Add some sysfs entries.
-cache_memory. Control the cache memory size.
-cache_reclaim_batch. Control how many stripes reclaim should run in one
time.
-cache_memory_watermark. The background reclaim runs if cache memory
hits the watermark and stops after hit 1.5x of the watermark.
-cache_disk_watermark. The background reclaim runs if cache disk space
hits the watermark and stops after hit 1.5x of the watermark.
-cache_stat. statistics about cache.
Signed-off-by: Shaohua Li <shli@xxxxxx>
---
drivers/md/raid5-cache.c | 299 ++++++++++++++++++++++++++++++++++++++++++++++-
drivers/md/raid5.c | 3 +
drivers/md/raid5.h | 1 +
3 files changed, 302 insertions(+), 1 deletion(-)
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index 143f333..332230a 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -352,6 +352,12 @@ struct r5c_cache {
struct kmem_cache *io_range_kc;
struct kmem_cache *stripe_kc;
struct bio_set *bio_set;
+
+ atomic64_t in_cache_rq;
+ atomic64_t out_cache_rq;
+ atomic64_t in_cache_sectors;
+ atomic64_t out_cache_sectors;
+ atomic64_t read_cache_sectors;
};
/* reclaim reason */
@@ -405,6 +411,12 @@ static inline int r5l_page_blocks(struct r5l_log *log, int pages)
return pages << log->page_block_shift;
}
+static inline int r5l_max_flush_stripes(struct r5l_log *log)
+{
+ return (log->block_size - sizeof(struct r5l_flush_block)) /
+ sizeof(__le64);
+}
+
static u32 r5l_calculate_checksum(struct r5l_log *log, u32 crc,
void *buf, size_t size, bool data)
{
@@ -1804,6 +1816,9 @@ static void r5c_write_bio(struct r5c_cache *cache, struct bio *bio)
stripe->existing_pages += new_pages;
r5c_unlock_stripe(cache, stripe, &flags);
+ atomic64_inc(&cache->in_cache_rq);
+ atomic64_add(bio_sectors(bio), &cache->in_cache_sectors);
+
if (r5l_queue_bio(&cache->log, bio, r5c_bio_task_end, io_range,
reserved_blocks))
goto put_error;
@@ -1852,6 +1867,8 @@ static void r5c_read_bio(struct r5c_cache *cache, struct bio *bio)
split = bio;
r5c_copy_bio(split, &stripe->data_pages[start], true);
+ atomic64_add(bio_sectors(split),
+ &cache->read_cache_sectors);
bio_endio(split, 0);
@@ -2010,6 +2027,10 @@ static void r5c_flush_one(struct r5c_cache *cache, struct r5c_stripe *stripe,
bio->bi_end_io = r5c_flush_endio;
bio->bi_rw = WRITE;
atomic_inc(&stripe->pending_bios);
+
+ atomic64_inc(&cache->out_cache_rq);
+ atomic64_add(bio_sectors(bio), &cache->out_cache_sectors);
+
raid5_make_request(cache->mddev, bio);
}
}
@@ -3310,6 +3331,278 @@ static int r5c_shrink_cache_memory(struct r5c_cache *cache, unsigned long size)
return 0;
}
+static ssize_t r5c_show_cache_memory(struct mddev *mddev, char *page)
+{
+ struct r5conf *conf = mddev->private;
+ struct r5c_cache *cache = conf->cache;
+
+ return sprintf(page, "%lld\n", cache->max_pages << PAGE_SHIFT);
+}
+
+static ssize_t r5c_store_cache_memory(struct mddev *mddev, const char *page,
+ size_t len)
+{
+ struct r5conf *conf = mddev->private;
+ struct r5c_cache *cache = conf->cache;
+ unsigned long new;
+ LIST_HEAD(page_list);
+ u64 i;
+
+ if (len >= PAGE_SIZE)
+ return -EINVAL;
+ if (kstrtoul(page, 0, &new))
+ return -EINVAL;
+ new >>= PAGE_SHIFT;
+
+ if (new > cache->max_pages) {
+ i = cache->max_pages;
+ while (i < new) {
+ struct page *page = alloc_page(GFP_KERNEL);
+
+ if (!page)
+ break;
+ list_add(&page->lru, &page_list);
+ i++;
+ }
+
+ spin_lock_irq(&cache->pool_lock);
+ list_splice(&page_list, &cache->page_pool);
+ cache->free_pages += i - cache->max_pages;
+ cache->max_pages = i;
+ cache->total_pages = i;
+ r5c_calculate_watermark(cache);
+ spin_unlock_irq(&cache->pool_lock);
+ return len;
+ }
+ r5c_shrink_cache_memory(cache, new);
+ return len;
+}
+
+static struct md_sysfs_entry r5c_cache_memory = __ATTR(cache_memory,
+ S_IRUGO | S_IWUSR, r5c_show_cache_memory, r5c_store_cache_memory);
+
+/*
+ * we reclaim stripes in a batch way, so we must make sure there are enough
+ * stripe cache. Otherwise, reclaim will deadlock to wait some stripe caches
+ * free, but such stripe caches don't even run since reclaim is waitting
+ * */
+int r5c_min_stripe_cache_size(struct r5c_cache *cache)
+{
+ struct r5conf *conf = cache->mddev->private;
+ return (conf->chunk_sectors >> PAGE_SECTOR_SHIFT) *
+ cache->reclaim_batch;
+}
+
+static void r5c_set_reclaim_batch(struct r5c_cache *cache, int batch)
+{
+ struct mddev *mddev = cache->mddev;
+ struct r5conf *conf = mddev->private;
+ int size;
+
+ size = (cache->stripe_parity_pages << PAGE_SECTOR_SHIFT) * batch;
+ if (size > cache->reserved_space) {
+ cache->reserved_space = size;
+ mutex_lock(&cache->log.io_mutex);
+ cache->log.reserved_blocks = r5l_sector_to_block(&cache->log,
+ cache->reserved_space) + 1;
+ mutex_unlock(&cache->log.io_mutex);
+ r5c_wake_wait_reclaimer(cache,
+ RECLAIM_DISK_BACKGROUND);
+ } else {
+ mutex_lock(&cache->log.io_mutex);
+ cache->log.reserved_blocks -= r5l_sector_to_block(&cache->log,
+ cache->reserved_space - size);
+ mutex_unlock(&cache->log.io_mutex);
+ cache->reserved_space = size;
+ }
+
+ size = (conf->chunk_sectors >> PAGE_SECTOR_SHIFT) * batch;
+
+ mddev_lock(mddev);
+ if (size > conf->max_nr_stripes)
+ raid5_set_cache_size(mddev, size);
+ mddev_unlock(mddev);
+
+ cache->reclaim_batch = batch;
+}
+
+static ssize_t r5c_show_cache_reclaim_batch(struct mddev *mddev, char *page)
+{
+ struct r5conf *conf = mddev->private;
+ struct r5c_cache *cache = conf->cache;
+
+ return sprintf(page, "%d\n", cache->reclaim_batch);
+}
+
+static ssize_t r5c_store_cache_reclaim_batch(struct mddev *mddev,
+ const char *page, size_t len)
+{
+ struct r5conf *conf = mddev->private;
+ struct r5c_cache *cache = conf->cache;
+ unsigned long new;
+
+ if (len >= PAGE_SIZE)
+ return -EINVAL;
+ if (kstrtoul(page, 0, &new))
+ return -EINVAL;
+
+ if (new > r5l_max_flush_stripes(&cache->log))
+ new = r5l_max_flush_stripes(&cache->log);
+
+ if (new != cache->reclaim_batch)
+ r5c_set_reclaim_batch(cache, new);
+ return len;
+}
+
+static struct md_sysfs_entry r5c_cache_reclaim_batch =
+ __ATTR(cache_reclaim_batch, S_IRUGO | S_IWUSR,
+ r5c_show_cache_reclaim_batch, r5c_store_cache_reclaim_batch);
+
+static ssize_t r5c_show_cache_stat(struct mddev *mddev, char *page)
+{
+ struct r5conf *conf = mddev->private;
+ struct r5c_cache *cache = conf->cache;
+
+ return sprintf(page, "%lld %lld %lld %lld %lld\n",
+ (u64)atomic64_read(&cache->in_cache_rq),
+ (u64)atomic64_read(&cache->in_cache_sectors),
+ (u64)atomic64_read(&cache->out_cache_rq),
+ (u64)atomic64_read(&cache->out_cache_sectors),
+ (u64)atomic64_read(&cache->read_cache_sectors));
+}
+
+static struct md_sysfs_entry r5c_cache_stat =
+ __ATTR(cache_stat, S_IRUGO, r5c_show_cache_stat, NULL);
+
+static ssize_t r5c_show_cache_disk_watermark(struct mddev *mddev, char *page)
+{
+ struct r5conf *conf = mddev->private;
+ struct r5c_cache *cache = conf->cache;
+
+ return sprintf(page, "%lld\n", cache->log.low_watermark *
+ cache->log.block_size);
+}
+
+static ssize_t r5c_store_cache_disk_watermark(struct mddev *mddev,
+ const char *page, size_t len)
+{
+ struct r5conf *conf = mddev->private;
+ struct r5c_cache *cache = conf->cache;
+ struct r5l_log *log = &cache->log;
+ unsigned long new;
+
+ if (len >= PAGE_SIZE)
+ return -EINVAL;
+ if (kstrtoul(page, 0, &new))
+ return -EINVAL;
+ new /= log->block_size;
+
+ if (new * 3 / 2 >= log->total_blocks)
+ return -EINVAL;
+
+ mutex_lock(&log->io_mutex);
+ log->low_watermark = new;
+ log->high_watermark = new * 3 / 2;
+ mutex_unlock(&log->io_mutex);
+ return len;
+}
+
+static struct md_sysfs_entry r5c_cache_disk_watermark =
+ __ATTR(cache_disk_watermark, S_IRUGO | S_IWUSR,
+ r5c_show_cache_disk_watermark, r5c_store_cache_disk_watermark);
+
+static ssize_t r5c_show_cache_memory_watermark(struct mddev *mddev, char *page)
+{
+ struct r5conf *conf = mddev->private;
+ struct r5c_cache *cache = conf->cache;
+
+ return sprintf(page, "%lld\n", cache->low_watermark << PAGE_SHIFT);
+}
+
+static ssize_t r5c_store_cache_memory_watermark(struct mddev *mddev,
+ const char *page, size_t len)
+{
+ struct r5conf *conf = mddev->private;
+ struct r5c_cache *cache = conf->cache;
+ unsigned long new;
+
+ if (len >= PAGE_SIZE)
+ return -EINVAL;
+ if (kstrtoul(page, 0, &new))
+ return -EINVAL;
+ new >>= PAGE_SHIFT;
+
+ if (new * 2 >= cache->max_pages)
+ return -EINVAL;
+
+ spin_lock_irq(&cache->pool_lock);
+ cache->low_watermark = new;
+ cache->high_watermark = new << 1;
+ spin_unlock_irq(&cache->pool_lock);
+ return len;
+}
+
+static struct md_sysfs_entry r5c_cache_memory_watermark =
+ __ATTR(cache_memory_watermark, S_IRUGO | S_IWUSR,
+ r5c_show_cache_memory_watermark, r5c_store_cache_memory_watermark);
+
+static int r5c_init_sysfs(struct r5c_cache *cache)
+{
+ struct mddev *mddev = cache->mddev;
+ int ret;
+
+ ret = sysfs_add_file_to_group(&mddev->kobj, &r5c_cache_memory.attr,
+ NULL);
+ if (ret)
+ return ret;
+ ret = sysfs_add_file_to_group(&mddev->kobj,
+ &r5c_cache_reclaim_batch.attr, NULL);
+ if (ret)
+ goto err_reclaim;
+ ret = sysfs_add_file_to_group(&mddev->kobj,
+ &r5c_cache_disk_watermark.attr, NULL);
+ if (ret)
+ goto disk_watermark;
+ ret = sysfs_add_file_to_group(&mddev->kobj,
+ &r5c_cache_stat.attr, NULL);
+ if (ret)
+ goto stat;
+
+ ret = sysfs_add_file_to_group(&mddev->kobj,
+ &r5c_cache_memory_watermark.attr, NULL);
+ if (ret)
+ goto memory_watermark;
+ return 0;
+memory_watermark:
+ sysfs_remove_file_from_group(&mddev->kobj,
+ &r5c_cache_stat.attr, NULL);
+stat:
+ sysfs_remove_file_from_group(&mddev->kobj,
+ &r5c_cache_disk_watermark.attr, NULL);
+disk_watermark:
+ sysfs_remove_file_from_group(&mddev->kobj,
+ &r5c_cache_reclaim_batch.attr, NULL);
+err_reclaim:
+ sysfs_remove_file_from_group(&mddev->kobj,
+ &r5c_cache_memory.attr, NULL);
+ return ret;
+}
+
+static void r5c_exit_sysfs(struct r5c_cache *cache)
+{
+ struct mddev *mddev = cache->mddev;
+ sysfs_remove_file_from_group(&mddev->kobj,
+ &r5c_cache_reclaim_batch.attr, NULL);
+ sysfs_remove_file_from_group(&mddev->kobj,
+ &r5c_cache_memory.attr, NULL);
+ sysfs_remove_file_from_group(&mddev->kobj,
+ &r5c_cache_disk_watermark.attr, NULL);
+ sysfs_remove_file_from_group(&mddev->kobj,
+ &r5c_cache_stat.attr, NULL);
+ sysfs_remove_file_from_group(&mddev->kobj,
+ &r5c_cache_memory_watermark.attr, NULL);
+}
+
static void r5c_free_cache_data(struct r5c_cache *cache)
{
struct r5c_stripe *stripe;
@@ -3420,8 +3713,11 @@ struct r5c_cache *r5c_init_cache(struct r5conf *conf, struct md_rdev *rdev)
cache->reclaim_thread->timeout = CHECKPOINT_TIMEOUT;
r5c_shrink_cache_memory(cache, cache->max_pages);
-
+ if (r5c_init_sysfs(cache))
+ goto err_sysfs;
return cache;
+err_sysfs:
+ md_unregister_thread(&cache->reclaim_thread);
err_page:
r5c_free_cache_data(cache);
@@ -3440,6 +3736,7 @@ struct r5c_cache *r5c_init_cache(struct r5conf *conf, struct md_rdev *rdev)
void r5c_exit_cache(struct r5c_cache *cache)
{
+ r5c_exit_sysfs(cache);
md_unregister_thread(&cache->reclaim_thread);
r5l_exit_log(&cache->log);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index bcd6c1f..093611e 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -5906,6 +5906,9 @@ raid5_set_cache_size(struct mddev *mddev, int size)
if (size <= 16 || size > 32768)
return -EINVAL;
+ if (conf->cache && size < r5c_min_stripe_cache_size(conf->cache))
+ size = r5c_min_stripe_cache_size(conf->cache);
+
conf->min_nr_stripes = size;
while (size < conf->max_nr_stripes &&
drop_one_stripe(conf))
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 534e5be..25d9014 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -618,4 +618,5 @@ void r5c_exit_cache(struct r5c_cache *cache);
void r5c_write_start(struct mddev *mddev, struct bio *bi);
void r5c_write_end(struct mddev *mddev, struct bio *bi);
void r5c_quiesce(struct r5conf *conf, int state);
+int r5c_min_stripe_cache_size(struct r5c_cache *cache);
#endif
--
1.8.1
--
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
