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
//! Common options for DB, CF, read/write/flush/compact... use lazy_static::lazy_static; use std::fmt; use std::marker::PhantomData; use std::mem; use std::os::raw::c_int; use std::path::{Path, PathBuf}; use std::ptr; use std::slice; use std::str; use std::u64; use rocks_sys as ll; use crate::advanced_options::{CompactionOptionsFIFO, CompactionPri, CompactionStyle, CompressionOptions}; use crate::cache::Cache; use crate::compaction_filter::{CompactionFilter, CompactionFilterFactory}; use crate::comparator::Comparator; use crate::env::{Env, InfoLogLevel, Logger}; use crate::listener::EventListener; use crate::merge_operator::{AssociativeMergeOperator, MergeOperator}; use crate::rate_limiter::RateLimiter; use crate::slice_transform::SliceTransform; use crate::snapshot::Snapshot; use crate::sst_file_manager::SstFileManager; use crate::statistics::Statistics; use crate::table::{BlockBasedTableOptions, CuckooTableOptions, PlainTableOptions}; use crate::table_properties::TablePropertiesCollectorFactory; use crate::types::SequenceNumber; use crate::universal_compaction::CompactionOptionsUniversal; use crate::write_buffer_manager::WriteBufferManager; use crate::to_raw::{FromRaw, ToRaw}; lazy_static! { // since all Options field are guaranteed to be thread safe static ref DEFAULT_OPTIONS: Options = { Options::default().map_db_options(|db| db.create_if_missing(true)) }; static ref DEFAULT_READ_OPTIONS: ReadOptions<'static> = { ReadOptions::default() }; static ref DEFAULT_WRITE_OPTIONS: WriteOptions = { WriteOptions::default() }; static ref DEFAULT_FLUSH_OPTIONS: FlushOptions = { FlushOptions::default() }; } /// DB contents are stored in a set of blocks, each of which holds a /// sequence of key,value pairs. Each block may be compressed before /// being stored in a file. The following enum describes which /// compression method (if any) is used to compress a block. #[repr(C)] // FIXME: u8 in rocksdb #[derive(Debug, Copy, Clone, PartialEq, Eq, PartialOrd, Ord, Hash)] pub enum CompressionType { /// NOTE: do not change the values of existing entries, as these are /// part of the persistent format on disk. NoCompression = 0x0, SnappyCompression = 0x1, ZlibCompression = 0x2, BZip2Compression = 0x3, LZ4Compression = 0x4, LZ4HCCompression = 0x5, XpressCompression = 0x6, ZSTD = 0x7, /// Only use kZSTDNotFinalCompression if you have to use ZSTD lib older than /// 0.8.0 or consider a possibility of downgrading the service or copying /// the database files to another service running with an older version of /// RocksDB that doesn't have kZSTD. Otherwise, you should use kZSTD. We will /// eventually remove the option from the public API. ZSTDNotFinalCompression = 0x40, /// kDisableCompressionOption is used to disable some compression options. DisableCompressionOption = 0xff, } /// Recovery mode to control the consistency while replaying WAL #[repr(C)] pub enum WALRecoveryMode { /// Original levelDB recovery /// We tolerate incomplete record in trailing data on all logs /// Use case : This is legacy behavior (default) TolerateCorruptedTailRecords = 0x00, /// Recover from clean shutdown /// We don't expect to find any corruption in the WAL /// Use case : This is ideal for unit tests and rare applications that /// can require high consistency guarantee AbsoluteConsistency = 0x01, /// Recover to point-in-time consistency /// We stop the WAL playback on discovering WAL inconsistency /// Use case : Ideal for systems that have disk controller cache like /// hard disk, SSD without super capacitor that store related data PointInTimeRecovery = 0x02, /// Recovery after a disaster /// We ignore any corruption in the WAL and try to salvage as much data as /// possible /// Use case : Ideal for last ditch effort to recover data or systems that /// operate with low grade unrelated data SkipAnyCorruptedRecords = 0x03, } #[derive(Debug)] pub struct DbPath { pub path: PathBuf, /// Target size of total files under the path, in byte. pub target_size: u64, } impl DbPath { pub fn new<P: AsRef<Path>>(p: P, t: u64) -> DbPath { DbPath { path: p.as_ref().to_path_buf(), target_size: t, } } } impl Default for DbPath { fn default() -> Self { DbPath::new("", 0) } } impl<T: Into<PathBuf>> From<T> for DbPath { fn from(path: T) -> DbPath { DbPath { path: path.into(), target_size: 0, } } } /* impl<P: Into<PathBuf>, S: Into<u64>> From<(P, S)> for DbPath { fn from((path, size): (P, S)) -> DbPath { DbPath { path: path.into(), target_size: size.into(), } } } */ /// Options for a column family pub struct ColumnFamilyOptions { raw: *mut ll::rocks_cfoptions_t, } impl ToRaw<ll::rocks_cfoptions_t> for ColumnFamilyOptions { fn raw(&self) -> *mut ll::rocks_cfoptions_t { self.raw } } impl FromRaw<ll::rocks_cfoptions_t> for ColumnFamilyOptions { unsafe fn from_ll(raw: *mut ll::rocks_cfoptions_t) -> Self { ColumnFamilyOptions { raw } } } impl Default for ColumnFamilyOptions { fn default() -> Self { ColumnFamilyOptions { raw: unsafe { ll::rocks_cfoptions_create() }, } } } impl Drop for ColumnFamilyOptions { fn drop(&mut self) { unsafe { ll::rocks_cfoptions_destroy(self.raw); } } } impl fmt::Debug for ColumnFamilyOptions { fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result { write!(f, "ColumnFamilyOptions {{ ")?; unsafe { let cxx_string = ll::rocks_get_string_from_cfoptions(self.raw); let len = ll::cxx_string_size(cxx_string); let base = ll::cxx_string_data(cxx_string); if !cxx_string.is_null() { let str_rep = str::from_utf8_unchecked(slice::from_raw_parts(base as *const u8, len)); f.write_str(str_rep)?; ll::cxx_string_destroy(cxx_string); } else { write!(f, "error while converting to String")?; } } write!(f, "}}") } } impl ColumnFamilyOptions { /// Create ColumnFamilyOptions with default values for all fields pub fn new() -> ColumnFamilyOptions { ColumnFamilyOptions { raw: unsafe { ll::rocks_cfoptions_create() }, } } unsafe fn from_ll(raw: *mut ll::rocks_cfoptions_t) -> ColumnFamilyOptions { ColumnFamilyOptions { raw: raw } } pub fn from_options(opt: &Options) -> ColumnFamilyOptions { ColumnFamilyOptions { raw: unsafe { ll::rocks_cfoptions_create_from_options(opt.raw()) }, } } // ! Some functions that make it easier to optimize RocksDB /// Use this if your DB is very small (like under 1GB) and you don't want to /// spend lots of memory for memtables. pub fn optimize_for_small_db(self) -> Self { unsafe { ll::rocks_cfoptions_optimize_for_small_db(self.raw); } self } /// Use this if you don't need to keep the data sorted, i.e. you'll never use /// an iterator, only Put() and Get() API calls pub fn optimize_for_point_lookup(self, block_cache_size_mb: u64) -> Self { unsafe { ll::rocks_cfoptions_optimize_for_point_lookup(self.raw, block_cache_size_mb) } self } /// Default values for some parameters in ColumnFamilyOptions are not /// optimized for heavy workloads and big datasets, which means you might /// observe write stalls under some conditions. As a starting point for tuning /// RocksDB options, use the following two functions: /// /// * OptimizeLevelStyleCompaction -- optimizes level style compaction /// * OptimizeUniversalStyleCompaction -- optimizes universal style compaction /// /// Universal style compaction is focused on reducing Write Amplification /// Factor for big data sets, but increases Space Amplification. You can learn /// more about the different styles here: /// https://github.com/facebook/rocksdb/wiki/Rocksdb-Architecture-Guide /// Make sure to also call IncreaseParallelism(), which will provide the /// biggest performance gains. /// /// Note: we might use more memory than memtable_memory_budget during high /// write rate period /// /// Default: 512 * 1024 * 1024 pub fn optimize_level_style_compaction(self, memtable_memory_budget: u64) -> Self { unsafe { ll::rocks_cfoptions_optimize_level_style_compaction(self.raw, memtable_memory_budget); } self } /// Universal style compaction is focused on reducing Write Amplification /// Factor for big data sets, but increases Space Amplification. /// /// Default: 512 * 1024 * 1024 pub fn optimize_universal_style_compaction(self, memtable_memory_budget: u64) -> Self { unsafe { ll::rocks_cfoptions_optimize_universal_style_compaction(self.raw, memtable_memory_budget); } self } // ! Parameters that affect behavior /// Comparator used to define the order of keys in the table. /// Default: a comparator that uses lexicographic byte-wise ordering /// /// REQUIRES: The client must ensure that the comparator supplied /// here has the same name and orders keys *exactly* the same as the /// comparator provided to previous open calls on the same DB. pub fn comparator<T: Comparator>(self, val: &'static T) -> Self { unsafe { // Box<&dyn Comparator> let raw_ptr = Box::into_raw(Box::new(val as &dyn Comparator)); ll::rocks_cfoptions_set_comparator_by_trait(self.raw, raw_ptr as *mut _); } self } /// Use bitwise comparator and set if reversed. pub fn bitwise_comparator_reversed(self, val: bool) -> Self { unsafe { ll::rocks_cfoptions_set_bitwise_comparator(self.raw, val as u8); } self } /// REQUIRES: The client must provide a merge operator if Merge operation /// needs to be accessed. Calling Merge on a DB without a merge operator /// would result in Status::NotSupported. The client must ensure that the /// merge operator supplied here has the same name and *exactly* the same /// semantics as the merge operator provided to previous open calls on /// the same DB. The only exception is reserved for upgrade, where a DB /// previously without a merge operator is introduced to Merge operation /// for the first time. It's necessary to specify a merge operator when /// openning the DB in this case. /// /// Default: nullptr pub fn merge_operator(self, val: Box<dyn MergeOperator>) -> Self { unsafe { let raw_ptr = Box::into_raw(Box::new(val)); // Box<Box<MergeOperator>> ll::rocks_cfoptions_set_merge_operator_by_merge_op_trait(self.raw, raw_ptr as *mut _); } self } pub fn associative_merge_operator(self, val: Box<dyn AssociativeMergeOperator>) -> Self { unsafe { // FIXME: into_raw let raw_ptr = Box::into_raw(Box::new(val)); // Box<Box<AssociativeMergeOperator>> ll::rocks_cfoptions_set_merge_operator_by_assoc_op_trait(self.raw, raw_ptr as *mut _); } self } /// A single CompactionFilter instance to call into during compaction. /// Allows an application to modify/delete a key-value during background /// compaction. /// /// If the client requires a new compaction filter to be used for different /// compaction runs, it can specify compaction_filter_factory instead of this /// option. The client should specify only one of the two. /// compaction_filter takes precedence over compaction_filter_factory if /// client specifies both. /// /// If multithreaded compaction is being used, the supplied CompactionFilter /// instance may be used from different threads concurrently and so should be /// thread-safe. /// /// Default: nullptr pub fn compaction_filter(self, filter: &'static (dyn CompactionFilter + Sync)) -> Self { unsafe { // FIXME: mem leaks // CFOptions.compaction_filter is a raw pointer let raw_ptr = Box::into_raw(Box::new(filter)); // Box<Box<CompactionFilter>> ll::rocks_cfoptions_set_compaction_filter_by_trait(self.raw, raw_ptr as *mut _); } self } /// This is a factory that provides compaction filter objects which allow /// an application to modify/delete a key-value during background compaction. /// /// A new filter will be created on each compaction run. If multithreaded /// compaction is being used, each created CompactionFilter will only be used /// from a single thread and so does not need to be thread-safe. /// /// Default: nullptr pub fn compaction_filter_factory(self, factory: Box<dyn CompactionFilterFactory>) -> Self { // unsafe { // ll::rocks_cfoptions_set_compaction_filter_factory(self.raw, ) // } // self unimplemented!() } // ------------------- // Parameters that affect performance // ------------------- /// Amount of data to build up in memory (backed by an unsorted log /// on disk) before converting to a sorted on-disk file. /// /// Larger values increase performance, especially during bulk loads. /// Up to max_write_buffer_number write buffers may be held in memory /// at the same time, /// so you may wish to adjust this parameter to control memory usage. /// Also, a larger write buffer will result in a longer recovery time /// the next time the database is opened. /// /// Note that write_buffer_size is enforced per column family. /// See db_write_buffer_size for sharing memory across column families. /// /// Default: 64MB /// /// Dynamically changeable through `SetOptions()` API pub fn write_buffer_size(self, val: usize) -> Self { unsafe { ll::rocks_cfoptions_set_write_buffer_size(self.raw, val); } self } /// Compress blocks using the specified compression algorithm. This /// parameter can be changed dynamically. /// /// Default: kSnappyCompression, if it's supported. If snappy is not linked /// with the library, the default is kNoCompression. /// /// Typical speeds of kSnappyCompression on an Intel(R) Core(TM)2 2.4GHz: /// /// - ~200-500MB/s compression /// - ~400-800MB/s decompression /// /// Note that these speeds are significantly faster than most /// persistent storage speeds, and therefore it is typically never /// worth switching to kNoCompression. Even if the input data is /// incompressible, the kSnappyCompression implementation will /// efficiently detect that and will switch to uncompressed mode. pub fn compression(self, val: CompressionType) -> Self { unsafe { ll::rocks_cfoptions_set_compression(self.raw, mem::transmute(val)); } self } /// Compression algorithm that will be used for the bottommost level that /// contain files. If level-compaction is used, this option will only affect /// levels after base level. /// /// Default: kDisableCompressionOption (Disabled) pub fn bottommost_compression(self, val: CompressionType) -> Self { unsafe { ll::rocks_cfoptions_set_bottommost_compression(self.raw, mem::transmute(val)); } self } /// Different options for compression algorithms pub fn compression_opts(self, val: CompressionOptions) -> Self { unsafe { // FIXME: name changes from opts to options ll::rocks_cfoptions_set_compression_options( self.raw, val.window_bits, val.level, val.strategy, val.max_dict_bytes, ); } self } /// Number of files to trigger level-0 compaction. A value <0 means that /// level-0 compaction will not be triggered by number of files at all. /// /// Default: 4 /// /// Dynamically changeable through `SetOptions()` API pub fn level0_file_num_compaction_trigger(self, val: i32) -> Self { unsafe { ll::rocks_cfoptions_set_level0_file_num_compaction_trigger(self.raw, val); } self } /// If non-nullptr, use the specified function to determine the /// prefixes for keys. These prefixes will be placed in the filter. /// Depending on the workload, this can reduce the number of read-IOP /// cost for scans when a prefix is passed via ReadOptions to /// db.NewIterator(). For prefix filtering to work properly, /// "prefix_extractor" and "comparator" must be such that the following /// properties hold: /// /// 1) key.starts_with(prefix(key)) /// 2) Compare(prefix(key), key) <= 0. /// 3) If Compare(k1, k2) <= 0, then Compare(prefix(k1), prefix(k2)) <= 0 /// 4) prefix(prefix(key)) == prefix(key) /// /// Default: nullptr // FIXME: split other prefix extractor variants pub fn prefix_extractor(self, val: Box<dyn SliceTransform + Sync>) -> Self { unsafe { let raw_ptr = Box::into_raw(Box::new(val)); ll::rocks_cfoptions_set_prefix_extractor_by_trait(self.raw, raw_ptr as *mut _); } self } /// rocksdb.FixedPrefix.N pub fn prefix_extractor_fixed(self, len: usize) -> Self { unsafe { ll::rocks_cfoptions_set_prefix_extractor_fixed_prefix(self.raw, len); } self } /// rocksdb.CappedPrefix.N pub fn prefix_extractor_capped(self, len: usize) -> Self { unsafe { ll::rocks_cfoptions_set_prefix_extractor_capped_prefix(self.raw, len); } self } /// rocksdb.Noop pub fn prefix_extractor_noop(self) -> Self { unsafe { ll::rocks_cfoptions_set_prefix_extractor_noop(self.raw); } self } /// Control maximum total data size for a level. /// max_bytes_for_level_base is the max total for level-1. /// Maximum number of bytes for level L can be calculated as /// (max_bytes_for_level_base) * (max_bytes_for_level_multiplier ^ (L-1)) /// For example, if max_bytes_for_level_base is 200MB, and if /// max_bytes_for_level_multiplier is 10, total data size for level-1 /// will be 200MB, total file size for level-2 will be 2GB, /// and total file size for level-3 will be 20GB. /// /// Default: 256MB. /// /// Dynamically changeable through `SetOptions()` API pub fn max_bytes_for_level_base(self, val: u64) -> Self { unsafe { ll::rocks_cfoptions_set_max_bytes_for_level_base(self.raw, val); } self } /// Disable automatic compactions. Manual compactions can still /// be issued on this column family /// /// Dynamically changeable through `SetOptions()` API pub fn disable_auto_compactions(self, val: bool) -> Self { unsafe { ll::rocks_cfoptions_set_disable_auto_compactions(self.raw, val as u8); } self } /// This is a factory that provides TableFactory objects. /// /// Default: a block-based table factory that provides a default /// implementation of TableBuilder and TableReader with default /// BlockBasedTableOptions. /// /// For Rust: split into 3 different functions pub fn table_factory(self, val: ()) -> Self { panic!("use any of plain_table_factory, block_based_table_factory and cuckoo_table_factory") } /// Plain Table with prefix-only seek /// /// For this factory, you need to set Options.prefix_extractor properly to make /// it work. Look-up will starts with prefix hash lookup for key prefix. Inside /// the hash bucket found, a binary search is executed for hash conflicts. /// Finally, a linear search is used. pub fn table_factory_plain(self, opt: PlainTableOptions) -> Self { unsafe { ll::rocks_cfoptions_set_plain_table_factory(self.raw, opt.raw()); } self } /// Default block based table factory. pub fn table_factory_block_based(self, opt: BlockBasedTableOptions) -> Self { unsafe { ll::rocks_cfoptions_set_block_based_table_factory(self.raw, opt.raw()); } self } /// Cuckoo Table Factory for SST table format using Cache Friendly Cuckoo Hashing /// /// Requires DBOptions.allow_mmap_reads = true pub fn table_factory_cuckoo(self, opt: CuckooTableOptions) -> Self { unsafe { ll::rocks_cfoptions_set_cuckoo_table_factory(self.raw, opt.raw()); } self } // Following: AdvancedColumnFamilyOptions /// The maximum number of write buffers that are built up in memory. /// The default and the minimum number is 2, so that when 1 write buffer /// is being flushed to storage, new writes can continue to the other /// write buffer. /// /// If `max_write_buffer_number` > 3, writing will be slowed down to /// `options.delayed_write_rate` if we are writing to the last write buffer /// allowed. /// /// Default: 2 /// /// Dynamically changeable through `SetOptions()` API pub fn max_write_buffer_number(self, val: i32) -> Self { unsafe { ll::rocks_cfoptions_set_max_write_buffer_number(self.raw, val); } self } /// The minimum number of write buffers that will be merged together /// before writing to storage. If set to 1, then /// all write buffers are flushed to L0 as individual files and this increases /// read amplification because a get request has to check in all of these /// files. Also, an in-memory merge may result in writing lesser /// data to storage if there are duplicate records in each of these /// individual write buffers. /// /// Default: 1 pub fn min_write_buffer_number_to_merge(self, val: i32) -> Self { unsafe { ll::rocks_cfoptions_set_min_write_buffer_number_to_merge(self.raw, val); } self } /// The total maximum number of write buffers to maintain in memory including /// copies of buffers that have already been flushed. Unlike /// max_write_buffer_number, this parameter does not affect flushing. /// This controls the minimum amount of write history that will be available /// in memory for conflict checking when Transactions are used. /// /// When using an OptimisticTransactionDB: /// /// If this value is too low, some transactions may fail at commit time due /// to not being able to determine whether there were any write conflicts. /// /// When using a TransactionDB: /// /// If Transaction::SetSnapshot is used, TransactionDB will read either /// in-memory write buffers or SST files to do write-conflict checking. /// Increasing this value can reduce the number of reads to SST files /// done for conflict detection. /// /// Setting this value to 0 will cause write buffers to be freed immediately /// after they are flushed. /// /// If this value is set to -1, 'max_write_buffer_number' will be used. /// /// Default: /// /// If using a TransactionDB/OptimisticTransactionDB, the default value will /// be set to the value of 'max_write_buffer_number' if it is not explicitly /// set by the user. Otherwise, the default is 0. pub fn max_write_buffer_number_to_maintain(self, val: i32) -> Self { unsafe { ll::rocks_cfoptions_set_max_write_buffer_number_to_maintain(self.raw, val); } self } /// Allows thread-safe inplace updates. If this is true, there is no way to /// achieve point-in-time consistency using snapshot or iterator (assuming /// concurrent updates). Hence iterator and multi-get will return results /// which are not consistent as of any point-in-time. /// /// If inplace_callback function is not set, /// Put(key, new_value) will update inplace the existing_value iff /// /// * key exists in current memtable /// * new sizeof(new_value) <= sizeof(existing_value) /// * existing_value for that key is a put i.e. kTypeValue /// /// If inplace_callback function is set, check doc for inplace_callback. /// /// Default: false. pub fn inplace_update_support(self, val: bool) -> Self { unsafe { ll::rocks_cfoptions_set_inplace_update_support(self.raw, val as u8); } self } /// Number of locks used for inplace update /// /// Default: 10000, if inplace_update_support = true, else 0. /// /// Dynamically changeable through `SetOptions()` API pub fn inplace_update_num_locks(self, val: usize) -> Self { unsafe { ll::rocks_cfoptions_set_inplace_update_num_locks(self.raw, val); } self } /// /// * existing_value - pointer to previous value (from both memtable and sst). pub nullptr if /// key doesn't exist /// * existing_value_size - pointer to size of existing_value). pub nullptr if key doesn't exist /// * delta_value - Delta value to be merged with the existing_value. pub Stored in transaction /// logs. /// * merged_value - Set when delta is applied on the previous value. /// /// Applicable only when inplace_update_support is true, /// this callback function is called at the time of updating the memtable /// as part of a Put operation, lets say Put(key, delta_value). It allows the /// 'delta_value' specified as part of the Put operation to be merged with /// an 'existing_value' of the key in the database. /// /// If the merged value is smaller in size that the 'existing_value', /// then this function can update the 'existing_value' buffer inplace and /// the corresponding 'existing_value'_size pointer, if it wishes to. /// The callback should return UpdateStatus::UPDATED_INPLACE. /// In this case. (In this case, the snapshot-semantics of the rocksdb /// Iterator is not atomic anymore). /// /// If the merged value is larger in size than the 'existing_value' or the /// application does not wish to modify the 'existing_value' buffer inplace, /// then the merged value should be returned via *merge_value. It is set by /// merging the 'existing_value' and the Put 'delta_value'. The callback should /// return UpdateStatus::UPDATED in this case. This merged value will be added /// to the memtable. /// /// If merging fails or the application does not wish to take any action, /// then the callback should return `UpdateStatus::UPDATE_FAILED`. /// /// Please remember that the original call from the application is Put(key, /// delta_value). So the transaction log (if enabled) will still contain (key, /// delta_value). The 'merged_value' is not stored in the transaction log. /// Hence the inplace_callback function should be consistent across db reopens. /// /// Default: nullptr /// /// Rust: TODO: unimplemented!() pub fn inplace_callback<F>(self, val: Option<()>) -> Self { // unsafe { // ll::rocks_cfoptions_set_inplace_callback(self.raw, val); // } // self unimplemented!() } // UpdateStatus (*inplace_callback)(char* existing_value, // uint32_t* existing_value_size, // Slice delta_value, // std::string* merged_value) = nullptr; /// if prefix_extractor is set and memtable_prefix_bloom_size_ratio is not 0, /// create prefix bloom for memtable with the size of /// write_buffer_size * memtable_prefix_bloom_size_ratio. /// If it is larger than 0.25, it is santinized to 0.25. /// /// Default: 0 (disable) /// /// Dynamically changeable through `SetOptions()` API pub fn memtable_prefix_bloom_size_ratio(self, val: f64) -> Self { unsafe { ll::rocks_cfoptions_set_memtable_prefix_bloom_size_ratio(self.raw, val); } self } /// Page size for huge page for the arena used by the memtable. If <=0, it /// won't allocate from huge page but from malloc. /// Users are responsible to reserve huge pages for it to be allocated. For /// example: /// /// > `pub sysctl -w vm.nr_hugepages=20` /// /// See linux doc Documentation/vm/hugetlbpage.txt /// /// If there isn't enough free huge page available, it will fall back to /// malloc. /// /// Dynamically changeable through `SetOptions()` API pub fn memtable_huge_page_size(self, val: usize) -> Self { unsafe { ll::rocks_cfoptions_set_memtable_huge_page_size(self.raw, val); } self } /// If non-nullptr, memtable will use the specified function to extract /// prefixes for keys, and for each prefix maintain a hint of insert location /// to reduce CPU usage for inserting keys with the prefix. Keys out of /// domain of the prefix extractor will be insert without using hints. /// /// Currently only the default skiplist based memtable implements the feature. /// All other memtable implementation will ignore the option. It incurs ~250 /// additional bytes of memory overhead to store a hint for each prefix. /// Also concurrent writes (when allow_concurrent_memtable_write is true) will /// ignore the option. /// /// The option is best suited for workloads where keys will likely to insert /// to a location close the the last inserted key with the same prefix. /// One example could be inserting keys of the form (prefix + timestamp), /// and keys of the same prefix always comes in with time order. Another /// example would be updating the same key over and over again, in which case /// the prefix can be the key itself. /// /// Default: nullptr (disable) pub fn memtable_insert_with_hint_prefix_extractor(self, val: Box<dyn SliceTransform + Sync>) -> Self { unsafe { let raw_ptr = Box::into_raw(Box::new(val)); ll::rocks_cfoptions_set_memtable_insert_with_hint_prefix_extractor_by_trait(self.raw, raw_ptr as *mut _); } self } pub fn memtable_insert_with_hint_prefix_extractor_fixed(self, len: usize) -> Self { unsafe { ll::rocks_cfoptions_set_memtable_insert_with_hint_prefix_extractor_fixed_prefix(self.raw, len); } self } pub fn memtable_insert_with_hint_prefix_extractor_capped(self, len: usize) -> Self { unsafe { ll::rocks_cfoptions_set_memtable_insert_with_hint_prefix_extractor_capped_prefix(self.raw, len); } self } pub fn memtable_insert_with_hint_prefix_extractor_noop(self) -> Self { unsafe { ll::rocks_cfoptions_set_memtable_insert_with_hint_prefix_extractor_noop(self.raw); } self } /// Control locality of bloom filter probes to improve cache miss rate. /// /// This option only applies to memtable prefix bloom and plaintable /// prefix bloom. It essentially limits every bloom checking to one cache line. /// This optimization is turned off when set to 0, and positive number to turn /// it on. /// /// Default: 0 pub fn bloom_locality(self, val: u32) -> Self { unsafe { ll::rocks_cfoptions_set_bloom_locality(self.raw, val); } self } /// size of one block in arena memory allocation. /// /// If <= 0, a proper value is automatically calculated (usually 1/8 of /// writer_buffer_size, rounded up to a multiple of 4KB). /// /// There are two additional restriction of the The specified size: /// /// 1. size should be in the range of [4096, 2 << 30] and /// 2. be the multiple of the CPU word (which helps with the memory /// alignment). /// /// We'll automatically check and adjust the size number to make sure it /// conforms to the restrictions. /// /// Default: 0 /// /// Dynamically changeable through `SetOptions()` API pub fn arena_block_size(self, val: usize) -> Self { unsafe { ll::rocks_cfoptions_set_arena_block_size(self.raw, val); } self } /// Different levels can have different compression policies. There /// are cases where most lower levels would like to use quick compression /// algorithms while the higher levels (which have more data) use /// compression algorithms that have better compression but could /// be slower. This array, if non-empty, should have an entry for /// each level of the database; these override the value specified in /// the previous field 'compression'. /// /// NOTICE if level_compaction_dynamic_level_bytes=true, /// compression_per_level[0] still determines L0, but other elements /// of the array are based on base level (the level L0 files are merged /// to), and may not match the level users see from info log for metadata. /// If L0 files are merged to level-n, then, for i>0, compression_per_level[i] /// determines compaction type for level n+i-1. /// /// For example, if we have three 5 levels, and we determine to merge L0 /// data to L4 (which means L1..L3 will be empty), then the new files go to /// L4 uses compression type compression_per_level[1]. /// /// If now L0 is merged to L2. Data goes to L2 will be compressed /// according to compression_per_level[1], L3 using compression_per_level[2] /// and L4 using compression_per_level[3]. Compaction for each level can /// change when data grows. pub fn compression_per_level(self, val: &[CompressionType]) -> Self { unsafe { ll::rocks_cfoptions_set_compression_per_level( self.raw, mem::transmute(val.as_ptr()), // repr(C) val.len(), ); } self } /// Number of levels for this database /// /// Default: 7 pub fn num_levels(self, val: i32) -> Self { unsafe { ll::rocks_cfoptions_set_num_levels(self.raw, val); } self } /// Soft limit on number of level-0 files. We start slowing down writes at this /// point. A value <0 means that no writing slow down will be triggered by /// number of files in level-0. /// /// Default: 20 /// /// Dynamically changeable through `SetOptions()` API pub fn level0_slowdown_writes_trigger(self, val: i32) -> Self { unsafe { ll::rocks_cfoptions_set_level0_slowdown_writes_trigger(self.raw, val); } self } /// Maximum number of level-0 files. We stop writes at this point. /// /// Default: 36 /// /// Dynamically changeable through `SetOptions()` API pub fn level0_stop_writes_trigger(self, val: i32) -> Self { unsafe { ll::rocks_cfoptions_set_level0_stop_writes_trigger(self.raw, val); } self } /// Target file size for compaction. /// /// target_file_size_base is per-file size for level-1. /// Target file size for level L can be calculated by /// target_file_size_base * (target_file_size_multiplier ^ (L-1)) /// For example, if target_file_size_base is 2MB and /// target_file_size_multiplier is 10, then each file on level-1 will /// be 2MB, and each file on level 2 will be 20MB, /// and each file on level-3 will be 200MB. /// /// Default: 64MB. /// /// Dynamically changeable through `SetOptions()` API pub fn target_file_size_base(self, val: u64) -> Self { unsafe { ll::rocks_cfoptions_set_target_file_size_base(self.raw, val); } self } /// By default `target_file_size_multiplier` is 1, which means /// by default files in different levels will have similar size. /// /// Dynamically changeable through `SetOptions()` API pub fn target_file_size_multiplier(self, val: i32) -> Self { unsafe { ll::rocks_cfoptions_set_target_file_size_multiplier(self.raw, val); } self } /// If true, RocksDB will pick target size of each level dynamically. /// We will pick a base level b >= 1. L0 will be directly merged into level b, /// instead of always into level 1. Level 1 to b-1 need to be empty. /// We try to pick b and its target size so that /// /// 1. target size is in the range of /// (max_bytes_for_level_base / max_bytes_for_level_multiplier, /// max_bytes_for_level_base] /// 2. target size of the last level (level num_levels-1) equals to extra size /// of the level. /// /// At the same time max_bytes_for_level_multiplier and /// max_bytes_for_level_multiplier_additional are still satisfied. /// /// With this option on, from an empty DB, we make last level the base level, /// which means merging L0 data into the last level, until it exceeds /// max_bytes_for_level_base. And then we make the second last level to be /// base level, to start to merge L0 data to second last level, with its /// target size to be 1/max_bytes_for_level_multiplier of the last level's /// extra size. After the data accumulates more so that we need to move the /// base level to the third last one, and so on. /// /// For example, assume max_bytes_for_level_multiplier=10, num_levels=6, /// and max_bytes_for_level_base=10MB. /// /// Target sizes of level 1 to 5 starts with: /// /// > `[- - - - 10MB]` /// /// with base level is level. Target sizes of level 1 to 4 are not applicable /// because they will not be used. /// /// Until the size of Level 5 grows to more than 10MB, say 11MB, we make /// base target to level 4 and now the targets looks like: /// /// > `[- - - 1.1MB 11MB]` /// /// While data are accumulated, size targets are tuned based on actual data /// of level 5. When level 5 has 50MB of data, the target is like: /// /// > `[- - - 5MB 50MB]` /// /// Until level 5's actual size is more than 100MB, say 101MB. Now if we keep /// level 4 to be the base level, its target size needs to be 10.1MB, which /// doesn't satisfy the target size range. So now we make level 3 the target /// size and the target sizes of the levels look like: /// /// > `[- - 1.01MB 10.1MB 101MB]` /// /// In the same way, while level 5 further grows, all levels' targets grow, /// like /// /// > `[- - 5MB 50MB 500MB]` /// /// Until level 5 exceeds 1000MB and becomes 1001MB, we make level 2 the /// base level and make levels' target sizes like this: /// /// > `[- 1.001MB 10.01MB 100.1MB 1001MB]` /// /// and go on... /// /// By doing it, we give max_bytes_for_level_multiplier a priority against /// max_bytes_for_level_base, for a more predictable LSM tree shape. It is /// useful to limit worse case space amplification. /// /// `max_bytes_for_level_multiplier_additional` is ignored with this flag on. /// /// Turning this feature on or off for an existing DB can cause unexpected /// LSM tree structure so it's not recommended. /// /// NOTE: this option is experimental /// /// Default: false pub fn level_compaction_dynamic_level_bytes(self, val: bool) -> Self { unsafe { // wtf this name is a bool? ll::rocks_cfoptions_set_level_compaction_dynamic_level_bytes(self.raw, val as u8); } self } /// Default: 10. /// /// Dynamically changeable through `SetOptions()` API pub fn max_bytes_for_level_multiplier(self, val: f64) -> Self { unsafe { ll::rocks_cfoptions_set_max_bytes_for_level_multiplier(self.raw, val); } self } /// Different max-size multipliers for different levels. /// /// These are multiplied by max_bytes_for_level_multiplier to arrive /// at the max-size of each level. /// /// Default: 1 /// /// Dynamically changeable through `SetOptions()` API pub fn max_bytes_for_level_multiplier_additional(self, val: &[i32]) -> Self { let cval = val.iter().map(|&v| v as c_int).collect::<Vec<_>>(); let num_levels = val.len(); unsafe { ll::rocks_cfoptions_set_max_bytes_for_level_multiplier_additional(self.raw, cval.as_ptr(), num_levels); } self } /// We try to limit number of bytes in one compaction to be lower than this /// threshold. But it's not guaranteed. /// Value 0 will be sanitized. /// /// Default: result.target_file_size_base * 25 pub fn max_compaction_bytes(self, val: u64) -> Self { unsafe { ll::rocks_cfoptions_set_max_compaction_bytes(self.raw, val); } self } /// All writes will be slowed down to at least delayed_write_rate if estimated /// bytes needed to be compaction exceed this threshold. /// /// Default: 64GB pub fn soft_pending_compaction_bytes_limit(self, val: u64) -> Self { unsafe { ll::rocks_cfoptions_set_soft_pending_compaction_bytes_limit(self.raw, val); } self } /// All writes are stopped if estimated bytes needed to be compaction exceed /// this threshold. /// /// Default: 256GB pub fn hard_pending_compaction_bytes_limit(self, val: u64) -> Self { unsafe { ll::rocks_cfoptions_set_hard_pending_compaction_bytes_limit(self.raw, val); } self } /// The compaction style. /// /// Default: CompactionStyleLevel pub fn compaction_style(self, val: CompactionStyle) -> Self { unsafe { ll::rocks_cfoptions_set_compaction_style(self.raw, mem::transmute(val)); } self } /// If level compaction_style = kCompactionStyleLevel, for each level, /// which files are prioritized to be picked to compact. /// /// Default: ByCompensatedSize pub fn compaction_pri(self, val: CompactionPri) -> Self { unsafe { ll::rocks_cfoptions_set_compaction_pri(self.raw, mem::transmute(val)); } self } /// The options needed to support Universal Style compactions pub fn compaction_options_universal(self, opt: CompactionOptionsUniversal) -> Self { unsafe { ll::rocks_cfoptions_set_universal_compaction_options(self.raw, opt.raw()); } self } /// The options for FIFO compaction style pub fn compaction_options_fifo(self, val: CompactionOptionsFIFO) -> Self { unsafe { ll::rocks_cfoptions_set_fifo_compaction_options(self.raw, val.raw()); } self } /// An iteration->Next() sequentially skips over keys with the same /// user-key unless this option is set. This number specifies the number /// of keys (with the same userkey) that will be sequentially /// skipped before a reseek is issued. /// /// Default: 8 /// /// Dynamically changeable through `SetOptions()` API pub fn max_sequential_skip_in_iterations(self, val: u64) -> Self { unsafe { ll::rocks_cfoptions_set_max_sequential_skip_in_iterations(self.raw, val); } self } /// This creates MemTableReps that are backed by an std::vector. On iteration, /// the vector is sorted. This is useful for workloads where iteration is very /// rare and writes are generally not issued after reads begin. /// /// # Arguments /// /// - count: Passed to the constructor of the underlying std::vector of each VectorRep. On /// initialization, the underlying array will be at least count bytes reserved for usage. /// /// Default: 0 pub fn memtable_factory_vector_rep(self, count: usize) -> Self { unsafe { ll::rocks_cfoptions_set_memtable_vector_rep(self.raw, count); } self } /// This class contains a fixed array of buckets, each /// pointing to a skiplist (null if the bucket is empty). /// /// # Arguments /// /// - bucket_count: number of fixed array buckets /// /// Default: 1000000 /// - skiplist_height: the max height of the skiplist /// /// Default: 4 /// - skiplist_branching_factor: probabilistic size ratio between adjacent link lists in the /// skiplist /// /// Default: 4 pub fn memtable_factory_hash_skip_list_rep( self, bucket_count: usize, skiplist_height: i32, skiplist_branching_factor: i32, ) -> Self { unsafe { ll::rocks_cfoptions_set_hash_skip_list_rep( self.raw, bucket_count, skiplist_height, skiplist_branching_factor, ); } self } /// The factory is to create memtables based on a hash table: /// it contains a fixed array of buckets, each pointing to either a linked list /// or a skip list if number of entries inside the bucket exceeds /// threshold_use_skiplist. /// /// # Arguments /// /// - bucket_count: number of fixed array buckets /// /// Default: 50000 /// - huge_page_tlb_size: if <=0, allocate the hash table bytes from malloc. Otherwise from huge /// page TLB. The user needs to reserve huge pages for it to be allocated, like: /// /// > sysctl -w vm.nr_hugepages=20 /// /// See linux doc Documentation/vm/hugetlbpage.txt /// /// Default: 0 /// - bucket_entries_logging_threshold: if number of entries in one bucket exceeds this number, /// log about it. /// /// Default: 4096 /// - if_log_bucket_dist_when_flash: if true, log distribution of number of entries when /// flushing. /// /// Default: true /// - threshold_use_skiplist: a bucket switches to skip list if number of entries exceed this /// parameter. /// /// Default: 256 pub fn memtable_factory_hash_link_list_rep(self, bucket_count: usize) -> Self { unsafe { ll::rocks_cfoptions_set_hash_link_list_rep(self.raw, bucket_count); } self } /// Block-based table related options are moved to BlockBasedTableOptions. /// Related options that were originally here but now moved include: /// /// * no_block_cache /// * block_cache /// * block_cache_compressed /// * block_size /// * block_size_deviation /// * block_restart_interval /// * filter_policy /// * whole_key_filtering /// /// If you'd like to customize some of these options, you will need to /// use NewBlockBasedTableFactory() to construct a new table factory. /// /// This option allows user to collect their own interested statistics of /// the tables. /// /// Default: empty vector -- no user-defined statistics collection will be /// performed. /// /// Rust: add one at a time pub fn table_properties_collector_factory(self, val: Box<dyn TablePropertiesCollectorFactory>) -> Self { unsafe { let raw_ptr = Box::into_raw(Box::new(val)); ll::rocks_cfoptions_add_table_properties_collector_factories_by_trait(self.raw, raw_ptr as *mut _); } self } /// Maximum number of successive merge operations on a key in the memtable. /// /// When a merge operation is added to the memtable and the maximum number of /// successive merges is reached, the value of the key will be calculated and /// inserted into the memtable instead of the merge operation. This will /// ensure that there are never more than max_successive_merges merge /// operations in the memtable. /// /// Default: 0 (disabled) /// /// Dynamically changeable through `SetOptions()` API pub fn max_successive_merges(self, val: usize) -> Self { unsafe { ll::rocks_cfoptions_set_max_successive_merges(self.raw, val); } self } /// This flag specifies that the implementation should optimize the filters /// mainly for cases where keys are found rather than also optimize for keys /// missed. This would be used in cases where the application knows that /// there are very few misses or the performance in the case of misses is not /// important. /// /// For now, this flag allows us to not store filters for the last level i.e /// the largest level which contains data of the LSM store. For keys which /// are hits, the filters in this level are not useful because we will search /// for the data anyway. NOTE: the filters in other levels are still useful /// even for key hit because they tell us whether to look in that level or go /// to the higher level. /// /// Default: false pub fn optimize_filters_for_hits(self, val: bool) -> Self { unsafe { ll::rocks_cfoptions_set_optimize_filters_for_hits(self.raw, val as u8); } self } /// After writing every SST file, reopen it and read all the keys. /// /// Default: false pub fn paranoid_file_checks(self, val: bool) -> Self { unsafe { ll::rocks_cfoptions_set_paranoid_file_checks(self.raw, val as u8); } self } /// In debug mode, RocksDB run consistency checks on the LSM everytime the LSM /// change (Flush, Compaction, AddFile). These checks are disabled in release /// mode, use this option to enable them in release mode as well. /// /// Default: false pub fn force_consistency_checks(self, val: bool) -> Self { unsafe { ll::rocks_cfoptions_set_force_consistency_checks(self.raw, val as u8); } self } /// Measure IO stats in compactions and flushes, if true. /// /// Default: false pub fn report_bg_io_stats(self, val: bool) -> Self { unsafe { ll::rocks_cfoptions_set_report_bg_io_stats(self.raw, val as u8); } self } pub fn dump(&self, log: &mut Logger) { unimplemented!() } } /// Specify the file access pattern once a compaction is started. /// It will be applied to all input files of a compaction. /// /// Default: NORMAL #[repr(C)] pub enum AccessHint { None, Normal, Sequential, WillNeed, } /// Options for the DB pub struct DBOptions { raw: *mut ll::rocks_dboptions_t, } impl Default for DBOptions { fn default() -> Self { DBOptions { raw: unsafe { ll::rocks_dboptions_create() }, } } } impl Drop for DBOptions { fn drop(&mut self) { unsafe { ll::rocks_dboptions_destroy(self.raw); } } } impl ToRaw<ll::rocks_dboptions_t> for DBOptions { fn raw(&self) -> *mut ll::rocks_dboptions_t { self.raw } } impl fmt::Debug for DBOptions { fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result { write!(f, "DBOptions {{ ")?; unsafe { let cxx_string = ll::rocks_get_string_from_dboptions(self.raw); let len = ll::cxx_string_size(cxx_string); let base = ll::cxx_string_data(cxx_string); if !cxx_string.is_null() { let str_rep = str::from_utf8_unchecked(slice::from_raw_parts(base as *const u8, len)); f.write_str(str_rep)?; ll::cxx_string_destroy(cxx_string); } else { write!(f, "error while converting to String")?; } } write!(f, "}}") } } impl DBOptions { unsafe fn from_ll(raw: *mut ll::rocks_dboptions_t) -> DBOptions { DBOptions { raw: raw } } pub fn from_options(opt: &Options) -> DBOptions { DBOptions { raw: unsafe { ll::rocks_dboptions_create_from_options(opt.raw()) }, } } /// By default, RocksDB uses only one background thread for flush and /// compaction. Calling this function will set it up such that total of /// `total_threads` is used. Good value for `total_threads` is the number of /// cores. You almost definitely want to call this function if your system is /// bottlenecked by RocksDB. /// /// Default: 16 pub fn increase_parallelism(self, total_threads: i32) -> Self { unsafe { ll::rocks_dboptions_increase_parallelism(self.raw, total_threads); } self } /// If true, the database will be created if it is missing. /// /// Default: false pub fn create_if_missing(self, val: bool) -> Self { unsafe { ll::rocks_dboptions_set_create_if_missing(self.raw, val as u8); } self } /// If true, missing column families will be automatically created. /// /// Default: false pub fn create_missing_column_families(self, val: bool) -> Self { unsafe { ll::rocks_dboptions_set_create_missing_column_families(self.raw, val as u8); } self } /// If true, an error is raised if the database already exists. /// /// Default: false pub fn error_if_exists(self, val: bool) -> Self { unsafe { ll::rocks_dboptions_set_error_if_exists(self.raw, val as u8); } self } /// If true, RocksDB will aggressively check consistency of the data. /// Also, if any of the writes to the database fails (Put, Delete, Merge, /// Write), the database will switch to read-only mode and fail all other /// Write operations. /// /// In most cases you want this to be set to true. /// /// Default: true pub fn paranoid_checks(self, val: bool) -> Self { unsafe { ll::rocks_dboptions_set_paranoid_checks(self.raw, val as u8); } self } /// Use the specified object to interact with the environment, /// e.g. to read/write files, schedule background work, etc. /// /// Default: Env::Default() pub fn env(self, env: &'static Env) -> Self { unsafe { ll::rocks_dboptions_set_env(self.raw, env.raw()); } self } /// Use to control write rate of flush and compaction. Flush has higher /// priority than compaction. Rate limiting is disabled if nullptr. /// If rate limiter is enabled, bytes_per_sync is set to 1MB by default. /// /// Default: nullptr pub fn rate_limiter(self, val: Option<RateLimiter>) -> Self { unsafe { if let Some(limiter) = val { ll::rocks_dboptions_set_ratelimiter(self.raw, limiter.raw()); } else { ll::rocks_dboptions_set_ratelimiter(self.raw, ptr::null_mut()); } } self } /// Use to track SST files and control their file deletion rate. /// /// Features: /// /// - Throttle the deletion rate of the SST files. /// - Keep track the total size of all SST files. /// - Set a maximum allowed space limit for SST files that when reached the DB wont do any /// further flushes or compactions and will set the background error. /// - Can be shared between multiple dbs. /// /// Limitations: /// /// - Only track and throttle deletes of SST files in first db_path (db_name if db_paths is /// empty). /// /// Default: nullptr pub fn sst_file_manager(self, val: Option<SstFileManager>) -> Self { // unsafe { // ll::rocks_dboptions_set_sst_file_manager(self.raw, val); // } // self unimplemented!() } /// Any internal progress/error information generated by the db will /// be written to info_log if it is non-nullptr, or to a file stored /// in the same directory as the DB contents if info_log is nullptr. /// /// Default: nullptr pub fn info_log(self, val: Option<Logger>) -> Self { unsafe { if let Some(logger) = val { ll::rocks_dboptions_set_info_log(self.raw, logger.raw()); } else { ll::rocks_dboptions_set_info_log(self.raw, ptr::null_mut()); } } self } pub fn info_log_level(self, val: InfoLogLevel) -> Self { unsafe { ll::rocks_dboptions_set_info_log_level(self.raw, mem::transmute(val)); } self } /// Number of open files that can be used by the DB. You may need to /// increase this if your database has a large working set. Value -1 means /// files opened are always kept open. You can estimate number of files based /// on target_file_size_base and target_file_size_multiplier for level-based /// compaction. For universal-style compaction, you can usually set it to -1. /// /// Default: -1 pub fn max_open_files(self, val: i32) -> Self { unsafe { ll::rocks_dboptions_set_max_open_files(self.raw, val); } self } /// If max_open_files is -1, DB will open all files on DB::Open(). You can /// use this option to increase the number of threads used to open the files. /// /// Default: 16 pub fn max_file_opening_threads(self, val: i32) -> Self { unsafe { ll::rocks_dboptions_set_max_file_opening_threads(self.raw, val); } self } /// Once write-ahead logs exceed this size, we will start forcing the flush of /// column families whose memtables are backed by the oldest live WAL file /// (i.e. the ones that are causing all the space amplification). If set to 0 /// (default), we will dynamically choose the WAL size limit to be /// [sum of all write_buffer_size * max_write_buffer_number] * 4 /// /// Default: 0 pub fn max_total_wal_size(self, val: u64) -> Self { unsafe { ll::rocks_dboptions_set_max_total_wal_size(self.raw, val); } self } /// If non-null, then we should collect metrics about database operations pub fn statistics(self, val: Option<Statistics>) -> Self { match val { Some(stat) => unsafe { ll::rocks_dboptions_set_statistics(self.raw, stat.raw()) }, None => unsafe { ll::rocks_dboptions_set_statistics(self.raw, ptr::null_mut()) }, } self } /// If true, then every store to stable storage will issue a fsync. /// If false, then every store to stable storage will issue a fdatasync. /// This parameter should be set to true while storing data to /// filesystem like ext3 that can lose files after a reboot. /// /// Default: false /// /// Note: on many platforms fdatasync is defined as fsync, so this parameter /// would make no difference. Refer to fdatasync definition in this code base. pub fn use_fsync(self, val: bool) -> Self { unsafe { ll::rocks_dboptions_set_use_fsync(self.raw, val as u8); } self } /// A list of paths where SST files can be put into, with its target size. /// Newer data is placed into paths specified earlier in the vector while /// older data gradually moves to paths specified later in the vector. /// /// For example, you have a flash device with 10GB allocated for the DB, /// as well as a hard drive of 2TB, you should config it to be: /// /// > [{"/flash_path", 10GB}, {"/hard_drive", 2TB}] /// /// The system will try to guarantee data under each path is close to but /// not larger than the target size. But current and future file sizes used /// by determining where to place a file are based on best-effort estimation, /// which means there is a chance that the actual size under the directory /// is slightly more than target size under some workloads. User should give /// some buffer room for those cases. /// /// If none of the paths has sufficient room to place a file, the file will /// be placed to the last path anyway, despite to the target size. /// /// Placing newer data to earlier paths is also best-efforts. User should /// expect user files to be placed in higher levels in some extreme cases. /// /// If left empty, only one path will be used, which is db_name passed when /// opening the DB. /// /// Default: empty pub fn db_paths<P: Into<DbPath>, T: IntoIterator<Item = P>>(self, val: T) -> Self { let paths = val.into_iter().map(|p| p.into()).collect::<Vec<_>>(); // must hold PathBuf.to_str() let path_strs = paths .iter() .map(|s| (s.path.to_str().unwrap(), s.target_size)) .collect::<Vec<_>>(); let num_paths = paths.len(); let mut cpaths = Vec::with_capacity(num_paths); let mut cpath_lens = Vec::with_capacity(num_paths); let mut sizes = Vec::with_capacity(num_paths); for path in path_strs { cpaths.push(path.0.as_ptr() as _); cpath_lens.push(path.0.len()); sizes.push(path.1); } unsafe { ll::rocks_dboptions_set_db_paths( self.raw, cpaths.as_ptr(), cpath_lens.as_ptr(), sizes.as_ptr(), num_paths as c_int, ); } self } /// This specifies the info LOG dir. /// /// If it is empty, the log files will be in the same dir as data. /// /// If it is non empty, the log files will be in the specified dir, /// and the db data dir's absolute path will be used as the log file /// name's prefix. pub fn db_log_dir<P: AsRef<Path>>(self, path: P) -> Self { unsafe { let path_str = path.as_ref().to_str().unwrap(); ll::rocks_dboptions_set_db_log_dir(self.raw, path_str.as_ptr() as _, path_str.len()); } self } /// This specifies the absolute dir path for write-ahead logs (WAL). /// /// If it is empty, the log files will be in the same dir as data, /// dbname is used as the data dir by default /// /// If it is non empty, the log files will be in kept the specified dir. /// /// When destroying the db, /// all log files in wal_dir and the dir itself is deleted pub fn wal_dir<P: AsRef<Path>>(self, path: P) -> Self { unsafe { let path_str = path.as_ref().to_str().unwrap(); ll::rocks_dboptions_set_wal_dir(self.raw, path_str.as_ptr() as _, path_str.len()); } self } /// The periodicity when obsolete files get deleted. The default /// value is 6 hours. The files that get out of scope by compaction /// process will still get automatically delete on every compaction, /// regardless of this setting pub fn delete_obsolete_files_period_micros(self, val: u64) -> Self { unsafe { ll::rocks_dboptions_set_delete_obsolete_files_period_micros(self.raw, val); } self } /// Maximum number of concurrent background jobs (compactions and flushes). /// /// Default: 2 pub fn max_background_jobs(self, val: i32) -> Self { unsafe { ll::rocks_dboptions_set_max_background_jobs(self.raw, val); } self } /// This value represents the maximum number of threads that will /// concurrently perform a compaction job by breaking it into multiple, /// smaller ones that are run simultaneously. /// /// Default: 1 (i.e. no subcompactions) pub fn max_subcompactions(self, val: u32) -> Self { unsafe { ll::rocks_dboptions_set_max_subcompactions(self.raw, val); } self } /// Specify the maximal size of the info log file. If the log file /// is larger than `max_log_file_size`, a new info log file will /// be created. /// /// If max_log_file_size == 0, all logs will be written to one /// log file. pub fn max_log_file_size(self, val: usize) -> Self { unsafe { ll::rocks_dboptions_set_max_log_file_size(self.raw, val); } self } /// Time for the info log file to roll (in seconds). /// If specified with non-zero value, log file will be rolled /// if it has been active longer than `log_file_time_to_roll`. /// /// Default: 0 (disabled) pub fn log_file_time_to_roll(self, val: usize) -> Self { unsafe { ll::rocks_dboptions_set_log_file_time_to_roll(self.raw, val); } self } /// Maximal info log files to be kept. /// /// Default: 1000 pub fn keep_log_file_num(self, val: usize) -> Self { unsafe { ll::rocks_dboptions_set_keep_log_file_num(self.raw, val); } self } /// Recycle log files. /// /// If non-zero, we will reuse previously written log files for new /// logs, overwriting the old data. The value indicates how many /// such files we will keep around at any point in time for later /// use. This is more efficient because the blocks are already /// allocated and fdatasync does not need to update the inode after /// each write. /// /// Default: 0 pub fn recycle_log_file_num(self, val: usize) -> Self { unsafe { ll::rocks_dboptions_set_recycle_log_file_num(self.raw, val); } self } /// manifest file is rolled over on reaching this limit. /// /// The older manifest file be deleted. /// /// The default value is MAX_INT so that roll-over does not take place. pub fn max_manifest_file_size(self, val: u64) -> Self { unsafe { ll::rocks_dboptions_set_max_manifest_file_size(self.raw, val); } self } /// Number of shards used for table cache. pub fn table_cache_numshardbits(self, val: i32) -> Self { unsafe { ll::rocks_dboptions_set_table_cache_numshardbits(self.raw, val); } self } /// The following two fields affect how archived logs will be deleted. /// /// 1. If both set to 0, logs will be deleted asap and will not get into /// the archive. /// 2. If WAL_ttl_seconds is 0 and WAL_size_limit_MB is not 0, /// WAL files will be checked every 10 min and if total size is greater /// then WAL_size_limit_MB, they will be deleted starting with the /// earliest until size_limit is met. All empty files will be deleted. /// 3. If WAL_ttl_seconds is not 0 and WAL_size_limit_MB is 0, then /// WAL files will be checked every WAL_ttl_secondsi / 2 and those that /// are older than WAL_ttl_seconds will be deleted. /// 4. If both are not 0, WAL files will be checked every 10 min and both /// checks will be performed with ttl being first. pub fn wal_ttl_seconds(self, val: u64) -> Self { unsafe { ll::rocks_dboptions_set_wal_ttl_seconds(self.raw, val); } self } pub fn wal_size_limit_mb(self, val: u64) -> Self { unsafe { ll::rocks_dboptions_set_wal_size_limit_mb(self.raw, val); } self } /// Number of bytes to preallocate (via fallocate) the manifest /// files. Default is 4mb, which is reasonable to reduce random IO /// as well as prevent overallocation for mounts that preallocate /// large amounts of data (such as xfs's allocsize option). pub fn manifest_preallocation_size(self, val: usize) -> Self { unsafe { ll::rocks_dboptions_set_manifest_preallocation_size(self.raw, val); } self } /// Allow the OS to mmap file for reading sst tables. Default: false pub fn allow_mmap_reads(self, val: bool) -> Self { unsafe { ll::rocks_dboptions_set_allow_mmap_reads(self.raw, val as u8); } self } /// Allow the OS to mmap file for writing. /// /// DB::SyncWAL() only works if this is set to false. /// /// Default: false pub fn allow_mmap_writes(self, val: bool) -> Self { unsafe { ll::rocks_dboptions_set_allow_mmap_writes(self.raw, val as u8); } self } /// Enable direct I/O mode for read/write /// they may or may not improve performance depending on the use case /// /// Files will be opened in "direct I/O" mode /// which means that data r/w from the disk will not be cached or /// bufferized. The hardware buffer of the devices may however still /// be used. Memory mapped files are not impacted by these parameters. /// /// Use O_DIRECT for user reads /// /// Default: false /// /// Not supported in ROCKSDB_LITE mode! pub fn use_direct_reads(self, val: bool) -> Self { unsafe { ll::rocks_dboptions_set_use_direct_reads(self.raw, val as u8); } self } /// Use O_DIRECT for both reads and writes in background flush and compactions /// When true, we also force new_table_reader_for_compaction_inputs to true. /// /// Default: false pub fn use_direct_io_for_flush_and_compaction(self, val: bool) -> Self { unsafe { ll::rocks_dboptions_set_use_direct_io_for_flush_and_compaction(self.raw, val as u8); } self } /// If false, fallocate() calls are bypassed pub fn allow_fallocate(self, val: bool) -> Self { unsafe { ll::rocks_dboptions_set_allow_fallocate(self.raw, val as u8); } self } /// Disable child process inherit open files. /// /// Default: true pub fn is_fd_close_on_exec(self, val: bool) -> Self { unsafe { ll::rocks_dboptions_set_is_fd_close_on_exec(self.raw, val as u8); } self } /// if not zero, dump rocksdb.stats to LOG every stats_dump_period_sec /// /// Default: 600 (10 min) pub fn stats_dump_period_sec(self, val: u32) -> Self { unsafe { ll::rocks_dboptions_set_stats_dump_period_sec(self.raw, val); } self } /// If set true, will hint the underlying file system that the file /// access pattern is random, when a sst file is opened. /// /// Default: true pub fn advise_random_on_open(self, val: bool) -> Self { unsafe { ll::rocks_dboptions_set_advise_random_on_open(self.raw, val as u8); } self } /// Amount of data to build up in memtables across all column /// families before writing to disk. /// /// This is distinct from write_buffer_size, which enforces a limit /// for a single memtable. /// /// This feature is disabled by default. Specify a non-zero value /// to enable it. /// /// Default: 0 (disabled) pub fn db_write_buffer_size(self, val: usize) -> Self { unsafe { ll::rocks_dboptions_set_db_write_buffer_size(self.raw, val); } self } /// The memory usage of memtable will report to this object. The same object /// can be passed into multiple DBs and it will track the sum of size of all /// the DBs. If the total size of all live memtables of all the DBs exceeds /// a limit, a flush will be triggered in the next DB to which the next write /// is issued. /// /// If the object is only passed to on DB, the behavior is the same as /// db_write_buffer_size. When write_buffer_manager is set, the value set will /// override db_write_buffer_size. /// /// This feature is disabled by default. Specify a non-zero value /// to enable it. /// /// Default: null pub fn write_buffer_manager(self, val: &WriteBufferManager) -> Self { unsafe { ll::rocks_dboptions_set_write_buffer_manager(self.raw, val.raw()); } self } /// Specify the file access pattern once a compaction is started. /// It will be applied to all input files of a compaction. /// /// Default: NORMAL pub fn access_hint_on_compaction_start(self, val: AccessHint) -> Self { unsafe { ll::rocks_dboptions_set_access_hint_on_compaction_start(self.raw, mem::transmute(val)); } self } /// If true, always create a new file descriptor and new table reader /// for compaction inputs. Turn this parameter on may introduce extra /// memory usage in the table reader, if it allocates extra memory /// for indexes. This will allow file descriptor prefetch options /// to be set for compaction input files and not to impact file /// descriptors for the same file used by user queries. /// /// Suggest to enable `BlockBasedTableOptions.cache_index_and_filter_blocks` /// for this mode if using block-based table. /// /// Default: false pub fn new_table_reader_for_compaction_inputs(self, val: bool) -> Self { unsafe { ll::rocks_dboptions_set_new_table_reader_for_compaction_inputs(self.raw, val as u8); } self } /// If non-zero, we perform bigger reads when doing compaction. If you're /// running RocksDB on spinning disks, you should set this to at least 2MB. /// That way RocksDB's compaction is doing sequential instead of random reads. /// /// When non-zero, we also force new_table_reader_for_compaction_inputs to /// true. /// /// Default: 0 pub fn compaction_readahead_size(self, val: usize) -> Self { unsafe { ll::rocks_dboptions_set_compaction_readahead_size(self.raw, val); } self } /// This is a maximum buffer size that is used by WinMmapReadableFile in /// unbuffered disk I/O mode. We need to maintain an aligned buffer for /// reads. We allow the buffer to grow until the specified value and then /// for bigger requests allocate one shot buffers. In unbuffered mode we /// always bypass read-ahead buffer at ReadaheadRandomAccessFile /// When read-ahead is required we then make use of compaction_readahead_size /// value and always try to read ahead. With read-ahead we always /// pre-allocate buffer to the size instead of growing it up to a limit. /// /// This option is currently honored only on Windows /// /// Default: 1 Mb /// /// Special value: 0 - means do not maintain per instance buffer. Allocate /// per request buffer and avoid locking. pub fn random_access_max_buffer_size(self, val: usize) -> Self { unsafe { ll::rocks_dboptions_set_random_access_max_buffer_size(self.raw, val); } self } /// This is the maximum buffer size that is used by WritableFileWriter. /// On Windows, we need to maintain an aligned buffer for writes. /// We allow the buffer to grow until it's size hits the limit in buffered /// IO and fix the buffer size when using direct IO to ensure alignment of /// write requests if the logical sector size is unusual /// /// Default: 1024 * 1024 (1 MB) pub fn writable_file_max_buffer_size(self, val: usize) -> Self { unsafe { ll::rocks_dboptions_set_writable_file_max_buffer_size(self.raw, val); } self } /// Use adaptive mutex, which spins in the user space before resorting /// to kernel. This could reduce context switch when the mutex is not /// heavily contended. However, if the mutex is hot, we could end up /// wasting spin time. /// /// Default: false pub fn use_adaptive_mutex(self, val: bool) -> Self { unsafe { ll::rocks_dboptions_set_use_adaptive_mutex(self.raw, val as u8); } self } /// Allows OS to incrementally sync files to disk while they are being /// written, asynchronously, in the background. This operation can be used /// to smooth out write I/Os over time. Users shouldn't rely on it for /// persistency guarantee. /// Issue one request for every bytes_per_sync written. 0 turns it off. /// Default: 0 /// /// You may consider using rate_limiter to regulate write rate to device. /// When rate limiter is enabled, it automatically enables bytes_per_sync /// to 1MB. /// /// This option applies to table files pub fn bytes_per_sync(self, val: u64) -> Self { unsafe { ll::rocks_dboptions_set_bytes_per_sync(self.raw, val); } self } /// Same as bytes_per_sync, but applies to WAL files /// /// Default: 0, turned off pub fn wal_bytes_per_sync(self, val: u64) -> Self { unsafe { ll::rocks_dboptions_set_wal_bytes_per_sync(self.raw, val); } self } /// A vector of EventListeners which call-back functions will be called /// when specific RocksDB event happens. pub fn add_listener<T: EventListener>(self, val: T) -> Self { unsafe { ll::rocks_dboptions_add_listener( self.raw, Box::into_raw(Box::new(Box::new(val) as Box<dyn EventListener>)) as *mut _, ); } self } /// If true, then the status of the threads involved in this DB will /// be tracked and available via GetThreadList() API. /// /// Default: false pub fn enable_thread_tracking(self, val: bool) -> Self { unsafe { ll::rocks_dboptions_set_enable_thread_tracking(self.raw, val as u8); } self } /// The limited write rate to DB if soft_pending_compaction_bytes_limit or /// level0_slowdown_writes_trigger is triggered, or we are writing to the /// last mem table allowed and we allow more than 3 mem tables. It is /// calculated using size of user write requests before compression. /// RocksDB may decide to slow down more if the compaction still /// gets behind further. /// /// Unit: byte per second. /// /// Default: 16MB/s pub fn delayed_write_rate(self, val: u64) -> Self { unsafe { ll::rocks_dboptions_set_delayed_write_rate(self.raw, val); } self } /// If true, allow multi-writers to update mem tables in parallel. /// Only some memtable_factory-s support concurrent writes; currently it /// is implemented only for SkipListFactory. Concurrent memtable writes /// are not compatible with inplace_update_support or filter_deletes. /// It is strongly recommended to set enable_write_thread_adaptive_yield /// if you are going to use this feature. /// /// Default: true pub fn allow_concurrent_memtable_write(self, val: bool) -> Self { unsafe { ll::rocks_dboptions_set_allow_concurrent_memtable_write(self.raw, val as u8); } self } /// If true, threads synchronizing with the write batch group leader will /// wait for up to write_thread_max_yield_usec before blocking on a mutex. /// This can substantially improve throughput for concurrent workloads, /// regardless of whether allow_concurrent_memtable_write is enabled. /// /// Default: true pub fn enable_write_thread_adaptive_yield(self, val: bool) -> Self { unsafe { ll::rocks_dboptions_set_enable_write_thread_adaptive_yield(self.raw, val as u8); } self } /// The maximum number of microseconds that a write operation will use /// a yielding spin loop to coordinate with other write threads before /// blocking on a mutex. (Assuming write_thread_slow_yield_usec is /// set properly) increasing this value is likely to increase RocksDB /// throughput at the expense of increased CPU usage. /// /// Default: 100 pub fn write_thread_max_yield_usec(self, val: u64) -> Self { unsafe { ll::rocks_dboptions_set_write_thread_max_yield_usec(self.raw, val); } self } /// The latency in microseconds after which a std::this_thread::yield /// call (sched_yield on Linux) is considered to be a signal that /// other processes or threads would like to use the current core. /// Increasing this makes writer threads more likely to take CPU /// by spinning, which will show up as an increase in the number of /// involuntary context switches. /// /// Default: 3 pub fn write_thread_slow_yield_usec(self, val: u64) -> Self { unsafe { ll::rocks_dboptions_set_write_thread_slow_yield_usec(self.raw, val); } self } /// If true, then DB::Open() will not update the statistics used to optimize /// compaction decision by loading table properties from many files. /// Turning off this feature will improve DBOpen time especially in /// disk environment. /// /// Default: false pub fn skip_stats_update_on_db_open(self, val: bool) -> Self { unsafe { ll::rocks_dboptions_set_skip_stats_update_on_db_open(self.raw, val as u8); } self } /// Recovery mode to control the consistency while replaying WAL /// /// Default: PointInTimeRecovery pub fn wal_recovery_mode(self, val: WALRecoveryMode) -> Self { unsafe { ll::rocks_dboptions_set_wal_recovery_mode(self.raw, mem::transmute(val)); } self } /// if set to false then recovery will fail when a prepared /// transaction is encountered in the WAL pub fn allow_2pc(self, val: bool) -> Self { unsafe { ll::rocks_dboptions_set_allow_2pc(self.raw, val as u8); } self } /// A global cache for table-level rows. /// /// Default: nullptr (disabled) /// /// Not supported in ROCKSDB_LITE mode! /// /// Rust: will move in and use share_ptr pub fn row_cache(self, val: Option<Cache>) -> Self { unsafe { if let Some(cache) = val { ll::rocks_dboptions_set_row_cache(self.raw, cache.raw()); } else { ll::rocks_dboptions_set_row_cache(self.raw, ptr::null_mut()); } } self } // TODO // /// A filter object supplied to be invoked while processing write-ahead-logs // /// (WALs) during recovery. The filter provides a way to inspect log // /// records, ignoring a particular record or skipping replay. // /// The filter is invoked at startup and is invoked from a single-thread // /// currently. // WalFilter* wal_filter , /// If true, then DB::Open / CreateColumnFamily / DropColumnFamily /// / SetOptions will fail if options file is not detected or properly /// persisted. /// /// DEFAULT: false pub fn fail_if_options_file_error(self, val: bool) -> Self { unsafe { ll::rocks_dboptions_set_fail_if_options_file_error(self.raw, val as u8); } self } /// If true, then print malloc stats together with rocksdb.stats /// when printing to LOG. /// /// DEFAULT: false pub fn dump_malloc_stats(self, val: bool) -> Self { unsafe { ll::rocks_dboptions_set_dump_malloc_stats(self.raw, val as u8); } self } /// By default RocksDB replay WAL logs and flush them on DB open, which may /// create very small SST files. If this option is enabled, RocksDB will try /// to avoid (but not guarantee not to) flush during recovery. Also, existing /// WAL logs will be kept, so that if crash happened before flush, we still /// have logs to recover from. /// /// DEFAULT: false pub fn avoid_flush_during_recovery(self, val: bool) -> Self { unsafe { ll::rocks_dboptions_set_avoid_flush_during_recovery(self.raw, val as u8); } self } /// By default RocksDB will flush all memtables on DB close if there are /// unpersisted data (i.e. with WAL disabled) The flush can be skip to speedup /// DB close. Unpersisted data WILL BE LOST. /// /// DEFAULT: false /// /// Dynamically changeable through SetDBOptions() API. pub fn avoid_flush_during_shutdown(self, val: bool) -> Self { unsafe { ll::rocks_dboptions_set_avoid_flush_during_shutdown(self.raw, val as u8); } self } /// Set this option to true during creation of database if you want /// to be able to ingest behind (call IngestExternalFile() skipping keys /// that already exist, rather than overwriting matching keys). /// Setting this option to true will affect 2 things: /// /// 1. Disable some internal optimizations around SST file compression /// 2. Reserve bottom-most level for ingested files only. /// 3. Note that num_levels should be >= 3 if this option is turned on. /// /// DEFAULT: false /// /// Immutable. pub fn allow_ingest_behind(self, val: bool) -> Self { unsafe { ll::rocks_dboptions_set_allow_ingest_behind(self.raw, val as u8); } self } /// If true WAL is not flushed automatically after each write. Instead it /// relies on manual invocation of FlushWAL to write the WAL buffer to its /// file. /// /// Default: false pub fn manual_wal_flush(self, val: bool) -> Self { unsafe { ll::rocks_dboptions_set_manual_wal_flush(self.raw, val as u8); } self } } /// Options to control the behavior of a database (passed to `DB::Open`) /// /// ```no_run /// use rocks::options::Options; /// /// let _opt = Options::default() /// .map_db_options(|db| db.create_if_missing(true)) /// .map_cf_options(|cf| cf.disable_auto_compactions(true)); /// ``` pub struct Options { raw: *mut ll::rocks_options_t, } unsafe impl Sync for Options {} impl AsRef<Options> for Options { fn as_ref(&self) -> &Options { self } } impl Default for Options { fn default() -> Self { Options { raw: unsafe { ll::rocks_options_create() }, } } } impl Drop for Options { fn drop(&mut self) { unsafe { ll::rocks_options_destroy(self.raw); } } } impl ToRaw<ll::rocks_options_t> for Options { fn raw(&self) -> *mut ll::rocks_options_t { self.raw } } impl FromRaw<ll::rocks_options_t> for Options { unsafe fn from_ll(raw: *mut ll::rocks_options_t) -> Options { Options { raw: raw } } } impl Options { /// default `Options` with `create_if_missing = true` #[inline] pub fn default_instance() -> &'static Options { &*DEFAULT_OPTIONS } pub fn new(dbopt: Option<DBOptions>, cfopt: Option<ColumnFamilyOptions>) -> Options { let dbopt = dbopt.unwrap_or_default(); let cfopt = cfopt.unwrap_or_default(); Options { raw: unsafe { ll::rocks_options_create_from_db_cf_options(dbopt.raw(), cfopt.raw()) }, } } pub fn to_cf_options(&self) -> ColumnFamilyOptions { ColumnFamilyOptions::from_options(self) } pub fn to_db_options(&self) -> DBOptions { DBOptions::from_options(self) } // Some functions that make it easier to optimize RocksDB /// Configure DBOptions using builder style. pub fn map_db_options<F: FnOnce(DBOptions) -> DBOptions>(self, f: F) -> Self { let dbopt = unsafe { DBOptions::from_ll(ll::rocks_dboptions_create_from_options(self.raw)) }; let new_dbopt = f(dbopt); let old_cfopt = unsafe { ColumnFamilyOptions::from_ll(ll::rocks_cfoptions_create_from_options(self.raw)) }; unsafe { Options::from_ll(ll::rocks_options_create_from_db_cf_options( new_dbopt.raw(), old_cfopt.raw(), )) } } /// Configure ColumnFamilyOptions using builder style. pub fn map_cf_options<F: FnOnce(ColumnFamilyOptions) -> ColumnFamilyOptions>(self, f: F) -> Self { let cfopt = unsafe { ColumnFamilyOptions::from_ll(ll::rocks_cfoptions_create_from_options(self.raw)) }; let new_cfopt = f(cfopt); let old_dbopt = unsafe { DBOptions::from_ll(ll::rocks_dboptions_create_from_options(self.raw)) }; unsafe { Options::from_ll(ll::rocks_options_create_from_db_cf_options( old_dbopt.raw(), new_cfopt.raw(), )) } } /// Set appropriate parameters for bulk loading. /// /// All data will be in level 0 without any automatic compaction. /// It's recommended to manually call CompactRange(NULL, NULL) before reading /// from the database, because otherwise the read can be very slow. pub fn prepare_for_bulk_load(self) -> Self { unsafe { ll::rocks_options_prepare_for_bulk_load(self.raw) }; self } /// Use this if your DB is very small (like under 1GB) and you don't want to /// spend lots of memory for memtables. pub fn optimize_for_small_db(self) -> Self { unsafe { ll::rocks_options_optimize_for_small_db(self.raw) }; self } } /// An application can issue a read request (via Get/Iterators) and specify /// if that read should process data that ALREADY resides on a specified cache /// level. For example, if an application specifies kBlockCacheTier then the /// Get call will process data that is already processed in the memtable or /// the block cache. It will not page in data from the OS cache or data that /// resides in storage. #[repr(C)] #[derive(Debug, Copy, Clone, PartialEq, Eq, Hash)] pub enum ReadTier { /// data in memtable, block cache, OS cache or storage ReadAllTier = 0x0, /// data in memtable or block cache BlockCacheTier = 0x1, /// persisted data. When WAL is disabled, this option /// will skip data in memtable. /// Note that this ReadTier currently only supports /// Get and MultiGet and does not support iterators. PersistedTier = 0x2, } /// Options that control read operations. /// /// # Examples /// /// Construct `ReadOptions` using builder pattern. /// /// ```no_run /// use rocks::rocksdb::{ReadOptions, ReadTier}; /// /// let _ropt = ReadOptions::default() /// .fill_cache(true) /// .managed(true) /// .read_tier(ReadTier::PersistedTier); /// ``` pub struct ReadOptions<'a> { raw: *mut ll::rocks_readoptions_t, _marker: PhantomData<&'a ()>, } unsafe impl<'a> Sync for ReadOptions<'a> {} impl<'a> AsRef<ReadOptions<'a>> for ReadOptions<'a> { fn as_ref(&self) -> &ReadOptions<'a> { self } } impl<'a> Drop for ReadOptions<'a> { fn drop(&mut self) { unsafe { ll::rocks_readoptions_destroy(self.raw); } } } impl<'a> ToRaw<ll::rocks_readoptions_t> for ReadOptions<'a> { fn raw(&self) -> *mut ll::rocks_readoptions_t { self.raw } } impl<'a> Default for ReadOptions<'a> { fn default() -> Self { ReadOptions { raw: unsafe { ll::rocks_readoptions_create() }, _marker: PhantomData, } } } impl<'a> ReadOptions<'a> { /// default `ReadOptions` optimization #[inline] pub fn default_instance() -> &'static ReadOptions<'static> { &*DEFAULT_READ_OPTIONS } pub fn new<'b>(cksum: bool, cache: bool) -> ReadOptions<'b> { ReadOptions { raw: unsafe { ll::rocks_readoptions_new(cksum as u8, cache as u8) }, _marker: PhantomData, } } /// If `snapshot` is non-nullptr, read as of the supplied snapshot /// (which must belong to the DB that is being read and which must /// not have been released). If `snapshot` is nullptr, use an implicit /// snapshot of the state at the beginning of this read operation. /// /// Default: nullptr pub fn snapshot<'s, 'b: 'a, T: AsRef<Snapshot<'s>> + 'b>(self, val: Option<T>) -> Self { unsafe { ll::rocks_readoptions_set_snapshot(self.raw, val.map(|v| v.as_ref().raw()).unwrap_or(ptr::null_mut())); } self } /// `iterate_lower_bound` defines the smallest key at which the backward /// iterator can return an entry. Once the bound is passed, Valid() will be /// false. `iterate_lower_bound` is inclusive ie the bound value is a valid /// entry. /// /// If prefix_extractor is not null, the Seek target and `iterate_lower_bound` /// need to have the same prefix. This is because ordering is not guaranteed /// outside of prefix domain. /// /// Default: nullptr pub fn iterate_lower_bound<'b: 'a>(self, val: &'b [u8]) -> Self { unsafe { ll::rocks_readoptions_set_iterate_lower_bound(self.raw, val.as_ptr() as *const _, val.len()) } self } /// `iterate_upper_bound` defines the extent upto which the forward iterator /// can returns entries. Once the bound is reached, `is_valid()` will be false. /// `iterate_upper_bound` is exclusive ie the bound value is /// not a valid entry. If `iterator_extractor` is not null, the Seek target /// and `iterator_upper_bound` need to have the same prefix. /// This is because ordering is not guaranteed outside of prefix domain. /// There is no lower bound on the iterator. If needed, that can be easily /// implemented /// /// Default: nullptr pub fn iterate_upper_bound<'b: 'a>(self, val: &'b [u8]) -> Self { unsafe { ll::rocks_readoptions_set_iterate_upper_bound(self.raw, val.as_ptr() as *const _, val.len()) } self } /// If non-zero, NewIterator will create a new table reader which /// performs reads of the given size. Using a large size (> 2MB) can /// improve the performance of forward iteration on spinning disks. /// /// Default: 0 pub fn readahead_size(self, val: usize) -> Self { unsafe { ll::rocks_readoptions_set_readahead_size(self.raw, val); } self } /// A threshold for the number of keys that can be skipped before failing an /// iterator seek as incomplete. The default value of 0 should be used to /// never fail a request as incomplete, even on skipping too many keys. /// /// Default: 0 pub fn max_skippable_internal_keys(self, val: u64) -> Self { unsafe { ll::rocks_readoptions_set_max_skippable_internal_keys(self.raw, val); } self } /// Specify if this read request should process data that ALREADY /// resides on a particular cache. If the required data is not /// found at the specified cache, then `Status::Incomplete` is returned. /// /// Default: kReadAllTier pub fn read_tier(self, val: ReadTier) -> Self { unsafe { ll::rocks_readoptions_set_read_tier(self.raw, mem::transmute(val)); } self } /// If true, all data read from underlying storage will be /// verified against corresponding checksums. /// /// Default: true pub fn verify_checksums(self, val: bool) -> Self { unsafe { ll::rocks_readoptions_set_verify_checksums(self.raw, val as u8); } self } /// Should the "data block"/"index block"/"filter block" read for this /// iteration be cached in memory? /// /// Callers may wish to set this field to false for bulk scans. /// /// Default: true pub fn fill_cache(self, val: bool) -> Self { unsafe { ll::rocks_readoptions_set_fill_cache(self.raw, val as u8); } self } /// Specify to create a tailing iterator -- a special iterator that has a /// view of the complete database (i.e. it can also be used to read newly /// added data) and is optimized for sequential reads. It will return records /// that were inserted into the database after the creation of the iterator. /// /// Default: false pub fn tailing(self, val: bool) -> Self { unsafe { ll::rocks_readoptions_set_tailing(self.raw, val as u8); } self } /// Specify to create a managed iterator -- a special iterator that /// uses less resources by having the ability to free its underlying /// resources on request. /// /// Default: false pub fn managed(self, val: bool) -> Self { unsafe { ll::rocks_readoptions_set_managed(self.raw, val as u8); } self } /// Enable a total order seek regardless of index format (e.g. hash index) /// used in the table. Some table format (e.g. plain table) may not support /// this option. /// /// If true when calling `get()`, we also skip prefix bloom when reading from /// block based table. It provides a way to read existing data after /// changing implementation of prefix extractor. pub fn total_order_seek(self, val: bool) -> Self { unsafe { ll::rocks_readoptions_set_total_order_seek(self.raw, val as u8); } self } /// Enforce that the iterator only iterates over the same prefix as the seek. /// This option is effective only for prefix seeks, i.e. `prefix_extractor` is /// non-null for the column family and `total_order_seek` is false. Unlike /// `iterate_upper_bound`, `prefix_same_as_start` only works within a prefix /// but in both directions. /// /// Default: false pub fn prefix_same_as_start(self, val: bool) -> Self { unsafe { ll::rocks_readoptions_set_prefix_same_as_start(self.raw, val as u8); } self } /// Keep the blocks loaded by the iterator pinned in memory as long as the /// iterator is not deleted, If used when reading from tables created with /// `BlockBasedTableOptions::use_delta_encoding = false`, /// Iterator's property `"rocksdb.iterator.is-key-pinned"` is guaranteed to /// return 1. /// /// Default: false pub fn pin_data(self, val: bool) -> Self { unsafe { ll::rocks_readoptions_set_pin_data(self.raw, val as u8); } self } /// If true, when `PurgeObsoleteFile` is called in `CleanupIteratorState`, we /// schedule a background job in the flush job queue and delete obsolete files /// in background. /// /// Default: false pub fn background_purge_on_iterator_cleanup(self, val: bool) -> Self { unsafe { ll::rocks_readoptions_set_background_purge_on_iterator_cleanup(self.raw, val as u8); } self } /// If true, keys deleted using the `delete_range()` API will be visible to /// readers until they are naturally deleted during compaction. This improves /// read performance in DBs with many range deletions. /// /// Default: false pub fn ignore_range_deletions(self, val: bool) -> Self { unsafe { ll::rocks_readoptions_set_ignore_range_deletions(self.raw, val as u8); } self } /// Needed to support differential snapshots. Has 2 effects: /// /// 1) Iterator will skip all internal keys with seqnum < iter_start_seqnum /// 2) if this param > 0 iterator will return INTERNAL keys instead of /// user keys; e.g. return tombstones as well. /// /// Default: 0 (don't filter by seqnum, return user keys) pub fn iter_start_seqnum(self, val: SequenceNumber) -> Self { unsafe { ll::rocks_readoptions_set_iter_start_seqnum(self.raw, val.0); } self } } /// Options that control write operations pub struct WriteOptions { raw: *mut ll::rocks_writeoptions_t, } unsafe impl Sync for WriteOptions {} impl AsRef<WriteOptions> for WriteOptions { fn as_ref(&self) -> &WriteOptions { self } } impl Default for WriteOptions { fn default() -> Self { WriteOptions { raw: unsafe { ll::rocks_writeoptions_create() }, } } } impl Drop for WriteOptions { fn drop(&mut self) { unsafe { ll::rocks_writeoptions_destroy(self.raw); } } } impl ToRaw<ll::rocks_writeoptions_t> for WriteOptions { fn raw(&self) -> *mut ll::rocks_writeoptions_t { self.raw } } impl WriteOptions { /// default `WriteOptions` optimization #[inline] pub fn default_instance() -> &'static WriteOptions { &*DEFAULT_WRITE_OPTIONS } /// If true, the write will be flushed from the operating system /// buffer cache (by calling `WritableFile::Sync()`) before the write /// is considered complete. If this flag is true, writes will be /// slower. /// /// If this flag is false, and the machine crashes, some recent /// writes may be lost. Note that if it is just the process that /// crashes (i.e., the machine does not reboot), no writes will be /// lost even if sync==false. /// /// In other words, a DB write with sync==false has similar /// crash semantics as the "`write()`" system call. A DB write /// with `sync==true` has similar crash semantics to a "`write()`" /// system call followed by "`fdatasync()`". /// /// Default: false pub fn sync(self, val: bool) -> Self { unsafe { ll::rocks_writeoptions_set_sync(self.raw, val as u8); } self } /// If true, writes will not first go to the write ahead log, /// and the write may got lost after a crash. pub fn disable_wal(self, val: bool) -> Self { unsafe { ll::rocks_writeoptions_set_disable_wal(self.raw, val as u8); } self } /// If true and if user is trying to write to column families that don't exist /// (they were dropped), ignore the write (don't return an error). If there /// are multiple writes in a WriteBatch, other writes will succeed. /// /// Default: false pub fn ignore_missing_column_families(self, val: bool) -> Self { unsafe { ll::rocks_writeoptions_set_ignore_missing_column_families(self.raw, val as u8); } self } /// If true and we need to wait or sleep for the write request, fails /// immediately with Status::Incomplete(). pub fn no_slowdown(self, val: bool) -> Self { unsafe { ll::rocks_writeoptions_set_no_slowdown(self.raw, val as u8); } self } /// If true, this write request is of lower priority if compaction is /// behind. In this case, no_slowdown = true, the request will be cancelled /// immediately with Status::Incomplete() returned. Otherwise, it will be /// slowed down. The slowdown value is determined by RocksDB to guarantee /// it introduces minimum impacts to high priority writes. /// /// Default: false pub fn low_pri(self, val: bool) -> Self { unsafe { ll::rocks_writeoptions_set_low_pri(self.raw, val as u8); } self } /// If true, this writebatch will maintain the last insert positions of each /// memtable as hints in concurrent write. It can improve write performance /// in concurrent writes if keys in one writebatch are sequential. In /// non-concurrent writes (when concurrent_memtable_writes is false) this /// option will be ignored. /// /// Default: false pub fn memtable_insert_hint_per_batch(self, val: bool) -> Self { unsafe { ll::rocks_writeoptions_set_memtable_insert_hint_per_batch(self.raw, val as u8); } self } } /// Options that control flush operations #[repr(C)] pub struct FlushOptions { raw: *mut ll::rocks_flushoptions_t, } impl Default for FlushOptions { fn default() -> Self { FlushOptions { raw: unsafe { ll::rocks_flushoptions_create() }, } } } impl Drop for FlushOptions { fn drop(&mut self) { unsafe { ll::rocks_flushoptions_destroy(self.raw); } } } impl ToRaw<ll::rocks_flushoptions_t> for FlushOptions { fn raw(&self) -> *mut ll::rocks_flushoptions_t { self.raw } } impl FlushOptions { #[inline] pub fn default_instance() -> &'static FlushOptions { &*DEFAULT_FLUSH_OPTIONS } /// If true, the flush will wait until the flush is done. /// /// Default: true pub fn wait(self, val: bool) -> Self { unsafe { ll::rocks_flushoptions_set_wait(self.raw, val as u8); } self } /// If true, the flush would proceed immediately even it means writes will /// stall for the duration of the flush; if false the operation will wait /// until it's possible to do flush w/o causing stall or until required flush /// is performed by someone else (foreground call or background thread). /// /// Default: false pub fn allow_write_stall(self, val: bool) -> Self { unsafe { ll::rocks_flushoptions_set_allow_write_stall(self.raw, val as u8); } self } } unsafe impl Sync for FlushOptions {} /// `CompactionOptions` are used in `CompactFiles()` call. #[repr(C)] pub struct CompactionOptions { raw: *mut ll::rocks_compaction_options_t, } impl ToRaw<ll::rocks_compaction_options_t> for CompactionOptions { fn raw(&self) -> *mut ll::rocks_compaction_options_t { self.raw } } impl Default for CompactionOptions { fn default() -> Self { CompactionOptions::new() } } impl Drop for CompactionOptions { fn drop(&mut self) { unsafe { ll::rocks_compaction_options_destroy(self.raw); } } } impl CompactionOptions { pub fn new() -> CompactionOptions { CompactionOptions { raw: unsafe { ll::rocks_compaction_options_create() }, } } /// Compaction output compression type /// /// Default: snappy pub fn compression(self, val: CompressionType) -> Self { unsafe { ll::rocks_compaction_options_set_compression(self.raw, mem::transmute(val)); } self } /// Compaction will create files of size `output_file_size_limit`. /// /// Default: MAX, which means that compaction will create a single file pub fn output_file_size_limit(self, val: u64) -> Self { unsafe { ll::rocks_compaction_options_set_output_file_size_limit(self.raw, val); } self } } unsafe impl Sync for CompactionOptions {} /// For level based compaction, we can configure if we want to skip/force /// bottommost level compaction. #[repr(C)] #[derive(Debug, Copy, Clone, PartialEq, Eq, Hash)] pub enum BottommostLevelCompaction { /// Skip bottommost level compaction Skip, /// Only compact bottommost level if there is a compaction filter /// This is the default option IfHaveCompactionFilter, /// Always compact bottommost level Force, } /// `CompactRangeOptions` is used by `compact_range()` call. pub struct CompactRangeOptions { raw: *mut ll::rocks_compactrange_options_t, } impl Default for CompactRangeOptions { fn default() -> Self { CompactRangeOptions { raw: unsafe { ll::rocks_compactrange_options_create() }, } } } impl Drop for CompactRangeOptions { fn drop(&mut self) { unsafe { ll::rocks_compactrange_options_destroy(self.raw); } } } impl ToRaw<ll::rocks_compactrange_options_t> for CompactRangeOptions { fn raw(&self) -> *mut ll::rocks_compactrange_options_t { self.raw } } impl CompactRangeOptions { /// If true, no other compaction will run at the same time as this /// manual compaction pub fn exclusive_manual_compaction(self, val: bool) -> Self { unsafe { ll::rocks_compactrange_options_set_exclusive_manual_compaction(self.raw, val as u8); } self } /// If true, compacted files will be moved to the minimum level capable /// of holding the data or given level (specified non-negative target_level). pub fn change_level(self, val: bool) -> Self { unsafe { ll::rocks_compactrange_options_set_change_level(self.raw, val as u8); } self } /// If change_level is true and target_level have non-negative value, compacted /// files will be moved to target_level. pub fn target_level(self, val: i32) -> Self { unsafe { ll::rocks_compactrange_options_set_target_level(self.raw, val); } self } /// Compaction outputs will be placed in options.db_paths[target_path_id]. /// Behavior is undefined if target_path_id is out of range. pub fn target_path_id(self, val: u32) -> Self { unsafe { ll::rocks_compactrange_options_set_target_path_id(self.raw, val); } self } /// By default level based compaction will only compact the bottommost level /// if there is a compaction filter pub fn bottommost_level_compaction(self, val: BottommostLevelCompaction) -> Self { unsafe { ll::rocks_compactrange_options_set_bottommost_level_compaction(self.raw, mem::transmute(val)); } self } } unsafe impl Sync for CompactRangeOptions {} /// `IngestExternalFileOptions` is used by `ingest_external_file()` #[repr(C)] pub struct IngestExternalFileOptions { raw: *mut ll::rocks_ingestexternalfile_options_t, } impl Default for IngestExternalFileOptions { fn default() -> Self { IngestExternalFileOptions { raw: unsafe { ll::rocks_ingestexternalfile_options_create() }, } } } impl Drop for IngestExternalFileOptions { fn drop(&mut self) { unsafe { ll::rocks_ingestexternalfile_options_destroy(self.raw); } } } impl ToRaw<ll::rocks_ingestexternalfile_options_t> for IngestExternalFileOptions { fn raw(&self) -> *mut ll::rocks_ingestexternalfile_options_t { self.raw } } impl IngestExternalFileOptions { /// Can be set to true to move the files instead of copying them. pub fn move_files(self, val: bool) -> Self { unsafe { ll::rocks_ingestexternalfile_options_set_move_files(self.raw, val as u8); } self } /// If set to false, an ingested file keys could appear in existing snapshots /// that where created before the file was ingested. pub fn snapshot_consistency(self, val: bool) -> Self { unsafe { ll::rocks_ingestexternalfile_options_set_snapshot_consistency(self.raw, val as u8); } self } /// If set to false, IngestExternalFile() will fail if the file key range /// overlaps with existing keys or tombstones in the DB. pub fn allow_global_seqno(self, val: bool) -> Self { unsafe { ll::rocks_ingestexternalfile_options_set_allow_global_seqno(self.raw, val as u8); } self } /// If set to false and the file key range overlaps with the memtable key range /// (memtable flush required), IngestExternalFile will fail. pub fn allow_blocking_flush(self, val: bool) -> Self { unsafe { ll::rocks_ingestexternalfile_options_set_allow_blocking_flush(self.raw, val as u8); } self } /// Set to true if you would like duplicate keys in the file being ingested /// to be skipped rather than overwriting existing data under that key. /// Usecase: back-fill of some historical data in the database without /// over-writing existing newer version of data. /// /// This option could only be used if the DB has been running /// with allow_ingest_behind=true since the dawn of time. /// All files will be ingested at the bottommost level with seqno=0. pub fn ingest_behind(self, val: bool) -> Self { unsafe { ll::rocks_ingestexternalfile_options_set_ingest_behind(self.raw, val as u8); } self } } unsafe impl Sync for IngestExternalFileOptions {} #[cfg(test)] mod tests { use super::super::rocksdb::*; use super::*; #[test] fn dboptions_stringify() { let opts = DBOptions::default().allow_2pc(true); assert!(format!("{:?}", opts).contains("allow_2pc=true")); } #[test] fn cfoptions_stringify() { let opts = ColumnFamilyOptions::default().max_write_buffer_number(5); assert!(format!("{:?}", opts).contains("max_write_buffer_number=5")); } #[test] fn readoptions() { // FIXME: is disable block cache works? let tmp_dir = ::tempdir::TempDir::new_in(".", "rocks").unwrap(); let db = DB::open( Options::default() .map_db_options(|db| db.create_if_missing(true)) .map_cf_options(|cf| { cf.table_factory_block_based( BlockBasedTableOptions::default().no_block_cache(true).block_cache(None), ) }), &tmp_dir, ) .unwrap(); assert!(db .put(&Default::default(), b"long-key", vec![b'A'; 1024].as_ref()) .is_ok()); assert!(db.compact_range(&Default::default(), ..).is_ok()); let val = db.get(&ReadOptions::default().read_tier(ReadTier::BlockCacheTier), b"long-key"); assert!(val.is_ok()); } #[test] fn default_instance() { let w1 = WriteOptions::default_instance(); let w2 = WriteOptions::default_instance(); assert_eq!(w1.raw, w2.raw); let w1 = ReadOptions::default_instance(); let w2 = ReadOptions::default_instance(); assert_eq!(w1.raw, w2.raw); } #[test] fn compact_range_options() { let tmp_dir = ::tempdir::TempDir::new_in(".", "rocks").unwrap(); let db = DB::open( Options::default().map_db_options(|db| db.create_if_missing(true)), &tmp_dir, ) .unwrap(); assert!(db .put(&Default::default(), b"long-key", vec![b'A'; 1024 * 1024].as_ref()) .is_ok()); assert!(db.flush(&FlushOptions::default().wait(true)).is_ok()); assert!(db .put(&Default::default(), b"long-key-2", vec![b'A'; 2 * 1024].as_ref()) .is_ok()); assert!(db .compact_range( &CompactRangeOptions::default().change_level(true).target_level(4), // TO level 4 .., ) .is_ok()); let meta = db.get_column_family_metadata(&db.default_column_family()); println!("Meta => {:?}", meta); assert_eq!(meta.levels.len(), 7, "default level num"); assert_eq!(meta.levels[0].files.len(), 0); assert_eq!(meta.levels[1].files.len(), 0); assert_eq!(meta.levels[2].files.len(), 0); assert_eq!(meta.levels[3].files.len(), 0); assert!(meta.levels[4].files.len() > 0); } }