From: Tang Junhui <tang.junhui@xxxxxxxxxx>
LGTM, and I tested it, it promotes the write-back performance.
Reviewed-by: Tang Junhui <tang.junhui@xxxxxxxxxx>
Tested-by: Tang Junhui <tang.junhui@xxxxxxxxxx>
> From: Tang Junhui <tang.junhui@xxxxxxxxxx>
>
> In such scenario that there are some flash only volumes
> , and some cached devices, when many tasks request these devices in
> writeback mode, the write IOs may fall to the same bucket as bellow:
> | cached data | flash data | cached data | cached data| flash data|
> then after writeback of these cached devices, the bucket would
> be like bellow bucket:
> | free | flash data | free | free | flash data |
>
> So, there are many free space in this bucket, but since data of flash
> only volumes still exists, so this bucket cannot be reclaimable,
> which would cause waste of bucket space.
>
> In this patch, we segregate flash only volume write streams from
> cached devices, so data from flash only volumes and cached devices
> can store in different buckets.
>
> Compare to v1 patch, this patch do not add a additionally open bucket
> list, and it is try best to segregate flash only volume write streams
> from cached devices, sectors of flash only volumes may still be mixed
> with dirty sectors of cached device, but the number is very small.
>
> Signed-off-by: Tang Junhui <tang.junhui@xxxxxxxxxx>
> ---
> drivers/md/bcache/alloc.c | 19 ++++++++++++++-----
> 1 file changed, 14 insertions(+), 5 deletions(-)
> mode change 100644 => 100755 drivers/md/bcache/alloc.c
>
> diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
> old mode 100644
> new mode 100755
> index 0803563..4302922
> --- a/drivers/md/bcache/alloc.c
> +++ b/drivers/md/bcache/alloc.c
> @@ -514,15 +514,21 @@ struct open_bucket {
>
> /*
> * We keep multiple buckets open for writes, and try to segregate different
> - * write streams for better cache utilization: first we look for a bucket where
> - * the last write to it was sequential with the current write, and failing that
> - * we look for a bucket that was last used by the same task.
> + * write streams for better cache utilization: first we try to segregate flash
> + * only volume write streams from cached devices, secondly we look for a bucket
> + * where the last write to it was sequential with the current write, and
> + * failing that we look for a bucket that was last used by the same task.
> *
> * The ideas is if you've got multiple tasks pulling data into the cache at the
> * same time, you'll get better cache utilization if you try to segregate their
> * data and preserve locality.
> *
> - * For example, say you've starting Firefox at the same time you're copying a
> + * For example, dirty sectors of flash only volume is not reclaimable, if their
> + * dirty sectors mixed with dirty sectors of cached device, such buckets will
> + * be marked as dirty and won't be reclaimed, though the dirty data of cached
> + * device have been written back to backend device.
> + *
> + * And say you've starting Firefox at the same time you're copying a
> * bunch of files. Firefox will likely end up being fairly hot and stay in the
> * cache awhile, but the data you copied might not be; if you wrote all that
> * data to the same buckets it'd get invalidated at the same time.
> @@ -539,7 +545,10 @@ static struct open_bucket *pick_data_bucket(struct cache_set *c,
> struct open_bucket *ret, *ret_task = NULL;
>
> list_for_each_entry_reverse(ret, &c->data_buckets, list)
> - if (!bkey_cmp(&ret->key, search))
> + if (UUID_FLASH_ONLY(&c->uuids[KEY_INODE(&ret->key)]) !=
> + UUID_FLASH_ONLY(&c->uuids[KEY_INODE(search)]))
> + continue;
> + else if (!bkey_cmp(&ret->key, search))
> goto found;
> else if (ret->last_write_point == write_point)
> ret_task = ret;
> --
> 1.8.3.1
Thanks,
Tang
