* [PATCH v6 01/15] md/raid456: convert macro STRIPE_* to members of struct r5conf
2020-07-15 12:42 [PATCH v6 00/15] md/raid5: set STRIPE_SIZE as a configurable value Yufen Yu
@ 2020-07-15 12:42 ` Yufen Yu
2020-07-15 12:42 ` [PATCH v6 02/15] md/raid5: set default stripe_size as 4096 Yufen Yu
` (14 subsequent siblings)
15 siblings, 0 replies; 19+ messages in thread
From: Yufen Yu @ 2020-07-15 12:42 UTC (permalink / raw)
To: song; +Cc: linux-raid, neilb, guoqing.jiang, houtao1, yuyufen
We convert STRIPE_SIZE, STRIPE_SHIFT and STRIPE_SECTORS to stripe_size,
stripe_shift and stripe_sectors as members of struct r5conf. Then each
raid456 array can config different stripe_size. This patch is prepared
for following configurable stripe_size.
Simply replace word STRIPE_ with conf->stripe_ and add 'conf' argument
for function stripe_hash_locks_hash() and r5_next_bio() to get stripe_size.
After that, we initialize stripe_size into setup_conf().
Signed-off-by: Yufen Yu <yuyufen@huawei.com>
---
drivers/md/raid5-cache.c | 8 +-
drivers/md/raid5-ppl.c | 12 +-
drivers/md/raid5.c | 252 +++++++++++++++++++++++----------------
drivers/md/raid5.h | 41 +++----
4 files changed, 181 insertions(+), 132 deletions(-)
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index 0bea21d81697..e381542628b6 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -298,8 +298,8 @@ r5c_return_dev_pending_writes(struct r5conf *conf, struct r5dev *dev)
wbi = dev->written;
dev->written = NULL;
while (wbi && wbi->bi_iter.bi_sector <
- dev->sector + STRIPE_SECTORS) {
- wbi2 = r5_next_bio(wbi, dev->sector);
+ dev->sector + conf->stripe_sectors) {
+ wbi2 = r5_next_bio(conf, wbi, dev->sector);
md_write_end(conf->mddev);
bio_endio(wbi);
wbi = wbi2;
@@ -316,7 +316,7 @@ void r5c_handle_cached_data_endio(struct r5conf *conf,
set_bit(R5_UPTODATE, &sh->dev[i].flags);
r5c_return_dev_pending_writes(conf, &sh->dev[i]);
md_bitmap_endwrite(conf->mddev->bitmap, sh->sector,
- STRIPE_SECTORS,
+ conf->stripe_sectors,
!test_bit(STRIPE_DEGRADED, &sh->state),
0);
}
@@ -364,7 +364,7 @@ void r5c_check_cached_full_stripe(struct r5conf *conf)
*/
if (atomic_read(&conf->r5c_cached_full_stripes) >=
min(R5C_FULL_STRIPE_FLUSH_BATCH(conf),
- conf->chunk_sectors >> STRIPE_SHIFT))
+ conf->chunk_sectors >> conf->stripe_shift))
r5l_wake_reclaim(conf->log, 0);
}
diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c
index a750f4bbb5d9..412648412165 100644
--- a/drivers/md/raid5-ppl.c
+++ b/drivers/md/raid5-ppl.c
@@ -324,7 +324,7 @@ static int ppl_log_stripe(struct ppl_log *log, struct stripe_head *sh)
* be just after the last logged stripe and write to the same
* disks. Use bit shift and logarithm to avoid 64-bit division.
*/
- if ((sh->sector == sh_last->sector + STRIPE_SECTORS) &&
+ if ((sh->sector == sh_last->sector + conf->stripe_sectors) &&
(data_sector >> ilog2(conf->chunk_sectors) ==
data_sector_last >> ilog2(conf->chunk_sectors)) &&
((data_sector - data_sector_last) * data_disks ==
@@ -844,9 +844,9 @@ static int ppl_recover_entry(struct ppl_log *log, struct ppl_header_entry *e,
/* if start and end is 4k aligned, use a 4k block */
if (block_size == 512 &&
- (r_sector_first & (STRIPE_SECTORS - 1)) == 0 &&
- (r_sector_last & (STRIPE_SECTORS - 1)) == 0)
- block_size = STRIPE_SIZE;
+ (r_sector_first & (conf->stripe_sectors - 1)) == 0 &&
+ (r_sector_last & (conf->stripe_sectors - 1)) == 0)
+ block_size = conf->stripe_size;
/* iterate through blocks in strip */
for (i = 0; i < strip_sectors; i += (block_size >> 9)) {
@@ -1264,6 +1264,7 @@ static int ppl_validate_rdev(struct md_rdev *rdev)
char b[BDEVNAME_SIZE];
int ppl_data_sectors;
int ppl_size_new;
+ struct r5conf *conf = rdev->mddev->private;
/*
* The configured PPL size must be enough to store
@@ -1274,7 +1275,8 @@ static int ppl_validate_rdev(struct md_rdev *rdev)
ppl_data_sectors = rdev->ppl.size - (PPL_HEADER_SIZE >> 9);
if (ppl_data_sectors > 0)
- ppl_data_sectors = rounddown(ppl_data_sectors, STRIPE_SECTORS);
+ ppl_data_sectors =
+ rounddown(ppl_data_sectors, conf->stripe_sectors);
if (ppl_data_sectors <= 0) {
pr_warn("md/raid:%s: PPL space too small on %s\n",
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index a4fbafa5b8f8..7914da4e0092 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -69,13 +69,13 @@ static struct workqueue_struct *raid5_wq;
static inline struct hlist_head *stripe_hash(struct r5conf *conf, sector_t sect)
{
- int hash = (sect >> STRIPE_SHIFT) & HASH_MASK;
+ int hash = (sect >> conf->stripe_shift) & HASH_MASK;
return &conf->stripe_hashtbl[hash];
}
-static inline int stripe_hash_locks_hash(sector_t sect)
+static inline int stripe_hash_locks_hash(struct r5conf *conf, sector_t sect)
{
- return (sect >> STRIPE_SHIFT) & STRIPE_HASH_LOCKS_MASK;
+ return (sect >> conf->stripe_shift) & STRIPE_HASH_LOCKS_MASK;
}
static inline void lock_device_hash_lock(struct r5conf *conf, int hash)
@@ -627,7 +627,7 @@ raid5_get_active_stripe(struct r5conf *conf, sector_t sector,
int previous, int noblock, int noquiesce)
{
struct stripe_head *sh;
- int hash = stripe_hash_locks_hash(sector);
+ int hash = stripe_hash_locks_hash(conf, sector);
int inc_empty_inactive_list_flag;
pr_debug("get_stripe, sector %llu\n", (unsigned long long)sector);
@@ -748,9 +748,9 @@ static void stripe_add_to_batch_list(struct r5conf *conf, struct stripe_head *sh
tmp_sec = sh->sector;
if (!sector_div(tmp_sec, conf->chunk_sectors))
return;
- head_sector = sh->sector - STRIPE_SECTORS;
+ head_sector = sh->sector - conf->stripe_sectors;
- hash = stripe_hash_locks_hash(head_sector);
+ hash = stripe_hash_locks_hash(conf, head_sector);
spin_lock_irq(conf->hash_locks + hash);
head = __find_stripe(conf, head_sector, conf->generation);
if (head && !atomic_inc_not_zero(&head->count)) {
@@ -1057,8 +1057,9 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
test_bit(WriteErrorSeen, &rdev->flags)) {
sector_t first_bad;
int bad_sectors;
- int bad = is_badblock(rdev, sh->sector, STRIPE_SECTORS,
- &first_bad, &bad_sectors);
+ int bad = is_badblock(rdev, sh->sector,
+ conf->stripe_sectors,
+ &first_bad, &bad_sectors);
if (!bad)
break;
@@ -1089,7 +1090,7 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
if (rdev) {
if (s->syncing || s->expanding || s->expanded
|| s->replacing)
- md_sync_acct(rdev->bdev, STRIPE_SECTORS);
+ md_sync_acct(rdev->bdev, conf->stripe_sectors);
set_bit(STRIPE_IO_STARTED, &sh->state);
@@ -1129,9 +1130,9 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
else
sh->dev[i].vec.bv_page = sh->dev[i].page;
bi->bi_vcnt = 1;
- bi->bi_io_vec[0].bv_len = STRIPE_SIZE;
+ bi->bi_io_vec[0].bv_len = conf->stripe_size;
bi->bi_io_vec[0].bv_offset = 0;
- bi->bi_iter.bi_size = STRIPE_SIZE;
+ bi->bi_iter.bi_size = conf->stripe_size;
bi->bi_write_hint = sh->dev[i].write_hint;
if (!rrdev)
sh->dev[i].write_hint = RWH_WRITE_LIFE_NOT_SET;
@@ -1156,7 +1157,7 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
if (rrdev) {
if (s->syncing || s->expanding || s->expanded
|| s->replacing)
- md_sync_acct(rrdev->bdev, STRIPE_SECTORS);
+ md_sync_acct(rrdev->bdev, conf->stripe_sectors);
set_bit(STRIPE_IO_STARTED, &sh->state);
@@ -1183,9 +1184,9 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
WARN_ON(test_bit(R5_UPTODATE, &sh->dev[i].flags));
sh->dev[i].rvec.bv_page = sh->dev[i].page;
rbi->bi_vcnt = 1;
- rbi->bi_io_vec[0].bv_len = STRIPE_SIZE;
+ rbi->bi_io_vec[0].bv_len = conf->stripe_size;
rbi->bi_io_vec[0].bv_offset = 0;
- rbi->bi_iter.bi_size = STRIPE_SIZE;
+ rbi->bi_iter.bi_size = conf->stripe_size;
rbi->bi_write_hint = sh->dev[i].write_hint;
sh->dev[i].write_hint = RWH_WRITE_LIFE_NOT_SET;
/*
@@ -1235,6 +1236,7 @@ async_copy_data(int frombio, struct bio *bio, struct page **page,
int page_offset;
struct async_submit_ctl submit;
enum async_tx_flags flags = 0;
+ struct r5conf *conf = sh->raid_conf;
if (bio->bi_iter.bi_sector >= sector)
page_offset = (signed)(bio->bi_iter.bi_sector - sector) * 512;
@@ -1256,8 +1258,8 @@ async_copy_data(int frombio, struct bio *bio, struct page **page,
len -= b_offset;
}
- if (len > 0 && page_offset + len > STRIPE_SIZE)
- clen = STRIPE_SIZE - page_offset;
+ if (len > 0 && page_offset + len > conf->stripe_size)
+ clen = conf->stripe_size - page_offset;
else
clen = len;
@@ -1267,7 +1269,7 @@ async_copy_data(int frombio, struct bio *bio, struct page **page,
if (frombio) {
if (sh->raid_conf->skip_copy &&
b_offset == 0 && page_offset == 0 &&
- clen == STRIPE_SIZE &&
+ clen == conf->stripe_size &&
!no_skipcopy)
*page = bio_page;
else
@@ -1292,6 +1294,7 @@ static void ops_complete_biofill(void *stripe_head_ref)
{
struct stripe_head *sh = stripe_head_ref;
int i;
+ struct r5conf *conf = sh->raid_conf;
pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
@@ -1312,8 +1315,8 @@ static void ops_complete_biofill(void *stripe_head_ref)
rbi = dev->read;
dev->read = NULL;
while (rbi && rbi->bi_iter.bi_sector <
- dev->sector + STRIPE_SECTORS) {
- rbi2 = r5_next_bio(rbi, dev->sector);
+ dev->sector + conf->stripe_sectors) {
+ rbi2 = r5_next_bio(conf, rbi, dev->sector);
bio_endio(rbi);
rbi = rbi2;
}
@@ -1344,10 +1347,11 @@ static void ops_run_biofill(struct stripe_head *sh)
dev->toread = NULL;
spin_unlock_irq(&sh->stripe_lock);
while (rbi && rbi->bi_iter.bi_sector <
- dev->sector + STRIPE_SECTORS) {
+ dev->sector + sh->raid_conf->stripe_sectors) {
tx = async_copy_data(0, rbi, &dev->page,
dev->sector, tx, sh, 0);
- rbi = r5_next_bio(rbi, dev->sector);
+ rbi = r5_next_bio(sh->raid_conf, rbi,
+ dev->sector);
}
}
}
@@ -1413,6 +1417,7 @@ ops_run_compute5(struct stripe_head *sh, struct raid5_percpu *percpu)
struct dma_async_tx_descriptor *tx;
struct async_submit_ctl submit;
int i;
+ struct r5conf *conf = sh->raid_conf;
BUG_ON(sh->batch_head);
@@ -1429,9 +1434,11 @@ ops_run_compute5(struct stripe_head *sh, struct raid5_percpu *percpu)
init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST, NULL,
ops_complete_compute, sh, to_addr_conv(sh, percpu, 0));
if (unlikely(count == 1))
- tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE, &submit);
+ tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0,
+ conf->stripe_size, &submit);
else
- tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, &submit);
+ tx = async_xor(xor_dest, xor_srcs, 0, count,
+ conf->stripe_size, &submit);
return tx;
}
@@ -1496,6 +1503,7 @@ ops_run_compute6_1(struct stripe_head *sh, struct raid5_percpu *percpu)
struct page *dest;
int i;
int count;
+ struct r5conf *conf = sh->raid_conf;
BUG_ON(sh->batch_head);
if (sh->ops.target < 0)
@@ -1522,7 +1530,8 @@ ops_run_compute6_1(struct stripe_head *sh, struct raid5_percpu *percpu)
init_async_submit(&submit, ASYNC_TX_FENCE, NULL,
ops_complete_compute, sh,
to_addr_conv(sh, percpu, 0));
- tx = async_gen_syndrome(blocks, 0, count+2, STRIPE_SIZE, &submit);
+ tx = async_gen_syndrome(blocks, 0, count+2,
+ conf->stripe_size, &submit);
} else {
/* Compute any data- or p-drive using XOR */
count = 0;
@@ -1535,7 +1544,8 @@ ops_run_compute6_1(struct stripe_head *sh, struct raid5_percpu *percpu)
init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST,
NULL, ops_complete_compute, sh,
to_addr_conv(sh, percpu, 0));
- tx = async_xor(dest, blocks, 0, count, STRIPE_SIZE, &submit);
+ tx = async_xor(dest, blocks, 0, count,
+ conf->stripe_size, &submit);
}
return tx;
@@ -1555,6 +1565,7 @@ ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu)
struct dma_async_tx_descriptor *tx;
struct page **blocks = to_addr_page(percpu, 0);
struct async_submit_ctl submit;
+ struct r5conf *conf = sh->raid_conf;
BUG_ON(sh->batch_head);
pr_debug("%s: stripe %llu block1: %d block2: %d\n",
@@ -1598,7 +1609,7 @@ ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu)
ops_complete_compute, sh,
to_addr_conv(sh, percpu, 0));
return async_gen_syndrome(blocks, 0, syndrome_disks+2,
- STRIPE_SIZE, &submit);
+ conf->stripe_size, &submit);
} else {
struct page *dest;
int data_target;
@@ -1621,15 +1632,15 @@ ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu)
ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST,
NULL, NULL, NULL,
to_addr_conv(sh, percpu, 0));
- tx = async_xor(dest, blocks, 0, count, STRIPE_SIZE,
- &submit);
+ tx = async_xor(dest, blocks, 0, count,
+ conf->stripe_size, &submit);
count = set_syndrome_sources(blocks, sh, SYNDROME_SRC_ALL);
init_async_submit(&submit, ASYNC_TX_FENCE, tx,
ops_complete_compute, sh,
to_addr_conv(sh, percpu, 0));
return async_gen_syndrome(blocks, 0, count+2,
- STRIPE_SIZE, &submit);
+ conf->stripe_size, &submit);
}
} else {
init_async_submit(&submit, ASYNC_TX_FENCE, NULL,
@@ -1638,12 +1649,13 @@ ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu)
if (failb == syndrome_disks) {
/* We're missing D+P. */
return async_raid6_datap_recov(syndrome_disks+2,
- STRIPE_SIZE, faila,
+ conf->stripe_size, faila,
blocks, &submit);
} else {
/* We're missing D+D. */
return async_raid6_2data_recov(syndrome_disks+2,
- STRIPE_SIZE, faila, failb,
+ conf->stripe_size,
+ faila, failb,
blocks, &submit);
}
}
@@ -1672,6 +1684,7 @@ ops_run_prexor5(struct stripe_head *sh, struct raid5_percpu *percpu,
struct page **xor_srcs = to_addr_page(percpu, 0);
int count = 0, pd_idx = sh->pd_idx, i;
struct async_submit_ctl submit;
+ struct r5conf *conf = sh->raid_conf;
/* existing parity data subtracted */
struct page *xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page;
@@ -1691,7 +1704,8 @@ ops_run_prexor5(struct stripe_head *sh, struct raid5_percpu *percpu,
init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
ops_complete_prexor, sh, to_addr_conv(sh, percpu, 0));
- tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, &submit);
+ tx = async_xor(xor_dest, xor_srcs, 0, count,
+ conf->stripe_size, &submit);
return tx;
}
@@ -1703,6 +1717,7 @@ ops_run_prexor6(struct stripe_head *sh, struct raid5_percpu *percpu,
struct page **blocks = to_addr_page(percpu, 0);
int count;
struct async_submit_ctl submit;
+ struct r5conf *conf = sh->raid_conf;
pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
@@ -1711,7 +1726,8 @@ ops_run_prexor6(struct stripe_head *sh, struct raid5_percpu *percpu,
init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_PQ_XOR_DST, tx,
ops_complete_prexor, sh, to_addr_conv(sh, percpu, 0));
- tx = async_gen_syndrome(blocks, 0, count+2, STRIPE_SIZE, &submit);
+ tx = async_gen_syndrome(blocks, 0, count+2,
+ conf->stripe_size, &submit);
return tx;
}
@@ -1752,7 +1768,7 @@ ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
WARN_ON(dev->page != dev->orig_page);
while (wbi && wbi->bi_iter.bi_sector <
- dev->sector + STRIPE_SECTORS) {
+ dev->sector + conf->stripe_sectors) {
if (wbi->bi_opf & REQ_FUA)
set_bit(R5_WantFUA, &dev->flags);
if (wbi->bi_opf & REQ_SYNC)
@@ -1770,7 +1786,7 @@ ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
clear_bit(R5_OVERWRITE, &dev->flags);
}
}
- wbi = r5_next_bio(wbi, dev->sector);
+ wbi = r5_next_bio(conf, wbi, dev->sector);
}
if (head_sh->batch_head) {
@@ -1848,6 +1864,7 @@ ops_run_reconstruct5(struct stripe_head *sh, struct raid5_percpu *percpu,
int j = 0;
struct stripe_head *head_sh = sh;
int last_stripe;
+ struct r5conf *conf = sh->raid_conf;
pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
@@ -1910,9 +1927,11 @@ ops_run_reconstruct5(struct stripe_head *sh, struct raid5_percpu *percpu,
}
if (unlikely(count == 1))
- tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE, &submit);
+ tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0,
+ conf->stripe_size, &submit);
else
- tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, &submit);
+ tx = async_xor(xor_dest, xor_srcs, 0, count,
+ conf->stripe_size, &submit);
if (!last_stripe) {
j++;
sh = list_first_entry(&sh->batch_list, struct stripe_head,
@@ -1932,6 +1951,7 @@ ops_run_reconstruct6(struct stripe_head *sh, struct raid5_percpu *percpu,
int last_stripe;
int synflags;
unsigned long txflags;
+ struct r5conf *conf = sh->raid_conf;
pr_debug("%s: stripe %llu\n", __func__, (unsigned long long)sh->sector);
@@ -1972,7 +1992,8 @@ ops_run_reconstruct6(struct stripe_head *sh, struct raid5_percpu *percpu,
} else
init_async_submit(&submit, 0, tx, NULL, NULL,
to_addr_conv(sh, percpu, j));
- tx = async_gen_syndrome(blocks, 0, count+2, STRIPE_SIZE, &submit);
+ tx = async_gen_syndrome(blocks, 0, count+2,
+ conf->stripe_size, &submit);
if (!last_stripe) {
j++;
sh = list_first_entry(&sh->batch_list, struct stripe_head,
@@ -2004,6 +2025,7 @@ static void ops_run_check_p(struct stripe_head *sh, struct raid5_percpu *percpu)
struct async_submit_ctl submit;
int count;
int i;
+ struct r5conf *conf = sh->raid_conf;
pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
@@ -2020,7 +2042,7 @@ static void ops_run_check_p(struct stripe_head *sh, struct raid5_percpu *percpu)
init_async_submit(&submit, 0, NULL, NULL, NULL,
to_addr_conv(sh, percpu, 0));
- tx = async_xor_val(xor_dest, xor_srcs, 0, count, STRIPE_SIZE,
+ tx = async_xor_val(xor_dest, xor_srcs, 0, count, conf->stripe_size,
&sh->ops.zero_sum_result, &submit);
atomic_inc(&sh->count);
@@ -2033,6 +2055,7 @@ static void ops_run_check_pq(struct stripe_head *sh, struct raid5_percpu *percpu
struct page **srcs = to_addr_page(percpu, 0);
struct async_submit_ctl submit;
int count;
+ struct r5conf *conf = sh->raid_conf;
pr_debug("%s: stripe %llu checkp: %d\n", __func__,
(unsigned long long)sh->sector, checkp);
@@ -2045,7 +2068,7 @@ static void ops_run_check_pq(struct stripe_head *sh, struct raid5_percpu *percpu
atomic_inc(&sh->count);
init_async_submit(&submit, ASYNC_TX_ACK, NULL, ops_complete_check,
sh, to_addr_conv(sh, percpu, 0));
- async_syndrome_val(srcs, 0, count+2, STRIPE_SIZE,
+ async_syndrome_val(srcs, 0, count+2, conf->stripe_size,
&sh->ops.zero_sum_result, percpu->spare_page, &submit);
}
@@ -2275,7 +2298,7 @@ static int resize_chunks(struct r5conf *conf, int new_disks, int new_sectors)
percpu = per_cpu_ptr(conf->percpu, cpu);
err = scribble_alloc(percpu, new_disks,
- new_sectors / STRIPE_SECTORS);
+ new_sectors / conf->stripe_sectors);
if (err)
break;
}
@@ -2509,10 +2532,11 @@ static void raid5_end_read_request(struct bio * bi)
*/
pr_info_ratelimited(
"md/raid:%s: read error corrected (%lu sectors at %llu on %s)\n",
- mdname(conf->mddev), STRIPE_SECTORS,
+ mdname(conf->mddev),
+ conf->stripe_sectors,
(unsigned long long)s,
bdevname(rdev->bdev, b));
- atomic_add(STRIPE_SECTORS, &rdev->corrected_errors);
+ atomic_add(conf->stripe_sectors, &rdev->corrected_errors);
clear_bit(R5_ReadError, &sh->dev[i].flags);
clear_bit(R5_ReWrite, &sh->dev[i].flags);
} else if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags))
@@ -2585,7 +2609,8 @@ static void raid5_end_read_request(struct bio * bi)
if (!(set_bad
&& test_bit(In_sync, &rdev->flags)
&& rdev_set_badblocks(
- rdev, sh->sector, STRIPE_SECTORS, 0)))
+ rdev, sh->sector,
+ conf->stripe_sectors, 0)))
md_error(conf->mddev, rdev);
}
}
@@ -2637,7 +2662,7 @@ static void raid5_end_write_request(struct bio *bi)
if (bi->bi_status)
md_error(conf->mddev, rdev);
else if (is_badblock(rdev, sh->sector,
- STRIPE_SECTORS,
+ conf->stripe_sectors,
&first_bad, &bad_sectors))
set_bit(R5_MadeGoodRepl, &sh->dev[i].flags);
} else {
@@ -2649,7 +2674,7 @@ static void raid5_end_write_request(struct bio *bi)
set_bit(MD_RECOVERY_NEEDED,
&rdev->mddev->recovery);
} else if (is_badblock(rdev, sh->sector,
- STRIPE_SECTORS,
+ conf->stripe_sectors,
&first_bad, &bad_sectors)) {
set_bit(R5_MadeGood, &sh->dev[i].flags);
if (test_bit(R5_ReadError, &sh->dev[i].flags))
@@ -3283,13 +3308,13 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx,
/* check if page is covered */
sector_t sector = sh->dev[dd_idx].sector;
for (bi=sh->dev[dd_idx].towrite;
- sector < sh->dev[dd_idx].sector + STRIPE_SECTORS &&
+ sector < sh->dev[dd_idx].sector + conf->stripe_sectors &&
bi && bi->bi_iter.bi_sector <= sector;
- bi = r5_next_bio(bi, sh->dev[dd_idx].sector)) {
+ bi = r5_next_bio(conf, bi, sh->dev[dd_idx].sector)) {
if (bio_end_sector(bi) >= sector)
sector = bio_end_sector(bi);
}
- if (sector >= sh->dev[dd_idx].sector + STRIPE_SECTORS)
+ if (sector >= sh->dev[dd_idx].sector + conf->stripe_sectors)
if (!test_and_set_bit(R5_OVERWRITE, &sh->dev[dd_idx].flags))
sh->overwrite_disks++;
}
@@ -3314,7 +3339,7 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx,
set_bit(STRIPE_BITMAP_PENDING, &sh->state);
spin_unlock_irq(&sh->stripe_lock);
md_bitmap_startwrite(conf->mddev->bitmap, sh->sector,
- STRIPE_SECTORS, 0);
+ conf->stripe_sectors, 0);
spin_lock_irq(&sh->stripe_lock);
clear_bit(STRIPE_BITMAP_PENDING, &sh->state);
if (!sh->batch_head) {
@@ -3376,7 +3401,7 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
if (!rdev_set_badblocks(
rdev,
sh->sector,
- STRIPE_SECTORS, 0))
+ conf->stripe_sectors, 0))
md_error(conf->mddev, rdev);
rdev_dec_pending(rdev, conf->mddev);
}
@@ -3396,8 +3421,9 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
wake_up(&conf->wait_for_overlap);
while (bi && bi->bi_iter.bi_sector <
- sh->dev[i].sector + STRIPE_SECTORS) {
- struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector);
+ sh->dev[i].sector + conf->stripe_sectors) {
+ struct bio *nextbi =
+ r5_next_bio(conf, bi, sh->dev[i].sector);
md_write_end(conf->mddev);
bio_io_error(bi);
@@ -3405,7 +3431,7 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
}
if (bitmap_end)
md_bitmap_endwrite(conf->mddev->bitmap, sh->sector,
- STRIPE_SECTORS, 0, 0);
+ conf->stripe_sectors, 0, 0);
bitmap_end = 0;
/* and fail all 'written' */
bi = sh->dev[i].written;
@@ -3417,8 +3443,9 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
if (bi) bitmap_end = 1;
while (bi && bi->bi_iter.bi_sector <
- sh->dev[i].sector + STRIPE_SECTORS) {
- struct bio *bi2 = r5_next_bio(bi, sh->dev[i].sector);
+ sh->dev[i].sector + conf->stripe_sectors) {
+ struct bio *bi2 =
+ r5_next_bio(conf, bi, sh->dev[i].sector);
md_write_end(conf->mddev);
bio_io_error(bi);
@@ -3441,9 +3468,9 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
if (bi)
s->to_read--;
while (bi && bi->bi_iter.bi_sector <
- sh->dev[i].sector + STRIPE_SECTORS) {
- struct bio *nextbi =
- r5_next_bio(bi, sh->dev[i].sector);
+ sh->dev[i].sector + conf->stripe_sectors) {
+ struct bio *nextbi = r5_next_bio(conf,
+ bi, sh->dev[i].sector);
bio_io_error(bi);
bi = nextbi;
@@ -3451,7 +3478,7 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
}
if (bitmap_end)
md_bitmap_endwrite(conf->mddev->bitmap, sh->sector,
- STRIPE_SECTORS, 0, 0);
+ conf->stripe_sectors, 0, 0);
/* If we were in the middle of a write the parity block might
* still be locked - so just clear all R5_LOCKED flags
*/
@@ -3496,14 +3523,14 @@ handle_failed_sync(struct r5conf *conf, struct stripe_head *sh,
&& !test_bit(Faulty, &rdev->flags)
&& !test_bit(In_sync, &rdev->flags)
&& !rdev_set_badblocks(rdev, sh->sector,
- STRIPE_SECTORS, 0))
+ conf->stripe_sectors, 0))
abort = 1;
rdev = rcu_dereference(conf->disks[i].replacement);
if (rdev
&& !test_bit(Faulty, &rdev->flags)
&& !test_bit(In_sync, &rdev->flags)
&& !rdev_set_badblocks(rdev, sh->sector,
- STRIPE_SECTORS, 0))
+ conf->stripe_sectors, 0))
abort = 1;
}
rcu_read_unlock();
@@ -3511,7 +3538,7 @@ handle_failed_sync(struct r5conf *conf, struct stripe_head *sh,
conf->recovery_disabled =
conf->mddev->recovery_disabled;
}
- md_done_sync(conf->mddev, STRIPE_SECTORS, !abort);
+ md_done_sync(conf->mddev, conf->stripe_sectors, !abort);
}
static int want_replace(struct stripe_head *sh, int disk_idx)
@@ -3785,14 +3812,15 @@ static void handle_stripe_clean_event(struct r5conf *conf,
wbi = dev->written;
dev->written = NULL;
while (wbi && wbi->bi_iter.bi_sector <
- dev->sector + STRIPE_SECTORS) {
- wbi2 = r5_next_bio(wbi, dev->sector);
+ dev->sector + conf->stripe_sectors) {
+ wbi2 = r5_next_bio(conf,
+ wbi, dev->sector);
md_write_end(conf->mddev);
bio_endio(wbi);
wbi = wbi2;
}
md_bitmap_endwrite(conf->mddev->bitmap, sh->sector,
- STRIPE_SECTORS,
+ conf->stripe_sectors,
!test_bit(STRIPE_DEGRADED, &sh->state),
0);
if (head_sh->batch_head) {
@@ -4099,7 +4127,8 @@ static void handle_parity_checks5(struct r5conf *conf, struct stripe_head *sh,
*/
set_bit(STRIPE_INSYNC, &sh->state);
else {
- atomic64_add(STRIPE_SECTORS, &conf->mddev->resync_mismatches);
+ atomic64_add(conf->stripe_sectors,
+ &conf->mddev->resync_mismatches);
if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery)) {
/* don't try to repair!! */
set_bit(STRIPE_INSYNC, &sh->state);
@@ -4107,7 +4136,7 @@ static void handle_parity_checks5(struct r5conf *conf, struct stripe_head *sh,
"%llu-%llu\n", mdname(conf->mddev),
(unsigned long long) sh->sector,
(unsigned long long) sh->sector +
- STRIPE_SECTORS);
+ conf->stripe_sectors);
} else {
sh->check_state = check_state_compute_run;
set_bit(STRIPE_COMPUTE_RUN, &sh->state);
@@ -4264,7 +4293,8 @@ static void handle_parity_checks6(struct r5conf *conf, struct stripe_head *sh,
*/
}
} else {
- atomic64_add(STRIPE_SECTORS, &conf->mddev->resync_mismatches);
+ atomic64_add(conf->stripe_sectors,
+ &conf->mddev->resync_mismatches);
if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery)) {
/* don't try to repair!! */
set_bit(STRIPE_INSYNC, &sh->state);
@@ -4272,7 +4302,7 @@ static void handle_parity_checks6(struct r5conf *conf, struct stripe_head *sh,
"%llu-%llu\n", mdname(conf->mddev),
(unsigned long long) sh->sector,
(unsigned long long) sh->sector +
- STRIPE_SECTORS);
+ conf->stripe_sectors);
} else {
int *target = &sh->ops.target;
@@ -4343,7 +4373,8 @@ static void handle_stripe_expansion(struct r5conf *conf, struct stripe_head *sh)
/* place all the copies on one channel */
init_async_submit(&submit, 0, tx, NULL, NULL, NULL);
tx = async_memcpy(sh2->dev[dd_idx].page,
- sh->dev[i].page, 0, 0, STRIPE_SIZE,
+ sh->dev[i].page, 0, 0,
+ conf->stripe_size,
&submit);
set_bit(R5_Expanded, &sh2->dev[dd_idx].flags);
@@ -4442,8 +4473,9 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
*/
rdev = rcu_dereference(conf->disks[i].replacement);
if (rdev && !test_bit(Faulty, &rdev->flags) &&
- rdev->recovery_offset >= sh->sector + STRIPE_SECTORS &&
- !is_badblock(rdev, sh->sector, STRIPE_SECTORS,
+ (rdev->recovery_offset >=
+ sh->sector + conf->stripe_sectors) &&
+ !is_badblock(rdev, sh->sector, conf->stripe_sectors,
&first_bad, &bad_sectors))
set_bit(R5_ReadRepl, &dev->flags);
else {
@@ -4457,8 +4489,9 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
if (rdev && test_bit(Faulty, &rdev->flags))
rdev = NULL;
if (rdev) {
- is_bad = is_badblock(rdev, sh->sector, STRIPE_SECTORS,
- &first_bad, &bad_sectors);
+ is_bad = is_badblock(rdev, sh->sector,
+ conf->stripe_sectors,
+ &first_bad, &bad_sectors);
if (s->blocked_rdev == NULL
&& (test_bit(Blocked, &rdev->flags)
|| is_bad < 0)) {
@@ -4484,7 +4517,8 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
}
} else if (test_bit(In_sync, &rdev->flags))
set_bit(R5_Insync, &dev->flags);
- else if (sh->sector + STRIPE_SECTORS <= rdev->recovery_offset)
+ else if (sh->sector + conf->stripe_sectors <=
+ rdev->recovery_offset)
/* in sync if before recovery_offset */
set_bit(R5_Insync, &dev->flags);
else if (test_bit(R5_UPTODATE, &dev->flags) &&
@@ -4927,7 +4961,7 @@ static void handle_stripe(struct stripe_head *sh)
if ((s.syncing || s.replacing) && s.locked == 0 &&
!test_bit(STRIPE_COMPUTE_RUN, &sh->state) &&
test_bit(STRIPE_INSYNC, &sh->state)) {
- md_done_sync(conf->mddev, STRIPE_SECTORS, 1);
+ md_done_sync(conf->mddev, conf->stripe_sectors, 1);
clear_bit(STRIPE_SYNCING, &sh->state);
if (test_and_clear_bit(R5_Overlap, &sh->dev[sh->pd_idx].flags))
wake_up(&conf->wait_for_overlap);
@@ -4995,7 +5029,7 @@ static void handle_stripe(struct stripe_head *sh)
clear_bit(STRIPE_EXPAND_READY, &sh->state);
atomic_dec(&conf->reshape_stripes);
wake_up(&conf->wait_for_overlap);
- md_done_sync(conf->mddev, STRIPE_SECTORS, 1);
+ md_done_sync(conf->mddev, conf->stripe_sectors, 1);
}
if (s.expanding && s.locked == 0 &&
@@ -5025,14 +5059,14 @@ static void handle_stripe(struct stripe_head *sh)
/* We own a safe reference to the rdev */
rdev = conf->disks[i].rdev;
if (!rdev_set_badblocks(rdev, sh->sector,
- STRIPE_SECTORS, 0))
+ conf->stripe_sectors, 0))
md_error(conf->mddev, rdev);
rdev_dec_pending(rdev, conf->mddev);
}
if (test_and_clear_bit(R5_MadeGood, &dev->flags)) {
rdev = conf->disks[i].rdev;
rdev_clear_badblocks(rdev, sh->sector,
- STRIPE_SECTORS, 0);
+ conf->stripe_sectors, 0);
rdev_dec_pending(rdev, conf->mddev);
}
if (test_and_clear_bit(R5_MadeGoodRepl, &dev->flags)) {
@@ -5041,7 +5075,7 @@ static void handle_stripe(struct stripe_head *sh)
/* rdev have been moved down */
rdev = conf->disks[i].rdev;
rdev_clear_badblocks(rdev, sh->sector,
- STRIPE_SECTORS, 0);
+ conf->stripe_sectors, 0);
rdev_dec_pending(rdev, conf->mddev);
}
}
@@ -5505,7 +5539,8 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi)
/* Skip discard while reshape is happening */
return;
- logical_sector = bi->bi_iter.bi_sector & ~((sector_t)STRIPE_SECTORS-1);
+ logical_sector = bi->bi_iter.bi_sector &
+ ~((sector_t)conf->stripe_sectors-1);
last_sector = bio_end_sector(bi);
bi->bi_next = NULL;
@@ -5520,7 +5555,7 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi)
last_sector *= conf->chunk_sectors;
for (; logical_sector < last_sector;
- logical_sector += STRIPE_SECTORS) {
+ logical_sector += conf->stripe_sectors) {
DEFINE_WAIT(w);
int d;
again:
@@ -5565,7 +5600,7 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi)
d++)
md_bitmap_startwrite(mddev->bitmap,
sh->sector,
- STRIPE_SECTORS,
+ conf->stripe_sectors,
0);
sh->bm_seq = conf->seq_flush + 1;
set_bit(STRIPE_BIT_DELAY, &sh->state);
@@ -5630,12 +5665,14 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
return true;
}
- logical_sector = bi->bi_iter.bi_sector & ~((sector_t)STRIPE_SECTORS-1);
+ logical_sector = bi->bi_iter.bi_sector &
+ ~((sector_t)conf->stripe_sectors-1);
last_sector = bio_end_sector(bi);
bi->bi_next = NULL;
prepare_to_wait(&conf->wait_for_overlap, &w, TASK_UNINTERRUPTIBLE);
- for (;logical_sector < last_sector; logical_sector += STRIPE_SECTORS) {
+ for (; logical_sector < last_sector;
+ logical_sector += conf->stripe_sectors) {
int previous;
int seq;
@@ -5917,7 +5954,7 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk
}
INIT_LIST_HEAD(&stripes);
- for (i = 0; i < reshape_sectors; i += STRIPE_SECTORS) {
+ for (i = 0; i < reshape_sectors; i += conf->stripe_sectors) {
int j;
int skipped_disk = 0;
sh = raid5_get_active_stripe(conf, stripe_addr+i, 0, 0, 1);
@@ -5938,7 +5975,8 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk
skipped_disk = 1;
continue;
}
- memset(page_address(sh->dev[j].page), 0, STRIPE_SIZE);
+ memset(page_address(sh->dev[j].page), 0,
+ conf->stripe_size);
set_bit(R5_Expanded, &sh->dev[j].flags);
set_bit(R5_UPTODATE, &sh->dev[j].flags);
}
@@ -5973,7 +6011,7 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk
set_bit(STRIPE_EXPAND_SOURCE, &sh->state);
set_bit(STRIPE_HANDLE, &sh->state);
raid5_release_stripe(sh);
- first_sector += STRIPE_SECTORS;
+ first_sector += conf->stripe_sectors;
}
/* Now that the sources are clearly marked, we can release
* the destination stripes
@@ -6079,11 +6117,12 @@ static inline sector_t raid5_sync_request(struct mddev *mddev, sector_t sector_n
if (!test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) &&
!conf->fullsync &&
!md_bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, 1) &&
- sync_blocks >= STRIPE_SECTORS) {
+ sync_blocks >= conf->stripe_sectors) {
/* we can skip this block, and probably more */
- sync_blocks /= STRIPE_SECTORS;
+ sync_blocks /= conf->stripe_sectors;
*skipped = 1;
- return sync_blocks * STRIPE_SECTORS; /* keep things rounded to whole stripes */
+ /* keep things rounded to whole stripes */
+ return sync_blocks * conf->stripe_sectors;
}
md_bitmap_cond_end_sync(mddev->bitmap, sector_nr, false);
@@ -6116,7 +6155,7 @@ static inline sector_t raid5_sync_request(struct mddev *mddev, sector_t sector_n
raid5_release_stripe(sh);
- return STRIPE_SECTORS;
+ return conf->stripe_sectors;
}
static int retry_aligned_read(struct r5conf *conf, struct bio *raid_bio,
@@ -6139,14 +6178,14 @@ static int retry_aligned_read(struct r5conf *conf, struct bio *raid_bio,
int handled = 0;
logical_sector = raid_bio->bi_iter.bi_sector &
- ~((sector_t)STRIPE_SECTORS-1);
+ ~((sector_t)conf->stripe_sectors-1);
sector = raid5_compute_sector(conf, logical_sector,
0, &dd_idx, NULL);
last_sector = bio_end_sector(raid_bio);
for (; logical_sector < last_sector;
- logical_sector += STRIPE_SECTORS,
- sector += STRIPE_SECTORS,
+ logical_sector += conf->stripe_sectors,
+ sector += conf->stripe_sectors,
scnt++) {
if (scnt < offset)
@@ -6766,7 +6805,7 @@ static int alloc_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu
conf->previous_raid_disks),
max(conf->chunk_sectors,
conf->prev_chunk_sectors)
- / STRIPE_SECTORS)) {
+ / conf->stripe_sectors)) {
free_scratch_buffer(conf, percpu);
return -ENOMEM;
}
@@ -6918,6 +6957,11 @@ static struct r5conf *setup_conf(struct mddev *mddev)
conf = kzalloc(sizeof(struct r5conf), GFP_KERNEL);
if (conf == NULL)
goto abort;
+
+ conf->stripe_size = PAGE_SIZE;
+ conf->stripe_shift = PAGE_SHIFT - 9;
+ conf->stripe_sectors = conf->stripe_size >> 9;
+
INIT_LIST_HEAD(&conf->free_list);
INIT_LIST_HEAD(&conf->pending_list);
conf->pending_data = kcalloc(PENDING_IO_MAX,
@@ -7069,8 +7113,9 @@ static struct r5conf *setup_conf(struct mddev *mddev)
conf->min_nr_stripes = NR_STRIPES;
if (mddev->reshape_position != MaxSector) {
int stripes = max_t(int,
- ((mddev->chunk_sectors << 9) / STRIPE_SIZE) * 4,
- ((mddev->new_chunk_sectors << 9) / STRIPE_SIZE) * 4);
+ ((mddev->chunk_sectors << 9) / conf->stripe_size) * 4,
+ ((mddev->new_chunk_sectors << 9) /
+ conf->stripe_size) * 4);
conf->min_nr_stripes = max(NR_STRIPES, stripes);
if (conf->min_nr_stripes != NR_STRIPES)
pr_info("md/raid:%s: force stripe size %d for reshape\n",
@@ -7801,14 +7846,14 @@ static int check_stripe_cache(struct mddev *mddev)
* stripe_heads first.
*/
struct r5conf *conf = mddev->private;
- if (((mddev->chunk_sectors << 9) / STRIPE_SIZE) * 4
+ if (((mddev->chunk_sectors << 9) / conf->stripe_size) * 4
> conf->min_nr_stripes ||
- ((mddev->new_chunk_sectors << 9) / STRIPE_SIZE) * 4
+ ((mddev->new_chunk_sectors << 9) / conf->stripe_size) * 4
> conf->min_nr_stripes) {
pr_warn("md/raid:%s: reshape: not enough stripes. Needed %lu\n",
mdname(mddev),
((max(mddev->chunk_sectors, mddev->new_chunk_sectors) << 9)
- / STRIPE_SIZE)*4);
+ / conf->stripe_size)*4);
return 0;
}
return 1;
@@ -8127,6 +8172,7 @@ static void *raid5_takeover_raid1(struct mddev *mddev)
{
int chunksect;
void *ret;
+ struct r5conf *conf = mddev->private;
if (mddev->raid_disks != 2 ||
mddev->degraded > 1)
@@ -8140,7 +8186,7 @@ static void *raid5_takeover_raid1(struct mddev *mddev)
while (chunksect && (mddev->array_sectors & (chunksect-1)))
chunksect >>= 1;
- if ((chunksect<<9) < STRIPE_SIZE)
+ if ((chunksect<<9) < conf->stripe_size)
/* array size does not allow a suitable chunk size */
return ERR_PTR(-EINVAL);
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index f90e0704bed9..0579497a6ff8 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -472,32 +472,12 @@ struct disk_info {
*/
#define NR_STRIPES 256
-#define STRIPE_SIZE PAGE_SIZE
-#define STRIPE_SHIFT (PAGE_SHIFT - 9)
-#define STRIPE_SECTORS (STRIPE_SIZE>>9)
#define IO_THRESHOLD 1
#define BYPASS_THRESHOLD 1
#define NR_HASH (PAGE_SIZE / sizeof(struct hlist_head))
#define HASH_MASK (NR_HASH - 1)
#define MAX_STRIPE_BATCH 8
-/* bio's attached to a stripe+device for I/O are linked together in bi_sector
- * order without overlap. There may be several bio's per stripe+device, and
- * a bio could span several devices.
- * When walking this list for a particular stripe+device, we must never proceed
- * beyond a bio that extends past this device, as the next bio might no longer
- * be valid.
- * This function is used to determine the 'next' bio in the list, given the
- * sector of the current stripe+device
- */
-static inline struct bio *r5_next_bio(struct bio *bio, sector_t sector)
-{
- if (bio_end_sector(bio) < sector + STRIPE_SECTORS)
- return bio->bi_next;
- else
- return NULL;
-}
-
/* NOTE NR_STRIPE_HASH_LOCKS must remain below 64.
* This is because we sometimes take all the spinlocks
* and creating that much locking depth can cause
@@ -574,6 +554,9 @@ struct r5conf {
int raid_disks;
int max_nr_stripes;
int min_nr_stripes;
+ unsigned long stripe_size;
+ unsigned int stripe_shift;
+ unsigned long stripe_sectors;
/* reshape_progress is the leading edge of a 'reshape'
* It has value MaxSector when no reshape is happening
@@ -752,6 +735,24 @@ static inline int algorithm_is_DDF(int layout)
return layout >= 8 && layout <= 10;
}
+/* bio's attached to a stripe+device for I/O are linked together in bi_sector
+ * order without overlap. There may be several bio's per stripe+device, and
+ * a bio could span several devices.
+ * When walking this list for a particular stripe+device, we must never proceed
+ * beyond a bio that extends past this device, as the next bio might no longer
+ * be valid.
+ * This function is used to determine the 'next' bio in the list, given the
+ * sector of the current stripe+device
+ */
+static inline struct bio *
+r5_next_bio(struct r5conf *conf, struct bio *bio, sector_t sector)
+{
+ if (bio_end_sector(bio) < sector + conf->stripe_sectors)
+ return bio->bi_next;
+ else
+ return NULL;
+}
+
extern void md_raid5_kick_device(struct r5conf *conf);
extern int raid5_set_cache_size(struct mddev *mddev, int size);
extern sector_t raid5_compute_blocknr(struct stripe_head *sh, int i, int previous);
--
2.25.4
^ permalink raw reply related [flat|nested] 19+ messages in thread* [PATCH v6 02/15] md/raid5: set default stripe_size as 4096
2020-07-15 12:42 [PATCH v6 00/15] md/raid5: set STRIPE_SIZE as a configurable value Yufen Yu
2020-07-15 12:42 ` [PATCH v6 01/15] md/raid456: convert macro STRIPE_* to members of struct r5conf Yufen Yu
@ 2020-07-15 12:42 ` Yufen Yu
2020-07-15 12:42 ` [PATCH v6 03/15] md/raid5: add a member of r5pages for struct stripe_head Yufen Yu
` (13 subsequent siblings)
15 siblings, 0 replies; 19+ messages in thread
From: Yufen Yu @ 2020-07-15 12:42 UTC (permalink / raw)
To: song; +Cc: linux-raid, neilb, guoqing.jiang, houtao1, yuyufen
In RAID5, if issued bio size is bigger than stripe_size, it will be split
in the unit of stripe_size and process them one by one. Even for size
less then stripe_size, RAID5 also request data from disk at least of
stripe_size.
Nowdays, stripe_size is equal to the value of PAGE_SIZE. Since filesystem
usually issue bio in the unit of 4KB, there is no problem for PAGE_SIZE as
4KB. But, for 64KB PAGE_SIZE, bio from filesystem requests 4KB data while
RAID5 issue IO at least stripe_size (64KB) each time. That will waste
resource of disk bandwidth and compute xor.
To avoding the waste, we want to make stripe_size configurable. This patch
just set default stripe_size as 4096. User can also set the value bigger
than 4KB for some special requirements, such as we know the issued io
size is more than 4KB.
To evaluate the new feature, we create raid5 device '/dev/md5' with
4 SSD disk and test it on arm64 machine with 64KB PAGE_SIZE.
1) We format /dev/md5 with mkfs.ext4 and mount ext4 with default
configure on /mnt directory. Then, trying to test it by dbench with
command: dbench -D /mnt -t 1000 10. Result show as:
'stripe_size = 64KB'
Operation Count AvgLat MaxLat
----------------------------------------
NTCreateX 9805011 0.021 64.728
Close 7202525 0.001 0.120
Rename 415213 0.051 44.681
Unlink 1980066 0.079 93.147
Deltree 240 1.793 6.516
Mkdir 120 0.004 0.007
Qpathinfo 8887512 0.007 37.114
Qfileinfo 1557262 0.001 0.030
Qfsinfo 1629582 0.012 0.152
Sfileinfo 798756 0.040 57.641
Find 3436004 0.019 57.782
WriteX 4887239 0.021 57.638
ReadX 15370483 0.005 37.818
LockX 31934 0.003 0.022
UnlockX 31933 0.001 0.021
Flush 687205 13.302 530.088
Throughput 307.799 MB/sec 10 clients 10 procs max_latency=530.091 ms
-------------------------------------------------------
'stripe_size = 4KB'
Operation Count AvgLat MaxLat
----------------------------------------
NTCreateX 11999166 0.021 36.380
Close 8814128 0.001 0.122
Rename 508113 0.051 29.169
Unlink 2423242 0.070 38.141
Deltree 300 1.885 7.155
Mkdir 150 0.004 0.006
Qpathinfo 10875921 0.007 35.485
Qfileinfo 1905837 0.001 0.032
Qfsinfo 1994304 0.012 0.125
Sfileinfo 977450 0.029 26.489
Find 4204952 0.019 9.361
WriteX 5981890 0.019 27.804
ReadX 18809742 0.004 33.491
LockX 39074 0.003 0.025
UnlockX 39074 0.001 0.014
Flush 841022 10.712 458.848
Throughput 376.777 MB/sec 10 clients 10 procs max_latency=458.852 ms
-------------------------------------------------------
It show that setting stripe_size as 4KB has higher thoughput, i.e.
(376.777 vs 307.799) and has smaller latency (530.091 vs 458.852)
than that setting as 64KB.
2) We try to evaluate IO throughput for /dev/md5 by fio with config:
[4KB randwrite]
direct=1
numjob=2
iodepth=64
ioengine=libaio
filename=/dev/md5
bs=4KB
rw=randwrite
[64KB write]
direct=1
numjob=2
iodepth=64
ioengine=libaio
filename=/dev/md5
bs=1MB
rw=write
The result as follow:
+ +
| stripe_size(64KB) | stripe_size(4KB)
+----------------------------------------------------+
4KB randwrite | 15MB/s | 100MB/s
+----------------------------------------------------+
1MB write | 1000MB/s | 700MB/s
The result show that when size of io is bigger than 4KB (64KB),
64KB stripe_size has much higher IOPS. But for 4KB randwrite, that
means, size of io issued to device are smaller, 4KB stripe_size
have better performance.
Normally, default value (4096) can get relatively good performance.
But if each issued io is bigger than 4096, setting value more than
4096 may get better performance.
Here, we just set default stripe_size as 4096, and we will try to support
setting different stripe_size by sysfs interface in the following patch.
Signed-off-by: Yufen Yu <yuyufen@huawei.com>
---
drivers/md/raid5.c | 6 +++---
drivers/md/raid5.h | 1 +
2 files changed, 4 insertions(+), 3 deletions(-)
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 7914da4e0092..0824fe7c3bec 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -6958,9 +6958,9 @@ static struct r5conf *setup_conf(struct mddev *mddev)
if (conf == NULL)
goto abort;
- conf->stripe_size = PAGE_SIZE;
- conf->stripe_shift = PAGE_SHIFT - 9;
- conf->stripe_sectors = conf->stripe_size >> 9;
+ conf->stripe_size = DEFAULT_STRIPE_SIZE;
+ conf->stripe_shift = ilog2(DEFAULT_STRIPE_SIZE) - 9;
+ conf->stripe_sectors = DEFAULT_STRIPE_SIZE >> 9;
INIT_LIST_HEAD(&conf->free_list);
INIT_LIST_HEAD(&conf->pending_list);
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 0579497a6ff8..5a79a657f162 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -477,6 +477,7 @@ struct disk_info {
#define NR_HASH (PAGE_SIZE / sizeof(struct hlist_head))
#define HASH_MASK (NR_HASH - 1)
#define MAX_STRIPE_BATCH 8
+#define DEFAULT_STRIPE_SIZE 4096
/* NOTE NR_STRIPE_HASH_LOCKS must remain below 64.
* This is because we sometimes take all the spinlocks
--
2.25.4
^ permalink raw reply related [flat|nested] 19+ messages in thread* [PATCH v6 03/15] md/raid5: add a member of r5pages for struct stripe_head
2020-07-15 12:42 [PATCH v6 00/15] md/raid5: set STRIPE_SIZE as a configurable value Yufen Yu
2020-07-15 12:42 ` [PATCH v6 01/15] md/raid456: convert macro STRIPE_* to members of struct r5conf Yufen Yu
2020-07-15 12:42 ` [PATCH v6 02/15] md/raid5: set default stripe_size as 4096 Yufen Yu
@ 2020-07-15 12:42 ` Yufen Yu
2020-07-15 12:42 ` [PATCH v6 04/15] md/raid5: allocate and free shared pages of r5pages Yufen Yu
` (12 subsequent siblings)
15 siblings, 0 replies; 19+ messages in thread
From: Yufen Yu @ 2020-07-15 12:42 UTC (permalink / raw)
To: song; +Cc: linux-raid, neilb, guoqing.jiang, houtao1, yuyufen
Since grow_buffers() uses alloc_page() to allocate the buffers for
each stripe_head(), means, it will allocate 64K buffers and just use
4K of them, after setting stripe_size as 4096.
To avoid wasting memory, we try to contain multiple 'page' of sh->dev
into one real page. That means, multiple sh->dev[i].page will point to
the only page with different offset. Example of 64K PAGE_SIZE and
4K stripe_size as following:
64K PAGE_SIZE
+---+---+---+---+------------------------------+
| | | | |
| | | | |
+-+-+-+-+-+-+-+-+------------------------------+
^ ^ ^ ^
| | | +----------------------------+
| | | |
| | +-------------------+ |
| | | |
| +----------+ | |
| | | |
+-+ | | |
| | | |
+-----+-----+------+-----+------+-----+------+------+
sh | offset(0) | offset(4K) | offset(8K) | offset(12K) |
+ +-----------+------------+------------+-------------+
+----> dev[0].page dev[1].page dev[2].page dev[3].page
After trying to share one page, the users of sh->dev[i].page need to
take care:
1) When issue bio into stripe_head, bi_io_vec.bv_page will point to
the page directly. So, we should make sure bv_offset to been set
with correct offset.
2) When compute xor, the page will be passed to computer function.
So, we also need to pass offset of that page to computer. Let it
compute correct location of each sh->dev[i].page.
This patch will add a new member of r5pages into stripe_head to manage
all pages needed by each sh->dev[i]. We also add 'offset' for each r5dev
so that users can get related page offset easily. And add helper function
to get page and it's index in r5pages array by disk index.
Signed-off-by: Yufen Yu <yuyufen@huawei.com>
---
drivers/md/raid5.h | 38 ++++++++++++++++++++++++++++++++++++++
1 file changed, 38 insertions(+)
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 5a79a657f162..ff03c0ac2995 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -246,6 +246,14 @@ struct stripe_head {
int target, target2;
enum sum_check_flags zero_sum_result;
} ops;
+
+ /* These pages will be used by bios in dev[i] */
+ struct r5pages {
+ struct page **page;
+ int size; /* page array size */
+ int stripes_per_page;
+ } pages;
+
struct r5dev {
/* rreq and rvec are used for the replacement device when
* writing data to both devices.
@@ -253,6 +261,7 @@ struct stripe_head {
struct bio req, rreq;
struct bio_vec vec, rvec;
struct page *page, *orig_page;
+ unsigned int offset; /* offset of this page */
struct bio *toread, *read, *towrite, *written;
sector_t sector; /* sector of this page */
unsigned long flags;
@@ -754,6 +763,35 @@ r5_next_bio(struct r5conf *conf, struct bio *bio, sector_t sector)
return NULL;
}
+/*
+ * Return offset of the corresponding page for r5dev.
+ */
+static inline int raid5_get_page_offset(struct stripe_head *sh, int disk_idx)
+{
+ struct r5conf *conf = sh->raid_conf;
+
+ return (disk_idx % sh->pages.stripes_per_page) * conf->stripe_size;
+}
+
+/*
+ * Return corresponding page address for r5dev.
+ */
+static inline struct page *
+raid5_get_dev_page(struct stripe_head *sh, int disk_idx)
+{
+ return sh->pages.page[disk_idx / sh->pages.stripes_per_page];
+}
+
+/*
+ * We want to let multiple buffers to share one real page for
+ * stripe_head when PAGE_SIZE is biggger than stripe_size. If
+ * they are equal, no need to use this strategy.
+ */
+static inline int raid5_stripe_pages_shared(struct r5conf *conf)
+{
+ return conf->stripe_size < PAGE_SIZE;
+}
+
extern void md_raid5_kick_device(struct r5conf *conf);
extern int raid5_set_cache_size(struct mddev *mddev, int size);
extern sector_t raid5_compute_blocknr(struct stripe_head *sh, int i, int previous);
--
2.25.4
^ permalink raw reply related [flat|nested] 19+ messages in thread* [PATCH v6 04/15] md/raid5: allocate and free shared pages of r5pages
2020-07-15 12:42 [PATCH v6 00/15] md/raid5: set STRIPE_SIZE as a configurable value Yufen Yu
` (2 preceding siblings ...)
2020-07-15 12:42 ` [PATCH v6 03/15] md/raid5: add a member of r5pages for struct stripe_head Yufen Yu
@ 2020-07-15 12:42 ` Yufen Yu
2020-07-15 12:42 ` [PATCH v6 05/15] md/raid5: set correct page offset for bi_io_vec in ops_run_io() Yufen Yu
` (11 subsequent siblings)
15 siblings, 0 replies; 19+ messages in thread
From: Yufen Yu @ 2020-07-15 12:42 UTC (permalink / raw)
To: song; +Cc: linux-raid, neilb, guoqing.jiang, houtao1, yuyufen
When PAGE_SIZE is bigger than stripe_size, try to allocate pages of
r5pages in grow_buffres() and free these pages in shrink_buffers().
Then, set sh->dev[i].page and sh->dev[i].offset as the page in
array. Without enable shared page, we just set offset as value of '0'.
Signed-off-by: Yufen Yu <yuyufen@huawei.com>
---
drivers/md/raid5.c | 112 ++++++++++++++++++++++++++++++++++++++++++---
1 file changed, 105 insertions(+), 7 deletions(-)
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 0824fe7c3bec..17f42203b0ae 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -448,15 +448,72 @@ static struct stripe_head *get_free_stripe(struct r5conf *conf, int hash)
return sh;
}
+/*
+ * Try to free all pages in r5pages array.
+ */
+static void free_stripe_pages(struct stripe_head *sh)
+{
+ int i;
+ struct page *p;
+
+ /* Have not allocate page pool */
+ if (!sh->pages.page)
+ return;
+
+ for (i = 0; i < sh->pages.size; i++) {
+ p = sh->pages.page[i];
+ if (p)
+ put_page(p);
+ sh->pages.page[i] = NULL;
+ }
+}
+
+/*
+ * Allocate pages for r5pages.
+ */
+static int alloc_stripe_pages(struct stripe_head *sh, gfp_t gfp)
+{
+ int i;
+ struct page *p;
+
+ for (i = 0; i < sh->pages.size; i++) {
+ /* The page have allocated. */
+ if (sh->pages.page[i])
+ continue;
+
+ p = alloc_page(gfp);
+ if (!p) {
+ free_stripe_pages(sh);
+ return -ENOMEM;
+ }
+ sh->pages.page[i] = p;
+ }
+ return 0;
+}
+
static void shrink_buffers(struct stripe_head *sh)
{
struct page *p;
int i;
int num = sh->raid_conf->pool_size;
- for (i = 0; i < num ; i++) {
+ if (raid5_stripe_pages_shared(sh->raid_conf))
+ free_stripe_pages(sh); /* Free pages in r5pages */
+
+ for (i = 0; i < num; i++) {
WARN_ON(sh->dev[i].page != sh->dev[i].orig_page);
p = sh->dev[i].page;
+
+ /*
+ * If we use pages in r5pages, these pages have been
+ * freed in free_stripe_pages().
+ */
+ if (raid5_stripe_pages_shared(sh->raid_conf)) {
+ if (p)
+ sh->dev[i].page = NULL;
+ continue;
+ }
+
if (!p)
continue;
sh->dev[i].page = NULL;
@@ -469,14 +526,26 @@ static int grow_buffers(struct stripe_head *sh, gfp_t gfp)
int i;
int num = sh->raid_conf->pool_size;
+ if (raid5_stripe_pages_shared(sh->raid_conf) &&
+ alloc_stripe_pages(sh, gfp))
+ return -ENOMEM;
+
for (i = 0; i < num; i++) {
struct page *page;
+ unsigned int offset;
- if (!(page = alloc_page(gfp))) {
- return 1;
+ if (raid5_stripe_pages_shared(sh->raid_conf)) {
+ page = raid5_get_dev_page(sh, i);
+ offset = raid5_get_page_offset(sh, i);
+ } else {
+ page = alloc_page(gfp);
+ if (!page)
+ return -ENOMEM;
+ offset = 0;
}
sh->dev[i].page = page;
sh->dev[i].orig_page = page;
+ sh->dev[i].offset = offset;
}
return 0;
@@ -2146,11 +2215,34 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
static void free_stripe(struct kmem_cache *sc, struct stripe_head *sh)
{
+ kfree(sh->pages.page);
+
if (sh->ppl_page)
__free_page(sh->ppl_page);
kmem_cache_free(sc, sh);
}
+static int
+init_stripe_shared_pages(struct stripe_head *sh, struct r5conf *conf)
+{
+ int nr_pages, cnt;
+
+ if (!raid5_stripe_pages_shared(conf) || sh->pages.page)
+ return 0;
+
+ /* Each of the sh->dev[i] need one conf->stripe_size */
+ cnt = PAGE_SIZE / conf->stripe_size;
+ nr_pages = (conf->raid_disks + cnt - 1) / cnt;
+
+ sh->pages.page = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL);
+ if (!sh->pages.page)
+ return -ENOMEM;
+ sh->pages.size = nr_pages;
+ sh->pages.stripes_per_page = cnt;
+
+ return 0;
+}
+
static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp,
int disks, struct r5conf *conf)
{
@@ -2177,14 +2269,20 @@ static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp,
if (raid5_has_ppl(conf)) {
sh->ppl_page = alloc_page(gfp);
- if (!sh->ppl_page) {
- free_stripe(sc, sh);
- sh = NULL;
- }
+ if (!sh->ppl_page)
+ goto fail;
}
+
+ if (init_stripe_shared_pages(sh, conf))
+ goto fail;
}
return sh;
+
+fail:
+ free_stripe(sc, sh);
+ return NULL;
}
+
static int grow_one_stripe(struct r5conf *conf, gfp_t gfp)
{
struct stripe_head *sh;
--
2.25.4
^ permalink raw reply related [flat|nested] 19+ messages in thread* [PATCH v6 05/15] md/raid5: set correct page offset for bi_io_vec in ops_run_io()
2020-07-15 12:42 [PATCH v6 00/15] md/raid5: set STRIPE_SIZE as a configurable value Yufen Yu
` (3 preceding siblings ...)
2020-07-15 12:42 ` [PATCH v6 04/15] md/raid5: allocate and free shared pages of r5pages Yufen Yu
@ 2020-07-15 12:42 ` Yufen Yu
2020-07-15 12:42 ` [PATCH v6 06/15] md/raid5: set correct page offset for async_copy_data() Yufen Yu
` (10 subsequent siblings)
15 siblings, 0 replies; 19+ messages in thread
From: Yufen Yu @ 2020-07-15 12:42 UTC (permalink / raw)
To: song; +Cc: linux-raid, neilb, guoqing.jiang, houtao1, yuyufen
After using r5pages for each sh->dev[i], we need to set correct offset
of that page for bi_io_vec when issue bio. The value of offset is zero
without using r5pages.
Signed-off-by: Yufen Yu <yuyufen@huawei.com>
---
drivers/md/raid5.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 17f42203b0ae..96efb4ad8835 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1200,7 +1200,7 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
sh->dev[i].vec.bv_page = sh->dev[i].page;
bi->bi_vcnt = 1;
bi->bi_io_vec[0].bv_len = conf->stripe_size;
- bi->bi_io_vec[0].bv_offset = 0;
+ bi->bi_io_vec[0].bv_offset = sh->dev[i].offset;
bi->bi_iter.bi_size = conf->stripe_size;
bi->bi_write_hint = sh->dev[i].write_hint;
if (!rrdev)
@@ -1254,7 +1254,7 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
sh->dev[i].rvec.bv_page = sh->dev[i].page;
rbi->bi_vcnt = 1;
rbi->bi_io_vec[0].bv_len = conf->stripe_size;
- rbi->bi_io_vec[0].bv_offset = 0;
+ rbi->bi_io_vec[0].bv_offset = sh->dev[i].offset;
rbi->bi_iter.bi_size = conf->stripe_size;
rbi->bi_write_hint = sh->dev[i].write_hint;
sh->dev[i].write_hint = RWH_WRITE_LIFE_NOT_SET;
--
2.25.4
^ permalink raw reply related [flat|nested] 19+ messages in thread* [PATCH v6 06/15] md/raid5: set correct page offset for async_copy_data()
2020-07-15 12:42 [PATCH v6 00/15] md/raid5: set STRIPE_SIZE as a configurable value Yufen Yu
` (4 preceding siblings ...)
2020-07-15 12:42 ` [PATCH v6 05/15] md/raid5: set correct page offset for bi_io_vec in ops_run_io() Yufen Yu
@ 2020-07-15 12:42 ` Yufen Yu
2020-07-15 12:42 ` [PATCH v6 07/15] md/raid5: resize stripes and set correct offset when reshape array Yufen Yu
` (9 subsequent siblings)
15 siblings, 0 replies; 19+ messages in thread
From: Yufen Yu @ 2020-07-15 12:42 UTC (permalink / raw)
To: song; +Cc: linux-raid, neilb, guoqing.jiang, houtao1, yuyufen
ops_run_biofill() and ops_run_biodrain() will call async_copy_data()
to copy sh->dev[i].page from or to bio. It also need to set correct
page offset for dev->page when use r5pages.
Without modifying original code logic, we replace 'page_offset' with
'page_offset + poff' simplify. In case of that wihtout using r5pages,
poff is zero.
Signed-off-by: Yufen Yu <yuyufen@huawei.com>
---
drivers/md/raid5.c | 14 +++++++++-----
1 file changed, 9 insertions(+), 5 deletions(-)
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 96efb4ad8835..6f13ac9502a5 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1296,7 +1296,7 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
static struct dma_async_tx_descriptor *
async_copy_data(int frombio, struct bio *bio, struct page **page,
- sector_t sector, struct dma_async_tx_descriptor *tx,
+ unsigned int poff, sector_t sector, struct dma_async_tx_descriptor *tx,
struct stripe_head *sh, int no_skipcopy)
{
struct bio_vec bvl;
@@ -1342,11 +1342,13 @@ async_copy_data(int frombio, struct bio *bio, struct page **page,
!no_skipcopy)
*page = bio_page;
else
- tx = async_memcpy(*page, bio_page, page_offset,
- b_offset, clen, &submit);
+ tx = async_memcpy(*page, bio_page,
+ page_offset + poff, b_offset,
+ clen, &submit);
} else
tx = async_memcpy(bio_page, *page, b_offset,
- page_offset, clen, &submit);
+ page_offset + poff,
+ clen, &submit);
}
/* chain the operations */
submit.depend_tx = tx;
@@ -1418,7 +1420,8 @@ static void ops_run_biofill(struct stripe_head *sh)
while (rbi && rbi->bi_iter.bi_sector <
dev->sector + sh->raid_conf->stripe_sectors) {
tx = async_copy_data(0, rbi, &dev->page,
- dev->sector, tx, sh, 0);
+ dev->offset,
+ dev->sector, tx, sh, 0);
rbi = r5_next_bio(sh->raid_conf, rbi,
dev->sector);
}
@@ -1846,6 +1849,7 @@ ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
set_bit(R5_Discard, &dev->flags);
else {
tx = async_copy_data(1, wbi, &dev->page,
+ dev->offset,
dev->sector, tx, sh,
r5c_is_writeback(conf->log));
if (dev->page != dev->orig_page &&
--
2.25.4
^ permalink raw reply related [flat|nested] 19+ messages in thread* [PATCH v6 07/15] md/raid5: resize stripes and set correct offset when reshape array
2020-07-15 12:42 [PATCH v6 00/15] md/raid5: set STRIPE_SIZE as a configurable value Yufen Yu
` (5 preceding siblings ...)
2020-07-15 12:42 ` [PATCH v6 06/15] md/raid5: set correct page offset for async_copy_data() Yufen Yu
@ 2020-07-15 12:42 ` Yufen Yu
2020-07-15 12:42 ` [PATCH v6 08/15] md/raid5: add new xor function to support different page offset Yufen Yu
` (8 subsequent siblings)
15 siblings, 0 replies; 19+ messages in thread
From: Yufen Yu @ 2020-07-15 12:42 UTC (permalink / raw)
To: song; +Cc: linux-raid, neilb, guoqing.jiang, houtao1, yuyufen
When reshape array, we try to reuse shared pages of old stripe_head,
and allocate more for the new one if needed. At the same time, set
correct offset when call handle_stripe_expansion().
By the way, we call resize_stripes() only when grow raid array disks,
so that don't worry about memleak for old r5pages.
Signed-off-by: Yufen Yu <yuyufen@huawei.com>
---
drivers/md/raid5.c | 50 +++++++++++++++++++++++++++++++++++++++-------
1 file changed, 43 insertions(+), 7 deletions(-)
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 6f13ac9502a5..2702a1cb2281 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2492,10 +2492,20 @@ static int resize_stripes(struct r5conf *conf, int newsize)
osh = get_free_stripe(conf, hash);
unlock_device_hash_lock(conf, hash);
- for(i=0; i<conf->pool_size; i++) {
+ if (raid5_stripe_pages_shared(conf)) {
+ /* We reuse pages in r5pages of old stripe head */
+ for (i = 0; i < osh->pages.size; i++) {
+ nsh->pages.page[i] = osh->pages.page[i];
+ osh->pages.page[i] = NULL;
+ }
+ }
+
+ for (i = 0; i < conf->pool_size; i++) {
nsh->dev[i].page = osh->dev[i].page;
nsh->dev[i].orig_page = osh->dev[i].page;
+ nsh->dev[i].offset = osh->dev[i].offset;
}
+
nsh->hash_lock_index = hash;
free_stripe(conf->slab_cache, osh);
cnt++;
@@ -2542,17 +2552,41 @@ static int resize_stripes(struct r5conf *conf, int newsize)
/* Step 4, return new stripes to service */
while(!list_empty(&newstripes)) {
+ struct page *p;
+ unsigned int offset;
nsh = list_entry(newstripes.next, struct stripe_head, lru);
list_del_init(&nsh->lru);
- for (i=conf->raid_disks; i < newsize; i++)
- if (nsh->dev[i].page == NULL) {
- struct page *p = alloc_page(GFP_NOIO);
- nsh->dev[i].page = p;
- nsh->dev[i].orig_page = p;
+ /* allocate shared pages it needed for new stripe_head */
+ if (raid5_stripe_pages_shared(conf)) {
+ for (i = 0; i < nsh->pages.size; i++) {
+ if (nsh->pages.page[i] == NULL) {
+ p = alloc_page(GFP_NOIO);
+ if (!p)
+ err = -ENOMEM;
+ nsh->pages.page[i] = p;
+ }
+ }
+ }
+
+ for (i = conf->raid_disks; i < newsize; i++) {
+ if (nsh->dev[i].page)
+ continue;
+
+ if (raid5_stripe_pages_shared(conf)) {
+ p = raid5_get_dev_page(nsh, i);
+ offset = raid5_get_page_offset(nsh, i);
+ } else {
+ p = alloc_page(GFP_NOIO);
if (!p)
err = -ENOMEM;
+ offset = 0;
}
+
+ nsh->dev[i].page = p;
+ nsh->dev[i].orig_page = p;
+ nsh->dev[i].offset = offset;
+ }
raid5_release_stripe(nsh);
}
/* critical section pass, GFP_NOIO no longer needed */
@@ -4475,7 +4509,9 @@ static void handle_stripe_expansion(struct r5conf *conf, struct stripe_head *sh)
/* place all the copies on one channel */
init_async_submit(&submit, 0, tx, NULL, NULL, NULL);
tx = async_memcpy(sh2->dev[dd_idx].page,
- sh->dev[i].page, 0, 0,
+ sh->dev[i].page,
+ sh2->dev[dd_idx].offset,
+ sh->dev[i].offset,
conf->stripe_size,
&submit);
--
2.25.4
^ permalink raw reply related [flat|nested] 19+ messages in thread* [PATCH v6 08/15] md/raid5: add new xor function to support different page offset
2020-07-15 12:42 [PATCH v6 00/15] md/raid5: set STRIPE_SIZE as a configurable value Yufen Yu
` (6 preceding siblings ...)
2020-07-15 12:42 ` [PATCH v6 07/15] md/raid5: resize stripes and set correct offset when reshape array Yufen Yu
@ 2020-07-15 12:42 ` Yufen Yu
2020-07-15 12:42 ` [PATCH v6 09/15] md/raid5: add offset array in scribble buffer Yufen Yu
` (7 subsequent siblings)
15 siblings, 0 replies; 19+ messages in thread
From: Yufen Yu @ 2020-07-15 12:42 UTC (permalink / raw)
To: song; +Cc: linux-raid, neilb, guoqing.jiang, houtao1, yuyufen
RAID5 will call async_xor() and async_xor_val() to compute xor.
However, both of them require common src/dst page offset. After
introducing shared pages of r5pages, we want these xor computer
function to support different src/dst page offset.
Here, we add two new functions async_xor_offsets() and
async_xor_val_offsets() respectively for async_xor() and async_xor_val().
Signed-off-by: Yufen Yu <yuyufen@huawei.com>
---
crypto/async_tx/async_xor.c | 120 +++++++++++++++++++++++++++++++-----
include/linux/async_tx.h | 11 ++++
2 files changed, 114 insertions(+), 17 deletions(-)
diff --git a/crypto/async_tx/async_xor.c b/crypto/async_tx/async_xor.c
index 4e5eebe52e6a..f5666ac84d34 100644
--- a/crypto/async_tx/async_xor.c
+++ b/crypto/async_tx/async_xor.c
@@ -97,7 +97,8 @@ do_async_xor(struct dma_chan *chan, struct dmaengine_unmap_data *unmap,
}
static void
-do_sync_xor(struct page *dest, struct page **src_list, unsigned int offset,
+do_sync_xor_offsets(struct page *dest, unsigned int offset,
+ struct page **src_list, unsigned int *src_offset,
int src_cnt, size_t len, struct async_submit_ctl *submit)
{
int i;
@@ -114,7 +115,8 @@ do_sync_xor(struct page *dest, struct page **src_list, unsigned int offset,
/* convert to buffer pointers */
for (i = 0; i < src_cnt; i++)
if (src_list[i])
- srcs[xor_src_cnt++] = page_address(src_list[i]) + offset;
+ srcs[xor_src_cnt++] = page_address(src_list[i]) +
+ (src_offset ? src_offset[i] : offset);
src_cnt = xor_src_cnt;
/* set destination address */
dest_buf = page_address(dest) + offset;
@@ -135,11 +137,31 @@ do_sync_xor(struct page *dest, struct page **src_list, unsigned int offset,
async_tx_sync_epilog(submit);
}
+static inline bool
+dma_xor_aligned_offsets(struct dma_device *device, unsigned int offset,
+ unsigned int *src_offset, int src_cnt, int len)
+{
+ int i;
+
+ if (!is_dma_xor_aligned(device, offset, 0, len))
+ return false;
+
+ if (!src_offset)
+ return true;
+
+ for (i = 0; i < src_cnt; i++) {
+ if (!is_dma_xor_aligned(device, src_offset[i], 0, len))
+ return false;
+ }
+ return true;
+}
+
/**
- * async_xor - attempt to xor a set of blocks with a dma engine.
+ * async_xor_offsets - attempt to xor a set of blocks with a dma engine.
* @dest: destination page
+ * @offset: dst offset to start transaction
* @src_list: array of source pages
- * @offset: common src/dst offset to start transaction
+ * @src_offset: array of source pages offset, NULL means common src/dst offset
* @src_cnt: number of source pages
* @len: length in bytes
* @submit: submission / completion modifiers
@@ -157,8 +179,9 @@ do_sync_xor(struct page *dest, struct page **src_list, unsigned int offset,
* is not specified.
*/
struct dma_async_tx_descriptor *
-async_xor(struct page *dest, struct page **src_list, unsigned int offset,
- int src_cnt, size_t len, struct async_submit_ctl *submit)
+async_xor_offsets(struct page *dest, unsigned int offset,
+ struct page **src_list, unsigned int *src_offset,
+ int src_cnt, size_t len, struct async_submit_ctl *submit)
{
struct dma_chan *chan = async_tx_find_channel(submit, DMA_XOR,
&dest, 1, src_list,
@@ -171,7 +194,8 @@ async_xor(struct page *dest, struct page **src_list, unsigned int offset,
if (device)
unmap = dmaengine_get_unmap_data(device->dev, src_cnt+1, GFP_NOWAIT);
- if (unmap && is_dma_xor_aligned(device, offset, 0, len)) {
+ if (unmap && dma_xor_aligned_offsets(device, offset,
+ src_offset, src_cnt, len)) {
struct dma_async_tx_descriptor *tx;
int i, j;
@@ -184,7 +208,8 @@ async_xor(struct page *dest, struct page **src_list, unsigned int offset,
continue;
unmap->to_cnt++;
unmap->addr[j++] = dma_map_page(device->dev, src_list[i],
- offset, len, DMA_TO_DEVICE);
+ src_offset ? src_offset[i] : offset,
+ len, DMA_TO_DEVICE);
}
/* map it bidirectional as it may be re-used as a source */
@@ -213,11 +238,42 @@ async_xor(struct page *dest, struct page **src_list, unsigned int offset,
/* wait for any prerequisite operations */
async_tx_quiesce(&submit->depend_tx);
- do_sync_xor(dest, src_list, offset, src_cnt, len, submit);
+ do_sync_xor_offsets(dest, offset, src_list, src_offset,
+ src_cnt, len, submit);
return NULL;
}
}
+EXPORT_SYMBOL_GPL(async_xor_offsets);
+
+/**
+ * async_xor - attempt to xor a set of blocks with a dma engine.
+ * @dest: destination page
+ * @src_list: array of source pages
+ * @offset: common src/dst offset to start transaction
+ * @src_cnt: number of source pages
+ * @len: length in bytes
+ * @submit: submission / completion modifiers
+ *
+ * honored flags: ASYNC_TX_ACK, ASYNC_TX_XOR_ZERO_DST, ASYNC_TX_XOR_DROP_DST
+ *
+ * xor_blocks always uses the dest as a source so the
+ * ASYNC_TX_XOR_ZERO_DST flag must be set to not include dest data in
+ * the calculation. The assumption with dma eninges is that they only
+ * use the destination buffer as a source when it is explicity specified
+ * in the source list.
+ *
+ * src_list note: if the dest is also a source it must be at index zero.
+ * The contents of this array will be overwritten if a scribble region
+ * is not specified.
+ */
+struct dma_async_tx_descriptor *
+async_xor(struct page *dest, struct page **src_list, unsigned int offset,
+ int src_cnt, size_t len, struct async_submit_ctl *submit)
+{
+ return async_xor_offsets(dest, offset, src_list, NULL,
+ src_cnt, len, submit);
+}
EXPORT_SYMBOL_GPL(async_xor);
static int page_is_zero(struct page *p, unsigned int offset, size_t len)
@@ -237,10 +293,11 @@ xor_val_chan(struct async_submit_ctl *submit, struct page *dest,
}
/**
- * async_xor_val - attempt a xor parity check with a dma engine.
+ * async_xor_val_offsets - attempt a xor parity check with a dma engine.
* @dest: destination page used if the xor is performed synchronously
+ * @offset: des offset in pages to start transaction
* @src_list: array of source pages
- * @offset: offset in pages to start transaction
+ * @src_offset: array of source pages offset, NULL means common src/det offset
* @src_cnt: number of source pages
* @len: length in bytes
* @result: 0 if sum == 0 else non-zero
@@ -253,9 +310,10 @@ xor_val_chan(struct async_submit_ctl *submit, struct page *dest,
* is not specified.
*/
struct dma_async_tx_descriptor *
-async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
- int src_cnt, size_t len, enum sum_check_flags *result,
- struct async_submit_ctl *submit)
+async_xor_val_offsets(struct page *dest, unsigned int offset,
+ struct page **src_list, unsigned int *src_offset,
+ int src_cnt, size_t len, enum sum_check_flags *result,
+ struct async_submit_ctl *submit)
{
struct dma_chan *chan = xor_val_chan(submit, dest, src_list, src_cnt, len);
struct dma_device *device = chan ? chan->device : NULL;
@@ -268,7 +326,7 @@ async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
unmap = dmaengine_get_unmap_data(device->dev, src_cnt, GFP_NOWAIT);
if (unmap && src_cnt <= device->max_xor &&
- is_dma_xor_aligned(device, offset, 0, len)) {
+ dma_xor_aligned_offsets(device, offset, src_offset, src_cnt, len)) {
unsigned long dma_prep_flags = 0;
int i;
@@ -281,7 +339,8 @@ async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
for (i = 0; i < src_cnt; i++) {
unmap->addr[i] = dma_map_page(device->dev, src_list[i],
- offset, len, DMA_TO_DEVICE);
+ src_offset ? src_offset[i] : offset,
+ len, DMA_TO_DEVICE);
unmap->to_cnt++;
}
unmap->len = len;
@@ -312,7 +371,8 @@ async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
submit->flags |= ASYNC_TX_XOR_DROP_DST;
submit->flags &= ~ASYNC_TX_ACK;
- tx = async_xor(dest, src_list, offset, src_cnt, len, submit);
+ tx = async_xor_offsets(dest, offset, src_list, src_offset,
+ src_cnt, len, submit);
async_tx_quiesce(&tx);
@@ -325,6 +385,32 @@ async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
return tx;
}
+EXPORT_SYMBOL_GPL(async_xor_val_offsets);
+
+/**
+ * async_xor_val - attempt a xor parity check with a dma engine.
+ * @dest: destination page used if the xor is performed synchronously
+ * @src_list: array of source pages
+ * @offset: offset in pages to start transaction
+ * @src_cnt: number of source pages
+ * @len: length in bytes
+ * @result: 0 if sum == 0 else non-zero
+ * @submit: submission / completion modifiers
+ *
+ * honored flags: ASYNC_TX_ACK
+ *
+ * src_list note: if the dest is also a source it must be at index zero.
+ * The contents of this array will be overwritten if a scribble region
+ * is not specified.
+ */
+struct dma_async_tx_descriptor *
+async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
+ int src_cnt, size_t len, enum sum_check_flags *result,
+ struct async_submit_ctl *submit)
+{
+ return async_xor_val_offsets(dest, offset, src_list, NULL, src_cnt,
+ len, result, submit);
+}
EXPORT_SYMBOL_GPL(async_xor_val);
MODULE_AUTHOR("Intel Corporation");
diff --git a/include/linux/async_tx.h b/include/linux/async_tx.h
index 75e582b8d2d9..8d79e2de06bd 100644
--- a/include/linux/async_tx.h
+++ b/include/linux/async_tx.h
@@ -162,11 +162,22 @@ struct dma_async_tx_descriptor *
async_xor(struct page *dest, struct page **src_list, unsigned int offset,
int src_cnt, size_t len, struct async_submit_ctl *submit);
+struct dma_async_tx_descriptor *
+async_xor_offsets(struct page *dest, unsigned int offset,
+ struct page **src_list, unsigned int *src_offset,
+ int src_cnt, size_t len, struct async_submit_ctl *submit);
+
struct dma_async_tx_descriptor *
async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
int src_cnt, size_t len, enum sum_check_flags *result,
struct async_submit_ctl *submit);
+struct dma_async_tx_descriptor *
+async_xor_val_offsets(struct page *dest, unsigned int offset,
+ struct page **src_list, unsigned int *src_offset,
+ int src_cnt, size_t len, enum sum_check_flags *result,
+ struct async_submit_ctl *submit);
+
struct dma_async_tx_descriptor *
async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset,
unsigned int src_offset, size_t len,
--
2.25.4
^ permalink raw reply related [flat|nested] 19+ messages in thread* [PATCH v6 09/15] md/raid5: add offset array in scribble buffer
2020-07-15 12:42 [PATCH v6 00/15] md/raid5: set STRIPE_SIZE as a configurable value Yufen Yu
` (7 preceding siblings ...)
2020-07-15 12:42 ` [PATCH v6 08/15] md/raid5: add new xor function to support different page offset Yufen Yu
@ 2020-07-15 12:42 ` Yufen Yu
2020-07-15 12:42 ` [PATCH v6 10/15] md/raid5: compute xor with correct page offset Yufen Yu
` (6 subsequent siblings)
15 siblings, 0 replies; 19+ messages in thread
From: Yufen Yu @ 2020-07-15 12:42 UTC (permalink / raw)
To: song; +Cc: linux-raid, neilb, guoqing.jiang, houtao1, yuyufen
When enable shared buffers for stripe_head, it need an offset
array to record page offset to compute xor. To avoid repeatly allocate
an new array each time, we add a memory region into scribble buffer
to record offset.
Signed-off-by: Yufen Yu <yuyufen@huawei.com>
---
drivers/md/raid5.c | 14 ++++++++++++--
1 file changed, 12 insertions(+), 2 deletions(-)
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 2702a1cb2281..b5a00f64db5c 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1477,6 +1477,15 @@ static addr_conv_t *to_addr_conv(struct stripe_head *sh,
return (void *) (to_addr_page(percpu, i) + sh->disks + 2);
}
+/*
+ * Return a pointer to record offset address.
+ */
+static unsigned int *
+to_addr_offs(struct stripe_head *sh, struct raid5_percpu *percpu)
+{
+ return (unsigned int *) (to_addr_conv(sh, percpu, 0) + sh->disks + 2);
+}
+
static struct dma_async_tx_descriptor *
ops_run_compute5(struct stripe_head *sh, struct raid5_percpu *percpu)
{
@@ -2359,8 +2368,9 @@ static int scribble_alloc(struct raid5_percpu *percpu,
int num, int cnt)
{
size_t obj_size =
- sizeof(struct page *) * (num+2) +
- sizeof(addr_conv_t) * (num+2);
+ sizeof(struct page *) * (num + 2) +
+ sizeof(addr_conv_t) * (num + 2) +
+ sizeof(unsigned int) * (num + 2);
void *scribble;
/*
--
2.25.4
^ permalink raw reply related [flat|nested] 19+ messages in thread* [PATCH v6 10/15] md/raid5: compute xor with correct page offset
2020-07-15 12:42 [PATCH v6 00/15] md/raid5: set STRIPE_SIZE as a configurable value Yufen Yu
` (8 preceding siblings ...)
2020-07-15 12:42 ` [PATCH v6 09/15] md/raid5: add offset array in scribble buffer Yufen Yu
@ 2020-07-15 12:42 ` Yufen Yu
2020-07-15 12:42 ` [PATCH v6 11/15] md/raid5: support config stripe_size by sysfs entry Yufen Yu
` (5 subsequent siblings)
15 siblings, 0 replies; 19+ messages in thread
From: Yufen Yu @ 2020-07-15 12:42 UTC (permalink / raw)
To: song; +Cc: linux-raid, neilb, guoqing.jiang, houtao1, yuyufen
When compute xor, the pages address will be passed to computer function.
After trying to use pages in r5pages, we also need to pass page offset
to let it know correct location of each page.
For now raid5-cache and raid5-ppl are supported only when PAGE_SIZE is
equal to 4096. In that case, shared pages will not be supported and
dev->offset is '0'. So, we can use that value directly.
Signed-off-by: Yufen Yu <yuyufen@huawei.com>
---
drivers/md/raid5.c | 67 ++++++++++++++++++++++++++++++++++------------
1 file changed, 50 insertions(+), 17 deletions(-)
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index b5a00f64db5c..84c35eb225b4 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1491,6 +1491,7 @@ ops_run_compute5(struct stripe_head *sh, struct raid5_percpu *percpu)
{
int disks = sh->disks;
struct page **xor_srcs = to_addr_page(percpu, 0);
+ unsigned int *offs = to_addr_offs(sh, percpu);
int target = sh->ops.target;
struct r5dev *tgt = &sh->dev[target];
struct page *xor_dest = tgt->page;
@@ -1499,6 +1500,7 @@ ops_run_compute5(struct stripe_head *sh, struct raid5_percpu *percpu)
struct async_submit_ctl submit;
int i;
struct r5conf *conf = sh->raid_conf;
+ unsigned int des_offset = tgt->offset;
BUG_ON(sh->batch_head);
@@ -1506,20 +1508,23 @@ ops_run_compute5(struct stripe_head *sh, struct raid5_percpu *percpu)
__func__, (unsigned long long)sh->sector, target);
BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags));
- for (i = disks; i--; )
- if (i != target)
+ for (i = disks; i--; ) {
+ if (i != target) {
+ offs[count] = sh->dev[i].offset;
xor_srcs[count++] = sh->dev[i].page;
+ }
+ }
atomic_inc(&sh->count);
init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST, NULL,
ops_complete_compute, sh, to_addr_conv(sh, percpu, 0));
if (unlikely(count == 1))
- tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0,
+ tx = async_memcpy(xor_dest, xor_srcs[0], des_offset, offs[0],
conf->stripe_size, &submit);
else
- tx = async_xor(xor_dest, xor_srcs, 0, count,
- conf->stripe_size, &submit);
+ tx = async_xor_offsets(xor_dest, des_offset, xor_srcs, offs,
+ count, conf->stripe_size, &submit);
return tx;
}
@@ -1763,11 +1768,13 @@ ops_run_prexor5(struct stripe_head *sh, struct raid5_percpu *percpu,
{
int disks = sh->disks;
struct page **xor_srcs = to_addr_page(percpu, 0);
+ unsigned int *offs = to_addr_offs(sh, percpu);
int count = 0, pd_idx = sh->pd_idx, i;
struct async_submit_ctl submit;
struct r5conf *conf = sh->raid_conf;
/* existing parity data subtracted */
+ unsigned int des_offset = offs[count] = sh->dev[pd_idx].offset;
struct page *xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page;
BUG_ON(sh->batch_head);
@@ -1777,16 +1784,23 @@ ops_run_prexor5(struct stripe_head *sh, struct raid5_percpu *percpu,
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
/* Only process blocks that are known to be uptodate */
- if (test_bit(R5_InJournal, &dev->flags))
+ if (test_bit(R5_InJournal, &dev->flags)) {
+ /*
+ * For this case, PAGE_SIZE must be 4KB and will not
+ * use r5pages. So dev->offset is zero.
+ */
+ offs[count] = dev->offset;
xor_srcs[count++] = dev->orig_page;
- else if (test_bit(R5_Wantdrain, &dev->flags))
+ } else if (test_bit(R5_Wantdrain, &dev->flags)) {
+ offs[count] = dev->offset;
xor_srcs[count++] = dev->page;
+ }
}
init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
ops_complete_prexor, sh, to_addr_conv(sh, percpu, 0));
- tx = async_xor(xor_dest, xor_srcs, 0, count,
- conf->stripe_size, &submit);
+ tx = async_xor_offsets(xor_dest, des_offset, xor_srcs, offs,
+ count, conf->stripe_size, &submit);
return tx;
}
@@ -1938,6 +1952,7 @@ ops_run_reconstruct5(struct stripe_head *sh, struct raid5_percpu *percpu,
{
int disks = sh->disks;
struct page **xor_srcs;
+ unsigned int *offs;
struct async_submit_ctl submit;
int count, pd_idx = sh->pd_idx, i;
struct page *xor_dest;
@@ -1947,6 +1962,7 @@ ops_run_reconstruct5(struct stripe_head *sh, struct raid5_percpu *percpu,
struct stripe_head *head_sh = sh;
int last_stripe;
struct r5conf *conf = sh->raid_conf;
+ unsigned int des_offset;
pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
@@ -1966,24 +1982,33 @@ ops_run_reconstruct5(struct stripe_head *sh, struct raid5_percpu *percpu,
again:
count = 0;
xor_srcs = to_addr_page(percpu, j);
+ offs = to_addr_offs(sh, percpu);
/* check if prexor is active which means only process blocks
* that are part of a read-modify-write (written)
*/
if (head_sh->reconstruct_state == reconstruct_state_prexor_drain_run) {
prexor = 1;
+ des_offset = offs[count] = sh->dev[pd_idx].offset;
xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page;
+
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
if (head_sh->dev[i].written ||
- test_bit(R5_InJournal, &head_sh->dev[i].flags))
+ test_bit(R5_InJournal, &head_sh->dev[i].flags)) {
+ offs[count] = dev->offset;
xor_srcs[count++] = dev->page;
+ }
}
} else {
xor_dest = sh->dev[pd_idx].page;
+ des_offset = sh->dev[pd_idx].offset;
+
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
- if (i != pd_idx)
+ if (i != pd_idx) {
+ offs[count] = dev->offset;
xor_srcs[count++] = dev->page;
+ }
}
}
@@ -2009,11 +2034,12 @@ ops_run_reconstruct5(struct stripe_head *sh, struct raid5_percpu *percpu,
}
if (unlikely(count == 1))
- tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0,
- conf->stripe_size, &submit);
+ tx = async_memcpy(xor_dest, xor_srcs[0], des_offset,
+ offs[0], conf->stripe_size, &submit);
else
- tx = async_xor(xor_dest, xor_srcs, 0, count,
- conf->stripe_size, &submit);
+ tx = async_xor_offsets(xor_dest, des_offset, xor_srcs,
+ offs, count, conf->stripe_size, &submit);
+
if (!last_stripe) {
j++;
sh = list_first_entry(&sh->batch_list, struct stripe_head,
@@ -2103,11 +2129,13 @@ static void ops_run_check_p(struct stripe_head *sh, struct raid5_percpu *percpu)
int qd_idx = sh->qd_idx;
struct page *xor_dest;
struct page **xor_srcs = to_addr_page(percpu, 0);
+ unsigned int *offs = to_addr_offs(sh, percpu);
struct dma_async_tx_descriptor *tx;
struct async_submit_ctl submit;
int count;
int i;
struct r5conf *conf = sh->raid_conf;
+ unsigned int dest_offset;
pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
@@ -2115,17 +2143,22 @@ static void ops_run_check_p(struct stripe_head *sh, struct raid5_percpu *percpu)
BUG_ON(sh->batch_head);
count = 0;
xor_dest = sh->dev[pd_idx].page;
+ dest_offset = sh->dev[pd_idx].offset;
+ offs[count] = dest_offset;
xor_srcs[count++] = xor_dest;
+
for (i = disks; i--; ) {
if (i == pd_idx || i == qd_idx)
continue;
+ offs[count] = sh->dev[i].offset;
xor_srcs[count++] = sh->dev[i].page;
}
init_async_submit(&submit, 0, NULL, NULL, NULL,
to_addr_conv(sh, percpu, 0));
- tx = async_xor_val(xor_dest, xor_srcs, 0, count, conf->stripe_size,
- &sh->ops.zero_sum_result, &submit);
+ tx = async_xor_val_offsets(xor_dest, dest_offset, xor_srcs, offs,
+ count, conf->stripe_size,
+ &sh->ops.zero_sum_result, &submit);
atomic_inc(&sh->count);
init_async_submit(&submit, ASYNC_TX_ACK, tx, ops_complete_check, sh, NULL);
--
2.25.4
^ permalink raw reply related [flat|nested] 19+ messages in thread* [PATCH v6 11/15] md/raid5: support config stripe_size by sysfs entry
2020-07-15 12:42 [PATCH v6 00/15] md/raid5: set STRIPE_SIZE as a configurable value Yufen Yu
` (9 preceding siblings ...)
2020-07-15 12:42 ` [PATCH v6 10/15] md/raid5: compute xor with correct page offset Yufen Yu
@ 2020-07-15 12:42 ` Yufen Yu
2020-07-16 7:06 ` Song Liu
2020-07-15 12:42 ` [PATCH v6 12/15] md/raid6: let syndrome computor support different page offset Yufen Yu
` (4 subsequent siblings)
15 siblings, 1 reply; 19+ messages in thread
From: Yufen Yu @ 2020-07-15 12:42 UTC (permalink / raw)
To: song; +Cc: linux-raid, neilb, guoqing.jiang, houtao1, yuyufen
Adding a new 'stripe_size' sysfs entry to set and show stripe_size.
After that, we can adjust stripe_size by writing value into sysfs
entry, likely, set stripe_size as 16KB:
echo 16384 > /sys/block/md1/md/stripe_size
Show current stripe_size value:
cat /sys/block/md1/md/stripe_size
stripe_size should not be bigger than PAGE_SIZE, and it requires to be
multiple of 4096.
Signed-off-by: Yufen Yu <yuyufen@huawei.com>
---
drivers/md/raid5.c | 94 ++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 94 insertions(+)
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 84c35eb225b4..338a0732c202 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -6699,6 +6699,99 @@ raid5_rmw_level = __ATTR(rmw_level, S_IRUGO | S_IWUSR,
raid5_show_rmw_level,
raid5_store_rmw_level);
+static ssize_t
+raid5_show_stripe_size(struct mddev *mddev, char *page)
+{
+ struct r5conf *conf;
+ int ret = 0;
+
+ spin_lock(&mddev->lock);
+ conf = mddev->private;
+ if (conf)
+ ret = sprintf(page, "%lu\n", conf->stripe_size);
+ spin_unlock(&mddev->lock);
+ return ret;
+}
+
+static ssize_t
+raid5_store_stripe_size(struct mddev *mddev, const char *page, size_t len)
+{
+ struct r5conf *conf;
+ unsigned long new;
+ int err;
+ int nr;
+
+ if (len >= PAGE_SIZE)
+ return -EINVAL;
+ if (kstrtoul(page, 10, &new))
+ return -EINVAL;
+ /*
+ * When PAGE_SZIE is 4096, we don't need to modify stripe_size.
+ * And the value should not be bigger than PAGE_SIZE.
+ * It requires to be multiple of 4096.
+ */
+ if (PAGE_SIZE == 4096 || new % 4096 != 0 ||
+ new > PAGE_SIZE || new == 0)
+ return -EINVAL;
+
+ err = mddev_lock(mddev);
+ if (err)
+ return err;
+
+ conf = mddev->private;
+ if (!conf) {
+ err = -ENODEV;
+ goto out_unlock;
+ }
+
+ if (new == conf->stripe_size)
+ goto out_unlock;
+
+ pr_debug("md/raid: change stripe_size from %lu to %lu\n",
+ conf->stripe_size, new);
+
+ if (mddev->sync_thread ||
+ test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
+ mddev->reshape_position != MaxSector ||
+ mddev->sysfs_active) {
+ err = -EBUSY;
+ goto out_unlock;
+ }
+
+ nr = conf->max_nr_stripes;
+
+ /* 1. suspend raid array */
+ mddev_suspend(mddev);
+
+ /* 2. free all old stripe_head */
+ mutex_lock(&conf->cache_size_mutex);
+ shrink_stripes(conf);
+
+ /* 3. set new stripe_size */
+ conf->stripe_size = new;
+ conf->stripe_shift = ilog2(new) - 9;
+ conf->stripe_sectors = new >> 9;
+
+ /* 4. allocate new stripe_head */
+ if (grow_stripes(conf, nr)) {
+ pr_warn("md/raid:%s: couldn't allocate buffers\n",
+ mdname(mddev));
+ err = -ENOMEM;
+ }
+ mutex_unlock(&conf->cache_size_mutex);
+
+ /* 5. resume raid array */
+ mddev_resume(mddev);
+
+out_unlock:
+ mddev_unlock(mddev);
+ return err ?: len;
+}
+
+static struct md_sysfs_entry
+raid5_stripe_size = __ATTR(stripe_size, 0644,
+ raid5_show_stripe_size,
+ raid5_store_stripe_size);
static ssize_t
raid5_show_preread_threshold(struct mddev *mddev, char *page)
@@ -6887,6 +6980,7 @@ static struct attribute *raid5_attrs[] = {
&raid5_group_thread_cnt.attr,
&raid5_skip_copy.attr,
&raid5_rmw_level.attr,
+ &raid5_stripe_size.attr,
&r5c_journal_mode.attr,
&ppl_write_hint.attr,
NULL,
--
2.25.4
^ permalink raw reply related [flat|nested] 19+ messages in thread* Re: [PATCH v6 11/15] md/raid5: support config stripe_size by sysfs entry
2020-07-15 12:42 ` [PATCH v6 11/15] md/raid5: support config stripe_size by sysfs entry Yufen Yu
@ 2020-07-16 7:06 ` Song Liu
0 siblings, 0 replies; 19+ messages in thread
From: Song Liu @ 2020-07-16 7:06 UTC (permalink / raw)
To: Yufen Yu; +Cc: linux-raid, NeilBrown, Guoqing Jiang, Hou Tao
On Wed, Jul 15, 2020 at 5:42 AM Yufen Yu <yuyufen@huawei.com> wrote:
>
> Adding a new 'stripe_size' sysfs entry to set and show stripe_size.
> After that, we can adjust stripe_size by writing value into sysfs
> entry, likely, set stripe_size as 16KB:
>
> echo 16384 > /sys/block/md1/md/stripe_size
>
> Show current stripe_size value:
>
> cat /sys/block/md1/md/stripe_size
>
> stripe_size should not be bigger than PAGE_SIZE, and it requires to be
> multiple of 4096.
>
> Signed-off-by: Yufen Yu <yuyufen@huawei.com>
For this patch, please consider the following changes:
1) use DEFAULT_STRIPE_SIZE instead of 4096;
2) make the sysfs entry read only for PAGE_SIZE == 4096
diff --git i/drivers/md/raid5.c w/drivers/md/raid5.c
index 735238425c7f3..320fc14bc628c 100644
--- i/drivers/md/raid5.c
+++ w/drivers/md/raid5.c
@@ -6532,6 +6532,8 @@ raid5_show_stripe_size(struct mddev *mddev, char *page)
return ret;
}
+#if PAGE_SIZE != DEFAULT_STRIPE_SIZE
+
static ssize_t
raid5_store_stripe_size(struct mddev *mddev, const char *page, size_t len)
{
@@ -6544,13 +6546,12 @@ raid5_store_stripe_size(struct mddev *mddev,
const char *page, size_t len)
return -EINVAL;
if (kstrtoul(page, 10, &new))
return -EINVAL;
+
/*
- * When PAGE_SZIE is 4096, we don't need to modify stripe_size.
- * And the value should not be bigger than PAGE_SIZE.
- * It requires to be multiple of 4096.
+ * The value should not be bigger than PAGE_SIZE. It requires to
+ * be multiple of DEFAULT_STRIPE_SIZE.
*/
- if (PAGE_SIZE == 4096 || new % 4096 != 0 ||
- new > PAGE_SIZE || new == 0)
+ if (new % DEFAULT_STRIPE_SIZE != 0 || new > PAGE_SIZE || new == 0)
return -EINVAL;
err = mddev_lock(mddev);
@@ -6612,6 +6613,15 @@ raid5_stripe_size = __ATTR(stripe_size, 0644,
raid5_show_stripe_size,
raid5_store_stripe_size);
+#else
+
+static struct md_sysfs_entry
+raid5_stripe_size = __ATTR(stripe_size, 0444,
+ raid5_show_stripe_size,
+ NULL);
+
+#endif /* PAGE_SIZE != DEFAULT_STRIPE_SIZE */
+
static ssize_t
raid5_show_preread_threshold(struct mddev *mddev, char *page)
{
^ permalink raw reply related [flat|nested] 19+ messages in thread
* [PATCH v6 12/15] md/raid6: let syndrome computor support different page offset
2020-07-15 12:42 [PATCH v6 00/15] md/raid5: set STRIPE_SIZE as a configurable value Yufen Yu
` (10 preceding siblings ...)
2020-07-15 12:42 ` [PATCH v6 11/15] md/raid5: support config stripe_size by sysfs entry Yufen Yu
@ 2020-07-15 12:42 ` Yufen Yu
2020-07-15 12:42 ` [PATCH v6 13/15] md/raid6: let async recovery function " Yufen Yu
` (3 subsequent siblings)
15 siblings, 0 replies; 19+ messages in thread
From: Yufen Yu @ 2020-07-15 12:42 UTC (permalink / raw)
To: song; +Cc: linux-raid, neilb, guoqing.jiang, houtao1, yuyufen
For now, syndrome compute functions require common offset in the pages
array. However, we expect these function can support different page
offset when try to use share page. Simplily covert them by adding page
offset where each page address are referred.
Since the only caller of async_gen_syndrome() and async_syndrome_val()
are in md/raid6, we don't want to reserve them but modify the interface
directly.
Signed-off-by: Yufen Yu <yuyufen@huawei.com>
---
crypto/async_tx/async_pq.c | 72 +++++++++++++++++++++++++-------------
include/linux/async_tx.h | 6 ++--
2 files changed, 51 insertions(+), 27 deletions(-)
diff --git a/crypto/async_tx/async_pq.c b/crypto/async_tx/async_pq.c
index 341ece61cf9b..f3256e9ceafe 100644
--- a/crypto/async_tx/async_pq.c
+++ b/crypto/async_tx/async_pq.c
@@ -104,7 +104,7 @@ do_async_gen_syndrome(struct dma_chan *chan,
* do_sync_gen_syndrome - synchronously calculate a raid6 syndrome
*/
static void
-do_sync_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
+do_sync_gen_syndrome(struct page **blocks, unsigned int *offsets, int disks,
size_t len, struct async_submit_ctl *submit)
{
void **srcs;
@@ -121,7 +121,8 @@ do_sync_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
BUG_ON(i > disks - 3); /* P or Q can't be zero */
srcs[i] = (void*)raid6_empty_zero_page;
} else {
- srcs[i] = page_address(blocks[i]) + offset;
+ srcs[i] = page_address(blocks[i]) + offsets[i];
+
if (i < disks - 2) {
stop = i;
if (start == -1)
@@ -138,10 +139,23 @@ do_sync_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
async_tx_sync_epilog(submit);
}
+static inline bool
+is_dma_pq_aligned_offs(struct dma_device *dev, unsigned int *offs,
+ int src_cnt, size_t len)
+{
+ int i;
+
+ for (i = 0; i < src_cnt; i++) {
+ if (!is_dma_pq_aligned(dev, offs[i], 0, len))
+ return false;
+ }
+ return true;
+}
+
/**
* async_gen_syndrome - asynchronously calculate a raid6 syndrome
* @blocks: source blocks from idx 0..disks-3, P @ disks-2 and Q @ disks-1
- * @offset: common offset into each block (src and dest) to start transaction
+ * @offsets: offset array into each block (src and dest) to start transaction
* @disks: number of blocks (including missing P or Q, see below)
* @len: length of operation in bytes
* @submit: submission/completion modifiers
@@ -160,7 +174,7 @@ do_sync_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
* path.
*/
struct dma_async_tx_descriptor *
-async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
+async_gen_syndrome(struct page **blocks, unsigned int *offsets, int disks,
size_t len, struct async_submit_ctl *submit)
{
int src_cnt = disks - 2;
@@ -179,7 +193,7 @@ async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
if (unmap && !(submit->flags & ASYNC_TX_PQ_XOR_DST) &&
(src_cnt <= dma_maxpq(device, 0) ||
dma_maxpq(device, DMA_PREP_CONTINUE) > 0) &&
- is_dma_pq_aligned(device, offset, 0, len)) {
+ is_dma_pq_aligned_offs(device, offsets, disks, len)) {
struct dma_async_tx_descriptor *tx;
enum dma_ctrl_flags dma_flags = 0;
unsigned char coefs[MAX_DISKS];
@@ -196,8 +210,8 @@ async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
for (i = 0, j = 0; i < src_cnt; i++) {
if (blocks[i] == NULL)
continue;
- unmap->addr[j] = dma_map_page(device->dev, blocks[i], offset,
- len, DMA_TO_DEVICE);
+ unmap->addr[j] = dma_map_page(device->dev, blocks[i],
+ offsets[i], len, DMA_TO_DEVICE);
coefs[j] = raid6_gfexp[i];
unmap->to_cnt++;
j++;
@@ -210,7 +224,8 @@ async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
unmap->bidi_cnt++;
if (P(blocks, disks))
unmap->addr[j++] = dma_map_page(device->dev, P(blocks, disks),
- offset, len, DMA_BIDIRECTIONAL);
+ P(offsets, disks),
+ len, DMA_BIDIRECTIONAL);
else {
unmap->addr[j++] = 0;
dma_flags |= DMA_PREP_PQ_DISABLE_P;
@@ -219,7 +234,8 @@ async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
unmap->bidi_cnt++;
if (Q(blocks, disks))
unmap->addr[j++] = dma_map_page(device->dev, Q(blocks, disks),
- offset, len, DMA_BIDIRECTIONAL);
+ Q(offsets, disks),
+ len, DMA_BIDIRECTIONAL);
else {
unmap->addr[j++] = 0;
dma_flags |= DMA_PREP_PQ_DISABLE_Q;
@@ -240,13 +256,13 @@ async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
if (!P(blocks, disks)) {
P(blocks, disks) = pq_scribble_page;
- BUG_ON(len + offset > PAGE_SIZE);
+ P(offsets, disks) = 0;
}
if (!Q(blocks, disks)) {
Q(blocks, disks) = pq_scribble_page;
- BUG_ON(len + offset > PAGE_SIZE);
+ Q(offsets, disks) = 0;
}
- do_sync_gen_syndrome(blocks, offset, disks, len, submit);
+ do_sync_gen_syndrome(blocks, offsets, disks, len, submit);
return NULL;
}
@@ -270,6 +286,7 @@ pq_val_chan(struct async_submit_ctl *submit, struct page **blocks, int disks, si
* @len: length of operation in bytes
* @pqres: on val failure SUM_CHECK_P_RESULT and/or SUM_CHECK_Q_RESULT are set
* @spare: temporary result buffer for the synchronous case
+ * @s_off: spare buffer page offset
* @submit: submission / completion modifiers
*
* The same notes from async_gen_syndrome apply to the 'blocks',
@@ -278,9 +295,9 @@ pq_val_chan(struct async_submit_ctl *submit, struct page **blocks, int disks, si
* specified.
*/
struct dma_async_tx_descriptor *
-async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
+async_syndrome_val(struct page **blocks, unsigned int *offsets, int disks,
size_t len, enum sum_check_flags *pqres, struct page *spare,
- struct async_submit_ctl *submit)
+ unsigned int s_off, struct async_submit_ctl *submit)
{
struct dma_chan *chan = pq_val_chan(submit, blocks, disks, len);
struct dma_device *device = chan ? chan->device : NULL;
@@ -295,7 +312,7 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOWAIT);
if (unmap && disks <= dma_maxpq(device, 0) &&
- is_dma_pq_aligned(device, offset, 0, len)) {
+ is_dma_pq_aligned_offs(device, offsets, disks, len)) {
struct device *dev = device->dev;
dma_addr_t pq[2];
int i, j = 0, src_cnt = 0;
@@ -307,7 +324,7 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
for (i = 0; i < disks-2; i++)
if (likely(blocks[i])) {
unmap->addr[j] = dma_map_page(dev, blocks[i],
- offset, len,
+ offsets[i], len,
DMA_TO_DEVICE);
coefs[j] = raid6_gfexp[i];
unmap->to_cnt++;
@@ -320,7 +337,7 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
dma_flags |= DMA_PREP_PQ_DISABLE_P;
} else {
pq[0] = dma_map_page(dev, P(blocks, disks),
- offset, len,
+ P(offsets, disks), len,
DMA_TO_DEVICE);
unmap->addr[j++] = pq[0];
unmap->to_cnt++;
@@ -330,7 +347,7 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
dma_flags |= DMA_PREP_PQ_DISABLE_Q;
} else {
pq[1] = dma_map_page(dev, Q(blocks, disks),
- offset, len,
+ Q(offsets, disks), len,
DMA_TO_DEVICE);
unmap->addr[j++] = pq[1];
unmap->to_cnt++;
@@ -355,7 +372,9 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
async_tx_submit(chan, tx, submit);
} else {
struct page *p_src = P(blocks, disks);
+ unsigned int p_off = P(offsets, disks);
struct page *q_src = Q(blocks, disks);
+ unsigned int q_off = Q(offsets, disks);
enum async_tx_flags flags_orig = submit->flags;
dma_async_tx_callback cb_fn_orig = submit->cb_fn;
void *scribble = submit->scribble;
@@ -381,27 +400,32 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
if (p_src) {
init_async_submit(submit, ASYNC_TX_XOR_ZERO_DST, NULL,
NULL, NULL, scribble);
- tx = async_xor(spare, blocks, offset, disks-2, len, submit);
+ tx = async_xor_offsets(spare, s_off,
+ blocks, offsets, disks-2, len, submit);
async_tx_quiesce(&tx);
- p = page_address(p_src) + offset;
- s = page_address(spare) + offset;
+ p = page_address(p_src) + p_off;
+ s = page_address(spare) + s_off;
*pqres |= !!memcmp(p, s, len) << SUM_CHECK_P;
}
if (q_src) {
P(blocks, disks) = NULL;
Q(blocks, disks) = spare;
+ Q(offsets, disks) = s_off;
init_async_submit(submit, 0, NULL, NULL, NULL, scribble);
- tx = async_gen_syndrome(blocks, offset, disks, len, submit);
+ tx = async_gen_syndrome(blocks, offsets, disks,
+ len, submit);
async_tx_quiesce(&tx);
- q = page_address(q_src) + offset;
- s = page_address(spare) + offset;
+ q = page_address(q_src) + q_off;
+ s = page_address(spare) + s_off;
*pqres |= !!memcmp(q, s, len) << SUM_CHECK_Q;
}
/* restore P, Q and submit */
P(blocks, disks) = p_src;
+ P(offsets, disks) = p_off;
Q(blocks, disks) = q_src;
+ Q(offsets, disks) = q_off;
submit->cb_fn = cb_fn_orig;
submit->cb_param = cb_param_orig;
diff --git a/include/linux/async_tx.h b/include/linux/async_tx.h
index 8d79e2de06bd..bbda58d48dbd 100644
--- a/include/linux/async_tx.h
+++ b/include/linux/async_tx.h
@@ -186,13 +186,13 @@ async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset,
struct dma_async_tx_descriptor *async_trigger_callback(struct async_submit_ctl *submit);
struct dma_async_tx_descriptor *
-async_gen_syndrome(struct page **blocks, unsigned int offset, int src_cnt,
+async_gen_syndrome(struct page **blocks, unsigned int *offsets, int src_cnt,
size_t len, struct async_submit_ctl *submit);
struct dma_async_tx_descriptor *
-async_syndrome_val(struct page **blocks, unsigned int offset, int src_cnt,
+async_syndrome_val(struct page **blocks, unsigned int *offsets, int src_cnt,
size_t len, enum sum_check_flags *pqres, struct page *spare,
- struct async_submit_ctl *submit);
+ unsigned int s_off, struct async_submit_ctl *submit);
struct dma_async_tx_descriptor *
async_raid6_2data_recov(int src_num, size_t bytes, int faila, int failb,
--
2.25.4
^ permalink raw reply related [flat|nested] 19+ messages in thread* [PATCH v6 13/15] md/raid6: let async recovery function support different page offset
2020-07-15 12:42 [PATCH v6 00/15] md/raid5: set STRIPE_SIZE as a configurable value Yufen Yu
` (11 preceding siblings ...)
2020-07-15 12:42 ` [PATCH v6 12/15] md/raid6: let syndrome computor support different page offset Yufen Yu
@ 2020-07-15 12:42 ` Yufen Yu
2020-07-15 12:42 ` [PATCH v6 14/15] md/raid6: compute syndrome with correct " Yufen Yu
` (2 subsequent siblings)
15 siblings, 0 replies; 19+ messages in thread
From: Yufen Yu @ 2020-07-15 12:42 UTC (permalink / raw)
To: song; +Cc: linux-raid, neilb, guoqing.jiang, houtao1, yuyufen
For now, asynchronous raid6 recovery calculate functions are require
common offset for pages. But, we expect them to support different page
offset after introducing stripe shared page. Do that by simplily adding
page offset where each page address are referred.
Signed-off-by: Yufen Yu <yuyufen@huawei.com>
---
crypto/async_tx/async_raid6_recov.c | 163 ++++++++++++++++++++--------
include/linux/async_tx.h | 6 +-
2 files changed, 124 insertions(+), 45 deletions(-)
diff --git a/crypto/async_tx/async_raid6_recov.c b/crypto/async_tx/async_raid6_recov.c
index f249142ceac4..0eb323a618b0 100644
--- a/crypto/async_tx/async_raid6_recov.c
+++ b/crypto/async_tx/async_raid6_recov.c
@@ -15,8 +15,9 @@
#include <linux/dmaengine.h>
static struct dma_async_tx_descriptor *
-async_sum_product(struct page *dest, struct page **srcs, unsigned char *coef,
- size_t len, struct async_submit_ctl *submit)
+async_sum_product(struct page *dest, unsigned int d_off,
+ struct page **srcs, unsigned int *src_offs, unsigned char *coef,
+ size_t len, struct async_submit_ctl *submit)
{
struct dma_chan *chan = async_tx_find_channel(submit, DMA_PQ,
&dest, 1, srcs, 2, len);
@@ -37,11 +38,14 @@ async_sum_product(struct page *dest, struct page **srcs, unsigned char *coef,
if (submit->flags & ASYNC_TX_FENCE)
dma_flags |= DMA_PREP_FENCE;
- unmap->addr[0] = dma_map_page(dev, srcs[0], 0, len, DMA_TO_DEVICE);
- unmap->addr[1] = dma_map_page(dev, srcs[1], 0, len, DMA_TO_DEVICE);
+ unmap->addr[0] = dma_map_page(dev, srcs[0], src_offs[0],
+ len, DMA_TO_DEVICE);
+ unmap->addr[1] = dma_map_page(dev, srcs[1], src_offs[1],
+ len, DMA_TO_DEVICE);
unmap->to_cnt = 2;
- unmap->addr[2] = dma_map_page(dev, dest, 0, len, DMA_BIDIRECTIONAL);
+ unmap->addr[2] = dma_map_page(dev, dest, d_off,
+ len, DMA_BIDIRECTIONAL);
unmap->bidi_cnt = 1;
/* engine only looks at Q, but expects it to follow P */
pq[1] = unmap->addr[2];
@@ -66,9 +70,9 @@ async_sum_product(struct page *dest, struct page **srcs, unsigned char *coef,
async_tx_quiesce(&submit->depend_tx);
amul = raid6_gfmul[coef[0]];
bmul = raid6_gfmul[coef[1]];
- a = page_address(srcs[0]);
- b = page_address(srcs[1]);
- c = page_address(dest);
+ a = page_address(srcs[0]) + src_offs[0];
+ b = page_address(srcs[1]) + src_offs[1];
+ c = page_address(dest) + d_off;
while (len--) {
ax = amul[*a++];
@@ -80,8 +84,9 @@ async_sum_product(struct page *dest, struct page **srcs, unsigned char *coef,
}
static struct dma_async_tx_descriptor *
-async_mult(struct page *dest, struct page *src, u8 coef, size_t len,
- struct async_submit_ctl *submit)
+async_mult(struct page *dest, unsigned int d_off, struct page *src,
+ unsigned int s_off, u8 coef, size_t len,
+ struct async_submit_ctl *submit)
{
struct dma_chan *chan = async_tx_find_channel(submit, DMA_PQ,
&dest, 1, &src, 1, len);
@@ -101,9 +106,11 @@ async_mult(struct page *dest, struct page *src, u8 coef, size_t len,
if (submit->flags & ASYNC_TX_FENCE)
dma_flags |= DMA_PREP_FENCE;
- unmap->addr[0] = dma_map_page(dev, src, 0, len, DMA_TO_DEVICE);
+ unmap->addr[0] = dma_map_page(dev, src, s_off,
+ len, DMA_TO_DEVICE);
unmap->to_cnt++;
- unmap->addr[1] = dma_map_page(dev, dest, 0, len, DMA_BIDIRECTIONAL);
+ unmap->addr[1] = dma_map_page(dev, dest, d_off,
+ len, DMA_BIDIRECTIONAL);
dma_dest[1] = unmap->addr[1];
unmap->bidi_cnt++;
unmap->len = len;
@@ -133,8 +140,8 @@ async_mult(struct page *dest, struct page *src, u8 coef, size_t len,
*/
async_tx_quiesce(&submit->depend_tx);
qmul = raid6_gfmul[coef];
- d = page_address(dest);
- s = page_address(src);
+ d = page_address(dest) + d_off;
+ s = page_address(src) + s_off;
while (len--)
*d++ = qmul[*s++];
@@ -144,11 +151,14 @@ async_mult(struct page *dest, struct page *src, u8 coef, size_t len,
static struct dma_async_tx_descriptor *
__2data_recov_4(int disks, size_t bytes, int faila, int failb,
- struct page **blocks, struct async_submit_ctl *submit)
+ struct page **blocks, unsigned int *offs,
+ struct async_submit_ctl *submit)
{
struct dma_async_tx_descriptor *tx = NULL;
struct page *p, *q, *a, *b;
+ unsigned int p_off, q_off, a_off, b_off;
struct page *srcs[2];
+ unsigned int src_offs[2];
unsigned char coef[2];
enum async_tx_flags flags = submit->flags;
dma_async_tx_callback cb_fn = submit->cb_fn;
@@ -156,26 +166,34 @@ __2data_recov_4(int disks, size_t bytes, int faila, int failb,
void *scribble = submit->scribble;
p = blocks[disks-2];
+ p_off = offs[disks-2];
q = blocks[disks-1];
+ q_off = offs[disks-1];
a = blocks[faila];
+ a_off = offs[faila];
b = blocks[failb];
+ b_off = offs[failb];
/* in the 4 disk case P + Pxy == P and Q + Qxy == Q */
/* Dx = A*(P+Pxy) + B*(Q+Qxy) */
srcs[0] = p;
+ src_offs[0] = p_off;
srcs[1] = q;
+ src_offs[1] = q_off;
coef[0] = raid6_gfexi[failb-faila];
coef[1] = raid6_gfinv[raid6_gfexp[faila]^raid6_gfexp[failb]];
init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
- tx = async_sum_product(b, srcs, coef, bytes, submit);
+ tx = async_sum_product(b, b_off, srcs, src_offs, coef, bytes, submit);
/* Dy = P+Pxy+Dx */
srcs[0] = p;
+ src_offs[0] = p_off;
srcs[1] = b;
+ src_offs[1] = b_off;
init_async_submit(submit, flags | ASYNC_TX_XOR_ZERO_DST, tx, cb_fn,
cb_param, scribble);
- tx = async_xor(a, srcs, 0, 2, bytes, submit);
+ tx = async_xor_offsets(a, a_off, srcs, src_offs, 2, bytes, submit);
return tx;
@@ -183,11 +201,14 @@ __2data_recov_4(int disks, size_t bytes, int faila, int failb,
static struct dma_async_tx_descriptor *
__2data_recov_5(int disks, size_t bytes, int faila, int failb,
- struct page **blocks, struct async_submit_ctl *submit)
+ struct page **blocks, unsigned int *offs,
+ struct async_submit_ctl *submit)
{
struct dma_async_tx_descriptor *tx = NULL;
struct page *p, *q, *g, *dp, *dq;
+ unsigned int p_off, q_off, g_off, dp_off, dq_off;
struct page *srcs[2];
+ unsigned int src_offs[2];
unsigned char coef[2];
enum async_tx_flags flags = submit->flags;
dma_async_tx_callback cb_fn = submit->cb_fn;
@@ -208,60 +229,77 @@ __2data_recov_5(int disks, size_t bytes, int faila, int failb,
BUG_ON(good_srcs > 1);
p = blocks[disks-2];
+ p_off = offs[disks-2];
q = blocks[disks-1];
+ q_off = offs[disks-1];
g = blocks[good];
+ g_off = offs[good];
/* Compute syndrome with zero for the missing data pages
* Use the dead data pages as temporary storage for delta p and
* delta q
*/
dp = blocks[faila];
+ dp_off = offs[faila];
dq = blocks[failb];
+ dq_off = offs[failb];
init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
- tx = async_memcpy(dp, g, 0, 0, bytes, submit);
+ tx = async_memcpy(dp, g, dp_off, g_off, bytes, submit);
init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
- tx = async_mult(dq, g, raid6_gfexp[good], bytes, submit);
+ tx = async_mult(dq, dq_off, g, g_off,
+ raid6_gfexp[good], bytes, submit);
/* compute P + Pxy */
srcs[0] = dp;
+ src_offs[0] = dp_off;
srcs[1] = p;
+ src_offs[1] = p_off;
init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
NULL, NULL, scribble);
- tx = async_xor(dp, srcs, 0, 2, bytes, submit);
+ tx = async_xor_offsets(dp, dp_off, srcs, src_offs, 2, bytes, submit);
/* compute Q + Qxy */
srcs[0] = dq;
+ src_offs[0] = dq_off;
srcs[1] = q;
+ src_offs[1] = q_off;
init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
NULL, NULL, scribble);
- tx = async_xor(dq, srcs, 0, 2, bytes, submit);
+ tx = async_xor_offsets(dq, dq_off, srcs, src_offs, 2, bytes, submit);
/* Dx = A*(P+Pxy) + B*(Q+Qxy) */
srcs[0] = dp;
+ src_offs[0] = dp_off;
srcs[1] = dq;
+ src_offs[1] = dq_off;
coef[0] = raid6_gfexi[failb-faila];
coef[1] = raid6_gfinv[raid6_gfexp[faila]^raid6_gfexp[failb]];
init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
- tx = async_sum_product(dq, srcs, coef, bytes, submit);
+ tx = async_sum_product(dq, dq_off, srcs, src_offs, coef, bytes, submit);
/* Dy = P+Pxy+Dx */
srcs[0] = dp;
+ src_offs[0] = dp_off;
srcs[1] = dq;
+ src_offs[1] = dq_off;
init_async_submit(submit, flags | ASYNC_TX_XOR_DROP_DST, tx, cb_fn,
cb_param, scribble);
- tx = async_xor(dp, srcs, 0, 2, bytes, submit);
+ tx = async_xor_offsets(dp, dp_off, srcs, src_offs, 2, bytes, submit);
return tx;
}
static struct dma_async_tx_descriptor *
__2data_recov_n(int disks, size_t bytes, int faila, int failb,
- struct page **blocks, struct async_submit_ctl *submit)
+ struct page **blocks, unsigned int *offs,
+ struct async_submit_ctl *submit)
{
struct dma_async_tx_descriptor *tx = NULL;
struct page *p, *q, *dp, *dq;
+ unsigned int p_off, q_off, dp_off, dq_off;
struct page *srcs[2];
+ unsigned int src_offs[2];
unsigned char coef[2];
enum async_tx_flags flags = submit->flags;
dma_async_tx_callback cb_fn = submit->cb_fn;
@@ -269,56 +307,74 @@ __2data_recov_n(int disks, size_t bytes, int faila, int failb,
void *scribble = submit->scribble;
p = blocks[disks-2];
+ p_off = offs[disks-2];
q = blocks[disks-1];
+ q_off = offs[disks-1];
/* Compute syndrome with zero for the missing data pages
* Use the dead data pages as temporary storage for
* delta p and delta q
*/
dp = blocks[faila];
+ dp_off = offs[faila];
blocks[faila] = NULL;
blocks[disks-2] = dp;
+ offs[disks-2] = dp_off;
dq = blocks[failb];
+ dq_off = offs[failb];
blocks[failb] = NULL;
blocks[disks-1] = dq;
+ offs[disks-1] = dq_off;
init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
- tx = async_gen_syndrome(blocks, 0, disks, bytes, submit);
+ tx = async_gen_syndrome(blocks, offs, disks, bytes, submit);
/* Restore pointer table */
blocks[faila] = dp;
+ offs[faila] = dp_off;
blocks[failb] = dq;
+ offs[failb] = dq_off;
blocks[disks-2] = p;
+ offs[disks-2] = p_off;
blocks[disks-1] = q;
+ offs[disks-1] = q_off;
/* compute P + Pxy */
srcs[0] = dp;
+ src_offs[0] = dp_off;
srcs[1] = p;
+ src_offs[1] = p_off;
init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
NULL, NULL, scribble);
- tx = async_xor(dp, srcs, 0, 2, bytes, submit);
+ tx = async_xor_offsets(dp, dp_off, srcs, src_offs, 2, bytes, submit);
/* compute Q + Qxy */
srcs[0] = dq;
+ src_offs[0] = dq_off;
srcs[1] = q;
+ src_offs[1] = q_off;
init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
NULL, NULL, scribble);
- tx = async_xor(dq, srcs, 0, 2, bytes, submit);
+ tx = async_xor_offsets(dq, dq_off, srcs, src_offs, 2, bytes, submit);
/* Dx = A*(P+Pxy) + B*(Q+Qxy) */
srcs[0] = dp;
+ src_offs[0] = dp_off;
srcs[1] = dq;
+ src_offs[1] = dq_off;
coef[0] = raid6_gfexi[failb-faila];
coef[1] = raid6_gfinv[raid6_gfexp[faila]^raid6_gfexp[failb]];
init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
- tx = async_sum_product(dq, srcs, coef, bytes, submit);
+ tx = async_sum_product(dq, dq_off, srcs, src_offs, coef, bytes, submit);
/* Dy = P+Pxy+Dx */
srcs[0] = dp;
+ src_offs[0] = dp_off;
srcs[1] = dq;
+ src_offs[1] = dq_off;
init_async_submit(submit, flags | ASYNC_TX_XOR_DROP_DST, tx, cb_fn,
cb_param, scribble);
- tx = async_xor(dp, srcs, 0, 2, bytes, submit);
+ tx = async_xor_offsets(dp, dp_off, srcs, src_offs, 2, bytes, submit);
return tx;
}
@@ -330,11 +386,13 @@ __2data_recov_n(int disks, size_t bytes, int faila, int failb,
* @faila: first failed drive index
* @failb: second failed drive index
* @blocks: array of source pointers where the last two entries are p and q
+ * @offs: array of offset for pages in blocks
* @submit: submission/completion modifiers
*/
struct dma_async_tx_descriptor *
async_raid6_2data_recov(int disks, size_t bytes, int faila, int failb,
- struct page **blocks, struct async_submit_ctl *submit)
+ struct page **blocks, unsigned int *offs,
+ struct async_submit_ctl *submit)
{
void *scribble = submit->scribble;
int non_zero_srcs, i;
@@ -358,7 +416,7 @@ async_raid6_2data_recov(int disks, size_t bytes, int faila, int failb,
if (blocks[i] == NULL)
ptrs[i] = (void *) raid6_empty_zero_page;
else
- ptrs[i] = page_address(blocks[i]);
+ ptrs[i] = page_address(blocks[i]) + offs[i];
raid6_2data_recov(disks, bytes, faila, failb, ptrs);
@@ -383,16 +441,19 @@ async_raid6_2data_recov(int disks, size_t bytes, int faila, int failb,
* explicitly handle the special case of a 4 disk array with
* both data disks missing.
*/
- return __2data_recov_4(disks, bytes, faila, failb, blocks, submit);
+ return __2data_recov_4(disks, bytes, faila, failb,
+ blocks, offs, submit);
case 3:
/* dma devices do not uniformly understand a single
* source pq operation (in contrast to the synchronous
* case), so explicitly handle the special case of a 5 disk
* array with 2 of 3 data disks missing.
*/
- return __2data_recov_5(disks, bytes, faila, failb, blocks, submit);
+ return __2data_recov_5(disks, bytes, faila, failb,
+ blocks, offs, submit);
default:
- return __2data_recov_n(disks, bytes, faila, failb, blocks, submit);
+ return __2data_recov_n(disks, bytes, faila, failb,
+ blocks, offs, submit);
}
}
EXPORT_SYMBOL_GPL(async_raid6_2data_recov);
@@ -403,14 +464,17 @@ EXPORT_SYMBOL_GPL(async_raid6_2data_recov);
* @bytes: block size
* @faila: failed drive index
* @blocks: array of source pointers where the last two entries are p and q
+ * @offs: array of offset for pages in blocks
* @submit: submission/completion modifiers
*/
struct dma_async_tx_descriptor *
async_raid6_datap_recov(int disks, size_t bytes, int faila,
- struct page **blocks, struct async_submit_ctl *submit)
+ struct page **blocks, unsigned int *offs,
+ struct async_submit_ctl *submit)
{
struct dma_async_tx_descriptor *tx = NULL;
struct page *p, *q, *dq;
+ unsigned int p_off, q_off, dq_off;
u8 coef;
enum async_tx_flags flags = submit->flags;
dma_async_tx_callback cb_fn = submit->cb_fn;
@@ -418,6 +482,7 @@ async_raid6_datap_recov(int disks, size_t bytes, int faila,
void *scribble = submit->scribble;
int good_srcs, good, i;
struct page *srcs[2];
+ unsigned int src_offs[2];
pr_debug("%s: disks: %d len: %zu\n", __func__, disks, bytes);
@@ -434,7 +499,7 @@ async_raid6_datap_recov(int disks, size_t bytes, int faila,
if (blocks[i] == NULL)
ptrs[i] = (void*)raid6_empty_zero_page;
else
- ptrs[i] = page_address(blocks[i]);
+ ptrs[i] = page_address(blocks[i]) + offs[i];
raid6_datap_recov(disks, bytes, faila, ptrs);
@@ -458,55 +523,67 @@ async_raid6_datap_recov(int disks, size_t bytes, int faila,
BUG_ON(good_srcs == 0);
p = blocks[disks-2];
+ p_off = offs[disks-2];
q = blocks[disks-1];
+ q_off = offs[disks-1];
/* Compute syndrome with zero for the missing data page
* Use the dead data page as temporary storage for delta q
*/
dq = blocks[faila];
+ dq_off = offs[faila];
blocks[faila] = NULL;
blocks[disks-1] = dq;
+ offs[disks-1] = dq_off;
/* in the 4-disk case we only need to perform a single source
* multiplication with the one good data block.
*/
if (good_srcs == 1) {
struct page *g = blocks[good];
+ unsigned int g_off = offs[good];
init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL,
scribble);
- tx = async_memcpy(p, g, 0, 0, bytes, submit);
+ tx = async_memcpy(p, g, p_off, g_off, bytes, submit);
init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL,
scribble);
- tx = async_mult(dq, g, raid6_gfexp[good], bytes, submit);
+ tx = async_mult(dq, dq_off, g, g_off,
+ raid6_gfexp[good], bytes, submit);
} else {
init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL,
scribble);
- tx = async_gen_syndrome(blocks, 0, disks, bytes, submit);
+ tx = async_gen_syndrome(blocks, offs, disks, bytes, submit);
}
/* Restore pointer table */
blocks[faila] = dq;
+ offs[faila] = dq_off;
blocks[disks-1] = q;
+ offs[disks-1] = q_off;
/* calculate g^{-faila} */
coef = raid6_gfinv[raid6_gfexp[faila]];
srcs[0] = dq;
+ src_offs[0] = dq_off;
srcs[1] = q;
+ src_offs[1] = q_off;
init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
NULL, NULL, scribble);
- tx = async_xor(dq, srcs, 0, 2, bytes, submit);
+ tx = async_xor_offsets(dq, dq_off, srcs, src_offs, 2, bytes, submit);
init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
- tx = async_mult(dq, dq, coef, bytes, submit);
+ tx = async_mult(dq, dq_off, dq, dq_off, coef, bytes, submit);
srcs[0] = p;
+ src_offs[0] = p_off;
srcs[1] = dq;
+ src_offs[1] = dq_off;
init_async_submit(submit, flags | ASYNC_TX_XOR_DROP_DST, tx, cb_fn,
cb_param, scribble);
- tx = async_xor(p, srcs, 0, 2, bytes, submit);
+ tx = async_xor_offsets(p, p_off, srcs, src_offs, 2, bytes, submit);
return tx;
}
diff --git a/include/linux/async_tx.h b/include/linux/async_tx.h
index bbda58d48dbd..84d5cc5ff060 100644
--- a/include/linux/async_tx.h
+++ b/include/linux/async_tx.h
@@ -196,11 +196,13 @@ async_syndrome_val(struct page **blocks, unsigned int *offsets, int src_cnt,
struct dma_async_tx_descriptor *
async_raid6_2data_recov(int src_num, size_t bytes, int faila, int failb,
- struct page **ptrs, struct async_submit_ctl *submit);
+ struct page **ptrs, unsigned int *offs,
+ struct async_submit_ctl *submit);
struct dma_async_tx_descriptor *
async_raid6_datap_recov(int src_num, size_t bytes, int faila,
- struct page **ptrs, struct async_submit_ctl *submit);
+ struct page **ptrs, unsigned int *offs,
+ struct async_submit_ctl *submit);
void async_tx_quiesce(struct dma_async_tx_descriptor **tx);
#endif /* _ASYNC_TX_H_ */
--
2.25.4
^ permalink raw reply related [flat|nested] 19+ messages in thread* [PATCH v6 14/15] md/raid6: compute syndrome with correct page offset
2020-07-15 12:42 [PATCH v6 00/15] md/raid5: set STRIPE_SIZE as a configurable value Yufen Yu
` (12 preceding siblings ...)
2020-07-15 12:42 ` [PATCH v6 13/15] md/raid6: let async recovery function " Yufen Yu
@ 2020-07-15 12:42 ` Yufen Yu
2020-07-15 12:42 ` [PATCH v6 15/15] raid6test: adaptation with syndrome function Yufen Yu
2020-07-16 7:20 ` [PATCH v6 00/15] md/raid5: set STRIPE_SIZE as a configurable value Song Liu
15 siblings, 0 replies; 19+ messages in thread
From: Yufen Yu @ 2020-07-15 12:42 UTC (permalink / raw)
To: song; +Cc: linux-raid, neilb, guoqing.jiang, houtao1, yuyufen
When raid6 compute syndrome, the pages address will be passed to computer
function. After trying to support shared page between multiple sh->dev,
we also need to let computor know the correct location of each page.
Signed-off-by: Yufen Yu <yuyufen@huawei.com>
---
drivers/md/raid5.c | 69 +++++++++++++++++++++++++++++++---------------
1 file changed, 47 insertions(+), 22 deletions(-)
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 338a0732c202..f89da2ef9bce 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1531,6 +1531,7 @@ ops_run_compute5(struct stripe_head *sh, struct raid5_percpu *percpu)
/* set_syndrome_sources - populate source buffers for gen_syndrome
* @srcs - (struct page *) array of size sh->disks
+ * @offs - (unsigned int) array of offset for each page
* @sh - stripe_head to parse
*
* Populates srcs in proper layout order for the stripe and returns the
@@ -1539,6 +1540,7 @@ ops_run_compute5(struct stripe_head *sh, struct raid5_percpu *percpu)
* is recorded in srcs[count+1]].
*/
static int set_syndrome_sources(struct page **srcs,
+ unsigned int *offs,
struct stripe_head *sh,
int srctype)
{
@@ -1569,6 +1571,12 @@ static int set_syndrome_sources(struct page **srcs,
srcs[slot] = sh->dev[i].orig_page;
else
srcs[slot] = sh->dev[i].page;
+ /*
+ * For R5_InJournal, PAGE_SIZE must be 4KB and will
+ * not use r5pages. In that case, dev[i].offset
+ * is 0. So we can also use the value directly.
+ */
+ offs[slot] = sh->dev[i].offset;
}
i = raid6_next_disk(i, disks);
} while (i != d0_idx);
@@ -1581,12 +1589,14 @@ ops_run_compute6_1(struct stripe_head *sh, struct raid5_percpu *percpu)
{
int disks = sh->disks;
struct page **blocks = to_addr_page(percpu, 0);
+ unsigned int *offs = to_addr_offs(sh, percpu);
int target;
int qd_idx = sh->qd_idx;
struct dma_async_tx_descriptor *tx;
struct async_submit_ctl submit;
struct r5dev *tgt;
struct page *dest;
+ unsigned int dest_off;
int i;
int count;
struct r5conf *conf = sh->raid_conf;
@@ -1606,32 +1616,35 @@ ops_run_compute6_1(struct stripe_head *sh, struct raid5_percpu *percpu)
tgt = &sh->dev[target];
BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags));
dest = tgt->page;
+ dest_off = tgt->offset;
atomic_inc(&sh->count);
if (target == qd_idx) {
- count = set_syndrome_sources(blocks, sh, SYNDROME_SRC_ALL);
+ count = set_syndrome_sources(blocks, offs,
+ sh, SYNDROME_SRC_ALL);
blocks[count] = NULL; /* regenerating p is not necessary */
BUG_ON(blocks[count+1] != dest); /* q should already be set */
init_async_submit(&submit, ASYNC_TX_FENCE, NULL,
ops_complete_compute, sh,
to_addr_conv(sh, percpu, 0));
- tx = async_gen_syndrome(blocks, 0, count+2,
- conf->stripe_size, &submit);
+ tx = async_gen_syndrome(blocks, offs,
+ count+2, conf->stripe_size, &submit);
} else {
/* Compute any data- or p-drive using XOR */
count = 0;
for (i = disks; i-- ; ) {
if (i == target || i == qd_idx)
continue;
+ offs[count] = sh->dev[i].offset;
blocks[count++] = sh->dev[i].page;
}
init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST,
NULL, ops_complete_compute, sh,
to_addr_conv(sh, percpu, 0));
- tx = async_xor(dest, blocks, 0, count,
- conf->stripe_size, &submit);
+ tx = async_xor_offsets(dest, dest_off, blocks, offs,
+ count, conf->stripe_size, &submit);
}
return tx;
@@ -1650,6 +1663,7 @@ ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu)
struct r5dev *tgt2 = &sh->dev[target2];
struct dma_async_tx_descriptor *tx;
struct page **blocks = to_addr_page(percpu, 0);
+ unsigned int *offs = to_addr_offs(sh, percpu);
struct async_submit_ctl submit;
struct r5conf *conf = sh->raid_conf;
@@ -1670,6 +1684,7 @@ ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu)
do {
int slot = raid6_idx_to_slot(i, sh, &count, syndrome_disks);
+ offs[slot] = sh->dev[i].offset;
blocks[slot] = sh->dev[i].page;
if (i == target)
@@ -1694,10 +1709,12 @@ ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu)
init_async_submit(&submit, ASYNC_TX_FENCE, NULL,
ops_complete_compute, sh,
to_addr_conv(sh, percpu, 0));
- return async_gen_syndrome(blocks, 0, syndrome_disks+2,
- conf->stripe_size, &submit);
+ return async_gen_syndrome(blocks, offs,
+ syndrome_disks+2,
+ conf->stripe_size, &submit);
} else {
struct page *dest;
+ unsigned int dest_off;
int data_target;
int qd_idx = sh->qd_idx;
@@ -1711,21 +1728,24 @@ ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu)
for (i = disks; i-- ; ) {
if (i == data_target || i == qd_idx)
continue;
+ offs[count] = sh->dev[i].offset;
blocks[count++] = sh->dev[i].page;
}
dest = sh->dev[data_target].page;
+ dest_off = sh->dev[data_target].offset;
init_async_submit(&submit,
ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST,
NULL, NULL, NULL,
to_addr_conv(sh, percpu, 0));
- tx = async_xor(dest, blocks, 0, count,
- conf->stripe_size, &submit);
+ tx = async_xor_offsets(dest, dest_off, blocks, offs,
+ count, conf->stripe_size, &submit);
- count = set_syndrome_sources(blocks, sh, SYNDROME_SRC_ALL);
+ count = set_syndrome_sources(blocks, offs,
+ sh, SYNDROME_SRC_ALL);
init_async_submit(&submit, ASYNC_TX_FENCE, tx,
ops_complete_compute, sh,
to_addr_conv(sh, percpu, 0));
- return async_gen_syndrome(blocks, 0, count+2,
+ return async_gen_syndrome(blocks, offs, count+2,
conf->stripe_size, &submit);
}
} else {
@@ -1736,13 +1756,13 @@ ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu)
/* We're missing D+P. */
return async_raid6_datap_recov(syndrome_disks+2,
conf->stripe_size, faila,
- blocks, &submit);
+ blocks, offs, &submit);
} else {
/* We're missing D+D. */
return async_raid6_2data_recov(syndrome_disks+2,
conf->stripe_size,
faila, failb,
- blocks, &submit);
+ blocks, offs, &submit);
}
}
}
@@ -1810,6 +1830,7 @@ ops_run_prexor6(struct stripe_head *sh, struct raid5_percpu *percpu,
struct dma_async_tx_descriptor *tx)
{
struct page **blocks = to_addr_page(percpu, 0);
+ unsigned int *offs = to_addr_offs(sh, percpu);
int count;
struct async_submit_ctl submit;
struct r5conf *conf = sh->raid_conf;
@@ -1817,12 +1838,12 @@ ops_run_prexor6(struct stripe_head *sh, struct raid5_percpu *percpu,
pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
- count = set_syndrome_sources(blocks, sh, SYNDROME_SRC_WANT_DRAIN);
+ count = set_syndrome_sources(blocks, offs, sh, SYNDROME_SRC_WANT_DRAIN);
init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_PQ_XOR_DST, tx,
ops_complete_prexor, sh, to_addr_conv(sh, percpu, 0));
- tx = async_gen_syndrome(blocks, 0, count+2,
- conf->stripe_size, &submit);
+ tx = async_gen_syndrome(blocks, offs, count+2,
+ conf->stripe_size, &submit);
return tx;
}
@@ -2054,6 +2075,7 @@ ops_run_reconstruct6(struct stripe_head *sh, struct raid5_percpu *percpu,
{
struct async_submit_ctl submit;
struct page **blocks;
+ unsigned int *offs;
int count, i, j = 0;
struct stripe_head *head_sh = sh;
int last_stripe;
@@ -2079,6 +2101,7 @@ ops_run_reconstruct6(struct stripe_head *sh, struct raid5_percpu *percpu,
again:
blocks = to_addr_page(percpu, j);
+ offs = to_addr_offs(sh, percpu);
if (sh->reconstruct_state == reconstruct_state_prexor_drain_run) {
synflags = SYNDROME_SRC_WRITTEN;
@@ -2088,7 +2111,7 @@ ops_run_reconstruct6(struct stripe_head *sh, struct raid5_percpu *percpu,
txflags = ASYNC_TX_ACK;
}
- count = set_syndrome_sources(blocks, sh, synflags);
+ count = set_syndrome_sources(blocks, offs, sh, synflags);
last_stripe = !head_sh->batch_head ||
list_first_entry(&sh->batch_list,
struct stripe_head, batch_list) == head_sh;
@@ -2100,8 +2123,8 @@ ops_run_reconstruct6(struct stripe_head *sh, struct raid5_percpu *percpu,
} else
init_async_submit(&submit, 0, tx, NULL, NULL,
to_addr_conv(sh, percpu, j));
- tx = async_gen_syndrome(blocks, 0, count+2,
- conf->stripe_size, &submit);
+ tx = async_gen_syndrome(blocks, offs, count+2,
+ conf->stripe_size, &submit);
if (!last_stripe) {
j++;
sh = list_first_entry(&sh->batch_list, struct stripe_head,
@@ -2168,6 +2191,7 @@ static void ops_run_check_p(struct stripe_head *sh, struct raid5_percpu *percpu)
static void ops_run_check_pq(struct stripe_head *sh, struct raid5_percpu *percpu, int checkp)
{
struct page **srcs = to_addr_page(percpu, 0);
+ unsigned int *offs = to_addr_offs(sh, percpu);
struct async_submit_ctl submit;
int count;
struct r5conf *conf = sh->raid_conf;
@@ -2176,15 +2200,16 @@ static void ops_run_check_pq(struct stripe_head *sh, struct raid5_percpu *percpu
(unsigned long long)sh->sector, checkp);
BUG_ON(sh->batch_head);
- count = set_syndrome_sources(srcs, sh, SYNDROME_SRC_ALL);
+ count = set_syndrome_sources(srcs, offs, sh, SYNDROME_SRC_ALL);
if (!checkp)
srcs[count] = NULL;
atomic_inc(&sh->count);
init_async_submit(&submit, ASYNC_TX_ACK, NULL, ops_complete_check,
sh, to_addr_conv(sh, percpu, 0));
- async_syndrome_val(srcs, 0, count+2, conf->stripe_size,
- &sh->ops.zero_sum_result, percpu->spare_page, &submit);
+ async_syndrome_val(srcs, offs, count+2, conf->stripe_size,
+ &sh->ops.zero_sum_result,
+ percpu->spare_page, 0, &submit);
}
static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
--
2.25.4
^ permalink raw reply related [flat|nested] 19+ messages in thread* [PATCH v6 15/15] raid6test: adaptation with syndrome function
2020-07-15 12:42 [PATCH v6 00/15] md/raid5: set STRIPE_SIZE as a configurable value Yufen Yu
` (13 preceding siblings ...)
2020-07-15 12:42 ` [PATCH v6 14/15] md/raid6: compute syndrome with correct " Yufen Yu
@ 2020-07-15 12:42 ` Yufen Yu
2020-07-16 7:20 ` [PATCH v6 00/15] md/raid5: set STRIPE_SIZE as a configurable value Song Liu
15 siblings, 0 replies; 19+ messages in thread
From: Yufen Yu @ 2020-07-15 12:42 UTC (permalink / raw)
To: song; +Cc: linux-raid, neilb, guoqing.jiang, houtao1, yuyufen
After changing some syndrome and recovery functions to support
different page offsets, we also need to adapt raid6test module.
In this module, pages are allocated by the itself and their offset
are '0'.
Signed-off-by: Yufen Yu <yuyufen@huawei.com>
---
crypto/async_tx/raid6test.c | 24 ++++++++++++++++--------
1 file changed, 16 insertions(+), 8 deletions(-)
diff --git a/crypto/async_tx/raid6test.c b/crypto/async_tx/raid6test.c
index 14e73dcd7475..66db82e5a3b1 100644
--- a/crypto/async_tx/raid6test.c
+++ b/crypto/async_tx/raid6test.c
@@ -18,6 +18,7 @@
#define NDISKS 64 /* Including P and Q */
static struct page *dataptrs[NDISKS];
+unsigned int dataoffs[NDISKS];
static addr_conv_t addr_conv[NDISKS];
static struct page *data[NDISKS+3];
static struct page *spare;
@@ -38,6 +39,7 @@ static void makedata(int disks)
for (i = 0; i < disks; i++) {
prandom_bytes(page_address(data[i]), PAGE_SIZE);
dataptrs[i] = data[i];
+ dataoffs[i] = 0;
}
}
@@ -52,7 +54,8 @@ static char disk_type(int d, int disks)
}
/* Recover two failed blocks. */
-static void raid6_dual_recov(int disks, size_t bytes, int faila, int failb, struct page **ptrs)
+static void raid6_dual_recov(int disks, size_t bytes, int faila, int failb,
+ struct page **ptrs, unsigned int *offs)
{
struct async_submit_ctl submit;
struct completion cmp;
@@ -66,7 +69,8 @@ static void raid6_dual_recov(int disks, size_t bytes, int faila, int failb, stru
if (faila == disks-2) {
/* P+Q failure. Just rebuild the syndrome. */
init_async_submit(&submit, 0, NULL, NULL, NULL, addr_conv);
- tx = async_gen_syndrome(ptrs, 0, disks, bytes, &submit);
+ tx = async_gen_syndrome(ptrs, offs,
+ disks, bytes, &submit);
} else {
struct page *blocks[NDISKS];
struct page *dest;
@@ -89,22 +93,26 @@ static void raid6_dual_recov(int disks, size_t bytes, int faila, int failb, stru
tx = async_xor(dest, blocks, 0, count, bytes, &submit);
init_async_submit(&submit, 0, tx, NULL, NULL, addr_conv);
- tx = async_gen_syndrome(ptrs, 0, disks, bytes, &submit);
+ tx = async_gen_syndrome(ptrs, offs,
+ disks, bytes, &submit);
}
} else {
if (failb == disks-2) {
/* data+P failure. */
init_async_submit(&submit, 0, NULL, NULL, NULL, addr_conv);
- tx = async_raid6_datap_recov(disks, bytes, faila, ptrs, &submit);
+ tx = async_raid6_datap_recov(disks, bytes,
+ faila, ptrs, offs, &submit);
} else {
/* data+data failure. */
init_async_submit(&submit, 0, NULL, NULL, NULL, addr_conv);
- tx = async_raid6_2data_recov(disks, bytes, faila, failb, ptrs, &submit);
+ tx = async_raid6_2data_recov(disks, bytes,
+ faila, failb, ptrs, offs, &submit);
}
}
init_completion(&cmp);
init_async_submit(&submit, ASYNC_TX_ACK, tx, callback, &cmp, addr_conv);
- tx = async_syndrome_val(ptrs, 0, disks, bytes, &result, spare, &submit);
+ tx = async_syndrome_val(ptrs, offs,
+ disks, bytes, &result, spare, 0, &submit);
async_tx_issue_pending(tx);
if (wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000)) == 0)
@@ -126,7 +134,7 @@ static int test_disks(int i, int j, int disks)
dataptrs[i] = recovi;
dataptrs[j] = recovj;
- raid6_dual_recov(disks, PAGE_SIZE, i, j, dataptrs);
+ raid6_dual_recov(disks, PAGE_SIZE, i, j, dataptrs, dataoffs);
erra = memcmp(page_address(data[i]), page_address(recovi), PAGE_SIZE);
errb = memcmp(page_address(data[j]), page_address(recovj), PAGE_SIZE);
@@ -162,7 +170,7 @@ static int test(int disks, int *tests)
/* Generate assumed good syndrome */
init_completion(&cmp);
init_async_submit(&submit, ASYNC_TX_ACK, NULL, callback, &cmp, addr_conv);
- tx = async_gen_syndrome(dataptrs, 0, disks, PAGE_SIZE, &submit);
+ tx = async_gen_syndrome(dataptrs, dataoffs, disks, PAGE_SIZE, &submit);
async_tx_issue_pending(tx);
if (wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000)) == 0) {
--
2.25.4
^ permalink raw reply related [flat|nested] 19+ messages in thread* Re: [PATCH v6 00/15] md/raid5: set STRIPE_SIZE as a configurable value
2020-07-15 12:42 [PATCH v6 00/15] md/raid5: set STRIPE_SIZE as a configurable value Yufen Yu
` (14 preceding siblings ...)
2020-07-15 12:42 ` [PATCH v6 15/15] raid6test: adaptation with syndrome function Yufen Yu
@ 2020-07-16 7:20 ` Song Liu
2020-07-16 14:01 ` Yufen Yu
15 siblings, 1 reply; 19+ messages in thread
From: Song Liu @ 2020-07-16 7:20 UTC (permalink / raw)
To: Yufen Yu; +Cc: linux-raid, NeilBrown, Guoqing Jiang, Hou Tao
On Wed, Jul 15, 2020 at 5:42 AM Yufen Yu <yuyufen@huawei.com> wrote:
>
> Hi, all
>
> For now, STRIPE_SIZE is equal to the value of PAGE_SIZE. That means, RAID5
> will issue each bio to disk at least 64KB when PAGE_SIZE is 64KB in arm64.
> However, filesystem usually issue bio in the unit of 4KB. Then, RAID5 may
> waste resource of disk bandwidth.
>
> To solve the problem, this patchset try to set stripe_size as a configuare
> value. The default value is 4096. We will add a new sysfs entry and set it
> by writing a new value, likely:
>
> echo 16384 > /sys/block/md1/md/stripe_size
[...]
> V6:
> * Convert stripe_size and stripe_sectors from 'unsigned int' to
> 'unsigned long' avoiding compiler warning.
> * Add a new member of stripes_per_page into r5conf, avoiding to
> compute each time.
> * Cover mddev->private with mddev_lock(mddev) for raid5_store/show_stripe_size().
> * Get rid of too many WARN_ON() and BUG_ON().
> * Unfold raid5_get_page_index() into raid5_get_dev_page() directly.
We are running out of time before the upcoming merge window, so we may not
be able to ship the whole set. How about we ship 01, and 11 in this
merge window,
and the rest in the next merge window? Would the array get most of the
performance benefit with these 2 patches? Do you see other issues with
this path?
Also I would like to minimize changes for PAGE_SIZE==4096 systems. Ideally,
we can hide these changes from these system in ifdef's, like:
#if PAGE_SIZE == DEFAULT_STRIPE_SIZE
#define STRIPE_SIZE PAGE_SIZE
#define STRIPE_SHIFT (PAGE_SHIFT - 9)
#define STRIPE_SECTORS (STRIPE_SIZE>>9)
#endif
#if PAGE_SIZE != DEFAULT_STRIPE_SIZE
unsigned long stripe_size;
unsigned int stripe_shift;
unsigned long stripe_sectors;
#endif
#if PAGE_SIZE != DEFAULT_STRIPE_SIZE
#define RAID5_STRIPE_SIZE(conf) DEFAULT_STRIPE_SIZE
#else
#define RAID5_STRIPE_SIZE(conf) ((conf)->stripe_size)
#endif
And then use RAID5_STRIPE_SIZE(conf) in the rest of the code.
Thanks,
Song
^ permalink raw reply [flat|nested] 19+ messages in thread* Re: [PATCH v6 00/15] md/raid5: set STRIPE_SIZE as a configurable value
2020-07-16 7:20 ` [PATCH v6 00/15] md/raid5: set STRIPE_SIZE as a configurable value Song Liu
@ 2020-07-16 14:01 ` Yufen Yu
0 siblings, 0 replies; 19+ messages in thread
From: Yufen Yu @ 2020-07-16 14:01 UTC (permalink / raw)
To: Song Liu; +Cc: linux-raid, NeilBrown, Guoqing Jiang, Hou Tao
On 2020/7/16 15:20, Song Liu wrote:
> On Wed, Jul 15, 2020 at 5:42 AM Yufen Yu <yuyufen@huawei.com> wrote:
>>
>> Hi, all
>>
>> For now, STRIPE_SIZE is equal to the value of PAGE_SIZE. That means, RAID5
>> will issue each bio to disk at least 64KB when PAGE_SIZE is 64KB in arm64.
>> However, filesystem usually issue bio in the unit of 4KB. Then, RAID5 may
>> waste resource of disk bandwidth.
>>
>> To solve the problem, this patchset try to set stripe_size as a configuare
>> value. The default value is 4096. We will add a new sysfs entry and set it
>> by writing a new value, likely:
>>
>> echo 16384 > /sys/block/md1/md/stripe_size
>
> [...]
>
>> V6:
>> * Convert stripe_size and stripe_sectors from 'unsigned int' to
>> 'unsigned long' avoiding compiler warning.
>> * Add a new member of stripes_per_page into r5conf, avoiding to
>> compute each time.
>> * Cover mddev->private with mddev_lock(mddev) for raid5_store/show_stripe_size().
>> * Get rid of too many WARN_ON() and BUG_ON().
>> * Unfold raid5_get_page_index() into raid5_get_dev_page() directly.
>
> We are running out of time before the upcoming merge window, so we may not
> be able to ship the whole set. How about we ship 01, and 11 in this
> merge window,
> and the rest in the next merge window? Would the array get most of the
> performance benefit with these 2 patches? Do you see other issues with
> this path?
>
This patchset includes two optimization, dynamically adjust stripe_size to improve
raid array performance and save memory used by stripe_head. If you think we may not
be able to ship the the whole set, I think just ship the first optimization (patch 01
and patch 11) can get better performance.
I will send the first optimization with adopting your suggestion as soon as possible.
Thanks a lot for your review.
Thanks,
Yufen
> Also I would like to minimize changes for PAGE_SIZE==4096 systems. Ideally,
> we can hide these changes from these system in ifdef's, like:
>
> #if PAGE_SIZE == DEFAULT_STRIPE_SIZE
> #define STRIPE_SIZE PAGE_SIZE
> #define STRIPE_SHIFT (PAGE_SHIFT - 9)
> #define STRIPE_SECTORS (STRIPE_SIZE>>9)
> #endif
>
> #if PAGE_SIZE != DEFAULT_STRIPE_SIZE
> unsigned long stripe_size;
> unsigned int stripe_shift;
> unsigned long stripe_sectors;
> #endif
>
> #if PAGE_SIZE != DEFAULT_STRIPE_SIZE
> #define RAID5_STRIPE_SIZE(conf) DEFAULT_STRIPE_SIZE
> #else
> #define RAID5_STRIPE_SIZE(conf) ((conf)->stripe_size)
> #endif
>
> And then use RAID5_STRIPE_SIZE(conf) in the rest of the code.
>
> Thanks,
> Song
> .
>
^ permalink raw reply [flat|nested] 19+ messages in thread