From fee468fdf41cdf36ba6b5a780e2474d0a3e066ac Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 2 Sep 2021 14:53:06 -0700 Subject: writeback: reliably update bandwidth estimation Currently we trigger writeback bandwidth estimation from balance_dirty_pages() and from wb_writeback(). However neither of these need to trigger when the system is relatively idle and writeback is triggered e.g. from fsync(2). Make sure writeback estimates happen reliably by triggering them from do_writepages(). Link: https://lkml.kernel.org/r/20210713104716.22868-2-jack@suse.cz Signed-off-by: Jan Kara Cc: Michael Stapelberg Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/writeback.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux/writeback.h') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 667e86cfbdcf..2480322c06a7 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -379,7 +379,6 @@ int dirty_writeback_centisecs_handler(struct ctl_table *table, int write, void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty); unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh); -void wb_update_bandwidth(struct bdi_writeback *wb, unsigned long start_time); void balance_dirty_pages_ratelimited(struct address_space *mapping); bool wb_over_bg_thresh(struct bdi_writeback *wb); -- cgit From 45a2966fd64147518dc5bca25f447bd0fb5359ac Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 2 Sep 2021 14:53:09 -0700 Subject: writeback: fix bandwidth estimate for spiky workload Michael Stapelberg has reported that for workload with short big spikes of writes (GCC linker seem to trigger this frequently) the write throughput is heavily underestimated and tends to steadily sink until it reaches zero. This has rather bad impact on writeback throttling (causing stalls). The problem is that writeback throughput estimate gets updated at most once per 200 ms. One update happens early after we submit pages for writeback (at that point writeout of only small fraction of pages is completed and thus observed throughput is tiny). Next update happens only during the next write spike (updates happen only from inode writeback and dirty throttling code) and if that is more than 1s after previous spike, we decide system was idle and just ignore whatever was written until this moment. Fix the problem by making sure writeback throughput estimate is also updated shortly after writeback completes to get reasonable estimate of throughput for spiky workloads. [jack@suse.cz: avoid division by 0 in wb_update_dirty_ratelimit()] Link: https://lore.kernel.org/lkml/20210617095309.3542373-1-stapelberg+linux@google.com Link: https://lkml.kernel.org/r/20210713104716.22868-3-jack@suse.cz Signed-off-by: Jan Kara Reported-by: Michael Stapelberg Tested-by: Michael Stapelberg Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/writeback.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/writeback.h') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 2480322c06a7..cbaef099645e 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -379,6 +379,7 @@ int dirty_writeback_centisecs_handler(struct ctl_table *table, int write, void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty); unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh); +void wb_update_bandwidth(struct bdi_writeback *wb); void balance_dirty_pages_ratelimited(struct address_space *mapping); bool wb_over_bg_thresh(struct bdi_writeback *wb); -- cgit From 7490a2d248145d8694e1e9828801b496250fd697 Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Thu, 2 Sep 2021 14:53:27 -0700 Subject: writeback: memcg: simplify cgroup_writeback_by_id Currently cgroup_writeback_by_id calls mem_cgroup_wb_stats() to get dirty pages for a memcg. However mem_cgroup_wb_stats() does a lot more than just get the number of dirty pages. Just directly get the number of dirty pages instead of calling mem_cgroup_wb_stats(). Also cgroup_writeback_by_id() is only called for best-effort dirty flushing, so remove the unused 'nr' parameter and no need to explicitly flush memcg stats. Link: https://lkml.kernel.org/r/20210722182627.2267368-1-shakeelb@google.com Signed-off-by: Shakeel Butt Reviewed-by: Jan Kara Cc: Tejun Heo Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/writeback.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/writeback.h') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index cbaef099645e..aeda2c0c9986 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -218,7 +218,7 @@ void wbc_attach_and_unlock_inode(struct writeback_control *wbc, void wbc_detach_inode(struct writeback_control *wbc); void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page, size_t bytes); -int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, unsigned long nr_pages, +int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, enum wb_reason reason, struct wb_completion *done); void cgroup_writeback_umount(void); bool cleanup_offline_cgwb(struct bdi_writeback *wb); -- cgit