aboutsummaryrefslogtreecommitdiffstats
path: root/crypto/async_tx/async_pq.c
diff options
context:
space:
mode:
authorMarkus Stockhausen <stockhausen@collogia.de>2014-12-15 12:57:05 +1100
committerNeilBrown <neilb@suse.de>2015-04-22 08:00:42 +1000
commit584acdd49cd2472ca0f5a06adbe979db82d0b4af (patch)
tree94abdc5ca0208e47275bc2a8ad82c2d25cefddfd /crypto/async_tx/async_pq.c
parentmd/raid6 algorithms: xor_syndrome() for SSE2 (diff)
downloadlinux-dev-584acdd49cd2472ca0f5a06adbe979db82d0b4af.tar.xz
linux-dev-584acdd49cd2472ca0f5a06adbe979db82d0b4af.zip
md/raid5: activate raid6 rmw feature
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>
Diffstat (limited to 'crypto/async_tx/async_pq.c')
-rw-r--r--crypto/async_tx/async_pq.c19
1 files changed, 16 insertions, 3 deletions
diff --git a/crypto/async_tx/async_pq.c b/crypto/async_tx/async_pq.c
index d05327caf69d..5d355e0c2633 100644
--- a/crypto/async_tx/async_pq.c
+++ b/crypto/async_tx/async_pq.c
@@ -124,6 +124,7 @@ do_sync_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
{
void **srcs;
int i;
+ int start = -1, stop = disks - 3;
if (submit->scribble)
srcs = submit->scribble;
@@ -134,10 +135,21 @@ do_sync_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
if (blocks[i] == NULL) {
BUG_ON(i > disks - 3); /* P or Q can't be zero */
srcs[i] = (void*)raid6_empty_zero_page;
- } else
+ } else {
srcs[i] = page_address(blocks[i]) + offset;
+ if (i < disks - 2) {
+ stop = i;
+ if (start == -1)
+ start = i;
+ }
+ }
}
- raid6_call.gen_syndrome(disks, len, srcs);
+ if (submit->flags & ASYNC_TX_PQ_XOR_DST) {
+ BUG_ON(!raid6_call.xor_syndrome);
+ if (start >= 0)
+ raid6_call.xor_syndrome(disks, start, stop, len, srcs);
+ } else
+ raid6_call.gen_syndrome(disks, len, srcs);
async_tx_sync_epilog(submit);
}
@@ -178,7 +190,8 @@ async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
if (device)
unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOIO);
- if (unmap &&
+ /* XORing P/Q is only implemented in software */
+ if (unmap && !(submit->flags & ASYNC_TX_PQ_XOR_DST) &&
(src_cnt <= dma_maxpq(device, 0) ||
dma_maxpq(device, DMA_PREP_CONTINUE) > 0) &&
is_dma_pq_aligned(device, offset, 0, len)) {