linux/drivers/md/bcache/writeback.c

514 lines
12 KiB
C
Raw Normal View History

/*
* background writeback - scan btree for dirty data and write it to the backing
* device
*
* Copyright 2010, 2011 Kent Overstreet <kent.overstreet@gmail.com>
* Copyright 2012 Google, Inc.
*/
#include "bcache.h"
#include "btree.h"
#include "debug.h"
#include "writeback.h"
#include <linux/delay.h>
#include <linux/freezer.h>
#include <linux/kthread.h>
#include <trace/events/bcache.h>
/* Rate limiting */
static void __update_writeback_rate(struct cached_dev *dc)
{
struct cache_set *c = dc->disk.c;
uint64_t cache_sectors = c->nbuckets * c->sb.bucket_size;
uint64_t cache_dirty_target =
div_u64(cache_sectors * dc->writeback_percent, 100);
int64_t target = div64_u64(cache_dirty_target * bdev_sectors(dc->bdev),
c->cached_dev_sectors);
/* PD controller */
int64_t dirty = bcache_dev_sectors_dirty(&dc->disk);
int64_t derivative = dirty - dc->disk.sectors_dirty_last;
int64_t proportional = dirty - target;
int64_t change;
dc->disk.sectors_dirty_last = dirty;
/* Scale to sectors per second */
proportional *= dc->writeback_rate_update_seconds;
proportional = div_s64(proportional, dc->writeback_rate_p_term_inverse);
derivative = div_s64(derivative, dc->writeback_rate_update_seconds);
derivative = ewma_add(dc->disk.sectors_dirty_derivative, derivative,
(dc->writeback_rate_d_term /
dc->writeback_rate_update_seconds) ?: 1, 0);
derivative *= dc->writeback_rate_d_term;
derivative = div_s64(derivative, dc->writeback_rate_p_term_inverse);
change = proportional + derivative;
/* Don't increase writeback rate if the device isn't keeping up */
if (change > 0 &&
time_after64(local_clock(),
dc->writeback_rate.next + NSEC_PER_MSEC))
change = 0;
dc->writeback_rate.rate =
clamp_t(int64_t, (int64_t) dc->writeback_rate.rate + change,
1, NSEC_PER_MSEC);
dc->writeback_rate_proportional = proportional;
dc->writeback_rate_derivative = derivative;
dc->writeback_rate_change = change;
dc->writeback_rate_target = target;
}
static void update_writeback_rate(struct work_struct *work)
{
struct cached_dev *dc = container_of(to_delayed_work(work),
struct cached_dev,
writeback_rate_update);
down_read(&dc->writeback_lock);
if (atomic_read(&dc->has_dirty) &&
dc->writeback_percent)
__update_writeback_rate(dc);
up_read(&dc->writeback_lock);
schedule_delayed_work(&dc->writeback_rate_update,
dc->writeback_rate_update_seconds * HZ);
}
static unsigned writeback_delay(struct cached_dev *dc, unsigned sectors)
{
if (test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags) ||
!dc->writeback_percent)
return 0;
return bch_next_delay(&dc->writeback_rate, sectors);
}
struct dirty_io {
struct closure cl;
struct cached_dev *dc;
struct bio bio;
};
static void dirty_init(struct keybuf_key *w)
{
struct dirty_io *io = w->private;
struct bio *bio = &io->bio;
bio_init(bio);
if (!io->dc->writeback_percent)
bio_set_prio(bio, IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0));
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
2013-10-12 06:44:27 +08:00
bio->bi_iter.bi_size = KEY_SIZE(&w->key) << 9;
bio->bi_max_vecs = DIV_ROUND_UP(KEY_SIZE(&w->key), PAGE_SECTORS);
bio->bi_private = w;
bio->bi_io_vec = bio->bi_inline_vecs;
bch_bio_map(bio, NULL);
}
static void dirty_io_destructor(struct closure *cl)
{
struct dirty_io *io = container_of(cl, struct dirty_io, cl);
kfree(io);
}
static void write_dirty_finish(struct closure *cl)
{
struct dirty_io *io = container_of(cl, struct dirty_io, cl);
struct keybuf_key *w = io->bio.bi_private;
struct cached_dev *dc = io->dc;
struct bio_vec *bv;
int i;
bio_for_each_segment_all(bv, &io->bio, i)
__free_page(bv->bv_page);
/* This is kind of a dumb way of signalling errors. */
if (KEY_DIRTY(&w->key)) {
int ret;
unsigned i;
struct keylist keys;
bch_keylist_init(&keys);
bkey_copy(keys.top, &w->key);
SET_KEY_DIRTY(keys.top, false);
bch_keylist_push(&keys);
for (i = 0; i < KEY_PTRS(&w->key); i++)
atomic_inc(&PTR_BUCKET(dc->disk.c, &w->key, i)->pin);
ret = bch_btree_insert(dc->disk.c, &keys, NULL, &w->key);
if (ret)
trace_bcache_writeback_collision(&w->key);
atomic_long_inc(ret
? &dc->disk.c->writeback_keys_failed
: &dc->disk.c->writeback_keys_done);
}
bch_keybuf_del(&dc->writeback_keys, w);
up(&dc->in_flight);
closure_return_with_destructor(cl, dirty_io_destructor);
}
static void dirty_endio(struct bio *bio)
{
struct keybuf_key *w = bio->bi_private;
struct dirty_io *io = w->private;
if (bio->bi_error)
SET_KEY_DIRTY(&w->key, false);
closure_put(&io->cl);
}
static void write_dirty(struct closure *cl)
{
struct dirty_io *io = container_of(cl, struct dirty_io, cl);
struct keybuf_key *w = io->bio.bi_private;
dirty_init(w);
io->bio.bi_rw = WRITE;
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
2013-10-12 06:44:27 +08:00
io->bio.bi_iter.bi_sector = KEY_START(&w->key);
io->bio.bi_bdev = io->dc->bdev;
io->bio.bi_end_io = dirty_endio;
closure_bio_submit(&io->bio, cl);
continue_at(cl, write_dirty_finish, system_wq);
}
static void read_dirty_endio(struct bio *bio)
{
struct keybuf_key *w = bio->bi_private;
struct dirty_io *io = w->private;
bch_count_io_errors(PTR_CACHE(io->dc->disk.c, &w->key, 0),
bio->bi_error, "reading dirty data from cache");
dirty_endio(bio);
}
static void read_dirty_submit(struct closure *cl)
{
struct dirty_io *io = container_of(cl, struct dirty_io, cl);
closure_bio_submit(&io->bio, cl);
continue_at(cl, write_dirty, system_wq);
}
static void read_dirty(struct cached_dev *dc)
{
unsigned delay = 0;
struct keybuf_key *w;
struct dirty_io *io;
struct closure cl;
closure_init_stack(&cl);
/*
* XXX: if we error, background writeback just spins. Should use some
* mempools.
*/
while (!kthread_should_stop()) {
try_to_freeze();
w = bch_keybuf_next(&dc->writeback_keys);
if (!w)
break;
BUG_ON(ptr_stale(dc->disk.c, &w->key, 0));
if (KEY_START(&w->key) != dc->last_read ||
jiffies_to_msecs(delay) > 50)
while (!kthread_should_stop() && delay)
delay = schedule_timeout_interruptible(delay);
dc->last_read = KEY_OFFSET(&w->key);
io = kzalloc(sizeof(struct dirty_io) + sizeof(struct bio_vec)
* DIV_ROUND_UP(KEY_SIZE(&w->key), PAGE_SECTORS),
GFP_KERNEL);
if (!io)
goto err;
w->private = io;
io->dc = dc;
dirty_init(w);
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
2013-10-12 06:44:27 +08:00
io->bio.bi_iter.bi_sector = PTR_OFFSET(&w->key, 0);
io->bio.bi_bdev = PTR_CACHE(dc->disk.c,
&w->key, 0)->bdev;
io->bio.bi_rw = READ;
io->bio.bi_end_io = read_dirty_endio;
if (bio_alloc_pages(&io->bio, GFP_KERNEL))
goto err_free;
trace_bcache_writeback(&w->key);
down(&dc->in_flight);
closure_call(&io->cl, read_dirty_submit, NULL, &cl);
delay = writeback_delay(dc, KEY_SIZE(&w->key));
}
if (0) {
err_free:
kfree(w->private);
err:
bch_keybuf_del(&dc->writeback_keys, w);
}
/*
* Wait for outstanding writeback IOs to finish (and keybuf slots to be
* freed) before refilling again
*/
closure_sync(&cl);
}
/* Scan for dirty data */
void bcache_dev_sectors_dirty_add(struct cache_set *c, unsigned inode,
uint64_t offset, int nr_sectors)
{
struct bcache_device *d = c->devices[inode];
unsigned stripe_offset, stripe, sectors_dirty;
if (!d)
return;
stripe = offset_to_stripe(d, offset);
stripe_offset = offset & (d->stripe_size - 1);
while (nr_sectors) {
int s = min_t(unsigned, abs(nr_sectors),
d->stripe_size - stripe_offset);
if (nr_sectors < 0)
s = -s;
if (stripe >= d->nr_stripes)
return;
sectors_dirty = atomic_add_return(s,
d->stripe_sectors_dirty + stripe);
if (sectors_dirty == d->stripe_size)
set_bit(stripe, d->full_dirty_stripes);
else
clear_bit(stripe, d->full_dirty_stripes);
nr_sectors -= s;
stripe_offset = 0;
stripe++;
}
}
static bool dirty_pred(struct keybuf *buf, struct bkey *k)
{
return KEY_DIRTY(k);
}
static void refill_full_stripes(struct cached_dev *dc)
{
struct keybuf *buf = &dc->writeback_keys;
unsigned start_stripe, stripe, next_stripe;
bool wrapped = false;
stripe = offset_to_stripe(&dc->disk, KEY_OFFSET(&buf->last_scanned));
if (stripe >= dc->disk.nr_stripes)
stripe = 0;
start_stripe = stripe;
while (1) {
stripe = find_next_bit(dc->disk.full_dirty_stripes,
dc->disk.nr_stripes, stripe);
if (stripe == dc->disk.nr_stripes)
goto next;
next_stripe = find_next_zero_bit(dc->disk.full_dirty_stripes,
dc->disk.nr_stripes, stripe);
buf->last_scanned = KEY(dc->disk.id,
stripe * dc->disk.stripe_size, 0);
bch_refill_keybuf(dc->disk.c, buf,
&KEY(dc->disk.id,
next_stripe * dc->disk.stripe_size, 0),
dirty_pred);
if (array_freelist_empty(&buf->freelist))
return;
stripe = next_stripe;
next:
if (wrapped && stripe > start_stripe)
return;
if (stripe == dc->disk.nr_stripes) {
stripe = 0;
wrapped = true;
}
}
}
static bool refill_dirty(struct cached_dev *dc)
{
struct keybuf *buf = &dc->writeback_keys;
struct bkey end = KEY(dc->disk.id, MAX_KEY_OFFSET, 0);
bool searched_from_start = false;
if (dc->partial_stripes_expensive) {
refill_full_stripes(dc);
if (array_freelist_empty(&buf->freelist))
return false;
}
if (bkey_cmp(&buf->last_scanned, &end) >= 0) {
buf->last_scanned = KEY(dc->disk.id, 0, 0);
searched_from_start = true;
}
bch_refill_keybuf(dc->disk.c, buf, &end, dirty_pred);
return bkey_cmp(&buf->last_scanned, &end) >= 0 && searched_from_start;
}
static int bch_writeback_thread(void *arg)
{
struct cached_dev *dc = arg;
bool searched_full_index;
while (!kthread_should_stop()) {
down_write(&dc->writeback_lock);
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())
return 0;
try_to_freeze();
schedule();
continue;
}
searched_full_index = refill_dirty(dc);
if (searched_full_index &&
RB_EMPTY_ROOT(&dc->writeback_keys.keys)) {
atomic_set(&dc->has_dirty, 0);
cached_dev_put(dc);
SET_BDEV_STATE(&dc->sb, BDEV_STATE_CLEAN);
bch_write_bdev_super(dc, NULL);
}
up_write(&dc->writeback_lock);
bch_ratelimit_reset(&dc->writeback_rate);
read_dirty(dc);
if (searched_full_index) {
unsigned delay = dc->writeback_delay * HZ;
while (delay &&
!kthread_should_stop() &&
!test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags))
delay = schedule_timeout_interruptible(delay);
}
}
return 0;
}
/* Init */
struct sectors_dirty_init {
struct btree_op op;
unsigned inode;
};
static int sectors_dirty_init_fn(struct btree_op *_op, struct btree *b,
struct bkey *k)
{
struct sectors_dirty_init *op = container_of(_op,
struct sectors_dirty_init, op);
if (KEY_INODE(k) > op->inode)
return MAP_DONE;
if (KEY_DIRTY(k))
bcache_dev_sectors_dirty_add(b->c, KEY_INODE(k),
KEY_START(k), KEY_SIZE(k));
return MAP_CONTINUE;
}
void bch_sectors_dirty_init(struct cached_dev *dc)
{
struct sectors_dirty_init op;
bch_btree_op_init(&op.op, -1);
op.inode = dc->disk.id;
bch_btree_map_keys(&op.op, dc->disk.c, &KEY(op.inode, 0, 0),
sectors_dirty_init_fn, 0);
dc->disk.sectors_dirty_last = bcache_dev_sectors_dirty(&dc->disk);
}
void bch_cached_dev_writeback_init(struct cached_dev *dc)
{
sema_init(&dc->in_flight, 64);
init_rwsem(&dc->writeback_lock);
bch_keybuf_init(&dc->writeback_keys);
dc->writeback_metadata = true;
dc->writeback_running = true;
dc->writeback_percent = 10;
dc->writeback_delay = 30;
dc->writeback_rate.rate = 1024;
dc->writeback_rate_update_seconds = 5;
dc->writeback_rate_d_term = 30;
dc->writeback_rate_p_term_inverse = 6000;
INIT_DELAYED_WORK(&dc->writeback_rate_update, update_writeback_rate);
}
int bch_cached_dev_writeback_start(struct cached_dev *dc)
{
dc->writeback_thread = kthread_create(bch_writeback_thread, dc,
"bcache_writeback");
if (IS_ERR(dc->writeback_thread))
return PTR_ERR(dc->writeback_thread);
schedule_delayed_work(&dc->writeback_rate_update,
dc->writeback_rate_update_seconds * HZ);
bch_writeback_queue(dc);
return 0;
}