_DEFAULT;
|
||||
dc->writeback_rate_p_term_inverse = 40;
|
||||
dc->writeback_rate_i_term_inverse = 10000;
|
||||
|
||||
|
|
|
@ -8,6 +8,9 @@
|
|||
#define MAX_WRITEBACKS_IN_PASS 5
|
||||
#define MAX_WRITESIZE_IN_PASS 5000 /* *512b */
|
||||
|
||||
#define WRITEBACK_RATE_UPDATE_SECS_MAX 60
|
||||
#define WRITEBACK_RATE_UPDATE_SECS_DEFAULT 5
|
||||
|
||||
/*
|
||||
* 14 (16384ths) is chosen here as something that each backing device
|
||||
* should be a reasonable fraction of the share, and not to blow up
|
||||
|
|
Loading…
Reference in New Issue