summaryrefslogtreecommitdiffstats
path: root/fs/fs-writeback.c
diff options
context:
space:
mode:
authorTejun Heo <tj@kernel.org>2015-05-22 17:13:55 -0400
committerJens Axboe <axboe@fb.com>2015-06-02 08:33:36 -0600
commitf2b65121607631df0753eedd624262818707af32 (patch)
tree1ba12510e26cca8f250161d6882443178417da7e /fs/fs-writeback.c
parent9ecf4866c018aeb304a7b49216c4d183665becb7 (diff)
downloadlinux-f2b65121607631df0753eedd624262818707af32.tar.bz2
writeback: make wakeup_flusher_threads() handle multiple bdi_writeback's
wakeup_flusher_threads() currently only starts writeback on the root wb (bdi_writeback). For cgroup writeback support, update the function to wake up all wbs and distribute the number of pages to write according to the proportion of each wb's write bandwidth, which is implemented in wb_split_bdi_pages(). Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Jan Kara <jack@suse.cz> Signed-off-by: Jens Axboe <axboe@fb.com>
Diffstat (limited to 'fs/fs-writeback.c')
-rw-r--r--fs/fs-writeback.c48
1 files changed, 46 insertions, 2 deletions
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 92aaf641ee22..508e10cc3fcd 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -198,6 +198,41 @@ int inode_congested(struct inode *inode, int cong_bits)
}
EXPORT_SYMBOL_GPL(inode_congested);
+/**
+ * wb_split_bdi_pages - split nr_pages to write according to bandwidth
+ * @wb: target bdi_writeback to split @nr_pages to
+ * @nr_pages: number of pages to write for the whole bdi
+ *
+ * Split @wb's portion of @nr_pages according to @wb's write bandwidth in
+ * relation to the total write bandwidth of all wb's w/ dirty inodes on
+ * @wb->bdi.
+ */
+static long wb_split_bdi_pages(struct bdi_writeback *wb, long nr_pages)
+{
+ unsigned long this_bw = wb->avg_write_bandwidth;
+ unsigned long tot_bw = atomic_long_read(&wb->bdi->tot_write_bandwidth);
+
+ if (nr_pages == LONG_MAX)
+ return LONG_MAX;
+
+ /*
+ * This may be called on clean wb's and proportional distribution
+ * may not make sense, just use the original @nr_pages in those
+ * cases. In general, we wanna err on the side of writing more.
+ */
+ if (!tot_bw || this_bw >= tot_bw)
+ return nr_pages;
+ else
+ return DIV_ROUND_UP_ULL((u64)nr_pages * this_bw, tot_bw);
+}
+
+#else /* CONFIG_CGROUP_WRITEBACK */
+
+static long wb_split_bdi_pages(struct bdi_writeback *wb, long nr_pages)
+{
+ return nr_pages;
+}
+
#endif /* CONFIG_CGROUP_WRITEBACK */
void wb_start_writeback(struct bdi_writeback *wb, long nr_pages,
@@ -1187,8 +1222,17 @@ void wakeup_flusher_threads(long nr_pages, enum wb_reason reason)
nr_pages = get_nr_dirty_pages();
rcu_read_lock();
- list_for_each_entry_rcu(bdi, &bdi_list, bdi_list)
- wb_start_writeback(&bdi->wb, nr_pages, false, reason);
+ list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) {
+ struct bdi_writeback *wb;
+ struct wb_iter iter;
+
+ if (!bdi_has_dirty_io(bdi))
+ continue;
+
+ bdi_for_each_wb(wb, bdi, &iter, 0)
+ wb_start_writeback(wb, wb_split_bdi_pages(wb, nr_pages),
+ false, reason);
+ }
rcu_read_unlock();
}