zram: use atomic operation for stat
Some of fields in zram->stats are protected by zram->lock which is rather coarse-grained so let's use atomic operation without explict locking. This patch is ready for removing dependency of zram->lock in read path which is very coarse-grained rw_semaphore. Of course, this patch adds new atomic operation so it might make slow but my 12CPU test couldn't spot any regression. All gain/lose is marginal within stddev. iozone -t -T -l 12 -u 12 -r 16K -s 60M -I +Z -V 0 ==Initial write ==Initial write records: 50 records: 50 avg: 412875.17 avg: 415638.23 std: 38543.12 (9.34%) std: 36601.11 (8.81%) max: 521262.03 max: 502976.72 min: 343263.13 min: 351389.12 ==Rewrite ==Rewrite records: 50 records: 50 avg: 416640.34 avg: 397914.33 std: 60798.92 (14.59%) std: 46150.42 (11.60%) max: 543057.07 max: 522669.17 min: 304071.67 min: 316588.77 ==Read ==Read records: 50 records: 50 avg: 4147338.63 avg: 4070736.51 std: 179333.25 (4.32%) std: 223499.89 (5.49%) max: 4459295.28 max: 4539514.44 min: 3753057.53 min: 3444686.31 ==Re-read ==Re-read records: 50 records: 50 avg: 4096706.71 avg: 4117218.57 std: 229735.04 (5.61%) std: 171676.25 (4.17%) max: 4430012.09 max: 4459263.94 min: 2987217.80 min: 3666904.28 ==Reverse Read ==Reverse Read records: 50 records: 50 avg: 4062763.83 avg: 4078508.32 std: 186208.46 (4.58%) std: 172684.34 (4.23%) max: 4401358.78 max: 4424757.22 min: 3381625.00 min: 3679359.94 ==Stride read ==Stride read records: 50 records: 50 avg: 4094933.49 avg: 4082170.22 std: 185710.52 (4.54%) std: 196346.68 (4.81%) max: 4478241.25 max: 4460060.97 min: 3732593.23 min: 3584125.78 ==Random read ==Random read records: 50 records: 50 avg: 4031070.04 avg: 4074847.49 std: 192065.51 (4.76%) std: 206911.33 (5.08%) max: 4356931.16 max: 4399442.56 min: 3481619.62 min: 3548372.44 ==Mixed workload ==Mixed workload records: 50 records: 50 avg: 149925.73 avg: 149675.54 std: 7701.26 (5.14%) std: 6902.09 (4.61%) max: 191301.56 max: 175162.05 min: 133566.28 min: 137762.87 ==Random write ==Random write records: 50 records: 50 avg: 404050.11 avg: 393021.47 std: 58887.57 (14.57%) std: 42813.70 (10.89%) max: 601798.09 max: 524533.43 min: 325176.99 min: 313255.34 ==Pwrite ==Pwrite records: 50 records: 50 avg: 411217.70 avg: 411237.96 std: 43114.99 (10.48%) std: 33136.29 (8.06%) max: 530766.79 max: 471899.76 min: 320786.84 min: 317906.94 ==Pread ==Pread records: 50 records: 50 avg: 4154908.65 avg: 4087121.92 std: 151272.08 (3.64%) std: 219505.04 (5.37%) max: 4459478.12 max: 4435857.38 min: 3730512.41 min: 3101101.67 Signed-off-by: Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Tested-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Jerome Marchand <jmarchan@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
Minchan Kim
Linus Torvalds
parent
874e3cddc3
commit
deb0bdeb2f
|
|
@ -104,7 +104,7 @@ static ssize_t zero_pages_show(struct device *dev,
|
|||
{
|
||||
struct zram *zram = dev_to_zram(dev);
|
||||
|
||||
return sprintf(buf, "%u\n", zram->stats.pages_zero);
|
||||
return sprintf(buf, "%u\n", atomic_read(&zram->stats.pages_zero));
|
||||
}
|
||||
|
||||
static ssize_t orig_data_size_show(struct device *dev,
|
||||
|
|
@ -113,7 +113,7 @@ static ssize_t orig_data_size_show(struct device *dev,
|
|||
struct zram *zram = dev_to_zram(dev);
|
||||
|
||||
return sprintf(buf, "%llu\n",
|
||||
(u64)(zram->stats.pages_stored) << PAGE_SHIFT);
|
||||
(u64)(atomic_read(&zram->stats.pages_stored)) << PAGE_SHIFT);
|
||||
}
|
||||
|
||||
static ssize_t compr_data_size_show(struct device *dev,
|
||||
|
|
@ -293,21 +293,21 @@ static void zram_free_page(struct zram *zram, size_t index)
|
|||
*/
|
||||
if (zram_test_flag(meta, index, ZRAM_ZERO)) {
|
||||
zram_clear_flag(meta, index, ZRAM_ZERO);
|
||||
zram->stats.pages_zero--;
|
||||
atomic_dec(&zram->stats.pages_zero);
|
||||
}
|
||||
return;
|
||||
}
|
||||
|
||||
if (unlikely(size > max_zpage_size))
|
||||
zram->stats.bad_compress--;
|
||||
atomic_dec(&zram->stats.bad_compress);
|
||||
|
||||
zs_free(meta->mem_pool, handle);
|
||||
|
||||
if (size <= PAGE_SIZE / 2)
|
||||
zram->stats.good_compress--;
|
||||
atomic_dec(&zram->stats.good_compress);
|
||||
|
||||
atomic64_sub(meta->table[index].size, &zram->stats.compr_size);
|
||||
zram->stats.pages_stored--;
|
||||
atomic_dec(&zram->stats.pages_stored);
|
||||
|
||||
meta->table[index].handle = 0;
|
||||
meta->table[index].size = 0;
|
||||
|
|
@ -435,7 +435,7 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
|
|||
/* Free memory associated with this sector now. */
|
||||
zram_free_page(zram, index);
|
||||
|
||||
zram->stats.pages_zero++;
|
||||
atomic_inc(&zram->stats.pages_zero);
|
||||
zram_set_flag(meta, index, ZRAM_ZERO);
|
||||
ret = 0;
|
||||
goto out;
|
||||
|
|
@ -456,7 +456,7 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
|
|||
}
|
||||
|
||||
if (unlikely(clen > max_zpage_size)) {
|
||||
zram->stats.bad_compress++;
|
||||
atomic_inc(&zram->stats.bad_compress);
|
||||
clen = PAGE_SIZE;
|
||||
src = NULL;
|
||||
if (is_partial_io(bvec))
|
||||
|
|
@ -493,9 +493,9 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
|
|||
|
||||
/* Update stats */
|
||||
atomic64_add(clen, &zram->stats.compr_size);
|
||||
zram->stats.pages_stored++;
|
||||
atomic_inc(&zram->stats.pages_stored);
|
||||
if (clen <= PAGE_SIZE / 2)
|
||||
zram->stats.good_compress++;
|
||||
atomic_inc(&zram->stats.good_compress);
|
||||
|
||||
out:
|
||||
if (is_partial_io(bvec))
|
||||
|
|
|
|||
|
|
@ -68,10 +68,6 @@ struct table {
|
|||
u8 flags;
|
||||
} __aligned(4);
|
||||
|
||||
/*
|
||||
* All 64bit fields should only be manipulated by 64bit atomic accessors.
|
||||
* All modifications to 32bit counter should be protected by zram->lock.
|
||||
*/
|
||||
struct zram_stats {
|
||||
atomic64_t compr_size; /* compressed size of pages stored */
|
||||
atomic64_t num_reads; /* failed + successful */
|
||||
|
|
@ -80,10 +76,10 @@ struct zram_stats {
|
|||
atomic64_t failed_writes; /* can happen when memory is too low */
|
||||
atomic64_t invalid_io; /* non-page-aligned I/O requests */
|
||||
atomic64_t notify_free; /* no. of swap slot free notifications */
|
||||
u32 pages_zero; /* no. of zero filled pages */
|
||||
u32 pages_stored; /* no. of pages currently stored */
|
||||
u32 good_compress; /* % of pages with compression ratio<=50% */
|
||||
u32 bad_compress; /* % of pages with compression ratio>=75% */
|
||||
atomic_t pages_zero; /* no. of zero filled pages */
|
||||
atomic_t pages_stored; /* no. of pages currently stored */
|
||||
atomic_t good_compress; /* % of pages with compression ratio<=50% */
|
||||
atomic_t bad_compress; /* % of pages with compression ratio>=75% */
|
||||
};
|
||||
|
||||
struct zram_meta {
|
||||
|
|
@ -101,8 +97,8 @@ struct zram_slot_free {
|
|||
struct zram {
|
||||
struct zram_meta *meta;
|
||||
struct rw_semaphore lock; /* protect compression buffers, table,
|
||||
* 32bit stat counters against concurrent
|
||||
* notifications, reads and writes */
|
||||
* reads and writes
|
||||
*/
|
||||
|
||||
struct work_struct free_work; /* handle pending free request */
|
||||
struct zram_slot_free *slot_free_rq; /* list head of free request */
|
||||
|
|
|
|||
Loading…
Reference in New Issue