The patch titled
md: define ->congested_fn for raid1, raid10, and multipath
has been added to the -mm tree. Its filename is
md-define-congested_fn-for-raid1-raid10-and-multipath.patch
See http://www.zip.com.au/~akpm/linux/patches/stuff/added-to-mm.txt to find
out what to do about this
------------------------------------------------------
Subject: md: define ->congested_fn for raid1, raid10, and multipath
From: NeilBrown <neilb@xxxxxxx>
raid1, raid10 and multipath don't report their 'congested' status through
bdi_*_congested, but should.
This patch adds the appropriate functions which just check the 'congested'
status of all active members (with appropriate locking).
raid1 read_balance should be modified to prefer devices where
bdi_read_congested returns false. Then we could use the '&' branch rather
than the '|' branch. However that should would need some benchmarking first
to make sure it is actually a good idea.
Signed-off-by: Neil Brown <neilb@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxx>
---
drivers/md/multipath.c | 24 ++++++++++++++++++++++++
drivers/md/raid1.c | 28 ++++++++++++++++++++++++++++
drivers/md/raid10.c | 22 ++++++++++++++++++++++
3 files changed, 74 insertions(+)
diff -puN drivers/md/multipath.c~md-define-congested_fn-for-raid1-raid10-and-multipath drivers/md/multipath.c
--- a/drivers/md/multipath.c~md-define-congested_fn-for-raid1-raid10-and-multipath
+++ a/drivers/md/multipath.c
@@ -228,6 +228,28 @@ static int multipath_issue_flush(request
rcu_read_unlock();
return ret;
}
+static int multipath_congested(void *data, int bits)
+{
+ mddev_t *mddev = data;
+ multipath_conf_t *conf = mddev_to_conf(mddev);
+ int i, ret = 0;
+
+ rcu_read_lock();
+ for (i = 0; i < mddev->raid_disks ; i++) {
+ mdk_rdev_t *rdev = rcu_dereference(conf->multipaths[i].rdev);
+ if (rdev && !test_bit(Faulty, &rdev->flags)) {
+ request_queue_t *q = bdev_get_queue(rdev->bdev);
+
+ ret |= bdi_congested(&q->backing_dev_info, bits);
+ /* Just like multipath_map, we just check the
+ * first available device
+ */
+ break;
+ }
+ }
+ rcu_read_unlock();
+ return ret;
+}
/*
* Careful, this can execute in IRQ contexts as well!
@@ -509,6 +531,8 @@ static int multipath_run (mddev_t *mddev
mddev->queue->unplug_fn = multipath_unplug;
mddev->queue->issue_flush_fn = multipath_issue_flush;
+ mddev->queue->backing_dev_info.congested_fn = multipath_congested;
+ mddev->queue->backing_dev_info.congested_data = mddev;
return 0;
diff -puN drivers/md/raid1.c~md-define-congested_fn-for-raid1-raid10-and-multipath drivers/md/raid1.c
--- a/drivers/md/raid1.c~md-define-congested_fn-for-raid1-raid10-and-multipath
+++ a/drivers/md/raid1.c
@@ -601,6 +601,32 @@ static int raid1_issue_flush(request_que
return ret;
}
+static int raid1_congested(void *data, int bits)
+{
+ mddev_t *mddev = data;
+ conf_t *conf = mddev_to_conf(mddev);
+ int i, ret = 0;
+
+ rcu_read_lock();
+ for (i = 0; i < mddev->raid_disks; i++) {
+ mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
+ if (rdev && !test_bit(Faulty, &rdev->flags)) {
+ request_queue_t *q = bdev_get_queue(rdev->bdev);
+
+ /* Note the '|| 1' - when read_balance prefers
+ * non-congested targets, it can be removed
+ */
+ if ((bits & (1<<BDI_write_congested)) || 1)
+ ret |= bdi_congested(&q->backing_dev_info, bits);
+ else
+ ret &= bdi_congested(&q->backing_dev_info, bits);
+ }
+ }
+ rcu_read_unlock();
+ return ret;
+}
+
+
/* Barriers....
* Sometimes we need to suspend IO while we do something else,
* either some resync/recovery, or reconfigure the array.
@@ -1965,6 +1991,8 @@ static int run(mddev_t *mddev)
mddev->queue->unplug_fn = raid1_unplug;
mddev->queue->issue_flush_fn = raid1_issue_flush;
+ mddev->queue->backing_dev_info.congested_fn = raid1_congested;
+ mddev->queue->backing_dev_info.congested_data = mddev;
return 0;
diff -puN drivers/md/raid10.c~md-define-congested_fn-for-raid1-raid10-and-multipath drivers/md/raid10.c
--- a/drivers/md/raid10.c~md-define-congested_fn-for-raid1-raid10-and-multipath
+++ a/drivers/md/raid10.c
@@ -648,6 +648,26 @@ static int raid10_issue_flush(request_qu
return ret;
}
+static int raid10_congested(void *data, int bits)
+{
+ mddev_t *mddev = data;
+ conf_t *conf = mddev_to_conf(mddev);
+ int i, ret = 0;
+
+ rcu_read_lock();
+ for (i = 0; i < mddev->raid_disks && ret == 0; i++) {
+ mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
+ if (rdev && !test_bit(Faulty, &rdev->flags)) {
+ request_queue_t *q = bdev_get_queue(rdev->bdev);
+
+ ret |= bdi_congested(&q->backing_dev_info, bits);
+ }
+ }
+ rcu_read_unlock();
+ return ret;
+}
+
+
/* Barriers....
* Sometimes we need to suspend IO while we do something else,
* either some resync/recovery, or reconfigure the array.
@@ -2094,6 +2114,8 @@ static int run(mddev_t *mddev)
mddev->queue->unplug_fn = raid10_unplug;
mddev->queue->issue_flush_fn = raid10_issue_flush;
+ mddev->queue->backing_dev_info.congested_fn = raid10_congested;
+ mddev->queue->backing_dev_info.congested_data = mddev;
/* Calculate max read-ahead size.
* We need to readahead at least twice a whole stripe....
_
Patches currently in -mm which might be from neilb@xxxxxxx are
md-fix-issues-with-referencing-rdev-in-md-raid1.patch
change-return-value-from-queue_work.patch
vfs-destroy-the-dentries-contributed-by-a-superblock-on-unmounting.patch
knfsd-knfsd-add-some-missing-newlines-in-printks.patch
knfsd-knfsd-remove-an-unused-variable-from-e_show.patch
knfsd-knfsd-remove-an-unused-variable-from-auth_unix_lookup.patch
knfsd-add-a-callback-for-when-last-rpc-thread-finishes.patch
knfsd-add-a-callback-for-when-last-rpc-thread-finishes-tidy.patch
knfsd-be-more-selective-in-which-sockets-lockd-listens-on.patch
knfsd-remove-nfsd_versbits-as-intermediate-storage-for-desired-versions.patch
knfsd-separate-out-some-parts-of-nfsd_svc-which-start-nfs-servers.patch
knfsd-separate-out-some-parts-of-nfsd_svc-which-start-nfs-servers-tweaks.patch
knfsd-define-new-nfsdfs-file-portlist-contains-list-of-ports.patch
knfsd-define-new-nfsdfs-file-portlist-contains-list-of-ports-tidy.patch
knfsd-define-new-nfsdfs-file-portlist-contains-list-of-ports-fix.patch
knfsd-allow-sockets-to-be-passed-to-nfsd-via-portlist.patch
knfsd-use-seq_start_token-instead-of-hardcoded-magic-void1.patch
knfsd-have-ext2-reject-file-handles-with-bad-inode-numbers-early.patch
knfsd-have-ext2-reject-file-handles-with-bad-inode-numbers-early-tidy.patch
knfsd-make-ext3-reject-filehandles-referring-to-invalid-inode-numbers.patch
knfsd-make-ext3-reject-filehandles-referring-to-invalid-inode-numbers-tidy.patch
knfsd-drop-serv-option-to-svc_recv-and-svc_process.patch
knfsd-drop-serv-option-to-svc_recv-and-svc_process-nfs-callback-fix-nfs-callback-fix.patch
knfsd-check-return-value-of-lockd_up-in-write_ports.patch
knfsd-move-makesock-failed-warning-into-make_socks.patch
knfsd-correctly-handle-error-condition-from-lockd_up.patch
knfsd-move-tempsock-aging-to-a-timer.patch
knfsd-move-tempsock-aging-to-a-timer-tidy.patch
knfsd-convert-sk_inuse-to-atomic_t.patch
knfsd-use-new-lock-for-svc_sock-deferred-list.patch
knfsd-convert-sk_reserved-to-atomic_t.patch
knfsd-test-and-set-sk_busy-atomically.patch
knfsd-split-svc_serv-into-pools.patch
knfsd-split-svc_serv-into-pools-fix.patch
knfsd-add-svc_get.patch
knfsd-add-svc_set_num_threads.patch
knfsd-use-svc_set_num_threads-to-manage-threads-in-knfsd.patch
knfsd-make-rpc-threads-pools-numa-aware.patch
knfsd-make-rpc-threads-pools-numa-aware-fix.patch
knfsd-allow-admin-to-set-nthreads-per-node.patch
nfsd-lockdep-annotation.patch
knfsd-nfsd-lockdep-annotation-fix.patch
knfsd-call-lockd_down-when-closing-a-socket-via-a-write-to-nfsd-portlist.patch
knfsd-protect-update-to-sn_nrthreads-with-lock_kernel.patch
knfsd-fixed-handling-of-lockd-fail-when-adding-nfsd-socket.patch
knfsd-replace-two-page-lists-in-struct-svc_rqst-with-one.patch
knfsd-avoid-excess-stack-usage-in-svc_tcp_recvfrom.patch
knfsd-prepare-knfsd-for-support-of-rsize-wsize-of-up-to-1mb-over-tcp.patch
knfsd-allow-max-size-of-nfsd-payload-to-be-configured.patch
knfsd-make-nfsd-readahead-params-cache-smp-friendly.patch
knfsd-knfsd-cache-ipmap-per-tcp-socket.patch
md-the-scheduled-removal-of-the-start_array-ioctl-for-md.patch
md-fix-a-comment-that-is-wrong-in-raid5h.patch
md-factor-out-part-of-raid10d-into-a-separate-function.patch
md-replace-magic-numbers-in-sb_dirty-with-well-defined-bit-flags.patch
md-remove-the-working_disks-and-failed_disks-from-raid5-state-data.patch
md-remove-working_disks-from-raid10-state.patch
md-new-sysfs-interface-for-setting-bits-in-the-write-intent-bitmap.patch
md-remove-unnecessary-variable-x-in-stripe_to_pdidx.patch
md-factor-out-part-of-raid1d-into-a-separate-function.patch
md-remove-working_disks-from-raid1-state-data.patch
md-improve-locking-around-error-handling.patch
md-define-backing_dev_infocongested_fn-for-raid0-and-linear.patch
md-define-congested_fn-for-raid1-raid10-and-multipath.patch
md-add-a-congested_fn-function-for-raid5-6.patch
md-make-messages-about-resync-recovery-etc-more-specific.patch
md-dm-reduce-stack-usage-with-stacked-block-devices.patch
-
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
