From cdb9481e388139a3ca534c46f58959971f4755d4 Mon Sep 17 00:00:00 2001
From: Nick Terrell <terrelln@fb.com>
Date: Wed, 5 Jun 2019 20:20:55 -0700
Subject: [PATCH] [libzstd] Optimize ZSTD_insertBt1() for repetitive data

We would only skip at most 192 bytes at a time before this diff.
This was added to optimize long matches and skip the middle of the
match. However, it doesn't handle the case of repetitive data.

This patch keeps the optimization, but also handles repetitive data
by taking the max of the two return values.

```
> for n in $(seq 9); do echo strategy=$n; dd status=none if=/dev/zero bs=1024k count=1000 | command time -f %U ./zstd --zstd=strategy=$n >/dev/null; done
strategy=1
0.27
strategy=2
0.23
strategy=3
0.27
strategy=4
0.43
strategy=5
0.56
strategy=6
0.43
strategy=7
0.34
strategy=8
0.34
strategy=9
0.35
```

At level 19 with multithreading the compressed size of `silesia.tar` regresses 300 bytes, and `enwik8` regresses 100 bytes.
In single threaded mode `enwik8` is also within 100 bytes, and I didn't test `silesia.tar`.

Fixes Issue #1634.
---
 lib/compress/zstd_opt.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/lib/compress/zstd_opt.c b/lib/compress/zstd_opt.c
index 12b56c70d..cf46e7501 100644
--- a/lib/compress/zstd_opt.c
+++ b/lib/compress/zstd_opt.c
@@ -506,9 +506,11 @@ static U32 ZSTD_insertBt1(
     }   }
 
     *smallerPtr = *largerPtr = 0;
-    if (bestLength > 384) return MIN(192, (U32)(bestLength - 384));   /* speed optimization */
-    assert(matchEndIdx > current + 8);
-    return matchEndIdx - (current + 8);
+    {   U32 positions = 0;
+        if (bestLength > 384) positions = MIN(192, (U32)(bestLength - 384));   /* speed optimization */
+        assert(matchEndIdx > current + 8);
+        return MAX(positions, matchEndIdx - (current + 8));
+    }
 }
 
 FORCE_INLINE_TEMPLATE