mm/writeback: discard NR_UNSTABLE_NFS, use NR_WRITEBACK instead

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 919e3bd ("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' (as 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. Where the NR_UNSTABLE_NFS count was included in statistics virtual-files, the entry is retained, but the value is hard-coded as zero. static trace points and warning printks which mentioned this counter no longer report it. [[email protected]: re-layout comment] [[email protected]: fix printk warning] Signed-off-by: NeilBrown <[email protected]> Signed-off-by: Andrew Morton <[email protected]> Reviewed-by: Jan Kara <[email protected]> Reviewed-by: Christoph Hellwig <[email protected]> Acked-by: Trond Myklebust <[email protected]> Acked-by: Michal Hocko <[email protected]> [mm] Cc: Christoph Hellwig <[email protected]> Cc: Chuck Lever <[email protected]> Link: http://lkml.kernel.org/r/[email protected] Signed-off-by: Linus Torvalds <[email protected]>
berg · Jun 2, 2020 · 8d92890 · 8d92890
1 parent a37b071
commit 8d92890
Show file tree

Hide file tree

Showing 12 changed files with 28 additions and 36 deletions.
diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst
@@ -1042,8 +1042,8 @@ 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
+              Always zero. Previous counted pages which had been written to
+              the server, but has not been committed to stable storage.
 Bounce
               Memory used for block device "bounce buffers"
 WritebackTmp

diff --git a/drivers/base/node.c b/drivers/base/node.c
@@ -439,7 +439,7 @@ 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, 0UL,
 		       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
@@ -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
@@ -668,16 +668,20 @@ 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)
 {
 	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
@@ -946,9 +946,9 @@ 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
@@ -106,8 +106,7 @@ 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, "NFS_Unstable:   ", 0);
 	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
@@ -193,7 +193,6 @@ 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
@@ -541,7 +541,6 @@ 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)
@@ -552,20 +551,18 @@ 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;
 		__entry->dirty_thresh	= dirty_thresh;
 		__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
@@ -4330,7 +4330,6 @@ 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
@@ -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;
@@ -1586,14 +1585,7 @@ 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);
 
@@ -1963,8 +1955,7 @@ 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
@@ -5319,7 +5319,7 @@ 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",
@@ -5332,7 +5332,6 @@ 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),
@@ -5365,7 +5364,6 @@ 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,
@@ -5387,7 +5385,6 @@ 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
@@ -1108,7 +1108,7 @@ int fragmentation_index(struct zone *zone, unsigned int order)
 					TEXT_FOR_HIGHMEM(xx) xx "_movable",
 
 const char * const vmstat_text[] = {
-	/* enum zone_stat_item countes */
+	/* enum zone_stat_item counters */
 	"nr_free_pages",
 	"nr_zone_inactive_anon",
 	"nr_zone_active_anon",
@@ -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",
@@ -1723,6 +1722,14 @@ static int vmstat_show(struct seq_file *m, void *arg)
 	seq_puts(m, vmstat_text[off]);
 	seq_put_decimal_ull(m, " ", *l);
 	seq_putc(m, '\n');
+
+	if (off == NR_VMSTAT_ITEMS - 1) {
+		/*
+		 * We've come to the end - add any deprecated counters to avoid
+		 * breaking userspace which might depend on them being present.
+		 */
+		seq_puts(m, "nr_unstable 0\n");
+	}
 	return 0;
 }