Hello, There's an inherent mismatch between memcg and writeback. The former trackes ownership per-page while the latter per-inode. This was a deliberate design decision because honoring per-page ownership in the writeback path is complicated, may lead to higher CPU and IO overheads and deemed unnecessary given that write-sharing an inode across different cgroups isn't a common use-case. Combined with inode majority-writer ownership switching, this works well enough in most cases but there are some pathological cases. For example, let's say there are two cgroups A and B which keep writing to different but confined parts of the same inode. B owns the inode and A's memory is limited far below B's. A's dirty ratio can rise enough to trigger balance_dirty_pages() sleeps but B's can be low enough to avoid triggering background writeback. A will be slowed down without a way to make writeback of the dirty pages happen. This patchset implements foreign dirty recording and foreign mechanism so that when a memcg encounters a condition as above it can trigger flushes on bdi_writebacks which can clean its pages. Please see the last patch for more details. This patchset contains the following four patches. 0001-writeback-Generalize-and-expose-wb_completion.patch 0002-bdi-Add-bdi-id.patch 0003-writeback-memcg-Implement-cgroup_writeback_by_id.patch 0004-writeback-memcg-Implement-foreign-dirty-flushing.patch 0001-0003 are prep patches which expose wb_completion and implement bdi->id and flushing by bdi and memcg IDs. 0004 implement foreign inode flushing. Thanks. diffstat follows. fs/fs-writeback.c | 111 ++++++++++++++++++++++++---------- include/linux/backing-dev-defs.h | 23 +++++++ include/linux/backing-dev.h | 3 include/linux/memcontrol.h | 35 ++++++++++ include/linux/writeback.h | 4 + mm/backing-dev.c | 65 +++++++++++++++++++- mm/memcontrol.c | 125 +++++++++++++++++++++++++++++++++++++++ mm/page-writeback.c | 4 + 8 files changed, 335 insertions(+), 35 deletions(-) -- tejun
