linux/drivers/md/bcache/movinggc.c

252 lines
5.4 KiB
C
Raw Normal View History

/*
* Moving/copying garbage collector
*
* Copyright 2012 Google, Inc.
*/
#include "bcache.h"
#include "btree.h"
#include "debug.h"
#include "request.h"
#include <trace/events/bcache.h>
struct moving_io {
struct closure cl;
struct keybuf_key *w;
struct data_insert_op op;
struct bbio bio;
};
static bool moving_pred(struct keybuf *buf, struct bkey *k)
{
struct cache_set *c = container_of(buf, struct cache_set,
moving_gc_keys);
unsigned i;
for (i = 0; i < KEY_PTRS(k); i++)
if (ptr_available(c, k, i) &&
GC_MOVE(PTR_BUCKET(c, k, i)))
return true;
return false;
}
/* Moving GC - IO loop */
static void moving_io_destructor(struct closure *cl)
{
struct moving_io *io = container_of(cl, struct moving_io, cl);
kfree(io);
}
static void write_moving_finish(struct closure *cl)
{
struct moving_io *io = container_of(cl, struct moving_io, cl);
struct bio *bio = &io->bio.bio;
bio_free_pages(bio);
if (io->op.replace_collision)
trace_bcache_gc_copy_collision(&io->w->key);
bch_keybuf_del(&io->op.c->moving_gc_keys, io->w);
up(&io->op.c->moving_in_flight);
closure_return_with_destructor(cl, moving_io_destructor);
}
static void read_moving_endio(struct bio *bio)
{
struct bbio *b = container_of(bio, struct bbio, bio);
struct moving_io *io = container_of(bio->bi_private,
struct moving_io, cl);
if (bio->bi_status)
io->op.status = bio->bi_status;
else if (!KEY_DIRTY(&b->key) &&
ptr_stale(io->op.c, &b->key, 0)) {
io->op.status = BLK_STS_IOERR;
}
bch_bbio_endio(io->op.c, bio, bio->bi_status, "reading data to move");
}
static void moving_init(struct moving_io *io)
{
struct bio *bio = &io->bio.bio;
bio_init(bio, bio->bi_inline_vecs,
DIV_ROUND_UP(KEY_SIZE(&io->w->key), PAGE_SECTORS));
bio_get(bio);
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
2013-10-11 22:44:27 +00:00
bio->bi_iter.bi_size = KEY_SIZE(&io->w->key) << 9;
bio->bi_private = &io->cl;
bch_bio_map(bio, NULL);
}
static void write_moving(struct closure *cl)
{
struct moving_io *io = container_of(cl, struct moving_io, cl);
struct data_insert_op *op = &io->op;
if (!op->status) {
moving_init(io);
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
io->bio.bio.bi_iter.bi_sector = KEY_START(&io->w->key);
op->write_prio = 1;
op->bio = &io->bio.bio;
op->writeback = KEY_DIRTY(&io->w->key);
op->csum = KEY_CSUM(&io->w->key);
bkey_copy(&op->replace_key, &io->w->key);
op->replace = true;
closure_call(&op->cl, bch_data_insert, NULL, cl);
}
continue_at(cl, write_moving_finish, op->wq);
}
static void read_moving_submit(struct closure *cl)
{
struct moving_io *io = container_of(cl, struct moving_io, cl);
struct bio *bio = &io->bio.bio;
bch_submit_bbio(bio, io->op.c, &io->w->key, 0);
continue_at(cl, write_moving, io->op.wq);
}
static void read_moving(struct cache_set *c)
{
struct keybuf_key *w;
struct moving_io *io;
struct bio *bio;
struct closure cl;
closure_init_stack(&cl);
/* XXX: if we error, background writeback could stall indefinitely */
while (!test_bit(CACHE_SET_STOPPING, &c->flags)) {
w = bch_keybuf_next_rescan(c, &c->moving_gc_keys,
&MAX_KEY, moving_pred);
if (!w)
break;
if (ptr_stale(c, &w->key, 0)) {
bch_keybuf_del(&c->moving_gc_keys, w);
continue;
}
io = kzalloc(sizeof(struct moving_io) + sizeof(struct bio_vec)
* DIV_ROUND_UP(KEY_SIZE(&w->key), PAGE_SECTORS),
GFP_KERNEL);
if (!io)
goto err;
w->private = io;
io->w = w;
io->op.inode = KEY_INODE(&w->key);
io->op.c = c;
io->op.wq = c->moving_gc_wq;
moving_init(io);
bio = &io->bio.bio;
bio_set_op_attrs(bio, REQ_OP_READ, 0);
bio->bi_end_io = read_moving_endio;
if (bio_alloc_pages(bio, GFP_KERNEL))
goto err;
trace_bcache_gc_copy(&w->key);
down(&c->moving_in_flight);
closure_call(&io->cl, read_moving_submit, NULL, &cl);
}
if (0) {
err: if (!IS_ERR_OR_NULL(w->private))
kfree(w->private);
bch_keybuf_del(&c->moving_gc_keys, w);
}
closure_sync(&cl);
}
static bool bucket_cmp(struct bucket *l, struct bucket *r)
{
return GC_SECTORS_USED(l) < GC_SECTORS_USED(r);
}
static unsigned bucket_heap_top(struct cache *ca)
{
struct bucket *b;
return (b = heap_peek(&ca->heap)) ? GC_SECTORS_USED(b) : 0;
}
void bch_moving_gc(struct cache_set *c)
{
struct cache *ca;
struct bucket *b;
unsigned i;
if (!c->copy_gc_enabled)
return;
mutex_lock(&c->bucket_lock);
for_each_cache(ca, c, i) {
unsigned sectors_to_move = 0;
unsigned reserve_sectors = ca->sb.bucket_size *
fifo_used(&ca->free[RESERVE_MOVINGGC]);
ca->heap.used = 0;
for_each_bucket(b, ca) {
if (GC_MARK(b) == GC_MARK_METADATA ||
!GC_SECTORS_USED(b) ||
GC_SECTORS_USED(b) == ca->sb.bucket_size ||
atomic_read(&b->pin))
continue;
if (!heap_full(&ca->heap)) {
sectors_to_move += GC_SECTORS_USED(b);
heap_add(&ca->heap, b, bucket_cmp);
} else if (bucket_cmp(b, heap_peek(&ca->heap))) {
sectors_to_move -= bucket_heap_top(ca);
sectors_to_move += GC_SECTORS_USED(b);
ca->heap.data[0] = b;
heap_sift(&ca->heap, 0, bucket_cmp);
}
}
while (sectors_to_move > reserve_sectors) {
heap_pop(&ca->heap, b, bucket_cmp);
sectors_to_move -= GC_SECTORS_USED(b);
}
while (heap_pop(&ca->heap, b, bucket_cmp))
SET_GC_MOVE(b, 1);
}
mutex_unlock(&c->bucket_lock);
c->moving_gc_keys.last_scanned = ZERO_KEY;
read_moving(c);
}
void bch_moving_init_cache_set(struct cache_set *c)
{
bch_keybuf_init(&c->moving_gc_keys);
sema_init(&c->moving_in_flight, 64);
}