Pull md updates from Neil Brown:
"More updates that usual this time. A few have performance impacts
which hould mostly be positive, but RAID5 (in particular) can be very
work-load ensitive... We'll have to wait and see.
Highlights:
- "experimental" code for managing md/raid1 across a cluster using
DLM. Code is not ready for general use and triggers a WARNING if
used. However it is looking good and mostly done and having in
mainline will help co-ordinate development.
- RAID5/6 can now batch multiple (4K wide) stripe_heads so as to
handle a full (chunk wide) stripe as a single unit.
- RAID6 can now perform read-modify-write cycles which should help
performance on larger arrays: 6 or more devices.
- RAID5/6 stripe cache now grows and shrinks dynamically. The value
set is used as a minimum.
- Resync is now allowed to go a little faster than the 'mininum' when
there is competing IO. How much faster depends on the speed of the
devices, so the effective minimum should scale with device speed to
some extent"
* tag 'md/4.1' of git://neil.brown.name/md: (58 commits)
md/raid5: don't do chunk aligned read on degraded array.
md/raid5: allow the stripe_cache to grow and shrink.
md/raid5: change ->inactive_blocked to a bit-flag.
md/raid5: move max_nr_stripes management into grow_one_stripe and drop_one_stripe
md/raid5: pass gfp_t arg to grow_one_stripe()
md/raid5: introduce configuration option rmw_level
md/raid5: activate raid6 rmw feature
md/raid6 algorithms: xor_syndrome() for SSE2
md/raid6 algorithms: xor_syndrome() for generic int
md/raid6 algorithms: improve test program
md/raid6 algorithms: delta syndrome functions
raid5: handle expansion/resync case with stripe batching
raid5: handle io error of batch list
RAID5: batch adjacent full stripe write
raid5: track overwrite disk count
raid5: add a new flag to track if a stripe can be batched
raid5: use flex_array for scribble data
md raid0: access mddev->queue (request queue member) conditionally because it is not set when accessed from dm-raid
md: allow resync to go faster when there is competing IO.
md: remove 'go_faster' option from ->sync_request()
...
When array is degraded, read data landed on failed drives will result in
reading rest of data in a stripe. So a single sequential read would
result in same data being read twice.
This patch is to avoid chunk aligned read for degraded array. The
downside is to involve stripe cache which means associated CPU overhead
and extra memory copy.
Test Results:
Following test are done on a enterprise storage node with Seagate 6T SAS
drives and Xeon E5-2648L CPU (10 cores, 1.9Ghz), 10 disks MD RAID6 8+2,
chunk size 128 KiB.
I use FIO, using direct-io with various bs size, enough queue depth,
tested sequential and 100% random read against 3 array config:
1) optimal, as baseline;
2) degraded;
3) degraded with this patch.
Kernel version is 4.0-rc3.
Each individual test I only did once so there might be some variations,
but we just focus on big trend.
Sequential Read:
bs=(KiB) optimal(MiB/s) degraded(MiB/s) degraded-with-patch (MiB/s)
1024 1608 656 995
512 1624 710 956
256 1635 728 980
128 1636 771 983
64 1612 1119 1000
32 1580 1420 1004
16 1368 688 986
8 768 647 953
4 411 413 850
Random Read:
bs=(KiB) optimal(IOPS) degraded(IOPS) degraded-with-patch (IOPS)
1024 163 160 156
512 274 273 272
256 426 428 424
128 576 592 591
64 726 724 726
32 849 848 837
16 900 970 971
8 927 940 929
4 948 940 955
Some notes:
* In sequential + optimal, as bs size getting smaller, the FIO thread
become CPU bound.
* In sequential + degraded, there's big increase when bs is 64K and
32K, I don't have explanation.
* In sequential + degraded-with-patch, the MD thread mostly become CPU
bound.
If you want to we can discuss specific data point in those data. But in
general it seems with this patch, we have more predictable and in most
cases significant better sequential read performance when array is
degraded, and almost no noticeable impact on random read.
Performance is a complicated thing, the patch works well for this
particular configuration, but may not be universal. For example I
imagine testing on all SSD array may have very different result. But I
personally think in most cases IO bandwidth is more scarce resource than
CPU.
Signed-off-by: Eric Mei <eric.mei@seagate.com>
Signed-off-by: NeilBrown <neilb@suse.de>
The default setting of 256 stripe_heads is probably
much too small for many configurations. So it is best to make it
auto-configure.
Shrinking the cache under memory pressure is easy. The only
interesting part here is that we put a fairly high cost
('seeks') on shrinking the cache as the cost is greater than
just having to read more data, it reduces parallelism.
Growing the cache on demand needs to be done carefully. If we allow
fast growth, that can upset memory balance as lots of dirty memory can
quickly turn into lots of memory queued in the stripe_cache.
It is important for the raid5 block device to appear congested to
allow write-throttling to work.
So we only add stripes slowly. We set a flag when an allocation
fails because all stripes are in use, allocate at a convenient
time when that flag is set, and don't allow it to be set again
until at least one stripe_head has been released for re-use.
This means that a spurt of requests will only cause one stripe_head
to be allocated, but a steady stream of requests will slowly
increase the cache size - until memory pressure puts it back again.
It could take hours to reach a steady state.
The value written to, and displayed in, stripe_cache_size is
used as a minimum. The cache can grow above this and shrink back
down to it. The actual size is not directly visible, though it can
be deduced to some extent by watching stripe_cache_active.
Signed-off-by: NeilBrown <neilb@suse.de>
Rather than adjusting max_nr_stripes whenever {grow,drop}_one_stripe()
succeeds, do it inside the functions.
Also choose the correct hash to handle next inside the functions.
This removes duplication and will help with future new uses of
{grow,drop}_one_stripe.
This also fixes a minor bug where the "md/raid:%md: allocate XXkB"
message always said "0kB".
Signed-off-by: NeilBrown <neilb@suse.de>
Depending on the available coding we allow optimized rmw logic for write
operations. To support easier testing this patch allows manual control
of the rmw/rcw descision through the interface /sys/block/mdX/md/rmw_level.
The configuration can handle three levels of control.
rmw_level=0: Disable rmw for all RAID types. Hardware assisted P/Q
calculation has no implementation path yet to factor in/out chunks of
a syndrome. Enforcing this level can be benefical for slow CPUs with
hardware syndrome support and fast SSDs.
rmw_level=1: Estimate rmw IOs and rcw IOs. Execute rmw only if we will
save IOs. This equals the "old" unpatched behaviour and will be the
default.
rmw_level=2: Execute rmw even if calculated IOs for rmw and rcw are
equal. We might have higher CPU consumption because of calculating the
parity twice but it can be benefical otherwise. E.g. RAID4 with fast
dedicated parity disk/SSD. The option is implemented just to be
forward-looking and will ONLY work with this patch!
Signed-off-by: Markus Stockhausen <stockhausen@collogia.de>
Signed-off-by: NeilBrown <neilb@suse.de>
Glue it altogehter. The raid6 rmw path should work the same as the
already existing raid5 logic. So emulate the prexor handling/flags
and split functions as needed.
1) Enable xor_syndrome() in the async layer.
2) Split ops_run_prexor() into RAID4/5 and RAID6 logic. Xor the syndrome
at the start of a rmw run as we did it before for the single parity.
3) Take care of rmw run in ops_run_reconstruct6(). Again process only
the changed pages to get syndrome back into sync.
4) Enhance set_syndrome_sources() to fill NULL pages if we are in a rmw
run. The lower layers will calculate start & end pages from that and
call the xor_syndrome() correspondingly.
5) Adapt the several places where we ignored Q handling up to now.
Performance numbers for a single E5630 system with a mix of 10 7200k
desktop/server disks. 300 seconds random write with 8 threads onto a
3,2TB (10*400GB) RAID6 64K chunk without spare (group_thread_cnt=4)
bsize rmw_level=1 rmw_level=0 rmw_level=1 rmw_level=0
skip_copy=1 skip_copy=1 skip_copy=0 skip_copy=0
4K 115 KB/s 141 KB/s 165 KB/s 140 KB/s
8K 225 KB/s 275 KB/s 324 KB/s 274 KB/s
16K 434 KB/s 536 KB/s 640 KB/s 534 KB/s
32K 751 KB/s 1,051 KB/s 1,234 KB/s 1,045 KB/s
64K 1,339 KB/s 1,958 KB/s 2,282 KB/s 1,962 KB/s
128K 2,673 KB/s 3,862 KB/s 4,113 KB/s 3,898 KB/s
256K 7,685 KB/s 7,539 KB/s 7,557 KB/s 7,638 KB/s
512K 19,556 KB/s 19,558 KB/s 19,652 KB/s 19,688 Kb/s
Signed-off-by: Markus Stockhausen <stockhausen@collogia.de>
Signed-off-by: NeilBrown <neilb@suse.de>
expansion/resync can grab a stripe when the stripe is in batch list. Since all
stripes in batch list must be in the same state, we can't allow some stripes
run into expansion/resync. So we delay expansion/resync for stripe in batch
list.
Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>
If io error happens in any stripe of a batch list, the batch list will be
split, then normal process will run for the stripes in the list.
Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>
stripe cache is 4k size. Even adjacent full stripe writes are handled in 4k
unit. Idealy we should use big size for adjacent full stripe writes. Bigger
stripe cache size means less stripes runing in the state machine so can reduce
cpu overhead. And also bigger size can cause bigger IO size dispatched to under
layer disks.
With below patch, we will automatically batch adjacent full stripe write
together. Such stripes will be added to the batch list. Only the first stripe
of the list will be put to handle_list and so run handle_stripe(). Some steps
of handle_stripe() are extended to cover all stripes of the list, including
ops_run_io, ops_run_biodrain and so on. With this patch, we have less stripes
running in handle_stripe() and we send IO of whole stripe list together to
increase IO size.
Stripes added to a batch list have some limitations. A batch list can only
include full stripe write and can't cross chunk boundary to make sure stripes
have the same parity disks. Stripes in a batch list must be in the same state
(no written, toread and so on). If a stripe is in a batch list, all new
read/write to add_stripe_bio will be blocked to overlap conflict till the batch
list is handled. The limitations will make sure stripes in a batch list be in
exactly the same state in the life circly.
I did test running 160k randwrite in a RAID5 array with 32k chunk size and 6
PCIe SSD. This patch improves around 30% performance and IO size to under layer
disk is exactly 32k. I also run a 4k randwrite test in the same array to make
sure the performance isn't changed with the patch.
Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>
Track overwrite disk count, so we can know if a stripe is a full stripe write.
Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>
A freshly new stripe with write request can be batched. Any time the stripe is
handled or new read is queued, the flag will be cleared.
Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>
Use flex_array for scribble data. Next patch will batch several stripes
together, so scribble data should be able to cover several stripes, so this
patch also allocates scribble data for stripes across a chunk.
Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>
The patch makes 3 references to mddev->queue in the raid0 personality
conditional in order to allow for it to be accessed from dm-raid.
Mandatory, because md instances underneath dm-raid don't manage
a request queue of their own which'd lead to oopses without the patch.
Signed-off-by: Heinz Mauelshagen <heinzm@redhat.com>
Tested-by: Heinz Mauelshagen <heinzm@redhat.com>
Signed-off-by: NeilBrown <neilb@suse.de>
When md notices non-sync IO happening while it is trying
to resync (or reshape or recover) it slows down to the
set minimum.
The default minimum might have made sense many years ago
but the drives have become faster. Changing the default
to match the times isn't really a long term solution.
This patch changes the code so that instead of waiting until the speed
has dropped to the target, it just waits until pending requests
have completed.
This means that the delay inserted is a function of the speed
of the devices.
Testing shows that:
- for some loads, the resync speed is unchanged. For those loads
increasing the minimum doesn't change the speed either.
So this is a good result. To increase resync speed under such
loads we would probably need to increase the resync window
size.
- for other loads, resync speed does increase to a reasonable
fraction (e.g. 20%) of maximum possible, and throughput of
the load only drops a little bit (e.g. 10%)
- for other loads, throughput of the non-sync load drops quite a bit
more. These seem to be latency-sensitive loads.
So it isn't a perfect solution, but it is mostly an improvement.
Signed-off-by: NeilBrown <neilb@suse.de>
This option is not well justified and testing suggests that
it hardly ever makes any difference.
The comment suggests there might be a need to wait for non-resync
activity indicated by ->nr_waiting, however raise_barrier()
already waits for all of that.
So just remove it to simplify reasoning about speed limiting.
This allows us to remove a 'FIXME' comment from raid5.c as that
never used the flag.
Signed-off-by: NeilBrown <neilb@suse.de>
There is really no need for sync_min to be a multiple of
chunk_size, and values read from here often aren't.
That means you cannot read a value and expect to be able
to write it back later.
So remove the chunk_size check, and round down to a multiple
of 4K, to be sure everything works with 4K-sector devices.
Signed-off-by: NeilBrown <neilb@suse.de>
When "re-add" is writted to /sys/block/mdXX/md/dev-YYY/state,
the clustered md:
1. Sends RE_ADD message with the desc_nr. Nodes receiving the message
clear the Faulty bit in their respective rdev->flags.
2. The node initiating re-add, gathers the bitmaps of all nodes
and copies them into the local bitmap. It does not clear the bitmap
from which it is copying.
3. Initiating node schedules a md recovery to sync the devices.
Signed-off-by: Guoqing Jiang <gqjiang@suse.com>
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
Signed-off-by: NeilBrown <neilb@suse.de>
This adds the capability of re-adding a failed disk by
writing "re-add" to /sys/block/mdXX/md/dev-YYY/state.
This facilitates adding disks which have encountered a temporary
error such as a network disconnection/hiccup in an iSCSI device,
or a SAN cable disconnection which has been restored. In such
a situation, you do not need to remove and re-add the device.
Writing re-add to the failed device's state would add it again
to the array and perform the recovery of only the blocks which
were written after the device failed.
This works for generic md, and is not related to clustering. However,
this patch is to ease re-add operations listed above in clustering
environments.
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
Signed-off-by: NeilBrown <neilb@suse.de>
This adds "remove" capabilities for the clustered environment.
When a user initiates removal of a device from the array, a
REMOVE message with disk number in the array is sent to all
the nodes which kick the respective device in their own array.
This facilitates the removal of failed devices.
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
Signed-off-by: NeilBrown <neilb@suse.de>
This is required by the clustering module (patches to follow) to
find the device to remove or re-add.
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
Signed-off-by: NeilBrown <neilb@suse.de>
This export is required for clustering module in order to
co-ordinate remove/readd a rdev from all nodes.
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
Signed-off-by: NeilBrown <neilb@suse.de>
Since the node num of md-cluster is from zero, and
cinfo->slot_number represents the slot num of dlm,
no need to check for equality.
Signed-off-by: Guoqing Jiang <gqjiang@suse.com>
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
Signed-off-by: NeilBrown <neilb@suse.de>
