After an NFS page has been written it is considered "unstable" until a COMMIT request succeeds. If the COMMIT fails, the page will be re-written. These "unstable" pages are currently accounted as "reclaimable", either in WB_RECLAIMABLE, or in NR_UNSTABLE_NFS which is included in a 'reclaimable' count. This might have made sense when sending the COMMIT required a separate action by the VFS/MM (e.g. releasepage() used to send a COMMIT). However now that all writes generated by ->writepages() will automatically be followed by a COMMIT (since commit 919e3bd9a875 ("NFS: Ensure we commit after writeback is complete")) it makes more sense to treat them as writeback pages. So this patch removes NR_UNSTABLE_NFS and accounts unstable pages in NR_WRITEBACK and WB_WRITEBACK. A particular effect of this change is that when wb_check_background_flush() calls wb_over_bg_threshold(), the latter will report 'true' a lot less often as the 'unstable' pages are no longer considered 'dirty' (and there is nothing that writeback can do about them anyway). Currently wb_check_background_flush() will trigger writeback to NFS even when there are relatively few dirty pages (if there are lots of unstable pages), this can result in small writes going to the server (10s of Kilobytes rather than a Megabyte) which hurts throughput. With this patch, there are fewer writes which are each larger on average. Signed-off-by: NeilBrown --- NR_UNSTABLE_NFS completely removed as recommended by Christoph, removal of an unnecessary comment, and improvements to commit message. Thanks. Documentation/filesystems/proc.txt | 3 --- drivers/base/node.c | 2 -- fs/fs-writeback.c | 1 - fs/nfs/internal.h | 10 +++++++--- fs/nfs/write.c | 4 ++-- fs/proc/meminfo.c | 2 -- include/linux/mmzone.h | 1 - include/trace/events/writeback.h | 5 +---- mm/memcontrol.c | 1 - mm/page-writeback.c | 17 ++++------------- mm/page_alloc.c | 5 +---- mm/vmstat.c | 1 - 12 files changed, 15 insertions(+), 37 deletions(-) diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index 99ca040e3f90..690c712f5f79 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -904,7 +904,6 @@ Slab: 284364 kB SReclaimable: 159856 kB SUnreclaim: 124508 kB PageTables: 24448 kB -NFS_Unstable: 0 kB Bounce: 0 kB WritebackTmp: 0 kB CommitLimit: 7669796 kB @@ -975,8 +974,6 @@ SReclaimable: Part of Slab, that might be reclaimed, such as caches SUnreclaim: Part of Slab, that cannot be reclaimed on memory pressure PageTables: amount of memory dedicated to the lowest level of page tables. -NFS_Unstable: NFS pages sent to the server, but not yet committed to stable - storage Bounce: Memory used for block device "bounce buffers" WritebackTmp: Memory used by FUSE for temporary writeback buffers CommitLimit: Based on the overcommit ratio ('vm.overcommit_ratio'), diff --git a/drivers/base/node.c b/drivers/base/node.c index 98a31bafc8a2..7059021ce2af 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -416,7 +416,6 @@ static ssize_t node_read_meminfo(struct device *dev, "Node %d Shmem: %8lu kB\n" "Node %d KernelStack: %8lu kB\n" "Node %d PageTables: %8lu kB\n" - "Node %d NFS_Unstable: %8lu kB\n" "Node %d Bounce: %8lu kB\n" "Node %d WritebackTmp: %8lu kB\n" "Node %d KReclaimable: %8lu kB\n" @@ -439,7 +438,6 @@ static ssize_t node_read_meminfo(struct device *dev, nid, K(i.sharedram), nid, sum_zone_node_page_state(nid, NR_KERNEL_STACK_KB), nid, K(sum_zone_node_page_state(nid, NR_PAGETABLE)), - nid, K(node_page_state(pgdat, NR_UNSTABLE_NFS)), nid, K(sum_zone_node_page_state(nid, NR_BOUNCE)), nid, K(node_page_state(pgdat, NR_WRITEBACK_TEMP)), nid, K(sreclaimable + diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 76ac9c7d32ec..c5bdf46e3b4b 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1070,7 +1070,6 @@ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, static unsigned long get_nr_dirty_pages(void) { return global_node_page_state(NR_FILE_DIRTY) + - global_node_page_state(NR_UNSTABLE_NFS) + get_nr_dirty_inodes(); } diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index f80c47d5ff27..749da02b547a 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -652,7 +652,8 @@ void nfs_super_set_maxbytes(struct super_block *sb, __u64 maxfilesize) } /* - * Record the page as unstable and mark its inode as dirty. + * Record the page as unstable (an extra writeback period) and mark its + * inode as dirty. */ static inline void nfs_mark_page_unstable(struct page *page, struct nfs_commit_info *cinfo) @@ -660,8 +661,11 @@ void nfs_mark_page_unstable(struct page *page, struct nfs_commit_info *cinfo) if (!cinfo->dreq) { struct inode *inode = page_file_mapping(page)->host; - inc_node_page_state(page, NR_UNSTABLE_NFS); - inc_wb_stat(&inode_to_bdi(inode)->wb, WB_RECLAIMABLE); + /* This page is really still in write-back - just that the + * writeback is happening on the server now. + */ + inc_node_page_state(page, NR_WRITEBACK); + inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK); __mark_inode_dirty(inode, I_DIRTY_DATASYNC); } } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index c478b772cc49..2e15a56620b3 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -958,9 +958,9 @@ nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, static void nfs_clear_page_commit(struct page *page) { - dec_node_page_state(page, NR_UNSTABLE_NFS); + dec_node_page_state(page, NR_WRITEBACK); dec_wb_stat(&inode_to_bdi(page_file_mapping(page)->host)->wb, - WB_RECLAIMABLE); + WB_WRITEBACK); } /* Called holding the request lock on @req */ diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index 8c1f1bb1a5ce..1378a132ff7e 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -106,8 +106,6 @@ static int meminfo_proc_show(struct seq_file *m, void *v) show_val_kb(m, "PageTables: ", global_zone_page_state(NR_PAGETABLE)); - show_val_kb(m, "NFS_Unstable: ", - global_node_page_state(NR_UNSTABLE_NFS)); show_val_kb(m, "Bounce: ", global_zone_page_state(NR_BOUNCE)); show_val_kb(m, "WritebackTmp: ", diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 462f6873905a..a18611197bea 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -237,7 +237,6 @@ enum node_stat_item { NR_FILE_THPS, NR_FILE_PMDMAPPED, NR_ANON_THPS, - NR_UNSTABLE_NFS, /* NFS unstable pages */ NR_VMSCAN_WRITE, NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */ NR_DIRTIED, /* page dirtyings since bootup */ diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index d94def25e4dc..45b5fbdb1f62 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -542,7 +542,6 @@ TRACE_EVENT(global_dirty_state, TP_STRUCT__entry( __field(unsigned long, nr_dirty) __field(unsigned long, nr_writeback) - __field(unsigned long, nr_unstable) __field(unsigned long, background_thresh) __field(unsigned long, dirty_thresh) __field(unsigned long, dirty_limit) @@ -553,7 +552,6 @@ TRACE_EVENT(global_dirty_state, TP_fast_assign( __entry->nr_dirty = global_node_page_state(NR_FILE_DIRTY); __entry->nr_writeback = global_node_page_state(NR_WRITEBACK); - __entry->nr_unstable = global_node_page_state(NR_UNSTABLE_NFS); __entry->nr_dirtied = global_node_page_state(NR_DIRTIED); __entry->nr_written = global_node_page_state(NR_WRITTEN); __entry->background_thresh = background_thresh; @@ -561,12 +559,11 @@ TRACE_EVENT(global_dirty_state, __entry->dirty_limit = global_wb_domain.dirty_limit; ), - TP_printk("dirty=%lu writeback=%lu unstable=%lu " + TP_printk("dirty=%lu writeback=%lu " "bg_thresh=%lu thresh=%lu limit=%lu " "dirtied=%lu written=%lu", __entry->nr_dirty, __entry->nr_writeback, - __entry->nr_unstable, __entry->background_thresh, __entry->dirty_thresh, __entry->dirty_limit, diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 7ddf91c4295f..fad8e8a23235 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4317,7 +4317,6 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, *pdirty = memcg_exact_page_state(memcg, NR_FILE_DIRTY); - /* this should eventually include NR_UNSTABLE_NFS */ *pwriteback = memcg_exact_page_state(memcg, NR_WRITEBACK); *pfilepages = memcg_exact_page_state(memcg, NR_INACTIVE_FILE) + memcg_exact_page_state(memcg, NR_ACTIVE_FILE); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 2afb09fa2fe0..dbc73522609e 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -504,7 +504,6 @@ bool node_dirty_ok(struct pglist_data *pgdat) unsigned long nr_pages = 0; nr_pages += node_page_state(pgdat, NR_FILE_DIRTY); - nr_pages += node_page_state(pgdat, NR_UNSTABLE_NFS); nr_pages += node_page_state(pgdat, NR_WRITEBACK); return nr_pages <= limit; @@ -758,7 +757,7 @@ static void mdtc_calc_avail(struct dirty_throttle_control *mdtc, * bounded by the bdi->min_ratio and/or bdi->max_ratio parameters, if set. * * Return: @wb's dirty limit in pages. The term "dirty" in the context of - * dirty balancing includes all PG_dirty, PG_writeback and NFS unstable pages. + * dirty balancing includes all PG_dirty and PG_writeback pages. */ static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc) { @@ -1566,7 +1565,7 @@ static void balance_dirty_pages(struct bdi_writeback *wb, struct dirty_throttle_control * const mdtc = mdtc_valid(&mdtc_stor) ? &mdtc_stor : NULL; struct dirty_throttle_control *sdtc; - unsigned long nr_reclaimable; /* = file_dirty + unstable_nfs */ + unsigned long nr_reclaimable; /* = file_dirty */ long period; long pause; long max_pause; @@ -1589,14 +1588,7 @@ static void balance_dirty_pages(struct bdi_writeback *wb, unsigned long m_thresh = 0; unsigned long m_bg_thresh = 0; - /* - * Unstable writes are a feature of certain networked - * filesystems (i.e. NFS) in which data may have been - * written to the server's write cache, but has not yet - * been flushed to permanent storage. - */ - nr_reclaimable = global_node_page_state(NR_FILE_DIRTY) + - global_node_page_state(NR_UNSTABLE_NFS); + nr_reclaimable = global_node_page_state(NR_FILE_DIRTY); gdtc->avail = global_dirtyable_memory(); gdtc->dirty = nr_reclaimable + global_node_page_state(NR_WRITEBACK); @@ -1940,8 +1932,7 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb) * as we're trying to decide whether to put more under writeback. */ gdtc->avail = global_dirtyable_memory(); - gdtc->dirty = global_node_page_state(NR_FILE_DIRTY) + - global_node_page_state(NR_UNSTABLE_NFS); + gdtc->dirty = global_node_page_state(NR_FILE_DIRTY); domain_dirty_limits(gdtc); if (gdtc->dirty > gdtc->bg_thresh) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 3c4eb750a199..6bd1112d590d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5239,7 +5239,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) printk("active_anon:%lu inactive_anon:%lu isolated_anon:%lu\n" " active_file:%lu inactive_file:%lu isolated_file:%lu\n" - " unevictable:%lu dirty:%lu writeback:%lu unstable:%lu\n" + " unevictable:%lu dirty:%lu writeback:%lu\n" " slab_reclaimable:%lu slab_unreclaimable:%lu\n" " mapped:%lu shmem:%lu pagetables:%lu bounce:%lu\n" " free:%lu free_pcp:%lu free_cma:%lu\n", @@ -5252,7 +5252,6 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) global_node_page_state(NR_UNEVICTABLE), global_node_page_state(NR_FILE_DIRTY), global_node_page_state(NR_WRITEBACK), - global_node_page_state(NR_UNSTABLE_NFS), global_node_page_state(NR_SLAB_RECLAIMABLE), global_node_page_state(NR_SLAB_UNRECLAIMABLE), global_node_page_state(NR_FILE_MAPPED), @@ -5285,7 +5284,6 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) " anon_thp: %lukB" #endif " writeback_tmp:%lukB" - " unstable:%lukB" " all_unreclaimable? %s" "\n", pgdat->node_id, @@ -5307,7 +5305,6 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) K(node_page_state(pgdat, NR_ANON_THPS) * HPAGE_PMD_NR), #endif K(node_page_state(pgdat, NR_WRITEBACK_TEMP)), - K(node_page_state(pgdat, NR_UNSTABLE_NFS)), pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES ? "yes" : "no"); } diff --git a/mm/vmstat.c b/mm/vmstat.c index 78d53378db99..d1291537bbb9 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1162,7 +1162,6 @@ const char * const vmstat_text[] = { "nr_file_hugepages", "nr_file_pmdmapped", "nr_anon_transparent_hugepages", - "nr_unstable", "nr_vmscan_write", "nr_vmscan_immediate_reclaim", "nr_dirtied", -- 2.26.0