1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360
|
#include "builtin.h"
#include "cache.h"
#include "repository.h"
#include "config.h"
#include "attr.h"
#include "object.h"
#include "blob.h"
#include "commit.h"
#include "tag.h"
#include "tree.h"
#include "delta.h"
#include "pack.h"
#include "pack-revindex.h"
#include "csum-file.h"
#include "tree-walk.h"
#include "diff.h"
#include "revision.h"
#include "list-objects.h"
#include "list-objects-filter.h"
#include "list-objects-filter-options.h"
#include "pack-objects.h"
#include "progress.h"
#include "refs.h"
#include "streaming.h"
#include "thread-utils.h"
#include "pack-bitmap.h"
#include "reachable.h"
#include "sha1-array.h"
#include "argv-array.h"
#include "list.h"
#include "packfile.h"
#include "object-store.h"
#include "dir.h"
#define IN_PACK(obj) oe_in_pack(&to_pack, obj)
#define SIZE(obj) oe_size(&to_pack, obj)
#define SET_SIZE(obj,size) oe_set_size(&to_pack, obj, size)
#define DELTA_SIZE(obj) oe_delta_size(&to_pack, obj)
#define DELTA(obj) oe_delta(&to_pack, obj)
#define DELTA_CHILD(obj) oe_delta_child(&to_pack, obj)
#define DELTA_SIBLING(obj) oe_delta_sibling(&to_pack, obj)
#define SET_DELTA(obj, val) oe_set_delta(&to_pack, obj, val)
#define SET_DELTA_SIZE(obj, val) oe_set_delta_size(&to_pack, obj, val)
#define SET_DELTA_CHILD(obj, val) oe_set_delta_child(&to_pack, obj, val)
#define SET_DELTA_SIBLING(obj, val) oe_set_delta_sibling(&to_pack, obj, val)
static const char *pack_usage[] = {
N_("git pack-objects --stdout [<options>...] [< <ref-list> | < <object-list>]"),
N_("git pack-objects [<options>...] <base-name> [< <ref-list> | < <object-list>]"),
NULL
};
/*
* Objects we are going to pack are collected in the `to_pack` structure.
* It contains an array (dynamically expanded) of the object data, and a map
* that can resolve SHA1s to their position in the array.
*/
static struct packing_data to_pack;
static struct pack_idx_entry **written_list;
static uint32_t nr_result, nr_written, nr_seen;
static int non_empty;
static int reuse_delta = 1, reuse_object = 1;
static int keep_unreachable, unpack_unreachable, include_tag;
static timestamp_t unpack_unreachable_expiration;
static int pack_loose_unreachable;
static int local;
static int have_non_local_packs;
static int incremental;
static int ignore_packed_keep_on_disk;
static int ignore_packed_keep_in_core;
static int allow_ofs_delta;
static struct pack_idx_option pack_idx_opts;
static const char *base_name;
static int progress = 1;
static int window = 10;
static unsigned long pack_size_limit;
static int depth = 50;
static int delta_search_threads;
static int pack_to_stdout;
static int num_preferred_base;
static struct progress *progress_state;
static struct packed_git *reuse_packfile;
static uint32_t reuse_packfile_objects;
static off_t reuse_packfile_offset;
static int use_bitmap_index_default = 1;
static int use_bitmap_index = -1;
static int write_bitmap_index;
static uint16_t write_bitmap_options;
static int exclude_promisor_objects;
static unsigned long delta_cache_size = 0;
static unsigned long max_delta_cache_size = DEFAULT_DELTA_CACHE_SIZE;
static unsigned long cache_max_small_delta_size = 1000;
static unsigned long window_memory_limit = 0;
static struct list_objects_filter_options filter_options;
enum missing_action {
MA_ERROR = 0, /* fail if any missing objects are encountered */
MA_ALLOW_ANY, /* silently allow ALL missing objects */
MA_ALLOW_PROMISOR, /* silently allow all missing PROMISOR objects */
};
static enum missing_action arg_missing_action;
static show_object_fn fn_show_object;
/*
* stats
*/
static uint32_t written, written_delta;
static uint32_t reused, reused_delta;
/*
* Indexed commits
*/
static struct commit **indexed_commits;
static unsigned int indexed_commits_nr;
static unsigned int indexed_commits_alloc;
static void index_commit_for_bitmap(struct commit *commit)
{
if (indexed_commits_nr >= indexed_commits_alloc) {
indexed_commits_alloc = (indexed_commits_alloc + 32) * 2;
REALLOC_ARRAY(indexed_commits, indexed_commits_alloc);
}
indexed_commits[indexed_commits_nr++] = commit;
}
static void *get_delta(struct object_entry *entry)
{
unsigned long size, base_size, delta_size;
void *buf, *base_buf, *delta_buf;
enum object_type type;
buf = read_object_file(&entry->idx.oid, &type, &size);
if (!buf)
die("unable to read %s", oid_to_hex(&entry->idx.oid));
base_buf = read_object_file(&DELTA(entry)->idx.oid, &type,
&base_size);
if (!base_buf)
die("unable to read %s",
oid_to_hex(&DELTA(entry)->idx.oid));
delta_buf = diff_delta(base_buf, base_size,
buf, size, &delta_size, 0);
if (!delta_buf || delta_size != DELTA_SIZE(entry))
die("delta size changed");
free(buf);
free(base_buf);
return delta_buf;
}
static unsigned long do_compress(void **pptr, unsigned long size)
{
git_zstream stream;
void *in, *out;
unsigned long maxsize;
git_deflate_init(&stream, pack_compression_level);
maxsize = git_deflate_bound(&stream, size);
in = *pptr;
out = xmalloc(maxsize);
*pptr = out;
stream.next_in = in;
stream.avail_in = size;
stream.next_out = out;
stream.avail_out = maxsize;
while (git_deflate(&stream, Z_FINISH) == Z_OK)
; /* nothing */
git_deflate_end(&stream);
free(in);
return stream.total_out;
}
static unsigned long write_large_blob_data(struct git_istream *st, struct hashfile *f,
const struct object_id *oid)
{
git_zstream stream;
unsigned char ibuf[1024 * 16];
unsigned char obuf[1024 * 16];
unsigned long olen = 0;
git_deflate_init(&stream, pack_compression_level);
for (;;) {
ssize_t readlen;
int zret = Z_OK;
readlen = read_istream(st, ibuf, sizeof(ibuf));
if (readlen == -1)
die(_("unable to read %s"), oid_to_hex(oid));
stream.next_in = ibuf;
stream.avail_in = readlen;
while ((stream.avail_in || readlen == 0) &&
(zret == Z_OK || zret == Z_BUF_ERROR)) {
stream.next_out = obuf;
stream.avail_out = sizeof(obuf);
zret = git_deflate(&stream, readlen ? 0 : Z_FINISH);
hashwrite(f, obuf, stream.next_out - obuf);
olen += stream.next_out - obuf;
}
if (stream.avail_in)
die(_("deflate error (%d)"), zret);
if (readlen == 0) {
if (zret != Z_STREAM_END)
die(_("deflate error (%d)"), zret);
break;
}
}
git_deflate_end(&stream);
return olen;
}
/*
* we are going to reuse the existing object data as is. make
* sure it is not corrupt.
*/
static int check_pack_inflate(struct packed_git *p,
struct pack_window **w_curs,
off_t offset,
off_t len,
unsigned long expect)
{
git_zstream stream;
unsigned char fakebuf[4096], *in;
int st;
memset(&stream, 0, sizeof(stream));
git_inflate_init(&stream);
do {
in = use_pack(p, w_curs, offset, &stream.avail_in);
stream.next_in = in;
stream.next_out = fakebuf;
stream.avail_out = sizeof(fakebuf);
st = git_inflate(&stream, Z_FINISH);
offset += stream.next_in - in;
} while (st == Z_OK || st == Z_BUF_ERROR);
git_inflate_end(&stream);
return (st == Z_STREAM_END &&
stream.total_out == expect &&
stream.total_in == len) ? 0 : -1;
}
static void copy_pack_data(struct hashfile *f,
struct packed_git *p,
struct pack_window **w_curs,
off_t offset,
off_t len)
{
unsigned char *in;
unsigned long avail;
while (len) {
in = use_pack(p, w_curs, offset, &avail);
if (avail > len)
avail = (unsigned long)len;
hashwrite(f, in, avail);
offset += avail;
len -= avail;
}
}
/* Return 0 if we will bust the pack-size limit */
static unsigned long write_no_reuse_object(struct hashfile *f, struct object_entry *entry,
unsigned long limit, int usable_delta)
{
unsigned long size, datalen;
unsigned char header[MAX_PACK_OBJECT_HEADER],
dheader[MAX_PACK_OBJECT_HEADER];
unsigned hdrlen;
enum object_type type;
void *buf;
struct git_istream *st = NULL;
const unsigned hashsz = the_hash_algo->rawsz;
if (!usable_delta) {
if (oe_type(entry) == OBJ_BLOB &&
oe_size_greater_than(&to_pack, entry, big_file_threshold) &&
(st = open_istream(&entry->idx.oid, &type, &size, NULL)) != NULL)
buf = NULL;
else {
buf = read_object_file(&entry->idx.oid, &type, &size);
if (!buf)
die(_("unable to read %s"),
oid_to_hex(&entry->idx.oid));
}
/*
* make sure no cached delta data remains from a
* previous attempt before a pack split occurred.
*/
FREE_AND_NULL(entry->delta_data);
entry->z_delta_size = 0;
} else if (entry->delta_data) {
size = DELTA_SIZE(entry);
buf = entry->delta_data;
entry->delta_data = NULL;
type = (allow_ofs_delta && DELTA(entry)->idx.offset) ?
OBJ_OFS_DELTA : OBJ_REF_DELTA;
} else {
buf = get_delta(entry);
size = DELTA_SIZE(entry);
type = (allow_ofs_delta && DELTA(entry)->idx.offset) ?
OBJ_OFS_DELTA : OBJ_REF_DELTA;
}
if (st) /* large blob case, just assume we don't compress well */
datalen = size;
else if (entry->z_delta_size)
datalen = entry->z_delta_size;
else
datalen = do_compress(&buf, size);
/*
* The object header is a byte of 'type' followed by zero or
* more bytes of length.
*/
hdrlen = encode_in_pack_object_header(header, sizeof(header),
type, size);
if (type == OBJ_OFS_DELTA) {
/*
* Deltas with relative base contain an additional
* encoding of the relative offset for the delta
* base from this object's position in the pack.
*/
off_t ofs = entry->idx.offset - DELTA(entry)->idx.offset;
unsigned pos = sizeof(dheader) - 1;
dheader[pos] = ofs & 127;
while (ofs >>= 7)
dheader[--pos] = 128 | (--ofs & 127);
if (limit && hdrlen + sizeof(dheader) - pos + datalen + hashsz >= limit) {
if (st)
close_istream(st);
free(buf);
return 0;
}
hashwrite(f, header, hdrlen);
hashwrite(f, dheader + pos, sizeof(dheader) - pos);
hdrlen += sizeof(dheader) - pos;
} else if (type == OBJ_REF_DELTA) {
/*
* Deltas with a base reference contain
* additional bytes for the base object ID.
*/
if (limit && hdrlen + hashsz + datalen + hashsz >= limit) {
if (st)
close_istream(st);
free(buf);
return 0;
}
hashwrite(f, header, hdrlen);
hashwrite(f, DELTA(entry)->idx.oid.hash, hashsz);
hdrlen += hashsz;
} else {
if (limit && hdrlen + datalen + hashsz >= limit) {
if (st)
close_istream(st);
free(buf);
return 0;
}
hashwrite(f, header, hdrlen);
}
if (st) {
datalen = write_large_blob_data(st, f, &entry->idx.oid);
close_istream(st);
} else {
hashwrite(f, buf, datalen);
free(buf);
}
return hdrlen + datalen;
}
/* Return 0 if we will bust the pack-size limit */
static off_t write_reuse_object(struct hashfile *f, struct object_entry *entry,
unsigned long limit, int usable_delta)
{
struct packed_git *p = IN_PACK(entry);
struct pack_window *w_curs = NULL;
struct revindex_entry *revidx;
off_t offset;
enum object_type type = oe_type(entry);
off_t datalen;
unsigned char header[MAX_PACK_OBJECT_HEADER],
dheader[MAX_PACK_OBJECT_HEADER];
unsigned hdrlen;
const unsigned hashsz = the_hash_algo->rawsz;
unsigned long entry_size = SIZE(entry);
if (DELTA(entry))
type = (allow_ofs_delta && DELTA(entry)->idx.offset) ?
OBJ_OFS_DELTA : OBJ_REF_DELTA;
hdrlen = encode_in_pack_object_header(header, sizeof(header),
type, entry_size);
offset = entry->in_pack_offset;
revidx = find_pack_revindex(p, offset);
datalen = revidx[1].offset - offset;
if (!pack_to_stdout && p->index_version > 1 &&
check_pack_crc(p, &w_curs, offset, datalen, revidx->nr)) {
error("bad packed object CRC for %s",
oid_to_hex(&entry->idx.oid));
unuse_pack(&w_curs);
return write_no_reuse_object(f, entry, limit, usable_delta);
}
offset += entry->in_pack_header_size;
datalen -= entry->in_pack_header_size;
if (!pack_to_stdout && p->index_version == 1 &&
check_pack_inflate(p, &w_curs, offset, datalen, entry_size)) {
error("corrupt packed object for %s",
oid_to_hex(&entry->idx.oid));
unuse_pack(&w_curs);
return write_no_reuse_object(f, entry, limit, usable_delta);
}
if (type == OBJ_OFS_DELTA) {
off_t ofs = entry->idx.offset - DELTA(entry)->idx.offset;
unsigned pos = sizeof(dheader) - 1;
dheader[pos] = ofs & 127;
while (ofs >>= 7)
dheader[--pos] = 128 | (--ofs & 127);
if (limit && hdrlen + sizeof(dheader) - pos + datalen + hashsz >= limit) {
unuse_pack(&w_curs);
return 0;
}
hashwrite(f, header, hdrlen);
hashwrite(f, dheader + pos, sizeof(dheader) - pos);
hdrlen += sizeof(dheader) - pos;
reused_delta++;
} else if (type == OBJ_REF_DELTA) {
if (limit && hdrlen + hashsz + datalen + hashsz >= limit) {
unuse_pack(&w_curs);
return 0;
}
hashwrite(f, header, hdrlen);
hashwrite(f, DELTA(entry)->idx.oid.hash, hashsz);
hdrlen += hashsz;
reused_delta++;
} else {
if (limit && hdrlen + datalen + hashsz >= limit) {
unuse_pack(&w_curs);
return 0;
}
hashwrite(f, header, hdrlen);
}
copy_pack_data(f, p, &w_curs, offset, datalen);
unuse_pack(&w_curs);
reused++;
return hdrlen + datalen;
}
/* Return 0 if we will bust the pack-size limit */
static off_t write_object(struct hashfile *f,
struct object_entry *entry,
off_t write_offset)
{
unsigned long limit;
off_t len;
int usable_delta, to_reuse;
if (!pack_to_stdout)
crc32_begin(f);
/* apply size limit if limited packsize and not first object */
if (!pack_size_limit || !nr_written)
limit = 0;
else if (pack_size_limit <= write_offset)
/*
* the earlier object did not fit the limit; avoid
* mistaking this with unlimited (i.e. limit = 0).
*/
limit = 1;
else
limit = pack_size_limit - write_offset;
if (!DELTA(entry))
usable_delta = 0; /* no delta */
else if (!pack_size_limit)
usable_delta = 1; /* unlimited packfile */
else if (DELTA(entry)->idx.offset == (off_t)-1)
usable_delta = 0; /* base was written to another pack */
else if (DELTA(entry)->idx.offset)
usable_delta = 1; /* base already exists in this pack */
else
usable_delta = 0; /* base could end up in another pack */
if (!reuse_object)
to_reuse = 0; /* explicit */
else if (!IN_PACK(entry))
to_reuse = 0; /* can't reuse what we don't have */
else if (oe_type(entry) == OBJ_REF_DELTA ||
oe_type(entry) == OBJ_OFS_DELTA)
/* check_object() decided it for us ... */
to_reuse = usable_delta;
/* ... but pack split may override that */
else if (oe_type(entry) != entry->in_pack_type)
to_reuse = 0; /* pack has delta which is unusable */
else if (DELTA(entry))
to_reuse = 0; /* we want to pack afresh */
else
to_reuse = 1; /* we have it in-pack undeltified,
* and we do not need to deltify it.
*/
if (!to_reuse)
len = write_no_reuse_object(f, entry, limit, usable_delta);
else
len = write_reuse_object(f, entry, limit, usable_delta);
if (!len)
return 0;
if (usable_delta)
written_delta++;
written++;
if (!pack_to_stdout)
entry->idx.crc32 = crc32_end(f);
return len;
}
enum write_one_status {
WRITE_ONE_SKIP = -1, /* already written */
WRITE_ONE_BREAK = 0, /* writing this will bust the limit; not written */
WRITE_ONE_WRITTEN = 1, /* normal */
WRITE_ONE_RECURSIVE = 2 /* already scheduled to be written */
};
static enum write_one_status write_one(struct hashfile *f,
struct object_entry *e,
off_t *offset)
{
off_t size;
int recursing;
/*
* we set offset to 1 (which is an impossible value) to mark
* the fact that this object is involved in "write its base
* first before writing a deltified object" recursion.
*/
recursing = (e->idx.offset == 1);
if (recursing) {
warning("recursive delta detected for object %s",
oid_to_hex(&e->idx.oid));
return WRITE_ONE_RECURSIVE;
} else if (e->idx.offset || e->preferred_base) {
/* offset is non zero if object is written already. */
return WRITE_ONE_SKIP;
}
/* if we are deltified, write out base object first. */
if (DELTA(e)) {
e->idx.offset = 1; /* now recurse */
switch (write_one(f, DELTA(e), offset)) {
case WRITE_ONE_RECURSIVE:
/* we cannot depend on this one */
SET_DELTA(e, NULL);
break;
default:
break;
case WRITE_ONE_BREAK:
e->idx.offset = recursing;
return WRITE_ONE_BREAK;
}
}
e->idx.offset = *offset;
size = write_object(f, e, *offset);
if (!size) {
e->idx.offset = recursing;
return WRITE_ONE_BREAK;
}
written_list[nr_written++] = &e->idx;
/* make sure off_t is sufficiently large not to wrap */
if (signed_add_overflows(*offset, size))
die("pack too large for current definition of off_t");
*offset += size;
return WRITE_ONE_WRITTEN;
}
static int mark_tagged(const char *path, const struct object_id *oid, int flag,
void *cb_data)
{
struct object_id peeled;
struct object_entry *entry = packlist_find(&to_pack, oid->hash, NULL);
if (entry)
entry->tagged = 1;
if (!peel_ref(path, &peeled)) {
entry = packlist_find(&to_pack, peeled.hash, NULL);
if (entry)
entry->tagged = 1;
}
return 0;
}
static inline void add_to_write_order(struct object_entry **wo,
unsigned int *endp,
struct object_entry *e)
{
if (e->filled)
return;
wo[(*endp)++] = e;
e->filled = 1;
}
static void add_descendants_to_write_order(struct object_entry **wo,
unsigned int *endp,
struct object_entry *e)
{
int add_to_order = 1;
while (e) {
if (add_to_order) {
struct object_entry *s;
/* add this node... */
add_to_write_order(wo, endp, e);
/* all its siblings... */
for (s = DELTA_SIBLING(e); s; s = DELTA_SIBLING(s)) {
add_to_write_order(wo, endp, s);
}
}
/* drop down a level to add left subtree nodes if possible */
if (DELTA_CHILD(e)) {
add_to_order = 1;
e = DELTA_CHILD(e);
} else {
add_to_order = 0;
/* our sibling might have some children, it is next */
if (DELTA_SIBLING(e)) {
e = DELTA_SIBLING(e);
continue;
}
/* go back to our parent node */
e = DELTA(e);
while (e && !DELTA_SIBLING(e)) {
/* we're on the right side of a subtree, keep
* going up until we can go right again */
e = DELTA(e);
}
if (!e) {
/* done- we hit our original root node */
return;
}
/* pass it off to sibling at this level */
e = DELTA_SIBLING(e);
}
};
}
static void add_family_to_write_order(struct object_entry **wo,
unsigned int *endp,
struct object_entry *e)
{
struct object_entry *root;
for (root = e; DELTA(root); root = DELTA(root))
; /* nothing */
add_descendants_to_write_order(wo, endp, root);
}
static struct object_entry **compute_write_order(void)
{
unsigned int i, wo_end, last_untagged;
struct object_entry **wo;
struct object_entry *objects = to_pack.objects;
for (i = 0; i < to_pack.nr_objects; i++) {
objects[i].tagged = 0;
objects[i].filled = 0;
SET_DELTA_CHILD(&objects[i], NULL);
SET_DELTA_SIBLING(&objects[i], NULL);
}
/*
* Fully connect delta_child/delta_sibling network.
* Make sure delta_sibling is sorted in the original
* recency order.
*/
for (i = to_pack.nr_objects; i > 0;) {
struct object_entry *e = &objects[--i];
if (!DELTA(e))
continue;
/* Mark me as the first child */
e->delta_sibling_idx = DELTA(e)->delta_child_idx;
SET_DELTA_CHILD(DELTA(e), e);
}
/*
* Mark objects that are at the tip of tags.
*/
for_each_tag_ref(mark_tagged, NULL);
/*
* Give the objects in the original recency order until
* we see a tagged tip.
*/
ALLOC_ARRAY(wo, to_pack.nr_objects);
for (i = wo_end = 0; i < to_pack.nr_objects; i++) {
if (objects[i].tagged)
break;
add_to_write_order(wo, &wo_end, &objects[i]);
}
last_untagged = i;
/*
* Then fill all the tagged tips.
*/
for (; i < to_pack.nr_objects; i++) {
if (objects[i].tagged)
add_to_write_order(wo, &wo_end, &objects[i]);
}
/*
* And then all remaining commits and tags.
*/
for (i = last_untagged; i < to_pack.nr_objects; i++) {
if (oe_type(&objects[i]) != OBJ_COMMIT &&
oe_type(&objects[i]) != OBJ_TAG)
continue;
add_to_write_order(wo, &wo_end, &objects[i]);
}
/*
* And then all the trees.
*/
for (i = last_untagged; i < to_pack.nr_objects; i++) {
if (oe_type(&objects[i]) != OBJ_TREE)
continue;
add_to_write_order(wo, &wo_end, &objects[i]);
}
/*
* Finally all the rest in really tight order
*/
for (i = last_untagged; i < to_pack.nr_objects; i++) {
if (!objects[i].filled)
add_family_to_write_order(wo, &wo_end, &objects[i]);
}
if (wo_end != to_pack.nr_objects)
die("ordered %u objects, expected %"PRIu32, wo_end, to_pack.nr_objects);
return wo;
}
static off_t write_reused_pack(struct hashfile *f)
{
unsigned char buffer[8192];
off_t to_write, total;
int fd;
if (!is_pack_valid(reuse_packfile))
die("packfile is invalid: %s", reuse_packfile->pack_name);
fd = git_open(reuse_packfile->pack_name);
if (fd < 0)
die_errno("unable to open packfile for reuse: %s",
reuse_packfile->pack_name);
if (lseek(fd, sizeof(struct pack_header), SEEK_SET) == -1)
die_errno("unable to seek in reused packfile");
if (reuse_packfile_offset < 0)
reuse_packfile_offset = reuse_packfile->pack_size - the_hash_algo->rawsz;
total = to_write = reuse_packfile_offset - sizeof(struct pack_header);
while (to_write) {
int read_pack = xread(fd, buffer, sizeof(buffer));
if (read_pack <= 0)
die_errno("unable to read from reused packfile");
if (read_pack > to_write)
read_pack = to_write;
hashwrite(f, buffer, read_pack);
to_write -= read_pack;
/*
* We don't know the actual number of objects written,
* only how many bytes written, how many bytes total, and
* how many objects total. So we can fake it by pretending all
* objects we are writing are the same size. This gives us a
* smooth progress meter, and at the end it matches the true
* answer.
*/
written = reuse_packfile_objects *
(((double)(total - to_write)) / total);
display_progress(progress_state, written);
}
close(fd);
written = reuse_packfile_objects;
display_progress(progress_state, written);
return reuse_packfile_offset - sizeof(struct pack_header);
}
static const char no_split_warning[] = N_(
"disabling bitmap writing, packs are split due to pack.packSizeLimit"
);
static void write_pack_file(void)
{
uint32_t i = 0, j;
struct hashfile *f;
off_t offset;
uint32_t nr_remaining = nr_result;
time_t last_mtime = 0;
struct object_entry **write_order;
if (progress > pack_to_stdout)
progress_state = start_progress(_("Writing objects"), nr_result);
ALLOC_ARRAY(written_list, to_pack.nr_objects);
write_order = compute_write_order();
do {
struct object_id oid;
char *pack_tmp_name = NULL;
if (pack_to_stdout)
f = hashfd_throughput(1, "<stdout>", progress_state);
else
f = create_tmp_packfile(&pack_tmp_name);
offset = write_pack_header(f, nr_remaining);
if (reuse_packfile) {
off_t packfile_size;
assert(pack_to_stdout);
packfile_size = write_reused_pack(f);
offset += packfile_size;
}
nr_written = 0;
for (; i < to_pack.nr_objects; i++) {
struct object_entry *e = write_order[i];
if (write_one(f, e, &offset) == WRITE_ONE_BREAK)
break;
display_progress(progress_state, written);
}
/*
* Did we write the wrong # entries in the header?
* If so, rewrite it like in fast-import
*/
if (pack_to_stdout) {
finalize_hashfile(f, oid.hash, CSUM_HASH_IN_STREAM | CSUM_CLOSE);
} else if (nr_written == nr_remaining) {
finalize_hashfile(f, oid.hash, CSUM_HASH_IN_STREAM | CSUM_FSYNC | CSUM_CLOSE);
} else {
int fd = finalize_hashfile(f, oid.hash, 0);
fixup_pack_header_footer(fd, oid.hash, pack_tmp_name,
nr_written, oid.hash, offset);
close(fd);
if (write_bitmap_index) {
warning(_(no_split_warning));
write_bitmap_index = 0;
}
}
if (!pack_to_stdout) {
struct stat st;
struct strbuf tmpname = STRBUF_INIT;
/*
* Packs are runtime accessed in their mtime
* order since newer packs are more likely to contain
* younger objects. So if we are creating multiple
* packs then we should modify the mtime of later ones
* to preserve this property.
*/
if (stat(pack_tmp_name, &st) < 0) {
warning_errno("failed to stat %s", pack_tmp_name);
} else if (!last_mtime) {
last_mtime = st.st_mtime;
} else {
struct utimbuf utb;
utb.actime = st.st_atime;
utb.modtime = --last_mtime;
if (utime(pack_tmp_name, &utb) < 0)
warning_errno("failed utime() on %s", pack_tmp_name);
}
strbuf_addf(&tmpname, "%s-", base_name);
if (write_bitmap_index) {
bitmap_writer_set_checksum(oid.hash);
bitmap_writer_build_type_index(
&to_pack, written_list, nr_written);
}
finish_tmp_packfile(&tmpname, pack_tmp_name,
written_list, nr_written,
&pack_idx_opts, oid.hash);
if (write_bitmap_index) {
strbuf_addf(&tmpname, "%s.bitmap", oid_to_hex(&oid));
stop_progress(&progress_state);
bitmap_writer_show_progress(progress);
bitmap_writer_reuse_bitmaps(&to_pack);
bitmap_writer_select_commits(indexed_commits, indexed_commits_nr, -1);
bitmap_writer_build(&to_pack);
bitmap_writer_finish(written_list, nr_written,
tmpname.buf, write_bitmap_options);
write_bitmap_index = 0;
}
strbuf_release(&tmpname);
free(pack_tmp_name);
puts(oid_to_hex(&oid));
}
/* mark written objects as written to previous pack */
for (j = 0; j < nr_written; j++) {
written_list[j]->offset = (off_t)-1;
}
nr_remaining -= nr_written;
} while (nr_remaining && i < to_pack.nr_objects);
free(written_list);
free(write_order);
stop_progress(&progress_state);
if (written != nr_result)
die("wrote %"PRIu32" objects while expecting %"PRIu32,
written, nr_result);
}
static int no_try_delta(const char *path)
{
static struct attr_check *check;
if (!check)
check = attr_check_initl("delta", NULL);
if (git_check_attr(path, check))
return 0;
if (ATTR_FALSE(check->items[0].value))
return 1;
return 0;
}
/*
* When adding an object, check whether we have already added it
* to our packing list. If so, we can skip. However, if we are
* being asked to excludei t, but the previous mention was to include
* it, make sure to adjust its flags and tweak our numbers accordingly.
*
* As an optimization, we pass out the index position where we would have
* found the item, since that saves us from having to look it up again a
* few lines later when we want to add the new entry.
*/
static int have_duplicate_entry(const struct object_id *oid,
int exclude,
uint32_t *index_pos)
{
struct object_entry *entry;
entry = packlist_find(&to_pack, oid->hash, index_pos);
if (!entry)
return 0;
if (exclude) {
if (!entry->preferred_base)
nr_result--;
entry->preferred_base = 1;
}
return 1;
}
static int want_found_object(int exclude, struct packed_git *p)
{
if (exclude)
return 1;
if (incremental)
return 0;
/*
* When asked to do --local (do not include an object that appears in a
* pack we borrow from elsewhere) or --honor-pack-keep (do not include
* an object that appears in a pack marked with .keep), finding a pack
* that matches the criteria is sufficient for us to decide to omit it.
* However, even if this pack does not satisfy the criteria, we need to
* make sure no copy of this object appears in _any_ pack that makes us
* to omit the object, so we need to check all the packs.
*
* We can however first check whether these options can possible matter;
* if they do not matter we know we want the object in generated pack.
* Otherwise, we signal "-1" at the end to tell the caller that we do
* not know either way, and it needs to check more packs.
*/
if (!ignore_packed_keep_on_disk &&
!ignore_packed_keep_in_core &&
(!local || !have_non_local_packs))
return 1;
if (local && !p->pack_local)
return 0;
if (p->pack_local &&
((ignore_packed_keep_on_disk && p->pack_keep) ||
(ignore_packed_keep_in_core && p->pack_keep_in_core)))
return 0;
/* we don't know yet; keep looking for more packs */
return -1;
}
/*
* Check whether we want the object in the pack (e.g., we do not want
* objects found in non-local stores if the "--local" option was used).
*
* If the caller already knows an existing pack it wants to take the object
* from, that is passed in *found_pack and *found_offset; otherwise this
* function finds if there is any pack that has the object and returns the pack
* and its offset in these variables.
*/
static int want_object_in_pack(const struct object_id *oid,
int exclude,
struct packed_git **found_pack,
off_t *found_offset)
{
int want;
struct list_head *pos;
if (!exclude && local && has_loose_object_nonlocal(oid))
return 0;
/*
* If we already know the pack object lives in, start checks from that
* pack - in the usual case when neither --local was given nor .keep files
* are present we will determine the answer right now.
*/
if (*found_pack) {
want = want_found_object(exclude, *found_pack);
if (want != -1)
return want;
}
list_for_each(pos, get_packed_git_mru(the_repository)) {
struct packed_git *p = list_entry(pos, struct packed_git, mru);
off_t offset;
if (p == *found_pack)
offset = *found_offset;
else
offset = find_pack_entry_one(oid->hash, p);
if (offset) {
if (!*found_pack) {
if (!is_pack_valid(p))
continue;
*found_offset = offset;
*found_pack = p;
}
want = want_found_object(exclude, p);
if (!exclude && want > 0)
list_move(&p->mru,
get_packed_git_mru(the_repository));
if (want != -1)
return want;
}
}
return 1;
}
static void create_object_entry(const struct object_id *oid,
enum object_type type,
uint32_t hash,
int exclude,
int no_try_delta,
uint32_t index_pos,
struct packed_git *found_pack,
off_t found_offset)
{
struct object_entry *entry;
entry = packlist_alloc(&to_pack, oid->hash, index_pos);
entry->hash = hash;
oe_set_type(entry, type);
if (exclude)
entry->preferred_base = 1;
else
nr_result++;
if (found_pack) {
oe_set_in_pack(&to_pack, entry, found_pack);
entry->in_pack_offset = found_offset;
}
entry->no_try_delta = no_try_delta;
}
static const char no_closure_warning[] = N_(
"disabling bitmap writing, as some objects are not being packed"
);
static int add_object_entry(const struct object_id *oid, enum object_type type,
const char *name, int exclude)
{
struct packed_git *found_pack = NULL;
off_t found_offset = 0;
uint32_t index_pos;
display_progress(progress_state, ++nr_seen);
if (have_duplicate_entry(oid, exclude, &index_pos))
return 0;
if (!want_object_in_pack(oid, exclude, &found_pack, &found_offset)) {
/* The pack is missing an object, so it will not have closure */
if (write_bitmap_index) {
warning(_(no_closure_warning));
write_bitmap_index = 0;
}
return 0;
}
create_object_entry(oid, type, pack_name_hash(name),
exclude, name && no_try_delta(name),
index_pos, found_pack, found_offset);
return 1;
}
static int add_object_entry_from_bitmap(const struct object_id *oid,
enum object_type type,
int flags, uint32_t name_hash,
struct packed_git *pack, off_t offset)
{
uint32_t index_pos;
display_progress(progress_state, ++nr_seen);
if (have_duplicate_entry(oid, 0, &index_pos))
return 0;
if (!want_object_in_pack(oid, 0, &pack, &offset))
return 0;
create_object_entry(oid, type, name_hash, 0, 0, index_pos, pack, offset);
return 1;
}
struct pbase_tree_cache {
struct object_id oid;
int ref;
int temporary;
void *tree_data;
unsigned long tree_size;
};
static struct pbase_tree_cache *(pbase_tree_cache[256]);
static int pbase_tree_cache_ix(const struct object_id *oid)
{
return oid->hash[0] % ARRAY_SIZE(pbase_tree_cache);
}
static int pbase_tree_cache_ix_incr(int ix)
{
return (ix+1) % ARRAY_SIZE(pbase_tree_cache);
}
static struct pbase_tree {
struct pbase_tree *next;
/* This is a phony "cache" entry; we are not
* going to evict it or find it through _get()
* mechanism -- this is for the toplevel node that
* would almost always change with any commit.
*/
struct pbase_tree_cache pcache;
} *pbase_tree;
static struct pbase_tree_cache *pbase_tree_get(const struct object_id *oid)
{
struct pbase_tree_cache *ent, *nent;
void *data;
unsigned long size;
enum object_type type;
int neigh;
int my_ix = pbase_tree_cache_ix(oid);
int available_ix = -1;
/* pbase-tree-cache acts as a limited hashtable.
* your object will be found at your index or within a few
* slots after that slot if it is cached.
*/
for (neigh = 0; neigh < 8; neigh++) {
ent = pbase_tree_cache[my_ix];
if (ent && !oidcmp(&ent->oid, oid)) {
ent->ref++;
return ent;
}
else if (((available_ix < 0) && (!ent || !ent->ref)) ||
((0 <= available_ix) &&
(!ent && pbase_tree_cache[available_ix])))
available_ix = my_ix;
if (!ent)
break;
my_ix = pbase_tree_cache_ix_incr(my_ix);
}
/* Did not find one. Either we got a bogus request or
* we need to read and perhaps cache.
*/
data = read_object_file(oid, &type, &size);
if (!data)
return NULL;
if (type != OBJ_TREE) {
free(data);
return NULL;
}
/* We need to either cache or return a throwaway copy */
if (available_ix < 0)
ent = NULL;
else {
ent = pbase_tree_cache[available_ix];
my_ix = available_ix;
}
if (!ent) {
nent = xmalloc(sizeof(*nent));
nent->temporary = (available_ix < 0);
}
else {
/* evict and reuse */
free(ent->tree_data);
nent = ent;
}
oidcpy(&nent->oid, oid);
nent->tree_data = data;
nent->tree_size = size;
nent->ref = 1;
if (!nent->temporary)
pbase_tree_cache[my_ix] = nent;
return nent;
}
static void pbase_tree_put(struct pbase_tree_cache *cache)
{
if (!cache->temporary) {
cache->ref--;
return;
}
free(cache->tree_data);
free(cache);
}
static int name_cmp_len(const char *name)
{
int i;
for (i = 0; name[i] && name[i] != '\n' && name[i] != '/'; i++)
;
return i;
}
static void add_pbase_object(struct tree_desc *tree,
const char *name,
int cmplen,
const char *fullname)
{
struct name_entry entry;
int cmp;
while (tree_entry(tree,&entry)) {
if (S_ISGITLINK(entry.mode))
continue;
cmp = tree_entry_len(&entry) != cmplen ? 1 :
memcmp(name, entry.path, cmplen);
if (cmp > 0)
continue;
if (cmp < 0)
return;
if (name[cmplen] != '/') {
add_object_entry(entry.oid,
object_type(entry.mode),
fullname, 1);
return;
}
if (S_ISDIR(entry.mode)) {
struct tree_desc sub;
struct pbase_tree_cache *tree;
const char *down = name+cmplen+1;
int downlen = name_cmp_len(down);
tree = pbase_tree_get(entry.oid);
if (!tree)
return;
init_tree_desc(&sub, tree->tree_data, tree->tree_size);
add_pbase_object(&sub, down, downlen, fullname);
pbase_tree_put(tree);
}
}
}
static unsigned *done_pbase_paths;
static int done_pbase_paths_num;
static int done_pbase_paths_alloc;
static int done_pbase_path_pos(unsigned hash)
{
int lo = 0;
int hi = done_pbase_paths_num;
while (lo < hi) {
int mi = lo + (hi - lo) / 2;
if (done_pbase_paths[mi] == hash)
return mi;
if (done_pbase_paths[mi] < hash)
hi = mi;
else
lo = mi + 1;
}
return -lo-1;
}
static int check_pbase_path(unsigned hash)
{
int pos = done_pbase_path_pos(hash);
if (0 <= pos)
return 1;
pos = -pos - 1;
ALLOC_GROW(done_pbase_paths,
done_pbase_paths_num + 1,
done_pbase_paths_alloc);
done_pbase_paths_num++;
if (pos < done_pbase_paths_num)
MOVE_ARRAY(done_pbase_paths + pos + 1, done_pbase_paths + pos,
done_pbase_paths_num - pos - 1);
done_pbase_paths[pos] = hash;
return 0;
}
static void add_preferred_base_object(const char *name)
{
struct pbase_tree *it;
int cmplen;
unsigned hash = pack_name_hash(name);
if (!num_preferred_base || check_pbase_path(hash))
return;
cmplen = name_cmp_len(name);
for (it = pbase_tree; it; it = it->next) {
if (cmplen == 0) {
add_object_entry(&it->pcache.oid, OBJ_TREE, NULL, 1);
}
else {
struct tree_desc tree;
init_tree_desc(&tree, it->pcache.tree_data, it->pcache.tree_size);
add_pbase_object(&tree, name, cmplen, name);
}
}
}
static void add_preferred_base(struct object_id *oid)
{
struct pbase_tree *it;
void *data;
unsigned long size;
struct object_id tree_oid;
if (window <= num_preferred_base++)
return;
data = read_object_with_reference(oid, tree_type, &size, &tree_oid);
if (!data)
return;
for (it = pbase_tree; it; it = it->next) {
if (!oidcmp(&it->pcache.oid, &tree_oid)) {
free(data);
return;
}
}
it = xcalloc(1, sizeof(*it));
it->next = pbase_tree;
pbase_tree = it;
oidcpy(&it->pcache.oid, &tree_oid);
it->pcache.tree_data = data;
it->pcache.tree_size = size;
}
static void cleanup_preferred_base(void)
{
struct pbase_tree *it;
unsigned i;
it = pbase_tree;
pbase_tree = NULL;
while (it) {
struct pbase_tree *tmp = it;
it = tmp->next;
free(tmp->pcache.tree_data);
free(tmp);
}
for (i = 0; i < ARRAY_SIZE(pbase_tree_cache); i++) {
if (!pbase_tree_cache[i])
continue;
free(pbase_tree_cache[i]->tree_data);
FREE_AND_NULL(pbase_tree_cache[i]);
}
FREE_AND_NULL(done_pbase_paths);
done_pbase_paths_num = done_pbase_paths_alloc = 0;
}
static void check_object(struct object_entry *entry)
{
unsigned long canonical_size;
if (IN_PACK(entry)) {
struct packed_git *p = IN_PACK(entry);
struct pack_window *w_curs = NULL;
const unsigned char *base_ref = NULL;
struct object_entry *base_entry;
unsigned long used, used_0;
unsigned long avail;
off_t ofs;
unsigned char *buf, c;
enum object_type type;
unsigned long in_pack_size;
buf = use_pack(p, &w_curs, entry->in_pack_offset, &avail);
/*
* We want in_pack_type even if we do not reuse delta
* since non-delta representations could still be reused.
*/
used = unpack_object_header_buffer(buf, avail,
&type,
&in_pack_size);
if (used == 0)
goto give_up;
if (type < 0)
BUG("invalid type %d", type);
entry->in_pack_type = type;
/*
* Determine if this is a delta and if so whether we can
* reuse it or not. Otherwise let's find out as cheaply as
* possible what the actual type and size for this object is.
*/
switch (entry->in_pack_type) {
default:
/* Not a delta hence we've already got all we need. */
oe_set_type(entry, entry->in_pack_type);
SET_SIZE(entry, in_pack_size);
entry->in_pack_header_size = used;
if (oe_type(entry) < OBJ_COMMIT || oe_type(entry) > OBJ_BLOB)
goto give_up;
unuse_pack(&w_curs);
return;
case OBJ_REF_DELTA:
if (reuse_delta && !entry->preferred_base)
base_ref = use_pack(p, &w_curs,
entry->in_pack_offset + used, NULL);
entry->in_pack_header_size = used + the_hash_algo->rawsz;
break;
case OBJ_OFS_DELTA:
buf = use_pack(p, &w_curs,
entry->in_pack_offset + used, NULL);
used_0 = 0;
c = buf[used_0++];
ofs = c & 127;
while (c & 128) {
ofs += 1;
if (!ofs || MSB(ofs, 7)) {
error("delta base offset overflow in pack for %s",
oid_to_hex(&entry->idx.oid));
goto give_up;
}
c = buf[used_0++];
ofs = (ofs << 7) + (c & 127);
}
ofs = entry->in_pack_offset - ofs;
if (ofs <= 0 || ofs >= entry->in_pack_offset) {
error("delta base offset out of bound for %s",
oid_to_hex(&entry->idx.oid));
goto give_up;
}
if (reuse_delta && !entry->preferred_base) {
struct revindex_entry *revidx;
revidx = find_pack_revindex(p, ofs);
if (!revidx)
goto give_up;
base_ref = nth_packed_object_sha1(p, revidx->nr);
}
entry->in_pack_header_size = used + used_0;
break;
}
if (base_ref && (base_entry = packlist_find(&to_pack, base_ref, NULL))) {
/*
* If base_ref was set above that means we wish to
* reuse delta data, and we even found that base
* in the list of objects we want to pack. Goodie!
*
* Depth value does not matter - find_deltas() will
* never consider reused delta as the base object to
* deltify other objects against, in order to avoid
* circular deltas.
*/
oe_set_type(entry, entry->in_pack_type);
SET_SIZE(entry, in_pack_size); /* delta size */
SET_DELTA(entry, base_entry);
SET_DELTA_SIZE(entry, in_pack_size);
entry->delta_sibling_idx = base_entry->delta_child_idx;
SET_DELTA_CHILD(base_entry, entry);
unuse_pack(&w_curs);
return;
}
if (oe_type(entry)) {
off_t delta_pos;
/*
* This must be a delta and we already know what the
* final object type is. Let's extract the actual
* object size from the delta header.
*/
delta_pos = entry->in_pack_offset + entry->in_pack_header_size;
canonical_size = get_size_from_delta(p, &w_curs, delta_pos);
if (canonical_size == 0)
goto give_up;
SET_SIZE(entry, canonical_size);
unuse_pack(&w_curs);
return;
}
/*
* No choice but to fall back to the recursive delta walk
* with sha1_object_info() to find about the object type
* at this point...
*/
give_up:
unuse_pack(&w_curs);
}
oe_set_type(entry,
oid_object_info(the_repository, &entry->idx.oid, &canonical_size));
if (entry->type_valid) {
SET_SIZE(entry, canonical_size);
} else {
/*
* Bad object type is checked in prepare_pack(). This is
* to permit a missing preferred base object to be ignored
* as a preferred base. Doing so can result in a larger
* pack file, but the transfer will still take place.
*/
}
}
static int pack_offset_sort(const void *_a, const void *_b)
{
const struct object_entry *a = *(struct object_entry **)_a;
const struct object_entry *b = *(struct object_entry **)_b;
const struct packed_git *a_in_pack = IN_PACK(a);
const struct packed_git *b_in_pack = IN_PACK(b);
/* avoid filesystem trashing with loose objects */
if (!a_in_pack && !b_in_pack)
return oidcmp(&a->idx.oid, &b->idx.oid);
if (a_in_pack < b_in_pack)
return -1;
if (a_in_pack > b_in_pack)
return 1;
return a->in_pack_offset < b->in_pack_offset ? -1 :
(a->in_pack_offset > b->in_pack_offset);
}
/*
* Drop an on-disk delta we were planning to reuse. Naively, this would
* just involve blanking out the "delta" field, but we have to deal
* with some extra book-keeping:
*
* 1. Removing ourselves from the delta_sibling linked list.
*
* 2. Updating our size/type to the non-delta representation. These were
* either not recorded initially (size) or overwritten with the delta type
* (type) when check_object() decided to reuse the delta.
*
* 3. Resetting our delta depth, as we are now a base object.
*/
static void drop_reused_delta(struct object_entry *entry)
{
unsigned *idx = &to_pack.objects[entry->delta_idx - 1].delta_child_idx;
struct object_info oi = OBJECT_INFO_INIT;
enum object_type type;
unsigned long size;
while (*idx) {
struct object_entry *oe = &to_pack.objects[*idx - 1];
if (oe == entry)
*idx = oe->delta_sibling_idx;
else
idx = &oe->delta_sibling_idx;
}
SET_DELTA(entry, NULL);
entry->depth = 0;
oi.sizep = &size;
oi.typep = &type;
if (packed_object_info(the_repository, IN_PACK(entry), entry->in_pack_offset, &oi) < 0) {
/*
* We failed to get the info from this pack for some reason;
* fall back to sha1_object_info, which may find another copy.
* And if that fails, the error will be recorded in oe_type(entry)
* and dealt with in prepare_pack().
*/
oe_set_type(entry,
oid_object_info(the_repository, &entry->idx.oid, &size));
} else {
oe_set_type(entry, type);
}
SET_SIZE(entry, size);
}
/*
* Follow the chain of deltas from this entry onward, throwing away any links
* that cause us to hit a cycle (as determined by the DFS state flags in
* the entries).
*
* We also detect too-long reused chains that would violate our --depth
* limit.
*/
static void break_delta_chains(struct object_entry *entry)
{
/*
* The actual depth of each object we will write is stored as an int,
* as it cannot exceed our int "depth" limit. But before we break
* changes based no that limit, we may potentially go as deep as the
* number of objects, which is elsewhere bounded to a uint32_t.
*/
uint32_t total_depth;
struct object_entry *cur, *next;
for (cur = entry, total_depth = 0;
cur;
cur = DELTA(cur), total_depth++) {
if (cur->dfs_state == DFS_DONE) {
/*
* We've already seen this object and know it isn't
* part of a cycle. We do need to append its depth
* to our count.
*/
total_depth += cur->depth;
break;
}
/*
* We break cycles before looping, so an ACTIVE state (or any
* other cruft which made its way into the state variable)
* is a bug.
*/
if (cur->dfs_state != DFS_NONE)
BUG("confusing delta dfs state in first pass: %d",
cur->dfs_state);
/*
* Now we know this is the first time we've seen the object. If
* it's not a delta, we're done traversing, but we'll mark it
* done to save time on future traversals.
*/
if (!DELTA(cur)) {
cur->dfs_state = DFS_DONE;
break;
}
/*
* Mark ourselves as active and see if the next step causes
* us to cycle to another active object. It's important to do
* this _before_ we loop, because it impacts where we make the
* cut, and thus how our total_depth counter works.
* E.g., We may see a partial loop like:
*
* A -> B -> C -> D -> B
*
* Cutting B->C breaks the cycle. But now the depth of A is
* only 1, and our total_depth counter is at 3. The size of the
* error is always one less than the size of the cycle we
* broke. Commits C and D were "lost" from A's chain.
*
* If we instead cut D->B, then the depth of A is correct at 3.
* We keep all commits in the chain that we examined.
*/
cur->dfs_state = DFS_ACTIVE;
if (DELTA(cur)->dfs_state == DFS_ACTIVE) {
drop_reused_delta(cur);
cur->dfs_state = DFS_DONE;
break;
}
}
/*
* And now that we've gone all the way to the bottom of the chain, we
* need to clear the active flags and set the depth fields as
* appropriate. Unlike the loop above, which can quit when it drops a
* delta, we need to keep going to look for more depth cuts. So we need
* an extra "next" pointer to keep going after we reset cur->delta.
*/
for (cur = entry; cur; cur = next) {
next = DELTA(cur);
/*
* We should have a chain of zero or more ACTIVE states down to
* a final DONE. We can quit after the DONE, because either it
* has no bases, or we've already handled them in a previous
* call.
*/
if (cur->dfs_state == DFS_DONE)
break;
else if (cur->dfs_state != DFS_ACTIVE)
BUG("confusing delta dfs state in second pass: %d",
cur->dfs_state);
/*
* If the total_depth is more than depth, then we need to snip
* the chain into two or more smaller chains that don't exceed
* the maximum depth. Most of the resulting chains will contain
* (depth + 1) entries (i.e., depth deltas plus one base), and
* the last chain (i.e., the one containing entry) will contain
* whatever entries are left over, namely
* (total_depth % (depth + 1)) of them.
*
* Since we are iterating towards decreasing depth, we need to
* decrement total_depth as we go, and we need to write to the
* entry what its final depth will be after all of the
* snipping. Since we're snipping into chains of length (depth
* + 1) entries, the final depth of an entry will be its
* original depth modulo (depth + 1). Any time we encounter an
* entry whose final depth is supposed to be zero, we snip it
* from its delta base, thereby making it so.
*/
cur->depth = (total_depth--) % (depth + 1);
if (!cur->depth)
drop_reused_delta(cur);
cur->dfs_state = DFS_DONE;
}
}
static void get_object_details(void)
{
uint32_t i;
struct object_entry **sorted_by_offset;
if (progress)
progress_state = start_progress(_("Counting objects"),
to_pack.nr_objects);
sorted_by_offset = xcalloc(to_pack.nr_objects, sizeof(struct object_entry *));
for (i = 0; i < to_pack.nr_objects; i++)
sorted_by_offset[i] = to_pack.objects + i;
QSORT(sorted_by_offset, to_pack.nr_objects, pack_offset_sort);
for (i = 0; i < to_pack.nr_objects; i++) {
struct object_entry *entry = sorted_by_offset[i];
check_object(entry);
if (entry->type_valid &&
oe_size_greater_than(&to_pack, entry, big_file_threshold))
entry->no_try_delta = 1;
display_progress(progress_state, i + 1);
}
stop_progress(&progress_state);
/*
* This must happen in a second pass, since we rely on the delta
* information for the whole list being completed.
*/
for (i = 0; i < to_pack.nr_objects; i++)
break_delta_chains(&to_pack.objects[i]);
free(sorted_by_offset);
}
/*
* We search for deltas in a list sorted by type, by filename hash, and then
* by size, so that we see progressively smaller and smaller files.
* That's because we prefer deltas to be from the bigger file
* to the smaller -- deletes are potentially cheaper, but perhaps
* more importantly, the bigger file is likely the more recent
* one. The deepest deltas are therefore the oldest objects which are
* less susceptible to be accessed often.
*/
static int type_size_sort(const void *_a, const void *_b)
{
const struct object_entry *a = *(struct object_entry **)_a;
const struct object_entry *b = *(struct object_entry **)_b;
enum object_type a_type = oe_type(a);
enum object_type b_type = oe_type(b);
unsigned long a_size = SIZE(a);
unsigned long b_size = SIZE(b);
if (a_type > b_type)
return -1;
if (a_type < b_type)
return 1;
if (a->hash > b->hash)
return -1;
if (a->hash < b->hash)
return 1;
if (a->preferred_base > b->preferred_base)
return -1;
if (a->preferred_base < b->preferred_base)
return 1;
if (a_size > b_size)
return -1;
if (a_size < b_size)
return 1;
return a < b ? -1 : (a > b); /* newest first */
}
struct unpacked {
struct object_entry *entry;
void *data;
struct delta_index *index;
unsigned depth;
};
static int delta_cacheable(unsigned long src_size, unsigned long trg_size,
unsigned long delta_size)
{
if (max_delta_cache_size && delta_cache_size + delta_size > max_delta_cache_size)
return 0;
if (delta_size < cache_max_small_delta_size)
return 1;
/* cache delta, if objects are large enough compared to delta size */
if ((src_size >> 20) + (trg_size >> 21) > (delta_size >> 10))
return 1;
return 0;
}
#ifndef NO_PTHREADS
static pthread_mutex_t read_mutex;
#define read_lock() pthread_mutex_lock(&read_mutex)
#define read_unlock() pthread_mutex_unlock(&read_mutex)
static pthread_mutex_t cache_mutex;
#define cache_lock() pthread_mutex_lock(&cache_mutex)
#define cache_unlock() pthread_mutex_unlock(&cache_mutex)
static pthread_mutex_t progress_mutex;
#define progress_lock() pthread_mutex_lock(&progress_mutex)
#define progress_unlock() pthread_mutex_unlock(&progress_mutex)
#else
#define read_lock() (void)0
#define read_unlock() (void)0
#define cache_lock() (void)0
#define cache_unlock() (void)0
#define progress_lock() (void)0
#define progress_unlock() (void)0
#endif
/*
* Return the size of the object without doing any delta
* reconstruction (so non-deltas are true object sizes, but deltas
* return the size of the delta data).
*/
unsigned long oe_get_size_slow(struct packing_data *pack,
const struct object_entry *e)
{
struct packed_git *p;
struct pack_window *w_curs;
unsigned char *buf;
enum object_type type;
unsigned long used, avail, size;
if (e->type_ != OBJ_OFS_DELTA && e->type_ != OBJ_REF_DELTA) {
read_lock();
if (oid_object_info(the_repository, &e->idx.oid, &size) < 0)
die(_("unable to get size of %s"),
oid_to_hex(&e->idx.oid));
read_unlock();
return size;
}
p = oe_in_pack(pack, e);
if (!p)
BUG("when e->type is a delta, it must belong to a pack");
read_lock();
w_curs = NULL;
buf = use_pack(p, &w_curs, e->in_pack_offset, &avail);
used = unpack_object_header_buffer(buf, avail, &type, &size);
if (used == 0)
die(_("unable to parse object header of %s"),
oid_to_hex(&e->idx.oid));
unuse_pack(&w_curs);
read_unlock();
return size;
}
static int try_delta(struct unpacked *trg, struct unpacked *src,
unsigned max_depth, unsigned long *mem_usage)
{
struct object_entry *trg_entry = trg->entry;
struct object_entry *src_entry = src->entry;
unsigned long trg_size, src_size, delta_size, sizediff, max_size, sz;
unsigned ref_depth;
enum object_type type;
void *delta_buf;
/* Don't bother doing diffs between different types */
if (oe_type(trg_entry) != oe_type(src_entry))
return -1;
/*
* We do not bother to try a delta that we discarded on an
* earlier try, but only when reusing delta data. Note that
* src_entry that is marked as the preferred_base should always
* be considered, as even if we produce a suboptimal delta against
* it, we will still save the transfer cost, as we already know
* the other side has it and we won't send src_entry at all.
*/
if (reuse_delta && IN_PACK(trg_entry) &&
IN_PACK(trg_entry) == IN_PACK(src_entry) &&
!src_entry->preferred_base &&
trg_entry->in_pack_type != OBJ_REF_DELTA &&
trg_entry->in_pack_type != OBJ_OFS_DELTA)
return 0;
/* Let's not bust the allowed depth. */
if (src->depth >= max_depth)
return 0;
/* Now some size filtering heuristics. */
trg_size = SIZE(trg_entry);
if (!DELTA(trg_entry)) {
max_size = trg_size/2 - the_hash_algo->rawsz;
ref_depth = 1;
} else {
max_size = DELTA_SIZE(trg_entry);
ref_depth = trg->depth;
}
max_size = (uint64_t)max_size * (max_depth - src->depth) /
(max_depth - ref_depth + 1);
if (max_size == 0)
return 0;
src_size = SIZE(src_entry);
sizediff = src_size < trg_size ? trg_size - src_size : 0;
if (sizediff >= max_size)
return 0;
if (trg_size < src_size / 32)
return 0;
/* Load data if not already done */
if (!trg->data) {
read_lock();
trg->data = read_object_file(&trg_entry->idx.oid, &type, &sz);
read_unlock();
if (!trg->data)
die("object %s cannot be read",
oid_to_hex(&trg_entry->idx.oid));
if (sz != trg_size)
die("object %s inconsistent object length (%lu vs %lu)",
oid_to_hex(&trg_entry->idx.oid), sz,
trg_size);
*mem_usage += sz;
}
if (!src->data) {
read_lock();
src->data = read_object_file(&src_entry->idx.oid, &type, &sz);
read_unlock();
if (!src->data) {
if (src_entry->preferred_base) {
static int warned = 0;
if (!warned++)
warning("object %s cannot be read",
oid_to_hex(&src_entry->idx.oid));
/*
* Those objects are not included in the
* resulting pack. Be resilient and ignore
* them if they can't be read, in case the
* pack could be created nevertheless.
*/
return 0;
}
die("object %s cannot be read",
oid_to_hex(&src_entry->idx.oid));
}
if (sz != src_size)
die("object %s inconsistent object length (%lu vs %lu)",
oid_to_hex(&src_entry->idx.oid), sz,
src_size);
*mem_usage += sz;
}
if (!src->index) {
src->index = create_delta_index(src->data, src_size);
if (!src->index) {
static int warned = 0;
if (!warned++)
warning("suboptimal pack - out of memory");
return 0;
}
*mem_usage += sizeof_delta_index(src->index);
}
delta_buf = create_delta(src->index, trg->data, trg_size, &delta_size, max_size);
if (!delta_buf)
return 0;
if (delta_size >= (1U << OE_DELTA_SIZE_BITS)) {
free(delta_buf);
return 0;
}
if (DELTA(trg_entry)) {
/* Prefer only shallower same-sized deltas. */
if (delta_size == DELTA_SIZE(trg_entry) &&
src->depth + 1 >= trg->depth) {
free(delta_buf);
return 0;
}
}
/*
* Handle memory allocation outside of the cache
* accounting lock. Compiler will optimize the strangeness
* away when NO_PTHREADS is defined.
*/
free(trg_entry->delta_data);
cache_lock();
if (trg_entry->delta_data) {
delta_cache_size -= DELTA_SIZE(trg_entry);
trg_entry->delta_data = NULL;
}
if (delta_cacheable(src_size, trg_size, delta_size)) {
delta_cache_size += delta_size;
cache_unlock();
trg_entry->delta_data = xrealloc(delta_buf, delta_size);
} else {
cache_unlock();
free(delta_buf);
}
SET_DELTA(trg_entry, src_entry);
SET_DELTA_SIZE(trg_entry, delta_size);
trg->depth = src->depth + 1;
return 1;
}
static unsigned int check_delta_limit(struct object_entry *me, unsigned int n)
{
struct object_entry *child = DELTA_CHILD(me);
unsigned int m = n;
while (child) {
unsigned int c = check_delta_limit(child, n + 1);
if (m < c)
m = c;
child = DELTA_SIBLING(child);
}
return m;
}
static unsigned long free_unpacked(struct unpacked *n)
{
unsigned long freed_mem = sizeof_delta_index(n->index);
free_delta_index(n->index);
n->index = NULL;
if (n->data) {
freed_mem += SIZE(n->entry);
FREE_AND_NULL(n->data);
}
n->entry = NULL;
n->depth = 0;
return freed_mem;
}
static void find_deltas(struct object_entry **list, unsigned *list_size,
int window, int depth, unsigned *processed)
{
uint32_t i, idx = 0, count = 0;
struct unpacked *array;
unsigned long mem_usage = 0;
array = xcalloc(window, sizeof(struct unpacked));
for (;;) {
struct object_entry *entry;
struct unpacked *n = array + idx;
int j, max_depth, best_base = -1;
progress_lock();
if (!*list_size) {
progress_unlock();
break;
}
entry = *list++;
(*list_size)--;
if (!entry->preferred_base) {
(*processed)++;
display_progress(progress_state, *processed);
}
progress_unlock();
mem_usage -= free_unpacked(n);
n->entry = entry;
while (window_memory_limit &&
mem_usage > window_memory_limit &&
count > 1) {
uint32_t tail = (idx + window - count) % window;
mem_usage -= free_unpacked(array + tail);
count--;
}
/* We do not compute delta to *create* objects we are not
* going to pack.
*/
if (entry->preferred_base)
goto next;
/*
* If the current object is at pack edge, take the depth the
* objects that depend on the current object into account
* otherwise they would become too deep.
*/
max_depth = depth;
if (DELTA_CHILD(entry)) {
max_depth -= check_delta_limit(entry, 0);
if (max_depth <= 0)
goto next;
}
j = window;
while (--j > 0) {
int ret;
uint32_t other_idx = idx + j;
struct unpacked *m;
if (other_idx >= window)
other_idx -= window;
m = array + other_idx;
if (!m->entry)
break;
ret = try_delta(n, m, max_depth, &mem_usage);
if (ret < 0)
break;
else if (ret > 0)
best_base = other_idx;
}
/*
* If we decided to cache the delta data, then it is best
* to compress it right away. First because we have to do
* it anyway, and doing it here while we're threaded will
* save a lot of time in the non threaded write phase,
* as well as allow for caching more deltas within
* the same cache size limit.
* ...
* But only if not writing to stdout, since in that case
* the network is most likely throttling writes anyway,
* and therefore it is best to go to the write phase ASAP
* instead, as we can afford spending more time compressing
* between writes at that moment.
*/
if (entry->delta_data && !pack_to_stdout) {
unsigned long size;
size = do_compress(&entry->delta_data, DELTA_SIZE(entry));
if (size < (1U << OE_Z_DELTA_BITS)) {
entry->z_delta_size = size;
cache_lock();
delta_cache_size -= DELTA_SIZE(entry);
delta_cache_size += entry->z_delta_size;
cache_unlock();
} else {
FREE_AND_NULL(entry->delta_data);
entry->z_delta_size = 0;
}
}
/* if we made n a delta, and if n is already at max
* depth, leaving it in the window is pointless. we
* should evict it first.
*/
if (DELTA(entry) && max_depth <= n->depth)
continue;
/*
* Move the best delta base up in the window, after the
* currently deltified object, to keep it longer. It will
* be the first base object to be attempted next.
*/
if (DELTA(entry)) {
struct unpacked swap = array[best_base];
int dist = (window + idx - best_base) % window;
int dst = best_base;
while (dist--) {
int src = (dst + 1) % window;
array[dst] = array[src];
dst = src;
}
array[dst] = swap;
}
next:
idx++;
if (count + 1 < window)
count++;
if (idx >= window)
idx = 0;
}
for (i = 0; i < window; ++i) {
free_delta_index(array[i].index);
free(array[i].data);
}
free(array);
}
#ifndef NO_PTHREADS
static void try_to_free_from_threads(size_t size)
{
read_lock();
release_pack_memory(size);
read_unlock();
}
static try_to_free_t old_try_to_free_routine;
/*
* The main thread waits on the condition that (at least) one of the workers
* has stopped working (which is indicated in the .working member of
* struct thread_params).
* When a work thread has completed its work, it sets .working to 0 and
* signals the main thread and waits on the condition that .data_ready
* becomes 1.
*/
struct thread_params {
pthread_t thread;
struct object_entry **list;
unsigned list_size;
unsigned remaining;
int window;
int depth;
int working;
int data_ready;
pthread_mutex_t mutex;
pthread_cond_t cond;
unsigned *processed;
};
static pthread_cond_t progress_cond;
/*
* Mutex and conditional variable can't be statically-initialized on Windows.
*/
static void init_threaded_search(void)
{
init_recursive_mutex(&read_mutex);
pthread_mutex_init(&cache_mutex, NULL);
pthread_mutex_init(&progress_mutex, NULL);
pthread_cond_init(&progress_cond, NULL);
old_try_to_free_routine = set_try_to_free_routine(try_to_free_from_threads);
}
static void cleanup_threaded_search(void)
{
set_try_to_free_routine(old_try_to_free_routine);
pthread_cond_destroy(&progress_cond);
pthread_mutex_destroy(&read_mutex);
pthread_mutex_destroy(&cache_mutex);
pthread_mutex_destroy(&progress_mutex);
}
static void *threaded_find_deltas(void *arg)
{
struct thread_params *me = arg;
progress_lock();
while (me->remaining) {
progress_unlock();
find_deltas(me->list, &me->remaining,
me->window, me->depth, me->processed);
progress_lock();
me->working = 0;
pthread_cond_signal(&progress_cond);
progress_unlock();
/*
* We must not set ->data_ready before we wait on the
* condition because the main thread may have set it to 1
* before we get here. In order to be sure that new
* work is available if we see 1 in ->data_ready, it
* was initialized to 0 before this thread was spawned
* and we reset it to 0 right away.
*/
pthread_mutex_lock(&me->mutex);
while (!me->data_ready)
pthread_cond_wait(&me->cond, &me->mutex);
me->data_ready = 0;
pthread_mutex_unlock(&me->mutex);
progress_lock();
}
progress_unlock();
/* leave ->working 1 so that this doesn't get more work assigned */
return NULL;
}
static void ll_find_deltas(struct object_entry **list, unsigned list_size,
int window, int depth, unsigned *processed)
{
struct thread_params *p;
int i, ret, active_threads = 0;
init_threaded_search();
if (delta_search_threads <= 1) {
find_deltas(list, &list_size, window, depth, processed);
cleanup_threaded_search();
return;
}
if (progress > pack_to_stdout)
fprintf(stderr, "Delta compression using up to %d threads.\n",
delta_search_threads);
p = xcalloc(delta_search_threads, sizeof(*p));
/* Partition the work amongst work threads. */
for (i = 0; i < delta_search_threads; i++) {
unsigned sub_size = list_size / (delta_search_threads - i);
/* don't use too small segments or no deltas will be found */
if (sub_size < 2*window && i+1 < delta_search_threads)
sub_size = 0;
p[i].window = window;
p[i].depth = depth;
p[i].processed = processed;
p[i].working = 1;
p[i].data_ready = 0;
/* try to split chunks on "path" boundaries */
while (sub_size && sub_size < list_size &&
list[sub_size]->hash &&
list[sub_size]->hash == list[sub_size-1]->hash)
sub_size++;
p[i].list = list;
p[i].list_size = sub_size;
p[i].remaining = sub_size;
list += sub_size;
list_size -= sub_size;
}
/* Start work threads. */
for (i = 0; i < delta_search_threads; i++) {
if (!p[i].list_size)
continue;
pthread_mutex_init(&p[i].mutex, NULL);
pthread_cond_init(&p[i].cond, NULL);
ret = pthread_create(&p[i].thread, NULL,
threaded_find_deltas, &p[i]);
if (ret)
die("unable to create thread: %s", strerror(ret));
active_threads++;
}
/*
* Now let's wait for work completion. Each time a thread is done
* with its work, we steal half of the remaining work from the
* thread with the largest number of unprocessed objects and give
* it to that newly idle thread. This ensure good load balancing
* until the remaining object list segments are simply too short
* to be worth splitting anymore.
*/
while (active_threads) {
struct thread_params *target = NULL;
struct thread_params *victim = NULL;
unsigned sub_size = 0;
progress_lock();
for (;;) {
for (i = 0; !target && i < delta_search_threads; i++)
if (!p[i].working)
target = &p[i];
if (target)
break;
pthread_cond_wait(&progress_cond, &progress_mutex);
}
for (i = 0; i < delta_search_threads; i++)
if (p[i].remaining > 2*window &&
(!victim || victim->remaining < p[i].remaining))
victim = &p[i];
if (victim) {
sub_size = victim->remaining / 2;
list = victim->list + victim->list_size - sub_size;
while (sub_size && list[0]->hash &&
list[0]->hash == list[-1]->hash) {
list++;
sub_size--;
}
if (!sub_size) {
/*
* It is possible for some "paths" to have
* so many objects that no hash boundary
* might be found. Let's just steal the
* exact half in that case.
*/
sub_size = victim->remaining / 2;
list -= sub_size;
}
target->list = list;
victim->list_size -= sub_size;
victim->remaining -= sub_size;
}
target->list_size = sub_size;
target->remaining = sub_size;
target->working = 1;
progress_unlock();
pthread_mutex_lock(&target->mutex);
target->data_ready = 1;
pthread_cond_signal(&target->cond);
pthread_mutex_unlock(&target->mutex);
if (!sub_size) {
pthread_join(target->thread, NULL);
pthread_cond_destroy(&target->cond);
pthread_mutex_destroy(&target->mutex);
active_threads--;
}
}
cleanup_threaded_search();
free(p);
}
#else
#define ll_find_deltas(l, s, w, d, p) find_deltas(l, &s, w, d, p)
#endif
static void add_tag_chain(const struct object_id *oid)
{
struct tag *tag;
/*
* We catch duplicates already in add_object_entry(), but we'd
* prefer to do this extra check to avoid having to parse the
* tag at all if we already know that it's being packed (e.g., if
* it was included via bitmaps, we would not have parsed it
* previously).
*/
if (packlist_find(&to_pack, oid->hash, NULL))
return;
tag = lookup_tag(oid);
while (1) {
if (!tag || parse_tag(tag) || !tag->tagged)
die("unable to pack objects reachable from tag %s",
oid_to_hex(oid));
add_object_entry(&tag->object.oid, OBJ_TAG, NULL, 0);
if (tag->tagged->type != OBJ_TAG)
return;
tag = (struct tag *)tag->tagged;
}
}
static int add_ref_tag(const char *path, const struct object_id *oid, int flag, void *cb_data)
{
struct object_id peeled;
if (starts_with(path, "refs/tags/") && /* is a tag? */
!peel_ref(path, &peeled) && /* peelable? */
packlist_find(&to_pack, peeled.hash, NULL)) /* object packed? */
add_tag_chain(oid);
return 0;
}
static void prepare_pack(int window, int depth)
{
struct object_entry **delta_list;
uint32_t i, nr_deltas;
unsigned n;
get_object_details();
/*
* If we're locally repacking then we need to be doubly careful
* from now on in order to make sure no stealth corruption gets
* propagated to the new pack. Clients receiving streamed packs
* should validate everything they get anyway so no need to incur
* the additional cost here in that case.
*/
if (!pack_to_stdout)
do_check_packed_object_crc = 1;
if (!to_pack.nr_objects || !window || !depth)
return;
ALLOC_ARRAY(delta_list, to_pack.nr_objects);
nr_deltas = n = 0;
for (i = 0; i < to_pack.nr_objects; i++) {
struct object_entry *entry = to_pack.objects + i;
if (DELTA(entry))
/* This happens if we decided to reuse existing
* delta from a pack. "reuse_delta &&" is implied.
*/
continue;
if (!entry->type_valid ||
oe_size_less_than(&to_pack, entry, 50))
continue;
if (entry->no_try_delta)
continue;
if (!entry->preferred_base) {
nr_deltas++;
if (oe_type(entry) < 0)
die("unable to get type of object %s",
oid_to_hex(&entry->idx.oid));
} else {
if (oe_type(entry) < 0) {
/*
* This object is not found, but we
* don't have to include it anyway.
*/
continue;
}
}
delta_list[n++] = entry;
}
if (nr_deltas && n > 1) {
unsigned nr_done = 0;
if (progress)
progress_state = start_progress(_("Compressing objects"),
nr_deltas);
QSORT(delta_list, n, type_size_sort);
ll_find_deltas(delta_list, n, window+1, depth, &nr_done);
stop_progress(&progress_state);
if (nr_done != nr_deltas)
die("inconsistency with delta count");
}
free(delta_list);
}
static int git_pack_config(const char *k, const char *v, void *cb)
{
if (!strcmp(k, "pack.window")) {
window = git_config_int(k, v);
return 0;
}
if (!strcmp(k, "pack.windowmemory")) {
window_memory_limit = git_config_ulong(k, v);
return 0;
}
if (!strcmp(k, "pack.depth")) {
depth = git_config_int(k, v);
return 0;
}
if (!strcmp(k, "pack.deltacachesize")) {
max_delta_cache_size = git_config_int(k, v);
return 0;
}
if (!strcmp(k, "pack.deltacachelimit")) {
cache_max_small_delta_size = git_config_int(k, v);
return 0;
}
if (!strcmp(k, "pack.writebitmaphashcache")) {
if (git_config_bool(k, v))
write_bitmap_options |= BITMAP_OPT_HASH_CACHE;
else
write_bitmap_options &= ~BITMAP_OPT_HASH_CACHE;
}
if (!strcmp(k, "pack.usebitmaps")) {
use_bitmap_index_default = git_config_bool(k, v);
return 0;
}
if (!strcmp(k, "pack.threads")) {
delta_search_threads = git_config_int(k, v);
if (delta_search_threads < 0)
die("invalid number of threads specified (%d)",
delta_search_threads);
#ifdef NO_PTHREADS
if (delta_search_threads != 1) {
warning("no threads support, ignoring %s", k);
delta_search_threads = 0;
}
#endif
return 0;
}
if (!strcmp(k, "pack.indexversion")) {
pack_idx_opts.version = git_config_int(k, v);
if (pack_idx_opts.version > 2)
die("bad pack.indexversion=%"PRIu32,
pack_idx_opts.version);
return 0;
}
return git_default_config(k, v, cb);
}
static void read_object_list_from_stdin(void)
{
char line[GIT_MAX_HEXSZ + 1 + PATH_MAX + 2];
struct object_id oid;
const char *p;
for (;;) {
if (!fgets(line, sizeof(line), stdin)) {
if (feof(stdin))
break;
if (!ferror(stdin))
die("fgets returned NULL, not EOF, not error!");
if (errno != EINTR)
die_errno("fgets");
clearerr(stdin);
continue;
}
if (line[0] == '-') {
if (get_oid_hex(line+1, &oid))
die("expected edge object ID, got garbage:\n %s",
line);
add_preferred_base(&oid);
continue;
}
if (parse_oid_hex(line, &oid, &p))
die("expected object ID, got garbage:\n %s", line);
add_preferred_base_object(p + 1);
add_object_entry(&oid, OBJ_NONE, p + 1, 0);
}
}
/* Remember to update object flag allocation in object.h */
#define OBJECT_ADDED (1u<<20)
static void show_commit(struct commit *commit, void *data)
{
add_object_entry(&commit->object.oid, OBJ_COMMIT, NULL, 0);
commit->object.flags |= OBJECT_ADDED;
if (write_bitmap_index)
index_commit_for_bitmap(commit);
}
static void show_object(struct object *obj, const char *name, void *data)
{
add_preferred_base_object(name);
add_object_entry(&obj->oid, obj->type, name, 0);
obj->flags |= OBJECT_ADDED;
}
static void show_object__ma_allow_any(struct object *obj, const char *name, void *data)
{
assert(arg_missing_action == MA_ALLOW_ANY);
/*
* Quietly ignore ALL missing objects. This avoids problems with
* staging them now and getting an odd error later.
*/
if (!has_object_file(&obj->oid))
return;
show_object(obj, name, data);
}
static void show_object__ma_allow_promisor(struct object *obj, const char *name, void *data)
{
assert(arg_missing_action == MA_ALLOW_PROMISOR);
/*
* Quietly ignore EXPECTED missing objects. This avoids problems with
* staging them now and getting an odd error later.
*/
if (!has_object_file(&obj->oid) && is_promisor_object(&obj->oid))
return;
show_object(obj, name, data);
}
static int option_parse_missing_action(const struct option *opt,
const char *arg, int unset)
{
assert(arg);
assert(!unset);
if (!strcmp(arg, "error")) {
arg_missing_action = MA_ERROR;
fn_show_object = show_object;
return 0;
}
if (!strcmp(arg, "allow-any")) {
arg_missing_action = MA_ALLOW_ANY;
fetch_if_missing = 0;
fn_show_object = show_object__ma_allow_any;
return 0;
}
if (!strcmp(arg, "allow-promisor")) {
arg_missing_action = MA_ALLOW_PROMISOR;
fetch_if_missing = 0;
fn_show_object = show_object__ma_allow_promisor;
return 0;
}
die(_("invalid value for --missing"));
return 0;
}
static void show_edge(struct commit *commit)
{
add_preferred_base(&commit->object.oid);
}
struct in_pack_object {
off_t offset;
struct object *object;
};
struct in_pack {
unsigned int alloc;
unsigned int nr;
struct in_pack_object *array;
};
static void mark_in_pack_object(struct object *object, struct packed_git *p, struct in_pack *in_pack)
{
in_pack->array[in_pack->nr].offset = find_pack_entry_one(object->oid.hash, p);
in_pack->array[in_pack->nr].object = object;
in_pack->nr++;
}
/*
* Compare the objects in the offset order, in order to emulate the
* "git rev-list --objects" output that produced the pack originally.
*/
static int ofscmp(const void *a_, const void *b_)
{
struct in_pack_object *a = (struct in_pack_object *)a_;
struct in_pack_object *b = (struct in_pack_object *)b_;
if (a->offset < b->offset)
return -1;
else if (a->offset > b->offset)
return 1;
else
return oidcmp(&a->object->oid, &b->object->oid);
}
static void add_objects_in_unpacked_packs(struct rev_info *revs)
{
struct packed_git *p;
struct in_pack in_pack;
uint32_t i;
memset(&in_pack, 0, sizeof(in_pack));
for (p = get_packed_git(the_repository); p; p = p->next) {
struct object_id oid;
struct object *o;
if (!p->pack_local || p->pack_keep || p->pack_keep_in_core)
continue;
if (open_pack_index(p))
die("cannot open pack index");
ALLOC_GROW(in_pack.array,
in_pack.nr + p->num_objects,
in_pack.alloc);
for (i = 0; i < p->num_objects; i++) {
nth_packed_object_oid(&oid, p, i);
o = lookup_unknown_object(oid.hash);
if (!(o->flags & OBJECT_ADDED))
mark_in_pack_object(o, p, &in_pack);
o->flags |= OBJECT_ADDED;
}
}
if (in_pack.nr) {
QSORT(in_pack.array, in_pack.nr, ofscmp);
for (i = 0; i < in_pack.nr; i++) {
struct object *o = in_pack.array[i].object;
add_object_entry(&o->oid, o->type, "", 0);
}
}
free(in_pack.array);
}
static int add_loose_object(const struct object_id *oid, const char *path,
void *data)
{
enum object_type type = oid_object_info(the_repository, oid, NULL);
if (type < 0) {
warning("loose object at %s could not be examined", path);
return 0;
}
add_object_entry(oid, type, "", 0);
return 0;
}
/*
* We actually don't even have to worry about reachability here.
* add_object_entry will weed out duplicates, so we just add every
* loose object we find.
*/
static void add_unreachable_loose_objects(void)
{
for_each_loose_file_in_objdir(get_object_directory(),
add_loose_object,
NULL, NULL, NULL);
}
static int has_sha1_pack_kept_or_nonlocal(const struct object_id *oid)
{
static struct packed_git *last_found = (void *)1;
struct packed_git *p;
p = (last_found != (void *)1) ? last_found :
get_packed_git(the_repository);
while (p) {
if ((!p->pack_local || p->pack_keep ||
p->pack_keep_in_core) &&
find_pack_entry_one(oid->hash, p)) {
last_found = p;
return 1;
}
if (p == last_found)
p = get_packed_git(the_repository);
else
p = p->next;
if (p == last_found)
p = p->next;
}
return 0;
}
/*
* Store a list of sha1s that are should not be discarded
* because they are either written too recently, or are
* reachable from another object that was.
*
* This is filled by get_object_list.
*/
static struct oid_array recent_objects;
static int loosened_object_can_be_discarded(const struct object_id *oid,
timestamp_t mtime)
{
if (!unpack_unreachable_expiration)
return 0;
if (mtime > unpack_unreachable_expiration)
return 0;
if (oid_array_lookup(&recent_objects, oid) >= 0)
return 0;
return 1;
}
static void loosen_unused_packed_objects(struct rev_info *revs)
{
struct packed_git *p;
uint32_t i;
struct object_id oid;
for (p = get_packed_git(the_repository); p; p = p->next) {
if (!p->pack_local || p->pack_keep || p->pack_keep_in_core)
continue;
if (open_pack_index(p))
die("cannot open pack index");
for (i = 0; i < p->num_objects; i++) {
nth_packed_object_oid(&oid, p, i);
if (!packlist_find(&to_pack, oid.hash, NULL) &&
!has_sha1_pack_kept_or_nonlocal(&oid) &&
!loosened_object_can_be_discarded(&oid, p->mtime))
if (force_object_loose(&oid, p->mtime))
die("unable to force loose object");
}
}
}
/*
* This tracks any options which pack-reuse code expects to be on, or which a
* reader of the pack might not understand, and which would therefore prevent
* blind reuse of what we have on disk.
*/
static int pack_options_allow_reuse(void)
{
return pack_to_stdout &&
allow_ofs_delta &&
!ignore_packed_keep_on_disk &&
!ignore_packed_keep_in_core &&
(!local || !have_non_local_packs) &&
!incremental;
}
static int get_object_list_from_bitmap(struct rev_info *revs)
{
if (prepare_bitmap_walk(revs) < 0)
return -1;
if (pack_options_allow_reuse() &&
!reuse_partial_packfile_from_bitmap(
&reuse_packfile,
&reuse_packfile_objects,
&reuse_packfile_offset)) {
assert(reuse_packfile_objects);
nr_result += reuse_packfile_objects;
display_progress(progress_state, nr_result);
}
traverse_bitmap_commit_list(&add_object_entry_from_bitmap);
return 0;
}
static void record_recent_object(struct object *obj,
const char *name,
void *data)
{
oid_array_append(&recent_objects, &obj->oid);
}
static void record_recent_commit(struct commit *commit, void *data)
{
oid_array_append(&recent_objects, &commit->object.oid);
}
static void get_object_list(int ac, const char **av)
{
struct rev_info revs;
char line[1000];
int flags = 0;
init_revisions(&revs, NULL);
save_commit_buffer = 0;
setup_revisions(ac, av, &revs, NULL);
/* make sure shallows are read */
is_repository_shallow();
while (fgets(line, sizeof(line), stdin) != NULL) {
int len = strlen(line);
if (len && line[len - 1] == '\n')
line[--len] = 0;
if (!len)
break;
if (*line == '-') {
if (!strcmp(line, "--not")) {
flags ^= UNINTERESTING;
write_bitmap_index = 0;
continue;
}
if (starts_with(line, "--shallow ")) {
struct object_id oid;
if (get_oid_hex(line + 10, &oid))
die("not an SHA-1 '%s'", line + 10);
register_shallow(&oid);
use_bitmap_index = 0;
continue;
}
die("not a rev '%s'", line);
}
if (handle_revision_arg(line, &revs, flags, REVARG_CANNOT_BE_FILENAME))
die("bad revision '%s'", line);
}
if (use_bitmap_index && !get_object_list_from_bitmap(&revs))
return;
if (prepare_revision_walk(&revs))
die("revision walk setup failed");
mark_edges_uninteresting(&revs, show_edge);
if (!fn_show_object)
fn_show_object = show_object;
traverse_commit_list_filtered(&filter_options, &revs,
show_commit, fn_show_object, NULL,
NULL);
if (unpack_unreachable_expiration) {
revs.ignore_missing_links = 1;
if (add_unseen_recent_objects_to_traversal(&revs,
unpack_unreachable_expiration))
die("unable to add recent objects");
if (prepare_revision_walk(&revs))
die("revision walk setup failed");
traverse_commit_list(&revs, record_recent_commit,
record_recent_object, NULL);
}
if (keep_unreachable)
add_objects_in_unpacked_packs(&revs);
if (pack_loose_unreachable)
add_unreachable_loose_objects();
if (unpack_unreachable)
loosen_unused_packed_objects(&revs);
oid_array_clear(&recent_objects);
}
static void add_extra_kept_packs(const struct string_list *names)
{
struct packed_git *p;
if (!names->nr)
return;
for (p = get_packed_git(the_repository); p; p = p->next) {
const char *name = basename(p->pack_name);
int i;
if (!p->pack_local)
continue;
for (i = 0; i < names->nr; i++)
if (!fspathcmp(name, names->items[i].string))
break;
if (i < names->nr) {
p->pack_keep_in_core = 1;
ignore_packed_keep_in_core = 1;
continue;
}
}
}
static int option_parse_index_version(const struct option *opt,
const char *arg, int unset)
{
char *c;
const char *val = arg;
pack_idx_opts.version = strtoul(val, &c, 10);
if (pack_idx_opts.version > 2)
die(_("unsupported index version %s"), val);
if (*c == ',' && c[1])
pack_idx_opts.off32_limit = strtoul(c+1, &c, 0);
if (*c || pack_idx_opts.off32_limit & 0x80000000)
die(_("bad index version '%s'"), val);
return 0;
}
static int option_parse_unpack_unreachable(const struct option *opt,
const char *arg, int unset)
{
if (unset) {
unpack_unreachable = 0;
unpack_unreachable_expiration = 0;
}
else {
unpack_unreachable = 1;
if (arg)
unpack_unreachable_expiration = approxidate(arg);
}
return 0;
}
int cmd_pack_objects(int argc, const char **argv, const char *prefix)
{
int use_internal_rev_list = 0;
int thin = 0;
int shallow = 0;
int all_progress_implied = 0;
struct argv_array rp = ARGV_ARRAY_INIT;
int rev_list_unpacked = 0, rev_list_all = 0, rev_list_reflog = 0;
int rev_list_index = 0;
struct string_list keep_pack_list = STRING_LIST_INIT_NODUP;
struct option pack_objects_options[] = {
OPT_SET_INT('q', "quiet", &progress,
N_("do not show progress meter"), 0),
OPT_SET_INT(0, "progress", &progress,
N_("show progress meter"), 1),
OPT_SET_INT(0, "all-progress", &progress,
N_("show progress meter during object writing phase"), 2),
OPT_BOOL(0, "all-progress-implied",
&all_progress_implied,
N_("similar to --all-progress when progress meter is shown")),
{ OPTION_CALLBACK, 0, "index-version", NULL, N_("version[,offset]"),
N_("write the pack index file in the specified idx format version"),
0, option_parse_index_version },
OPT_MAGNITUDE(0, "max-pack-size", &pack_size_limit,
N_("maximum size of each output pack file")),
OPT_BOOL(0, "local", &local,
N_("ignore borrowed objects from alternate object store")),
OPT_BOOL(0, "incremental", &incremental,
N_("ignore packed objects")),
OPT_INTEGER(0, "window", &window,
N_("limit pack window by objects")),
OPT_MAGNITUDE(0, "window-memory", &window_memory_limit,
N_("limit pack window by memory in addition to object limit")),
OPT_INTEGER(0, "depth", &depth,
N_("maximum length of delta chain allowed in the resulting pack")),
OPT_BOOL(0, "reuse-delta", &reuse_delta,
N_("reuse existing deltas")),
OPT_BOOL(0, "reuse-object", &reuse_object,
N_("reuse existing objects")),
OPT_BOOL(0, "delta-base-offset", &allow_ofs_delta,
N_("use OFS_DELTA objects")),
OPT_INTEGER(0, "threads", &delta_search_threads,
N_("use threads when searching for best delta matches")),
OPT_BOOL(0, "non-empty", &non_empty,
N_("do not create an empty pack output")),
OPT_BOOL(0, "revs", &use_internal_rev_list,
N_("read revision arguments from standard input")),
OPT_SET_INT_F(0, "unpacked", &rev_list_unpacked,
N_("limit the objects to those that are not yet packed"),
1, PARSE_OPT_NONEG),
OPT_SET_INT_F(0, "all", &rev_list_all,
N_("include objects reachable from any reference"),
1, PARSE_OPT_NONEG),
OPT_SET_INT_F(0, "reflog", &rev_list_reflog,
N_("include objects referred by reflog entries"),
1, PARSE_OPT_NONEG),
OPT_SET_INT_F(0, "indexed-objects", &rev_list_index,
N_("include objects referred to by the index"),
1, PARSE_OPT_NONEG),
OPT_BOOL(0, "stdout", &pack_to_stdout,
N_("output pack to stdout")),
OPT_BOOL(0, "include-tag", &include_tag,
N_("include tag objects that refer to objects to be packed")),
OPT_BOOL(0, "keep-unreachable", &keep_unreachable,
N_("keep unreachable objects")),
OPT_BOOL(0, "pack-loose-unreachable", &pack_loose_unreachable,
N_("pack loose unreachable objects")),
{ OPTION_CALLBACK, 0, "unpack-unreachable", NULL, N_("time"),
N_("unpack unreachable objects newer than <time>"),
PARSE_OPT_OPTARG, option_parse_unpack_unreachable },
OPT_BOOL(0, "thin", &thin,
N_("create thin packs")),
OPT_BOOL(0, "shallow", &shallow,
N_("create packs suitable for shallow fetches")),
OPT_BOOL(0, "honor-pack-keep", &ignore_packed_keep_on_disk,
N_("ignore packs that have companion .keep file")),
OPT_STRING_LIST(0, "keep-pack", &keep_pack_list, N_("name"),
N_("ignore this pack")),
OPT_INTEGER(0, "compression", &pack_compression_level,
N_("pack compression level")),
OPT_SET_INT(0, "keep-true-parents", &grafts_replace_parents,
N_("do not hide commits by grafts"), 0),
OPT_BOOL(0, "use-bitmap-index", &use_bitmap_index,
N_("use a bitmap index if available to speed up counting objects")),
OPT_BOOL(0, "write-bitmap-index", &write_bitmap_index,
N_("write a bitmap index together with the pack index")),
OPT_PARSE_LIST_OBJECTS_FILTER(&filter_options),
{ OPTION_CALLBACK, 0, "missing", NULL, N_("action"),
N_("handling for missing objects"), PARSE_OPT_NONEG,
option_parse_missing_action },
OPT_BOOL(0, "exclude-promisor-objects", &exclude_promisor_objects,
N_("do not pack objects in promisor packfiles")),
OPT_END(),
};
if (DFS_NUM_STATES > (1 << OE_DFS_STATE_BITS))
BUG("too many dfs states, increase OE_DFS_STATE_BITS");
check_replace_refs = 0;
reset_pack_idx_option(&pack_idx_opts);
git_config(git_pack_config, NULL);
progress = isatty(2);
argc = parse_options(argc, argv, prefix, pack_objects_options,
pack_usage, 0);
if (argc) {
base_name = argv[0];
argc--;
}
if (pack_to_stdout != !base_name || argc)
usage_with_options(pack_usage, pack_objects_options);
if (depth >= (1 << OE_DEPTH_BITS)) {
warning(_("delta chain depth %d is too deep, forcing %d"),
depth, (1 << OE_DEPTH_BITS) - 1);
depth = (1 << OE_DEPTH_BITS) - 1;
}
if (cache_max_small_delta_size >= (1U << OE_Z_DELTA_BITS)) {
warning(_("pack.deltaCacheLimit is too high, forcing %d"),
(1U << OE_Z_DELTA_BITS) - 1);
cache_max_small_delta_size = (1U << OE_Z_DELTA_BITS) - 1;
}
argv_array_push(&rp, "pack-objects");
if (thin) {
use_internal_rev_list = 1;
argv_array_push(&rp, shallow
? "--objects-edge-aggressive"
: "--objects-edge");
} else
argv_array_push(&rp, "--objects");
if (rev_list_all) {
use_internal_rev_list = 1;
argv_array_push(&rp, "--all");
}
if (rev_list_reflog) {
use_internal_rev_list = 1;
argv_array_push(&rp, "--reflog");
}
if (rev_list_index) {
use_internal_rev_list = 1;
argv_array_push(&rp, "--indexed-objects");
}
if (rev_list_unpacked) {
use_internal_rev_list = 1;
argv_array_push(&rp, "--unpacked");
}
if (exclude_promisor_objects) {
use_internal_rev_list = 1;
fetch_if_missing = 0;
argv_array_push(&rp, "--exclude-promisor-objects");
}
if (unpack_unreachable || keep_unreachable || pack_loose_unreachable)
use_internal_rev_list = 1;
if (!reuse_object)
reuse_delta = 0;
if (pack_compression_level == -1)
pack_compression_level = Z_DEFAULT_COMPRESSION;
else if (pack_compression_level < 0 || pack_compression_level > Z_BEST_COMPRESSION)
die("bad pack compression level %d", pack_compression_level);
if (!delta_search_threads) /* --threads=0 means autodetect */
delta_search_threads = online_cpus();
#ifdef NO_PTHREADS
if (delta_search_threads != 1)
warning("no threads support, ignoring --threads");
#endif
if (!pack_to_stdout && !pack_size_limit)
pack_size_limit = pack_size_limit_cfg;
if (pack_to_stdout && pack_size_limit)
die("--max-pack-size cannot be used to build a pack for transfer.");
if (pack_size_limit && pack_size_limit < 1024*1024) {
warning("minimum pack size limit is 1 MiB");
pack_size_limit = 1024*1024;
}
if (!pack_to_stdout && thin)
die("--thin cannot be used to build an indexable pack.");
if (keep_unreachable && unpack_unreachable)
die("--keep-unreachable and --unpack-unreachable are incompatible.");
if (!rev_list_all || !rev_list_reflog || !rev_list_index)
unpack_unreachable_expiration = 0;
if (filter_options.choice) {
if (!pack_to_stdout)
die("cannot use --filter without --stdout.");
use_bitmap_index = 0;
}
/*
* "soft" reasons not to use bitmaps - for on-disk repack by default we want
*
* - to produce good pack (with bitmap index not-yet-packed objects are
* packed in suboptimal order).
*
* - to use more robust pack-generation codepath (avoiding possible
* bugs in bitmap code and possible bitmap index corruption).
*/
if (!pack_to_stdout)
use_bitmap_index_default = 0;
if (use_bitmap_index < 0)
use_bitmap_index = use_bitmap_index_default;
/* "hard" reasons not to use bitmaps; these just won't work at all */
if (!use_internal_rev_list || (!pack_to_stdout && write_bitmap_index) || is_repository_shallow())
use_bitmap_index = 0;
if (pack_to_stdout || !rev_list_all)
write_bitmap_index = 0;
if (progress && all_progress_implied)
progress = 2;
add_extra_kept_packs(&keep_pack_list);
if (ignore_packed_keep_on_disk) {
struct packed_git *p;
for (p = get_packed_git(the_repository); p; p = p->next)
if (p->pack_local && p->pack_keep)
break;
if (!p) /* no keep-able packs found */
ignore_packed_keep_on_disk = 0;
}
if (local) {
/*
* unlike ignore_packed_keep_on_disk above, we do not
* want to unset "local" based on looking at packs, as
* it also covers non-local objects
*/
struct packed_git *p;
for (p = get_packed_git(the_repository); p; p = p->next) {
if (!p->pack_local) {
have_non_local_packs = 1;
break;
}
}
}
prepare_packing_data(&to_pack);
if (progress)
progress_state = start_progress(_("Enumerating objects"), 0);
if (!use_internal_rev_list)
read_object_list_from_stdin();
else {
get_object_list(rp.argc, rp.argv);
argv_array_clear(&rp);
}
cleanup_preferred_base();
if (include_tag && nr_result)
for_each_ref(add_ref_tag, NULL);
stop_progress(&progress_state);
if (non_empty && !nr_result)
return 0;
if (nr_result)
prepare_pack(window, depth);
write_pack_file();
if (progress)
fprintf(stderr, "Total %"PRIu32" (delta %"PRIu32"),"
" reused %"PRIu32" (delta %"PRIu32")\n",
written, written_delta, reused, reused_delta);
return 0;
}
|