diff options
Diffstat (limited to 'Documentation/admin-guide/blockdev')
15 files changed, 2459 insertions, 0 deletions
diff --git a/Documentation/admin-guide/blockdev/drbd/DRBD-8.3-data-packets.svg b/Documentation/admin-guide/blockdev/drbd/DRBD-8.3-data-packets.svg new file mode 100644 index 0000000000..f87cfa0dc2 --- /dev/null +++ b/Documentation/admin-guide/blockdev/drbd/DRBD-8.3-data-packets.svg @@ -0,0 +1,588 @@ +<?xml version="1.0" encoding="UTF-8" standalone="no"?> +<!-- Created with Inkscape (http://www.inkscape.org/) --> +<svg + xmlns:svg="http://www.w3.org/2000/svg" + xmlns="http://www.w3.org/2000/svg" + version="1.0" + width="210mm" + height="297mm" + viewBox="0 0 21000 29700" + id="svg2" + style="fill-rule:evenodd"> + <defs + id="defs4" /> + <g + id="Default" + style="visibility:visible"> + <desc + id="desc180">Master slide</desc> + </g> + <path + d="M 11999,8601 L 11899,8301 L 12099,8301 L 11999,8601 z" + id="path193" + style="fill:#008000;visibility:visible" /> + <path + d="M 11999,7801 L 11999,8361" + id="path197" + style="fill:none;stroke:#008000;visibility:visible" /> + <path + d="M 7999,10401 L 7899,10101 L 8099,10101 L 7999,10401 z" + id="path209" + style="fill:#008000;visibility:visible" /> + <path + d="M 7999,9601 L 7999,10161" + id="path213" + style="fill:none;stroke:#008000;visibility:visible" /> + <path + d="M 11999,7801 L 11685,7840 L 11724,7644 L 11999,7801 z" + id="path225" + style="fill:#008000;visibility:visible" /> + <path + d="M 7999,7001 L 11764,7754" + id="path229" + style="fill:none;stroke:#008000;visibility:visible" /> + <g + transform="matrix(0.9895258,-0.1443562,0.1443562,0.9895258,-1244.4792,1416.5139)" + id="g245" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <text + id="text247"> + <tspan + x="9139 9368 9579 9808 9986 10075 10252 10481 10659 10837 10909" + y="9284" + id="tspan249">RSDataReply</tspan> + </text> + </g> + <path + d="M 7999,9601 L 8281,9458 L 8311,9655 L 7999,9601 z" + id="path259" + style="fill:#008000;visibility:visible" /> + <path + d="M 11999,9001 L 8236,9565" + id="path263" + style="fill:none;stroke:#008000;visibility:visible" /> + <g + transform="matrix(0.9788674,0.2044961,-0.2044961,0.9788674,1620.9382,-1639.4947)" + id="g279" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <text + id="text281"> + <tspan + x="8743 8972 9132 9310 9573 9801 10013 10242 10419 10597 10775 10953 11114" + y="7023" + id="tspan283">CsumRSRequest</tspan> + </text> + </g> + <text + id="text297" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="4034 4263 4440 4703 4881 5042 5219 5397 5503 5681 5842 6003 6180 6341 6519 6625 6803 6980 7158 7336 7497 7586 7692" + y="5707" + id="tspan299">w_make_resync_request()</tspan> + </text> + <text + id="text313" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="12199 12305 12483 12644 12821 12893 13054 13232 13410 13638 13816 13905 14083 14311 14489 14667 14845 15023 15184 15272 15378" + y="7806" + id="tspan315">receive_DataRequest()</tspan> + </text> + <text + id="text329" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="12199 12377 12483 12660 12838 13016 13194 13372 13549 13621 13799 13977 14083 14261 14438 14616 14794 14955 15133 15294 15399" + y="8606" + id="tspan331">drbd_endio_read_sec()</tspan> + </text> + <text + id="text345" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="12191 12420 12597 12775 12953 13131 13309 13486 13664 13825 13986 14164 14426 14604 14710 14871 15049 15154 15332 15510 15616" + y="9007" + id="tspan347">w_e_end_csum_rs_req()</tspan> + </text> + <text + id="text361" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="4444 4550 4728 4889 5066 5138 5299 5477 5655 5883 6095 6324 6501 6590 6768 6997 7175 7352 7424 7585 7691" + y="9507" + id="tspan363">receive_RSDataReply()</tspan> + </text> + <text + id="text377" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="4457 4635 4741 4918 5096 5274 5452 5630 5807 5879 6057 6235 6464 6569 6641 6730 6908 7086 7247 7425 7585 7691" + y="10407" + id="tspan379">drbd_endio_write_sec()</tspan> + </text> + <text + id="text393" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="4647 4825 5003 5180 5358 5536 5714 5820 5997 6158 6319 6497 6658 6836 7013 7085 7263 7424 7585 7691" + y="10907" + id="tspan395">e_end_resync_block()</tspan> + </text> + <path + d="M 11999,11601 L 11685,11640 L 11724,11444 L 11999,11601 z" + id="path405" + style="fill:#000080;visibility:visible" /> + <path + d="M 7999,10801 L 11764,11554" + id="path409" + style="fill:none;stroke:#000080;visibility:visible" /> + <g + transform="matrix(0.9788674,0.2044961,-0.2044961,0.9788674,2434.7562,-1674.649)" + id="g425" + style="font-size:318px;font-weight:400;fill:#000080;visibility:visible;font-family:Helvetica embedded"> + <text + id="text427"> + <tspan + x="9320 9621 9726 9798 9887 10065 10277 10438" + y="10943" + id="tspan429">WriteAck</tspan> + </text> + </g> + <text + id="text443" + style="font-size:318px;font-weight:400;fill:#000080;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="12199 12377 12555 12644 12821 13033 13105 13283 13444 13604 13816 13977 14138 14244" + y="11559" + id="tspan445">got_BlockAck()</tspan> + </text> + <text + id="text459" + style="font-size:423px;font-weight:400;fill:#000000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="7999 8304 8541 8778 8990 9201 9413 9650 10001 10120 10357 10594 10806 11043 11280 11398 11703 11940 12152 12364 12601 12812 12931 13049 13261 13498 13710 13947 14065 14302 14540 14658 14777 14870 15107 15225 15437 15649 15886" + y="4877" + id="tspan461">Checksum based Resync, case not in sync</tspan> + </text> + <text + id="text475" + style="font-size:423px;font-weight:400;fill:#000000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="6961 7266 7571 7854 8159 8299 8536 8654 8891 9010 9247 9484 9603 9840 9958 10077 10170 10407" + y="2806" + id="tspan477">DRBD-8.3 data flow</tspan> + </text> + <text + id="text491" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="5190 5419 5596 5774 5952 6113 6291 6468 6646 6824 6985 7146 7324 7586 7692" + y="7005" + id="tspan493">w_e_send_csum()</tspan> + </text> + <path + d="M 11999,17601 L 11899,17301 L 12099,17301 L 11999,17601 z" + id="path503" + style="fill:#008000;visibility:visible" /> + <path + d="M 11999,16801 L 11999,17361" + id="path507" + style="fill:none;stroke:#008000;visibility:visible" /> + <path + d="M 11999,16801 L 11685,16840 L 11724,16644 L 11999,16801 z" + id="path519" + style="fill:#008000;visibility:visible" /> + <path + d="M 7999,16001 L 11764,16754" + id="path523" + style="fill:none;stroke:#008000;visibility:visible" /> + <g + transform="matrix(0.9895258,-0.1443562,0.1443562,0.9895258,-2539.5806,1529.3491)" + id="g539" + style="font-size:318px;font-weight:400;fill:#000080;visibility:visible;font-family:Helvetica embedded"> + <text + id="text541"> + <tspan + x="9269 9498 9709 9798 9959 10048 10226 10437 10598 10776" + y="18265" + id="tspan543">RSIsInSync</tspan> + </text> + </g> + <path + d="M 7999,18601 L 8281,18458 L 8311,18655 L 7999,18601 z" + id="path553" + style="fill:#000080;visibility:visible" /> + <path + d="M 11999,18001 L 8236,18565" + id="path557" + style="fill:none;stroke:#000080;visibility:visible" /> + <g + transform="matrix(0.9788674,0.2044961,-0.2044961,0.9788674,3461.4027,-1449.3012)" + id="g573" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <text + id="text575"> + <tspan + x="8743 8972 9132 9310 9573 9801 10013 10242 10419 10597 10775 10953 11114" + y="16023" + id="tspan577">CsumRSRequest</tspan> + </text> + </g> + <text + id="text591" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="12199 12305 12483 12644 12821 12893 13054 13232 13410 13638 13816 13905 14083 14311 14489 14667 14845 15023 15184 15272 15378" + y="16806" + id="tspan593">receive_DataRequest()</tspan> + </text> + <text + id="text607" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="12199 12377 12483 12660 12838 13016 13194 13372 13549 13621 13799 13977 14083 14261 14438 14616 14794 14955 15133 15294 15399" + y="17606" + id="tspan609">drbd_endio_read_sec()</tspan> + </text> + <text + id="text623" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="12191 12420 12597 12775 12953 13131 13309 13486 13664 13825 13986 14164 14426 14604 14710 14871 15049 15154 15332 15510 15616" + y="18007" + id="tspan625">w_e_end_csum_rs_req()</tspan> + </text> + <text + id="text639" + style="font-size:318px;font-weight:400;fill:#000080;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="5735 5913 6091 6180 6357 6446 6607 6696 6874 7085 7246 7424 7585 7691" + y="18507" + id="tspan641">got_IsInSync()</tspan> + </text> + <text + id="text655" + style="font-size:423px;font-weight:400;fill:#000000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="7999 8304 8541 8778 8990 9201 9413 9650 10001 10120 10357 10594 10806 11043 11280 11398 11703 11940 12152 12364 12601 12812 12931 13049 13261 13498 13710 13947 14065 14159 14396 14514 14726 14937 15175" + y="13877" + id="tspan657">Checksum based Resync, case in sync</tspan> + </text> + <path + d="M 12000,24601 L 11900,24301 L 12100,24301 L 12000,24601 z" + id="path667" + style="fill:#008000;visibility:visible" /> + <path + d="M 12000,23801 L 12000,24361" + id="path671" + style="fill:none;stroke:#008000;visibility:visible" /> + <path + d="M 8000,26401 L 7900,26101 L 8100,26101 L 8000,26401 z" + id="path683" + style="fill:#008000;visibility:visible" /> + <path + d="M 8000,25601 L 8000,26161" + id="path687" + style="fill:none;stroke:#008000;visibility:visible" /> + <path + d="M 12000,23801 L 11686,23840 L 11725,23644 L 12000,23801 z" + id="path699" + style="fill:#008000;visibility:visible" /> + <path + d="M 8000,23001 L 11765,23754" + id="path703" + style="fill:none;stroke:#008000;visibility:visible" /> + <g + transform="matrix(0.9895258,-0.1443562,0.1443562,0.9895258,-3543.8452,1630.5143)" + id="g719" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <text + id="text721"> + <tspan + x="9464 9710 9921 10150 10328 10505 10577" + y="25236" + id="tspan723">OVReply</tspan> + </text> + </g> + <path + d="M 8000,25601 L 8282,25458 L 8312,25655 L 8000,25601 z" + id="path733" + style="fill:#008000;visibility:visible" /> + <path + d="M 12000,25001 L 8237,25565" + id="path737" + style="fill:none;stroke:#008000;visibility:visible" /> + <g + transform="matrix(0.9788674,0.2044961,-0.2044961,0.9788674,4918.2801,-1381.2128)" + id="g753" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <text + id="text755"> + <tspan + x="9142 9388 9599 9828 10006 10183 10361 10539 10700" + y="23106" + id="tspan757">OVRequest</tspan> + </text> + </g> + <text + id="text771" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="12200 12306 12484 12645 12822 12894 13055 13233 13411 13656 13868 14097 14274 14452 14630 14808 14969 15058 15163" + y="23806" + id="tspan773">receive_OVRequest()</tspan> + </text> + <text + id="text787" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="12200 12378 12484 12661 12839 13017 13195 13373 13550 13622 13800 13978 14084 14262 14439 14617 14795 14956 15134 15295 15400" + y="24606" + id="tspan789">drbd_endio_read_sec()</tspan> + </text> + <text + id="text803" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="12192 12421 12598 12776 12954 13132 13310 13487 13665 13843 14004 14182 14288 14465 14643 14749" + y="25007" + id="tspan805">w_e_end_ov_req()</tspan> + </text> + <text + id="text819" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="5101 5207 5385 5546 5723 5795 5956 6134 6312 6557 6769 6998 7175 7353 7425 7586 7692" + y="25507" + id="tspan821">receive_OVReply()</tspan> + </text> + <text + id="text835" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="4492 4670 4776 4953 5131 5309 5487 5665 5842 5914 6092 6270 6376 6554 6731 6909 7087 7248 7426 7587 7692" + y="26407" + id="tspan837">drbd_endio_read_sec()</tspan> + </text> + <text + id="text851" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="4902 5131 5308 5486 5664 5842 6020 6197 6375 6553 6714 6892 6998 7175 7353 7425 7586 7692" + y="26907" + id="tspan853">w_e_end_ov_reply()</tspan> + </text> + <path + d="M 12000,27601 L 11686,27640 L 11725,27444 L 12000,27601 z" + id="path863" + style="fill:#000080;visibility:visible" /> + <path + d="M 8000,26801 L 11765,27554" + id="path867" + style="fill:none;stroke:#000080;visibility:visible" /> + <g + transform="matrix(0.9788674,0.2044961,-0.2044961,0.9788674,5704.1907,-1328.312)" + id="g883" + style="font-size:318px;font-weight:400;fill:#000080;visibility:visible;font-family:Helvetica embedded"> + <text + id="text885"> + <tspan + x="9279 9525 9736 9965 10143 10303 10481 10553" + y="26935" + id="tspan887">OVResult</tspan> + </text> + </g> + <text + id="text901" + style="font-size:318px;font-weight:400;fill:#000080;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="12200 12378 12556 12645 12822 13068 13280 13508 13686 13847 14025 14097 14185 14291" + y="27559" + id="tspan903">got_OVResult()</tspan> + </text> + <text + id="text917" + style="font-size:423px;font-weight:400;fill:#000000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="8000 8330 8567 8660 8754 8991 9228 9346 9558 9795 9935 10028 10146" + y="21877" + id="tspan919">Online verify</tspan> + </text> + <text + id="text933" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="4641 4870 5047 5310 5488 5649 5826 6004 6182 6343 6521 6626 6804 6982 7160 7338 7499 7587 7693" + y="23005" + id="tspan935">w_make_ov_request()</tspan> + </text> + <path + d="M 8000,6500 L 7900,6200 L 8100,6200 L 8000,6500 z" + id="path945" + style="fill:#008000;visibility:visible" /> + <path + d="M 8000,5700 L 8000,6260" + id="path949" + style="fill:none;stroke:#008000;visibility:visible" /> + <path + d="M 3900,5500 L 3700,5500 L 3700,11000 L 3900,11000" + id="path961" + style="fill:none;stroke:#000000;visibility:visible" /> + <path + d="M 3900,14500 L 3700,14500 L 3700,18600 L 3900,18600" + id="path973" + style="fill:none;stroke:#000000;visibility:visible" /> + <path + d="M 3900,22800 L 3700,22800 L 3700,26900 L 3900,26900" + id="path985" + style="fill:none;stroke:#000000;visibility:visible" /> + <text + id="text1001" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="4492 4670 4776 4953 5131 5309 5487 5665 5842 5914 6092 6270 6376 6554 6731 6909 7087 7248 7426 7587 7692" + y="6506" + id="tspan1003">drbd_endio_read_sec()</tspan> + </text> + <text + id="text1017" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="4034 4263 4440 4703 4881 5042 5219 5397 5503 5681 5842 6003 6180 6341 6519 6625 6803 6980 7158 7336 7497 7586 7692" + y="14708" + id="tspan1019">w_make_resync_request()</tspan> + </text> + <text + id="text1033" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="5190 5419 5596 5774 5952 6113 6291 6468 6646 6824 6985 7146 7324 7586 7692" + y="16006" + id="tspan1035">w_e_send_csum()</tspan> + </text> + <path + d="M 8000,15501 L 7900,15201 L 8100,15201 L 8000,15501 z" + id="path1045" + style="fill:#008000;visibility:visible" /> + <path + d="M 8000,14701 L 8000,15261" + id="path1049" + style="fill:none;stroke:#008000;visibility:visible" /> + <text + id="text1065" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="4492 4670 4776 4953 5131 5309 5487 5665 5842 5914 6092 6270 6376 6554 6731 6909 7087 7248 7426 7587 7692" + y="15507" + id="tspan1067">drbd_endio_read_sec()</tspan> + </text> + <path + d="M 16100,9000 L 16300,9000 L 16300,7500 L 16100,7500" + id="path1077" + style="fill:none;stroke:#000000;visibility:visible" /> + <path + d="M 16100,18000 L 16300,18000 L 16300,16500 L 16100,16500" + id="path1089" + style="fill:none;stroke:#000000;visibility:visible" /> + <path + d="M 16100,25000 L 16300,25000 L 16300,23500 L 16100,23500" + id="path1101" + style="fill:none;stroke:#000000;visibility:visible" /> + <text + id="text1117" + style="font-size:318px;font-weight:400;fill:#000000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="2026 2132 2293 2471 2648 2826 3004 3076 3254 3431 3503 3681 3787" + y="5402" + id="tspan1119">rs_begin_io()</tspan> + </text> + <text + id="text1133" + style="font-size:318px;font-weight:400;fill:#000000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="2027 2133 2294 2472 2649 2827 3005 3077 3255 3432 3504 3682 3788" + y="14402" + id="tspan1135">rs_begin_io()</tspan> + </text> + <text + id="text1149" + style="font-size:318px;font-weight:400;fill:#000000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="2026 2132 2293 2471 2648 2826 3004 3076 3254 3431 3503 3681 3787" + y="22602" + id="tspan1151">rs_begin_io()</tspan> + </text> + <text + id="text1165" + style="font-size:318px;font-weight:400;fill:#000000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="1426 1532 1693 1871 2031 2209 2472 2649 2721 2899 2988 3166 3344 3416 3593 3699" + y="11302" + id="tspan1167">rs_complete_io()</tspan> + </text> + <text + id="text1181" + style="font-size:318px;font-weight:400;fill:#000000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="1526 1632 1793 1971 2131 2309 2572 2749 2821 2999 3088 3266 3444 3516 3693 3799" + y="18931" + id="tspan1183">rs_complete_io()</tspan> + </text> + <text + id="text1197" + style="font-size:318px;font-weight:400;fill:#000000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="1526 1632 1793 1971 2131 2309 2572 2749 2821 2999 3088 3266 3444 3516 3693 3799" + y="27231" + id="tspan1199">rs_complete_io()</tspan> + </text> + <text + id="text1213" + style="font-size:318px;font-weight:400;fill:#000000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="16126 16232 16393 16571 16748 16926 17104 17176 17354 17531 17603 17781 17887" + y="7402" + id="tspan1215">rs_begin_io()</tspan> + </text> + <text + id="text1229" + style="font-size:318px;font-weight:400;fill:#000000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="16127 16233 16394 16572 16749 16927 17105 17177 17355 17532 17604 17782 17888" + y="16331" + id="tspan1231">rs_begin_io()</tspan> + </text> + <text + id="text1245" + style="font-size:318px;font-weight:400;fill:#000000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="16127 16233 16394 16572 16749 16927 17105 17177 17355 17532 17604 17782 17888" + y="23302" + id="tspan1247">rs_begin_io()</tspan> + </text> + <text + id="text1261" + style="font-size:318px;font-weight:400;fill:#000000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="16115 16221 16382 16560 16720 16898 17161 17338 17410 17588 17677 17855 18033 18105 18282 18388" + y="9302" + id="tspan1263">rs_complete_io()</tspan> + </text> + <text + id="text1277" + style="font-size:318px;font-weight:400;fill:#000000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="16115 16221 16382 16560 16720 16898 17161 17338 17410 17588 17677 17855 18033 18105 18282 18388" + y="18331" + id="tspan1279">rs_complete_io()</tspan> + </text> + <text + id="text1293" + style="font-size:318px;font-weight:400;fill:#000000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="16126 16232 16393 16571 16731 16909 17172 17349 17421 17599 17688 17866 18044 18116 18293 18399" + y="25302" + id="tspan1295">rs_complete_io()</tspan> + </text> +</svg> diff --git a/Documentation/admin-guide/blockdev/drbd/DRBD-data-packets.svg b/Documentation/admin-guide/blockdev/drbd/DRBD-data-packets.svg new file mode 100644 index 0000000000..48a1e2165f --- /dev/null +++ b/Documentation/admin-guide/blockdev/drbd/DRBD-data-packets.svg @@ -0,0 +1,459 @@ +<?xml version="1.0" encoding="UTF-8" standalone="no"?> +<!-- Created with Inkscape (http://www.inkscape.org/) --> +<svg + xmlns:svg="http://www.w3.org/2000/svg" + xmlns="http://www.w3.org/2000/svg" + version="1.0" + width="210mm" + height="297mm" + viewBox="0 0 21000 29700" + id="svg2" + style="fill-rule:evenodd"> + <defs + id="defs4" /> + <g + id="Default" + style="visibility:visible"> + <desc + id="desc176">Master slide</desc> + </g> + <path + d="M 11999,19601 L 11899,19301 L 12099,19301 L 11999,19601 z" + id="path189" + style="fill:#008000;visibility:visible" /> + <path + d="M 11999,18801 L 11999,19361" + id="path193" + style="fill:none;stroke:#008000;visibility:visible" /> + <path + d="M 7999,21401 L 7899,21101 L 8099,21101 L 7999,21401 z" + id="path205" + style="fill:#008000;visibility:visible" /> + <path + d="M 7999,20601 L 7999,21161" + id="path209" + style="fill:none;stroke:#008000;visibility:visible" /> + <path + d="M 11999,18801 L 11685,18840 L 11724,18644 L 11999,18801 z" + id="path221" + style="fill:#008000;visibility:visible" /> + <path + d="M 7999,18001 L 11764,18754" + id="path225" + style="fill:none;stroke:#008000;visibility:visible" /> + <text + x="-3023.845" + y="1106.8124" + transform="matrix(0.9895258,-0.1443562,0.1443562,0.9895258,0,0)" + id="text243" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="6115.1553 6344.1553 6555.1553 6784.1553 6962.1553 7051.1553 7228.1553 7457.1553 7635.1553 7813.1553 7885.1553" + y="21390.812" + id="tspan245">RSDataReply</tspan> + </text> + <path + d="M 7999,20601 L 8281,20458 L 8311,20655 L 7999,20601 z" + id="path255" + style="fill:#008000;visibility:visible" /> + <path + d="M 11999,20001 L 8236,20565" + id="path259" + style="fill:none;stroke:#008000;visibility:visible" /> + <text + x="3502.5356" + y="-2184.6621" + transform="matrix(0.9788674,0.2044961,-0.2044961,0.9788674,0,0)" + id="text277" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="12321.536 12550.536 12761.536 12990.536 13168.536 13257.536 13434.536 13663.536 13841.536 14019.536 14196.536 14374.536 14535.536" + y="15854.338" + id="tspan279">RSDataRequest</tspan> + </text> + <text + id="text293" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="4034 4263 4440 4703 4881 5042 5219 5397 5503 5681 5842 6003 6180 6341 6519 6625 6803 6980 7158 7336 7497 7586 7692" + y="17807" + id="tspan295">w_make_resync_request()</tspan> + </text> + <text + id="text309" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="12199 12305 12483 12644 12821 12893 13054 13232 13410 13638 13816 13905 14083 14311 14489 14667 14845 15023 15184 15272 15378" + y="18806" + id="tspan311">receive_DataRequest()</tspan> + </text> + <text + id="text325" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="12199 12377 12483 12660 12838 13016 13194 13372 13549 13621 13799 13977 14083 14261 14438 14616 14794 14955 15133 15294 15399" + y="19606" + id="tspan327">drbd_endio_read_sec()</tspan> + </text> + <text + id="text341" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="12191 12420 12597 12775 12953 13131 13309 13486 13664 13770 13931 14109 14287 14375 14553 14731 14837 15015 15192 15298" + y="20007" + id="tspan343">w_e_end_rsdata_req()</tspan> + </text> + <text + id="text357" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="4444 4550 4728 4889 5066 5138 5299 5477 5655 5883 6095 6324 6501 6590 6768 6997 7175 7352 7424 7585 7691" + y="20507" + id="tspan359">receive_RSDataReply()</tspan> + </text> + <text + id="text373" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="4457 4635 4741 4918 5096 5274 5452 5630 5807 5879 6057 6235 6464 6569 6641 6730 6908 7086 7247 7425 7585 7691" + y="21407" + id="tspan375">drbd_endio_write_sec()</tspan> + </text> + <text + id="text389" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="4647 4825 5003 5180 5358 5536 5714 5820 5997 6158 6319 6497 6658 6836 7013 7085 7263 7424 7585 7691" + y="21907" + id="tspan391">e_end_resync_block()</tspan> + </text> + <path + d="M 11999,22601 L 11685,22640 L 11724,22444 L 11999,22601 z" + id="path401" + style="fill:#000080;visibility:visible" /> + <path + d="M 7999,21801 L 11764,22554" + id="path405" + style="fill:none;stroke:#000080;visibility:visible" /> + <text + x="4290.3008" + y="-2369.6162" + transform="matrix(0.9788674,0.2044961,-0.2044961,0.9788674,0,0)" + id="text423" + style="font-size:318px;font-weight:400;fill:#000080;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="13610.301 13911.301 14016.301 14088.301 14177.301 14355.301 14567.301 14728.301" + y="19573.385" + id="tspan425">WriteAck</tspan> + </text> + <text + id="text439" + style="font-size:318px;font-weight:400;fill:#000080;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="12199 12377 12555 12644 12821 13033 13105 13283 13444 13604 13816 13977 14138 14244" + y="22559" + id="tspan441">got_BlockAck()</tspan> + </text> + <text + id="text455" + style="font-size:423px;font-weight:400;fill:#000000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="7999 8304 8541 8753 8964 9201 9413 9531 9769 9862 10099 10310 10522 10734 10852 10971 11208 11348 11585 11822" + y="16877" + id="tspan457">Resync blocks, 4-32K</tspan> + </text> + <path + d="M 12000,7601 L 11900,7301 L 12100,7301 L 12000,7601 z" + id="path467" + style="fill:#008000;visibility:visible" /> + <path + d="M 12000,6801 L 12000,7361" + id="path471" + style="fill:none;stroke:#008000;visibility:visible" /> + <path + d="M 12000,6801 L 11686,6840 L 11725,6644 L 12000,6801 z" + id="path483" + style="fill:#008000;visibility:visible" /> + <path + d="M 8000,6001 L 11765,6754" + id="path487" + style="fill:none;stroke:#008000;visibility:visible" /> + <text + x="-1288.1796" + y="1279.7666" + transform="matrix(0.9895258,-0.1443562,0.1443562,0.9895258,0,0)" + id="text505" + style="font-size:318px;font-weight:400;fill:#000080;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="8174.8208 8475.8203 8580.8203 8652.8203 8741.8203 8919.8203 9131.8203 9292.8203" + y="9516.7666" + id="tspan507">WriteAck</tspan> + </text> + <path + d="M 8000,8601 L 8282,8458 L 8312,8655 L 8000,8601 z" + id="path517" + style="fill:#000080;visibility:visible" /> + <path + d="M 12000,8001 L 8237,8565" + id="path521" + style="fill:none;stroke:#000080;visibility:visible" /> + <text + x="1065.6655" + y="-2097.7664" + transform="matrix(0.9788674,0.2044961,-0.2044961,0.9788674,0,0)" + id="text539" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="10682.666 10911.666 11088.666 11177.666" + y="4107.2339" + id="tspan541">Data</tspan> + </text> + <text + id="text555" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="4746 4924 5030 5207 5385 5563 5826 6003 6164 6342 6520 6626 6803 6981 7159 7337 7498 7587 7692" + y="5505" + id="tspan557">drbd_make_request()</tspan> + </text> + <text + id="text571" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="12200 12306 12484 12645 12822 12894 13055 13233 13411 13639 13817 13906 14084 14190" + y="6806" + id="tspan573">receive_Data()</tspan> + </text> + <text + id="text587" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="12200 12378 12484 12661 12839 13017 13195 13373 13550 13622 13800 13978 14207 14312 14384 14473 14651 14829 14990 15168 15328 15434" + y="7606" + id="tspan589">drbd_endio_write_sec()</tspan> + </text> + <text + id="text603" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="12192 12370 12548 12725 12903 13081 13259 13437 13509 13686 13847 14008 14114" + y="8007" + id="tspan605">e_end_block()</tspan> + </text> + <text + id="text619" + style="font-size:318px;font-weight:400;fill:#000080;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="5647 5825 6003 6092 6269 6481 6553 6731 6892 7052 7264 7425 7586 7692" + y="8606" + id="tspan621">got_BlockAck()</tspan> + </text> + <text + id="text635" + style="font-size:423px;font-weight:400;fill:#000000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="8000 8305 8542 8779 9016 9109 9346 9486 9604 9956 10049 10189 10328 10565 10705 10942 11179 11298 11603 11742 11835 11954 12191 12310 12428 12665 12902 13139 13279 13516 13753" + y="4877" + id="tspan637">Regular mirrored write, 512-32K</tspan> + </text> + <text + id="text651" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="5381 5610 5787 5948 6126 6304 6482 6659 6837 7015 7087 7265 7426 7587 7692" + y="6003" + id="tspan653">w_send_dblock()</tspan> + </text> + <path + d="M 8000,6800 L 7900,6500 L 8100,6500 L 8000,6800 z" + id="path663" + style="fill:#008000;visibility:visible" /> + <path + d="M 8000,6000 L 8000,6560" + id="path667" + style="fill:none;stroke:#008000;visibility:visible" /> + <text + id="text683" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="4602 4780 4886 5063 5241 5419 5597 5775 5952 6024 6202 6380 6609 6714 6786 6875 7053 7231 7409 7515 7587 7692" + y="6905" + id="tspan685">drbd_endio_write_pri()</tspan> + </text> + <path + d="M 12000,13602 L 11900,13302 L 12100,13302 L 12000,13602 z" + id="path695" + style="fill:#008000;visibility:visible" /> + <path + d="M 12000,12802 L 12000,13362" + id="path699" + style="fill:none;stroke:#008000;visibility:visible" /> + <path + d="M 12000,12802 L 11686,12841 L 11725,12645 L 12000,12802 z" + id="path711" + style="fill:#008000;visibility:visible" /> + <path + d="M 8000,12002 L 11765,12755" + id="path715" + style="fill:none;stroke:#008000;visibility:visible" /> + <text + x="-2155.5266" + y="1201.5964" + transform="matrix(0.9895258,-0.1443562,0.1443562,0.9895258,0,0)" + id="text733" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="7202.4736 7431.4736 7608.4736 7697.4736 7875.4736 8104.4736 8282.4736 8459.4736 8531.4736" + y="15454.597" + id="tspan735">DataReply</tspan> + </text> + <path + d="M 8000,14602 L 8282,14459 L 8312,14656 L 8000,14602 z" + id="path745" + style="fill:#008000;visibility:visible" /> + <path + d="M 12000,14002 L 8237,14566" + id="path749" + style="fill:none;stroke:#008000;visibility:visible" /> + <text + x="2280.3804" + y="-2103.2141" + transform="matrix(0.9788674,0.2044961,-0.2044961,0.9788674,0,0)" + id="text767" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="11316.381 11545.381 11722.381 11811.381 11989.381 12218.381 12396.381 12573.381 12751.381 12929.381 13090.381" + y="9981.7861" + id="tspan769">DataRequest</tspan> + </text> + <text + id="text783" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="4746 4924 5030 5207 5385 5563 5826 6003 6164 6342 6520 6626 6803 6981 7159 7337 7498 7587 7692" + y="11506" + id="tspan785">drbd_make_request()</tspan> + </text> + <text + id="text799" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="12200 12306 12484 12645 12822 12894 13055 13233 13411 13639 13817 13906 14084 14312 14490 14668 14846 15024 15185 15273 15379" + y="12807" + id="tspan801">receive_DataRequest()</tspan> + </text> + <text + id="text815" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="12200 12378 12484 12661 12839 13017 13195 13373 13550 13622 13800 13978 14084 14262 14439 14617 14795 14956 15134 15295 15400" + y="13607" + id="tspan817">drbd_endio_read_sec()</tspan> + </text> + <text + id="text831" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="12192 12421 12598 12776 12954 13132 13310 13487 13665 13843 14021 14110 14288 14465 14571 14749 14927 15033" + y="14008" + id="tspan833">w_e_end_data_req()</tspan> + </text> + <g + id="g835" + style="visibility:visible"> + <desc + id="desc837">Drawing</desc> + <text + id="text847" + style="font-size:318px;font-weight:400;fill:#008000;font-family:Helvetica embedded"> + <tspan + x="4885 4991 5169 5330 5507 5579 5740 5918 6096 6324 6502 6591 6769 6997 7175 7353 7425 7586 7692" + y="14607" + id="tspan849">receive_DataReply()</tspan> + </text> + </g> + <text + id="text863" + style="font-size:423px;font-weight:400;fill:#000000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="8000 8305 8398 8610 8821 8914 9151 9363 9575 9693 9833 10070 10307 10544 10663 10781 11018 11255 11493 11632 11869 12106" + y="10878" + id="tspan865">Diskless read, 512-32K</tspan> + </text> + <text + id="text879" + style="font-size:318px;font-weight:400;fill:#008000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="5029 5258 5435 5596 5774 5952 6130 6307 6413 6591 6769 6947 7125 7230 7408 7586 7692" + y="12004" + id="tspan881">w_send_read_req()</tspan> + </text> + <text + id="text895" + style="font-size:423px;font-weight:400;fill:#000000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="6961 7266 7571 7854 8159 8278 8515 8633 8870 9107 9226 9463 9581 9700 9793 10030" + y="2806" + id="tspan897">DRBD 8 data flow</tspan> + </text> + <path + d="M 3900,5300 L 3700,5300 L 3700,7000 L 3900,7000" + id="path907" + style="fill:none;stroke:#000000;visibility:visible" /> + <path + d="M 3900,17600 L 3700,17600 L 3700,22000 L 3900,22000" + id="path919" + style="fill:none;stroke:#000000;visibility:visible" /> + <path + d="M 16100,20000 L 16300,20000 L 16300,18500 L 16100,18500" + id="path931" + style="fill:none;stroke:#000000;visibility:visible" /> + <text + id="text947" + style="font-size:318px;font-weight:400;fill:#000000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="2126 2304 2376 2554 2731 2909 3087 3159 3337 3515 3587 3764 3870" + y="5202" + id="tspan949">al_begin_io()</tspan> + </text> + <text + id="text963" + style="font-size:318px;font-weight:400;fill:#000000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="1632 1810 1882 2060 2220 2398 2661 2839 2910 3088 3177 3355 3533 3605 3783 3888" + y="7331" + id="tspan965">al_complete_io()</tspan> + </text> + <text + id="text979" + style="font-size:318px;font-weight:400;fill:#000000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="2126 2232 2393 2571 2748 2926 3104 3176 3354 3531 3603 3781 3887" + y="17431" + id="tspan981">rs_begin_io()</tspan> + </text> + <text + id="text995" + style="font-size:318px;font-weight:400;fill:#000000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="1626 1732 1893 2071 2231 2409 2672 2849 2921 3099 3188 3366 3544 3616 3793 3899" + y="22331" + id="tspan997">rs_complete_io()</tspan> + </text> + <text + id="text1011" + style="font-size:318px;font-weight:400;fill:#000000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="16027 16133 16294 16472 16649 16827 17005 17077 17255 17432 17504 17682 17788" + y="18402" + id="tspan1013">rs_begin_io()</tspan> + </text> + <text + id="text1027" + style="font-size:318px;font-weight:400;fill:#000000;visibility:visible;font-family:Helvetica embedded"> + <tspan + x="16115 16221 16382 16560 16720 16898 17161 17338 17410 17588 17677 17855 18033 18105 18282 18388" + y="20331" + id="tspan1029">rs_complete_io()</tspan> + </text> +</svg> diff --git a/Documentation/admin-guide/blockdev/drbd/conn-states-8.dot b/Documentation/admin-guide/blockdev/drbd/conn-states-8.dot new file mode 100644 index 0000000000..025e8cf5e6 --- /dev/null +++ b/Documentation/admin-guide/blockdev/drbd/conn-states-8.dot @@ -0,0 +1,18 @@ +digraph conn_states { + StandAllone -> WFConnection [ label = "ioctl_set_net()" ] + WFConnection -> Unconnected [ label = "unable to bind()" ] + WFConnection -> WFReportParams [ label = "in connect() after accept" ] + WFReportParams -> StandAllone [ label = "checks in receive_param()" ] + WFReportParams -> Connected [ label = "in receive_param()" ] + WFReportParams -> WFBitMapS [ label = "sync_handshake()" ] + WFReportParams -> WFBitMapT [ label = "sync_handshake()" ] + WFBitMapS -> SyncSource [ label = "receive_bitmap()" ] + WFBitMapT -> SyncTarget [ label = "receive_bitmap()" ] + SyncSource -> Connected + SyncTarget -> Connected + SyncSource -> PausedSyncS + SyncTarget -> PausedSyncT + PausedSyncS -> SyncSource + PausedSyncT -> SyncTarget + Connected -> WFConnection [ label = "* on network error" ] +} diff --git a/Documentation/admin-guide/blockdev/drbd/data-structure-v9.rst b/Documentation/admin-guide/blockdev/drbd/data-structure-v9.rst new file mode 100644 index 0000000000..66036b9016 --- /dev/null +++ b/Documentation/admin-guide/blockdev/drbd/data-structure-v9.rst @@ -0,0 +1,42 @@ +================================ +kernel data structure for DRBD-9 +================================ + +This describes the in kernel data structure for DRBD-9. Starting with +Linux v3.14 we are reorganizing DRBD to use this data structure. + +Basic Data Structure +==================== + +A node has a number of DRBD resources. Each such resource has a number of +devices (aka volumes) and connections to other nodes ("peer nodes"). Each DRBD +device is represented by a block device locally. + +The DRBD objects are interconnected to form a matrix as depicted below; a +drbd_peer_device object sits at each intersection between a drbd_device and a +drbd_connection:: + + /--------------+---------------+.....+---------------\ + | resource | device | | device | + +--------------+---------------+.....+---------------+ + | connection | peer_device | | peer_device | + +--------------+---------------+.....+---------------+ + : : : : : + : : : : : + +--------------+---------------+.....+---------------+ + | connection | peer_device | | peer_device | + \--------------+---------------+.....+---------------/ + +In this table, horizontally, devices can be accessed from resources by their +volume number. Likewise, peer_devices can be accessed from connections by +their volume number. Objects in the vertical direction are connected by double +linked lists. There are back pointers from peer_devices to their connections a +devices, and from connections and devices to their resource. + +All resources are in the drbd_resources double-linked list. In addition, all +devices can be accessed by their minor device number via the drbd_devices idr. + +The drbd_resource, drbd_connection, and drbd_device objects are reference +counted. The peer_device objects only serve to establish the links between +devices and connections; their lifetime is determined by the lifetime of the +device and connection which they reference. diff --git a/Documentation/admin-guide/blockdev/drbd/disk-states-8.dot b/Documentation/admin-guide/blockdev/drbd/disk-states-8.dot new file mode 100644 index 0000000000..d06cfb46fb --- /dev/null +++ b/Documentation/admin-guide/blockdev/drbd/disk-states-8.dot @@ -0,0 +1,16 @@ +digraph disk_states { + Diskless -> Inconsistent [ label = "ioctl_set_disk()" ] + Diskless -> Consistent [ label = "ioctl_set_disk()" ] + Diskless -> Outdated [ label = "ioctl_set_disk()" ] + Consistent -> Outdated [ label = "receive_param()" ] + Consistent -> UpToDate [ label = "receive_param()" ] + Consistent -> Inconsistent [ label = "start resync" ] + Outdated -> Inconsistent [ label = "start resync" ] + UpToDate -> Inconsistent [ label = "ioctl_replicate" ] + Inconsistent -> UpToDate [ label = "resync completed" ] + Consistent -> Failed [ label = "io completion error" ] + Outdated -> Failed [ label = "io completion error" ] + UpToDate -> Failed [ label = "io completion error" ] + Inconsistent -> Failed [ label = "io completion error" ] + Failed -> Diskless [ label = "sending notify to peer" ] +} diff --git a/Documentation/admin-guide/blockdev/drbd/drbd-connection-state-overview.dot b/Documentation/admin-guide/blockdev/drbd/drbd-connection-state-overview.dot new file mode 100644 index 0000000000..6d9cf0a7b1 --- /dev/null +++ b/Documentation/admin-guide/blockdev/drbd/drbd-connection-state-overview.dot @@ -0,0 +1,85 @@ +// vim: set sw=2 sts=2 : +digraph { + rankdir=BT + bgcolor=white + + node [shape=plaintext] + node [fontcolor=black] + + StandAlone [ style=filled,fillcolor=gray,label=StandAlone ] + + node [fontcolor=lightgray] + + Unconnected [ label=Unconnected ] + + CommTrouble [ shape=record, + label="{communication loss|{Timeout|BrokenPipe|NetworkFailure}}" ] + + node [fontcolor=gray] + + subgraph cluster_try_connect { + label="try to connect, handshake" + rank=max + WFConnection [ label=WFConnection ] + WFReportParams [ label=WFReportParams ] + } + + TearDown [ label=TearDown ] + + Connected [ label=Connected,style=filled,fillcolor=green,fontcolor=black ] + + node [fontcolor=lightblue] + + StartingSyncS [ label=StartingSyncS ] + StartingSyncT [ label=StartingSyncT ] + + subgraph cluster_bitmap_exchange { + node [fontcolor=red] + fontcolor=red + label="new application (WRITE?) requests blocked\lwhile bitmap is exchanged" + + WFBitMapT [ label=WFBitMapT ] + WFSyncUUID [ label=WFSyncUUID ] + WFBitMapS [ label=WFBitMapS ] + } + + node [fontcolor=blue] + + cluster_resync [ shape=record,label="{<any>resynchronisation process running\l'concurrent' application requests allowed|{{<T>PausedSyncT\nSyncTarget}|{<S>PausedSyncS\nSyncSource}}}" ] + + node [shape=box,fontcolor=black] + + // drbdadm [label="drbdadm connect"] + // handshake [label="drbd_connect()\ndrbd_do_handshake\ndrbd_sync_handshake() etc."] + // comm_error [label="communication trouble"] + + // + // edges + // -------------------------------------- + + StandAlone -> Unconnected [ label="drbdadm connect" ] + Unconnected -> StandAlone [ label="drbdadm disconnect\lor serious communication trouble" ] + Unconnected -> WFConnection [ label="receiver thread is started" ] + WFConnection -> WFReportParams [ headlabel="accept()\land/or \lconnect()\l" ] + + WFReportParams -> StandAlone [ label="during handshake\lpeers do not agree\labout something essential" ] + WFReportParams -> Connected [ label="data identical\lno sync needed",color=green,fontcolor=green ] + + WFReportParams -> WFBitMapS + WFReportParams -> WFBitMapT + WFBitMapT -> WFSyncUUID [minlen=0.1,constraint=false] + + WFBitMapS -> cluster_resync:S + WFSyncUUID -> cluster_resync:T + + edge [color=green] + cluster_resync:any -> Connected [ label="resnyc done",fontcolor=green ] + + edge [color=red] + WFReportParams -> CommTrouble + Connected -> CommTrouble + cluster_resync:any -> CommTrouble + edge [color=black] + CommTrouble -> Unconnected [label="receiver thread is stopped" ] + +} diff --git a/Documentation/admin-guide/blockdev/drbd/figures.rst b/Documentation/admin-guide/blockdev/drbd/figures.rst new file mode 100644 index 0000000000..9f73253ea3 --- /dev/null +++ b/Documentation/admin-guide/blockdev/drbd/figures.rst @@ -0,0 +1,30 @@ +.. SPDX-License-Identifier: GPL-2.0 + +.. The here included files are intended to help understand the implementation + +Data flows that Relate some functions, and write packets +======================================================== + +.. kernel-figure:: DRBD-8.3-data-packets.svg + :alt: DRBD-8.3-data-packets.svg + :align: center + +.. kernel-figure:: DRBD-data-packets.svg + :alt: DRBD-data-packets.svg + :align: center + + +Sub graphs of DRBD's state transitions +====================================== + +.. kernel-figure:: conn-states-8.dot + :alt: conn-states-8.dot + :align: center + +.. kernel-figure:: disk-states-8.dot + :alt: disk-states-8.dot + :align: center + +.. kernel-figure:: peer-states-8.dot + :alt: peer-states-8.dot + :align: center diff --git a/Documentation/admin-guide/blockdev/drbd/index.rst b/Documentation/admin-guide/blockdev/drbd/index.rst new file mode 100644 index 0000000000..561fd1e359 --- /dev/null +++ b/Documentation/admin-guide/blockdev/drbd/index.rst @@ -0,0 +1,19 @@ +========================================== +Distributed Replicated Block Device - DRBD +========================================== + +Description +=========== + + DRBD is a shared-nothing, synchronously replicated block device. It + is designed to serve as a building block for high availability + clusters and in this context, is a "drop-in" replacement for shared + storage. Simplistically, you could see it as a network RAID 1. + + Please visit https://www.drbd.org to find out more. + +.. toctree:: + :maxdepth: 1 + + data-structure-v9 + figures diff --git a/Documentation/admin-guide/blockdev/drbd/peer-states-8.dot b/Documentation/admin-guide/blockdev/drbd/peer-states-8.dot new file mode 100644 index 0000000000..6dc3954954 --- /dev/null +++ b/Documentation/admin-guide/blockdev/drbd/peer-states-8.dot @@ -0,0 +1,8 @@ +digraph peer_states { + Secondary -> Primary [ label = "recv state packet" ] + Primary -> Secondary [ label = "recv state packet" ] + Primary -> Unknown [ label = "connection lost" ] + Secondary -> Unknown [ label = "connection lost" ] + Unknown -> Primary [ label = "connected" ] + Unknown -> Secondary [ label = "connected" ] +} diff --git a/Documentation/admin-guide/blockdev/floppy.rst b/Documentation/admin-guide/blockdev/floppy.rst new file mode 100644 index 0000000000..0328438ebe --- /dev/null +++ b/Documentation/admin-guide/blockdev/floppy.rst @@ -0,0 +1,255 @@ +============= +Floppy Driver +============= + +FAQ list: +========= + +A FAQ list may be found in the fdutils package (see below), and also +at <https://fdutils.linux.lu/faq.html>. + + +LILO configuration options (Thinkpad users, read this) +====================================================== + +The floppy driver is configured using the 'floppy=' option in +lilo. This option can be typed at the boot prompt, or entered in the +lilo configuration file. + +Example: If your kernel is called linux-2.6.9, type the following line +at the lilo boot prompt (if you have a thinkpad):: + + linux-2.6.9 floppy=thinkpad + +You may also enter the following line in /etc/lilo.conf, in the description +of linux-2.6.9:: + + append = "floppy=thinkpad" + +Several floppy related options may be given, example:: + + linux-2.6.9 floppy=daring floppy=two_fdc + append = "floppy=daring floppy=two_fdc" + +If you give options both in the lilo config file and on the boot +prompt, the option strings of both places are concatenated, the boot +prompt options coming last. That's why there are also options to +restore the default behavior. + + +Module configuration options +============================ + +If you use the floppy driver as a module, use the following syntax:: + + modprobe floppy floppy="<options>" + +Example:: + + modprobe floppy floppy="omnibook messages" + +If you need certain options enabled every time you load the floppy driver, +you can put:: + + options floppy floppy="omnibook messages" + +in a configuration file in /etc/modprobe.d/. + + +The floppy driver related options are: + + floppy=asus_pci + Sets the bit mask to allow only units 0 and 1. (default) + + floppy=daring + Tells the floppy driver that you have a well behaved floppy controller. + This allows more efficient and smoother operation, but may fail on + certain controllers. This may speed up certain operations. + + floppy=0,daring + Tells the floppy driver that your floppy controller should be used + with caution. + + floppy=one_fdc + Tells the floppy driver that you have only one floppy controller. + (default) + + floppy=two_fdc / floppy=<address>,two_fdc + Tells the floppy driver that you have two floppy controllers. + The second floppy controller is assumed to be at <address>. + This option is not needed if the second controller is at address + 0x370, and if you use the 'cmos' option. + + floppy=thinkpad + Tells the floppy driver that you have a Thinkpad. Thinkpads use an + inverted convention for the disk change line. + + floppy=0,thinkpad + Tells the floppy driver that you don't have a Thinkpad. + + floppy=omnibook / floppy=nodma + Tells the floppy driver not to use Dma for data transfers. + This is needed on HP Omnibooks, which don't have a workable + DMA channel for the floppy driver. This option is also useful + if you frequently get "Unable to allocate DMA memory" messages. + Indeed, dma memory needs to be continuous in physical memory, + and is thus harder to find, whereas non-dma buffers may be + allocated in virtual memory. However, I advise against this if + you have an FDC without a FIFO (8272A or 82072). 82072A and + later are OK. You also need at least a 486 to use nodma. + If you use nodma mode, I suggest you also set the FIFO + threshold to 10 or lower, in order to limit the number of data + transfer interrupts. + + If you have a FIFO-able FDC, the floppy driver automatically + falls back on non DMA mode if no DMA-able memory can be found. + If you want to avoid this, explicitly ask for 'yesdma'. + + floppy=yesdma + Tells the floppy driver that a workable DMA channel is available. + (default) + + floppy=nofifo + Disables the FIFO entirely. This is needed if you get "Bus + master arbitration error" messages from your Ethernet card (or + from other devices) while accessing the floppy. + + floppy=usefifo + Enables the FIFO. (default) + + floppy=<threshold>,fifo_depth + Sets the FIFO threshold. This is mostly relevant in DMA + mode. If this is higher, the floppy driver tolerates more + interrupt latency, but it triggers more interrupts (i.e. it + imposes more load on the rest of the system). If this is + lower, the interrupt latency should be lower too (faster + processor). The benefit of a lower threshold is less + interrupts. + + To tune the fifo threshold, switch on over/underrun messages + using 'floppycontrol --messages'. Then access a floppy + disk. If you get a huge amount of "Over/Underrun - retrying" + messages, then the fifo threshold is too low. Try with a + higher value, until you only get an occasional Over/Underrun. + It is a good idea to compile the floppy driver as a module + when doing this tuning. Indeed, it allows to try different + fifo values without rebooting the machine for each test. Note + that you need to do 'floppycontrol --messages' every time you + re-insert the module. + + Usually, tuning the fifo threshold should not be needed, as + the default (0xa) is reasonable. + + floppy=<drive>,<type>,cmos + Sets the CMOS type of <drive> to <type>. This is mandatory if + you have more than two floppy drives (only two can be + described in the physical CMOS), or if your BIOS uses + non-standard CMOS types. The CMOS types are: + + == ================================== + 0 Use the value of the physical CMOS + 1 5 1/4 DD + 2 5 1/4 HD + 3 3 1/2 DD + 4 3 1/2 HD + 5 3 1/2 ED + 6 3 1/2 ED + 16 unknown or not installed + == ================================== + + (Note: there are two valid types for ED drives. This is because 5 was + initially chosen to represent floppy *tapes*, and 6 for ED drives. + AMI ignored this, and used 5 for ED drives. That's why the floppy + driver handles both.) + + floppy=unexpected_interrupts + Print a warning message when an unexpected interrupt is received. + (default) + + floppy=no_unexpected_interrupts / floppy=L40SX + Don't print a message when an unexpected interrupt is received. This + is needed on IBM L40SX laptops in certain video modes. (There seems + to be an interaction between video and floppy. The unexpected + interrupts affect only performance, and can be safely ignored.) + + floppy=broken_dcl + Don't use the disk change line, but assume that the disk was + changed whenever the device node is reopened. Needed on some + boxes where the disk change line is broken or unsupported. + This should be regarded as a stopgap measure, indeed it makes + floppy operation less efficient due to unneeded cache + flushings, and slightly more unreliable. Please verify your + cable, connection and jumper settings if you have any DCL + problems. However, some older drives, and also some laptops + are known not to have a DCL. + + floppy=debug + Print debugging messages. + + floppy=messages + Print informational messages for some operations (disk change + notifications, warnings about over and underruns, and about + autodetection). + + floppy=silent_dcl_clear + Uses a less noisy way to clear the disk change line (which + doesn't involve seeks). Implied by 'daring' option. + + floppy=<nr>,irq + Sets the floppy IRQ to <nr> instead of 6. + + floppy=<nr>,dma + Sets the floppy DMA channel to <nr> instead of 2. + + floppy=slow + Use PS/2 stepping rate:: + + PS/2 floppies have much slower step rates than regular floppies. + It's been recommended that take about 1/4 of the default speed + in some more extreme cases. + + +Supporting utilities and additional documentation: +================================================== + +Additional parameters of the floppy driver can be configured at +runtime. Utilities which do this can be found in the fdutils package. +This package also contains a new version of mtools which allows to +access high capacity disks (up to 1992K on a high density 3 1/2 disk!). +It also contains additional documentation about the floppy driver. + +The latest version can be found at fdutils homepage: + + https://fdutils.linux.lu + +The fdutils releases can be found at: + + https://fdutils.linux.lu/download.html + + http://www.tux.org/pub/knaff/fdutils/ + + ftp://metalab.unc.edu/pub/Linux/utils/disk-management/ + +Reporting problems about the floppy driver +========================================== + +If you have a question or a bug report about the floppy driver, mail +me at Alain.Knaff@poboxes.com . If you post to Usenet, preferably use +comp.os.linux.hardware. As the volume in these groups is rather high, +be sure to include the word "floppy" (or "FLOPPY") in the subject +line. If the reported problem happens when mounting floppy disks, be +sure to mention also the type of the filesystem in the subject line. + +Be sure to read the FAQ before mailing/posting any bug reports! + +Alain + +Changelog +========= + +10-30-2004 : + Cleanup, updating, add reference to module configuration. + James Nelson <james4765@gmail.com> + +6-3-2000 : + Original Document diff --git a/Documentation/admin-guide/blockdev/index.rst b/Documentation/admin-guide/blockdev/index.rst new file mode 100644 index 0000000000..957ccf6177 --- /dev/null +++ b/Documentation/admin-guide/blockdev/index.rst @@ -0,0 +1,16 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============= +Block Devices +============= + +.. toctree:: + :maxdepth: 1 + + floppy + nbd + paride + ramdisk + zram + + drbd/index diff --git a/Documentation/admin-guide/blockdev/nbd.rst b/Documentation/admin-guide/blockdev/nbd.rst new file mode 100644 index 0000000000..faf2ac4b15 --- /dev/null +++ b/Documentation/admin-guide/blockdev/nbd.rst @@ -0,0 +1,31 @@ +================================== +Network Block Device (TCP version) +================================== + +1) Overview +----------- + +What is it: With this compiled in the kernel (or as a module), Linux +can use a remote server as one of its block devices. So every time +the client computer wants to read, e.g., /dev/nb0, it sends a +request over TCP to the server, which will reply with the data read. +This can be used for stations with low disk space (or even diskless) +to borrow disk space from another computer. +Unlike NFS, it is possible to put any filesystem on it, etc. + +For more information, or to download the nbd-client and nbd-server +tools, go to https://github.com/NetworkBlockDevice/nbd. + +The nbd kernel module need only be installed on the client +system, as the nbd-server is completely in userspace. In fact, +the nbd-server has been successfully ported to other operating +systems, including Windows. + +A) NBD parameters +----------------- + +max_part + Number of partitions per device (default: 0). + +nbds_max + Number of block devices that should be initialized (default: 16). diff --git a/Documentation/admin-guide/blockdev/paride.rst b/Documentation/admin-guide/blockdev/paride.rst new file mode 100644 index 0000000000..e85ad37cc0 --- /dev/null +++ b/Documentation/admin-guide/blockdev/paride.rst @@ -0,0 +1,207 @@ +=================================== +Linux and parallel port IDE devices +=================================== + +PARIDE v1.03 (c) 1997-8 Grant Guenther <grant@torque.net> +PATA_PARPORT (c) 2023 Ondrej Zary + +1. Introduction +=============== + +Owing to the simplicity and near universality of the parallel port interface +to personal computers, many external devices such as portable hard-disk, +CD-ROM, LS-120 and tape drives use the parallel port to connect to their +host computer. While some devices (notably scanners) use ad-hoc methods +to pass commands and data through the parallel port interface, most +external devices are actually identical to an internal model, but with +a parallel-port adapter chip added in. Some of the original parallel port +adapters were little more than mechanisms for multiplexing a SCSI bus. +(The Iomega PPA-3 adapter used in the ZIP drives is an example of this +approach). Most current designs, however, take a different approach. +The adapter chip reproduces a small ISA or IDE bus in the external device +and the communication protocol provides operations for reading and writing +device registers, as well as data block transfer functions. Sometimes, +the device being addressed via the parallel cable is a standard SCSI +controller like an NCR 5380. The "ditto" family of external tape +drives use the ISA replicator to interface a floppy disk controller, +which is then connected to a floppy-tape mechanism. The vast majority +of external parallel port devices, however, are now based on standard +IDE type devices, which require no intermediate controller. If one +were to open up a parallel port CD-ROM drive, for instance, one would +find a standard ATAPI CD-ROM drive, a power supply, and a single adapter +that interconnected a standard PC parallel port cable and a standard +IDE cable. It is usually possible to exchange the CD-ROM device with +any other device using the IDE interface. + +The document describes the support in Linux for parallel port IDE +devices. It does not cover parallel port SCSI devices, "ditto" tape +drives or scanners. Many different devices are supported by the +parallel port IDE subsystem, including: + + - MicroSolutions backpack CD-ROM + - MicroSolutions backpack PD/CD + - MicroSolutions backpack hard-drives + - MicroSolutions backpack 8000t tape drive + - SyQuest EZ-135, EZ-230 & SparQ drives + - Avatar Shark + - Imation Superdisk LS-120 + - Maxell Superdisk LS-120 + - FreeCom Power CD + - Hewlett-Packard 5GB and 8GB tape drives + - Hewlett-Packard 7100 and 7200 CD-RW drives + +as well as most of the clone and no-name products on the market. + +To support such a wide range of devices, pata_parport is actually structured +in two parts. There is a base pata_parport module which provides an interface +to kernel libata subsystem, registry and some common methods for accessing +the parallel ports. + +The second component is a set of low-level protocol drivers for each of the +parallel port IDE adapter chips. Thanks to the interest and encouragement of +Linux users from many parts of the world, support is available for almost all +known adapter protocols: + + ==== ====================================== ==== + aten ATEN EH-100 (HK) + bpck Microsolutions backpack (US) + comm DataStor (old-type) "commuter" adapter (TW) + dstr DataStor EP-2000 (TW) + epat Shuttle EPAT (UK) + epia Shuttle EPIA (UK) + fit2 FIT TD-2000 (US) + fit3 FIT TD-3000 (US) + friq Freecom IQ cable (DE) + frpw Freecom Power (DE) + kbic KingByte KBIC-951A and KBIC-971A (TW) + ktti KT Technology PHd adapter (SG) + on20 OnSpec 90c20 (US) + on26 OnSpec 90c26 (US) + ==== ====================================== ==== + + +2. Using pata_parport subsystem +=============================== + +While configuring the Linux kernel, you may choose either to build +the pata_parport drivers into your kernel, or to build them as modules. + +In either case, you will need to select "Parallel port IDE device support" +and at least one of the parallel port communication protocols. +If you do not know what kind of parallel port adapter is used in your drive, +you could begin by checking the file names and any text files on your DOS +installation floppy. Alternatively, you can look at the markings on +the adapter chip itself. That's usually sufficient to identify the +correct device. + +You can actually select all the protocol modules, and allow the pata_parport +subsystem to try them all for you. + +For the "brand-name" products listed above, here are the protocol +and high-level drivers that you would use: + + ================ ============ ======== + Manufacturer Model Protocol + ================ ============ ======== + MicroSolutions CD-ROM bpck + MicroSolutions PD drive bpck + MicroSolutions hard-drive bpck + MicroSolutions 8000t tape bpck + SyQuest EZ, SparQ epat + Imation Superdisk epat + Maxell Superdisk friq + Avatar Shark epat + FreeCom CD-ROM frpw + Hewlett-Packard 5GB Tape epat + Hewlett-Packard 7200e (CD) epat + Hewlett-Packard 7200e (CD-R) epat + ================ ============ ======== + +All parports and all protocol drivers are probed automatically unless probe=0 +parameter is used. So just "modprobe epat" is enough for a Imation SuperDisk +drive to work. + +Manual device creation:: + + # echo "port protocol mode unit delay" >/sys/bus/pata_parport/new_device + +where: + + ======== ================================================ + port parport name (or "auto" for all parports) + protocol protocol name (or "auto" for all protocols) + mode mode number (protocol-specific) or -1 for probe + unit unit number (for backpack only, see below) + delay I/O delay (see troubleshooting section below) + ======== ================================================ + +If you happen to be using a MicroSolutions backpack device, you will +also need to know the unit ID number for each drive. This is usually +the last two digits of the drive's serial number (but read MicroSolutions' +documentation about this). + +If you omit the parameters from the end, defaults will be used, e.g.: + +Probe all parports with all protocols:: + + # echo auto >/sys/bus/pata_parport/new_device + +Probe parport0 using protocol epat and mode 4 (EPP-16):: + + # echo "parport0 epat 4" >/sys/bus/pata_parport/new_device + +Probe parport0 using all protocols:: + + # echo "parport0 auto" >/sys/bus/pata_parport/new_device + +Probe all parports using protoocol epat:: + + # echo "auto epat" >/sys/bus/pata_parport/new_device + +Deleting devices:: + + # echo pata_parport.0 >/sys/bus/pata_parport/delete_device + + +3. Troubleshooting +================== + +3.1 Use EPP mode if you can +---------------------------- + +The most common problems that people report with the pata_parport drivers +concern the parallel port CMOS settings. At this time, none of the +protocol modules support ECP mode, or any ECP combination modes. +If you are able to do so, please set your parallel port into EPP mode +using your CMOS setup procedure. + +3.2 Check the port delay +------------------------- + +Some parallel ports cannot reliably transfer data at full speed. To +offset the errors, the protocol modules introduce a "port +delay" between each access to the i/o ports. Each protocol sets +a default value for this delay. In most cases, the user can override +the default and set it to 0 - resulting in somewhat higher transfer +rates. In some rare cases (especially with older 486 systems) the +default delays are not long enough. if you experience corrupt data +transfers, or unexpected failures, you may wish to increase the +port delay. + +3.3 Some drives need a printer reset +------------------------------------- + +There appear to be a number of "noname" external drives on the market +that do not always power up correctly. We have noticed this with some +drives based on OnSpec and older Freecom adapters. In these rare cases, +the adapter can often be reinitialised by issuing a "printer reset" on +the parallel port. As the reset operation is potentially disruptive in +multiple device environments, the pata_parport drivers will not do it +automatically. You can however, force a printer reset by doing:: + + insmod lp reset=1 + rmmod lp + +If you have one of these marginal cases, you should probably build +your pata_parport drivers as modules, and arrange to do the printer reset +before loading the pata_parport drivers. diff --git a/Documentation/admin-guide/blockdev/ramdisk.rst b/Documentation/admin-guide/blockdev/ramdisk.rst new file mode 100644 index 0000000000..9ce6101e8d --- /dev/null +++ b/Documentation/admin-guide/blockdev/ramdisk.rst @@ -0,0 +1,153 @@ +========================================== +Using the RAM disk block device with Linux +========================================== + +.. Contents: + + 1) Overview + 2) Kernel Command Line Parameters + 3) Using "rdev" + 4) An Example of Creating a Compressed RAM Disk + + +1) Overview +----------- + +The RAM disk driver is a way to use main system memory as a block device. It +is required for initrd, an initial filesystem used if you need to load modules +in order to access the root filesystem (see Documentation/admin-guide/initrd.rst). It can +also be used for a temporary filesystem for crypto work, since the contents +are erased on reboot. + +The RAM disk dynamically grows as more space is required. It does this by using +RAM from the buffer cache. The driver marks the buffers it is using as dirty +so that the VM subsystem does not try to reclaim them later. + +The RAM disk supports up to 16 RAM disks by default, and can be reconfigured +to support an unlimited number of RAM disks (at your own risk). Just change +the configuration symbol BLK_DEV_RAM_COUNT in the Block drivers config menu +and (re)build the kernel. + +To use RAM disk support with your system, run './MAKEDEV ram' from the /dev +directory. RAM disks are all major number 1, and start with minor number 0 +for /dev/ram0, etc. If used, modern kernels use /dev/ram0 for an initrd. + +The new RAM disk also has the ability to load compressed RAM disk images, +allowing one to squeeze more programs onto an average installation or +rescue floppy disk. + + +2) Parameters +--------------------------------- + +2a) Kernel Command Line Parameters + + ramdisk_size=N + Size of the ramdisk. + +This parameter tells the RAM disk driver to set up RAM disks of N k size. The +default is 4096 (4 MB). + +2b) Module parameters + + rd_nr + /dev/ramX devices created. + + max_part + Maximum partition number. + + rd_size + See ramdisk_size. + +3) Using "rdev" +--------------- + +"rdev" is an obsolete, deprecated, antiquated utility that could be used +to set the boot device in a Linux kernel image. + +Instead of using rdev, just place the boot device information on the +kernel command line and pass it to the kernel from the bootloader. + +You can also pass arguments to the kernel by setting FDARGS in +arch/x86/boot/Makefile and specify in initrd image by setting FDINITRD in +arch/x86/boot/Makefile. + +Some of the kernel command line boot options that may apply here are:: + + ramdisk_start=N + ramdisk_size=M + +If you make a boot disk that has LILO, then for the above, you would use:: + + append = "ramdisk_start=N ramdisk_size=M" + +4) An Example of Creating a Compressed RAM Disk +----------------------------------------------- + +To create a RAM disk image, you will need a spare block device to +construct it on. This can be the RAM disk device itself, or an +unused disk partition (such as an unmounted swap partition). For this +example, we will use the RAM disk device, "/dev/ram0". + +Note: This technique should not be done on a machine with less than 8 MB +of RAM. If using a spare disk partition instead of /dev/ram0, then this +restriction does not apply. + +a) Decide on the RAM disk size that you want. Say 2 MB for this example. + Create it by writing to the RAM disk device. (This step is not currently + required, but may be in the future.) It is wise to zero out the + area (esp. for disks) so that maximal compression is achieved for + the unused blocks of the image that you are about to create:: + + dd if=/dev/zero of=/dev/ram0 bs=1k count=2048 + +b) Make a filesystem on it. Say ext2fs for this example:: + + mke2fs -vm0 /dev/ram0 2048 + +c) Mount it, copy the files you want to it (eg: /etc/* /dev/* ...) + and unmount it again. + +d) Compress the contents of the RAM disk. The level of compression + will be approximately 50% of the space used by the files. Unused + space on the RAM disk will compress to almost nothing:: + + dd if=/dev/ram0 bs=1k count=2048 | gzip -v9 > /tmp/ram_image.gz + +e) Put the kernel onto the floppy:: + + dd if=zImage of=/dev/fd0 bs=1k + +f) Put the RAM disk image onto the floppy, after the kernel. Use an offset + that is slightly larger than the kernel, so that you can put another + (possibly larger) kernel onto the same floppy later without overlapping + the RAM disk image. An offset of 400 kB for kernels about 350 kB in + size would be reasonable. Make sure offset+size of ram_image.gz is + not larger than the total space on your floppy (usually 1440 kB):: + + dd if=/tmp/ram_image.gz of=/dev/fd0 bs=1k seek=400 + +g) Make sure that you have already specified the boot information in + FDARGS and FDINITRD or that you use a bootloader to pass kernel + command line boot options to the kernel. + +That is it. You now have your boot/root compressed RAM disk floppy. Some +users may wish to combine steps (d) and (f) by using a pipe. + + + Paul Gortmaker 12/95 + +Changelog: +---------- + +SEPT-2020 : + + Removed usage of "rdev" + +10-22-04 : + Updated to reflect changes in command line options, remove + obsolete references, general cleanup. + James Nelson (james4765@gmail.com) + +12-95 : + Original Document diff --git a/Documentation/admin-guide/blockdev/zram.rst b/Documentation/admin-guide/blockdev/zram.rst new file mode 100644 index 0000000000..e4551579cb --- /dev/null +++ b/Documentation/admin-guide/blockdev/zram.rst @@ -0,0 +1,532 @@ +======================================== +zram: Compressed RAM-based block devices +======================================== + +Introduction +============ + +The zram module creates RAM-based block devices named /dev/zram<id> +(<id> = 0, 1, ...). Pages written to these disks are compressed and stored +in memory itself. These disks allow very fast I/O and compression provides +good amounts of memory savings. Some of the use cases include /tmp storage, +use as swap disks, various caches under /var and maybe many more. :) + +Statistics for individual zram devices are exported through sysfs nodes at +/sys/block/zram<id>/ + +Usage +===== + +There are several ways to configure and manage zram device(-s): + +a) using zram and zram_control sysfs attributes +b) using zramctl utility, provided by util-linux (util-linux@vger.kernel.org). + +In this document we will describe only 'manual' zram configuration steps, +IOW, zram and zram_control sysfs attributes. + +In order to get a better idea about zramctl please consult util-linux +documentation, zramctl man-page or `zramctl --help`. Please be informed +that zram maintainers do not develop/maintain util-linux or zramctl, should +you have any questions please contact util-linux@vger.kernel.org + +Following shows a typical sequence of steps for using zram. + +WARNING +======= + +For the sake of simplicity we skip error checking parts in most of the +examples below. However, it is your sole responsibility to handle errors. + +zram sysfs attributes always return negative values in case of errors. +The list of possible return codes: + +======== ============================================================= +-EBUSY an attempt to modify an attribute that cannot be changed once + the device has been initialised. Please reset device first. +-ENOMEM zram was not able to allocate enough memory to fulfil your + needs. +-EINVAL invalid input has been provided. +======== ============================================================= + +If you use 'echo', the returned value is set by the 'echo' utility, +and, in general case, something like:: + + echo 3 > /sys/block/zram0/max_comp_streams + if [ $? -ne 0 ]; then + handle_error + fi + +should suffice. + +1) Load Module +============== + +:: + + modprobe zram num_devices=4 + +This creates 4 devices: /dev/zram{0,1,2,3} + +num_devices parameter is optional and tells zram how many devices should be +pre-created. Default: 1. + +2) Set max number of compression streams +======================================== + +Regardless of the value passed to this attribute, ZRAM will always +allocate multiple compression streams - one per online CPU - thus +allowing several concurrent compression operations. The number of +allocated compression streams goes down when some of the CPUs +become offline. There is no single-compression-stream mode anymore, +unless you are running a UP system or have only 1 CPU online. + +To find out how many streams are currently available:: + + cat /sys/block/zram0/max_comp_streams + +3) Select compression algorithm +=============================== + +Using comp_algorithm device attribute one can see available and +currently selected (shown in square brackets) compression algorithms, +or change the selected compression algorithm (once the device is initialised +there is no way to change compression algorithm). + +Examples:: + + #show supported compression algorithms + cat /sys/block/zram0/comp_algorithm + lzo [lz4] + + #select lzo compression algorithm + echo lzo > /sys/block/zram0/comp_algorithm + +For the time being, the `comp_algorithm` content does not necessarily +show every compression algorithm supported by the kernel. We keep this +list primarily to simplify device configuration and one can configure +a new device with a compression algorithm that is not listed in +`comp_algorithm`. The thing is that, internally, ZRAM uses Crypto API +and, if some of the algorithms were built as modules, it's impossible +to list all of them using, for instance, /proc/crypto or any other +method. This, however, has an advantage of permitting the usage of +custom crypto compression modules (implementing S/W or H/W compression). + +4) Set Disksize +=============== + +Set disk size by writing the value to sysfs node 'disksize'. +The value can be either in bytes or you can use mem suffixes. +Examples:: + + # Initialize /dev/zram0 with 50MB disksize + echo $((50*1024*1024)) > /sys/block/zram0/disksize + + # Using mem suffixes + echo 256K > /sys/block/zram0/disksize + echo 512M > /sys/block/zram0/disksize + echo 1G > /sys/block/zram0/disksize + +Note: +There is little point creating a zram of greater than twice the size of memory +since we expect a 2:1 compression ratio. Note that zram uses about 0.1% of the +size of the disk when not in use so a huge zram is wasteful. + +5) Set memory limit: Optional +============================= + +Set memory limit by writing the value to sysfs node 'mem_limit'. +The value can be either in bytes or you can use mem suffixes. +In addition, you could change the value in runtime. +Examples:: + + # limit /dev/zram0 with 50MB memory + echo $((50*1024*1024)) > /sys/block/zram0/mem_limit + + # Using mem suffixes + echo 256K > /sys/block/zram0/mem_limit + echo 512M > /sys/block/zram0/mem_limit + echo 1G > /sys/block/zram0/mem_limit + + # To disable memory limit + echo 0 > /sys/block/zram0/mem_limit + +6) Activate +=========== + +:: + + mkswap /dev/zram0 + swapon /dev/zram0 + + mkfs.ext4 /dev/zram1 + mount /dev/zram1 /tmp + +7) Add/remove zram devices +========================== + +zram provides a control interface, which enables dynamic (on-demand) device +addition and removal. + +In order to add a new /dev/zramX device, perform a read operation on the hot_add +attribute. This will return either the new device's device id (meaning that you +can use /dev/zram<id>) or an error code. + +Example:: + + cat /sys/class/zram-control/hot_add + 1 + +To remove the existing /dev/zramX device (where X is a device id) +execute:: + + echo X > /sys/class/zram-control/hot_remove + +8) Stats +======== + +Per-device statistics are exported as various nodes under /sys/block/zram<id>/ + +A brief description of exported device attributes follows. For more details +please read Documentation/ABI/testing/sysfs-block-zram. + +====================== ====== =============================================== +Name access description +====================== ====== =============================================== +disksize RW show and set the device's disk size +initstate RO shows the initialization state of the device +reset WO trigger device reset +mem_used_max WO reset the `mem_used_max` counter (see later) +mem_limit WO specifies the maximum amount of memory ZRAM can + use to store the compressed data +writeback_limit WO specifies the maximum amount of write IO zram + can write out to backing device as 4KB unit +writeback_limit_enable RW show and set writeback_limit feature +max_comp_streams RW the number of possible concurrent compress + operations +comp_algorithm RW show and change the compression algorithm +compact WO trigger memory compaction +debug_stat RO this file is used for zram debugging purposes +backing_dev RW set up backend storage for zram to write out +idle WO mark allocated slot as idle +====================== ====== =============================================== + + +User space is advised to use the following files to read the device statistics. + +File /sys/block/zram<id>/stat + +Represents block layer statistics. Read Documentation/block/stat.rst for +details. + +File /sys/block/zram<id>/io_stat + +The stat file represents device's I/O statistics not accounted by block +layer and, thus, not available in zram<id>/stat file. It consists of a +single line of text and contains the following stats separated by +whitespace: + + ============= ============================================================= + failed_reads The number of failed reads + failed_writes The number of failed writes + invalid_io The number of non-page-size-aligned I/O requests + notify_free Depending on device usage scenario it may account + + a) the number of pages freed because of swap slot free + notifications + b) the number of pages freed because of + REQ_OP_DISCARD requests sent by bio. The former ones are + sent to a swap block device when a swap slot is freed, + which implies that this disk is being used as a swap disk. + + The latter ones are sent by filesystem mounted with + discard option, whenever some data blocks are getting + discarded. + ============= ============================================================= + +File /sys/block/zram<id>/mm_stat + +The mm_stat file represents the device's mm statistics. It consists of a single +line of text and contains the following stats separated by whitespace: + + ================ ============================================================= + orig_data_size uncompressed size of data stored in this disk. + Unit: bytes + compr_data_size compressed size of data stored in this disk + mem_used_total the amount of memory allocated for this disk. This + includes allocator fragmentation and metadata overhead, + allocated for this disk. So, allocator space efficiency + can be calculated using compr_data_size and this statistic. + Unit: bytes + mem_limit the maximum amount of memory ZRAM can use to store + the compressed data + mem_used_max the maximum amount of memory zram has consumed to + store the data + same_pages the number of same element filled pages written to this disk. + No memory is allocated for such pages. + pages_compacted the number of pages freed during compaction + huge_pages the number of incompressible pages + huge_pages_since the number of incompressible pages since zram set up + ================ ============================================================= + +File /sys/block/zram<id>/bd_stat + +The bd_stat file represents a device's backing device statistics. It consists of +a single line of text and contains the following stats separated by whitespace: + + ============== ============================================================= + bd_count size of data written in backing device. + Unit: 4K bytes + bd_reads the number of reads from backing device + Unit: 4K bytes + bd_writes the number of writes to backing device + Unit: 4K bytes + ============== ============================================================= + +9) Deactivate +============= + +:: + + swapoff /dev/zram0 + umount /dev/zram1 + +10) Reset +========= + + Write any positive value to 'reset' sysfs node:: + + echo 1 > /sys/block/zram0/reset + echo 1 > /sys/block/zram1/reset + + This frees all the memory allocated for the given device and + resets the disksize to zero. You must set the disksize again + before reusing the device. + +Optional Feature +================ + +writeback +--------- + +With CONFIG_ZRAM_WRITEBACK, zram can write idle/incompressible page +to backing storage rather than keeping it in memory. +To use the feature, admin should set up backing device via:: + + echo /dev/sda5 > /sys/block/zramX/backing_dev + +before disksize setting. It supports only partitions at this moment. +If admin wants to use incompressible page writeback, they could do it via:: + + echo huge > /sys/block/zramX/writeback + +To use idle page writeback, first, user need to declare zram pages +as idle:: + + echo all > /sys/block/zramX/idle + +From now on, any pages on zram are idle pages. The idle mark +will be removed until someone requests access of the block. +IOW, unless there is access request, those pages are still idle pages. +Additionally, when CONFIG_ZRAM_MEMORY_TRACKING is enabled pages can be +marked as idle based on how long (in seconds) it's been since they were +last accessed:: + + echo 86400 > /sys/block/zramX/idle + +In this example all pages which haven't been accessed in more than 86400 +seconds (one day) will be marked idle. + +Admin can request writeback of those idle pages at right timing via:: + + echo idle > /sys/block/zramX/writeback + +With the command, zram will writeback idle pages from memory to the storage. + +Additionally, if a user choose to writeback only huge and idle pages +this can be accomplished with:: + + echo huge_idle > /sys/block/zramX/writeback + +If a user chooses to writeback only incompressible pages (pages that none of +algorithms can compress) this can be accomplished with:: + + echo incompressible > /sys/block/zramX/writeback + +If an admin wants to write a specific page in zram device to the backing device, +they could write a page index into the interface:: + + echo "page_index=1251" > /sys/block/zramX/writeback + +If there are lots of write IO with flash device, potentially, it has +flash wearout problem so that admin needs to design write limitation +to guarantee storage health for entire product life. + +To overcome the concern, zram supports "writeback_limit" feature. +The "writeback_limit_enable"'s default value is 0 so that it doesn't limit +any writeback. IOW, if admin wants to apply writeback budget, they should +enable writeback_limit_enable via:: + + $ echo 1 > /sys/block/zramX/writeback_limit_enable + +Once writeback_limit_enable is set, zram doesn't allow any writeback +until admin sets the budget via /sys/block/zramX/writeback_limit. + +(If admin doesn't enable writeback_limit_enable, writeback_limit's value +assigned via /sys/block/zramX/writeback_limit is meaningless.) + +If admin wants to limit writeback as per-day 400M, they could do it +like below:: + + $ MB_SHIFT=20 + $ 4K_SHIFT=12 + $ echo $((400<<MB_SHIFT>>4K_SHIFT)) > \ + /sys/block/zram0/writeback_limit. + $ echo 1 > /sys/block/zram0/writeback_limit_enable + +If admins want to allow further write again once the budget is exhausted, +they could do it like below:: + + $ echo $((400<<MB_SHIFT>>4K_SHIFT)) > \ + /sys/block/zram0/writeback_limit + +If an admin wants to see the remaining writeback budget since last set:: + + $ cat /sys/block/zramX/writeback_limit + +If an admin wants to disable writeback limit, they could do:: + + $ echo 0 > /sys/block/zramX/writeback_limit_enable + +The writeback_limit count will reset whenever you reset zram (e.g., +system reboot, echo 1 > /sys/block/zramX/reset) so keeping how many of +writeback happened until you reset the zram to allocate extra writeback +budget in next setting is user's job. + +If admin wants to measure writeback count in a certain period, they could +know it via /sys/block/zram0/bd_stat's 3rd column. + +recompression +------------- + +With CONFIG_ZRAM_MULTI_COMP, zram can recompress pages using alternative +(secondary) compression algorithms. The basic idea is that alternative +compression algorithm can provide better compression ratio at a price of +(potentially) slower compression/decompression speeds. Alternative compression +algorithm can, for example, be more successful compressing huge pages (those +that default algorithm failed to compress). Another application is idle pages +recompression - pages that are cold and sit in the memory can be recompressed +using more effective algorithm and, hence, reduce zsmalloc memory usage. + +With CONFIG_ZRAM_MULTI_COMP, zram supports up to 4 compression algorithms: +one primary and up to 3 secondary ones. Primary zram compressor is explained +in "3) Select compression algorithm", secondary algorithms are configured +using recomp_algorithm device attribute. + +Example::: + + #show supported recompression algorithms + cat /sys/block/zramX/recomp_algorithm + #1: lzo lzo-rle lz4 lz4hc [zstd] + #2: lzo lzo-rle lz4 [lz4hc] zstd + +Alternative compression algorithms are sorted by priority. In the example +above, zstd is used as the first alternative algorithm, which has priority +of 1, while lz4hc is configured as a compression algorithm with priority 2. +Alternative compression algorithm's priority is provided during algorithms +configuration::: + + #select zstd recompression algorithm, priority 1 + echo "algo=zstd priority=1" > /sys/block/zramX/recomp_algorithm + + #select deflate recompression algorithm, priority 2 + echo "algo=deflate priority=2" > /sys/block/zramX/recomp_algorithm + +Another device attribute that CONFIG_ZRAM_MULTI_COMP enables is recompress, +which controls recompression. + +Examples::: + + #IDLE pages recompression is activated by `idle` mode + echo "type=idle" > /sys/block/zramX/recompress + + #HUGE pages recompression is activated by `huge` mode + echo "type=huge" > /sys/block/zram0/recompress + + #HUGE_IDLE pages recompression is activated by `huge_idle` mode + echo "type=huge_idle" > /sys/block/zramX/recompress + +The number of idle pages can be significant, so user-space can pass a size +threshold (in bytes) to the recompress knob: zram will recompress only pages +of equal or greater size::: + + #recompress all pages larger than 3000 bytes + echo "threshold=3000" > /sys/block/zramX/recompress + + #recompress idle pages larger than 2000 bytes + echo "type=idle threshold=2000" > /sys/block/zramX/recompress + +Recompression of idle pages requires memory tracking. + +During re-compression for every page, that matches re-compression criteria, +ZRAM iterates the list of registered alternative compression algorithms in +order of their priorities. ZRAM stops either when re-compression was +successful (re-compressed object is smaller in size than the original one) +and matches re-compression criteria (e.g. size threshold) or when there are +no secondary algorithms left to try. If none of the secondary algorithms can +successfully re-compressed the page such a page is marked as incompressible, +so ZRAM will not attempt to re-compress it in the future. + +This re-compression behaviour, when it iterates through the list of +registered compression algorithms, increases our chances of finding the +algorithm that successfully compresses a particular page. Sometimes, however, +it is convenient (and sometimes even necessary) to limit recompression to +only one particular algorithm so that it will not try any other algorithms. +This can be achieved by providing a algo=NAME parameter::: + + #use zstd algorithm only (if registered) + echo "type=huge algo=zstd" > /sys/block/zramX/recompress + +memory tracking +=============== + +With CONFIG_ZRAM_MEMORY_TRACKING, user can know information of the +zram block. It could be useful to catch cold or incompressible +pages of the process with*pagemap. + +If you enable the feature, you could see block state via +/sys/kernel/debug/zram/zram0/block_state". The output is as follows:: + + 300 75.033841 .wh... + 301 63.806904 s..... + 302 63.806919 ..hi.. + 303 62.801919 ....r. + 304 146.781902 ..hi.n + +First column + zram's block index. +Second column + access time since the system was booted +Third column + state of the block: + + s: + same page + w: + written page to backing store + h: + huge page + i: + idle page + r: + recompressed page (secondary compression algorithm) + n: + none (including secondary) of algorithms could compress it + +First line of above example says 300th block is accessed at 75.033841sec +and the block's state is huge so it is written back to the backing +storage. It's a debugging feature so anyone shouldn't rely on it to work +properly. + +Nitin Gupta +ngupta@vflare.org |
