From 4b5bbc39d7a637a135fd8b3ef86e60a6a7301e9d Mon Sep 17 00:00:00 2001 From: Kemeng Shi Date: Tue, 23 Apr 2024 11:46:40 +0800 Subject: [PATCH] writeback: support retrieving per group debug writeback stats of bdi Add /sys/kernel/debug/bdi/xxx/wb_stats to show per group writeback stats of bdi. Following domain hierarchy is tested: global domain (320G) / \ cgroup domain1(10G) cgroup domain2(10G) | | bdi wb1 wb2 /* per wb writeback info of bdi is collected */ cat wb_stats WbCgIno: 1 WbWriteback: 0 kB WbReclaimable: 0 kB WbDirtyThresh: 0 kB WbDirtied: 0 kB WbWritten: 0 kB WbWriteBandwidth: 102400 kBps b_dirty: 0 b_io: 0 b_more_io: 0 b_dirty_time: 0 state: 1 WbCgIno: 4091 WbWriteback: 1792 kB WbReclaimable: 820512 kB WbDirtyThresh: 6004692 kB WbDirtied: 1820448 kB WbWritten: 999488 kB WbWriteBandwidth: 169020 kBps b_dirty: 0 b_io: 0 b_more_io: 1 b_dirty_time: 0 state: 5 WbCgIno: 4131 WbWriteback: 1120 kB WbReclaimable: 820064 kB WbDirtyThresh: 6004728 kB WbDirtied: 1822688 kB WbWritten: 1002400 kB WbWriteBandwidth: 153520 kBps b_dirty: 0 b_io: 0 b_more_io: 1 b_dirty_time: 0 state: 5 [shikemeng@huaweicloud.com: fix build problems] Link: https://lkml.kernel.org/r/20240423034643.141219-4-shikemeng@huaweicloud.com Link: https://lkml.kernel.org/r/20240423034643.141219-3-shikemeng@huaweicloud.com Signed-off-by: Kemeng Shi Cc: Brian Foster Cc: David Howells Cc: David Sterba Cc: Jan Kara Cc: Mateusz Guzik Cc: Matthew Wilcox (Oracle) Cc: SeongJae Park Cc: Stephen Rothwell Cc: Tejun Heo Signed-off-by: Andrew Morton --- include/linux/writeback.h | 1 + mm/backing-dev.c | 81 ++++++++++++++++++++++++++++++++++++++- mm/page-writeback.c | 19 +++++++++ 3 files changed, 99 insertions(+), 2 deletions(-) diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 9845cb62e40b..112d806ddbe4 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -355,6 +355,7 @@ int dirtytime_interval_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); +unsigned long cgwb_calc_thresh(struct bdi_writeback *wb); void wb_update_bandwidth(struct bdi_writeback *wb); diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 089146feb830..e61bbb1bd622 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -155,19 +155,96 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v) } DEFINE_SHOW_ATTRIBUTE(bdi_debug_stats); +static void wb_stats_show(struct seq_file *m, struct bdi_writeback *wb, + struct wb_stats *stats) +{ + + seq_printf(m, + "WbCgIno: %10lu\n" + "WbWriteback: %10lu kB\n" + "WbReclaimable: %10lu kB\n" + "WbDirtyThresh: %10lu kB\n" + "WbDirtied: %10lu kB\n" + "WbWritten: %10lu kB\n" + "WbWriteBandwidth: %10lu kBps\n" + "b_dirty: %10lu\n" + "b_io: %10lu\n" + "b_more_io: %10lu\n" + "b_dirty_time: %10lu\n" + "state: %10lx\n\n", +#ifdef CONFIG_CGROUP_WRITEBACK + cgroup_ino(wb->memcg_css->cgroup), +#else + 1ul, +#endif + K(stats->nr_writeback), + K(stats->nr_reclaimable), + K(stats->wb_thresh), + K(stats->nr_dirtied), + K(stats->nr_written), + K(wb->avg_write_bandwidth), + stats->nr_dirty, + stats->nr_io, + stats->nr_more_io, + stats->nr_dirty_time, + wb->state); +} + +static int cgwb_debug_stats_show(struct seq_file *m, void *v) +{ + struct backing_dev_info *bdi = m->private; + unsigned long background_thresh; + unsigned long dirty_thresh; + struct bdi_writeback *wb; + + global_dirty_limits(&background_thresh, &dirty_thresh); + + rcu_read_lock(); + list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) { + struct wb_stats stats = { .dirty_thresh = dirty_thresh }; + + if (!wb_tryget(wb)) + continue; + + collect_wb_stats(&stats, wb); + + /* + * Calculate thresh of wb in writeback cgroup which is min of + * thresh in global domain and thresh in cgroup domain. Drop + * rcu lock because cgwb_calc_thresh may sleep in + * cgroup_rstat_flush. We can do so here because we have a ref. + */ + if (mem_cgroup_wb_domain(wb)) { + rcu_read_unlock(); + stats.wb_thresh = min(stats.wb_thresh, cgwb_calc_thresh(wb)); + rcu_read_lock(); + } + + wb_stats_show(m, wb, &stats); + + wb_put(wb); + } + rcu_read_unlock(); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(cgwb_debug_stats); + static void bdi_debug_register(struct backing_dev_info *bdi, const char *name) { bdi->debug_dir = debugfs_create_dir(name, bdi_debug_root); debugfs_create_file("stats", 0444, bdi->debug_dir, bdi, &bdi_debug_stats_fops); + debugfs_create_file("wb_stats", 0444, bdi->debug_dir, bdi, + &cgwb_debug_stats_fops); } static void bdi_debug_unregister(struct backing_dev_info *bdi) { debugfs_remove_recursive(bdi->debug_dir); } -#else +#else /* CONFIG_DEBUG_FS */ static inline void bdi_debug_init(void) { } @@ -178,7 +255,7 @@ static inline void bdi_debug_register(struct backing_dev_info *bdi, static inline void bdi_debug_unregister(struct backing_dev_info *bdi) { } -#endif +#endif /* CONFIG_DEBUG_FS */ static ssize_t read_ahead_kb_store(struct device *dev, struct device_attribute *attr, diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 2c1f595d1ddc..c5fb3121469a 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -892,6 +892,25 @@ unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh) return __wb_calc_thresh(&gdtc); } +unsigned long cgwb_calc_thresh(struct bdi_writeback *wb) +{ + struct dirty_throttle_control gdtc = { GDTC_INIT_NO_WB }; + struct dirty_throttle_control mdtc = { MDTC_INIT(wb, &gdtc) }; + unsigned long filepages = 0, headroom = 0, writeback = 0; + + gdtc.avail = global_dirtyable_memory(); + gdtc.dirty = global_node_page_state(NR_FILE_DIRTY) + + global_node_page_state(NR_WRITEBACK); + + mem_cgroup_wb_stats(wb, &filepages, &headroom, + &mdtc.dirty, &writeback); + mdtc.dirty += writeback; + mdtc_calc_avail(&mdtc, filepages, headroom); + domain_dirty_limits(&mdtc); + + return __wb_calc_thresh(&mdtc); +} + /* * setpoint - dirty 3 * f(dirty) := 1.0 + (----------------)