On Mon, Apr 22, 2013 at 06:42:23PM -0400, Jeff Moyer wrote: > > Jan, if I were to come up with a way of promoting a particular async > queue to the front of the line, where would I put such a call in the > ext4/jbd2 code to be effective? Well, I thought we had discussed trying to bump a pending I/O automatically when there was an attempt to call lock_buffer() on the bh? That would be ideal, because we could keep the async writeback low priority until someone is trying to wait upon it, at which point obviously it should no longer be considered an async write call. Failing that, this is something I've been toying with.... what do you think? http://patchwork.ozlabs.org/patch/238192/ http://patchwork.ozlabs.org/patch/238257/ (The first patch in the series just makes sure that allocation bitmap reads are marked with the META/PRIO flags. It's not strictly speaking related to the problem discussed here, but for completeness: http://patchwork.ozlabs.org/patch/238193/) - Ted -- To unsubscribe from this list: send the line "unsubscribe linux-ext4" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
