On 2017/5/23 下午4:14, tang.junhui@xxxxxxxxxx wrote: > From: "tang.junhui" <tang.junhui@xxxxxxxxxx> > > We'd better let the stacking driver inherit underlying queue limits, > so, we can avoid the unnessary mergering in the top layer, and It leads > a 10% performance promotion in large sequential IO reading testing as > follows: > Hi Junhui, I don't get the point why there is unnecessary merging in the upper layer, and how the unnecessary merging can be avoided by set a queue limit. And from the testing, I see total data size is around 21GB which is not convinced enough. Is it possible to use a large enough data size, e.g. 512GB or 1TB ? Thanks. > before: > [root@ceph192-9-9-151 ~]# dd if=/dev/bcache3p2 of=/dev/zero bs=1M > count=20480 iflag=direct > 20480+0 records in > 20480+0 records out > 21474836480 bytes (21 GB) copied, 173.424 s, 124 MB/s > > after: > [root@ceph192-9-9-151 tjh]# dd if=/dev/bcache3p2 of=/dev/zero bs=1M > count=20480 iflag=direct > 20480+0 records in > 20480+0 records out > 21474836480 bytes (21 GB) copied, 151.107 s, 142 MB/s > > Signed-off-by: tang.junhui <tang.junhui@xxxxxxxxxx> > --- > drivers/md/bcache/super.c | 2 ++ > 1 file changed, 2 insertions(+) > > diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c > index 3a19cbc..615782c 100644 > --- a/drivers/md/bcache/super.c > +++ b/drivers/md/bcache/super.c > @@ -1129,6 +1129,8 @@ static int cached_dev_init(struct cached_dev *dc, unsigned block_size) > if (ret) > return ret; > > + blk_queue_stack_limits(dc->disk.disk->queue, q); > + > set_capacity(dc->disk.disk, > dc->bdev->bd_part->nr_sects - dc->sb.data_offset); > > -- Coly Li -- To unsubscribe from this list: send the line "unsubscribe linux-bcache" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
