On Tue, Apr 21, 2009 at 02:29:58PM -0400, Vivek Goyal wrote: > On Tue, Apr 21, 2009 at 10:23:05AM -0400, Vivek Goyal wrote: > > On Tue, Apr 21, 2009 at 10:37:03AM +0200, Andrea Righi wrote: > > > On Mon, Apr 20, 2009 at 09:08:46PM -0400, Vivek Goyal wrote: > > > > On Tue, Apr 21, 2009 at 12:05:12AM +0200, Andrea Righi wrote: > > > > > > > > [..] > > > > > > > > Are we not already controlling submission of request (at crude level). > > > > > > > > If application is doing writeout at high rate, then it hits vm_dirty_ratio > > > > > > > > hits and this application is forced to do write out and hence it is slowed > > > > > > > > down and is not allowed to submit writes at high rate. > > > > > > > > > > > > > > > > Just that it is not a very fair scheme right now as during right out > > > > > > > > a high prio/high weight cgroup application can start writing out some > > > > > > > > other cgroups' pages. > > > > > > > > > > > > > > > > For this we probably need to have some combination of solutions like > > > > > > > > per cgroup upper limit on dirty pages. Secondly probably if an application > > > > > > > > is slowed down because of hitting vm_drity_ratio, it should try to > > > > > > > > write out the inode it is dirtying first instead of picking any random > > > > > > > > inode and associated pages. This will ensure that a high weight > > > > > > > > application can quickly get through the write outs and see higher > > > > > > > > throughput from the disk. > > > > > > > > > > > > > > For the first, I submitted a patchset some months ago to provide this > > > > > > > feature in the memory controller: > > > > > > > > > > > > > > https://lists.linux-foundation.org/pipermail/containers/2008-September/013140.html > > > > > > > > > > > > > > We focused on the best interface to use for setting the dirty pages > > > > > > > limit, but we didn't finalize it. I can rework on that and repost an > > > > > > > updated version. Now that we have the dirty_ratio/dirty_bytes to set the > > > > > > > global limit I think we can use the same interface and the same semantic > > > > > > > within the cgroup fs, something like: > > > > > > > > > > > > > > memory.dirty_ratio > > > > > > > memory.dirty_bytes > > > > > > > > > > > > > > For the second point something like this should be enough to force tasks > > > > > > > to write out only the inode they're actually dirtying when they hit the > > > > > > > vm_dirty_ratio limit. But it should be tested carefully and may cause > > > > > > > heavy performance regressions. > > > > > > > > > > > > > > Signed-off-by: Andrea Righi <righi.andrea@xxxxxxxxx> > > > > > > > --- > > > > > > > mm/page-writeback.c | 2 +- > > > > > > > 1 files changed, 1 insertions(+), 1 deletions(-) > > > > > > > > > > > > > > diff --git a/mm/page-writeback.c b/mm/page-writeback.c > > > > > > > index 2630937..1e07c9d 100644 > > > > > > > --- a/mm/page-writeback.c > > > > > > > +++ b/mm/page-writeback.c > > > > > > > @@ -543,7 +543,7 @@ static void balance_dirty_pages(struct address_space *mapping) > > > > > > > * been flushed to permanent storage. > > > > > > > */ > > > > > > > if (bdi_nr_reclaimable) { > > > > > > > - writeback_inodes(&wbc); > > > > > > > + sync_inode(mapping->host, &wbc); > > > > > > > pages_written += write_chunk - wbc.nr_to_write; > > > > > > > get_dirty_limits(&background_thresh, &dirty_thresh, > > > > > > > &bdi_thresh, bdi); > > > > > > > > > > > > This patch seems to be helping me a bit in getting more service > > > > > > differentiation between two writer dd of different weights. But strangely > > > > > > it is helping only for ext3 and not ext4. Debugging is on. > > > > > > > > > > Are you explicitly mounting ext3 with data=ordered? > > > > > > > > Yes. Still using 29-rc8 and data=ordered was the default then. > > > > > > > > I got two partitions on same disk and created one ext3 filesystem on each > > > > partition (just to take journaling intereference out of two dd threads > > > > for the time being). > > > > > > > > Two dd threads doing writes to each partition. > > > > > > ...and if you're using data=writeback with ext4 sync_inode() should sync > > > the metadata only. If this is the case, could you check data=ordered > > > also for ext4? > > > > No, even data=ordered mode with ext4 is also not helping. It has to be > > something else. > > > > Ok, with data=ordered mode with ext4, now I can get significant service > differentiation between two dd processes. I had to tweak cfq a bit. > > - Instead of 40ms slice for async queue, do 20ms at a time (tunable). > - change cfq quantum to 1 from 4 to not dispatch a bunch of requests at > one go. > > Above changes help a bit in making sure two continuously backlogged queues > at IO scheduler so that IO scheduler can offer more disk time to higher > weight process. Good, also testing the WB_SYNC_ALL would be interesting I think. -Andrea _______________________________________________ Containers mailing list Containers@xxxxxxxxxxxxxxxxxxxxxxxxxx https://lists.linux-foundation.org/mailman/listinfo/containers
