Re: [PATCH] raid6: fix the input of raid6 algorithm
On August 22, 2016 8:22:57 PM PDT, liuzhengy...@kylinos.cn wrote:
>
>To test and choose an best algorithm for raid6, disk number
>and disk data must be offered. Those input depend on page
>size and gfmul table at current time. It would lead the disk
>number less than 4 when the page size is more than 64KB.This
>patch would support arbitrarily page size by defining a macro
>for disk number and using random number to fill with disk data.
>
>Signed-off-by: ZhengYuan Liu
>---
> lib/raid6/algos.c | 36 ++--
> 1 file changed, 22 insertions(+), 14 deletions(-)
>
>diff --git a/lib/raid6/algos.c b/lib/raid6/algos.c
>index 975c6e0..f15a4d2 100644
>--- a/lib/raid6/algos.c
>+++ b/lib/raid6/algos.c
>@@ -23,6 +23,7 @@
> #else
> #include
> #include
>+#include
> #if !RAID6_USE_EMPTY_ZERO_PAGE
> /* In .bss so it's zeroed */
>const char raid6_empty_zero_page[PAGE_SIZE]
>__attribute__((aligned(256)));
>@@ -30,6 +31,8 @@ EXPORT_SYMBOL(raid6_empty_zero_page);
> #endif
> #endif
>
>+#define RAID6_DISKS 8
>+
> struct raid6_calls raid6_call;
> EXPORT_SYMBOL_GPL(raid6_call);
>
>@@ -129,7 +132,7 @@ 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)
>+ void *(*const dptrs)[RAID6_DISKS], const int disks)
> {
> unsigned long perf, bestgenperf, bestxorperf, j0, j1;
> int start = (disks>>1)-1, stop = disks-3; /* work on the second
> half
>of the disks */
>@@ -206,27 +209,32 @@ static inline const struct raid6_calls
>*raid6_choose_gen(
>
> int __init raid6_select_algo(void)
> {
>- const int disks = (65536/PAGE_SIZE)+2;
>+ const int disks = RAID6_DISKS;
>
> const struct raid6_calls *gen_best;
> const struct raid6_recov_calls *rec_best;
>- char *syndromes;
>- void *dptrs[(65536/PAGE_SIZE)+2];
>- int i;
>-
>- for (i = 0; i < disks-2; i++)
>- dptrs[i] = ((char *)raid6_gfmul) + PAGE_SIZE*i;
>+ char *disk_ptr;
>+ void *dptrs[RAID6_DISKS];
>+ int i, j;
>
>- /* Normal code - use a 2-page allocation to avoid D$ conflict */
>- syndromes = (void *) __get_free_pages(GFP_KERNEL, 1);
>+ /* use a 8-page allocation, The first 6 pages for disks
>+ and the last 2 pages for syndromes */
>+ disk_ptr = (void *) __get_free_pages(GFP_KERNEL, 3);
>
>- if (!syndromes) {
>+ if (!disk_ptr) {
> pr_err("raid6: Yikes! No memory available.\n");
> return -ENOMEM;
> }
>
>- dptrs[disks-2] = syndromes;
>- dptrs[disks-1] = syndromes + PAGE_SIZE;
>+ /* Fix-me: may should use get_random_bytes_arch() instead of
>get_random_bytes() */
>+ for (i = 0; i < disks-2; i++) {
>+ dptrs[i] = disk_ptr + PAGE_SIZE*i;
>+ for (j = 0; j < PAGE_SIZE; j++)
>+ get_random_bytes(dptrs[i]+j, 1);
>+ }
>+
>+ dptrs[disks-2] = disk_ptr + PAGE_SIZE*(disks-2);
>+ dptrs[disks-1] = disk_ptr + PAGE_SIZE*(disks-1);
>
> /* select raid gen_syndrome function */
> gen_best = raid6_choose_gen(&dptrs, disks);
>@@ -234,7 +242,7 @@ int __init raid6_select_algo(void)
> /* select raid recover functions */
> rec_best = raid6_choose_recov();
>
>- free_pages((unsigned long)syndromes, 1);
>+ free_pages((unsigned long)disk_ptr, 3);
>
> return gen_best && rec_best ? 0 : -EINVAL;
> }
Do you have any idea how long this takes to run? People are already
complaining about the boot time penalty. get_random_*() is quite expensive and
is overkill...
--
Sent from my Android device with K-9 Mail. Please excuse brevity and formatting.
Re: [PATCH] raid6: fix the input of raid6 algorithm
Oh, get_random_*() is really expensive. Thanks for your tips. The boot log on
my aarch64 showed bellow
told it taked about 0.6 second to fill with disk data.
[0.172831] DMA: preallocated 256 KiB pool for atomic allocations
[0.788664] raid6: int64x1 gen() 121 MB/s
[0.856613] raid6: int64x1 xor()74 MB/s
[0.924665] raid6: int64x2 gen() 166 MB/s
[0.992846] raid6: int64x2 xor()95 MB/s
[1.060681] raid6: int64x4 gen() 290 MB/s
[1.128774] raid6: int64x4 xor() 160 MB/s
[1.196933] raid6: int64x8 gen() 238 MB/s
[1.264937] raid6: int64x8 xor() 148 MB/s
[1.332878] raid6: neonx1 gen() 256 MB/s
[1.400975] raid6: neonx1 xor() 130 MB/s
[1.468951] raid6: neonx2 gen() 333 MB/s
[1.537085] raid6: neonx2 xor() 181 MB/s
[1.605042] raid6: neonx4 gen() 451 MB/s
[1.673121] raid6: neonx4 xor() 289 MB/s
[1.741143] raid6: neonx8 gen() 452 MB/s
[1.809151] raid6: neonx8 xor() 277 MB/s
[1.809154] raid6: using algorithm neonx8 gen() 452 MB/s
[1.809157] raid6: xor() 277 MB/s, rmw enabled
[1.809160] raid6: using intx1 recovery algorithm
I replaced get_random_* with a local PRNG based on well-know
"linear congruential bit". The patch was like this:
+/* use the linear congruential bit. */
+static int32_t get_random_number_by_lcb(void)
+{
+static int32_t seed = 1;
+int32_t ret = 0;
+ret = ((seed * 1103515245) + 12345) & 0x7fff;
+seed = ret;
+return ret;
+}
/* Try to pick the best algorithm */
/* This code uses the gfmul table as convenient data set to abuse */
@@ -229,8 +238,8 @@ int __init raid6_select_algo(void)
for (i = 0; i < disks-2; i++) {
dptrs[i] = disk_ptr + PAGE_SIZE*i;
- for (j = 0; j < PAGE_SIZE; j++)
- get_random_bytes(dptrs[i]+j, 1);
+ for (j = 0; j < PAGE_SIZE; j = j + 4)
+ *(int32_t *)(dptrs[i]+j) = get_random_number_by_lcb();
}
dptrs[disks-2] = disk_ptr + PAGE_SIZE*(disks-2);
The boot log with this patch was showd bellow, it taked about 0.08 second.
[0.172858] DMA: preallocated 256 KiB pool for atomic allocations
[0.256673] raid6: int64x1 gen() 121 MB/s
[0.324484] raid6: int64x1 xor()73 MB/s
[0.392606] raid6: int64x2 gen() 166 MB/s
[0.460309] raid6: int64x2 xor()92 MB/s
[0.528368] raid6: int64x4 gen() 290 MB/s
[0.596401] raid6: int64x4 xor() 156 MB/s
[0.664601] raid6: int64x8 gen() 238 MB/s
[0.732609] raid6: int64x8 xor() 148 MB/s
[0.800523] raid6: neonx1 gen() 256 MB/s
[0.868730] raid6: neonx1 xor() 129 MB/s
[0.936741] raid6: neonx2 gen() 334 MB/s
[1.004717] raid6: neonx2 xor() 202 MB/s
[1.072692] raid6: neonx4 gen() 451 MB/s
[1.140763] raid6: neonx4 xor() 260 MB/s
[1.208842] raid6: neonx8 gen() 452 MB/s
[1.276887] raid6: neonx8 xor() 277 MB/s
[1.276890] raid6: using algorithm neonx8 gen() 452 MB/s
[1.276894] raid6: xor() 277 MB/s, rmw enabled
[1.276897] raid6: using intx1 recovery algorithm
[1.276941] ACPI: Interpreter disabled.
I'm not familiar with spurious D$ conflicts and CPU cache behavior. How do you
think this PRNG or anything else I need to do?
-- Original --
From: "H. Peter Anvin";
Date: Tue, Aug 23, 2016 11:53 AM
To: "liuzhengyuan";
Cc: "shli"; "linux-raid";
"fenghua.yu";
"linux-kernel";
"liuzhengyuang521";
Subject: Re: [PATCH] raid6: fix the input of raid6 algorithm
Do you have any idea how long this takes to run? People are already
complaining about the boot time penalty. get_random_*() is quite expensive and
is overkill...
--
Sent from my Android device with K-9 Mail. Please excuse brevity and formatting.
