md/raid6 algorithms: delta syndrome functions

v3: s-o-b comment, explanation of performance and descision for
the start/stop implementation

Implementing rmw functionality for RAID6 requires optimized syndrome
calculation. Up to now we can only generate a complete syndrome. The
target P/Q pages are always overwritten. With this patch we provide
a framework for inplace P/Q modification. In the first place simply
fill those functions with NULL values.

xor_syndrome() has two additional parameters: start & stop. These
will indicate the first and last page that are changing during a
rmw run. That makes it possible to avoid several unneccessary loops
and speed up calculation. The caller needs to implement the following
logic to make the functions work.

1) xor_syndrome(disks, start, stop, ...): "Remove" all data of source
blocks inside P/Q between (and including) start and end.

2) modify any block with start <= block <= stop

3) xor_syndrome(disks, start, stop, ...): "Reinsert" all data of
source blocks into P/Q between (and including) start and end.

Pages between start and stop that won't be changed should be filled
with a pointer to the kernel zero page. The reasons for not taking NULL
pages are:

1) Algorithms cross the whole source data line by line. Thus avoid
additional branches.

2) Having a NULL page avoids calculating the XOR P parity but still
need calulation steps for the Q parity. Depending on the algorithm
unrolling that might be only a difference of 2 instructions per loop.

The benchmark numbers of the gen_syndrome() functions are displayed in
the kernel log. Do the same for the xor_syndrome() functions. This
will help to analyze performance problems and give an rough estimate
how well the algorithm works. The choice of the fastest algorithm will
still depend on the gen_syndrome() performance.

With the start/stop page implementation the speed can vary a lot in real
life. E.g. a change of page 0 & page 15 on a stripe will be harder to
compute than the case where page 0 & page 1 are XOR candidates. To be not
to enthusiatic about the expected speeds we will run a worse case test
that simulates a change on the upper half of the stripe. So we do:

1) calculation of P/Q for the upper pages

2) continuation of Q for the lower (empty) pages

Signed-off-by: Markus Stockhausen <stockhausen@collogia.de>
Signed-off-by: NeilBrown <neilb@suse.de>

diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h
index 73069cb..a7a06d1 100644 (file)
--- a/include/linux/raid/pq.h
+++ b/include/linux/raid/pq.h
@@ -72,6 +72,7 @@ extern const char raid6_empty_zero_page[PAGE_SIZE];
 /* Routine choices */
 struct raid6_calls {
        void (*gen_syndrome)(int, size_t, void **);
+       void (*xor_syndrome)(int, int, int, size_t, void **);
        int  (*valid)(void);    /* Returns 1 if this routine set is usable */
        const char *name;       /* Name of this routine set */
        int prefer;             /* Has special performance attribute */

diff --git a/lib/raid6/algos.c b/lib/raid6/algos.c
index dbef231..975c6e0 100644 (file)
--- a/lib/raid6/algos.c
+++ b/lib/raid6/algos.c
@@ -131,11 +131,12 @@ static inline const struct raid6_recov_calls *raid6_choose_recov(void)
 static inline const struct raid6_calls *raid6_choose_gen(
        void *(*const dptrs)[(65536/PAGE_SIZE)+2], const int disks)
 {
-       unsigned long perf, bestperf, j0, j1;
+       unsigned long perf, bestgenperf, bestxorperf, j0, j1;
+       int start = (disks>>1)-1, stop = disks-3;       /* work on the second half of the disks */
        const struct raid6_calls *const *algo;
        const struct raid6_calls *best;
 
-       for (bestperf = 0, best = NULL, algo = raid6_algos; *algo; algo++) {
+       for (bestgenperf = 0, bestxorperf = 0, best = NULL, algo = raid6_algos; *algo; algo++) {
                if (!best || (*algo)->prefer >= best->prefer) {
                        if ((*algo)->valid && !(*algo)->valid())
                                continue;
@@ -153,19 +154,45 @@ static inline const struct raid6_calls *raid6_choose_gen(
                        }
                        preempt_enable();
 
-                       if (perf > bestperf) {
-                               bestperf = perf;
+                       if (perf > bestgenperf) {
+                               bestgenperf = perf;
                                best = *algo;
                        }
-                       pr_info("raid6: %-8s %5ld MB/s\n", (*algo)->name,
+                       pr_info("raid6: %-8s gen() %5ld MB/s\n", (*algo)->name,
                               (perf*HZ) >> (20-16+RAID6_TIME_JIFFIES_LG2));
+
+                       if (!(*algo)->xor_syndrome)
+                               continue;
+
+                       perf = 0;
+
+                       preempt_disable();
+                       j0 = jiffies;
+                       while ((j1 = jiffies) == j0)
+                               cpu_relax();
+                       while (time_before(jiffies,
+                                           j1 + (1<<RAID6_TIME_JIFFIES_LG2))) {
+                               (*algo)->xor_syndrome(disks, start, stop,
+                                                     PAGE_SIZE, *dptrs);
+                               perf++;
+                       }
+                       preempt_enable();
+
+                       if (best == *algo)
+                               bestxorperf = perf;
+
+                       pr_info("raid6: %-8s xor() %5ld MB/s\n", (*algo)->name,
+                               (perf*HZ) >> (20-16+RAID6_TIME_JIFFIES_LG2+1));
                }
        }
 
        if (best) {
-               pr_info("raid6: using algorithm %s (%ld MB/s)\n",
+               pr_info("raid6: using algorithm %s gen() %ld MB/s\n",
                       best->name,
-                      (bestperf*HZ) >> (20-16+RAID6_TIME_JIFFIES_LG2));
+                      (bestgenperf*HZ) >> (20-16+RAID6_TIME_JIFFIES_LG2));
+               if (best->xor_syndrome)
+                       pr_info("raid6: .... xor() %ld MB/s, rmw enabled\n",
+                              (bestxorperf*HZ) >> (20-16+RAID6_TIME_JIFFIES_LG2+1));
                raid6_call = *best;
        } else
                pr_err("raid6: Yikes!  No algorithm found!\n");

diff --cc lib/raid6/altivec.uc
Simple merge

diff --cc lib/raid6/avx2.c
Simple merge

diff --cc lib/raid6/int.uc
Simple merge

diff --cc lib/raid6/mmx.c
Simple merge

diff --cc lib/raid6/neon.c
Simple merge

diff --cc lib/raid6/sse1.c
Simple merge

diff --cc lib/raid6/sse2.c
Simple merge

diff --cc lib/raid6/tilegx.uc
Simple merge