On Tue, Apr 25, 2017 at 12:38:54PM +0800, tang.junhui@xxxxxxxxxx wrote: > Hello all, > > > > > We test sequential write IO with bs=1M by FIO, > > and the bcache cache_mode is writeback, > > we expect these IOs to be bypassed cache, > > but actually they not. > > We debug the code, and find in check_should_bypass(): > > if (!congested && > > mode == CACHE_MODE_WRITEBACK && > > op_is_write(bio_op(bio)) && > > (bio-＞bi_opf & REQ_SYNC)) > > goto rescale > > that means, If in writeback mode, a write IO with REQ_SYNC flag > > will not be bypassed though it is a sequential large IO. > > > > So, my question is: why do not we bypass these IOs ? > > We planned to remove these codes. Does the modification do any harm? You can remove that check, it won't break anything. -- 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
