From: NeilBrown <neilb@xxxxxxx>
Subject: ceph: remove reliance on bdi congestion
The bdi congestion tracking in not widely used and will be removed.
CEPHfs is one of a small number of filesystems that uses it, setting just
the async (write) congestion flags at what it determines are appropriate
times.
The only remaining effect of the async flag is to cause (some)
WB_SYNC_NONE writes to be skipped.
So instead of setting the flag, set an internal flag and change:
- .writepages to do nothing if WB_SYNC_NONE and the flag is set
- .writepage to return AOP_WRITEPAGE_ACTIVATE if WB_SYNC_NONE
and the flag is set.
The writepages change causes a behavioural change in that pageout() can
now return PAGE_ACTIVATE instead of PAGE_KEEP, so SetPageActive() will be
called on the page which (I think) wil further delay the next attempt at
writeout. This might be a good thing.
Link: https://lkml.kernel.org/r/164549983739.9187.14895675781408171186.stgit@noble.brown
Signed-off-by: NeilBrown <neilb@xxxxxxx>
Cc: Anna Schumaker <Anna.Schumaker@xxxxxxxxxx>
Cc: Chao Yu <chao@xxxxxxxxxx>
Cc: Darrick J. Wong <djwong@xxxxxxxxxx>
Cc: Ilya Dryomov <idryomov@xxxxxxxxx>
Cc: Jaegeuk Kim <jaegeuk@xxxxxxxxxx>
Cc: Jan Kara <jack@xxxxxxx>
Cc: Jeff Layton <jlayton@xxxxxxxxxx>
Cc: Jens Axboe <axboe@xxxxxxxxx>
Cc: Lars Ellenberg <lars.ellenberg@xxxxxxxxxx>
Cc: Miklos Szeredi <miklos@xxxxxxxxxx>
Cc: Paolo Valente <paolo.valente@xxxxxxxxxx>
Cc: Philipp Reisner <philipp.reisner@xxxxxxxxxx>
Cc: Ryusuke Konishi <konishi.ryusuke@xxxxxxxxx>
Cc: Trond Myklebust <trond.myklebust@xxxxxxxxxxxxxxx>
Cc: Wu Fengguang <fengguang.wu@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/ceph/addr.c | 22 +++++++++++++---------
fs/ceph/super.c | 1 +
fs/ceph/super.h | 1 +
3 files changed, 15 insertions(+), 9 deletions(-)
--- a/fs/ceph/addr.c~ceph-remove-reliance-on-bdi-congestion
+++ a/fs/ceph/addr.c
@@ -563,7 +563,7 @@ static int writepage_nounlock(struct pag
if (atomic_long_inc_return(&fsc->writeback_count) >
CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb))
- set_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC);
+ fsc->write_congested = true;
req = ceph_osdc_new_request(osdc, &ci->i_layout, ceph_vino(inode), page_off, &len, 0, 1,
CEPH_OSD_OP_WRITE, CEPH_OSD_FLAG_WRITE, snapc,
@@ -623,7 +623,7 @@ static int writepage_nounlock(struct pag
if (atomic_long_dec_return(&fsc->writeback_count) <
CONGESTION_OFF_THRESH(fsc->mount_options->congestion_kb))
- clear_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC);
+ fsc->write_congested = false;
return err;
}
@@ -635,6 +635,10 @@ static int ceph_writepage(struct page *p
BUG_ON(!inode);
ihold(inode);
+ if (wbc->sync_mode == WB_SYNC_NONE &&
+ ceph_inode_to_client(inode)->write_congested)
+ return AOP_WRITEPAGE_ACTIVATE;
+
wait_on_page_fscache(page);
err = writepage_nounlock(page, wbc);
@@ -707,8 +711,7 @@ static void writepages_finish(struct cep
if (atomic_long_dec_return(&fsc->writeback_count) <
CONGESTION_OFF_THRESH(
fsc->mount_options->congestion_kb))
- clear_bdi_congested(inode_to_bdi(inode),
- BLK_RW_ASYNC);
+ fsc->write_congested = false;
ceph_put_snap_context(detach_page_private(page));
end_page_writeback(page);
@@ -760,6 +763,10 @@ static int ceph_writepages_start(struct
bool done = false;
bool caching = ceph_is_cache_enabled(inode);
+ if (wbc->sync_mode == WB_SYNC_NONE &&
+ fsc->write_congested)
+ return 0;
+
dout("writepages_start %p (mode=%s)\n", inode,
wbc->sync_mode == WB_SYNC_NONE ? "NONE" :
(wbc->sync_mode == WB_SYNC_ALL ? "ALL" : "HOLD"));
@@ -954,11 +961,8 @@ get_more_pages:
if (atomic_long_inc_return(&fsc->writeback_count) >
CONGESTION_ON_THRESH(
- fsc->mount_options->congestion_kb)) {
- set_bdi_congested(inode_to_bdi(inode),
- BLK_RW_ASYNC);
- }
-
+ fsc->mount_options->congestion_kb))
+ fsc->write_congested = true;
pages[locked_pages++] = page;
pvec.pages[i] = NULL;
--- a/fs/ceph/super.c~ceph-remove-reliance-on-bdi-congestion
+++ a/fs/ceph/super.c
@@ -802,6 +802,7 @@ static struct ceph_fs_client *create_fs_
fsc->have_copy_from2 = true;
atomic_long_set(&fsc->writeback_count, 0);
+ fsc->write_congested = false;
err = -ENOMEM;
/*
--- a/fs/ceph/super.h~ceph-remove-reliance-on-bdi-congestion
+++ a/fs/ceph/super.h
@@ -121,6 +121,7 @@ struct ceph_fs_client {
struct ceph_mds_client *mdsc;
atomic_long_t writeback_count;
+ bool write_congested;
struct workqueue_struct *inode_wq;
struct workqueue_struct *cap_wq;
_
