| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20111020155542.GA7054@localhost>
Date: Thu, 20 Oct 2011 23:55:42 +0800
From: Wu Fengguang <fengguang.wu@...el.com>
To: Trond Myklebust <Trond.Myklebust@...app.com>,
linux-nfs@...r.kernel.org
Cc: Peter Zijlstra <a.p.zijlstra@...llo.nl>,
"linux-fsdevel@...r.kernel.org" <linux-fsdevel@...r.kernel.org>,
Andrew Morton <akpm@...ux-foundation.org>,
Jan Kara <jack@...e.cz>, Christoph Hellwig <hch@....de>,
Dave Chinner <david@...morbit.com>,
Greg Thelen <gthelen@...gle.com>,
Minchan Kim <minchan.kim@...il.com>,
Vivek Goyal <vgoyal@...hat.com>,
Andrea Righi <arighi@...eler.com>,
linux-mm <linux-mm@...ck.org>,
LKML <linux-kernel@...r.kernel.org>
Subject: [PATCH 1/2] nfs: writeback pages wait queue
The generic writeback routines are departing from congestion_wait()
in preference of get_request_wait(), aka. waiting on the block queues.
Introduce the missing writeback wait queue for NFS, otherwise its
writeback pages will grow out of control, exhausting all PG_dirty pages.
Feng: do more coarse grained throttle on each ->writepages rather than
on each page, for better performance and avoid throttled-before-send-rpc
deadlock
CC: Jens Axboe <axboe@...nel.dk>
CC: Chris Mason <chris.mason@...cle.com>
CC: Peter Zijlstra <a.p.zijlstra@...llo.nl>
CC: Trond Myklebust <Trond.Myklebust@...app.com>
Signed-off-by: Feng Tang <feng.tang@...el.com>
Signed-off-by: Wu Fengguang <fengguang.wu@...el.com>
---
fs/nfs/client.c | 2
fs/nfs/write.c | 84 +++++++++++++++++++++++++++++++-----
include/linux/nfs_fs_sb.h | 1
3 files changed, 77 insertions(+), 10 deletions(-)
--- linux-next.orig/fs/nfs/write.c 2011-10-20 23:08:17.000000000 +0800
+++ linux-next/fs/nfs/write.c 2011-10-20 23:45:59.000000000 +0800
@@ -190,11 +190,64 @@ static int wb_priority(struct writeback_
* NFS congestion control
*/
+#define NFS_WAIT_PAGES (1024L >> (PAGE_SHIFT - 10))
int nfs_congestion_kb;
-#define NFS_CONGESTION_ON_THRESH (nfs_congestion_kb >> (PAGE_SHIFT-10))
-#define NFS_CONGESTION_OFF_THRESH \
- (NFS_CONGESTION_ON_THRESH - (NFS_CONGESTION_ON_THRESH >> 2))
+/*
+ * SYNC requests will block on (2*limit) and wakeup on (2*limit-NFS_WAIT_PAGES)
+ * ASYNC requests will block on (limit) and wakeup on (limit - NFS_WAIT_PAGES)
+ * In this way SYNC writes will never be blocked by ASYNC ones.
+ */
+
+static void nfs_set_congested(long nr, struct backing_dev_info *bdi)
+{
+ long limit = nfs_congestion_kb >> (PAGE_SHIFT - 10);
+
+ if (nr > limit && !test_bit(BDI_async_congested, &bdi->state))
+ set_bdi_congested(bdi, BLK_RW_ASYNC);
+ else if (nr > 2 * limit && !test_bit(BDI_sync_congested, &bdi->state))
+ set_bdi_congested(bdi, BLK_RW_SYNC);
+}
+
+static void nfs_wait_congested(int is_sync,
+ struct backing_dev_info *bdi,
+ wait_queue_head_t *wqh)
+{
+ int waitbit = is_sync ? BDI_sync_congested : BDI_async_congested;
+ DEFINE_WAIT(wait);
+
+ if (!test_bit(waitbit, &bdi->state))
+ return;
+
+ for (;;) {
+ prepare_to_wait(&wqh[is_sync], &wait, TASK_UNINTERRUPTIBLE);
+ if (!test_bit(waitbit, &bdi->state))
+ break;
+
+ io_schedule();
+ }
+ finish_wait(&wqh[is_sync], &wait);
+}
+
+static void nfs_wakeup_congested(long nr,
+ struct backing_dev_info *bdi,
+ wait_queue_head_t *wqh)
+{
+ long limit = nfs_congestion_kb >> (PAGE_SHIFT - 10);
+
+ if (nr < 2 * limit - min(limit / 8, NFS_WAIT_PAGES)) {
+ if (test_bit(BDI_sync_congested, &bdi->state))
+ clear_bdi_congested(bdi, BLK_RW_SYNC);
+ if (waitqueue_active(&wqh[BLK_RW_SYNC]))
+ wake_up(&wqh[BLK_RW_SYNC]);
+ }
+ if (nr < limit - min(limit / 8, NFS_WAIT_PAGES)) {
+ if (test_bit(BDI_async_congested, &bdi->state))
+ clear_bdi_congested(bdi, BLK_RW_ASYNC);
+ if (waitqueue_active(&wqh[BLK_RW_ASYNC]))
+ wake_up(&wqh[BLK_RW_ASYNC]);
+ }
+}
static int nfs_set_page_writeback(struct page *page)
{
@@ -205,11 +258,8 @@ static int nfs_set_page_writeback(struct
struct nfs_server *nfss = NFS_SERVER(inode);
page_cache_get(page);
- if (atomic_long_inc_return(&nfss->writeback) >
- NFS_CONGESTION_ON_THRESH) {
- set_bdi_congested(&nfss->backing_dev_info,
- BLK_RW_ASYNC);
- }
+ nfs_set_congested(atomic_long_inc_return(&nfss->writeback),
+ &nfss->backing_dev_info);
}
return ret;
}
@@ -221,8 +271,10 @@ static void nfs_end_page_writeback(struc
end_page_writeback(page);
page_cache_release(page);
- if (atomic_long_dec_return(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH)
- clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC);
+
+ nfs_wakeup_congested(atomic_long_dec_return(&nfss->writeback),
+ &nfss->backing_dev_info,
+ nfss->writeback_wait);
}
static struct nfs_page *nfs_find_and_lock_request(struct page *page, bool nonblock)
@@ -323,10 +375,17 @@ static int nfs_writepage_locked(struct p
int nfs_writepage(struct page *page, struct writeback_control *wbc)
{
+ struct inode *inode = page->mapping->host;
+ struct nfs_server *nfss = NFS_SERVER(inode);
int ret;
ret = nfs_writepage_locked(page, wbc);
unlock_page(page);
+
+ nfs_wait_congested(wbc->sync_mode == WB_SYNC_ALL,
+ &nfss->backing_dev_info,
+ nfss->writeback_wait);
+
return ret;
}
@@ -342,6 +401,7 @@ static int nfs_writepages_callback(struc
int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
{
struct inode *inode = mapping->host;
+ struct nfs_server *nfss = NFS_SERVER(inode);
unsigned long *bitlock = &NFS_I(inode)->flags;
struct nfs_pageio_descriptor pgio;
int err;
@@ -358,6 +418,10 @@ int nfs_writepages(struct address_space
err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio);
nfs_pageio_complete(&pgio);
+ nfs_wait_congested(wbc->sync_mode == WB_SYNC_ALL,
+ &nfss->backing_dev_info,
+ nfss->writeback_wait);
+
clear_bit_unlock(NFS_INO_FLUSHING, bitlock);
smp_mb__after_clear_bit();
wake_up_bit(bitlock, NFS_INO_FLUSHING);
--- linux-next.orig/include/linux/nfs_fs_sb.h 2011-10-20 23:08:17.000000000 +0800
+++ linux-next/include/linux/nfs_fs_sb.h 2011-10-20 23:45:12.000000000 +0800
@@ -102,6 +102,7 @@ struct nfs_server {
struct nfs_iostats __percpu *io_stats; /* I/O statistics */
struct backing_dev_info backing_dev_info;
atomic_long_t writeback; /* number of writeback pages */
+ wait_queue_head_t writeback_wait[2];
int flags; /* various flags */
unsigned int caps; /* server capabilities */
unsigned int rsize; /* read size */
--- linux-next.orig/fs/nfs/client.c 2011-10-20 23:08:17.000000000 +0800
+++ linux-next/fs/nfs/client.c 2011-10-20 23:45:12.000000000 +0800
@@ -1066,6 +1066,8 @@ static struct nfs_server *nfs_alloc_serv
INIT_LIST_HEAD(&server->layouts);
atomic_set(&server->active, 0);
+ init_waitqueue_head(&server->writeback_wait[BLK_RW_SYNC]);
+ init_waitqueue_head(&server->writeback_wait[BLK_RW_ASYNC]);
server->io_stats = nfs_alloc_iostats();
if (!server->io_stats) {
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists