[PATCH 2/2] nfs: scale writeback threshold proportional to dirtythreshold

[Wu Fengguang]

nfs_congestion_kb is to control the max allowed writeback and in-commit
pages. It's not reasonable for them to outnumber dirty and to-commit
pages. So each of them should not take more than 1/4 dirty threshold.

Considering that nfs_init_writepagecache() is called on fresh boot,
at the time dirty_thresh is much higher than the real dirty limit after
lots of user space memory consumptions, use 1/8 instead.

Feng: fix deadlock by preventing (nfs_congestion_kb == 0)

CC: Trond Myklebust <Trond.Myklebust@xxxxxxxxxx>
Signed-off-by: Feng Tang <feng.tang@xxxxxxxxx>
Signed-off-by: Wu Fengguang <fengguang.wu@xxxxxxxxx>
---
 fs/nfs/write.c      |   36 +++++++++++++++++-------------------
 mm/page-writeback.c |    6 ++++++
 2 files changed, 23 insertions(+), 19 deletions(-)

--- linux-next.orig/fs/nfs/write.c	2011-10-20 23:45:59.000000000 +0800
+++ linux-next/fs/nfs/write.c	2011-10-20 23:53:16.000000000 +0800
@@ -1782,6 +1782,22 @@ out:
 }
 #endif
 
+void nfs_update_congestion_thresh(void)
+{
+	unsigned long background_thresh;
+	unsigned long dirty_thresh;
+
+	/*
+	 * Limit to 1/8 dirty threshold, so that writeback+in_commit pages
+	 * won't overnumber dirty+to_commit pages.
+	 */
+	global_dirty_limits(&background_thresh, &dirty_thresh);
+	dirty_thresh <<= PAGE_SHIFT - 10;
+	dirty_thresh += 1024;
+
+	nfs_congestion_kb = dirty_thresh / 8;
+}
+
 int __init nfs_init_writepagecache(void)
 {
 	nfs_wdata_cachep = kmem_cache_create("nfs_write_data",
@@ -1801,25 +1817,7 @@ int __init nfs_init_writepagecache(void)
 	if (nfs_commit_mempool == NULL)
 		return -ENOMEM;
 
-	/*
-	 * NFS congestion size, scale with available memory.
-	 *
-	 *  64MB:    8192k
-	 * 128MB:   11585k
-	 * 256MB:   16384k
-	 * 512MB:   23170k
-	 *   1GB:   32768k
-	 *   2GB:   46340k
-	 *   4GB:   65536k
-	 *   8GB:   92681k
-	 *  16GB:  131072k
-	 *
-	 * This allows larger machines to have larger/more transfers.
-	 * Limit the default to 256M
-	 */
-	nfs_congestion_kb = (16*int_sqrt(totalram_pages)) << (PAGE_SHIFT-10);
-	if (nfs_congestion_kb > 256*1024)
-		nfs_congestion_kb = 256*1024;
+	nfs_update_congestion_thresh();
 
 	return 0;
 }
--- linux-next.orig/mm/page-writeback.c	2011-10-20 23:45:23.000000000 +0800
+++ linux-next/mm/page-writeback.c	2011-10-20 23:48:07.000000000 +0800
@@ -207,6 +207,10 @@ static int calc_period_shift(void)
 	return 2 + ilog2(dirty_total - 1);
 }
 
+void __weak nfs_update_congestion_thresh(void)
+{
+}
+
 /*
  * update the period when the dirty threshold changes.
  */
@@ -217,6 +221,7 @@ static void update_completion_period(voi
 	prop_change_shift(&vm_dirties, shift);
 
 	writeback_set_ratelimit();
+	nfs_update_congestion_thresh();
 }
 
 int dirty_background_ratio_handler(struct ctl_table *table, int write,
@@ -447,6 +452,7 @@ unsigned long bdi_dirty_limit(struct bac
 
 	return bdi_dirty;
 }
+EXPORT_SYMBOL_GPL(global_dirty_limits);
 
 /*
  * Dirty position control.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/