1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373
// Copyright 2020 Tyler Neely
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
use std::ffi::CStr;
use std::path::Path;
use std::ptr::{null_mut, NonNull};
use std::slice;
use std::sync::Arc;
use libc::{self, c_char, c_double, c_int, c_uchar, c_uint, c_void, size_t};
use crate::statistics::{Histogram, HistogramData, StatsLevel};
use crate::{
compaction_filter::{self, CompactionFilterCallback, CompactionFilterFn},
compaction_filter_factory::{self, CompactionFilterFactory},
comparator::{self, ComparatorCallback, CompareFn},
db::DBAccess,
env::Env,
ffi,
ffi_util::{from_cstr, to_cpath, CStrLike},
merge_operator::{
self, full_merge_callback, partial_merge_callback, MergeFn, MergeOperatorCallback,
},
slice_transform::SliceTransform,
statistics::Ticker,
ColumnFamilyDescriptor, Error, SnapshotWithThreadMode,
};
pub(crate) struct WriteBufferManagerWrapper {
pub(crate) inner: NonNull<ffi::rocksdb_write_buffer_manager_t>,
}
impl Drop for WriteBufferManagerWrapper {
fn drop(&mut self) {
unsafe {
ffi::rocksdb_write_buffer_manager_destroy(self.inner.as_ptr());
}
}
}
#[derive(Clone)]
pub struct WriteBufferManager(pub(crate) Arc<WriteBufferManagerWrapper>);
impl WriteBufferManager {
/// <https://github.com/facebook/rocksdb/wiki/Write-Buffer-Manager>
/// Write buffer manager helps users control the total memory used by memtables across multiple column families and/or DB instances.
/// Users can enable this control by 2 ways:
///
/// 1- Limit the total memtable usage across multiple column families and DBs under a threshold.
/// 2- Cost the memtable memory usage to block cache so that memory of RocksDB can be capped by the single limit.
/// The usage of a write buffer manager is similar to rate_limiter and sst_file_manager.
/// Users can create one write buffer manager object and pass it to all the options of column families or DBs whose memtable size they want to be controlled by this object.
///
/// A memory limit is given when creating the write buffer manager object. RocksDB will try to limit the total memory to under this limit.
///
/// a flush will be triggered on one column family of the DB you are inserting to,
///
/// If mutable memtable size exceeds about 90% of the limit,
/// If the total memory is over the limit, more aggressive flush may also be triggered only if the mutable memtable size also exceeds 50% of the limit.
/// Both checks are needed because if already more than half memory is being flushed, triggering more flush may not help.
///
/// The total memory is counted as total memory allocated in the arena, even if some of that may not yet be used by memtable.
///
/// buffer_size: the memory limit in bytes.
/// allow_stall: If set true, it will enable stalling of all writers when memory usage exceeds buffer_size (soft limit).
/// It will wait for flush to complete and memory usage to drop down
pub fn new_write_buffer_manager(buffer_size: size_t, allow_stall: bool) -> Self {
let inner = NonNull::new(unsafe {
ffi::rocksdb_write_buffer_manager_create(buffer_size, allow_stall)
})
.unwrap();
WriteBufferManager(Arc::new(WriteBufferManagerWrapper { inner }))
}
/// Users can set up RocksDB to cost memory used by memtables to block cache.
/// This can happen no matter whether you enable memtable memory limit or not.
/// This option is added to manage memory (memtables + block cache) under a single limit.
///
/// buffer_size: the memory limit in bytes.
/// allow_stall: If set true, it will enable stalling of all writers when memory usage exceeds buffer_size (soft limit).
/// It will wait for flush to complete and memory usage to drop down
/// cache: the block cache instance
pub fn new_write_buffer_manager_with_cache(
buffer_size: size_t,
allow_stall: bool,
cache: Cache,
) -> Self {
let inner = NonNull::new(unsafe {
ffi::rocksdb_write_buffer_manager_create_with_cache(
buffer_size,
cache.0.inner.as_ptr(),
allow_stall,
)
})
.unwrap();
WriteBufferManager(Arc::new(WriteBufferManagerWrapper { inner }))
}
/// Returns the WriteBufferManager memory usage in bytes.
pub fn get_usage(&self) -> usize {
unsafe { ffi::rocksdb_write_buffer_manager_memory_usage(self.0.inner.as_ptr()) }
}
/// Returns the current buffer size in bytes.
pub fn get_buffer_size(&self) -> usize {
unsafe { ffi::rocksdb_write_buffer_manager_buffer_size(self.0.inner.as_ptr()) }
}
/// Set the buffer size in bytes.
pub fn set_buffer_size(&self, new_size: usize) {
unsafe {
ffi::rocksdb_write_buffer_manager_set_buffer_size(self.0.inner.as_ptr(), new_size);
}
}
/// Returns if WriteBufferManager is enabled.
pub fn enabled(&self) -> bool {
unsafe { ffi::rocksdb_write_buffer_manager_enabled(self.0.inner.as_ptr()) }
}
/// set the allow_stall flag.
pub fn set_allow_stall(&self, allow_stall: bool) {
unsafe {
ffi::rocksdb_write_buffer_manager_set_allow_stall(self.0.inner.as_ptr(), allow_stall);
}
}
}
pub(crate) struct CacheWrapper {
pub(crate) inner: NonNull<ffi::rocksdb_cache_t>,
}
impl Drop for CacheWrapper {
fn drop(&mut self) {
unsafe {
ffi::rocksdb_cache_destroy(self.inner.as_ptr());
}
}
}
#[derive(Clone)]
pub struct Cache(pub(crate) Arc<CacheWrapper>);
impl Cache {
/// Creates an LRU cache with capacity in bytes.
pub fn new_lru_cache(capacity: size_t) -> Cache {
let inner = NonNull::new(unsafe { ffi::rocksdb_cache_create_lru(capacity) }).unwrap();
Cache(Arc::new(CacheWrapper { inner }))
}
/// Creates a HyperClockCache with capacity in bytes.
///
/// `estimated_entry_charge` is an important tuning parameter. The optimal
/// choice at any given time is
/// `(cache.get_usage() - 64 * cache.get_table_address_count()) /
/// cache.get_occupancy_count()`, or approximately `cache.get_usage() /
/// cache.get_occupancy_count()`.
///
/// However, the value cannot be changed dynamically, so as the cache
/// composition changes at runtime, the following tradeoffs apply:
///
/// * If the estimate is substantially too high (e.g., 25% higher),
/// the cache may have to evict entries to prevent load factors that
/// would dramatically affect lookup times.
/// * If the estimate is substantially too low (e.g., less than half),
/// then meta data space overhead is substantially higher.
///
/// The latter is generally preferable, and picking the larger of
/// block size and meta data block size is a reasonable choice that
/// errs towards this side.
pub fn new_hyper_clock_cache(capacity: size_t, estimated_entry_charge: size_t) -> Cache {
Cache(Arc::new(CacheWrapper {
inner: NonNull::new(unsafe {
ffi::rocksdb_cache_create_hyper_clock(capacity, estimated_entry_charge)
})
.unwrap(),
}))
}
/// Returns the cache memory usage in bytes.
pub fn get_usage(&self) -> usize {
unsafe { ffi::rocksdb_cache_get_usage(self.0.inner.as_ptr()) }
}
/// Returns the pinned memory usage in bytes.
pub fn get_pinned_usage(&self) -> usize {
unsafe { ffi::rocksdb_cache_get_pinned_usage(self.0.inner.as_ptr()) }
}
/// Sets cache capacity in bytes.
pub fn set_capacity(&mut self, capacity: size_t) {
unsafe {
ffi::rocksdb_cache_set_capacity(self.0.inner.as_ptr(), capacity);
}
}
}
#[derive(Default)]
pub(crate) struct OptionsMustOutliveDB {
env: Option<Env>,
row_cache: Option<Cache>,
block_based: Option<BlockBasedOptionsMustOutliveDB>,
write_buffer_manager: Option<WriteBufferManager>,
}
impl OptionsMustOutliveDB {
pub(crate) fn clone(&self) -> Self {
Self {
env: self.env.as_ref().map(Env::clone),
row_cache: self.row_cache.as_ref().map(Cache::clone),
block_based: self
.block_based
.as_ref()
.map(BlockBasedOptionsMustOutliveDB::clone),
write_buffer_manager: self
.write_buffer_manager
.as_ref()
.map(WriteBufferManager::clone),
}
}
}
#[derive(Default)]
struct BlockBasedOptionsMustOutliveDB {
block_cache: Option<Cache>,
}
impl BlockBasedOptionsMustOutliveDB {
fn clone(&self) -> Self {
Self {
block_cache: self.block_cache.as_ref().map(Cache::clone),
}
}
}
/// Database-wide options around performance and behavior.
///
/// Please read the official tuning [guide](https://github.com/facebook/rocksdb/wiki/RocksDB-Tuning-Guide)
/// and most importantly, measure performance under realistic workloads with realistic hardware.
///
/// # Examples
///
/// ```
/// use rocksdb::{Options, DB};
/// use rocksdb::DBCompactionStyle;
///
/// fn badly_tuned_for_somebody_elses_disk() -> DB {
/// let path = "path/for/rocksdb/storageX";
/// let mut opts = Options::default();
/// opts.create_if_missing(true);
/// opts.set_max_open_files(10000);
/// opts.set_use_fsync(false);
/// opts.set_bytes_per_sync(8388608);
/// opts.optimize_for_point_lookup(1024);
/// opts.set_table_cache_num_shard_bits(6);
/// opts.set_max_write_buffer_number(32);
/// opts.set_write_buffer_size(536870912);
/// opts.set_target_file_size_base(1073741824);
/// opts.set_min_write_buffer_number_to_merge(4);
/// opts.set_level_zero_stop_writes_trigger(2000);
/// opts.set_level_zero_slowdown_writes_trigger(0);
/// opts.set_compaction_style(DBCompactionStyle::Universal);
/// opts.set_disable_auto_compactions(true);
///
/// DB::open(&opts, path).unwrap()
/// }
/// ```
pub struct Options {
pub(crate) inner: *mut ffi::rocksdb_options_t,
pub(crate) outlive: OptionsMustOutliveDB,
}
/// Optionally disable WAL or sync for this write.
///
/// # Examples
///
/// Making an unsafe write of a batch:
///
/// ```
/// use rocksdb::{DB, Options, WriteBatch, WriteOptions};
///
/// let path = "_path_for_rocksdb_storageY1";
/// {
/// let db = DB::open_default(path).unwrap();
/// let mut batch = WriteBatch::default();
/// batch.put(b"my key", b"my value");
/// batch.put(b"key2", b"value2");
/// batch.put(b"key3", b"value3");
///
/// let mut write_options = WriteOptions::default();
/// write_options.set_sync(false);
/// write_options.disable_wal(true);
///
/// db.write_opt(batch, &write_options);
/// }
/// let _ = DB::destroy(&Options::default(), path);
/// ```
pub struct WriteOptions {
pub(crate) inner: *mut ffi::rocksdb_writeoptions_t,
}
/// Optionally wait for the memtable flush to be performed.
///
/// # Examples
///
/// Manually flushing the memtable:
///
/// ```
/// use rocksdb::{DB, Options, FlushOptions};
///
/// let path = "_path_for_rocksdb_storageY2";
/// {
/// let db = DB::open_default(path).unwrap();
///
/// let mut flush_options = FlushOptions::default();
/// flush_options.set_wait(true);
///
/// db.flush_opt(&flush_options);
/// }
/// let _ = DB::destroy(&Options::default(), path);
/// ```
pub struct FlushOptions {
pub(crate) inner: *mut ffi::rocksdb_flushoptions_t,
}
/// For configuring block-based file storage.
pub struct BlockBasedOptions {
pub(crate) inner: *mut ffi::rocksdb_block_based_table_options_t,
outlive: BlockBasedOptionsMustOutliveDB,
}
pub struct ReadOptions {
pub(crate) inner: *mut ffi::rocksdb_readoptions_t,
iterate_upper_bound: Option<Vec<u8>>,
iterate_lower_bound: Option<Vec<u8>>,
}
/// Configuration of cuckoo-based storage.
pub struct CuckooTableOptions {
pub(crate) inner: *mut ffi::rocksdb_cuckoo_table_options_t,
}
/// For configuring external files ingestion.
///
/// # Examples
///
/// Move files instead of copying them:
///
/// ```
/// use rocksdb::{DB, IngestExternalFileOptions, SstFileWriter, Options};
///
/// let writer_opts = Options::default();
/// let mut writer = SstFileWriter::create(&writer_opts);
/// writer.open("_path_for_sst_file").unwrap();
/// writer.put(b"k1", b"v1").unwrap();
/// writer.finish().unwrap();
///
/// let path = "_path_for_rocksdb_storageY3";
/// {
/// let db = DB::open_default(&path).unwrap();
/// let mut ingest_opts = IngestExternalFileOptions::default();
/// ingest_opts.set_move_files(true);
/// db.ingest_external_file_opts(&ingest_opts, vec!["_path_for_sst_file"]).unwrap();
/// }
/// let _ = DB::destroy(&Options::default(), path);
/// ```
pub struct IngestExternalFileOptions {
pub(crate) inner: *mut ffi::rocksdb_ingestexternalfileoptions_t,
}
// Safety note: auto-implementing Send on most db-related types is prevented by the inner FFI
// pointer. In most cases, however, this pointer is Send-safe because it is never aliased and
// rocksdb internally does not rely on thread-local information for its user-exposed types.
unsafe impl Send for Options {}
unsafe impl Send for WriteOptions {}
unsafe impl Send for FlushOptions {}
unsafe impl Send for BlockBasedOptions {}
unsafe impl Send for CuckooTableOptions {}
unsafe impl Send for ReadOptions {}
unsafe impl Send for IngestExternalFileOptions {}
unsafe impl Send for CacheWrapper {}
unsafe impl Send for CompactOptions {}
unsafe impl Send for WriteBufferManagerWrapper {}
// Sync is similarly safe for many types because they do not expose interior mutability, and their
// use within the rocksdb library is generally behind a const reference
unsafe impl Sync for Options {}
unsafe impl Sync for WriteOptions {}
unsafe impl Sync for FlushOptions {}
unsafe impl Sync for BlockBasedOptions {}
unsafe impl Sync for CuckooTableOptions {}
unsafe impl Sync for ReadOptions {}
unsafe impl Sync for IngestExternalFileOptions {}
unsafe impl Sync for CacheWrapper {}
unsafe impl Sync for CompactOptions {}
unsafe impl Sync for WriteBufferManagerWrapper {}
impl Drop for Options {
fn drop(&mut self) {
unsafe {
ffi::rocksdb_options_destroy(self.inner);
}
}
}
impl Clone for Options {
fn clone(&self) -> Self {
let inner = unsafe { ffi::rocksdb_options_create_copy(self.inner) };
assert!(!inner.is_null(), "Could not copy RocksDB options");
Self {
inner,
outlive: self.outlive.clone(),
}
}
}
impl Drop for BlockBasedOptions {
fn drop(&mut self) {
unsafe {
ffi::rocksdb_block_based_options_destroy(self.inner);
}
}
}
impl Drop for CuckooTableOptions {
fn drop(&mut self) {
unsafe {
ffi::rocksdb_cuckoo_options_destroy(self.inner);
}
}
}
impl Drop for FlushOptions {
fn drop(&mut self) {
unsafe {
ffi::rocksdb_flushoptions_destroy(self.inner);
}
}
}
impl Drop for WriteOptions {
fn drop(&mut self) {
unsafe {
ffi::rocksdb_writeoptions_destroy(self.inner);
}
}
}
impl Drop for ReadOptions {
fn drop(&mut self) {
unsafe {
ffi::rocksdb_readoptions_destroy(self.inner);
}
}
}
impl Drop for IngestExternalFileOptions {
fn drop(&mut self) {
unsafe {
ffi::rocksdb_ingestexternalfileoptions_destroy(self.inner);
}
}
}
impl BlockBasedOptions {
/// Approximate size of user data packed per block. Note that the
/// block size specified here corresponds to uncompressed data. The
/// actual size of the unit read from disk may be smaller if
/// compression is enabled. This parameter can be changed dynamically.
pub fn set_block_size(&mut self, size: usize) {
unsafe {
ffi::rocksdb_block_based_options_set_block_size(self.inner, size);
}
}
/// Block size for partitioned metadata. Currently applied to indexes when
/// kTwoLevelIndexSearch is used and to filters when partition_filters is used.
/// Note: Since in the current implementation the filters and index partitions
/// are aligned, an index/filter block is created when either index or filter
/// block size reaches the specified limit.
///
/// Note: this limit is currently applied to only index blocks; a filter
/// partition is cut right after an index block is cut.
pub fn set_metadata_block_size(&mut self, size: usize) {
unsafe {
ffi::rocksdb_block_based_options_set_metadata_block_size(self.inner, size as u64);
}
}
/// Note: currently this option requires kTwoLevelIndexSearch to be set as
/// well.
///
/// Use partitioned full filters for each SST file. This option is
/// incompatible with block-based filters.
pub fn set_partition_filters(&mut self, size: bool) {
unsafe {
ffi::rocksdb_block_based_options_set_partition_filters(self.inner, c_uchar::from(size));
}
}
/// Sets global cache for blocks (user data is stored in a set of blocks, and
/// a block is the unit of reading from disk).
///
/// If set, use the specified cache for blocks.
/// By default, rocksdb will automatically create and use an 8MB internal cache.
pub fn set_block_cache(&mut self, cache: &Cache) {
unsafe {
ffi::rocksdb_block_based_options_set_block_cache(self.inner, cache.0.inner.as_ptr());
}
self.outlive.block_cache = Some(cache.clone());
}
/// Disable block cache
pub fn disable_cache(&mut self) {
unsafe {
ffi::rocksdb_block_based_options_set_no_block_cache(self.inner, c_uchar::from(true));
}
}
/// Sets a [Bloom filter](https://github.com/facebook/rocksdb/wiki/RocksDB-Bloom-Filter)
/// policy to reduce disk reads.
///
/// # Examples
///
/// ```
/// use rocksdb::BlockBasedOptions;
///
/// let mut opts = BlockBasedOptions::default();
/// opts.set_bloom_filter(10.0, true);
/// ```
pub fn set_bloom_filter(&mut self, bits_per_key: c_double, block_based: bool) {
unsafe {
let bloom = if block_based {
ffi::rocksdb_filterpolicy_create_bloom(bits_per_key as _)
} else {
ffi::rocksdb_filterpolicy_create_bloom_full(bits_per_key as _)
};
ffi::rocksdb_block_based_options_set_filter_policy(self.inner, bloom);
}
}
/// Sets a [Ribbon filter](http://rocksdb.org/blog/2021/12/29/ribbon-filter.html)
/// policy to reduce disk reads.
///
/// Ribbon filters use less memory in exchange for slightly more CPU usage
/// compared to an equivalent bloom filter.
///
/// # Examples
///
/// ```
/// use rocksdb::BlockBasedOptions;
///
/// let mut opts = BlockBasedOptions::default();
/// opts.set_ribbon_filter(10.0);
/// ```
pub fn set_ribbon_filter(&mut self, bloom_equivalent_bits_per_key: c_double) {
unsafe {
let ribbon = ffi::rocksdb_filterpolicy_create_ribbon(bloom_equivalent_bits_per_key);
ffi::rocksdb_block_based_options_set_filter_policy(self.inner, ribbon);
}
}
/// Sets a hybrid [Ribbon filter](http://rocksdb.org/blog/2021/12/29/ribbon-filter.html)
/// policy to reduce disk reads.
///
/// Uses Bloom filters before the given level, and Ribbon filters for all
/// other levels. This combines the memory savings from Ribbon filters
/// with the lower CPU usage of Bloom filters.
///
/// # Examples
///
/// ```
/// use rocksdb::BlockBasedOptions;
///
/// let mut opts = BlockBasedOptions::default();
/// opts.set_hybrid_ribbon_filter(10.0, 2);
/// ```
pub fn set_hybrid_ribbon_filter(
&mut self,
bloom_equivalent_bits_per_key: c_double,
bloom_before_level: c_int,
) {
unsafe {
let ribbon = ffi::rocksdb_filterpolicy_create_ribbon_hybrid(
bloom_equivalent_bits_per_key,
bloom_before_level,
);
ffi::rocksdb_block_based_options_set_filter_policy(self.inner, ribbon);
}
}
/// If cache_index_and_filter_blocks is enabled, cache index and filter blocks with high priority.
/// If set to true, depending on implementation of block cache,
/// index and filter blocks may be less likely to be evicted than data blocks.
pub fn set_cache_index_and_filter_blocks(&mut self, v: bool) {
unsafe {
ffi::rocksdb_block_based_options_set_cache_index_and_filter_blocks(
self.inner,
c_uchar::from(v),
);
}
}
/// Defines the index type to be used for SS-table lookups.
///
/// # Examples
///
/// ```
/// use rocksdb::{BlockBasedOptions, BlockBasedIndexType, Options};
///
/// let mut opts = Options::default();
/// let mut block_opts = BlockBasedOptions::default();
/// block_opts.set_index_type(BlockBasedIndexType::HashSearch);
/// ```
pub fn set_index_type(&mut self, index_type: BlockBasedIndexType) {
let index = index_type as i32;
unsafe {
ffi::rocksdb_block_based_options_set_index_type(self.inner, index);
}
}
/// If cache_index_and_filter_blocks is true and the below is true, then
/// filter and index blocks are stored in the cache, but a reference is
/// held in the "table reader" object so the blocks are pinned and only
/// evicted from cache when the table reader is freed.
///
/// Default: false.
pub fn set_pin_l0_filter_and_index_blocks_in_cache(&mut self, v: bool) {
unsafe {
ffi::rocksdb_block_based_options_set_pin_l0_filter_and_index_blocks_in_cache(
self.inner,
c_uchar::from(v),
);
}
}
/// If cache_index_and_filter_blocks is true and the below is true, then
/// the top-level index of partitioned filter and index blocks are stored in
/// the cache, but a reference is held in the "table reader" object so the
/// blocks are pinned and only evicted from cache when the table reader is
/// freed. This is not limited to l0 in LSM tree.
///
/// Default: false.
pub fn set_pin_top_level_index_and_filter(&mut self, v: bool) {
unsafe {
ffi::rocksdb_block_based_options_set_pin_top_level_index_and_filter(
self.inner,
c_uchar::from(v),
);
}
}
/// Format version, reserved for backward compatibility.
///
/// See full [list](https://github.com/facebook/rocksdb/blob/v8.6.7/include/rocksdb/table.h#L493-L521)
/// of the supported versions.
///
/// Default: 5.
pub fn set_format_version(&mut self, version: i32) {
unsafe {
ffi::rocksdb_block_based_options_set_format_version(self.inner, version);
}
}
/// Number of keys between restart points for delta encoding of keys.
/// This parameter can be changed dynamically. Most clients should
/// leave this parameter alone. The minimum value allowed is 1. Any smaller
/// value will be silently overwritten with 1.
///
/// Default: 16.
pub fn set_block_restart_interval(&mut self, interval: i32) {
unsafe {
ffi::rocksdb_block_based_options_set_block_restart_interval(self.inner, interval);
}
}
/// Same as block_restart_interval but used for the index block.
/// If you don't plan to run RocksDB before version 5.16 and you are
/// using `index_block_restart_interval` > 1, you should
/// probably set the `format_version` to >= 4 as it would reduce the index size.
///
/// Default: 1.
pub fn set_index_block_restart_interval(&mut self, interval: i32) {
unsafe {
ffi::rocksdb_block_based_options_set_index_block_restart_interval(self.inner, interval);
}
}
/// Set the data block index type for point lookups:
/// `DataBlockIndexType::BinarySearch` to use binary search within the data block.
/// `DataBlockIndexType::BinaryAndHash` to use the data block hash index in combination with
/// the normal binary search.
///
/// The hash table utilization ratio is adjustable using [`set_data_block_hash_ratio`](#method.set_data_block_hash_ratio), which is
/// valid only when using `DataBlockIndexType::BinaryAndHash`.
///
/// Default: `BinarySearch`
/// # Examples
///
/// ```
/// use rocksdb::{BlockBasedOptions, DataBlockIndexType, Options};
///
/// let mut opts = Options::default();
/// let mut block_opts = BlockBasedOptions::default();
/// block_opts.set_data_block_index_type(DataBlockIndexType::BinaryAndHash);
/// block_opts.set_data_block_hash_ratio(0.85);
/// ```
pub fn set_data_block_index_type(&mut self, index_type: DataBlockIndexType) {
let index_t = index_type as i32;
unsafe {
ffi::rocksdb_block_based_options_set_data_block_index_type(self.inner, index_t);
}
}
/// Set the data block hash index utilization ratio.
///
/// The smaller the utilization ratio, the less hash collisions happen, and so reduce the risk for a
/// point lookup to fall back to binary search due to the collisions. A small ratio means faster
/// lookup at the price of more space overhead.
///
/// Default: 0.75
pub fn set_data_block_hash_ratio(&mut self, ratio: f64) {
unsafe {
ffi::rocksdb_block_based_options_set_data_block_hash_ratio(self.inner, ratio);
}
}
/// If false, place only prefixes in the filter, not whole keys.
///
/// Defaults to true.
pub fn set_whole_key_filtering(&mut self, v: bool) {
unsafe {
ffi::rocksdb_block_based_options_set_whole_key_filtering(self.inner, c_uchar::from(v));
}
}
/// Use the specified checksum type.
/// Newly created table files will be protected with this checksum type.
/// Old table files will still be readable, even though they have different checksum type.
pub fn set_checksum_type(&mut self, checksum_type: ChecksumType) {
unsafe {
ffi::rocksdb_block_based_options_set_checksum(self.inner, checksum_type as c_char);
}
}
/// If true, generate Bloom/Ribbon filters that minimize memory internal
/// fragmentation.
/// See official [wiki](
/// https://github.com/facebook/rocksdb/wiki/RocksDB-Bloom-Filter#reducing-internal-fragmentation)
/// for more information.
///
/// Defaults to false.
/// # Examples
///
/// ```
/// use rocksdb::BlockBasedOptions;
///
/// let mut opts = BlockBasedOptions::default();
/// opts.set_bloom_filter(10.0, true);
/// opts.set_optimize_filters_for_memory(true);
/// ```
pub fn set_optimize_filters_for_memory(&mut self, v: bool) {
unsafe {
ffi::rocksdb_block_based_options_set_optimize_filters_for_memory(
self.inner,
c_uchar::from(v),
);
}
}
}
impl Default for BlockBasedOptions {
fn default() -> Self {
let block_opts = unsafe { ffi::rocksdb_block_based_options_create() };
assert!(
!block_opts.is_null(),
"Could not create RocksDB block based options"
);
Self {
inner: block_opts,
outlive: BlockBasedOptionsMustOutliveDB::default(),
}
}
}
impl CuckooTableOptions {
/// Determines the utilization of hash tables. Smaller values
/// result in larger hash tables with fewer collisions.
/// Default: 0.9
pub fn set_hash_ratio(&mut self, ratio: f64) {
unsafe {
ffi::rocksdb_cuckoo_options_set_hash_ratio(self.inner, ratio);
}
}
/// A property used by builder to determine the depth to go to
/// to search for a path to displace elements in case of
/// collision. See Builder.MakeSpaceForKey method. Higher
/// values result in more efficient hash tables with fewer
/// lookups but take more time to build.
/// Default: 100
pub fn set_max_search_depth(&mut self, depth: u32) {
unsafe {
ffi::rocksdb_cuckoo_options_set_max_search_depth(self.inner, depth);
}
}
/// In case of collision while inserting, the builder
/// attempts to insert in the next cuckoo_block_size
/// locations before skipping over to the next Cuckoo hash
/// function. This makes lookups more cache friendly in case
/// of collisions.
/// Default: 5
pub fn set_cuckoo_block_size(&mut self, size: u32) {
unsafe {
ffi::rocksdb_cuckoo_options_set_cuckoo_block_size(self.inner, size);
}
}
/// If this option is enabled, user key is treated as uint64_t and its value
/// is used as hash value directly. This option changes builder's behavior.
/// Reader ignore this option and behave according to what specified in
/// table property.
/// Default: false
pub fn set_identity_as_first_hash(&mut self, flag: bool) {
unsafe {
ffi::rocksdb_cuckoo_options_set_identity_as_first_hash(self.inner, c_uchar::from(flag));
}
}
/// If this option is set to true, module is used during hash calculation.
/// This often yields better space efficiency at the cost of performance.
/// If this option is set to false, # of entries in table is constrained to
/// be power of two, and bit and is used to calculate hash, which is faster in general.
/// Default: true
pub fn set_use_module_hash(&mut self, flag: bool) {
unsafe {
ffi::rocksdb_cuckoo_options_set_use_module_hash(self.inner, c_uchar::from(flag));
}
}
}
impl Default for CuckooTableOptions {
fn default() -> Self {
let opts = unsafe { ffi::rocksdb_cuckoo_options_create() };
assert!(!opts.is_null(), "Could not create RocksDB cuckoo options");
Self { inner: opts }
}
}
// Verbosity of the LOG.
#[derive(Debug, Copy, Clone, PartialEq, Eq)]
#[repr(i32)]
pub enum LogLevel {
Debug = 0,
Info,
Warn,
Error,
Fatal,
Header,
}
impl Options {
/// Constructs the DBOptions and ColumnFamilyDescriptors by loading the
/// latest RocksDB options file stored in the specified rocksdb database.
pub fn load_latest<P: AsRef<Path>>(
path: P,
env: Env,
ignore_unknown_options: bool,
cache: Cache,
) -> Result<(Options, Vec<ColumnFamilyDescriptor>), Error> {
let path = to_cpath(path)?;
let mut db_options: *mut ffi::rocksdb_options_t = null_mut();
let mut num_column_families: usize = 0;
let mut column_family_names: *mut *mut c_char = null_mut();
let mut column_family_options: *mut *mut ffi::rocksdb_options_t = null_mut();
unsafe {
ffi_try!(ffi::rocksdb_load_latest_options(
path.as_ptr(),
env.0.inner,
ignore_unknown_options,
cache.0.inner.as_ptr(),
&mut db_options,
&mut num_column_families,
&mut column_family_names,
&mut column_family_options,
));
}
let options = Options {
inner: db_options,
outlive: OptionsMustOutliveDB::default(),
};
let column_families = unsafe {
Options::read_column_descriptors(
num_column_families,
column_family_names,
column_family_options,
)
};
Ok((options, column_families))
}
/// read column descriptors from c pointers
#[inline]
unsafe fn read_column_descriptors(
num_column_families: usize,
column_family_names: *mut *mut c_char,
column_family_options: *mut *mut ffi::rocksdb_options_t,
) -> Vec<ColumnFamilyDescriptor> {
let column_family_names_iter =
slice::from_raw_parts(column_family_names, num_column_families)
.iter()
.map(|ptr| from_cstr(*ptr));
let column_family_options_iter =
slice::from_raw_parts(column_family_options, num_column_families)
.iter()
.map(|ptr| Options {
inner: *ptr,
outlive: OptionsMustOutliveDB::default(),
});
let column_descriptors = column_family_names_iter
.zip(column_family_options_iter)
.map(|(name, options)| ColumnFamilyDescriptor { name, options })
.collect::<Vec<_>>();
// free pointers
slice::from_raw_parts(column_family_names, num_column_families)
.iter()
.for_each(|ptr| ffi::rocksdb_free(*ptr as *mut c_void));
ffi::rocksdb_free(column_family_names as *mut c_void);
ffi::rocksdb_free(column_family_options as *mut c_void);
column_descriptors
}
/// 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.
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut opts = Options::default();
/// opts.increase_parallelism(3);
/// ```
pub fn increase_parallelism(&mut self, parallelism: i32) {
unsafe {
ffi::rocksdb_options_increase_parallelism(self.inner, parallelism);
}
}
/// Optimize level style compaction.
///
/// Default values for some parameters in `Options` are not optimized for heavy
/// workloads and big datasets, which means you might observe write stalls under
/// some conditions.
///
/// This can be used as one of the starting points for tuning RocksDB options in
/// such cases.
///
/// Internally, it sets `write_buffer_size`, `min_write_buffer_number_to_merge`,
/// `max_write_buffer_number`, `level0_file_num_compaction_trigger`,
/// `target_file_size_base`, `max_bytes_for_level_base`, so it can override if those
/// parameters were set before.
///
/// It sets buffer sizes so that memory consumption would be constrained by
/// `memtable_memory_budget`.
pub fn optimize_level_style_compaction(&mut self, memtable_memory_budget: usize) {
unsafe {
ffi::rocksdb_options_optimize_level_style_compaction(
self.inner,
memtable_memory_budget as u64,
);
}
}
/// Optimize universal style compaction.
///
/// Default values for some parameters in `Options` are not optimized for heavy
/// workloads and big datasets, which means you might observe write stalls under
/// some conditions.
///
/// This can be used as one of the starting points for tuning RocksDB options in
/// such cases.
///
/// Internally, it sets `write_buffer_size`, `min_write_buffer_number_to_merge`,
/// `max_write_buffer_number`, `level0_file_num_compaction_trigger`,
/// `target_file_size_base`, `max_bytes_for_level_base`, so it can override if those
/// parameters were set before.
///
/// It sets buffer sizes so that memory consumption would be constrained by
/// `memtable_memory_budget`.
pub fn optimize_universal_style_compaction(&mut self, memtable_memory_budget: usize) {
unsafe {
ffi::rocksdb_options_optimize_universal_style_compaction(
self.inner,
memtable_memory_budget as u64,
);
}
}
/// If true, the database will be created if it is missing.
///
/// Default: `false`
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut opts = Options::default();
/// opts.create_if_missing(true);
/// ```
pub fn create_if_missing(&mut self, create_if_missing: bool) {
unsafe {
ffi::rocksdb_options_set_create_if_missing(
self.inner,
c_uchar::from(create_if_missing),
);
}
}
/// If true, any column families that didn't exist when opening the database
/// will be created.
///
/// Default: `false`
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut opts = Options::default();
/// opts.create_missing_column_families(true);
/// ```
pub fn create_missing_column_families(&mut self, create_missing_cfs: bool) {
unsafe {
ffi::rocksdb_options_set_create_missing_column_families(
self.inner,
c_uchar::from(create_missing_cfs),
);
}
}
/// Specifies whether an error should be raised if the database already exists.
///
/// Default: false
pub fn set_error_if_exists(&mut self, enabled: bool) {
unsafe {
ffi::rocksdb_options_set_error_if_exists(self.inner, c_uchar::from(enabled));
}
}
/// Enable/disable paranoid checks.
///
/// If true, the implementation will do aggressive checking of the
/// data it is processing and will stop early if it detects any
/// errors. This may have unforeseen ramifications: for example, a
/// corruption of one DB entry may cause a large number of entries to
/// become unreadable or for the entire DB to become unopenable.
/// 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.
///
/// Default: false
pub fn set_paranoid_checks(&mut self, enabled: bool) {
unsafe {
ffi::rocksdb_options_set_paranoid_checks(self.inner, c_uchar::from(enabled));
}
}
/// 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 `path` passed when
/// opening the DB.
///
/// Default: empty
pub fn set_db_paths(&mut self, paths: &[DBPath]) {
let mut paths: Vec<_> = paths
.iter()
.map(|path| path.inner as *const ffi::rocksdb_dbpath_t)
.collect();
let num_paths = paths.len();
unsafe {
ffi::rocksdb_options_set_db_paths(self.inner, paths.as_mut_ptr(), num_paths);
}
}
/// Use the specified object to interact with the environment,
/// e.g. to read/write files, schedule background work, etc. In the near
/// future, support for doing storage operations such as read/write files
/// through env will be deprecated in favor of file_system.
///
/// Default: Env::default()
pub fn set_env(&mut self, env: &Env) {
unsafe {
ffi::rocksdb_options_set_env(self.inner, env.0.inner);
}
self.outlive.env = Some(env.clone());
}
/// Sets the compression algorithm that will be used for compressing blocks.
///
/// Default: `DBCompressionType::Snappy` (`DBCompressionType::None` if
/// snappy feature is not enabled).
///
/// # Examples
///
/// ```
/// use rocksdb::{Options, DBCompressionType};
///
/// let mut opts = Options::default();
/// opts.set_compression_type(DBCompressionType::Snappy);
/// ```
pub fn set_compression_type(&mut self, t: DBCompressionType) {
unsafe {
ffi::rocksdb_options_set_compression(self.inner, t as c_int);
}
}
/// Number of threads for parallel compression.
/// Parallel compression is enabled only if threads > 1.
/// THE FEATURE IS STILL EXPERIMENTAL
///
/// See [code](https://github.com/facebook/rocksdb/blob/v8.6.7/include/rocksdb/advanced_options.h#L116-L127)
/// for more information.
///
/// Default: 1
///
/// Examples
///
/// ```
/// use rocksdb::{Options, DBCompressionType};
///
/// let mut opts = Options::default();
/// opts.set_compression_type(DBCompressionType::Zstd);
/// opts.set_compression_options_parallel_threads(3);
/// ```
pub fn set_compression_options_parallel_threads(&mut self, num: i32) {
unsafe {
ffi::rocksdb_options_set_compression_options_parallel_threads(self.inner, num);
}
}
/// Sets the compression algorithm that will be used for compressing WAL.
///
/// At present, only ZSTD compression is supported!
///
/// Default: `DBCompressionType::None`
///
/// # Examples
///
/// ```
/// use rocksdb::{Options, DBCompressionType};
///
/// let mut opts = Options::default();
/// opts.set_wal_compression_type(DBCompressionType::Zstd);
/// // Or None to disable it
/// opts.set_wal_compression_type(DBCompressionType::None);
/// ```
pub fn set_wal_compression_type(&mut self, t: DBCompressionType) {
match t {
DBCompressionType::None | DBCompressionType::Zstd => unsafe {
ffi::rocksdb_options_set_wal_compression(self.inner, t as c_int);
},
other => unimplemented!("{:?} is not supported for WAL compression", other),
}
}
/// Sets the bottom-most compression algorithm that will be used for
/// compressing blocks at the bottom-most level.
///
/// Note that to actually enable bottom-most compression configuration after
/// setting the compression type, it needs to be enabled by calling
/// [`set_bottommost_compression_options`](#method.set_bottommost_compression_options) or
/// [`set_bottommost_zstd_max_train_bytes`](#method.set_bottommost_zstd_max_train_bytes) method with `enabled` argument
/// set to `true`.
///
/// # Examples
///
/// ```
/// use rocksdb::{Options, DBCompressionType};
///
/// let mut opts = Options::default();
/// opts.set_bottommost_compression_type(DBCompressionType::Zstd);
/// opts.set_bottommost_zstd_max_train_bytes(0, true);
/// ```
pub fn set_bottommost_compression_type(&mut self, t: DBCompressionType) {
unsafe {
ffi::rocksdb_options_set_bottommost_compression(self.inner, t as c_int);
}
}
/// 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'.
///
/// # Examples
///
/// ```
/// use rocksdb::{Options, DBCompressionType};
///
/// let mut opts = Options::default();
/// opts.set_compression_per_level(&[
/// DBCompressionType::None,
/// DBCompressionType::None,
/// DBCompressionType::Snappy,
/// DBCompressionType::Snappy,
/// DBCompressionType::Snappy
/// ]);
/// ```
pub fn set_compression_per_level(&mut self, level_types: &[DBCompressionType]) {
unsafe {
let mut level_types: Vec<_> = level_types.iter().map(|&t| t as c_int).collect();
ffi::rocksdb_options_set_compression_per_level(
self.inner,
level_types.as_mut_ptr(),
level_types.len() as size_t,
);
}
}
/// Maximum size of dictionaries used to prime the compression library.
/// Enabling dictionary can improve compression ratios when there are
/// repetitions across data blocks.
///
/// The dictionary is created by sampling the SST file data. If
/// `zstd_max_train_bytes` is nonzero, the samples are passed through zstd's
/// dictionary generator. Otherwise, the random samples are used directly as
/// the dictionary.
///
/// When compression dictionary is disabled, we compress and write each block
/// before buffering data for the next one. When compression dictionary is
/// enabled, we buffer all SST file data in-memory so we can sample it, as data
/// can only be compressed and written after the dictionary has been finalized.
/// So users of this feature may see increased memory usage.
///
/// Default: `0`
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut opts = Options::default();
/// opts.set_compression_options(4, 5, 6, 7);
/// ```
pub fn set_compression_options(
&mut self,
w_bits: c_int,
level: c_int,
strategy: c_int,
max_dict_bytes: c_int,
) {
unsafe {
ffi::rocksdb_options_set_compression_options(
self.inner,
w_bits,
level,
strategy,
max_dict_bytes,
);
}
}
/// Sets compression options for blocks at the bottom-most level. Meaning
/// of all settings is the same as in [`set_compression_options`](#method.set_compression_options) method but
/// affect only the bottom-most compression which is set using
/// [`set_bottommost_compression_type`](#method.set_bottommost_compression_type) method.
///
/// # Examples
///
/// ```
/// use rocksdb::{Options, DBCompressionType};
///
/// let mut opts = Options::default();
/// opts.set_bottommost_compression_type(DBCompressionType::Zstd);
/// opts.set_bottommost_compression_options(4, 5, 6, 7, true);
/// ```
pub fn set_bottommost_compression_options(
&mut self,
w_bits: c_int,
level: c_int,
strategy: c_int,
max_dict_bytes: c_int,
enabled: bool,
) {
unsafe {
ffi::rocksdb_options_set_bottommost_compression_options(
self.inner,
w_bits,
level,
strategy,
max_dict_bytes,
c_uchar::from(enabled),
);
}
}
/// Sets maximum size of training data passed to zstd's dictionary trainer. Using zstd's
/// dictionary trainer can achieve even better compression ratio improvements than using
/// `max_dict_bytes` alone.
///
/// The training data will be used to generate a dictionary of max_dict_bytes.
///
/// Default: 0.
pub fn set_zstd_max_train_bytes(&mut self, value: c_int) {
unsafe {
ffi::rocksdb_options_set_compression_options_zstd_max_train_bytes(self.inner, value);
}
}
/// Sets maximum size of training data passed to zstd's dictionary trainer
/// when compressing the bottom-most level. Using zstd's dictionary trainer
/// can achieve even better compression ratio improvements than using
/// `max_dict_bytes` alone.
///
/// The training data will be used to generate a dictionary of
/// `max_dict_bytes`.
///
/// Default: 0.
pub fn set_bottommost_zstd_max_train_bytes(&mut self, value: c_int, enabled: bool) {
unsafe {
ffi::rocksdb_options_set_bottommost_compression_options_zstd_max_train_bytes(
self.inner,
value,
c_uchar::from(enabled),
);
}
}
/// 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.
///
/// Default: 2 * 1024 * 1024 (2 MB)
pub fn set_compaction_readahead_size(&mut self, compaction_readahead_size: usize) {
unsafe {
ffi::rocksdb_options_compaction_readahead_size(self.inner, compaction_readahead_size);
}
}
/// Allow RocksDB to pick dynamic base of bytes for levels.
/// With this feature turned on, RocksDB will automatically adjust max bytes for each level.
/// The goal of this feature is to have lower bound on size amplification.
///
/// Default: false.
pub fn set_level_compaction_dynamic_level_bytes(&mut self, v: bool) {
unsafe {
ffi::rocksdb_options_set_level_compaction_dynamic_level_bytes(
self.inner,
c_uchar::from(v),
);
}
}
/// This option has different meanings for different compaction styles:
///
/// Leveled: files older than `periodic_compaction_seconds` will be picked up
/// for compaction and will be re-written to the same level as they were
/// before.
///
/// FIFO: not supported. Setting this option has no effect for FIFO compaction.
///
/// Universal: when there are files older than `periodic_compaction_seconds`,
/// rocksdb will try to do as large a compaction as possible including the
/// last level. Such compaction is only skipped if only last level is to
/// be compacted and no file in last level is older than
/// `periodic_compaction_seconds`. See more in
/// UniversalCompactionBuilder::PickPeriodicCompaction().
/// For backward compatibility, the effective value of this option takes
/// into account the value of option `ttl`. The logic is as follows:
/// - both options are set to 30 days if they have the default value.
/// - if both options are zero, zero is picked. Otherwise, we take the min
/// value among non-zero options values (i.e. takes the stricter limit).
///
/// One main use of the feature is to make sure a file goes through compaction
/// filters periodically. Users can also use the feature to clear up SST
/// files using old format.
///
/// A file's age is computed by looking at file_creation_time or creation_time
/// table properties in order, if they have valid non-zero values; if not, the
/// age is based on the file's last modified time (given by the underlying
/// Env).
///
/// This option only supports block based table format for any compaction
/// style.
///
/// unit: seconds. Ex: 7 days = 7 * 24 * 60 * 60
///
/// Values:
/// 0: Turn off Periodic compactions.
/// UINT64_MAX - 1 (0xfffffffffffffffe) is special flag to allow RocksDB to
/// pick default.
///
/// Default: 30 days if using block based table format + compaction filter +
/// leveled compaction or block based table format + universal compaction.
/// 0 (disabled) otherwise.
///
pub fn set_periodic_compaction_seconds(&mut self, secs: u64) {
unsafe {
ffi::rocksdb_options_set_periodic_compaction_seconds(self.inner, secs);
}
}
pub fn set_merge_operator_associative<F: MergeFn + Clone>(
&mut self,
name: impl CStrLike,
full_merge_fn: F,
) {
let cb = Box::new(MergeOperatorCallback {
name: name.into_c_string().unwrap(),
full_merge_fn: full_merge_fn.clone(),
partial_merge_fn: full_merge_fn,
});
unsafe {
let mo = ffi::rocksdb_mergeoperator_create(
Box::into_raw(cb).cast::<c_void>(),
Some(merge_operator::destructor_callback::<F, F>),
Some(full_merge_callback::<F, F>),
Some(partial_merge_callback::<F, F>),
Some(merge_operator::delete_callback),
Some(merge_operator::name_callback::<F, F>),
);
ffi::rocksdb_options_set_merge_operator(self.inner, mo);
}
}
pub fn set_merge_operator<F: MergeFn, PF: MergeFn>(
&mut self,
name: impl CStrLike,
full_merge_fn: F,
partial_merge_fn: PF,
) {
let cb = Box::new(MergeOperatorCallback {
name: name.into_c_string().unwrap(),
full_merge_fn,
partial_merge_fn,
});
unsafe {
let mo = ffi::rocksdb_mergeoperator_create(
Box::into_raw(cb).cast::<c_void>(),
Some(merge_operator::destructor_callback::<F, PF>),
Some(full_merge_callback::<F, PF>),
Some(partial_merge_callback::<F, PF>),
Some(merge_operator::delete_callback),
Some(merge_operator::name_callback::<F, PF>),
);
ffi::rocksdb_options_set_merge_operator(self.inner, mo);
}
}
#[deprecated(
since = "0.5.0",
note = "add_merge_operator has been renamed to set_merge_operator"
)]
pub fn add_merge_operator<F: MergeFn + Clone>(&mut self, name: &str, merge_fn: F) {
self.set_merge_operator_associative(name, merge_fn);
}
/// Sets a compaction filter used to determine if entries should be kept, changed,
/// or removed during compaction.
///
/// An example use case is to remove entries with an expired TTL.
///
/// If you take a snapshot of the database, only values written since the last
/// snapshot will be passed through the compaction filter.
///
/// If multi-threaded compaction is used, `filter_fn` may be called multiple times
/// simultaneously.
pub fn set_compaction_filter<F>(&mut self, name: impl CStrLike, filter_fn: F)
where
F: CompactionFilterFn + Send + 'static,
{
let cb = Box::new(CompactionFilterCallback {
name: name.into_c_string().unwrap(),
filter_fn,
});
unsafe {
let cf = ffi::rocksdb_compactionfilter_create(
Box::into_raw(cb).cast::<c_void>(),
Some(compaction_filter::destructor_callback::<CompactionFilterCallback<F>>),
Some(compaction_filter::filter_callback::<CompactionFilterCallback<F>>),
Some(compaction_filter::name_callback::<CompactionFilterCallback<F>>),
);
ffi::rocksdb_options_set_compaction_filter(self.inner, cf);
}
}
/// 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 set_compaction_filter_factory<F>(&mut self, factory: F)
where
F: CompactionFilterFactory + 'static,
{
let factory = Box::new(factory);
unsafe {
let cff = ffi::rocksdb_compactionfilterfactory_create(
Box::into_raw(factory).cast::<c_void>(),
Some(compaction_filter_factory::destructor_callback::<F>),
Some(compaction_filter_factory::create_compaction_filter_callback::<F>),
Some(compaction_filter_factory::name_callback::<F>),
);
ffi::rocksdb_options_set_compaction_filter_factory(self.inner, cff);
}
}
/// Sets the comparator used to define the order of keys in the table.
/// Default: a comparator that uses lexicographic byte-wise ordering
///
/// 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 set_comparator(&mut self, name: impl CStrLike, compare_fn: Box<CompareFn>) {
let cb = Box::new(ComparatorCallback {
name: name.into_c_string().unwrap(),
f: compare_fn,
});
unsafe {
let cmp = ffi::rocksdb_comparator_create(
Box::into_raw(cb).cast::<c_void>(),
Some(comparator::destructor_callback),
Some(comparator::compare_callback),
Some(comparator::name_callback),
);
ffi::rocksdb_options_set_comparator(self.inner, cmp);
}
}
pub fn set_prefix_extractor(&mut self, prefix_extractor: SliceTransform) {
unsafe {
ffi::rocksdb_options_set_prefix_extractor(self.inner, prefix_extractor.inner);
}
}
// 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(&mut self, block_cache_size_mb: u64) {
unsafe {
ffi::rocksdb_options_optimize_for_point_lookup(self.inner, block_cache_size_mb);
}
}
/// Sets the optimize_filters_for_hits flag
///
/// Default: `false`
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut opts = Options::default();
/// opts.set_optimize_filters_for_hits(true);
/// ```
pub fn set_optimize_filters_for_hits(&mut self, optimize_for_hits: bool) {
unsafe {
ffi::rocksdb_options_set_optimize_filters_for_hits(
self.inner,
c_int::from(optimize_for_hits),
);
}
}
/// Sets the periodicity when obsolete files get deleted.
///
/// The files that get out of scope by compaction
/// process will still get automatically delete on every compaction,
/// regardless of this setting.
///
/// Default: 6 hours
pub fn set_delete_obsolete_files_period_micros(&mut self, micros: u64) {
unsafe {
ffi::rocksdb_options_set_delete_obsolete_files_period_micros(self.inner, micros);
}
}
/// Prepare the DB 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(&mut self) {
unsafe {
ffi::rocksdb_options_prepare_for_bulk_load(self.inner);
}
}
/// Sets the 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`
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut opts = Options::default();
/// opts.set_max_open_files(10);
/// ```
pub fn set_max_open_files(&mut self, nfiles: c_int) {
unsafe {
ffi::rocksdb_options_set_max_open_files(self.inner, nfiles);
}
}
/// 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 set_max_file_opening_threads(&mut self, nthreads: c_int) {
unsafe {
ffi::rocksdb_options_set_max_file_opening_threads(self.inner, nthreads);
}
}
/// By default, writes to stable storage use fdatasync (on platforms
/// where this function is available). If this option is true,
/// fsync is used instead.
///
/// fsync and fdatasync are equally safe for our purposes and fdatasync is
/// faster, so it is rarely necessary to set this option. It is provided
/// as a workaround for kernel/filesystem bugs, such as one that affected
/// fdatasync with ext4 in kernel versions prior to 3.7.
///
/// Default: `false`
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut opts = Options::default();
/// opts.set_use_fsync(true);
/// ```
pub fn set_use_fsync(&mut self, useit: bool) {
unsafe {
ffi::rocksdb_options_set_use_fsync(self.inner, c_int::from(useit));
}
}
/// Specifies the absolute 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.
///
/// Default: empty
pub fn set_db_log_dir<P: AsRef<Path>>(&mut self, path: P) {
let p = to_cpath(path).unwrap();
unsafe {
ffi::rocksdb_options_set_db_log_dir(self.inner, p.as_ptr());
}
}
/// Specifies the log level.
/// Consider the `LogLevel` enum for a list of possible levels.
///
/// Default: Info
///
/// # Examples
///
/// ```
/// use rocksdb::{Options, LogLevel};
///
/// let mut opts = Options::default();
/// opts.set_log_level(LogLevel::Warn);
/// ```
pub fn set_log_level(&mut self, level: LogLevel) {
unsafe {
ffi::rocksdb_options_set_info_log_level(self.inner, level as c_int);
}
}
/// 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
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut opts = Options::default();
/// opts.set_bytes_per_sync(1024 * 1024);
/// ```
pub fn set_bytes_per_sync(&mut self, nbytes: u64) {
unsafe {
ffi::rocksdb_options_set_bytes_per_sync(self.inner, nbytes);
}
}
/// Same as bytes_per_sync, but applies to WAL files.
///
/// Default: 0, turned off
///
/// Dynamically changeable through SetDBOptions() API.
pub fn set_wal_bytes_per_sync(&mut self, nbytes: u64) {
unsafe {
ffi::rocksdb_options_set_wal_bytes_per_sync(self.inner, nbytes);
}
}
/// Sets 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)
///
/// Dynamically changeable through SetDBOptions() API.
pub fn set_writable_file_max_buffer_size(&mut self, nbytes: u64) {
unsafe {
ffi::rocksdb_options_set_writable_file_max_buffer_size(self.inner, nbytes);
}
}
/// 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
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut opts = Options::default();
/// opts.set_allow_concurrent_memtable_write(false);
/// ```
pub fn set_allow_concurrent_memtable_write(&mut self, allow: bool) {
unsafe {
ffi::rocksdb_options_set_allow_concurrent_memtable_write(
self.inner,
c_uchar::from(allow),
);
}
}
/// 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 set_enable_write_thread_adaptive_yield(&mut self, enabled: bool) {
unsafe {
ffi::rocksdb_options_set_enable_write_thread_adaptive_yield(
self.inner,
c_uchar::from(enabled),
);
}
}
/// Specifies whether an iteration->Next() sequentially skips over keys with the same user-key or not.
///
/// This number specifies the number of keys (with the same userkey)
/// that will be sequentially skipped before a reseek is issued.
///
/// Default: 8
pub fn set_max_sequential_skip_in_iterations(&mut self, num: u64) {
unsafe {
ffi::rocksdb_options_set_max_sequential_skip_in_iterations(self.inner, num);
}
}
/// Enable direct I/O mode for reading
/// 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 read from the disk will not be cached or
/// buffered. The hardware buffer of the devices may however still
/// be used. Memory mapped files are not impacted by these parameters.
///
/// Default: false
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut opts = Options::default();
/// opts.set_use_direct_reads(true);
/// ```
pub fn set_use_direct_reads(&mut self, enabled: bool) {
unsafe {
ffi::rocksdb_options_set_use_direct_reads(self.inner, c_uchar::from(enabled));
}
}
/// Enable direct I/O mode for flush and compaction
///
/// Files will be opened in "direct I/O" mode
/// which means that data written to the disk will not be cached or
/// buffered. The hardware buffer of the devices may however still
/// be used. Memory mapped files are not impacted by these parameters.
/// they may or may not improve performance depending on the use case
///
/// Default: false
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut opts = Options::default();
/// opts.set_use_direct_io_for_flush_and_compaction(true);
/// ```
pub fn set_use_direct_io_for_flush_and_compaction(&mut self, enabled: bool) {
unsafe {
ffi::rocksdb_options_set_use_direct_io_for_flush_and_compaction(
self.inner,
c_uchar::from(enabled),
);
}
}
/// Enable/dsiable child process inherit open files.
///
/// Default: true
pub fn set_is_fd_close_on_exec(&mut self, enabled: bool) {
unsafe {
ffi::rocksdb_options_set_is_fd_close_on_exec(self.inner, c_uchar::from(enabled));
}
}
/// Hints to the OS that it should not buffer disk I/O. Enabling this
/// parameter may improve performance but increases pressure on the
/// system cache.
///
/// The exact behavior of this parameter is platform dependent.
///
/// On POSIX systems, after RocksDB reads data from disk it will
/// mark the pages as "unneeded". The operating system may - or may not
/// - evict these pages from memory, reducing pressure on the system
/// cache. If the disk block is requested again this can result in
/// additional disk I/O.
///
/// On WINDOWS systems, files will be opened in "unbuffered I/O" mode
/// which means that data read 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 this parameter.
///
/// Default: true
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut opts = Options::default();
/// #[allow(deprecated)]
/// opts.set_allow_os_buffer(false);
/// ```
#[deprecated(
since = "0.7.0",
note = "replaced with set_use_direct_reads/set_use_direct_io_for_flush_and_compaction methods"
)]
pub fn set_allow_os_buffer(&mut self, is_allow: bool) {
self.set_use_direct_reads(!is_allow);
self.set_use_direct_io_for_flush_and_compaction(!is_allow);
}
/// Sets the number of shards used for table cache.
///
/// Default: `6`
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut opts = Options::default();
/// opts.set_table_cache_num_shard_bits(4);
/// ```
pub fn set_table_cache_num_shard_bits(&mut self, nbits: c_int) {
unsafe {
ffi::rocksdb_options_set_table_cache_numshardbits(self.inner, nbits);
}
}
/// 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 set_target_file_size_multiplier(&mut self, multiplier: i32) {
unsafe {
ffi::rocksdb_options_set_target_file_size_multiplier(self.inner, multiplier as c_int);
}
}
/// Sets 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`
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut opts = Options::default();
/// opts.set_min_write_buffer_number(2);
/// ```
pub fn set_min_write_buffer_number(&mut self, nbuf: c_int) {
unsafe {
ffi::rocksdb_options_set_min_write_buffer_number_to_merge(self.inner, nbuf);
}
}
/// Sets 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`
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut opts = Options::default();
/// opts.set_max_write_buffer_number(4);
/// ```
pub fn set_max_write_buffer_number(&mut self, nbuf: c_int) {
unsafe {
ffi::rocksdb_options_set_max_write_buffer_number(self.inner, nbuf);
}
}
/// Sets the 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: `0x4000000` (64MiB)
///
/// Dynamically changeable through SetOptions() API
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut opts = Options::default();
/// opts.set_write_buffer_size(128 * 1024 * 1024);
/// ```
pub fn set_write_buffer_size(&mut self, size: usize) {
unsafe {
ffi::rocksdb_options_set_write_buffer_size(self.inner, size);
}
}
/// 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)
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut opts = Options::default();
/// opts.set_db_write_buffer_size(128 * 1024 * 1024);
/// ```
pub fn set_db_write_buffer_size(&mut self, size: usize) {
unsafe {
ffi::rocksdb_options_set_db_write_buffer_size(self.inner, size);
}
}
/// 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: `0x10000000` (256MiB).
///
/// Dynamically changeable through SetOptions() API
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut opts = Options::default();
/// opts.set_max_bytes_for_level_base(512 * 1024 * 1024);
/// ```
pub fn set_max_bytes_for_level_base(&mut self, size: u64) {
unsafe {
ffi::rocksdb_options_set_max_bytes_for_level_base(self.inner, size);
}
}
/// Default: `10`
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut opts = Options::default();
/// opts.set_max_bytes_for_level_multiplier(4.0);
/// ```
pub fn set_max_bytes_for_level_multiplier(&mut self, mul: f64) {
unsafe {
ffi::rocksdb_options_set_max_bytes_for_level_multiplier(self.inner, mul);
}
}
/// The 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.
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut opts = Options::default();
/// opts.set_max_manifest_file_size(20 * 1024 * 1024);
/// ```
pub fn set_max_manifest_file_size(&mut self, size: usize) {
unsafe {
ffi::rocksdb_options_set_max_manifest_file_size(self.inner, size);
}
}
/// Sets the 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: `0x4000000` (64MiB)
///
/// Dynamically changeable through SetOptions() API
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut opts = Options::default();
/// opts.set_target_file_size_base(128 * 1024 * 1024);
/// ```
pub fn set_target_file_size_base(&mut self, size: u64) {
unsafe {
ffi::rocksdb_options_set_target_file_size_base(self.inner, size);
}
}
/// Sets 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`
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut opts = Options::default();
/// opts.set_min_write_buffer_number_to_merge(2);
/// ```
pub fn set_min_write_buffer_number_to_merge(&mut self, to_merge: c_int) {
unsafe {
ffi::rocksdb_options_set_min_write_buffer_number_to_merge(self.inner, to_merge);
}
}
/// Sets the 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
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut opts = Options::default();
/// opts.set_level_zero_file_num_compaction_trigger(8);
/// ```
pub fn set_level_zero_file_num_compaction_trigger(&mut self, n: c_int) {
unsafe {
ffi::rocksdb_options_set_level0_file_num_compaction_trigger(self.inner, n);
}
}
/// Sets the 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
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut opts = Options::default();
/// opts.set_level_zero_slowdown_writes_trigger(10);
/// ```
pub fn set_level_zero_slowdown_writes_trigger(&mut self, n: c_int) {
unsafe {
ffi::rocksdb_options_set_level0_slowdown_writes_trigger(self.inner, n);
}
}
/// Sets the maximum number of level-0 files. We stop writes at this point.
///
/// Default: `24`
///
/// Dynamically changeable through SetOptions() API
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut opts = Options::default();
/// opts.set_level_zero_stop_writes_trigger(48);
/// ```
pub fn set_level_zero_stop_writes_trigger(&mut self, n: c_int) {
unsafe {
ffi::rocksdb_options_set_level0_stop_writes_trigger(self.inner, n);
}
}
/// Sets the compaction style.
///
/// Default: DBCompactionStyle::Level
///
/// # Examples
///
/// ```
/// use rocksdb::{Options, DBCompactionStyle};
///
/// let mut opts = Options::default();
/// opts.set_compaction_style(DBCompactionStyle::Universal);
/// ```
pub fn set_compaction_style(&mut self, style: DBCompactionStyle) {
unsafe {
ffi::rocksdb_options_set_compaction_style(self.inner, style as c_int);
}
}
/// Sets the options needed to support Universal Style compactions.
pub fn set_universal_compaction_options(&mut self, uco: &UniversalCompactOptions) {
unsafe {
ffi::rocksdb_options_set_universal_compaction_options(self.inner, uco.inner);
}
}
/// Sets the options for FIFO compaction style.
pub fn set_fifo_compaction_options(&mut self, fco: &FifoCompactOptions) {
unsafe {
ffi::rocksdb_options_set_fifo_compaction_options(self.inner, fco.inner);
}
}
/// Sets unordered_write to true trades higher write throughput with
/// relaxing the immutability guarantee of snapshots. This violates the
/// repeatability one expects from ::Get from a snapshot, as well as
/// ::MultiGet and Iterator's consistent-point-in-time view property.
/// If the application cannot tolerate the relaxed guarantees, it can implement
/// its own mechanisms to work around that and yet benefit from the higher
/// throughput. Using TransactionDB with WRITE_PREPARED write policy and
/// two_write_queues=true is one way to achieve immutable snapshots despite
/// unordered_write.
///
/// By default, i.e., when it is false, rocksdb does not advance the sequence
/// number for new snapshots unless all the writes with lower sequence numbers
/// are already finished. This provides the immutability that we except from
/// snapshots. Moreover, since Iterator and MultiGet internally depend on
/// snapshots, the snapshot immutability results into Iterator and MultiGet
/// offering consistent-point-in-time view. If set to true, although
/// Read-Your-Own-Write property is still provided, the snapshot immutability
/// property is relaxed: the writes issued after the snapshot is obtained (with
/// larger sequence numbers) will be still not visible to the reads from that
/// snapshot, however, there still might be pending writes (with lower sequence
/// number) that will change the state visible to the snapshot after they are
/// landed to the memtable.
///
/// Default: false
pub fn set_unordered_write(&mut self, unordered: bool) {
unsafe {
ffi::rocksdb_options_set_unordered_write(self.inner, c_uchar::from(unordered));
}
}
/// Sets 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 set_max_subcompactions(&mut self, num: u32) {
unsafe {
ffi::rocksdb_options_set_max_subcompactions(self.inner, num);
}
}
/// Sets maximum number of concurrent background jobs
/// (compactions and flushes).
///
/// Default: 2
///
/// Dynamically changeable through SetDBOptions() API.
pub fn set_max_background_jobs(&mut self, jobs: c_int) {
unsafe {
ffi::rocksdb_options_set_max_background_jobs(self.inner, jobs);
}
}
/// Sets the maximum number of concurrent background compaction jobs, submitted to
/// the default LOW priority thread pool.
/// We first try to schedule compactions based on
/// `base_background_compactions`. If the compaction cannot catch up , we
/// will increase number of compaction threads up to
/// `max_background_compactions`.
///
/// If you're increasing this, also consider increasing number of threads in
/// LOW priority thread pool. For more information, see
/// Env::SetBackgroundThreads
///
/// Default: `1`
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut opts = Options::default();
/// #[allow(deprecated)]
/// opts.set_max_background_compactions(2);
/// ```
#[deprecated(
since = "0.15.0",
note = "RocksDB automatically decides this based on the value of max_background_jobs"
)]
pub fn set_max_background_compactions(&mut self, n: c_int) {
unsafe {
ffi::rocksdb_options_set_max_background_compactions(self.inner, n);
}
}
/// Sets the maximum number of concurrent background memtable flush jobs, submitted to
/// the HIGH priority thread pool.
///
/// By default, all background jobs (major compaction and memtable flush) go
/// to the LOW priority pool. If this option is set to a positive number,
/// memtable flush jobs will be submitted to the HIGH priority pool.
/// It is important when the same Env is shared by multiple db instances.
/// Without a separate pool, long running major compaction jobs could
/// potentially block memtable flush jobs of other db instances, leading to
/// unnecessary Put stalls.
///
/// If you're increasing this, also consider increasing number of threads in
/// HIGH priority thread pool. For more information, see
/// Env::SetBackgroundThreads
///
/// Default: `1`
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut opts = Options::default();
/// #[allow(deprecated)]
/// opts.set_max_background_flushes(2);
/// ```
#[deprecated(
since = "0.15.0",
note = "RocksDB automatically decides this based on the value of max_background_jobs"
)]
pub fn set_max_background_flushes(&mut self, n: c_int) {
unsafe {
ffi::rocksdb_options_set_max_background_flushes(self.inner, n);
}
}
/// Disables automatic compactions. Manual compactions can still
/// be issued on this column family
///
/// Default: `false`
///
/// Dynamically changeable through SetOptions() API
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut opts = Options::default();
/// opts.set_disable_auto_compactions(true);
/// ```
pub fn set_disable_auto_compactions(&mut self, disable: bool) {
unsafe {
ffi::rocksdb_options_set_disable_auto_compactions(self.inner, c_int::from(disable));
}
}
/// SetMemtableHugePageSize sets the page size for huge page for
/// 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:
/// 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 set_memtable_huge_page_size(&mut self, size: size_t) {
unsafe {
ffi::rocksdb_options_set_memtable_huge_page_size(self.inner, size);
}
}
/// Sets the 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)
pub fn set_max_successive_merges(&mut self, num: usize) {
unsafe {
ffi::rocksdb_options_set_max_successive_merges(self.inner, num);
}
}
/// 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 the max number of cache lines each
/// bloom filter check can touch.
///
/// This optimization is turned off when set to 0. The number should never
/// be greater than number of probes. This option can boost performance
/// for in-memory workload but should use with care since it can cause
/// higher false positive rate.
///
/// Default: 0
pub fn set_bloom_locality(&mut self, v: u32) {
unsafe {
ffi::rocksdb_options_set_bloom_locality(self.inner, v);
}
}
/// Enable/disable thread-safe inplace updates.
///
/// Requires updates if
/// * key exists in current memtable
/// * new sizeof(new_value) <= sizeof(old_value)
/// * old_value for that key is a put i.e. kTypeValue
///
/// Default: false.
pub fn set_inplace_update_support(&mut self, enabled: bool) {
unsafe {
ffi::rocksdb_options_set_inplace_update_support(self.inner, c_uchar::from(enabled));
}
}
/// Sets the number of locks used for inplace update.
///
/// Default: 10000 when inplace_update_support = true, otherwise 0.
pub fn set_inplace_update_locks(&mut self, num: usize) {
unsafe {
ffi::rocksdb_options_set_inplace_update_num_locks(self.inner, num);
}
}
/// 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 set_max_bytes_for_level_multiplier_additional(&mut self, level_values: &[i32]) {
let count = level_values.len();
unsafe {
ffi::rocksdb_options_set_max_bytes_for_level_multiplier_additional(
self.inner,
level_values.as_ptr() as *mut c_int,
count,
);
}
}
/// If true, then DB::Open() will not fetch and check sizes of all sst files.
/// This may significantly speed up startup if there are many sst files,
/// especially when using non-default Env with expensive GetFileSize().
/// We'll still check that all required sst files exist.
/// If paranoid_checks is false, this option is ignored, and sst files are
/// not checked at all.
///
/// Default: false
pub fn set_skip_checking_sst_file_sizes_on_db_open(&mut self, value: bool) {
unsafe {
ffi::rocksdb_options_set_skip_checking_sst_file_sizes_on_db_open(
self.inner,
c_uchar::from(value),
);
}
}
/// The total maximum size(bytes) of write buffers to maintain in memory
/// including copies of buffers that have already been flushed. This parameter
/// only affects trimming of flushed buffers and does not affect flushing.
/// This controls the maximum amount of write history that will be available
/// in memory for conflict checking when Transactions are used. The actual
/// size of write history (flushed Memtables) might be higher than this limit
/// if further trimming will reduce write history total size below this
/// limit. For example, if max_write_buffer_size_to_maintain is set to 64MB,
/// and there are three flushed Memtables, with sizes of 32MB, 20MB, 20MB.
/// Because trimming the next Memtable of size 20MB will reduce total memory
/// usage to 52MB which is below the limit, RocksDB will stop trimming.
///
/// 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 * write_buffer_size' will be used.
///
/// Default:
/// If using a TransactionDB/OptimisticTransactionDB, the default value will
/// be set to the value of 'max_write_buffer_number * write_buffer_size'
/// if it is not explicitly set by the user. Otherwise, the default is 0.
pub fn set_max_write_buffer_size_to_maintain(&mut self, size: i64) {
unsafe {
ffi::rocksdb_options_set_max_write_buffer_size_to_maintain(self.inner, size);
}
}
/// By default, a single write thread queue is maintained. The thread gets
/// to the head of the queue becomes write batch group leader and responsible
/// for writing to WAL and memtable for the batch group.
///
/// If enable_pipelined_write is true, separate write thread queue is
/// maintained for WAL write and memtable write. A write thread first enter WAL
/// writer queue and then memtable writer queue. Pending thread on the WAL
/// writer queue thus only have to wait for previous writers to finish their
/// WAL writing but not the memtable writing. Enabling the feature may improve
/// write throughput and reduce latency of the prepare phase of two-phase
/// commit.
///
/// Default: false
pub fn set_enable_pipelined_write(&mut self, value: bool) {
unsafe {
ffi::rocksdb_options_set_enable_pipelined_write(self.inner, c_uchar::from(value));
}
}
/// Defines the underlying memtable implementation.
/// See official [wiki](https://github.com/facebook/rocksdb/wiki/MemTable) for more information.
/// Defaults to using a skiplist.
///
/// # Examples
///
/// ```
/// use rocksdb::{Options, MemtableFactory};
/// let mut opts = Options::default();
/// let factory = MemtableFactory::HashSkipList {
/// bucket_count: 1_000_000,
/// height: 4,
/// branching_factor: 4,
/// };
///
/// opts.set_allow_concurrent_memtable_write(false);
/// opts.set_memtable_factory(factory);
/// ```
pub fn set_memtable_factory(&mut self, factory: MemtableFactory) {
match factory {
MemtableFactory::Vector => unsafe {
ffi::rocksdb_options_set_memtable_vector_rep(self.inner);
},
MemtableFactory::HashSkipList {
bucket_count,
height,
branching_factor,
} => unsafe {
ffi::rocksdb_options_set_hash_skip_list_rep(
self.inner,
bucket_count,
height,
branching_factor,
);
},
MemtableFactory::HashLinkList { bucket_count } => unsafe {
ffi::rocksdb_options_set_hash_link_list_rep(self.inner, bucket_count);
},
};
}
pub fn set_block_based_table_factory(&mut self, factory: &BlockBasedOptions) {
unsafe {
ffi::rocksdb_options_set_block_based_table_factory(self.inner, factory.inner);
}
self.outlive.block_based = Some(factory.outlive.clone());
}
/// Sets the table factory to a CuckooTableFactory (the default table
/// factory is a block-based table factory that provides a default
/// implementation of TableBuilder and TableReader with default
/// BlockBasedTableOptions).
/// See official [wiki](https://github.com/facebook/rocksdb/wiki/CuckooTable-Format) for more information on this table format.
/// # Examples
///
/// ```
/// use rocksdb::{Options, CuckooTableOptions};
///
/// let mut opts = Options::default();
/// let mut factory_opts = CuckooTableOptions::default();
/// factory_opts.set_hash_ratio(0.8);
/// factory_opts.set_max_search_depth(20);
/// factory_opts.set_cuckoo_block_size(10);
/// factory_opts.set_identity_as_first_hash(true);
/// factory_opts.set_use_module_hash(false);
///
/// opts.set_cuckoo_table_factory(&factory_opts);
/// ```
pub fn set_cuckoo_table_factory(&mut self, factory: &CuckooTableOptions) {
unsafe {
ffi::rocksdb_options_set_cuckoo_table_factory(self.inner, factory.inner);
}
}
// 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.
/// Sets the factory as plain table.
/// See official [wiki](https://github.com/facebook/rocksdb/wiki/PlainTable-Format) for more
/// information.
///
/// # Examples
///
/// ```
/// use rocksdb::{KeyEncodingType, Options, PlainTableFactoryOptions};
///
/// let mut opts = Options::default();
/// let factory_opts = PlainTableFactoryOptions {
/// user_key_length: 0,
/// bloom_bits_per_key: 20,
/// hash_table_ratio: 0.75,
/// index_sparseness: 16,
/// huge_page_tlb_size: 0,
/// encoding_type: KeyEncodingType::Plain,
/// full_scan_mode: false,
/// store_index_in_file: false,
/// };
///
/// opts.set_plain_table_factory(&factory_opts);
/// ```
pub fn set_plain_table_factory(&mut self, options: &PlainTableFactoryOptions) {
unsafe {
ffi::rocksdb_options_set_plain_table_factory(
self.inner,
options.user_key_length,
options.bloom_bits_per_key,
options.hash_table_ratio,
options.index_sparseness,
options.huge_page_tlb_size,
options.encoding_type as c_char,
c_uchar::from(options.full_scan_mode),
c_uchar::from(options.store_index_in_file),
);
}
}
/// Sets the start level to use compression.
pub fn set_min_level_to_compress(&mut self, lvl: c_int) {
unsafe {
ffi::rocksdb_options_set_min_level_to_compress(self.inner, lvl);
}
}
/// Measure IO stats in compactions and flushes, if `true`.
///
/// Default: `false`
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut opts = Options::default();
/// opts.set_report_bg_io_stats(true);
/// ```
pub fn set_report_bg_io_stats(&mut self, enable: bool) {
unsafe {
ffi::rocksdb_options_set_report_bg_io_stats(self.inner, c_int::from(enable));
}
}
/// 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).
///
/// Default: `0`
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut opts = Options::default();
/// // Set max total wal size to 1G.
/// opts.set_max_total_wal_size(1 << 30);
/// ```
pub fn set_max_total_wal_size(&mut self, size: u64) {
unsafe {
ffi::rocksdb_options_set_max_total_wal_size(self.inner, size);
}
}
/// Recovery mode to control the consistency while replaying WAL.
///
/// Default: DBRecoveryMode::PointInTime
///
/// # Examples
///
/// ```
/// use rocksdb::{Options, DBRecoveryMode};
///
/// let mut opts = Options::default();
/// opts.set_wal_recovery_mode(DBRecoveryMode::AbsoluteConsistency);
/// ```
pub fn set_wal_recovery_mode(&mut self, mode: DBRecoveryMode) {
unsafe {
ffi::rocksdb_options_set_wal_recovery_mode(self.inner, mode as c_int);
}
}
pub fn enable_statistics(&mut self) {
unsafe {
ffi::rocksdb_options_enable_statistics(self.inner);
}
}
pub fn get_statistics(&self) -> Option<String> {
unsafe {
let value = ffi::rocksdb_options_statistics_get_string(self.inner);
if value.is_null() {
return None;
}
// Must have valid UTF-8 format.
let s = CStr::from_ptr(value).to_str().unwrap().to_owned();
ffi::rocksdb_free(value as *mut c_void);
Some(s)
}
}
/// StatsLevel can be used to reduce statistics overhead by skipping certain
/// types of stats in the stats collection process.
pub fn set_statistics_level(&self, level: StatsLevel) {
unsafe { ffi::rocksdb_options_set_statistics_level(self.inner, level as c_int) }
}
/// Returns the value of cumulative db counters if stat collection is enabled.
pub fn get_ticker_count(&self, ticker: Ticker) -> u64 {
unsafe { ffi::rocksdb_options_statistics_get_ticker_count(self.inner, ticker as u32) }
}
/// Gets Histogram data from collected db stats. Requires stats to be enabled.
pub fn get_histogram_data(&self, histogram: Histogram) -> HistogramData {
unsafe {
let data = HistogramData::default();
ffi::rocksdb_options_statistics_get_histogram_data(
self.inner,
histogram as u32,
data.inner,
);
data
}
}
/// If not zero, dump `rocksdb.stats` to LOG every `stats_dump_period_sec`.
///
/// Default: `600` (10 mins)
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut opts = Options::default();
/// opts.set_stats_dump_period_sec(300);
/// ```
pub fn set_stats_dump_period_sec(&mut self, period: c_uint) {
unsafe {
ffi::rocksdb_options_set_stats_dump_period_sec(self.inner, period);
}
}
/// If not zero, dump rocksdb.stats to RocksDB to LOG every `stats_persist_period_sec`.
///
/// Default: `600` (10 mins)
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut opts = Options::default();
/// opts.set_stats_persist_period_sec(5);
/// ```
pub fn set_stats_persist_period_sec(&mut self, period: c_uint) {
unsafe {
ffi::rocksdb_options_set_stats_persist_period_sec(self.inner, period);
}
}
/// When set to true, reading SST files will opt out of the filesystem's
/// readahead. Setting this to false may improve sequential iteration
/// performance.
///
/// Default: `true`
pub fn set_advise_random_on_open(&mut self, advise: bool) {
unsafe {
ffi::rocksdb_options_set_advise_random_on_open(self.inner, c_uchar::from(advise));
}
}
/// Specifies the file access pattern once a compaction is started.
///
/// It will be applied to all input files of a compaction.
///
/// Default: Normal
pub fn set_access_hint_on_compaction_start(&mut self, pattern: AccessHint) {
unsafe {
ffi::rocksdb_options_set_access_hint_on_compaction_start(self.inner, pattern as c_int);
}
}
/// Enable/disable 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 set_use_adaptive_mutex(&mut self, enabled: bool) {
unsafe {
ffi::rocksdb_options_set_use_adaptive_mutex(self.inner, c_uchar::from(enabled));
}
}
/// Sets the number of levels for this database.
pub fn set_num_levels(&mut self, n: c_int) {
unsafe {
ffi::rocksdb_options_set_num_levels(self.inner, n);
}
}
/// When a `prefix_extractor` is defined through `opts.set_prefix_extractor` this
/// creates a prefix bloom filter for each memtable with the size of
/// `write_buffer_size * memtable_prefix_bloom_ratio` (capped at 0.25).
///
/// Default: `0`
///
/// # Examples
///
/// ```
/// use rocksdb::{Options, SliceTransform};
///
/// let mut opts = Options::default();
/// let transform = SliceTransform::create_fixed_prefix(10);
/// opts.set_prefix_extractor(transform);
/// opts.set_memtable_prefix_bloom_ratio(0.2);
/// ```
pub fn set_memtable_prefix_bloom_ratio(&mut self, ratio: f64) {
unsafe {
ffi::rocksdb_options_set_memtable_prefix_bloom_size_ratio(self.inner, ratio);
}
}
/// Sets the maximum number of bytes in all compacted files.
/// 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: target_file_size_base * 25
pub fn set_max_compaction_bytes(&mut self, nbytes: u64) {
unsafe {
ffi::rocksdb_options_set_max_compaction_bytes(self.inner, nbytes);
}
}
/// Specifies the absolute path of the directory the
/// write-ahead log (WAL) should be written to.
///
/// Default: same directory as the database
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut opts = Options::default();
/// opts.set_wal_dir("/path/to/dir");
/// ```
pub fn set_wal_dir<P: AsRef<Path>>(&mut self, path: P) {
let p = to_cpath(path).unwrap();
unsafe {
ffi::rocksdb_options_set_wal_dir(self.inner, p.as_ptr());
}
}
/// Sets the WAL ttl in seconds.
///
/// The following two options 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 wall_size_limit_mb is 0, then
/// WAL files will be checked every wal_ttl_seconds / 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.
///
/// Default: 0
pub fn set_wal_ttl_seconds(&mut self, secs: u64) {
unsafe {
ffi::rocksdb_options_set_WAL_ttl_seconds(self.inner, secs);
}
}
/// Sets the WAL size limit in MB.
///
/// If total size of WAL files is greater then wal_size_limit_mb,
/// they will be deleted starting with the earliest until size_limit is met.
///
/// Default: 0
pub fn set_wal_size_limit_mb(&mut self, size: u64) {
unsafe {
ffi::rocksdb_options_set_WAL_size_limit_MB(self.inner, size);
}
}
/// Sets the 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 set_manifest_preallocation_size(&mut self, size: usize) {
unsafe {
ffi::rocksdb_options_set_manifest_preallocation_size(self.inner, size);
}
}
/// 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 set_skip_stats_update_on_db_open(&mut self, skip: bool) {
unsafe {
ffi::rocksdb_options_set_skip_stats_update_on_db_open(self.inner, c_uchar::from(skip));
}
}
/// Specify the maximal number of info log files to be kept.
///
/// Default: 1000
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut options = Options::default();
/// options.set_keep_log_file_num(100);
/// ```
pub fn set_keep_log_file_num(&mut self, nfiles: usize) {
unsafe {
ffi::rocksdb_options_set_keep_log_file_num(self.inner, nfiles);
}
}
/// Allow the OS to mmap file for writing.
///
/// Default: false
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut options = Options::default();
/// options.set_allow_mmap_writes(true);
/// ```
pub fn set_allow_mmap_writes(&mut self, is_enabled: bool) {
unsafe {
ffi::rocksdb_options_set_allow_mmap_writes(self.inner, c_uchar::from(is_enabled));
}
}
/// Allow the OS to mmap file for reading sst tables.
///
/// Default: false
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut options = Options::default();
/// options.set_allow_mmap_reads(true);
/// ```
pub fn set_allow_mmap_reads(&mut self, is_enabled: bool) {
unsafe {
ffi::rocksdb_options_set_allow_mmap_reads(self.inner, c_uchar::from(is_enabled));
}
}
/// If enabled, WAL is not flushed automatically after each write. Instead it
/// relies on manual invocation of `DB::flush_wal()` to write the WAL buffer
/// to its file.
///
/// Default: false
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut options = Options::default();
/// options.set_manual_wal_flush(true);
/// ```
pub fn set_manual_wal_flush(&mut self, is_enabled: bool) {
unsafe {
ffi::rocksdb_options_set_manual_wal_flush(self.inner, c_uchar::from(is_enabled));
}
}
/// Guarantee that all column families are flushed together atomically.
/// This option applies to both manual flushes (`db.flush()`) and automatic
/// background flushes caused when memtables are filled.
///
/// Note that this is only useful when the WAL is disabled. When using the
/// WAL, writes are always consistent across column families.
///
/// Default: false
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut options = Options::default();
/// options.set_atomic_flush(true);
/// ```
pub fn set_atomic_flush(&mut self, atomic_flush: bool) {
unsafe {
ffi::rocksdb_options_set_atomic_flush(self.inner, c_uchar::from(atomic_flush));
}
}
/// Sets global cache for table-level rows.
///
/// Default: null (disabled)
/// Not supported in ROCKSDB_LITE mode!
pub fn set_row_cache(&mut self, cache: &Cache) {
unsafe {
ffi::rocksdb_options_set_row_cache(self.inner, cache.0.inner.as_ptr());
}
self.outlive.row_cache = Some(cache.clone());
}
/// Use to control write rate of flush and compaction. Flush has higher
/// priority than compaction.
/// If rate limiter is enabled, bytes_per_sync is set to 1MB by default.
///
/// Default: disable
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut options = Options::default();
/// options.set_ratelimiter(1024 * 1024, 100 * 1000, 10);
/// ```
pub fn set_ratelimiter(
&mut self,
rate_bytes_per_sec: i64,
refill_period_us: i64,
fairness: i32,
) {
unsafe {
let ratelimiter =
ffi::rocksdb_ratelimiter_create(rate_bytes_per_sec, refill_period_us, fairness);
// Since limiter is wrapped in shared_ptr, we don't need to
// call rocksdb_ratelimiter_destroy explicitly.
ffi::rocksdb_options_set_ratelimiter(self.inner, ratelimiter);
}
}
/// Sets 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` is equal to zero, all logs will
/// be written to one log file.
///
/// Default: 0
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut options = Options::default();
/// options.set_max_log_file_size(0);
/// ```
pub fn set_max_log_file_size(&mut self, size: usize) {
unsafe {
ffi::rocksdb_options_set_max_log_file_size(self.inner, size);
}
}
/// Sets the 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 set_log_file_time_to_roll(&mut self, secs: usize) {
unsafe {
ffi::rocksdb_options_set_log_file_time_to_roll(self.inner, secs);
}
}
/// Controls the recycling of log files.
///
/// If non-zero, previously written log files will be reused 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
///
/// # Examples
///
/// ```
/// use rocksdb::Options;
///
/// let mut options = Options::default();
/// options.set_recycle_log_file_num(5);
/// ```
pub fn set_recycle_log_file_num(&mut self, num: usize) {
unsafe {
ffi::rocksdb_options_set_recycle_log_file_num(self.inner, num);
}
}
/// Sets the threshold at which 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 set_soft_pending_compaction_bytes_limit(&mut self, limit: usize) {
unsafe {
ffi::rocksdb_options_set_soft_pending_compaction_bytes_limit(self.inner, limit);
}
}
/// Sets the bytes threshold at which all writes are stopped if estimated bytes needed to be compaction exceed
/// this threshold.
///
/// Default: 256GB
pub fn set_hard_pending_compaction_bytes_limit(&mut self, limit: usize) {
unsafe {
ffi::rocksdb_options_set_hard_pending_compaction_bytes_limit(self.inner, limit);
}
}
/// Sets the size of one block in arena memory allocation.
///
/// If <= 0, a proper value is automatically calculated (usually 1/10 of
/// writer_buffer_size).
///
/// Default: 0
pub fn set_arena_block_size(&mut self, size: usize) {
unsafe {
ffi::rocksdb_options_set_arena_block_size(self.inner, size);
}
}
/// If true, then print malloc stats together with rocksdb.stats when printing to LOG.
///
/// Default: false
pub fn set_dump_malloc_stats(&mut self, enabled: bool) {
unsafe {
ffi::rocksdb_options_set_dump_malloc_stats(self.inner, c_uchar::from(enabled));
}
}
/// Enable whole key bloom filter in memtable. Note this will only take effect
/// if memtable_prefix_bloom_size_ratio is not 0. Enabling whole key filtering
/// can potentially reduce CPU usage for point-look-ups.
///
/// Default: false (disable)
///
/// Dynamically changeable through SetOptions() API
pub fn set_memtable_whole_key_filtering(&mut self, whole_key_filter: bool) {
unsafe {
ffi::rocksdb_options_set_memtable_whole_key_filtering(
self.inner,
c_uchar::from(whole_key_filter),
);
}
}
/// Enable the use of key-value separation.
///
/// More details can be found here: [Integrated BlobDB](http://rocksdb.org/blog/2021/05/26/integrated-blob-db.html).
///
/// Default: false (disable)
///
/// Dynamically changeable through SetOptions() API
pub fn set_enable_blob_files(&mut self, val: bool) {
unsafe {
ffi::rocksdb_options_set_enable_blob_files(self.inner, u8::from(val));
}
}
/// Sets the minimum threshold value at or above which will be written
/// to blob files during flush or compaction.
///
/// Dynamically changeable through SetOptions() API
pub fn set_min_blob_size(&mut self, val: u64) {
unsafe {
ffi::rocksdb_options_set_min_blob_size(self.inner, val);
}
}
/// Sets the size limit for blob files.
///
/// Dynamically changeable through SetOptions() API
pub fn set_blob_file_size(&mut self, val: u64) {
unsafe {
ffi::rocksdb_options_set_blob_file_size(self.inner, val);
}
}
/// Sets the blob compression type. All blob files use the same
/// compression type.
///
/// Dynamically changeable through SetOptions() API
pub fn set_blob_compression_type(&mut self, val: DBCompressionType) {
unsafe {
ffi::rocksdb_options_set_blob_compression_type(self.inner, val as _);
}
}
/// If this is set to true RocksDB will actively relocate valid blobs from the oldest blob files
/// as they are encountered during compaction.
///
/// Dynamically changeable through SetOptions() API
pub fn set_enable_blob_gc(&mut self, val: bool) {
unsafe {
ffi::rocksdb_options_set_enable_blob_gc(self.inner, u8::from(val));
}
}
/// Sets the threshold that the GC logic uses to determine which blob files should be considered “old.”
///
/// For example, the default value of 0.25 signals to RocksDB that blobs residing in the
/// oldest 25% of blob files should be relocated by GC. This parameter can be tuned to adjust
/// the trade-off between write amplification and space amplification.
///
/// Dynamically changeable through SetOptions() API
pub fn set_blob_gc_age_cutoff(&mut self, val: c_double) {
unsafe {
ffi::rocksdb_options_set_blob_gc_age_cutoff(self.inner, val);
}
}
/// Sets the blob GC force threshold.
///
/// Dynamically changeable through SetOptions() API
pub fn set_blob_gc_force_threshold(&mut self, val: c_double) {
unsafe {
ffi::rocksdb_options_set_blob_gc_force_threshold(self.inner, val);
}
}
/// Sets the blob compaction read ahead size.
///
/// Dynamically changeable through SetOptions() API
pub fn set_blob_compaction_readahead_size(&mut self, val: u64) {
unsafe {
ffi::rocksdb_options_set_blob_compaction_readahead_size(self.inner, val);
}
}
/// 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 has the following effects:
/// 1) Disable some internal optimizations around SST file compression.
/// 2) Reserve the last level for ingested files only.
/// 3) Compaction will not include any file from the last level.
/// Note that only Universal Compaction supports allow_ingest_behind.
/// `num_levels` should be >= 3 if this option is turned on.
///
/// DEFAULT: false
/// Immutable.
pub fn set_allow_ingest_behind(&mut self, val: bool) {
unsafe {
ffi::rocksdb_options_set_allow_ingest_behind(self.inner, c_uchar::from(val));
}
}
// A factory of a table property collector that marks an SST
// file as need-compaction when it observe at least "D" deletion
// entries in any "N" consecutive entries, or the ratio of tombstone
// entries >= deletion_ratio.
//
// `window_size`: is the sliding window size "N"
// `num_dels_trigger`: is the deletion trigger "D"
// `deletion_ratio`: if <= 0 or > 1, disable triggering compaction based on
// deletion ratio.
pub fn add_compact_on_deletion_collector_factory(
&mut self,
window_size: size_t,
num_dels_trigger: size_t,
deletion_ratio: f64,
) {
unsafe {
ffi::rocksdb_options_add_compact_on_deletion_collector_factory_del_ratio(
self.inner,
window_size,
num_dels_trigger,
deletion_ratio,
);
}
}
/// <https://github.com/facebook/rocksdb/wiki/Write-Buffer-Manager>
/// Write buffer manager helps users control the total memory used by memtables across multiple column families and/or DB instances.
/// Users can enable this control by 2 ways:
///
/// 1- Limit the total memtable usage across multiple column families and DBs under a threshold.
/// 2- Cost the memtable memory usage to block cache so that memory of RocksDB can be capped by the single limit.
/// The usage of a write buffer manager is similar to rate_limiter and sst_file_manager.
/// Users can create one write buffer manager object and pass it to all the options of column families or DBs whose memtable size they want to be controlled by this object.
pub fn set_write_buffer_manager(&mut self, write_buffer_manager: &WriteBufferManager) {
unsafe {
ffi::rocksdb_options_set_write_buffer_manager(
self.inner,
write_buffer_manager.0.inner.as_ptr(),
);
}
self.outlive.write_buffer_manager = Some(write_buffer_manager.clone());
}
}
impl Default for Options {
fn default() -> Self {
unsafe {
let opts = ffi::rocksdb_options_create();
assert!(!opts.is_null(), "Could not create RocksDB options");
Self {
inner: opts,
outlive: OptionsMustOutliveDB::default(),
}
}
}
}
impl FlushOptions {
pub fn new() -> FlushOptions {
FlushOptions::default()
}
/// Waits until the flush is done.
///
/// Default: true
///
/// # Examples
///
/// ```
/// use rocksdb::FlushOptions;
///
/// let mut options = FlushOptions::default();
/// options.set_wait(false);
/// ```
pub fn set_wait(&mut self, wait: bool) {
unsafe {
ffi::rocksdb_flushoptions_set_wait(self.inner, c_uchar::from(wait));
}
}
}
impl Default for FlushOptions {
fn default() -> Self {
let flush_opts = unsafe { ffi::rocksdb_flushoptions_create() };
assert!(
!flush_opts.is_null(),
"Could not create RocksDB flush options"
);
Self { inner: flush_opts }
}
}
impl WriteOptions {
pub fn new() -> WriteOptions {
WriteOptions::default()
}
/// Sets the sync mode. If true, the write will be flushed
/// from the operating system buffer cache before the write is considered complete.
/// If this flag is true, writes will be slower.
///
/// Default: false
pub fn set_sync(&mut self, sync: bool) {
unsafe {
ffi::rocksdb_writeoptions_set_sync(self.inner, c_uchar::from(sync));
}
}
/// Sets whether WAL should be active or not.
/// If true, writes will not first go to the write ahead log,
/// and the write may got lost after a crash.
///
/// Default: false
pub fn disable_wal(&mut self, disable: bool) {
unsafe {
ffi::rocksdb_writeoptions_disable_WAL(self.inner, c_int::from(disable));
}
}
/// 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 set_ignore_missing_column_families(&mut self, ignore: bool) {
unsafe {
ffi::rocksdb_writeoptions_set_ignore_missing_column_families(
self.inner,
c_uchar::from(ignore),
);
}
}
/// If true and we need to wait or sleep for the write request, fails
/// immediately with Status::Incomplete().
///
/// Default: false
pub fn set_no_slowdown(&mut self, no_slowdown: bool) {
unsafe {
ffi::rocksdb_writeoptions_set_no_slowdown(self.inner, c_uchar::from(no_slowdown));
}
}
/// 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 set_low_pri(&mut self, v: bool) {
unsafe {
ffi::rocksdb_writeoptions_set_low_pri(self.inner, c_uchar::from(v));
}
}
/// If true, 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 set_memtable_insert_hint_per_batch(&mut self, v: bool) {
unsafe {
ffi::rocksdb_writeoptions_set_memtable_insert_hint_per_batch(
self.inner,
c_uchar::from(v),
);
}
}
}
impl Default for WriteOptions {
fn default() -> Self {
let write_opts = unsafe { ffi::rocksdb_writeoptions_create() };
assert!(
!write_opts.is_null(),
"Could not create RocksDB write options"
);
Self { inner: write_opts }
}
}
#[derive(Debug, Copy, Clone, PartialEq, Eq)]
#[cfg_attr(feature = "serde1", derive(serde::Serialize, serde::Deserialize))]
#[repr(i32)]
pub enum ReadTier {
/// Reads data in memtable, block cache, OS cache or storage.
All = 0,
/// Reads data in memtable or block cache.
BlockCache,
}
impl ReadOptions {
// TODO add snapshot setting here
// TODO add snapshot wrapper structs with proper destructors;
// that struct needs an "iterator" impl too.
/// Specify whether the "data block"/"index block"/"filter block"
/// read for this iteration should be cached in memory?
/// Callers may wish to set this field to false for bulk scans.
///
/// Default: true
pub fn fill_cache(&mut self, v: bool) {
unsafe {
ffi::rocksdb_readoptions_set_fill_cache(self.inner, c_uchar::from(v));
}
}
/// Sets the snapshot which should be used for the read.
/// The snapshot must belong to the DB that is being read and must
/// not have been released.
pub fn set_snapshot<D: DBAccess>(&mut self, snapshot: &SnapshotWithThreadMode<D>) {
unsafe {
ffi::rocksdb_readoptions_set_snapshot(self.inner, snapshot.inner);
}
}
/// Sets the lower bound for an iterator.
pub fn set_iterate_lower_bound<K: Into<Vec<u8>>>(&mut self, key: K) {
self.set_lower_bound_impl(Some(key.into()));
}
/// Sets the upper bound for an iterator.
/// The upper bound itself is not included on the iteration result.
pub fn set_iterate_upper_bound<K: Into<Vec<u8>>>(&mut self, key: K) {
self.set_upper_bound_impl(Some(key.into()));
}
/// Sets lower and upper bounds based on the provided range. This is
/// similar to setting lower and upper bounds separately except that it also
/// allows either bound to be reset.
///
/// The argument can be a regular Rust range, e.g. `lower..upper`. However,
/// since RocksDB upper bound is always excluded (i.e. range can never be
/// fully closed) inclusive ranges (`lower..=upper` and `..=upper`) are not
/// supported. For example:
///
/// ```
/// let mut options = rocksdb::ReadOptions::default();
/// options.set_iterate_range("xy".as_bytes().."xz".as_bytes());
/// ```
///
/// In addition, [`crate::PrefixRange`] can be used to specify a range of
/// keys with a given prefix. In particular, the above example is
/// equivalent to:
///
/// ```
/// let mut options = rocksdb::ReadOptions::default();
/// options.set_iterate_range(rocksdb::PrefixRange("xy".as_bytes()));
/// ```
///
/// Note that setting range using this method is separate to using prefix
/// iterators. Prefix iterators use prefix extractor configured for
/// a column family. Setting bounds via [`crate::PrefixRange`] is more akin
/// to using manual prefix.
///
/// Using this method clears any previously set bounds. In other words, the
/// bounds can be reset by setting the range to `..` as in:
///
/// ```
/// let mut options = rocksdb::ReadOptions::default();
/// options.set_iterate_range(..);
/// ```
pub fn set_iterate_range(&mut self, range: impl crate::IterateBounds) {
let (lower, upper) = range.into_bounds();
self.set_lower_bound_impl(lower);
self.set_upper_bound_impl(upper);
}
fn set_lower_bound_impl(&mut self, bound: Option<Vec<u8>>) {
let (ptr, len) = if let Some(ref bound) = bound {
(bound.as_ptr() as *const c_char, bound.len())
} else if self.iterate_lower_bound.is_some() {
(std::ptr::null(), 0)
} else {
return;
};
self.iterate_lower_bound = bound;
unsafe {
ffi::rocksdb_readoptions_set_iterate_lower_bound(self.inner, ptr, len);
}
}
fn set_upper_bound_impl(&mut self, bound: Option<Vec<u8>>) {
let (ptr, len) = if let Some(ref bound) = bound {
(bound.as_ptr() as *const c_char, bound.len())
} else if self.iterate_upper_bound.is_some() {
(std::ptr::null(), 0)
} else {
return;
};
self.iterate_upper_bound = bound;
unsafe {
ffi::rocksdb_readoptions_set_iterate_upper_bound(self.inner, ptr, len);
}
}
/// 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: ::All
pub fn set_read_tier(&mut self, tier: ReadTier) {
unsafe {
ffi::rocksdb_readoptions_set_read_tier(self.inner, tier as c_int);
}
}
/// 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 set_prefix_same_as_start(&mut self, v: bool) {
unsafe {
ffi::rocksdb_readoptions_set_prefix_same_as_start(self.inner, c_uchar::from(v));
}
}
/// 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 set_total_order_seek(&mut self, v: bool) {
unsafe {
ffi::rocksdb_readoptions_set_total_order_seek(self.inner, c_uchar::from(v));
}
}
/// Sets 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 set_max_skippable_internal_keys(&mut self, num: u64) {
unsafe {
ffi::rocksdb_readoptions_set_max_skippable_internal_keys(self.inner, num);
}
}
/// 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 set_background_purge_on_iterator_cleanup(&mut self, v: bool) {
unsafe {
ffi::rocksdb_readoptions_set_background_purge_on_iterator_cleanup(
self.inner,
c_uchar::from(v),
);
}
}
/// If true, keys deleted using the DeleteRange() 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 set_ignore_range_deletions(&mut self, v: bool) {
unsafe {
ffi::rocksdb_readoptions_set_ignore_range_deletions(self.inner, c_uchar::from(v));
}
}
/// If true, all data read from underlying storage will be
/// verified against corresponding checksums.
///
/// Default: true
pub fn set_verify_checksums(&mut self, v: bool) {
unsafe {
ffi::rocksdb_readoptions_set_verify_checksums(self.inner, c_uchar::from(v));
}
}
/// If non-zero, an iterator 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
///
/// ```
/// use rocksdb::{ReadOptions};
///
/// let mut opts = ReadOptions::default();
/// opts.set_readahead_size(4_194_304); // 4mb
/// ```
pub fn set_readahead_size(&mut self, v: usize) {
unsafe {
ffi::rocksdb_readoptions_set_readahead_size(self.inner, v as size_t);
}
}
/// If auto_readahead_size is set to true, it will auto tune the readahead_size
/// during scans internally.
/// For this feature to be enabled, iterate_upper_bound must also be specified.
///
/// NOTE: - Recommended for forward Scans only.
/// - If there is a backward scans, this option will be
/// disabled internally and won't be enabled again if the forward scan
/// is issued again.
///
/// Default: true
pub fn set_auto_readahead_size(&mut self, v: bool) {
unsafe {
ffi::rocksdb_readoptions_set_auto_readahead_size(self.inner, c_uchar::from(v));
}
}
/// If true, create a tailing iterator. Note that tailing iterators
/// only support moving in the forward direction. Iterating in reverse
/// or seek_to_last are not supported.
pub fn set_tailing(&mut self, v: bool) {
unsafe {
ffi::rocksdb_readoptions_set_tailing(self.inner, c_uchar::from(v));
}
}
/// Specifies the value of "pin_data". If true, it keeps 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 set_pin_data(&mut self, v: bool) {
unsafe {
ffi::rocksdb_readoptions_set_pin_data(self.inner, c_uchar::from(v));
}
}
/// Asynchronously prefetch some data.
///
/// Used for sequential reads and internal automatic prefetching.
///
/// Default: `false`
pub fn set_async_io(&mut self, v: bool) {
unsafe {
ffi::rocksdb_readoptions_set_async_io(self.inner, c_uchar::from(v));
}
}
}
impl Default for ReadOptions {
fn default() -> Self {
unsafe {
Self {
inner: ffi::rocksdb_readoptions_create(),
iterate_upper_bound: None,
iterate_lower_bound: None,
}
}
}
}
impl IngestExternalFileOptions {
/// Can be set to true to move the files instead of copying them.
pub fn set_move_files(&mut self, v: bool) {
unsafe {
ffi::rocksdb_ingestexternalfileoptions_set_move_files(self.inner, c_uchar::from(v));
}
}
/// If set to false, an ingested file keys could appear in existing snapshots
/// that where created before the file was ingested.
pub fn set_snapshot_consistency(&mut self, v: bool) {
unsafe {
ffi::rocksdb_ingestexternalfileoptions_set_snapshot_consistency(
self.inner,
c_uchar::from(v),
);
}
}
/// If set to false, IngestExternalFile() will fail if the file key range
/// overlaps with existing keys or tombstones in the DB.
pub fn set_allow_global_seqno(&mut self, v: bool) {
unsafe {
ffi::rocksdb_ingestexternalfileoptions_set_allow_global_seqno(
self.inner,
c_uchar::from(v),
);
}
}
/// If set to false and the file key range overlaps with the memtable key range
/// (memtable flush required), IngestExternalFile will fail.
pub fn set_allow_blocking_flush(&mut self, v: bool) {
unsafe {
ffi::rocksdb_ingestexternalfileoptions_set_allow_blocking_flush(
self.inner,
c_uchar::from(v),
);
}
}
/// 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 set_ingest_behind(&mut self, v: bool) {
unsafe {
ffi::rocksdb_ingestexternalfileoptions_set_ingest_behind(self.inner, c_uchar::from(v));
}
}
}
impl Default for IngestExternalFileOptions {
fn default() -> Self {
unsafe {
Self {
inner: ffi::rocksdb_ingestexternalfileoptions_create(),
}
}
}
}
/// Used by BlockBasedOptions::set_index_type.
pub enum BlockBasedIndexType {
/// A space efficient index block that is optimized for
/// binary-search-based index.
BinarySearch,
/// The hash index, if enabled, will perform a hash lookup if
/// a prefix extractor has been provided through Options::set_prefix_extractor.
HashSearch,
/// A two-level index implementation. Both levels are binary search indexes.
TwoLevelIndexSearch,
}
/// Used by BlockBasedOptions::set_data_block_index_type.
#[repr(C)]
pub enum DataBlockIndexType {
/// Use binary search when performing point lookup for keys in data blocks.
/// This is the default.
BinarySearch = 0,
/// Appends a compact hash table to the end of the data block for efficient indexing. Backwards
/// compatible with databases created without this feature. Once turned on, existing data will
/// be gradually converted to the hash index format.
BinaryAndHash = 1,
}
/// Defines the underlying memtable implementation.
/// See official [wiki](https://github.com/facebook/rocksdb/wiki/MemTable) for more information.
pub enum MemtableFactory {
Vector,
HashSkipList {
bucket_count: usize,
height: i32,
branching_factor: i32,
},
HashLinkList {
bucket_count: usize,
},
}
/// Used by BlockBasedOptions::set_checksum_type.
pub enum ChecksumType {
NoChecksum = 0,
CRC32c = 1,
XXHash = 2,
XXHash64 = 3,
XXH3 = 4, // Supported since RocksDB 6.27
}
/// Used in [`PlainTableFactoryOptions`].
#[derive(Debug, Copy, Clone, PartialEq, Eq, Default)]
pub enum KeyEncodingType {
/// Always write full keys.
#[default]
Plain = 0,
/// Find opportunities to write the same prefix for multiple rows.
Prefix = 1,
}
/// Used with DBOptions::set_plain_table_factory.
/// See official [wiki](https://github.com/facebook/rocksdb/wiki/PlainTable-Format) for more
/// information.
///
/// Defaults:
/// user_key_length: 0 (variable length)
/// bloom_bits_per_key: 10
/// hash_table_ratio: 0.75
/// index_sparseness: 16
/// huge_page_tlb_size: 0
/// encoding_type: KeyEncodingType::Plain
/// full_scan_mode: false
/// store_index_in_file: false
pub struct PlainTableFactoryOptions {
pub user_key_length: u32,
pub bloom_bits_per_key: i32,
pub hash_table_ratio: f64,
pub index_sparseness: usize,
pub huge_page_tlb_size: usize,
pub encoding_type: KeyEncodingType,
pub full_scan_mode: bool,
pub store_index_in_file: bool,
}
#[derive(Debug, Copy, Clone, PartialEq, Eq)]
#[cfg_attr(feature = "serde1", derive(serde::Serialize, serde::Deserialize))]
pub enum DBCompressionType {
None = ffi::rocksdb_no_compression as isize,
Snappy = ffi::rocksdb_snappy_compression as isize,
Zlib = ffi::rocksdb_zlib_compression as isize,
Bz2 = ffi::rocksdb_bz2_compression as isize,
Lz4 = ffi::rocksdb_lz4_compression as isize,
Lz4hc = ffi::rocksdb_lz4hc_compression as isize,
Zstd = ffi::rocksdb_zstd_compression as isize,
}
#[derive(Debug, Copy, Clone, PartialEq, Eq)]
#[cfg_attr(feature = "serde1", derive(serde::Serialize, serde::Deserialize))]
pub enum DBCompactionStyle {
Level = ffi::rocksdb_level_compaction as isize,
Universal = ffi::rocksdb_universal_compaction as isize,
Fifo = ffi::rocksdb_fifo_compaction as isize,
}
#[derive(Debug, Copy, Clone, PartialEq, Eq)]
#[cfg_attr(feature = "serde1", derive(serde::Serialize, serde::Deserialize))]
pub enum DBRecoveryMode {
TolerateCorruptedTailRecords = ffi::rocksdb_tolerate_corrupted_tail_records_recovery as isize,
AbsoluteConsistency = ffi::rocksdb_absolute_consistency_recovery as isize,
PointInTime = ffi::rocksdb_point_in_time_recovery as isize,
SkipAnyCorruptedRecord = ffi::rocksdb_skip_any_corrupted_records_recovery as isize,
}
/// File access pattern once a compaction has started
#[derive(Debug, Copy, Clone, PartialEq, Eq)]
#[cfg_attr(feature = "serde1", derive(serde::Serialize, serde::Deserialize))]
#[repr(i32)]
pub enum AccessHint {
None = 0,
Normal,
Sequential,
WillNeed,
}
pub struct FifoCompactOptions {
pub(crate) inner: *mut ffi::rocksdb_fifo_compaction_options_t,
}
impl Default for FifoCompactOptions {
fn default() -> Self {
let opts = unsafe { ffi::rocksdb_fifo_compaction_options_create() };
assert!(
!opts.is_null(),
"Could not create RocksDB Fifo Compaction Options"
);
Self { inner: opts }
}
}
impl Drop for FifoCompactOptions {
fn drop(&mut self) {
unsafe {
ffi::rocksdb_fifo_compaction_options_destroy(self.inner);
}
}
}
impl FifoCompactOptions {
/// Sets the max table file size.
///
/// Once the total sum of table files reaches this, we will delete the oldest
/// table file
///
/// Default: 1GB
pub fn set_max_table_files_size(&mut self, nbytes: u64) {
unsafe {
ffi::rocksdb_fifo_compaction_options_set_max_table_files_size(self.inner, nbytes);
}
}
}
#[derive(Debug, Copy, Clone, PartialEq, Eq)]
#[cfg_attr(feature = "serde1", derive(serde::Serialize, serde::Deserialize))]
pub enum UniversalCompactionStopStyle {
Similar = ffi::rocksdb_similar_size_compaction_stop_style as isize,
Total = ffi::rocksdb_total_size_compaction_stop_style as isize,
}
pub struct UniversalCompactOptions {
pub(crate) inner: *mut ffi::rocksdb_universal_compaction_options_t,
}
impl Default for UniversalCompactOptions {
fn default() -> Self {
let opts = unsafe { ffi::rocksdb_universal_compaction_options_create() };
assert!(
!opts.is_null(),
"Could not create RocksDB Universal Compaction Options"
);
Self { inner: opts }
}
}
impl Drop for UniversalCompactOptions {
fn drop(&mut self) {
unsafe {
ffi::rocksdb_universal_compaction_options_destroy(self.inner);
}
}
}
impl UniversalCompactOptions {
/// Sets the percentage flexibility while comparing file size.
/// If the candidate file(s) size is 1% smaller than the next file's size,
/// then include next file into this candidate set.
///
/// Default: 1
pub fn set_size_ratio(&mut self, ratio: c_int) {
unsafe {
ffi::rocksdb_universal_compaction_options_set_size_ratio(self.inner, ratio);
}
}
/// Sets the minimum number of files in a single compaction run.
///
/// Default: 2
pub fn set_min_merge_width(&mut self, num: c_int) {
unsafe {
ffi::rocksdb_universal_compaction_options_set_min_merge_width(self.inner, num);
}
}
/// Sets the maximum number of files in a single compaction run.
///
/// Default: UINT_MAX
pub fn set_max_merge_width(&mut self, num: c_int) {
unsafe {
ffi::rocksdb_universal_compaction_options_set_max_merge_width(self.inner, num);
}
}
/// sets the size amplification.
///
/// It is defined as the amount (in percentage) of
/// additional storage needed to store a single byte of data in the database.
/// For example, a size amplification of 2% means that a database that
/// contains 100 bytes of user-data may occupy upto 102 bytes of
/// physical storage. By this definition, a fully compacted database has
/// a size amplification of 0%. Rocksdb uses the following heuristic
/// to calculate size amplification: it assumes that all files excluding
/// the earliest file contribute to the size amplification.
///
/// Default: 200, which means that a 100 byte database could require upto 300 bytes of storage.
pub fn set_max_size_amplification_percent(&mut self, v: c_int) {
unsafe {
ffi::rocksdb_universal_compaction_options_set_max_size_amplification_percent(
self.inner, v,
);
}
}
/// Sets the percentage of compression size.
///
/// If this option is set to be -1, all the output files
/// will follow compression type specified.
///
/// If this option is not negative, we will try to make sure compressed
/// size is just above this value. In normal cases, at least this percentage
/// of data will be compressed.
/// When we are compacting to a new file, here is the criteria whether
/// it needs to be compressed: assuming here are the list of files sorted
/// by generation time:
/// A1...An B1...Bm C1...Ct
/// where A1 is the newest and Ct is the oldest, and we are going to compact
/// B1...Bm, we calculate the total size of all the files as total_size, as
/// well as the total size of C1...Ct as total_C, the compaction output file
/// will be compressed iff
/// total_C / total_size < this percentage
///
/// Default: -1
pub fn set_compression_size_percent(&mut self, v: c_int) {
unsafe {
ffi::rocksdb_universal_compaction_options_set_compression_size_percent(self.inner, v);
}
}
/// Sets the algorithm used to stop picking files into a single compaction run.
///
/// Default: ::Total
pub fn set_stop_style(&mut self, style: UniversalCompactionStopStyle) {
unsafe {
ffi::rocksdb_universal_compaction_options_set_stop_style(self.inner, style as c_int);
}
}
}
#[derive(Debug, Copy, Clone, PartialEq, Eq)]
#[cfg_attr(feature = "serde1", derive(serde::Serialize, serde::Deserialize))]
#[repr(u8)]
pub enum BottommostLevelCompaction {
/// Skip bottommost level compaction
Skip = 0,
/// Only compact bottommost level if there is a compaction filter
/// This is the default option
IfHaveCompactionFilter,
/// Always compact bottommost level
Force,
/// Always compact bottommost level but in bottommost level avoid
/// double-compacting files created in the same compaction
ForceOptimized,
}
pub struct CompactOptions {
pub(crate) inner: *mut ffi::rocksdb_compactoptions_t,
}
impl Default for CompactOptions {
fn default() -> Self {
let opts = unsafe { ffi::rocksdb_compactoptions_create() };
assert!(!opts.is_null(), "Could not create RocksDB Compact Options");
Self { inner: opts }
}
}
impl Drop for CompactOptions {
fn drop(&mut self) {
unsafe {
ffi::rocksdb_compactoptions_destroy(self.inner);
}
}
}
impl CompactOptions {
/// If more than one thread calls manual compaction,
/// only one will actually schedule it while the other threads will simply wait
/// for the scheduled manual compaction to complete. If exclusive_manual_compaction
/// is set to true, the call will disable scheduling of automatic compaction jobs
/// and wait for existing automatic compaction jobs to finish.
pub fn set_exclusive_manual_compaction(&mut self, v: bool) {
unsafe {
ffi::rocksdb_compactoptions_set_exclusive_manual_compaction(
self.inner,
c_uchar::from(v),
);
}
}
/// Sets bottommost level compaction.
pub fn set_bottommost_level_compaction(&mut self, lvl: BottommostLevelCompaction) {
unsafe {
ffi::rocksdb_compactoptions_set_bottommost_level_compaction(self.inner, lvl as c_uchar);
}
}
/// 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 set_change_level(&mut self, v: bool) {
unsafe {
ffi::rocksdb_compactoptions_set_change_level(self.inner, c_uchar::from(v));
}
}
/// If change_level is true and target_level have non-negative value, compacted
/// files will be moved to target_level.
pub fn set_target_level(&mut self, lvl: c_int) {
unsafe {
ffi::rocksdb_compactoptions_set_target_level(self.inner, lvl);
}
}
}
pub struct WaitForCompactOptions {
pub(crate) inner: *mut ffi::rocksdb_wait_for_compact_options_t,
}
impl Default for WaitForCompactOptions {
fn default() -> Self {
let opts = unsafe { ffi::rocksdb_wait_for_compact_options_create() };
assert!(
!opts.is_null(),
"Could not create RocksDB Wait For Compact Options"
);
Self { inner: opts }
}
}
impl Drop for WaitForCompactOptions {
fn drop(&mut self) {
unsafe {
ffi::rocksdb_wait_for_compact_options_destroy(self.inner);
}
}
}
impl WaitForCompactOptions {
/// If true, abort waiting if background jobs are paused. If false,
/// ContinueBackgroundWork() must be called to resume the background jobs.
/// Otherwise, jobs that were queued, but not scheduled yet may never finish
/// and WaitForCompact() may wait indefinitely (if timeout is set, it will
/// abort after the timeout).
///
/// Default: false
pub fn set_abort_on_pause(&mut self, v: bool) {
unsafe {
ffi::rocksdb_wait_for_compact_options_set_abort_on_pause(self.inner, c_uchar::from(v));
}
}
/// If true, flush all column families before starting to wait.
///
/// Default: false
pub fn set_flush(&mut self, v: bool) {
unsafe {
ffi::rocksdb_wait_for_compact_options_set_flush(self.inner, c_uchar::from(v));
}
}
/// Timeout in microseconds for waiting for compaction to complete.
/// when timeout == 0, WaitForCompact() will wait as long as there's background
/// work to finish.
///
/// Default: 0
pub fn set_timeout(&mut self, microseconds: u64) {
unsafe {
ffi::rocksdb_wait_for_compact_options_set_timeout(self.inner, microseconds);
}
}
}
/// Represents a path where sst files can be put into
pub struct DBPath {
pub(crate) inner: *mut ffi::rocksdb_dbpath_t,
}
impl DBPath {
/// Create a new path
pub fn new<P: AsRef<Path>>(path: P, target_size: u64) -> Result<Self, Error> {
let p = to_cpath(path.as_ref()).unwrap();
let dbpath = unsafe { ffi::rocksdb_dbpath_create(p.as_ptr(), target_size) };
if dbpath.is_null() {
Err(Error::new(format!(
"Could not create path for storing sst files at location: {}",
path.as_ref().display()
)))
} else {
Ok(DBPath { inner: dbpath })
}
}
}
impl Drop for DBPath {
fn drop(&mut self) {
unsafe {
ffi::rocksdb_dbpath_destroy(self.inner);
}
}
}
#[cfg(test)]
mod tests {
use crate::db_options::WriteBufferManager;
use crate::{Cache, MemtableFactory, Options};
#[test]
fn test_enable_statistics() {
let mut opts = Options::default();
opts.enable_statistics();
opts.set_stats_dump_period_sec(60);
assert!(opts.get_statistics().is_some());
let opts = Options::default();
assert!(opts.get_statistics().is_none());
}
#[test]
fn test_set_memtable_factory() {
let mut opts = Options::default();
opts.set_memtable_factory(MemtableFactory::Vector);
opts.set_memtable_factory(MemtableFactory::HashLinkList { bucket_count: 100 });
opts.set_memtable_factory(MemtableFactory::HashSkipList {
bucket_count: 100,
height: 4,
branching_factor: 4,
});
}
#[test]
fn test_set_stats_persist_period_sec() {
let mut opts = Options::default();
opts.enable_statistics();
opts.set_stats_persist_period_sec(5);
assert!(opts.get_statistics().is_some());
let opts = Options::default();
assert!(opts.get_statistics().is_none());
}
#[test]
fn test_set_write_buffer_manager() {
let mut opts = Options::default();
let lrucache = Cache::new_lru_cache(100);
let write_buffer_manager =
WriteBufferManager::new_write_buffer_manager_with_cache(100, false, lrucache);
assert_eq!(write_buffer_manager.get_buffer_size(), 100);
assert_eq!(write_buffer_manager.get_usage(), 0);
assert!(write_buffer_manager.enabled());
opts.set_write_buffer_manager(&write_buffer_manager);
drop(opts);
// WriteBufferManager outlives options
assert!(write_buffer_manager.enabled());
}
}