[devel] [PATCH] pack.c: downgrade XZ->LZMA automatically for small payloads

[Alexey Tourbin]

Recent changes left downgradeLzmaLevel dysfunctional (because it does
not recognize 'T').  In my view, the only advantage of XZ over LZMA is
that XZ can can split input into blocks and compress them in parallel
(resulting in a speed-up).  Other advantages, such as a checksum, are
immaterial for our purpose (because the package manager must verify the
integrity of a package beforehand).  Therefore, downgradeLzmaLevel will
also downgrade XZ->LZMA automatically, for payloads smaller than
5*dictSize (the default blockSize being 3*dictSize, so that there are
at least two blocks, the second block not too small).
---
 build/pack.c | 54 ++++++++++++++++++++++++++++++++++++++++------------
 1 file changed, 42 insertions(+), 12 deletions(-)

diff --git a/build/pack.c b/build/pack.c
index 23ad89e72..a779e7918 100644
--- a/build/pack.c
+++ b/build/pack.c
@@ -416,30 +416,60 @@ static uint64_t calcArchiveSize(TFI_t fi)
 // which is 8-64M.  For smaller inputs, levels 7-9 are downgraded automatically.
 static void downgradeLzmaLevel(char *mode, uint64_t archiveSize)
 {
-#define C(c) if (!(c)) return
-    C(mode[1] == '7' || mode[1] == '8' || mode[1] == '9');
-    C(mode[2] == '.');
-    C(mode[3] == 'l' || mode[3] == 'x');
-    C(mode[4] == 'z');
+    if (!(mode[1] >= '0' && mode[1] <= '9'))
+	return;
+    char *p = &mode[2];
+    if (*p == 'T') {
+	do
+	    p++;
+	while (*p >= '0' && *p <= '9');
+    }
+    if (!(*p == '.' && (p[1] != 'l' || p[1] == 'x') && p[2] == 'z'))
+	return;
 #define S(m) ((m << 20) + (m << 10))
+    // For small payloads, downgrade XZ->LZMA automatically.  XZ only makes
+    // sense in multi-threaded mode (to speed up compression).  The default
+    // block size in multi-threaded mode is three times the dictionary size.
+    // There has to be at least two blocks, the second block not too small,
+    // so we require at least five times the dictionary size.
+#define T(m) ((m << 20) * 5)
+#define ForceLzma memcpy(&mode[2], ".lzdio", 7)
     switch (mode[1]) {
     case '9':
-	if (archiveSize > S(32))
-	    break;
+	if (archiveSize < T(64)) ForceLzma;
+	if (archiveSize > S(32)) break;
 	mode[1] = '8';
 	/*@fallthrough@*/
     case '8':
-	if (archiveSize > S(16))
-	    break;
+	if (archiveSize < T(32)) ForceLzma;
+	if (archiveSize > S(16)) break;
 	mode[1] = '7';
 	/*@fallthrough@*/
     case '7':
-	if (archiveSize > S(8))
-	    break;
+	if (archiveSize < T(16)) ForceLzma;
+	if (archiveSize > S(8)) break;
 	mode[1] = '6';
+	/*@fallthrough@*/
+    case '6':
+    case '5':
+	if (archiveSize < T(8)) ForceLzma;
+	break;
+    case '4':
+    case '3':
+	if (archiveSize < T(4)) ForceLzma;
+	break;
+    case '2':
+	if (archiveSize < T(2)) ForceLzma;
+	break;
+    case '1':
+	if (archiveSize < T(1)) ForceLzma;
+	break;
+    case 0:
+	// Dictionary size is 256K, but block size is 1M.
+	if (archiveSize < (7<<18)) ForceLzma;
     }
-#undef C
 #undef S
+#undef T
 }
 
 int writeRPM(Header *hdrp, const char *fileName, int type,
-- 
2.25.4