linux/drivers/md/dm-cache-policy-mq.c

1474 lines
33 KiB
C
Raw Normal View History

/*
* Copyright (C) 2012 Red Hat. All rights reserved.
*
* This file is released under the GPL.
*/
#include "dm-cache-policy.h"
#include "dm.h"
#include <linux/hash.h>
#include <linux/jiffies.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#define DM_MSG_PREFIX "cache-policy-mq"
static struct kmem_cache *mq_entry_cache;
/*----------------------------------------------------------------*/
static unsigned next_power(unsigned n, unsigned min)
{
return roundup_pow_of_two(max(n, min));
}
/*----------------------------------------------------------------*/
/*
* Large, sequential ios are probably better left on the origin device since
* spindles tend to have good bandwidth.
*
* The io_tracker tries to spot when the io is in one of these sequential
* modes.
*
* Two thresholds to switch between random and sequential io mode are defaulting
* as follows and can be adjusted via the constructor and message interfaces.
*/
#define RANDOM_THRESHOLD_DEFAULT 4
#define SEQUENTIAL_THRESHOLD_DEFAULT 512
enum io_pattern {
PATTERN_SEQUENTIAL,
PATTERN_RANDOM
};
struct io_tracker {
enum io_pattern pattern;
unsigned nr_seq_samples;
unsigned nr_rand_samples;
unsigned thresholds[2];
dm_oblock_t last_end_oblock;
};
static void iot_init(struct io_tracker *t,
int sequential_threshold, int random_threshold)
{
t->pattern = PATTERN_RANDOM;
t->nr_seq_samples = 0;
t->nr_rand_samples = 0;
t->last_end_oblock = 0;
t->thresholds[PATTERN_RANDOM] = random_threshold;
t->thresholds[PATTERN_SEQUENTIAL] = sequential_threshold;
}
static enum io_pattern iot_pattern(struct io_tracker *t)
{
return t->pattern;
}
static void iot_update_stats(struct io_tracker *t, struct bio *bio)
{
block: Abstract out bvec iterator Immutable biovecs are going to require an explicit iterator. To implement immutable bvecs, a later patch is going to add a bi_bvec_done member to this struct; for now, this patch effectively just renames things. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Boaz Harrosh <bharrosh@panasas.com> Cc: Benny Halevy <bhalevy@tonian.com> Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "Nicholas A. Bellinger" <nab@linux-iscsi.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Chris Mason <chris.mason@fusionio.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Jaegeuk Kim <jaegeuk.kim@samsung.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Dave Kleikamp <shaggy@kernel.org> Cc: Joern Engel <joern@logfs.org> Cc: Prasad Joshi <prasadjoshi.linux@gmail.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: KONISHI Ryusuke <konishi.ryusuke@lab.ntt.co.jp> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Ben Myers <bpm@sgi.com> Cc: xfs@oss.sgi.com Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Len Brown <len.brown@intel.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Wei Yongjun <yongjun_wei@trendmicro.com.cn> Cc: "Roger Pau Monné" <roger.pau@citrix.com> Cc: Jan Beulich <jbeulich@suse.com> Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Cc: Ian Campbell <Ian.Campbell@citrix.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Jerome Marchand <jmarchand@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Peng Tao <tao.peng@emc.com> Cc: Andy Adamson <andros@netapp.com> Cc: fanchaoting <fanchaoting@cn.fujitsu.com> Cc: Jie Liu <jeff.liu@oracle.com> Cc: Sunil Mushran <sunil.mushran@gmail.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Namjae Jeon <namjae.jeon@samsung.com> Cc: Pankaj Kumar <pankaj.km@samsung.com> Cc: Dan Magenheimer <dan.magenheimer@oracle.com> Cc: Mel Gorman <mgorman@suse.de>6
2013-10-11 22:44:27 +00:00
if (bio->bi_iter.bi_sector == from_oblock(t->last_end_oblock) + 1)
t->nr_seq_samples++;
else {
/*
* Just one non-sequential IO is enough to reset the
* counters.
*/
if (t->nr_seq_samples) {
t->nr_seq_samples = 0;
t->nr_rand_samples = 0;
}
t->nr_rand_samples++;
}
block: Abstract out bvec iterator Immutable biovecs are going to require an explicit iterator. To implement immutable bvecs, a later patch is going to add a bi_bvec_done member to this struct; for now, this patch effectively just renames things. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Boaz Harrosh <bharrosh@panasas.com> Cc: Benny Halevy <bhalevy@tonian.com> Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "Nicholas A. Bellinger" <nab@linux-iscsi.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Chris Mason <chris.mason@fusionio.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Jaegeuk Kim <jaegeuk.kim@samsung.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Dave Kleikamp <shaggy@kernel.org> Cc: Joern Engel <joern@logfs.org> Cc: Prasad Joshi <prasadjoshi.linux@gmail.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: KONISHI Ryusuke <konishi.ryusuke@lab.ntt.co.jp> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Ben Myers <bpm@sgi.com> Cc: xfs@oss.sgi.com Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Len Brown <len.brown@intel.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Wei Yongjun <yongjun_wei@trendmicro.com.cn> Cc: "Roger Pau Monné" <roger.pau@citrix.com> Cc: Jan Beulich <jbeulich@suse.com> Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Cc: Ian Campbell <Ian.Campbell@citrix.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Jerome Marchand <jmarchand@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Peng Tao <tao.peng@emc.com> Cc: Andy Adamson <andros@netapp.com> Cc: fanchaoting <fanchaoting@cn.fujitsu.com> Cc: Jie Liu <jeff.liu@oracle.com> Cc: Sunil Mushran <sunil.mushran@gmail.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Namjae Jeon <namjae.jeon@samsung.com> Cc: Pankaj Kumar <pankaj.km@samsung.com> Cc: Dan Magenheimer <dan.magenheimer@oracle.com> Cc: Mel Gorman <mgorman@suse.de>6
2013-10-11 22:44:27 +00:00
t->last_end_oblock = to_oblock(bio_end_sector(bio) - 1);
}
static void iot_check_for_pattern_switch(struct io_tracker *t)
{
switch (t->pattern) {
case PATTERN_SEQUENTIAL:
if (t->nr_rand_samples >= t->thresholds[PATTERN_RANDOM]) {
t->pattern = PATTERN_RANDOM;
t->nr_seq_samples = t->nr_rand_samples = 0;
}
break;
case PATTERN_RANDOM:
if (t->nr_seq_samples >= t->thresholds[PATTERN_SEQUENTIAL]) {
t->pattern = PATTERN_SEQUENTIAL;
t->nr_seq_samples = t->nr_rand_samples = 0;
}
break;
}
}
static void iot_examine_bio(struct io_tracker *t, struct bio *bio)
{
iot_update_stats(t, bio);
iot_check_for_pattern_switch(t);
}
/*----------------------------------------------------------------*/
/*
* This queue is divided up into different levels. Allowing us to push
* entries to the back of any of the levels. Think of it as a partially
* sorted queue.
*/
#define NR_QUEUE_LEVELS 16u
#define NR_SENTINELS NR_QUEUE_LEVELS * 3
#define WRITEBACK_PERIOD HZ
struct queue {
unsigned nr_elts;
bool current_writeback_sentinels;
unsigned long next_writeback;
struct list_head qs[NR_QUEUE_LEVELS];
struct list_head sentinels[NR_SENTINELS];
};
static void queue_init(struct queue *q)
{
unsigned i;
q->nr_elts = 0;
q->current_writeback_sentinels = false;
q->next_writeback = 0;
for (i = 0; i < NR_QUEUE_LEVELS; i++) {
INIT_LIST_HEAD(q->qs + i);
INIT_LIST_HEAD(q->sentinels + i);
INIT_LIST_HEAD(q->sentinels + NR_QUEUE_LEVELS + i);
INIT_LIST_HEAD(q->sentinels + (2 * NR_QUEUE_LEVELS) + i);
}
}
static unsigned queue_size(struct queue *q)
{
return q->nr_elts;
}
static bool queue_empty(struct queue *q)
{
return q->nr_elts == 0;
}
/*
* Insert an entry to the back of the given level.
*/
static void queue_push(struct queue *q, unsigned level, struct list_head *elt)
{
q->nr_elts++;
list_add_tail(elt, q->qs + level);
}
static void queue_remove(struct queue *q, struct list_head *elt)
{
q->nr_elts--;
list_del(elt);
}
static bool is_sentinel(struct queue *q, struct list_head *h)
{
return (h >= q->sentinels) && (h < (q->sentinels + NR_SENTINELS));
}
/*
* Gives us the oldest entry of the lowest popoulated level. If the first
* level is emptied then we shift down one level.
*/
static struct list_head *queue_peek(struct queue *q)
{
unsigned level;
struct list_head *h;
for (level = 0; level < NR_QUEUE_LEVELS; level++)
list_for_each(h, q->qs + level)
if (!is_sentinel(q, h))
return h;
return NULL;
}
static struct list_head *queue_pop(struct queue *q)
{
struct list_head *r = queue_peek(q);
if (r) {
q->nr_elts--;
list_del(r);
}
return r;
}
/*
* Pops an entry from a level that is not past a sentinel.
*/
static struct list_head *queue_pop_old(struct queue *q)
{
unsigned level;
struct list_head *h;
for (level = 0; level < NR_QUEUE_LEVELS; level++)
list_for_each(h, q->qs + level) {
if (is_sentinel(q, h))
break;
q->nr_elts--;
list_del(h);
return h;
}
return NULL;
}
static struct list_head *list_pop(struct list_head *lh)
{
struct list_head *r = lh->next;
BUG_ON(!r);
list_del_init(r);
return r;
}
static struct list_head *writeback_sentinel(struct queue *q, unsigned level)
{
if (q->current_writeback_sentinels)
return q->sentinels + NR_QUEUE_LEVELS + level;
else
return q->sentinels + 2 * NR_QUEUE_LEVELS + level;
}
static void queue_update_writeback_sentinels(struct queue *q)
{
unsigned i;
struct list_head *h;
if (time_after(jiffies, q->next_writeback)) {
for (i = 0; i < NR_QUEUE_LEVELS; i++) {
h = writeback_sentinel(q, i);
list_del(h);
list_add_tail(h, q->qs + i);
}
q->next_writeback = jiffies + WRITEBACK_PERIOD;
q->current_writeback_sentinels = !q->current_writeback_sentinels;
}
}
/*
* Sometimes we want to iterate through entries that have been pushed since
* a certain event. We use sentinel entries on the queues to delimit these
* 'tick' events.
*/
static void queue_tick(struct queue *q)
{
unsigned i;
for (i = 0; i < NR_QUEUE_LEVELS; i++) {
list_del(q->sentinels + i);
list_add_tail(q->sentinels + i, q->qs + i);
}
}
typedef void (*iter_fn)(struct list_head *, void *);
static void queue_iterate_tick(struct queue *q, iter_fn fn, void *context)
{
unsigned i;
struct list_head *h;
for (i = 0; i < NR_QUEUE_LEVELS; i++) {
list_for_each_prev(h, q->qs + i) {
if (is_sentinel(q, h))
break;
fn(h, context);
}
}
}
/*----------------------------------------------------------------*/
/*
* Describes a cache entry. Used in both the cache and the pre_cache.
*/
struct entry {
struct hlist_node hlist;
struct list_head list;
dm_oblock_t oblock;
/*
* FIXME: pack these better
*/
bool dirty:1;
unsigned hit_count;
};
/*
* Rather than storing the cblock in an entry, we allocate all entries in
* an array, and infer the cblock from the entry position.
*
* Free entries are linked together into a list.
*/
struct entry_pool {
struct entry *entries, *entries_end;
struct list_head free;
unsigned nr_allocated;
};
static int epool_init(struct entry_pool *ep, unsigned nr_entries)
{
unsigned i;
ep->entries = vzalloc(sizeof(struct entry) * nr_entries);
if (!ep->entries)
return -ENOMEM;
ep->entries_end = ep->entries + nr_entries;
INIT_LIST_HEAD(&ep->free);
for (i = 0; i < nr_entries; i++)
list_add(&ep->entries[i].list, &ep->free);
ep->nr_allocated = 0;
return 0;
}
static void epool_exit(struct entry_pool *ep)
{
vfree(ep->entries);
}
static struct entry *alloc_entry(struct entry_pool *ep)
{
struct entry *e;
if (list_empty(&ep->free))
return NULL;
e = list_entry(list_pop(&ep->free), struct entry, list);
INIT_LIST_HEAD(&e->list);
INIT_HLIST_NODE(&e->hlist);
ep->nr_allocated++;
return e;
}
/*
* This assumes the cblock hasn't already been allocated.
*/
static struct entry *alloc_particular_entry(struct entry_pool *ep, dm_cblock_t cblock)
{
struct entry *e = ep->entries + from_cblock(cblock);
list_del_init(&e->list);
INIT_HLIST_NODE(&e->hlist);
ep->nr_allocated++;
return e;
}
static void free_entry(struct entry_pool *ep, struct entry *e)
{
BUG_ON(!ep->nr_allocated);
ep->nr_allocated--;
INIT_HLIST_NODE(&e->hlist);
list_add(&e->list, &ep->free);
}
/*
* Returns NULL if the entry is free.
*/
static struct entry *epool_find(struct entry_pool *ep, dm_cblock_t cblock)
{
struct entry *e = ep->entries + from_cblock(cblock);
return !hlist_unhashed(&e->hlist) ? e : NULL;
}
static bool epool_empty(struct entry_pool *ep)
{
return list_empty(&ep->free);
}
static bool in_pool(struct entry_pool *ep, struct entry *e)
{
return e >= ep->entries && e < ep->entries_end;
}
static dm_cblock_t infer_cblock(struct entry_pool *ep, struct entry *e)
{
return to_cblock(e - ep->entries);
}
/*----------------------------------------------------------------*/
struct mq_policy {
struct dm_cache_policy policy;
/* protects everything */
struct mutex lock;
dm_cblock_t cache_size;
struct io_tracker tracker;
/*
* Entries come from two pools, one of pre-cache entries, and one
* for the cache proper.
*/
struct entry_pool pre_cache_pool;
struct entry_pool cache_pool;
/*
* We maintain three queues of entries. The cache proper,
* consisting of a clean and dirty queue, contains the currently
* active mappings. Whereas the pre_cache tracks blocks that
* are being hit frequently and potential candidates for promotion
* to the cache.
*/
struct queue pre_cache;
struct queue cache_clean;
struct queue cache_dirty;
/*
* Keeps track of time, incremented by the core. We use this to
* avoid attributing multiple hits within the same tick.
*
* Access to tick_protected should be done with the spin lock held.
* It's copied to tick at the start of the map function (within the
* mutex).
*/
spinlock_t tick_lock;
unsigned tick_protected;
unsigned tick;
/*
* A count of the number of times the map function has been called
* and found an entry in the pre_cache or cache. Currently used to
* calculate the generation.
*/
unsigned hit_count;
/*
* A generation is a longish period that is used to trigger some
* book keeping effects. eg, decrementing hit counts on entries.
* This is needed to allow the cache to evolve as io patterns
* change.
*/
unsigned generation;
unsigned generation_period; /* in lookups (will probably change) */
unsigned discard_promote_adjustment;
unsigned read_promote_adjustment;
unsigned write_promote_adjustment;
/*
* The hash table allows us to quickly find an entry by origin
* block. Both pre_cache and cache entries are in here.
*/
unsigned nr_buckets;
dm_block_t hash_bits;
struct hlist_head *table;
};
#define DEFAULT_DISCARD_PROMOTE_ADJUSTMENT 1
#define DEFAULT_READ_PROMOTE_ADJUSTMENT 4
#define DEFAULT_WRITE_PROMOTE_ADJUSTMENT 8
#define DISCOURAGE_DEMOTING_DIRTY_THRESHOLD 128
/*----------------------------------------------------------------*/
/*
* Simple hash table implementation. Should replace with the standard hash
* table that's making its way upstream.
*/
static void hash_insert(struct mq_policy *mq, struct entry *e)
{
unsigned h = hash_64(from_oblock(e->oblock), mq->hash_bits);
hlist_add_head(&e->hlist, mq->table + h);
}
static struct entry *hash_lookup(struct mq_policy *mq, dm_oblock_t oblock)
{
unsigned h = hash_64(from_oblock(oblock), mq->hash_bits);
struct hlist_head *bucket = mq->table + h;
struct entry *e;
hlist_for_each_entry(e, bucket, hlist)
if (e->oblock == oblock) {
hlist_del(&e->hlist);
hlist_add_head(&e->hlist, bucket);
return e;
}
return NULL;
}
static void hash_remove(struct entry *e)
{
hlist_del(&e->hlist);
}
/*----------------------------------------------------------------*/
static bool any_free_cblocks(struct mq_policy *mq)
{
return !epool_empty(&mq->cache_pool);
}
static bool any_clean_cblocks(struct mq_policy *mq)
{
return !queue_empty(&mq->cache_clean);
}
/*----------------------------------------------------------------*/
/*
* Now we get to the meat of the policy. This section deals with deciding
* when to to add entries to the pre_cache and cache, and move between
* them.
*/
/*
* The queue level is based on the log2 of the hit count.
*/
static unsigned queue_level(struct entry *e)
{
return min((unsigned) ilog2(e->hit_count), NR_QUEUE_LEVELS - 1u);
}
static bool in_cache(struct mq_policy *mq, struct entry *e)
{
return in_pool(&mq->cache_pool, e);
}
/*
* Inserts the entry into the pre_cache or the cache. Ensures the cache
* block is marked as allocated if necc. Inserts into the hash table.
* Sets the tick which records when the entry was last moved about.
*/
static void push(struct mq_policy *mq, struct entry *e)
{
hash_insert(mq, e);
if (in_cache(mq, e))
queue_push(e->dirty ? &mq->cache_dirty : &mq->cache_clean,
queue_level(e), &e->list);
else
queue_push(&mq->pre_cache, queue_level(e), &e->list);
}
/*
* Removes an entry from pre_cache or cache. Removes from the hash table.
*/
static void del(struct mq_policy *mq, struct entry *e)
{
if (in_cache(mq, e))
queue_remove(e->dirty ? &mq->cache_dirty : &mq->cache_clean, &e->list);
else
queue_remove(&mq->pre_cache, &e->list);
hash_remove(e);
}
/*
* Like del, except it removes the first entry in the queue (ie. the least
* recently used).
*/
static struct entry *pop(struct mq_policy *mq, struct queue *q)
{
struct entry *e;
struct list_head *h = queue_pop(q);
if (!h)
return NULL;
e = container_of(h, struct entry, list);
hash_remove(e);
return e;
}
static struct entry *pop_old(struct mq_policy *mq, struct queue *q)
{
struct entry *e;
struct list_head *h = queue_pop_old(q);
if (!h)
return NULL;
e = container_of(h, struct entry, list);
hash_remove(e);
return e;
}
static struct entry *peek(struct queue *q)
{
struct list_head *h = queue_peek(q);
return h ? container_of(h, struct entry, list) : NULL;
}
/*
* The promotion threshold is adjusted every generation. As are the counts
* of the entries.
*
* At the moment the threshold is taken by averaging the hit counts of some
* of the entries in the cache (the first 20 entries across all levels in
* ascending order, giving preference to the clean entries at each level).
*
* We can be much cleverer than this though. For example, each promotion
* could bump up the threshold helping to prevent churn. Much more to do
* here.
*/
#define MAX_TO_AVERAGE 20
static void check_generation(struct mq_policy *mq)
{
unsigned total = 0, nr = 0, count = 0, level;
struct list_head *head;
struct entry *e;
if ((mq->hit_count >= mq->generation_period) && (epool_empty(&mq->cache_pool))) {
mq->hit_count = 0;
mq->generation++;
for (level = 0; level < NR_QUEUE_LEVELS && count < MAX_TO_AVERAGE; level++) {
head = mq->cache_clean.qs + level;
list_for_each_entry(e, head, list) {
nr++;
total += e->hit_count;
if (++count >= MAX_TO_AVERAGE)
break;
}
head = mq->cache_dirty.qs + level;
list_for_each_entry(e, head, list) {
nr++;
total += e->hit_count;
if (++count >= MAX_TO_AVERAGE)
break;
}
}
}
}
/*
* Whenever we use an entry we bump up it's hit counter, and push it to the
* back to it's current level.
*/
static void requeue(struct mq_policy *mq, struct entry *e)
{
check_generation(mq);
del(mq, e);
push(mq, e);
}
/*
* Demote the least recently used entry from the cache to the pre_cache.
* Returns the new cache entry to use, and the old origin block it was
* mapped to.
*
* We drop the hit count on the demoted entry back to 1 to stop it bouncing
* straight back into the cache if it's subsequently hit. There are
* various options here, and more experimentation would be good:
*
* - just forget about the demoted entry completely (ie. don't insert it
into the pre_cache).
* - divide the hit count rather that setting to some hard coded value.
* - set the hit count to a hard coded value other than 1, eg, is it better
* if it goes in at level 2?
*/
static int demote_cblock(struct mq_policy *mq,
struct policy_locker *locker, dm_oblock_t *oblock)
{
struct entry *demoted = peek(&mq->cache_clean);
if (!demoted)
/*
* We could get a block from mq->cache_dirty, but that
* would add extra latency to the triggering bio as it
* waits for the writeback. Better to not promote this
* time and hope there's a clean block next time this block
* is hit.
*/
return -ENOSPC;
if (locker->fn(locker, demoted->oblock))
/*
* We couldn't lock the demoted block.
*/
return -EBUSY;
del(mq, demoted);
*oblock = demoted->oblock;
free_entry(&mq->cache_pool, demoted);
/*
* We used to put the demoted block into the pre-cache, but I think
* it's simpler to just let it work it's way up from zero again.
* Stops blocks flickering in and out of the cache.
*/
return 0;
}
/*
* Entries in the pre_cache whose hit count passes the promotion
* threshold move to the cache proper. Working out the correct
* value for the promotion_threshold is crucial to this policy.
*/
static unsigned promote_threshold(struct mq_policy *mq)
{
struct entry *e;
if (any_free_cblocks(mq))
return 0;
e = peek(&mq->cache_clean);
if (e)
return e->hit_count;
e = peek(&mq->cache_dirty);
if (e)
return e->hit_count + DISCOURAGE_DEMOTING_DIRTY_THRESHOLD;
/* This should never happen */
return 0;
}
/*
* We modify the basic promotion_threshold depending on the specific io.
*
* If the origin block has been discarded then there's no cost to copy it
* to the cache.
*
* We bias towards reads, since they can be demoted at no cost if they
* haven't been dirtied.
*/
static unsigned adjusted_promote_threshold(struct mq_policy *mq,
bool discarded_oblock, int data_dir)
{
if (data_dir == READ)
return promote_threshold(mq) + mq->read_promote_adjustment;
if (discarded_oblock && (any_free_cblocks(mq) || any_clean_cblocks(mq))) {
/*
* We don't need to do any copying at all, so give this a
* very low threshold.
*/
return mq->discard_promote_adjustment;
}
return promote_threshold(mq) + mq->write_promote_adjustment;
}
static bool should_promote(struct mq_policy *mq, struct entry *e,
bool discarded_oblock, int data_dir)
{
return e->hit_count >=
adjusted_promote_threshold(mq, discarded_oblock, data_dir);
}
static int cache_entry_found(struct mq_policy *mq,
struct entry *e,
struct policy_result *result)
{
requeue(mq, e);
if (in_cache(mq, e)) {
result->op = POLICY_HIT;
result->cblock = infer_cblock(&mq->cache_pool, e);
}
return 0;
}
/*
* Moves an entry from the pre_cache to the cache. The main work is
* finding which cache block to use.
*/
static int pre_cache_to_cache(struct mq_policy *mq, struct entry *e,
struct policy_locker *locker,
struct policy_result *result)
{
int r;
struct entry *new_e;
/* Ensure there's a free cblock in the cache */
if (epool_empty(&mq->cache_pool)) {
result->op = POLICY_REPLACE;
r = demote_cblock(mq, locker, &result->old_oblock);
if (r) {
result->op = POLICY_MISS;
return 0;
}
} else
result->op = POLICY_NEW;
new_e = alloc_entry(&mq->cache_pool);
BUG_ON(!new_e);
new_e->oblock = e->oblock;
new_e->dirty = false;
new_e->hit_count = e->hit_count;
del(mq, e);
free_entry(&mq->pre_cache_pool, e);
push(mq, new_e);
result->cblock = infer_cblock(&mq->cache_pool, new_e);
return 0;
}
static int pre_cache_entry_found(struct mq_policy *mq, struct entry *e,
bool can_migrate, bool discarded_oblock,
int data_dir, struct policy_locker *locker,
struct policy_result *result)
{
int r = 0;
if (!should_promote(mq, e, discarded_oblock, data_dir)) {
requeue(mq, e);
result->op = POLICY_MISS;
} else if (!can_migrate)
r = -EWOULDBLOCK;
else {
requeue(mq, e);
r = pre_cache_to_cache(mq, e, locker, result);
}
return r;
}
static void insert_in_pre_cache(struct mq_policy *mq,
dm_oblock_t oblock)
{
struct entry *e = alloc_entry(&mq->pre_cache_pool);
if (!e)
/*
* There's no spare entry structure, so we grab the least
* used one from the pre_cache.
*/
e = pop(mq, &mq->pre_cache);
if (unlikely(!e)) {
DMWARN("couldn't pop from pre cache");
return;
}
e->dirty = false;
e->oblock = oblock;
e->hit_count = 1;
push(mq, e);
}
static void insert_in_cache(struct mq_policy *mq, dm_oblock_t oblock,
struct policy_locker *locker,
struct policy_result *result)
{
int r;
struct entry *e;
if (epool_empty(&mq->cache_pool)) {
result->op = POLICY_REPLACE;
r = demote_cblock(mq, locker, &result->old_oblock);
if (unlikely(r)) {
result->op = POLICY_MISS;
insert_in_pre_cache(mq, oblock);
return;
}
/*
* This will always succeed, since we've just demoted.
*/
e = alloc_entry(&mq->cache_pool);
BUG_ON(!e);
} else {
e = alloc_entry(&mq->cache_pool);
result->op = POLICY_NEW;
}
e->oblock = oblock;
e->dirty = false;
e->hit_count = 1;
push(mq, e);
result->cblock = infer_cblock(&mq->cache_pool, e);
}
static int no_entry_found(struct mq_policy *mq, dm_oblock_t oblock,
bool can_migrate, bool discarded_oblock,
int data_dir, struct policy_locker *locker,
struct policy_result *result)
{
if (adjusted_promote_threshold(mq, discarded_oblock, data_dir) <= 1) {
if (can_migrate)
insert_in_cache(mq, oblock, locker, result);
else
return -EWOULDBLOCK;
} else {
insert_in_pre_cache(mq, oblock);
result->op = POLICY_MISS;
}
return 0;
}
/*
* Looks the oblock up in the hash table, then decides whether to put in
* pre_cache, or cache etc.
*/
static int map(struct mq_policy *mq, dm_oblock_t oblock,
bool can_migrate, bool discarded_oblock,
int data_dir, struct policy_locker *locker,
struct policy_result *result)
{
int r = 0;
struct entry *e = hash_lookup(mq, oblock);
if (e && in_cache(mq, e))
r = cache_entry_found(mq, e, result);
else if (mq->tracker.thresholds[PATTERN_SEQUENTIAL] &&
iot_pattern(&mq->tracker) == PATTERN_SEQUENTIAL)
result->op = POLICY_MISS;
else if (e)
r = pre_cache_entry_found(mq, e, can_migrate, discarded_oblock,
data_dir, locker, result);
else
r = no_entry_found(mq, oblock, can_migrate, discarded_oblock,
data_dir, locker, result);
if (r == -EWOULDBLOCK)
result->op = POLICY_MISS;
return r;
}
/*----------------------------------------------------------------*/
/*
* Public interface, via the policy struct. See dm-cache-policy.h for a
* description of these.
*/
static struct mq_policy *to_mq_policy(struct dm_cache_policy *p)
{
return container_of(p, struct mq_policy, policy);
}
static void mq_destroy(struct dm_cache_policy *p)
{
struct mq_policy *mq = to_mq_policy(p);
dm cache mq: fix memory allocation failure for large cache devices The memory allocated for the multiqueue policy's hash table doesn't need to be physically contiguous. Use vzalloc() instead of kzalloc(). Fedora has been carrying this fix since 10/10/2013. Failure seen during creation of a 10TB cached device with a 2048 sector block size and 411GB cache size: dmsetup: page allocation failure: order:9, mode:0x10c0d0 CPU: 11 PID: 29235 Comm: dmsetup Not tainted 3.10.4 #3 Hardware name: Supermicro X8DTL/X8DTL, BIOS 2.1a 12/30/2011 000000000010c0d0 ffff880090941898 ffffffff81387ab4 ffff880090941928 ffffffff810bb26f 0000000000000009 000000000010c0d0 ffff880090941928 ffffffff81385dbc ffffffff815f3840 ffffffff00000000 000002000010c0d0 Call Trace: [<ffffffff81387ab4>] dump_stack+0x19/0x1b [<ffffffff810bb26f>] warn_alloc_failed+0x110/0x124 [<ffffffff81385dbc>] ? __alloc_pages_direct_compact+0x17c/0x18e [<ffffffff810bda2e>] __alloc_pages_nodemask+0x6c7/0x75e [<ffffffff810bdad7>] __get_free_pages+0x12/0x3f [<ffffffff810ea148>] kmalloc_order_trace+0x29/0x88 [<ffffffff810ec1fd>] __kmalloc+0x36/0x11b [<ffffffffa031eeed>] ? mq_create+0x1dc/0x2cf [dm_cache_mq] [<ffffffffa031efc0>] mq_create+0x2af/0x2cf [dm_cache_mq] [<ffffffffa0314605>] dm_cache_policy_create+0xa7/0xd2 [dm_cache] [<ffffffffa0312530>] ? cache_ctr+0x245/0xa13 [dm_cache] [<ffffffffa031263e>] cache_ctr+0x353/0xa13 [dm_cache] [<ffffffffa012b916>] dm_table_add_target+0x227/0x2ce [dm_mod] [<ffffffffa012e8e4>] table_load+0x286/0x2ac [dm_mod] [<ffffffffa012e65e>] ? dev_wait+0x8a/0x8a [dm_mod] [<ffffffffa012e324>] ctl_ioctl+0x39a/0x3c2 [dm_mod] [<ffffffffa012e35a>] dm_ctl_ioctl+0xe/0x12 [dm_mod] [<ffffffff81101181>] vfs_ioctl+0x21/0x34 [<ffffffff811019d3>] do_vfs_ioctl+0x3b1/0x3f4 [<ffffffff810f4d2e>] ? ____fput+0x9/0xb [<ffffffff81050b6c>] ? task_work_run+0x7e/0x92 [<ffffffff81101a68>] SyS_ioctl+0x52/0x82 [<ffffffff81391d92>] system_call_fastpath+0x16/0x1b Signed-off-by: Heinz Mauelshagen <heinzm@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com> Cc: stable@vger.kernel.org
2014-02-28 17:02:56 +00:00
vfree(mq->table);
epool_exit(&mq->cache_pool);
epool_exit(&mq->pre_cache_pool);
kfree(mq);
}
static void update_pre_cache_hits(struct list_head *h, void *context)
{
struct entry *e = container_of(h, struct entry, list);
e->hit_count++;
}
static void update_cache_hits(struct list_head *h, void *context)
{
struct mq_policy *mq = context;
struct entry *e = container_of(h, struct entry, list);
e->hit_count++;
mq->hit_count++;
}
static void copy_tick(struct mq_policy *mq)
{
unsigned long flags, tick;
spin_lock_irqsave(&mq->tick_lock, flags);
tick = mq->tick_protected;
if (tick != mq->tick) {
queue_iterate_tick(&mq->pre_cache, update_pre_cache_hits, mq);
queue_iterate_tick(&mq->cache_dirty, update_cache_hits, mq);
queue_iterate_tick(&mq->cache_clean, update_cache_hits, mq);
mq->tick = tick;
}
queue_tick(&mq->pre_cache);
queue_tick(&mq->cache_dirty);
queue_tick(&mq->cache_clean);
queue_update_writeback_sentinels(&mq->cache_dirty);
spin_unlock_irqrestore(&mq->tick_lock, flags);
}
static int mq_map(struct dm_cache_policy *p, dm_oblock_t oblock,
bool can_block, bool can_migrate, bool discarded_oblock,
struct bio *bio, struct policy_locker *locker,
struct policy_result *result)
{
int r;
struct mq_policy *mq = to_mq_policy(p);
result->op = POLICY_MISS;
if (can_block)
mutex_lock(&mq->lock);
else if (!mutex_trylock(&mq->lock))
return -EWOULDBLOCK;
copy_tick(mq);
iot_examine_bio(&mq->tracker, bio);
r = map(mq, oblock, can_migrate, discarded_oblock,
bio_data_dir(bio), locker, result);
mutex_unlock(&mq->lock);
return r;
}
static int mq_lookup(struct dm_cache_policy *p, dm_oblock_t oblock, dm_cblock_t *cblock)
{
int r;
struct mq_policy *mq = to_mq_policy(p);
struct entry *e;
if (!mutex_trylock(&mq->lock))
return -EWOULDBLOCK;
e = hash_lookup(mq, oblock);
if (e && in_cache(mq, e)) {
*cblock = infer_cblock(&mq->cache_pool, e);
r = 0;
} else
r = -ENOENT;
mutex_unlock(&mq->lock);
return r;
}
static void __mq_set_clear_dirty(struct mq_policy *mq, dm_oblock_t oblock, bool set)
{
struct entry *e;
e = hash_lookup(mq, oblock);
BUG_ON(!e || !in_cache(mq, e));
del(mq, e);
e->dirty = set;
push(mq, e);
}
static void mq_set_dirty(struct dm_cache_policy *p, dm_oblock_t oblock)
{
struct mq_policy *mq = to_mq_policy(p);
mutex_lock(&mq->lock);
__mq_set_clear_dirty(mq, oblock, true);
mutex_unlock(&mq->lock);
}
static void mq_clear_dirty(struct dm_cache_policy *p, dm_oblock_t oblock)
{
struct mq_policy *mq = to_mq_policy(p);
mutex_lock(&mq->lock);
__mq_set_clear_dirty(mq, oblock, false);
mutex_unlock(&mq->lock);
}
static int mq_load_mapping(struct dm_cache_policy *p,
dm_oblock_t oblock, dm_cblock_t cblock,
uint32_t hint, bool hint_valid)
{
struct mq_policy *mq = to_mq_policy(p);
struct entry *e;
e = alloc_particular_entry(&mq->cache_pool, cblock);
e->oblock = oblock;
e->dirty = false; /* this gets corrected in a minute */
e->hit_count = hint_valid ? hint : 1;
push(mq, e);
return 0;
}
static int mq_save_hints(struct mq_policy *mq, struct queue *q,
policy_walk_fn fn, void *context)
{
int r;
unsigned level;
struct list_head *h;
struct entry *e;
for (level = 0; level < NR_QUEUE_LEVELS; level++)
list_for_each(h, q->qs + level) {
if (is_sentinel(q, h))
continue;
e = container_of(h, struct entry, list);
r = fn(context, infer_cblock(&mq->cache_pool, e),
e->oblock, e->hit_count);
if (r)
return r;
}
return 0;
}
static int mq_walk_mappings(struct dm_cache_policy *p, policy_walk_fn fn,
void *context)
{
struct mq_policy *mq = to_mq_policy(p);
int r = 0;
mutex_lock(&mq->lock);
r = mq_save_hints(mq, &mq->cache_clean, fn, context);
if (!r)
r = mq_save_hints(mq, &mq->cache_dirty, fn, context);
mutex_unlock(&mq->lock);
return r;
}
static void __remove_mapping(struct mq_policy *mq, dm_oblock_t oblock)
{
struct entry *e;
e = hash_lookup(mq, oblock);
BUG_ON(!e || !in_cache(mq, e));
del(mq, e);
free_entry(&mq->cache_pool, e);
}
static void mq_remove_mapping(struct dm_cache_policy *p, dm_oblock_t oblock)
{
struct mq_policy *mq = to_mq_policy(p);
mutex_lock(&mq->lock);
__remove_mapping(mq, oblock);
mutex_unlock(&mq->lock);
}
static int __remove_cblock(struct mq_policy *mq, dm_cblock_t cblock)
{
struct entry *e = epool_find(&mq->cache_pool, cblock);
if (!e)
return -ENODATA;
del(mq, e);
free_entry(&mq->cache_pool, e);
return 0;
}
static int mq_remove_cblock(struct dm_cache_policy *p, dm_cblock_t cblock)
{
int r;
struct mq_policy *mq = to_mq_policy(p);
mutex_lock(&mq->lock);
r = __remove_cblock(mq, cblock);
mutex_unlock(&mq->lock);
return r;
}
#define CLEAN_TARGET_PERCENTAGE 25
static bool clean_target_met(struct mq_policy *mq)
{
/*
* Cache entries may not be populated. So we're cannot rely on the
* size of the clean queue.
*/
unsigned nr_clean = from_cblock(mq->cache_size) - queue_size(&mq->cache_dirty);
unsigned target = from_cblock(mq->cache_size) * CLEAN_TARGET_PERCENTAGE / 100;
return nr_clean >= target;
}
static int __mq_writeback_work(struct mq_policy *mq, dm_oblock_t *oblock,
dm_cblock_t *cblock)
{
struct entry *e = pop_old(mq, &mq->cache_dirty);
if (!e && !clean_target_met(mq))
e = pop(mq, &mq->cache_dirty);
if (!e)
return -ENODATA;
*oblock = e->oblock;
*cblock = infer_cblock(&mq->cache_pool, e);
e->dirty = false;
push(mq, e);
return 0;
}
static int mq_writeback_work(struct dm_cache_policy *p, dm_oblock_t *oblock,
dm_cblock_t *cblock, bool critical_only)
{
int r;
struct mq_policy *mq = to_mq_policy(p);
mutex_lock(&mq->lock);
r = __mq_writeback_work(mq, oblock, cblock);
mutex_unlock(&mq->lock);
return r;
}
static void __force_mapping(struct mq_policy *mq,
dm_oblock_t current_oblock, dm_oblock_t new_oblock)
{
struct entry *e = hash_lookup(mq, current_oblock);
if (e && in_cache(mq, e)) {
del(mq, e);
e->oblock = new_oblock;
e->dirty = true;
push(mq, e);
}
}
static void mq_force_mapping(struct dm_cache_policy *p,
dm_oblock_t current_oblock, dm_oblock_t new_oblock)
{
struct mq_policy *mq = to_mq_policy(p);
mutex_lock(&mq->lock);
__force_mapping(mq, current_oblock, new_oblock);
mutex_unlock(&mq->lock);
}
static dm_cblock_t mq_residency(struct dm_cache_policy *p)
{
dm_cblock_t r;
struct mq_policy *mq = to_mq_policy(p);
mutex_lock(&mq->lock);
r = to_cblock(mq->cache_pool.nr_allocated);
mutex_unlock(&mq->lock);
return r;
}
static void mq_tick(struct dm_cache_policy *p, bool can_block)
{
struct mq_policy *mq = to_mq_policy(p);
unsigned long flags;
spin_lock_irqsave(&mq->tick_lock, flags);
mq->tick_protected++;
spin_unlock_irqrestore(&mq->tick_lock, flags);
if (can_block) {
mutex_lock(&mq->lock);
copy_tick(mq);
mutex_unlock(&mq->lock);
}
}
static int mq_set_config_value(struct dm_cache_policy *p,
const char *key, const char *value)
{
struct mq_policy *mq = to_mq_policy(p);
unsigned long tmp;
if (kstrtoul(value, 10, &tmp))
return -EINVAL;
if (!strcasecmp(key, "random_threshold")) {
mq->tracker.thresholds[PATTERN_RANDOM] = tmp;
} else if (!strcasecmp(key, "sequential_threshold")) {
mq->tracker.thresholds[PATTERN_SEQUENTIAL] = tmp;
} else if (!strcasecmp(key, "discard_promote_adjustment"))
mq->discard_promote_adjustment = tmp;
else if (!strcasecmp(key, "read_promote_adjustment"))
mq->read_promote_adjustment = tmp;
else if (!strcasecmp(key, "write_promote_adjustment"))
mq->write_promote_adjustment = tmp;
else
return -EINVAL;
return 0;
}
static int mq_emit_config_values(struct dm_cache_policy *p, char *result,
unsigned maxlen, ssize_t *sz_ptr)
{
ssize_t sz = *sz_ptr;
struct mq_policy *mq = to_mq_policy(p);
DMEMIT("10 random_threshold %u "
"sequential_threshold %u "
"discard_promote_adjustment %u "
"read_promote_adjustment %u "
"write_promote_adjustment %u ",
mq->tracker.thresholds[PATTERN_RANDOM],
mq->tracker.thresholds[PATTERN_SEQUENTIAL],
mq->discard_promote_adjustment,
mq->read_promote_adjustment,
mq->write_promote_adjustment);
*sz_ptr = sz;
return 0;
}
/* Init the policy plugin interface function pointers. */
static void init_policy_functions(struct mq_policy *mq)
{
mq->policy.destroy = mq_destroy;
mq->policy.map = mq_map;
mq->policy.lookup = mq_lookup;
mq->policy.set_dirty = mq_set_dirty;
mq->policy.clear_dirty = mq_clear_dirty;
mq->policy.load_mapping = mq_load_mapping;
mq->policy.walk_mappings = mq_walk_mappings;
mq->policy.remove_mapping = mq_remove_mapping;
mq->policy.remove_cblock = mq_remove_cblock;
mq->policy.writeback_work = mq_writeback_work;
mq->policy.force_mapping = mq_force_mapping;
mq->policy.residency = mq_residency;
mq->policy.tick = mq_tick;
mq->policy.emit_config_values = mq_emit_config_values;
mq->policy.set_config_value = mq_set_config_value;
}
static struct dm_cache_policy *mq_create(dm_cblock_t cache_size,
sector_t origin_size,
sector_t cache_block_size)
{
struct mq_policy *mq = kzalloc(sizeof(*mq), GFP_KERNEL);
if (!mq)
return NULL;
init_policy_functions(mq);
iot_init(&mq->tracker, SEQUENTIAL_THRESHOLD_DEFAULT, RANDOM_THRESHOLD_DEFAULT);
mq->cache_size = cache_size;
if (epool_init(&mq->pre_cache_pool, from_cblock(cache_size))) {
DMERR("couldn't initialize pool of pre-cache entries");
goto bad_pre_cache_init;
}
if (epool_init(&mq->cache_pool, from_cblock(cache_size))) {
DMERR("couldn't initialize pool of cache entries");
goto bad_cache_init;
}
mq->tick_protected = 0;
mq->tick = 0;
mq->hit_count = 0;
mq->generation = 0;
mq->discard_promote_adjustment = DEFAULT_DISCARD_PROMOTE_ADJUSTMENT;
mq->read_promote_adjustment = DEFAULT_READ_PROMOTE_ADJUSTMENT;
mq->write_promote_adjustment = DEFAULT_WRITE_PROMOTE_ADJUSTMENT;
mutex_init(&mq->lock);
spin_lock_init(&mq->tick_lock);
queue_init(&mq->pre_cache);
queue_init(&mq->cache_clean);
queue_init(&mq->cache_dirty);
mq->generation_period = max((unsigned) from_cblock(cache_size), 1024U);
mq->nr_buckets = next_power(from_cblock(cache_size) / 2, 16);
mq->hash_bits = ffs(mq->nr_buckets) - 1;
dm cache mq: fix memory allocation failure for large cache devices The memory allocated for the multiqueue policy's hash table doesn't need to be physically contiguous. Use vzalloc() instead of kzalloc(). Fedora has been carrying this fix since 10/10/2013. Failure seen during creation of a 10TB cached device with a 2048 sector block size and 411GB cache size: dmsetup: page allocation failure: order:9, mode:0x10c0d0 CPU: 11 PID: 29235 Comm: dmsetup Not tainted 3.10.4 #3 Hardware name: Supermicro X8DTL/X8DTL, BIOS 2.1a 12/30/2011 000000000010c0d0 ffff880090941898 ffffffff81387ab4 ffff880090941928 ffffffff810bb26f 0000000000000009 000000000010c0d0 ffff880090941928 ffffffff81385dbc ffffffff815f3840 ffffffff00000000 000002000010c0d0 Call Trace: [<ffffffff81387ab4>] dump_stack+0x19/0x1b [<ffffffff810bb26f>] warn_alloc_failed+0x110/0x124 [<ffffffff81385dbc>] ? __alloc_pages_direct_compact+0x17c/0x18e [<ffffffff810bda2e>] __alloc_pages_nodemask+0x6c7/0x75e [<ffffffff810bdad7>] __get_free_pages+0x12/0x3f [<ffffffff810ea148>] kmalloc_order_trace+0x29/0x88 [<ffffffff810ec1fd>] __kmalloc+0x36/0x11b [<ffffffffa031eeed>] ? mq_create+0x1dc/0x2cf [dm_cache_mq] [<ffffffffa031efc0>] mq_create+0x2af/0x2cf [dm_cache_mq] [<ffffffffa0314605>] dm_cache_policy_create+0xa7/0xd2 [dm_cache] [<ffffffffa0312530>] ? cache_ctr+0x245/0xa13 [dm_cache] [<ffffffffa031263e>] cache_ctr+0x353/0xa13 [dm_cache] [<ffffffffa012b916>] dm_table_add_target+0x227/0x2ce [dm_mod] [<ffffffffa012e8e4>] table_load+0x286/0x2ac [dm_mod] [<ffffffffa012e65e>] ? dev_wait+0x8a/0x8a [dm_mod] [<ffffffffa012e324>] ctl_ioctl+0x39a/0x3c2 [dm_mod] [<ffffffffa012e35a>] dm_ctl_ioctl+0xe/0x12 [dm_mod] [<ffffffff81101181>] vfs_ioctl+0x21/0x34 [<ffffffff811019d3>] do_vfs_ioctl+0x3b1/0x3f4 [<ffffffff810f4d2e>] ? ____fput+0x9/0xb [<ffffffff81050b6c>] ? task_work_run+0x7e/0x92 [<ffffffff81101a68>] SyS_ioctl+0x52/0x82 [<ffffffff81391d92>] system_call_fastpath+0x16/0x1b Signed-off-by: Heinz Mauelshagen <heinzm@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com> Cc: stable@vger.kernel.org
2014-02-28 17:02:56 +00:00
mq->table = vzalloc(sizeof(*mq->table) * mq->nr_buckets);
if (!mq->table)
goto bad_alloc_table;
return &mq->policy;
bad_alloc_table:
epool_exit(&mq->cache_pool);
bad_cache_init:
epool_exit(&mq->pre_cache_pool);
bad_pre_cache_init:
kfree(mq);
return NULL;
}
/*----------------------------------------------------------------*/
static struct dm_cache_policy_type mq_policy_type = {
.name = "mq",
.version = {1, 4, 0},
.hint_size = 4,
.owner = THIS_MODULE,
.create = mq_create
};
static int __init mq_init(void)
{
int r;
mq_entry_cache = kmem_cache_create("dm_mq_policy_cache_entry",
sizeof(struct entry),
__alignof__(struct entry),
0, NULL);
if (!mq_entry_cache)
return -ENOMEM;
r = dm_cache_policy_register(&mq_policy_type);
if (r) {
DMERR("register failed %d", r);
kmem_cache_destroy(mq_entry_cache);
return -ENOMEM;
}
return 0;
}
static void __exit mq_exit(void)
{
dm_cache_policy_unregister(&mq_policy_type);
kmem_cache_destroy(mq_entry_cache);
}
module_init(mq_init);
module_exit(mq_exit);
MODULE_AUTHOR("Joe Thornber <dm-devel@redhat.com>");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("mq cache policy");