On Fri, Nov 07, 2008 at 12:21:45PM +0900, KAMEZAWA Hiroyuki wrote: > On Thu, 06 Nov 2008 10:30:25 -0500 > vgoyal@xxxxxxxxxx wrote: > > > > > o Core IO controller implementation > > > > Signed-off-by: Vivek Goyal <vgoyal@xxxxxxxxxx> > > > > 2 comments after a quick look. > > - I don't recommend generic work queue. More stacked dependency between "work" > is not good. (I think disk-driver uses "work" for their jobs.) Sorry, I did not get this. Are you recommending that don't create a new work queue, instead use existing work queue (say kblockd) to submit the bios here? I will look into it. I was little worried about a kblockd being overworked in case of too many logical devices enabling IO controller. > > - It seems this bio-cgroup can queue the bio to infinite. Then, a process can submit > io unitl cause OOM. > (IIUC, Dirty bit of the page is cleared at submitting I/O. > Then dirty_ratio can't help us.) > please add "wait for congestion by sleeping" code in bio-cgroup. Yes, you are right. I need to put some kind of control on max number of bios I can queue on a cgroup and after crossing the limit, I should put the submitting task to sleep. (Something like request descriptor kind of flow control implememented by elevators). Thanks Vivek _______________________________________________ Virtualization mailing list Virtualization@xxxxxxxxxxxxxxxxxxxxxxxxxx https://lists.linux-foundation.org/mailman/listinfo/virtualization
