From: Ming Lei <tom.leiming@gmail.com>
To: Shaohua Li <shli@kernel.org>, Jens Axboe <axboe@fb.com>,
linux-kernel@vger.kernel.org, linux-raid@vger.kernel.org,
linux-block@vger.kernel.org,
Christoph Hellwig <hch@infradead.org>
Cc: Ming Lei <tom.leiming@gmail.com>
Subject: [PATCH v1 12/14] md: raid10: don't use bio's vec table to manage resync pages
Date: Fri, 24 Feb 2017 23:42:49 +0800 [thread overview]
Message-ID: <1487950971-1131-13-git-send-email-tom.leiming@gmail.com> (raw)
In-Reply-To: <1487950971-1131-1-git-send-email-tom.leiming@gmail.com>
Now we allocate one page array for managing resync pages, instead
of using bio's vec table to do that, and the old way is very hacky
and won't work any more if multipage bvec is enabled.
The introduced cost is that we need to allocate (128 + 16) * copies
bytes per r10_bio, and it is fine because the inflight r10_bio for
resync shouldn't be much, as pointed by Shaohua.
Also bio_reset() in raid10_sync_request() and reshape_request()
are removed because all bios are freshly new now in these functions
and not necessary to reset any more.
This patch can be thought as cleanup too.
Suggested-by: Shaohua Li <shli@kernel.org>
Signed-off-by: Ming Lei <tom.leiming@gmail.com>
---
drivers/md/raid10.c | 127 ++++++++++++++++++++++++++++++----------------------
1 file changed, 74 insertions(+), 53 deletions(-)
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index c76e08ea4b92..931f5d80608b 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -110,6 +110,16 @@ static void end_reshape(struct r10conf *conf);
#define raid10_log(md, fmt, args...) \
do { if ((md)->queue) blk_add_trace_msg((md)->queue, "raid10 " fmt, ##args); } while (0)
+static inline struct resync_pages *get_resync_pages(struct bio *bio)
+{
+ return bio->bi_private;
+}
+
+static inline struct r10bio *get_resync_r10bio(struct bio *bio)
+{
+ return get_resync_pages(bio)->raid_bio;
+}
+
static void * r10bio_pool_alloc(gfp_t gfp_flags, void *data)
{
struct r10conf *conf = data;
@@ -140,11 +150,11 @@ static void r10bio_pool_free(void *r10_bio, void *data)
static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data)
{
struct r10conf *conf = data;
- struct page *page;
struct r10bio *r10_bio;
struct bio *bio;
- int i, j;
- int nalloc;
+ int j;
+ int nalloc, nalloc_rp;
+ struct resync_pages *rps;
r10_bio = r10bio_pool_alloc(gfp_flags, conf);
if (!r10_bio)
@@ -156,6 +166,15 @@ static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data)
else
nalloc = 2; /* recovery */
+ /* allocate once for all bios */
+ if (!conf->have_replacement)
+ nalloc_rp = nalloc;
+ else
+ nalloc_rp = nalloc * 2;
+ rps = kmalloc(sizeof(struct resync_pages) * nalloc_rp, gfp_flags);
+ if (!rps)
+ goto out_free_r10bio;
+
/*
* Allocate bios.
*/
@@ -175,36 +194,40 @@ static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data)
* Allocate RESYNC_PAGES data pages and attach them
* where needed.
*/
- for (j = 0 ; j < nalloc; j++) {
+ for (j = 0; j < nalloc; j++) {
struct bio *rbio = r10_bio->devs[j].repl_bio;
+ struct resync_pages *rp, *rp_repl;
+
+ rp = &rps[j];
+ if (rbio)
+ rp_repl = &rps[nalloc + j];
+
bio = r10_bio->devs[j].bio;
- for (i = 0; i < RESYNC_PAGES; i++) {
- if (j > 0 && !test_bit(MD_RECOVERY_SYNC,
- &conf->mddev->recovery)) {
- /* we can share bv_page's during recovery
- * and reshape */
- struct bio *rbio = r10_bio->devs[0].bio;
- page = rbio->bi_io_vec[i].bv_page;
- get_page(page);
- } else
- page = alloc_page(gfp_flags);
- if (unlikely(!page))
+
+ if (!j || test_bit(MD_RECOVERY_SYNC,
+ &conf->mddev->recovery)) {
+ if (resync_alloc_pages(rp, gfp_flags))
goto out_free_pages;
+ } else {
+ memcpy(rp, &rps[0], sizeof(*rp));
+ resync_get_all_pages(rp);
+ }
- bio->bi_io_vec[i].bv_page = page;
- if (rbio)
- rbio->bi_io_vec[i].bv_page = page;
+ rp->idx = 0;
+ rp->raid_bio = r10_bio;
+ bio->bi_private = rp;
+ if (rbio) {
+ memcpy(rp_repl, rp, sizeof(*rp));
+ rbio->bi_private = rp_repl;
}
}
return r10_bio;
out_free_pages:
- for ( ; i > 0 ; i--)
- safe_put_page(bio->bi_io_vec[i-1].bv_page);
- while (j--)
- for (i = 0; i < RESYNC_PAGES ; i++)
- safe_put_page(r10_bio->devs[j].bio->bi_io_vec[i].bv_page);
+ while (--j >= 0)
+ resync_free_pages(&rps[j * 2]);
+
j = 0;
out_free_bio:
for ( ; j < nalloc; j++) {
@@ -213,30 +236,34 @@ static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data)
if (r10_bio->devs[j].repl_bio)
bio_put(r10_bio->devs[j].repl_bio);
}
+ kfree(rps);
+out_free_r10bio:
r10bio_pool_free(r10_bio, conf);
return NULL;
}
static void r10buf_pool_free(void *__r10_bio, void *data)
{
- int i;
struct r10conf *conf = data;
struct r10bio *r10bio = __r10_bio;
int j;
+ struct resync_pages *rp = NULL;
- for (j=0; j < conf->copies; j++) {
+ for (j = conf->copies; j--; ) {
struct bio *bio = r10bio->devs[j].bio;
- if (bio) {
- for (i = 0; i < RESYNC_PAGES; i++) {
- safe_put_page(bio->bi_io_vec[i].bv_page);
- bio->bi_io_vec[i].bv_page = NULL;
- }
- bio_put(bio);
- }
+
+ rp = get_resync_pages(bio);
+ resync_free_pages(rp);
+ bio_put(bio);
+
bio = r10bio->devs[j].repl_bio;
if (bio)
bio_put(bio);
}
+
+ /* resync pages array stored in the 1st bio's .bi_private */
+ kfree(rp);
+
r10bio_pool_free(r10bio, conf);
}
@@ -1935,7 +1962,7 @@ static void __end_sync_read(struct r10bio *r10_bio, struct bio *bio, int d)
static void end_sync_read(struct bio *bio)
{
- struct r10bio *r10_bio = bio->bi_private;
+ struct r10bio *r10_bio = get_resync_r10bio(bio);
struct r10conf *conf = r10_bio->mddev->private;
int d = find_bio_disk(conf, r10_bio, bio, NULL, NULL);
@@ -1944,6 +1971,7 @@ static void end_sync_read(struct bio *bio)
static void end_reshape_read(struct bio *bio)
{
+ /* reshape read bio isn't allocated from r10buf_pool */
struct r10bio *r10_bio = bio->bi_private;
__end_sync_read(r10_bio, bio, r10_bio->read_slot);
@@ -1978,7 +2006,7 @@ static void end_sync_request(struct r10bio *r10_bio)
static void end_sync_write(struct bio *bio)
{
- struct r10bio *r10_bio = bio->bi_private;
+ struct r10bio *r10_bio = get_resync_r10bio(bio);
struct mddev *mddev = r10_bio->mddev;
struct r10conf *conf = mddev->private;
int d;
@@ -2058,6 +2086,7 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
for (i=0 ; i < conf->copies ; i++) {
int j, d;
struct md_rdev *rdev;
+ struct resync_pages *rp;
tbio = r10_bio->devs[i].bio;
@@ -2099,11 +2128,13 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
* First we need to fixup bv_offset, bv_len and
* bi_vecs, as the read request might have corrupted these
*/
+ rp = get_resync_pages(tbio);
bio_reset(tbio);
tbio->bi_vcnt = vcnt;
tbio->bi_iter.bi_size = fbio->bi_iter.bi_size;
- tbio->bi_private = r10_bio;
+ rp->raid_bio = r10_bio;
+ tbio->bi_private = rp;
tbio->bi_iter.bi_sector = r10_bio->devs[i].addr;
tbio->bi_end_io = end_sync_write;
bio_set_op_attrs(tbio, REQ_OP_WRITE, 0);
@@ -3171,10 +3202,8 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
}
}
bio = r10_bio->devs[0].bio;
- bio_reset(bio);
bio->bi_next = biolist;
biolist = bio;
- bio->bi_private = r10_bio;
bio->bi_end_io = end_sync_read;
bio_set_op_attrs(bio, REQ_OP_READ, 0);
if (test_bit(FailFast, &rdev->flags))
@@ -3198,10 +3227,8 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
if (!test_bit(In_sync, &mrdev->flags)) {
bio = r10_bio->devs[1].bio;
- bio_reset(bio);
bio->bi_next = biolist;
biolist = bio;
- bio->bi_private = r10_bio;
bio->bi_end_io = end_sync_write;
bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
bio->bi_iter.bi_sector = to_addr
@@ -3226,10 +3253,8 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
if (mreplace == NULL || bio == NULL ||
test_bit(Faulty, &mreplace->flags))
break;
- bio_reset(bio);
bio->bi_next = biolist;
biolist = bio;
- bio->bi_private = r10_bio;
bio->bi_end_io = end_sync_write;
bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
bio->bi_iter.bi_sector = to_addr +
@@ -3351,7 +3376,6 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
r10_bio->devs[i].repl_bio->bi_end_io = NULL;
bio = r10_bio->devs[i].bio;
- bio_reset(bio);
bio->bi_error = -EIO;
rcu_read_lock();
rdev = rcu_dereference(conf->mirrors[d].rdev);
@@ -3376,7 +3400,6 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
atomic_inc(&r10_bio->remaining);
bio->bi_next = biolist;
biolist = bio;
- bio->bi_private = r10_bio;
bio->bi_end_io = end_sync_read;
bio_set_op_attrs(bio, REQ_OP_READ, 0);
if (test_bit(FailFast, &conf->mirrors[d].rdev->flags))
@@ -3395,13 +3418,11 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
/* Need to set up for writing to the replacement */
bio = r10_bio->devs[i].repl_bio;
- bio_reset(bio);
bio->bi_error = -EIO;
sector = r10_bio->devs[i].addr;
bio->bi_next = biolist;
biolist = bio;
- bio->bi_private = r10_bio;
bio->bi_end_io = end_sync_write;
bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
if (test_bit(FailFast, &conf->mirrors[d].rdev->flags))
@@ -3441,12 +3462,12 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
break;
for (bio= biolist ; bio ; bio=bio->bi_next) {
struct bio *bio2;
- page = bio->bi_io_vec[bio->bi_vcnt].bv_page;
+ page = resync_fetch_page(get_resync_pages(bio));
if (bio_add_page(bio, page, len, 0))
continue;
/* stop here */
- bio->bi_io_vec[bio->bi_vcnt].bv_page = page;
+ resync_store_page(get_resync_pages(bio), page);
for (bio2 = biolist;
bio2 && bio2 != bio;
bio2 = bio2->bi_next) {
@@ -3458,7 +3479,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
}
nr_sectors += len>>9;
sector_nr += len>>9;
- } while (biolist->bi_vcnt < RESYNC_PAGES);
+ } while (resync_page_available(get_resync_pages(biolist)));
bio_full:
r10_bio->sectors = nr_sectors;
@@ -3467,7 +3488,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
biolist = biolist->bi_next;
bio->bi_next = NULL;
- r10_bio = bio->bi_private;
+ r10_bio = get_resync_r10bio(bio);
r10_bio->sectors = nr_sectors;
if (bio->bi_end_io == end_sync_read) {
@@ -4362,6 +4383,7 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
struct bio *blist;
struct bio *bio, *read_bio;
int sectors_done = 0;
+ struct page **pages;
if (sector_nr == 0) {
/* If restarting in the middle, skip the initial sectors */
@@ -4512,11 +4534,9 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
if (!rdev2 || test_bit(Faulty, &rdev2->flags))
continue;
- bio_reset(b);
b->bi_bdev = rdev2->bdev;
b->bi_iter.bi_sector = r10_bio->devs[s/2].addr +
rdev2->new_data_offset;
- b->bi_private = r10_bio;
b->bi_end_io = end_reshape_write;
bio_set_op_attrs(b, REQ_OP_WRITE, 0);
b->bi_next = blist;
@@ -4526,8 +4546,9 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
/* Now add as many pages as possible to all of these bios. */
nr_sectors = 0;
+ pages = get_resync_pages(r10_bio->devs[0].bio)->pages;
for (s = 0 ; s < max_sectors; s += PAGE_SIZE >> 9) {
- struct page *page = r10_bio->devs[0].bio->bi_io_vec[s/(PAGE_SIZE>>9)].bv_page;
+ struct page *page = pages[s / (PAGE_SIZE >> 9)];
int len = (max_sectors - s) << 9;
if (len > PAGE_SIZE)
len = PAGE_SIZE;
@@ -4720,7 +4741,7 @@ static int handle_reshape_read_error(struct mddev *mddev,
static void end_reshape_write(struct bio *bio)
{
- struct r10bio *r10_bio = bio->bi_private;
+ struct r10bio *r10_bio = get_resync_r10bio(bio);
struct mddev *mddev = r10_bio->mddev;
struct r10conf *conf = mddev->private;
int d;
--
2.7.4
next prev parent reply other threads:[~2017-02-24 15:43 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-02-24 15:42 [PATCH v1 00/14] md: cleanup on direct access to bvec table Ming Lei
2017-02-24 15:42 ` [PATCH v1 01/14] block: introduce bio_segments_all() Ming Lei
2017-02-25 18:22 ` Christoph Hellwig
2017-02-28 12:15 ` Ming Lei
2017-02-24 15:42 ` [PATCH v1 02/14] block: introduce bio_remove_last_page() Ming Lei
2017-02-25 18:23 ` Christoph Hellwig
2017-02-28 12:18 ` Ming Lei
2017-02-24 15:42 ` [PATCH v1 03/14] md: raid1/raid10: use bio_remove_last_page() Ming Lei
2017-02-24 15:42 ` [PATCH v1 04/14] md: move two macros into md.h Ming Lei
2017-02-24 15:42 ` [PATCH v1 05/14] md: prepare for managing resync I/O pages in clean way Ming Lei
2017-02-24 15:42 ` [PATCH v1 06/14] md: raid1: simplify r1buf_pool_free() Ming Lei
2017-02-24 15:42 ` [PATCH v1 07/14] md: raid1: don't use bio's vec table to manage resync pages Ming Lei
2017-02-24 15:42 ` [PATCH v1 08/14] md: raid1: retrieve page from pre-allocated resync page array Ming Lei
2017-02-24 15:42 ` [PATCH v1 09/14] md: raid1: use bio helper in process_checks() Ming Lei
2017-02-24 15:42 ` [PATCH v1 10/14] md: raid1: use bio_segments_all() Ming Lei
2017-02-24 15:42 ` [PATCH v1 11/14] md: raid10: refactor code of read reshape's .bi_end_io Ming Lei
2017-02-24 15:42 ` Ming Lei [this message]
2017-02-24 15:42 ` [PATCH v1 13/14] md: raid10: retrieve page from preallocated resync page array Ming Lei
2017-02-24 15:42 ` [PATCH v1 14/14] md: raid10: avoid direct access to bvec table in handle_reshape_read_error Ming Lei
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1487950971-1131-13-git-send-email-tom.leiming@gmail.com \
--to=tom.leiming@gmail.com \
--cc=axboe@fb.com \
--cc=hch@infradead.org \
--cc=linux-block@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-raid@vger.kernel.org \
--cc=shli@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).