| Message ID | 20230403220337.443510-1-yosryahmed@google.com (mailing list archive) |
|---|---|
| Headers | show |
| Series | cgroup: eliminate atomic rstat | expand |
On Mon, Apr 3, 2023 at 3:03 PM Yosry Ahmed <yosryahmed@google.com> wrote: > > A previous patch series ([1] currently in mm-unstable) changed most .. and I naturally forgot to link this: [1] https://lore.kernel.org/linux-mm/20230330191801.1967435-1-yosryahmed@google.com/ > atomic rstat flushing contexts to become non-atomic. This was done to > avoid an expensive operation that scales with # cgroups and # cpus to > happen with irqs disabled and scheduling not permitted. There were two > remaining atomic flushing contexts after that series. This series tries > to eliminate them as well, eliminating atomic rstat flushing completely. > > The two remaining atomic flushing contexts are: > (a) wb_over_bg_thresh()->mem_cgroup_wb_stats() > (b) mem_cgroup_threshold()->mem_cgroup_usage() > > For (a), flushing needs to be atomic as wb_writeback() calls > wb_over_bg_thresh() with a spinlock held. However, it seems like the > call to wb_over_bg_thresh() doesn't need to be protected by that > spinlock, so this series proposes a refactoring that moves the call > outside the lock criticial section and makes the stats flushing > in mem_cgroup_wb_stats() non-atomic. > > For (b), flushing needs to be atomic as mem_cgroup_threshold() is called > with irqs disabled. We only flush the stats when calculating the root > usage, as it is approximated as the sum of some memcg stats (file, anon, > and optionally swap) instead of the conventional page counter. This > series proposes changing this calculation to use the global stats > instead, eliminating the need for a memcg stat flush. > > After these 2 contexts are eliminated, we no longer need > mem_cgroup_flush_stats_atomic() or cgroup_rstat_flush_atomic(). We can > remove them and simplify the code. > > Yosry Ahmed (5): > writeback: move wb_over_bg_thresh() call outside lock section > memcg: flush stats non-atomically in mem_cgroup_wb_stats() > memcg: calculate root usage from global state > memcg: remove mem_cgroup_flush_stats_atomic() > cgroup: remove cgroup_rstat_flush_atomic() > > fs/fs-writeback.c | 16 +++++++---- > include/linux/cgroup.h | 1 - > include/linux/memcontrol.h | 5 ---- > kernel/cgroup/rstat.c | 26 ++++-------------- > mm/memcontrol.c | 54 ++++++++------------------------------ > 5 files changed, 27 insertions(+), 75 deletions(-) > > -- > 2.40.0.348.gf938b09366-goog >
On Mon, 2023-04-03 at 22:03 +0000, Yosry Ahmed wrote: > A previous patch series ([1] currently in mm-unstable) changed most Can you include the link to [1]? Thanks. Tim > atomic rstat flushing contexts to become non-atomic. This was done to > avoid an expensive operation that scales with # cgroups and # cpus to > happen with irqs disabled and scheduling not permitted. There were two > remaining atomic flushing contexts after that series. This series tries > to eliminate them as well, eliminating atomic rstat flushing completely. > > The two remaining atomic flushing contexts are: > (a) wb_over_bg_thresh()->mem_cgroup_wb_stats() > (b) mem_cgroup_threshold()->mem_cgroup_usage() > > For (a), flushing needs to be atomic as wb_writeback() calls > wb_over_bg_thresh() with a spinlock held. However, it seems like the > call to wb_over_bg_thresh() doesn't need to be protected by that > spinlock, so this series proposes a refactoring that moves the call > outside the lock criticial section and makes the stats flushing > in mem_cgroup_wb_stats() non-atomic. > > For (b), flushing needs to be atomic as mem_cgroup_threshold() is called > with irqs disabled. We only flush the stats when calculating the root > usage, as it is approximated as the sum of some memcg stats (file, anon, > and optionally swap) instead of the conventional page counter. This > series proposes changing this calculation to use the global stats > instead, eliminating the need for a memcg stat flush. > > After these 2 contexts are eliminated, we no longer need > mem_cgroup_flush_stats_atomic() or cgroup_rstat_flush_atomic(). We can > remove them and simplify the code. > > Yosry Ahmed (5): > writeback: move wb_over_bg_thresh() call outside lock section > memcg: flush stats non-atomically in mem_cgroup_wb_stats() > memcg: calculate root usage from global state > memcg: remove mem_cgroup_flush_stats_atomic() > cgroup: remove cgroup_rstat_flush_atomic() > > fs/fs-writeback.c | 16 +++++++---- > include/linux/cgroup.h | 1 - > include/linux/memcontrol.h | 5 ---- > kernel/cgroup/rstat.c | 26 ++++-------------- > mm/memcontrol.c | 54 ++++++++------------------------------ > 5 files changed, 27 insertions(+), 75 deletions(-) >
On Mon, 2023-04-03 at 15:04 -0700, Yosry Ahmed wrote: > On Mon, Apr 3, 2023 at 3:03 PM Yosry Ahmed <yosryahmed@google.com> wrote: > > > > A previous patch series ([1] currently in mm-unstable) changed most > > .. and I naturally forgot to link this: > [1] https://lore.kernel.org/linux-mm/20230330191801.1967435-1-yosryahmed@google.com/ Thanks. Saw this after I sent my request for link. Tim
On Mon, Apr 3, 2023 at 3:03 PM Yosry Ahmed <yosryahmed@google.com> wrote: > > A previous patch series ([1] currently in mm-unstable) changed most > atomic rstat flushing contexts to become non-atomic. This was done to > avoid an expensive operation that scales with # cgroups and # cpus to > happen with irqs disabled and scheduling not permitted. There were two > remaining atomic flushing contexts after that series. This series tries > to eliminate them as well, eliminating atomic rstat flushing completely. > > The two remaining atomic flushing contexts are: > (a) wb_over_bg_thresh()->mem_cgroup_wb_stats() > (b) mem_cgroup_threshold()->mem_cgroup_usage() > > For (a), flushing needs to be atomic as wb_writeback() calls > wb_over_bg_thresh() with a spinlock held. However, it seems like the > call to wb_over_bg_thresh() doesn't need to be protected by that > spinlock, so this series proposes a refactoring that moves the call > outside the lock criticial section and makes the stats flushing > in mem_cgroup_wb_stats() non-atomic. > > For (b), flushing needs to be atomic as mem_cgroup_threshold() is called > with irqs disabled. We only flush the stats when calculating the root > usage, as it is approximated as the sum of some memcg stats (file, anon, > and optionally swap) instead of the conventional page counter. This > series proposes changing this calculation to use the global stats > instead, eliminating the need for a memcg stat flush. > > After these 2 contexts are eliminated, we no longer need > mem_cgroup_flush_stats_atomic() or cgroup_rstat_flush_atomic(). We can > remove them and simplify the code. > > Yosry Ahmed (5): > writeback: move wb_over_bg_thresh() call outside lock section > memcg: flush stats non-atomically in mem_cgroup_wb_stats() > memcg: calculate root usage from global state > memcg: remove mem_cgroup_flush_stats_atomic() > cgroup: remove cgroup_rstat_flush_atomic() > > fs/fs-writeback.c | 16 +++++++---- > include/linux/cgroup.h | 1 - > include/linux/memcontrol.h | 5 ---- > kernel/cgroup/rstat.c | 26 ++++-------------- > mm/memcontrol.c | 54 ++++++++------------------------------ > 5 files changed, 27 insertions(+), 75 deletions(-) > > -- > 2.40.0.348.gf938b09366-goog > Any thoughts on this series, anyone? :)