adulau/aha
1
0
Fork 0
mirror of https://github.com/adulau/aha.git synced 2024-12-29 04:06:22 +00:00
Code Issues Projects Releases Packages Wiki Activity

Merge branch 'for-2.6.33' of git://git.kernel.dk/linux-2.6-block into for-2.6.33

Browse source
This commit is contained in:
Philipp Reisner 2009-11-03 10:59:10 +01:00
commit 59131d8e0a
46 changed files with 22432 additions and 1634 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

588
Documentation/blockdev/drbd/DRBD-8.3-data-packets.svg Normal file
View file

@ -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>
Side by side

After

Width:  |  Height:  |  Size: 22 KiB

459
Documentation/blockdev/drbd/DRBD-data-packets.svg Normal file
View file

@ -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>
Side by side

After

Width:  |  Height:  |  Size: 17 KiB

16
Documentation/blockdev/drbd/README.txt Normal file
View file

@ -0,0 +1,16 @@
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 http://www.drbd.org to find out more.
The here included files are intended to help understand the implementation
DRBD-8.3-data-packets.svg, DRBD-data-packets.svg
relates some functions, and write packets.
conn-states-8.dot, disk-states-8.dot, node-states-8.dot
The sub graphs of DRBD's state transitions

18
Documentation/blockdev/drbd/conn-states-8.dot Normal file
View file

@ -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" ]
}

16
Documentation/blockdev/drbd/disk-states-8.dot Normal file
View file

@ -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" ]
}

85
Documentation/blockdev/drbd/drbd-connection-state-overview.dot Normal file
View file

@ -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" ]
}

14
Documentation/blockdev/drbd/node-states-8.dot Normal file
View file

@ -0,0 +1,14 @@
digraph node_states {
Secondary -> Primary [ label = "ioctl_set_state()" ]
Primary -> Secondary [ label = "ioctl_set_state()" ]
}
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" ]
}

13
MAINTAINERS
View file

@ -1790,6 +1790,19 @@ S: Maintained
F: drivers/scsi/dpt*
F: drivers/scsi/dpt/
DRBD DRIVER
P: Philipp Reisner
P: Lars Ellenberg
M: drbd-dev@lists.linbit.com
L: drbd-user@lists.linbit.com
W: http://www.drbd.org
T: git git://git.drbd.org/linux-2.6-drbd.git drbd
T: git git://git.drbd.org/drbd-8.3.git
S: Supported
F: drivers/block/drbd/
F: lib/lru_cache.c
F: Documentation/blockdev/drbd/
DRIVER CORE, KOBJECTS, AND SYSFS
M: Greg Kroah-Hartman <gregkh@suse.de>
T: quilt kernel.org/pub/linux/kernel/people/gregkh/gregkh-2.6/

26
block/Kconfig.iosched
View file

@ -12,24 +12,14 @@ config IOSCHED_NOOP
that do their own scheduling and require only minimal assistance from
the kernel.
config IOSCHED_AS
tristate "Anticipatory I/O scheduler"
default y
---help---
The anticipatory I/O scheduler is generally a good choice for most
environments, but is quite large and complex when compared to the
deadline I/O scheduler, it can also be slower in some cases
especially some database loads.
config IOSCHED_DEADLINE
tristate "Deadline I/O scheduler"
default y
---help---
The deadline I/O scheduler is simple and compact, and is often as
good as the anticipatory I/O scheduler, and in some database
workloads, better. In the case of a single process performing I/O to
a disk at any one time, its behaviour is almost identical to the
anticipatory I/O scheduler and so is a good choice.
The deadline I/O scheduler is simple and compact. It will provide
CSCAN service with FIFO expiration of requests, switching to
a new point in the service tree and doing a batch of IO from there
in case of expiry.
config IOSCHED_CFQ
tristate "CFQ I/O scheduler"
@ -37,7 +27,9 @@ config IOSCHED_CFQ
---help---
The CFQ I/O scheduler tries to distribute bandwidth equally
among all processes in the system. It should provide a fair
working environment, suitable for desktop systems.
and low latency working environment, suitable for both desktop
and server systems.
This is the default I/O scheduler.
choice
@ -47,9 +39,6 @@ choice
Select the I/O scheduler which will be used by default for all
block devices.
config DEFAULT_AS
bool "Anticipatory" if IOSCHED_AS=y
config DEFAULT_DEADLINE
bool "Deadline" if IOSCHED_DEADLINE=y
@ -63,7 +52,6 @@ endchoice
config DEFAULT_IOSCHED
string
default "anticipatory" if DEFAULT_AS
default "deadline" if DEFAULT_DEADLINE
default "cfq" if DEFAULT_CFQ
default "noop" if DEFAULT_NOOP

1
block/Makefile
View file

@ -9,7 +9,6 @@ obj-$(CONFIG_BLOCK) := elevator.o blk-core.o blk-tag.o blk-sysfs.o \
obj-$(CONFIG_BLK_DEV_BSG) += bsg.o
obj-$(CONFIG_IOSCHED_NOOP) += noop-iosched.o
obj-$(CONFIG_IOSCHED_AS) += as-iosched.o
obj-$(CONFIG_IOSCHED_DEADLINE) += deadline-iosched.o
obj-$(CONFIG_IOSCHED_CFQ) += cfq-iosched.o

1520
block/as-iosched.c
View file

File diff suppressed because it is too large Load diff

262
block/cfq-iosched.c
View file

@ -38,6 +38,12 @@ static int cfq_slice_idle = HZ / 125;
*/
#define CFQ_MIN_TT (2)
/*
* Allow merged cfqqs to perform this amount of seeky I/O before
* deciding to break the queues up again.
*/
#define CFQQ_COOP_TOUT (HZ)
#define CFQ_SLICE_SCALE (5)
#define CFQ_HW_QUEUE_MIN (5)
@ -112,7 +118,15 @@ struct cfq_queue {
unsigned short ioprio, org_ioprio;
unsigned short ioprio_class, org_ioprio_class;
unsigned int seek_samples;
u64 seek_total;
sector_t seek_mean;
sector_t last_request_pos;
unsigned long seeky_start;
pid_t pid;
struct cfq_queue *new_cfqq;
};
/*
@ -195,7 +209,7 @@ enum cfqq_state_flags {
CFQ_CFQQ_FLAG_prio_changed, /* task priority has changed */
CFQ_CFQQ_FLAG_slice_new, /* no requests dispatched in slice */
CFQ_CFQQ_FLAG_sync, /* synchronous queue */
CFQ_CFQQ_FLAG_coop, /* has done a coop jump of the queue */
CFQ_CFQQ_FLAG_coop, /* cfqq is shared */
};
#define CFQ_CFQQ_FNS(name) \
@ -943,11 +957,8 @@ static struct cfq_queue *cfq_get_next_queue(struct cfq_data *cfqd)
static struct cfq_queue *cfq_set_active_queue(struct cfq_data *cfqd,
struct cfq_queue *cfqq)
{
if (!cfqq) {
if (!cfqq)
cfqq = cfq_get_next_queue(cfqd);
if (cfqq)
cfq_clear_cfqq_coop(cfqq);
}
__cfq_set_active_queue(cfqd, cfqq);
return cfqq;
@ -962,16 +973,16 @@ static inline sector_t cfq_dist_from_last(struct cfq_data *cfqd,
return cfqd->last_position - blk_rq_pos(rq);
}
#define CIC_SEEK_THR 8 * 1024
#define CIC_SEEKY(cic) ((cic)->seek_mean > CIC_SEEK_THR)
#define CFQQ_SEEK_THR 8 * 1024
#define CFQQ_SEEKY(cfqq) ((cfqq)->seek_mean > CFQQ_SEEK_THR)
static inline int cfq_rq_close(struct cfq_data *cfqd, struct request *rq)
static inline int cfq_rq_close(struct cfq_data *cfqd, struct cfq_queue *cfqq,
struct request *rq)
{
struct cfq_io_context *cic = cfqd->active_cic;
sector_t sdist = cic->seek_mean;
sector_t sdist = cfqq->seek_mean;
if (!sample_valid(cic->seek_samples))
sdist = CIC_SEEK_THR;
if (!sample_valid(cfqq->seek_samples))
sdist = CFQQ_SEEK_THR;
return cfq_dist_from_last(cfqd, rq) <= sdist;
}
@ -1000,7 +1011,7 @@ static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
* will contain the closest sector.
*/
__cfqq = rb_entry(parent, struct cfq_queue, p_node);
if (cfq_rq_close(cfqd, __cfqq->next_rq))
if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq))
return __cfqq;
if (blk_rq_pos(__cfqq->next_rq) < sector)
@ -1011,7 +1022,7 @@ static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
return NULL;
__cfqq = rb_entry(node, struct cfq_queue, p_node);
if (cfq_rq_close(cfqd, __cfqq->next_rq))
if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq))
return __cfqq;
return NULL;
@ -1028,16 +1039,13 @@ static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
* assumption.
*/
static struct cfq_queue *cfq_close_cooperator(struct cfq_data *cfqd,
struct cfq_queue *cur_cfqq,
bool probe)
struct cfq_queue *cur_cfqq)
{
struct cfq_queue *cfqq;
/*
* A valid cfq_io_context is necessary to compare requests against
* the seek_mean of the current cfqq.
*/
if (!cfqd->active_cic)
if (!cfq_cfqq_sync(cur_cfqq))
return NULL;
if (CFQQ_SEEKY(cur_cfqq))
return NULL;
/*
@ -1049,11 +1057,14 @@ static struct cfq_queue *cfq_close_cooperator(struct cfq_data *cfqd,
if (!cfqq)
return NULL;
if (cfq_cfqq_coop(cfqq))
/*
* It only makes sense to merge sync queues.
*/
if (!cfq_cfqq_sync(cfqq))
return NULL;
if (CFQQ_SEEKY(cfqq))
return NULL;
if (!probe)
cfq_mark_cfqq_coop(cfqq);
return cfqq;
}
@ -1110,7 +1121,7 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
* seeks. so allow a little bit of time for him to submit a new rq
*/
sl = cfqd->cfq_slice_idle;
if (sample_valid(cic->seek_samples) && CIC_SEEKY(cic))
if (sample_valid(cfqq->seek_samples) && CFQQ_SEEKY(cfqq))
sl = min(sl, msecs_to_jiffies(CFQ_MIN_TT));
mod_timer(&cfqd->idle_slice_timer, jiffies + sl);
@ -1169,6 +1180,52 @@ cfq_prio_to_maxrq(struct cfq_data *cfqd, struct cfq_queue *cfqq)
return 2 * (base_rq + base_rq * (CFQ_PRIO_LISTS - 1 - cfqq->ioprio));
}
/*
* Must be called with the queue_lock held.
*/
static int cfqq_process_refs(struct cfq_queue *cfqq)
{
int process_refs, io_refs;
io_refs = cfqq->allocated[READ] + cfqq->allocated[WRITE];
process_refs = atomic_read(&cfqq->ref) - io_refs;
BUG_ON(process_refs < 0);
return process_refs;
}
static void cfq_setup_merge(struct cfq_queue *cfqq, struct cfq_queue *new_cfqq)
{
int process_refs, new_process_refs;
struct cfq_queue *__cfqq;
/* Avoid a circular list and skip interim queue merges */
while ((__cfqq = new_cfqq->new_cfqq)) {
if (__cfqq == cfqq)
return;
new_cfqq = __cfqq;
}
process_refs = cfqq_process_refs(cfqq);
/*
* If the process for the cfqq has gone away, there is no
* sense in merging the queues.
*/
if (process_refs == 0)
return;
/*
* Merge in the direction of the lesser amount of work.
*/
new_process_refs = cfqq_process_refs(new_cfqq);
if (new_process_refs >= process_refs) {
cfqq->new_cfqq = new_cfqq;
atomic_add(process_refs, &new_cfqq->ref);
} else {
new_cfqq->new_cfqq = cfqq;
atomic_add(new_process_refs, &cfqq->ref);
}
}
/*
* Select a queue for service. If we have a current active queue,
* check whether to continue servicing it, or retrieve and set a new one.
@ -1198,11 +1255,14 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
* If another queue has a request waiting within our mean seek
* distance, let it run. The expire code will check for close
* cooperators and put the close queue at the front of the service
* tree.
* tree. If possible, merge the expiring queue with the new cfqq.
*/
new_cfqq = cfq_close_cooperator(cfqd, cfqq, 0);
if (new_cfqq)
new_cfqq = cfq_close_cooperator(cfqd, cfqq);
if (new_cfqq) {
if (!cfqq->new_cfqq)
cfq_setup_merge(cfqq, new_cfqq);
goto expire;
}
/*
* No requests pending. If the active queue still has requests in
@ -1513,11 +1573,29 @@ static void cfq_free_io_context(struct io_context *ioc)
static void cfq_exit_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
struct cfq_queue *__cfqq, *next;
if (unlikely(cfqq == cfqd->active_queue)) {
__cfq_slice_expired(cfqd, cfqq, 0);
cfq_schedule_dispatch(cfqd);
}
/*
* If this queue was scheduled to merge with another queue, be
* sure to drop the reference taken on that queue (and others in
* the merge chain). See cfq_setup_merge and cfq_merge_cfqqs.
*/
__cfqq = cfqq->new_cfqq;
while (__cfqq) {
if (__cfqq == cfqq) {
WARN(1, "cfqq->new_cfqq loop detected\n");
break;
}
next = __cfqq->new_cfqq;
cfq_put_queue(__cfqq);
__cfqq = next;
}
cfq_put_queue(cfqq);
}
@ -1947,33 +2025,46 @@ cfq_update_io_thinktime(struct cfq_data *cfqd, struct cfq_io_context *cic)
}
static void
cfq_update_io_seektime(struct cfq_data *cfqd, struct cfq_io_context *cic,
cfq_update_io_seektime(struct cfq_data *cfqd, struct cfq_queue *cfqq,
struct request *rq)
{
sector_t sdist;
u64 total;
if (!cic->last_request_pos)
if (!cfqq->last_request_pos)
sdist = 0;
else if (cic->last_request_pos < blk_rq_pos(rq))
sdist = blk_rq_pos(rq) - cic->last_request_pos;
else if (cfqq->last_request_pos < blk_rq_pos(rq))
sdist = blk_rq_pos(rq) - cfqq->last_request_pos;
else
sdist = cic->last_request_pos - blk_rq_pos(rq);
sdist = cfqq->last_request_pos - blk_rq_pos(rq);
/*
* Don't allow the seek distance to get too large from the
* odd fragment, pagein, etc
*/
if (cic->seek_samples <= 60) /* second&third seek */
sdist = min(sdist, (cic->seek_mean * 4) + 2*1024*1024);
if (cfqq->seek_samples <= 60) /* second&third seek */
sdist = min(sdist, (cfqq->seek_mean * 4) + 2*1024*1024);
else
sdist = min(sdist, (cic->seek_mean * 4) + 2*1024*64);
sdist = min(sdist, (cfqq->seek_mean * 4) + 2*1024*64);
cic->seek_samples = (7*cic->seek_samples + 256) / 8;
cic->seek_total = (7*cic->seek_total + (u64)256*sdist) / 8;
total = cic->seek_total + (cic->seek_samples/2);
do_div(total, cic->seek_samples);
cic->seek_mean = (sector_t)total;
cfqq->seek_samples = (7*cfqq->seek_samples + 256) / 8;
cfqq->seek_total = (7*cfqq->seek_total + (u64)256*sdist) / 8;
total = cfqq->seek_total + (cfqq->seek_samples/2);
do_div(total, cfqq->seek_samples);
cfqq->seek_mean = (sector_t)total;
/*
* If this cfqq is shared between multiple processes, check to
* make sure that those processes are still issuing I/Os within
* the mean seek distance. If not, it may be time to break the
* queues apart again.
*/
if (cfq_cfqq_coop(cfqq)) {
if (CFQQ_SEEKY(cfqq) && !cfqq->seeky_start)
cfqq->seeky_start = jiffies;
else if (!CFQQ_SEEKY(cfqq))
cfqq->seeky_start = 0;
}
}
/*
@ -1995,11 +2086,11 @@ cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq,
enable_idle = old_idle = cfq_cfqq_idle_window(cfqq);
if (!atomic_read(&cic->ioc->nr_tasks) || !cfqd->cfq_slice_idle ||
(!cfqd->cfq_latency && cfqd->hw_tag && CIC_SEEKY(cic)))
(!cfqd->cfq_latency && cfqd->hw_tag && CFQQ_SEEKY(cfqq)))
enable_idle = 0;
else if (sample_valid(cic->ttime_samples)) {
unsigned int slice_idle = cfqd->cfq_slice_idle;
if (sample_valid(cic->seek_samples) && CIC_SEEKY(cic))
if (sample_valid(cfqq->seek_samples) && CFQQ_SEEKY(cfqq))
slice_idle = msecs_to_jiffies(CFQ_MIN_TT);
if (cic->ttime_mean > slice_idle)
enable_idle = 0;
@ -2066,7 +2157,7 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
* if this request is as-good as one we would expect from the
* current cfqq, let it preempt
*/
if (cfq_rq_close(cfqd, rq))
if (cfq_rq_close(cfqd, cfqq, rq))
return true;
return false;
@ -2108,10 +2199,10 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
cfqq->meta_pending++;
cfq_update_io_thinktime(cfqd, cic);
cfq_update_io_seektime(cfqd, cic, rq);
cfq_update_io_seektime(cfqd, cfqq, rq);
cfq_update_idle_window(cfqd, cfqq, cic);
cic->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq);
cfqq->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq);
if (cfqq == cfqd->active_queue) {
/*
@ -2166,6 +2257,8 @@ static void cfq_insert_request(struct request_queue *q, struct request *rq)
*/
static void cfq_update_hw_tag(struct cfq_data *cfqd)
{
struct cfq_queue *cfqq = cfqd->active_queue;
if (rq_in_driver(cfqd) > cfqd->rq_in_driver_peak)
cfqd->rq_in_driver_peak = rq_in_driver(cfqd);
@ -2173,6 +2266,16 @@ static void cfq_update_hw_tag(struct cfq_data *cfqd)
rq_in_driver(cfqd) <= CFQ_HW_QUEUE_MIN)
return;
/*
* If active queue hasn't enough requests and can idle, cfq might not
* dispatch sufficient requests to hardware. Don't zero hw_tag in this
* case
*/
if (cfqq && cfq_cfqq_idle_window(cfqq) &&
cfqq->dispatched + cfqq->queued[0] + cfqq->queued[1] <
CFQ_HW_QUEUE_MIN && rq_in_driver(cfqd) < CFQ_HW_QUEUE_MIN)
return;
if (cfqd->hw_tag_samples++ < 50)
return;
@ -2230,7 +2333,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
*/
if (cfq_slice_used(cfqq) || cfq_class_idle(cfqq))
cfq_slice_expired(cfqd, 1);
else if (cfqq_empty && !cfq_close_cooperator(cfqd, cfqq, 1) &&
else if (cfqq_empty && !cfq_close_cooperator(cfqd, cfqq) &&
sync && !rq_noidle(rq))
cfq_arm_slice_timer(cfqd);
}
@ -2256,12 +2359,10 @@ static void cfq_prio_boost(struct cfq_queue *cfqq)
cfqq->ioprio = IOPRIO_NORM;
} else {
/*
* check if we need to unboost the queue
* unboost the queue (if needed)
*/
if (cfqq->ioprio_class != cfqq->org_ioprio_class)
cfqq->ioprio_class = cfqq->org_ioprio_class;
if (cfqq->ioprio != cfqq->org_ioprio)
cfqq->ioprio = cfqq->org_ioprio;
cfqq->ioprio_class = cfqq->org_ioprio_class;
cfqq->ioprio = cfqq->org_ioprio;
}
}
@ -2325,6 +2426,43 @@ static void cfq_put_request(struct request *rq)
}
}
static struct cfq_queue *
cfq_merge_cfqqs(struct cfq_data *cfqd, struct cfq_io_context *cic,
struct cfq_queue *cfqq)
{
cfq_log_cfqq(cfqd, cfqq, "merging with queue %p", cfqq->new_cfqq);
cic_set_cfqq(cic, cfqq->new_cfqq, 1);
cfq_mark_cfqq_coop(cfqq->new_cfqq);
cfq_put_queue(cfqq);
return cic_to_cfqq(cic, 1);
}
static int should_split_cfqq(struct cfq_queue *cfqq)
{
if (cfqq->seeky_start &&
time_after(jiffies, cfqq->seeky_start + CFQQ_COOP_TOUT))
return 1;
return 0;
}
/*
* Returns NULL if a new cfqq should be allocated, or the old cfqq if this
* was the last process referring to said cfqq.
*/
static struct cfq_queue *
split_cfqq(struct cfq_io_context *cic, struct cfq_queue *cfqq)
{
if (cfqq_process_refs(cfqq) == 1) {
cfqq->seeky_start = 0;
cfqq->pid = current->pid;
cfq_clear_cfqq_coop(cfqq);
return cfqq;
}
cic_set_cfqq(cic, NULL, 1);
cfq_put_queue(cfqq);
return NULL;
}
/*
* Allocate cfq data structures associated with this request.
*/
@ -2347,10 +2485,30 @@ cfq_set_request(struct request_queue *q, struct request *rq, gfp_t gfp_mask)
if (!cic)
goto queue_fail;
new_queue:
cfqq = cic_to_cfqq(cic, is_sync);
if (!cfqq || cfqq == &cfqd->oom_cfqq) {
cfqq = cfq_get_queue(cfqd, is_sync, cic->ioc, gfp_mask);
cic_set_cfqq(cic, cfqq, is_sync);
} else {
/*
* If the queue was seeky for too long, break it apart.
*/
if (cfq_cfqq_coop(cfqq) && should_split_cfqq(cfqq)) {
cfq_log_cfqq(cfqd, cfqq, "breaking apart cfqq");
cfqq = split_cfqq(cic, cfqq);
if (!cfqq)
goto new_queue;
}
/*
* Check to see if this queue is scheduled to merge with
* another, closely cooperating queue. The merging of
* queues happens here as it must be done in process context.
* The reference on new_cfqq was taken in merge_cfqqs.
*/
if (cfqq->new_cfqq)
cfqq = cfq_merge_cfqqs(cfqd, cic, cfqq);
}
cfqq->allocated[rw]++;

10
block/elevator.c
View file

@ -154,10 +154,7 @@ static struct elevator_type *elevator_get(const char *name)
spin_unlock(&elv_list_lock);
if (!strcmp(name, "anticipatory"))
sprintf(elv, "as-iosched");
else
sprintf(elv, "%s-iosched", name);
sprintf(elv, "%s-iosched", name);
request_module("%s", elv);
spin_lock(&elv_list_lock);
@ -193,10 +190,7 @@ static int __init elevator_setup(char *str)
* Be backwards-compatible with previous kernels, so users
* won't get the wrong elevator.
*/
if (!strcmp(str, "as"))
strcpy(chosen_elevator, "anticipatory");
else
strncpy(chosen_elevator, str, sizeof(chosen_elevator) - 1);
strncpy(chosen_elevator, str, sizeof(chosen_elevator) - 1);
return 1;
}

2
drivers/block/Kconfig
View file

@ -271,6 +271,8 @@ config BLK_DEV_CRYPTOLOOP
instead, which can be configured to be on-disk compatible with the
cryptoloop device.
source "drivers/block/drbd/Kconfig"
config BLK_DEV_NBD
tristate "Network block device support"
depends on NET

1
drivers/block/Makefile
View file

@ -36,5 +36,6 @@ obj-$(CONFIG_BLK_DEV_UB) += ub.o
obj-$(CONFIG_BLK_DEV_HD) += hd.o
obj-$(CONFIG_XEN_BLKDEV_FRONTEND) += xen-blkfront.o
obj-$(CONFIG_BLK_DEV_DRBD) += drbd/
swim_mod-objs := swim.o swim_asm.o

71
drivers/block/drbd/Kconfig Normal file
View file

@ -0,0 +1,71 @@
#
# DRBD device driver configuration
#
comment "DRBD disabled because PROC_FS, INET or CONNECTOR not selected"
depends on !PROC_FS || !INET || !CONNECTOR
config BLK_DEV_DRBD
tristate "DRBD Distributed Replicated Block Device support"
depends on PROC_FS && INET && CONNECTOR
select LRU_CACHE
default n
help
NOTE: In order to authenticate connections you have to select
CRYPTO_HMAC and a hash function as well.
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.
Each minor device has a role, which can be 'primary' or 'secondary'.
On the node with the primary device the application is supposed to
run and to access the device (/dev/drbdX). Every write is sent to
the local 'lower level block device' and, across the network, to the
node with the device in 'secondary' state. The secondary device
simply writes the data to its lower level block device.
DRBD can also be used in dual-Primary mode (device writable on both
nodes), which means it can exhibit shared disk semantics in a
shared-nothing cluster. Needless to say, on top of dual-Primary
DRBD utilizing a cluster file system is necessary to maintain for
cache coherency.
For automatic failover you need a cluster manager (e.g. heartbeat).
See also: http://www.drbd.org/, http://www.linux-ha.org
If unsure, say N.
config DRBD_FAULT_INJECTION
bool "DRBD fault injection"
depends on BLK_DEV_DRBD
help
Say Y here if you want to simulate IO errors, in order to test DRBD's
behavior.
The actual simulation of IO errors is done by writing 3 values to
/sys/module/drbd/parameters/
enable_faults: bitmask of...
1 meta data write
2 read
4 resync data write
8 read
16 data write
32 data read
64 read ahead
128 kmalloc of bitmap
256 allocation of EE (epoch_entries)
fault_devs: bitmask of minor numbers
fault_rate: frequency in percent
Example: Simulate data write errors on /dev/drbd0 with a probability of 5%.
echo 16 > /sys/module/drbd/parameters/enable_faults
echo 1 > /sys/module/drbd/parameters/fault_devs
echo 5 > /sys/module/drbd/parameters/fault_rate
If unsure, say N.

5
drivers/block/drbd/Makefile Normal file
View file

@ -0,0 +1,5 @@
drbd-y := drbd_bitmap.o drbd_proc.o
drbd-y += drbd_worker.o drbd_receiver.o drbd_req.o drbd_actlog.o
drbd-y += drbd_main.o drbd_strings.o drbd_nl.o
obj-$(CONFIG_BLK_DEV_DRBD) += drbd.o

1424
drivers/block/drbd/drbd_actlog.c Normal file
View file

File diff suppressed because it is too large Load diff

1327
drivers/block/drbd/drbd_bitmap.c Normal file
View file

File diff suppressed because it is too large Load diff

2252
drivers/block/drbd/drbd_int.h Normal file
View file

File diff suppressed because it is too large Load diff

3700
drivers/block/drbd/drbd_main.c Normal file
View file

File diff suppressed because it is too large Load diff

2360
drivers/block/drbd/drbd_nl.c Normal file
View file

File diff suppressed because it is too large Load diff

265
drivers/block/drbd/drbd_proc.c Normal file
View file

@ -0,0 +1,265 @@
/*
drbd_proc.c
This file is part of DRBD by Philipp Reisner and Lars Ellenberg.
Copyright (C) 2001-2008, LINBIT Information Technologies GmbH.
Copyright (C) 1999-2008, Philipp Reisner <philipp.reisner@linbit.com>.
Copyright (C) 2002-2008, Lars Ellenberg <lars.ellenberg@linbit.com>.
drbd is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.
drbd is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with drbd; see the file COPYING. If not, write to
the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#include <linux/module.h>
#include <asm/uaccess.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/slab.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/drbd.h>
#include "drbd_int.h"
static int drbd_proc_open(struct inode *inode, struct file *file);
struct proc_dir_entry *drbd_proc;
struct file_operations drbd_proc_fops = {
.owner = THIS_MODULE,
.open = drbd_proc_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release,
};
/*lge
* progress bars shamelessly adapted from driver/md/md.c
* output looks like
* [=====>..............] 33.5% (23456/123456)
* finish: 2:20:20 speed: 6,345 (6,456) K/sec
*/
static void drbd_syncer_progress(struct drbd_conf *mdev, struct seq_file *seq)
{
unsigned long db, dt, dbdt, rt, rs_left;
unsigned int res;
int i, x, y;
drbd_get_syncer_progress(mdev, &rs_left, &res);
x = res/50;
y = 20-x;
seq_printf(seq, "\t[");
for (i = 1; i < x; i++)
seq_printf(seq, "=");
seq_printf(seq, ">");
for (i = 0; i < y; i++)
seq_printf(seq, ".");
seq_printf(seq, "] ");
seq_printf(seq, "sync'ed:%3u.%u%% ", res / 10, res % 10);
/* if more than 1 GB display in MB */
if (mdev->rs_total > 0x100000L)
seq_printf(seq, "(%lu/%lu)M\n\t",
(unsigned long) Bit2KB(rs_left >> 10),
(unsigned long) Bit2KB(mdev->rs_total >> 10));
else
seq_printf(seq, "(%lu/%lu)K\n\t",
(unsigned long) Bit2KB(rs_left),
(unsigned long) Bit2KB(mdev->rs_total));
/* see drivers/md/md.c
* We do not want to overflow, so the order of operands and
* the * 100 / 100 trick are important. We do a +1 to be
* safe against division by zero. We only estimate anyway.
*
* dt: time from mark until now
* db: blocks written from mark until now
* rt: remaining time
*/
dt = (jiffies - mdev->rs_mark_time) / HZ;
if (dt > 20) {
/* if we made no update to rs_mark_time for too long,
* we are stalled. show that. */
seq_printf(seq, "stalled\n");
return;
}
if (!dt)
dt++;
db = mdev->rs_mark_left - rs_left;
rt = (dt * (rs_left / (db/100+1)))/100; /* seconds */
seq_printf(seq, "finish: %lu:%02lu:%02lu",
rt / 3600, (rt % 3600) / 60, rt % 60);
/* current speed average over (SYNC_MARKS * SYNC_MARK_STEP) jiffies */
dbdt = Bit2KB(db/dt);
if (dbdt > 1000)
seq_printf(seq, " speed: %ld,%03ld",
dbdt/1000, dbdt % 1000);
else
seq_printf(seq, " speed: %ld", dbdt);
/* mean speed since syncer started
* we do account for PausedSync periods */
dt = (jiffies - mdev->rs_start - mdev->rs_paused) / HZ;
if (dt <= 0)
dt = 1;
db = mdev->rs_total - rs_left;
dbdt = Bit2KB(db/dt);
if (dbdt > 1000)
seq_printf(seq, " (%ld,%03ld)",
dbdt/1000, dbdt % 1000);
else
seq_printf(seq, " (%ld)", dbdt);
seq_printf(seq, " K/sec\n");
}
static void resync_dump_detail(struct seq_file *seq, struct lc_element *e)
{
struct bm_extent *bme = lc_entry(e, struct bm_extent, lce);
seq_printf(seq, "%5d %s %s\n", bme->rs_left,
bme->flags & BME_NO_WRITES ? "NO_WRITES" : "---------",
bme->flags & BME_LOCKED ? "LOCKED" : "------"
);
}
static int drbd_seq_show(struct seq_file *seq, void *v)
{
int i, hole = 0;
const char *sn;
struct drbd_conf *mdev;
static char write_ordering_chars[] = {
[WO_none] = 'n',
[WO_drain_io] = 'd',
[WO_bdev_flush] = 'f',
[WO_bio_barrier] = 'b',
};
seq_printf(seq, "version: " REL_VERSION " (api:%d/proto:%d-%d)\n%s\n",
API_VERSION, PRO_VERSION_MIN, PRO_VERSION_MAX, drbd_buildtag());
/*
cs .. connection state
ro .. node role (local/remote)
ds .. disk state (local/remote)
protocol
various flags
ns .. network send
nr .. network receive
dw .. disk write
dr .. disk read
al .. activity log write count
bm .. bitmap update write count
pe .. pending (waiting for ack or data reply)
ua .. unack'd (still need to send ack or data reply)
ap .. application requests accepted, but not yet completed
ep .. number of epochs currently "on the fly", P_BARRIER_ACK pending
wo .. write ordering mode currently in use
oos .. known out-of-sync kB
*/
for (i = 0; i < minor_count; i++) {
mdev = minor_to_mdev(i);
if (!mdev) {
hole = 1;
continue;
}
if (hole) {
hole = 0;
seq_printf(seq, "\n");
}
sn = drbd_conn_str(mdev->state.conn);
if (mdev->state.conn == C_STANDALONE &&
mdev->state.disk == D_DISKLESS &&
mdev->state.role == R_SECONDARY) {
seq_printf(seq, "%2d: cs:Unconfigured\n", i);
} else {
seq_printf(seq,
"%2d: cs:%s ro:%s/%s ds:%s/%s %c %c%c%c%c%c\n"
" ns:%u nr:%u dw:%u dr:%u al:%u bm:%u "
"lo:%d pe:%d ua:%d ap:%d ep:%d wo:%c",
i, sn,
drbd_role_str(mdev->state.role),
drbd_role_str(mdev->state.peer),
drbd_disk_str(mdev->state.disk),
drbd_disk_str(mdev->state.pdsk),
(mdev->net_conf == NULL ? ' ' :
(mdev->net_conf->wire_protocol - DRBD_PROT_A+'A')),
mdev->state.susp ? 's' : 'r',
mdev->state.aftr_isp ? 'a' : '-',
mdev->state.peer_isp ? 'p' : '-',
mdev->state.user_isp ? 'u' : '-',
mdev->congestion_reason ?: '-',
mdev->send_cnt/2,
mdev->recv_cnt/2,
mdev->writ_cnt/2,
mdev->read_cnt/2,
mdev->al_writ_cnt,
mdev->bm_writ_cnt,
atomic_read(&mdev->local_cnt),
atomic_read(&mdev->ap_pending_cnt) +
atomic_read(&mdev->rs_pending_cnt),
atomic_read(&mdev->unacked_cnt),
atomic_read(&mdev->ap_bio_cnt),
mdev->epochs,
write_ordering_chars[mdev->write_ordering]
);
seq_printf(seq, " oos:%lu\n",
Bit2KB(drbd_bm_total_weight(mdev)));
}
if (mdev->state.conn == C_SYNC_SOURCE ||
mdev->state.conn == C_SYNC_TARGET)
drbd_syncer_progress(mdev, seq);
if (mdev->state.conn == C_VERIFY_S || mdev->state.conn == C_VERIFY_T)
seq_printf(seq, "\t%3d%% %lu/%lu\n",
(int)((mdev->rs_total-mdev->ov_left) /
(mdev->rs_total/100+1)),
mdev->rs_total - mdev->ov_left,
mdev->rs_total);
if (proc_details >= 1 && get_ldev_if_state(mdev, D_FAILED)) {
lc_seq_printf_stats(seq, mdev->resync);
lc_seq_printf_stats(seq, mdev->act_log);
put_ldev(mdev);
}
if (proc_details >= 2) {
if (mdev->resync) {
lc_seq_dump_details(seq, mdev->resync, "rs_left",
resync_dump_detail);
}
}
}
return 0;
}
static int drbd_proc_open(struct inode *inode, struct file *file)
{
return single_open(file, drbd_seq_show, PDE(inode)->data);
}
/* PROC FS stuff end */

4427
drivers/block/drbd/drbd_receiver.c Normal file
View file

File diff suppressed because it is too large Load diff

1120
drivers/block/drbd/drbd_req.c Normal file
View file

File diff suppressed because it is too large Load diff

326
drivers/block/drbd/drbd_req.h Normal file
View file

@ -0,0 +1,326 @@
/*
drbd_req.h
This file is part of DRBD by Philipp Reisner and Lars Ellenberg.
Copyright (C) 2006-2008, LINBIT Information Technologies GmbH.
Copyright (C) 2006-2008, Lars Ellenberg <lars.ellenberg@linbit.com>.
Copyright (C) 2006-2008, Philipp Reisner <philipp.reisner@linbit.com>.
DRBD is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.
DRBD is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with drbd; see the file COPYING. If not, write to
the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#ifndef _DRBD_REQ_H
#define _DRBD_REQ_H
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/drbd.h>
#include "drbd_int.h"
#include "drbd_wrappers.h"
/* The request callbacks will be called in irq context by the IDE drivers,
and in Softirqs/Tasklets/BH context by the SCSI drivers,
and by the receiver and worker in kernel-thread context.
Try to get the locking right :) */
/*
* Objects of type struct drbd_request do only exist on a R_PRIMARY node, and are
* associated with IO requests originating from the block layer above us.
*
* There are quite a few things that may happen to a drbd request
* during its lifetime.
*
* It will be created.
* It will be marked with the intention to be
* submitted to local disk and/or
* send via the network.
*
* It has to be placed on the transfer log and other housekeeping lists,
* In case we have a network connection.
*
* It may be identified as a concurrent (write) request
* and be handled accordingly.
*
* It may me handed over to the local disk subsystem.
* It may be completed by the local disk subsystem,
* either sucessfully or with io-error.
* In case it is a READ request, and it failed locally,
* it may be retried remotely.
*
* It may be queued for sending.
* It may be handed over to the network stack,
* which may fail.
* It may be acknowledged by the "peer" according to the wire_protocol in use.
* this may be a negative ack.
* It may receive a faked ack when the network connection is lost and the
* transfer log is cleaned up.
* Sending may be canceled due to network connection loss.
* When it finally has outlived its time,
* corresponding dirty bits in the resync-bitmap may be cleared or set,
* it will be destroyed,
* and completion will be signalled to the originator,
* with or without "success".
*/
enum drbd_req_event {
created,
to_be_send,
to_be_submitted,
/* XXX yes, now I am inconsistent...
* these two are not "events" but "actions"
* oh, well... */
queue_for_net_write,
queue_for_net_read,
send_canceled,
send_failed,
handed_over_to_network,
connection_lost_while_pending,
recv_acked_by_peer,
write_acked_by_peer,
write_acked_by_peer_and_sis, /* and set_in_sync */
conflict_discarded_by_peer,
neg_acked,
barrier_acked, /* in protocol A and B */
data_received, /* (remote read) */
read_completed_with_error,
read_ahead_completed_with_error,
write_completed_with_error,
completed_ok,
nothing, /* for tracing only */
};
/* encoding of request states for now. we don't actually need that many bits.
* we don't need to do atomic bit operations either, since most of the time we
* need to look at the connection state and/or manipulate some lists at the
* same time, so we should hold the request lock anyways.
*/
enum drbd_req_state_bits {
/* 210
* 000: no local possible
* 001: to be submitted
* UNUSED, we could map: 011: submitted, completion still pending
* 110: completed ok
* 010: completed with error
*/
__RQ_LOCAL_PENDING,
__RQ_LOCAL_COMPLETED,
__RQ_LOCAL_OK,
/* 76543
* 00000: no network possible
* 00001: to be send
* 00011: to be send, on worker queue
* 00101: sent, expecting recv_ack (B) or write_ack (C)
* 11101: sent,
* recv_ack (B) or implicit "ack" (A),
* still waiting for the barrier ack.
* master_bio may already be completed and invalidated.
* 11100: write_acked (C),
* data_received (for remote read, any protocol)
* or finally the barrier ack has arrived (B,A)...
* request can be freed
* 01100: neg-acked (write, protocol C)
* or neg-d-acked (read, any protocol)
* or killed from the transfer log
* during cleanup after connection loss
* request can be freed
* 01000: canceled or send failed...
* request can be freed
*/
/* if "SENT" is not set, yet, this can still fail or be canceled.
* if "SENT" is set already, we still wait for an Ack packet.
* when cleared, the master_bio may be completed.
* in (B,A) the request object may still linger on the transaction log
* until the corresponding barrier ack comes in */
__RQ_NET_PENDING,
/* If it is QUEUED, and it is a WRITE, it is also registered in the
* transfer log. Currently we need this flag to avoid conflicts between
* worker canceling the request and tl_clear_barrier killing it from
* transfer log. We should restructure the code so this conflict does
* no longer occur. */
__RQ_NET_QUEUED,
/* well, actually only "handed over to the network stack".
*
* TODO can potentially be dropped because of the similar meaning
* of RQ_NET_SENT and ~RQ_NET_QUEUED.
* however it is not exactly the same. before we drop it
* we must ensure that we can tell a request with network part
* from a request without, regardless of what happens to it. */
__RQ_NET_SENT,
/* when set, the request may be freed (if RQ_NET_QUEUED is clear).
* basically this means the corresponding P_BARRIER_ACK was received */
__RQ_NET_DONE,
/* whether or not we know (C) or pretend (B,A) that the write
* was successfully written on the peer.
*/
__RQ_NET_OK,
/* peer called drbd_set_in_sync() for this write */
__RQ_NET_SIS,
/* keep this last, its for the RQ_NET_MASK */
__RQ_NET_MAX,
};
#define RQ_LOCAL_PENDING (1UL << __RQ_LOCAL_PENDING)
#define RQ_LOCAL_COMPLETED (1UL << __RQ_LOCAL_COMPLETED)
#define RQ_LOCAL_OK (1UL << __RQ_LOCAL_OK)
#define RQ_LOCAL_MASK ((RQ_LOCAL_OK << 1)-1) /* 0x07 */
#define RQ_NET_PENDING (1UL << __RQ_NET_PENDING)
#define RQ_NET_QUEUED (1UL << __RQ_NET_QUEUED)
#define RQ_NET_SENT (1UL << __RQ_NET_SENT)
#define RQ_NET_DONE (1UL << __RQ_NET_DONE)
#define RQ_NET_OK (1UL << __RQ_NET_OK)
#define RQ_NET_SIS (1UL << __RQ_NET_SIS)
/* 0x1f8 */
#define RQ_NET_MASK (((1UL << __RQ_NET_MAX)-1) & ~RQ_LOCAL_MASK)
/* epoch entries */
static inline
struct hlist_head *ee_hash_slot(struct drbd_conf *mdev, sector_t sector)
{
BUG_ON(mdev->ee_hash_s == 0);
return mdev->ee_hash +
((unsigned int)(sector>>HT_SHIFT) % mdev->ee_hash_s);
}
/* transfer log (drbd_request objects) */
static inline
struct hlist_head *tl_hash_slot(struct drbd_conf *mdev, sector_t sector)
{
BUG_ON(mdev->tl_hash_s == 0);
return mdev->tl_hash +
((unsigned int)(sector>>HT_SHIFT) % mdev->tl_hash_s);
}
/* application reads (drbd_request objects) */
static struct hlist_head *ar_hash_slot(struct drbd_conf *mdev, sector_t sector)
{
return mdev->app_reads_hash
+ ((unsigned int)(sector) % APP_R_HSIZE);
}
/* when we receive the answer for a read request,
* verify that we actually know about it */
static inline struct drbd_request *_ar_id_to_req(struct drbd_conf *mdev,
u64 id, sector_t sector)
{
struct hlist_head *slot = ar_hash_slot(mdev, sector);
struct hlist_node *n;
struct drbd_request *req;
hlist_for_each_entry(req, n, slot, colision) {
if ((unsigned long)req == (unsigned long)id) {
D_ASSERT(req->sector == sector);
return req;
}
}
return NULL;
}
static inline struct drbd_request *drbd_req_new(struct drbd_conf *mdev,
struct bio *bio_src)
{
struct bio *bio;
struct drbd_request *req =
mempool_alloc(drbd_request_mempool, GFP_NOIO);
if (likely(req)) {
bio = bio_clone(bio_src, GFP_NOIO); /* XXX cannot fail?? */
req->rq_state = 0;
req->mdev = mdev;
req->master_bio = bio_src;
req->private_bio = bio;
req->epoch = 0;
req->sector = bio->bi_sector;
req->size = bio->bi_size;
req->start_time = jiffies;
INIT_HLIST_NODE(&req->colision);
INIT_LIST_HEAD(&req->tl_requests);
INIT_LIST_HEAD(&req->w.list);
bio->bi_private = req;
bio->bi_end_io = drbd_endio_pri;
bio->bi_next = NULL;
}
return req;
}
static inline void drbd_req_free(struct drbd_request *req)
{
mempool_free(req, drbd_request_mempool);
}
static inline int overlaps(sector_t s1, int l1, sector_t s2, int l2)
{
return !((s1 + (l1>>9) <= s2) || (s1 >= s2 + (l2>>9)));
}
/* Short lived temporary struct on the stack.
* We could squirrel the error to be returned into
* bio->bi_size, or similar. But that would be too ugly. */
struct bio_and_error {
struct bio *bio;
int error;
};
extern void _req_may_be_done(struct drbd_request *req,
struct bio_and_error *m);
extern void __req_mod(struct drbd_request *req, enum drbd_req_event what,
struct bio_and_error *m);
extern void complete_master_bio(struct drbd_conf *mdev,
struct bio_and_error *m);
/* use this if you don't want to deal with calling complete_master_bio()
* outside the spinlock, e.g. when walking some list on cleanup. */
static inline void _req_mod(struct drbd_request *req, enum drbd_req_event what)
{
struct drbd_conf *mdev = req->mdev;
struct bio_and_error m;
/* __req_mod possibly frees req, do not touch req after that! */
__req_mod(req, what, &m);
if (m.bio)
complete_master_bio(mdev, &m);
}
/* completion of master bio is outside of spinlock.
* If you need it irqsave, do it your self! */
static inline void req_mod(struct drbd_request *req,
enum drbd_req_event what)
{
struct drbd_conf *mdev = req->mdev;
struct bio_and_error m;
spin_lock_irq(&mdev->req_lock);
__req_mod(req, what, &m);
spin_unlock_irq(&mdev->req_lock);
if (m.bio)
complete_master_bio(mdev, &m);
}
#endif

113
drivers/block/drbd/drbd_strings.c Normal file
View file

@ -0,0 +1,113 @@
/*
drbd.h
This file is part of DRBD by Philipp Reisner and Lars Ellenberg.
Copyright (C) 2003-2008, LINBIT Information Technologies GmbH.
Copyright (C) 2003-2008, Philipp Reisner <philipp.reisner@linbit.com>.
Copyright (C) 2003-2008, Lars Ellenberg <lars.ellenberg@linbit.com>.
drbd is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.
drbd is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with drbd; see the file COPYING. If not, write to
the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#include <linux/drbd.h>
static const char *drbd_conn_s_names[] = {
[C_STANDALONE] = "StandAlone",
[C_DISCONNECTING] = "Disconnecting",
[C_UNCONNECTED] = "Unconnected",
[C_TIMEOUT] = "Timeout",
[C_BROKEN_PIPE] = "BrokenPipe",
[C_NETWORK_FAILURE] = "NetworkFailure",
[C_PROTOCOL_ERROR] = "ProtocolError",
[C_WF_CONNECTION] = "WFConnection",
[C_WF_REPORT_PARAMS] = "WFReportParams",
[C_TEAR_DOWN] = "TearDown",
[C_CONNECTED] = "Connected",
[C_STARTING_SYNC_S] = "StartingSyncS",
[C_STARTING_SYNC_T] = "StartingSyncT",
[C_WF_BITMAP_S] = "WFBitMapS",
[C_WF_BITMAP_T] = "WFBitMapT",
[C_WF_SYNC_UUID] = "WFSyncUUID",
[C_SYNC_SOURCE] = "SyncSource",
[C_SYNC_TARGET] = "SyncTarget",
[C_PAUSED_SYNC_S] = "PausedSyncS",
[C_PAUSED_SYNC_T] = "PausedSyncT",
[C_VERIFY_S] = "VerifyS",
[C_VERIFY_T] = "VerifyT",
};
static const char *drbd_role_s_names[] = {
[R_PRIMARY] = "Primary",
[R_SECONDARY] = "Secondary",
[R_UNKNOWN] = "Unknown"
};
static const char *drbd_disk_s_names[] = {
[D_DISKLESS] = "Diskless",
[D_ATTACHING] = "Attaching",
[D_FAILED] = "Failed",
[D_NEGOTIATING] = "Negotiating",
[D_INCONSISTENT] = "Inconsistent",
[D_OUTDATED] = "Outdated",
[D_UNKNOWN] = "DUnknown",
[D_CONSISTENT] = "Consistent",
[D_UP_TO_DATE] = "UpToDate",
};
static const char *drbd_state_sw_errors[] = {
[-SS_TWO_PRIMARIES] = "Multiple primaries not allowed by config",
[-SS_NO_UP_TO_DATE_DISK] = "Refusing to be Primary without at least one UpToDate disk",
[-SS_NO_LOCAL_DISK] = "Can not resync without local disk",
[-SS_NO_REMOTE_DISK] = "Can not resync without remote disk",
[-SS_CONNECTED_OUTDATES] = "Refusing to be Outdated while Connected",
[-SS_PRIMARY_NOP] = "Refusing to be Primary while peer is not outdated",
[-SS_RESYNC_RUNNING] = "Can not start OV/resync since it is already active",
[-SS_ALREADY_STANDALONE] = "Can not disconnect a StandAlone device",
[-SS_CW_FAILED_BY_PEER] = "State change was refused by peer node",
[-SS_IS_DISKLESS] = "Device is diskless, the requested operation requires a disk",
[-SS_DEVICE_IN_USE] = "Device is held open by someone",
[-SS_NO_NET_CONFIG] = "Have no net/connection configuration",
[-SS_NO_VERIFY_ALG] = "Need a verify algorithm to start online verify",
[-SS_NEED_CONNECTION] = "Need a connection to start verify or resync",
[-SS_NOT_SUPPORTED] = "Peer does not support protocol",
[-SS_LOWER_THAN_OUTDATED] = "Disk state is lower than outdated",
[-SS_IN_TRANSIENT_STATE] = "In transient state, retry after next state change",
[-SS_CONCURRENT_ST_CHG] = "Concurrent state changes detected and aborted",
};
const char *drbd_conn_str(enum drbd_conns s)
{
/* enums are unsigned... */
return s > C_PAUSED_SYNC_T ? "TOO_LARGE" : drbd_conn_s_names[s];
}
const char *drbd_role_str(enum drbd_role s)
{
return s > R_SECONDARY ? "TOO_LARGE" : drbd_role_s_names[s];
}
const char *drbd_disk_str(enum drbd_disk_state s)
{
return s > D_UP_TO_DATE ? "TOO_LARGE" : drbd_disk_s_names[s];
}
const char *drbd_set_st_err_str(enum drbd_state_ret_codes err)
{
return err <= SS_AFTER_LAST_ERROR ? "TOO_SMALL" :
err > SS_TWO_PRIMARIES ? "TOO_LARGE"
: drbd_state_sw_errors[-err];
}

351
drivers/block/drbd/drbd_vli.h Normal file
View file

@ -0,0 +1,351 @@
/*
-*- linux-c -*-
drbd_receiver.c
This file is part of DRBD by Philipp Reisner and Lars Ellenberg.
Copyright (C) 2001-2008, LINBIT Information Technologies GmbH.
Copyright (C) 1999-2008, Philipp Reisner <philipp.reisner@linbit.com>.
Copyright (C) 2002-2008, Lars Ellenberg <lars.ellenberg@linbit.com>.
drbd is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.
drbd is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with drbd; see the file COPYING. If not, write to
the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#ifndef _DRBD_VLI_H
#define _DRBD_VLI_H
/*
* At a granularity of 4KiB storage represented per bit,
* and stroage sizes of several TiB,
* and possibly small-bandwidth replication,
* the bitmap transfer time can take much too long,
* if transmitted in plain text.
*
* We try to reduce the transfered bitmap information
* by encoding runlengths of bit polarity.
*
* We never actually need to encode a "zero" (runlengths are positive).
* But then we have to store the value of the first bit.
* The first bit of information thus shall encode if the first runlength
* gives the number of set or unset bits.
*
* We assume that large areas are either completely set or unset,
* which gives good compression with any runlength method,
* even when encoding the runlength as fixed size 32bit/64bit integers.
*
* Still, there may be areas where the polarity flips every few bits,
* and encoding the runlength sequence of those areas with fix size
* integers would be much worse than plaintext.
*
* We want to encode small runlength values with minimum code length,
* while still being able to encode a Huge run of all zeros.
*
* Thus we need a Variable Length Integer encoding, VLI.
*
* For some cases, we produce more code bits than plaintext input.
* We need to send incompressible chunks as plaintext, skip over them
* and then see if the next chunk compresses better.
*
* We don't care too much about "excellent" compression ratio for large
* runlengths (all set/all clear): whether we achieve a factor of 100
* or 1000 is not that much of an issue.
* We do not want to waste too much on short runlengths in the "noisy"
* parts of the bitmap, though.
*
* There are endless variants of VLI, we experimented with:
* * simple byte-based
* * various bit based with different code word length.
*
* To avoid yet an other configuration parameter (choice of bitmap compression
* algorithm) which was difficult to explain and tune, we just chose the one
* variant that turned out best in all test cases.
* Based on real world usage patterns, with device sizes ranging from a few GiB
* to several TiB, file server/mailserver/webserver/mysql/postgress,
* mostly idle to really busy, the all time winner (though sometimes only
* marginally better) is:
*/
/*
* encoding is "visualised" as
* __little endian__ bitstream, least significant bit first (left most)
*
* this particular encoding is chosen so that the prefix code
* starts as unary encoding the level, then modified so that
* 10 levels can be described in 8bit, with minimal overhead
* for the smaller levels.
*
* Number of data bits follow fibonacci sequence, with the exception of the
* last level (+1 data bit, so it makes 64bit total). The only worse code when
* encoding bit polarity runlength is 1 plain bits => 2 code bits.
prefix data bits max val Nº data bits
0 x 0x2 1
10 x 0x4 1
110 xx 0x8 2
1110 xxx 0x10 3
11110 xxx xx 0x30 5
111110 xx xxxxxx 0x130 8
11111100 xxxxxxxx xxxxx 0x2130 13
11111110 xxxxxxxx xxxxxxxx xxxxx 0x202130 21
11111101 xxxxxxxx xxxxxxxx xxxxxxxx xxxxxxxx xx 0x400202130 34
11111111 xxxxxxxx xxxxxxxx xxxxxxxx xxxxxxxx xxxxxxxx xxxxxxxx xxxxxxxx 56
* maximum encodable value: 0x100000400202130 == 2**56 + some */
/* compression "table":
transmitted x 0.29
as plaintext x ........................
x ........................
x ........................
x 0.59 0.21........................
x ........................................................
x .. c ...................................................
x 0.44.. o ...................................................
x .......... d ...................................................
x .......... e ...................................................
X............. ...................................................
x.............. b ...................................................
2.0x............... i ...................................................
#X................ t ...................................................
#................. s ........................... plain bits ..........
-+-----------------------------------------------------------------------
1 16 32 64
*/
/* LEVEL: (total bits, prefix bits, prefix value),
* sorted ascending by number of total bits.
* The rest of the code table is calculated at compiletime from this. */
/* fibonacci data 1, 1, ... */
#define VLI_L_1_1() do { \
LEVEL( 2, 1, 0x00); \
LEVEL( 3, 2, 0x01); \
LEVEL( 5, 3, 0x03); \
LEVEL( 7, 4, 0x07); \
LEVEL(10, 5, 0x0f); \
LEVEL(14, 6, 0x1f); \
LEVEL(21, 8, 0x3f); \
LEVEL(29, 8, 0x7f); \
LEVEL(42, 8, 0xbf); \
LEVEL(64, 8, 0xff); \
} while (0)
/* finds a suitable level to decode the least significant part of in.
* returns number of bits consumed.
*
* BUG() for bad input, as that would mean a buggy code table. */
static inline int vli_decode_bits(u64 *out, const u64 in)
{
u64 adj = 1;
#define LEVEL(t,b,v) \
do { \
if ((in & ((1 << b) -1)) == v) { \
*out = ((in & ((~0ULL) >> (64-t))) >> b) + adj; \
return t; \
} \
adj += 1ULL << (t - b); \
} while (0)
VLI_L_1_1();
/* NOT REACHED, if VLI_LEVELS code table is defined properly */
BUG();
#undef LEVEL
}
/* return number of code bits needed,
* or negative error number */
static inline int __vli_encode_bits(u64 *out, const u64 in)
{
u64 max = 0;
u64 adj = 1;
if (in == 0)
return -EINVAL;
#define LEVEL(t,b,v) do { \
max += 1ULL << (t - b); \
if (in <= max) { \
if (out) \
*out = ((in - adj) << b) | v; \
return t; \
} \
adj = max + 1; \
} while (0)
VLI_L_1_1();
return -EOVERFLOW;
#undef LEVEL
}
#undef VLI_L_1_1
/* code from here down is independend of actually used bit code */
/*
* Code length is determined by some unique (e.g. unary) prefix.
* This encodes arbitrary bit length, not whole bytes: we have a bit-stream,
* not a byte stream.
*/
/* for the bitstream, we need a cursor */
struct bitstream_cursor {
/* the current byte */
u8 *b;
/* the current bit within *b, nomalized: 0..7 */
unsigned int bit;
};
/* initialize cursor to point to first bit of stream */
static inline void bitstream_cursor_reset(struct bitstream_cursor *cur, void *s)
{
cur->b = s;
cur->bit = 0;
}
/* advance cursor by that many bits; maximum expected input value: 64,
* but depending on VLI implementation, it may be more. */
static inline void bitstream_cursor_advance(struct bitstream_cursor *cur, unsigned int bits)
{
bits += cur->bit;
cur->b = cur->b + (bits >> 3);
cur->bit = bits & 7;
}
/* the bitstream itself knows its length */
struct bitstream {
struct bitstream_cursor cur;
unsigned char *buf;
size_t buf_len; /* in bytes */
/* for input stream:
* number of trailing 0 bits for padding
* total number of valid bits in stream: buf_len * 8 - pad_bits */
unsigned int pad_bits;
};
static inline void bitstream_init(struct bitstream *bs, void *s, size_t len, unsigned int pad_bits)
{
bs->buf = s;
bs->buf_len = len;
bs->pad_bits = pad_bits;
bitstream_cursor_reset(&bs->cur, bs->buf);
}
static inline void bitstream_rewind(struct bitstream *bs)
{
bitstream_cursor_reset(&bs->cur, bs->buf);
memset(bs->buf, 0, bs->buf_len);
}
/* Put (at most 64) least significant bits of val into bitstream, and advance cursor.
* Ignores "pad_bits".
* Returns zero if bits == 0 (nothing to do).
* Returns number of bits used if successful.
*
* If there is not enough room left in bitstream,
* leaves bitstream unchanged and returns -ENOBUFS.
*/
static inline int bitstream_put_bits(struct bitstream *bs, u64 val, const unsigned int bits)
{
unsigned char *b = bs->cur.b;
unsigned int tmp;
if (bits == 0)
return 0;
if ((bs->cur.b + ((bs->cur.bit + bits -1) >> 3)) - bs->buf >= bs->buf_len)
return -ENOBUFS;
/* paranoia: strip off hi bits; they should not be set anyways. */
if (bits < 64)
val &= ~0ULL >> (64 - bits);
*b++ |= (val & 0xff) << bs->cur.bit;
for (tmp = 8 - bs->cur.bit; tmp < bits; tmp += 8)
*b++ |= (val >> tmp) & 0xff;
bitstream_cursor_advance(&bs->cur, bits);
return bits;
}
/* Fetch (at most 64) bits from bitstream into *out, and advance cursor.
*
* If more than 64 bits are requested, returns -EINVAL and leave *out unchanged.
*
* If there are less than the requested number of valid bits left in the
* bitstream, still fetches all available bits.
*
* Returns number of actually fetched bits.
*/
static inline int bitstream_get_bits(struct bitstream *bs, u64 *out, int bits)
{
u64 val;
unsigned int n;
if (bits > 64)
return -EINVAL;
if (bs->cur.b + ((bs->cur.bit + bs->pad_bits + bits -1) >> 3) - bs->buf >= bs->buf_len)
bits = ((bs->buf_len - (bs->cur.b - bs->buf)) << 3)
- bs->cur.bit - bs->pad_bits;
if (bits == 0) {
*out = 0;
return 0;
}
/* get the high bits */
val = 0;
n = (bs->cur.bit + bits + 7) >> 3;
/* n may be at most 9, if cur.bit + bits > 64 */
/* which means this copies at most 8 byte */
if (n) {
memcpy(&val, bs->cur.b+1, n - 1);
val = le64_to_cpu(val) << (8 - bs->cur.bit);
}
/* we still need the low bits */
val |= bs->cur.b[0] >> bs->cur.bit;
/* and mask out bits we don't want */
val &= ~0ULL >> (64 - bits);
bitstream_cursor_advance(&bs->cur, bits);
*out = val;
return bits;
}
/* encodes @in as vli into @bs;
* return values
* > 0: number of bits successfully stored in bitstream
* -ENOBUFS @bs is full
* -EINVAL input zero (invalid)
* -EOVERFLOW input too large for this vli code (invalid)
*/
static inline int vli_encode_bits(struct bitstream *bs, u64 in)
{
u64 code = code;
int bits = __vli_encode_bits(&code, in);
if (bits <= 0)
return bits;
return bitstream_put_bits(bs, code, bits);
}
#endif

1512
drivers/block/drbd/drbd_worker.c Normal file
View file

File diff suppressed because it is too large Load diff

91
drivers/block/drbd/drbd_wrappers.h Normal file
View file

@ -0,0 +1,91 @@
#ifndef _DRBD_WRAPPERS_H
#define _DRBD_WRAPPERS_H
#include <linux/ctype.h>
#include <linux/mm.h>
/* see get_sb_bdev and bd_claim */
extern char *drbd_sec_holder;
/* sets the number of 512 byte sectors of our virtual device */
static inline void drbd_set_my_capacity(struct drbd_conf *mdev,
sector_t size)
{
/* set_capacity(mdev->this_bdev->bd_disk, size); */
set_capacity(mdev->vdisk, size);
mdev->this_bdev->bd_inode->i_size = (loff_t)size << 9;
}
#define drbd_bio_uptodate(bio) bio_flagged(bio, BIO_UPTODATE)
static inline int drbd_bio_has_active_page(struct bio *bio)
{
struct bio_vec *bvec;
int i;
__bio_for_each_segment(bvec, bio, i, 0) {
if (page_count(bvec->bv_page) > 1)
return 1;
}
return 0;
}
/* bi_end_io handlers */
extern void drbd_md_io_complete(struct bio *bio, int error);
extern void drbd_endio_read_sec(struct bio *bio, int error);
extern void drbd_endio_write_sec(struct bio *bio, int error);
extern void drbd_endio_pri(struct bio *bio, int error);
/*
* used to submit our private bio
*/
static inline void drbd_generic_make_request(struct drbd_conf *mdev,
int fault_type, struct bio *bio)
{
__release(local);
if (!bio->bi_bdev) {
printk(KERN_ERR "drbd%d: drbd_generic_make_request: "
"bio->bi_bdev == NULL\n",
mdev_to_minor(mdev));
dump_stack();
bio_endio(bio, -ENODEV);
return;
}
if (FAULT_ACTIVE(mdev, fault_type))
bio_endio(bio, -EIO);
else
generic_make_request(bio);
}
static inline void drbd_plug_device(struct drbd_conf *mdev)
{
struct request_queue *q;
q = bdev_get_queue(mdev->this_bdev);
spin_lock_irq(q->queue_lock);
/* XXX the check on !blk_queue_plugged is redundant,
* implicitly checked in blk_plug_device */
if (!blk_queue_plugged(q)) {
blk_plug_device(q);
del_timer(&q->unplug_timer);
/* unplugging should not happen automatically... */
}
spin_unlock_irq(q->queue_lock);
}
static inline int drbd_crypto_is_hash(struct crypto_tfm *tfm)
{
return (crypto_tfm_alg_type(tfm) & CRYPTO_ALG_TYPE_HASH_MASK)
== CRYPTO_ALG_TYPE_HASH;
}
#ifndef __CHECKER__
# undef __cond_lock
# define __cond_lock(x,c) (c)
#endif
#endif

62
fs/aio.c
View file

@ -15,6 +15,7 @@
#include <linux/aio_abi.h>
#include <linux/module.h>
#include <linux/syscalls.h>
#include <linux/backing-dev.h>
#include <linux/uio.h>
#define DEBUG 0
@ -32,6 +33,9 @@
#include <linux/workqueue.h>
#include <linux/security.h>
#include <linux/eventfd.h>
#include <linux/blkdev.h>
#include <linux/mempool.h>
#include <linux/hash.h>
#include <asm/kmap_types.h>
#include <asm/uaccess.h>
@ -60,6 +64,14 @@ static DECLARE_WORK(fput_work, aio_fput_routine);
static DEFINE_SPINLOCK(fput_lock);
static LIST_HEAD(fput_head);
#define AIO_BATCH_HASH_BITS 3 /* allocated on-stack, so don't go crazy */
#define AIO_BATCH_HASH_SIZE (1 << AIO_BATCH_HASH_BITS)
struct aio_batch_entry {
struct hlist_node list;
struct address_space *mapping;
};
mempool_t *abe_pool;
static void aio_kick_handler(struct work_struct *);
static void aio_queue_work(struct kioctx *);
@ -73,6 +85,8 @@ static int __init aio_setup(void)
kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC);
aio_wq = create_workqueue("aio");
abe_pool = mempool_create_kmalloc_pool(1, sizeof(struct aio_batch_entry));
BUG_ON(!abe_pool);
pr_debug("aio_setup: sizeof(struct page) = %d\n", (int)sizeof(struct page));
@ -1531,8 +1545,44 @@ static int aio_wake_function(wait_queue_t *wait, unsigned mode,
return 1;
}
static void aio_batch_add(struct address_space *mapping,
struct hlist_head *batch_hash)
{
struct aio_batch_entry *abe;
struct hlist_node *pos;
unsigned bucket;
bucket = hash_ptr(mapping, AIO_BATCH_HASH_BITS);
hlist_for_each_entry(abe, pos, &batch_hash[bucket], list) {
if (abe->mapping == mapping)
return;
}
abe = mempool_alloc(abe_pool, GFP_KERNEL);
BUG_ON(!igrab(mapping->host));
abe->mapping = mapping;
hlist_add_head(&abe->list, &batch_hash[bucket]);
return;
}
static void aio_batch_free(struct hlist_head *batch_hash)
{
struct aio_batch_entry *abe;
struct hlist_node *pos, *n;
int i;
for (i = 0; i < AIO_BATCH_HASH_SIZE; i++) {
hlist_for_each_entry_safe(abe, pos, n, &batch_hash[i], list) {
blk_run_address_space(abe->mapping);
iput(abe->mapping->host);
hlist_del(&abe->list);
mempool_free(abe, abe_pool);
}
}
}
static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
struct iocb *iocb)
struct iocb *iocb, struct hlist_head *batch_hash)
{
struct kiocb *req;
struct file *file;
@ -1608,6 +1658,12 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
;
}
spin_unlock_irq(&ctx->ctx_lock);
if (req->ki_opcode == IOCB_CMD_PREAD ||
req->ki_opcode == IOCB_CMD_PREADV ||
req->ki_opcode == IOCB_CMD_PWRITE ||
req->ki_opcode == IOCB_CMD_PWRITEV)
aio_batch_add(file->f_mapping, batch_hash);
aio_put_req(req); /* drop extra ref to req */
return 0;
@ -1635,6 +1691,7 @@ SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr,
struct kioctx *ctx;
long ret = 0;
int i;
struct hlist_head batch_hash[AIO_BATCH_HASH_SIZE] = { { 0, }, };
if (unlikely(nr < 0))
return -EINVAL;
@ -1666,10 +1723,11 @@ SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr,
break;
}
ret = io_submit_one(ctx, user_iocb, &tmp);
ret = io_submit_one(ctx, user_iocb, &tmp, batch_hash);
if (ret)
break;
}
aio_batch_free(batch_hash);
put_ioctx(ctx);
return i ? i : ret;

12
fs/block_dev.c
View file

@ -405,7 +405,17 @@ static loff_t block_llseek(struct file *file, loff_t offset, int origin)
static int block_fsync(struct file *filp, struct dentry *dentry, int datasync)
{
return sync_blockdev(I_BDEV(filp->f_mapping->host));
struct block_device *bdev = I_BDEV(filp->f_mapping->host);
int error;
error = sync_blockdev(bdev);
if (error)
return error;
error = blkdev_issue_flush(bdev, NULL);
if (error == -EOPNOTSUPP)
error = 0;
return error;
}
/*

10
fs/direct-io.c
View file

@ -1028,9 +1028,6 @@ direct_io_worker(int rw, struct kiocb *iocb, struct inode *inode,
if (dio->bio)
dio_bio_submit(dio);
/* All IO is now issued, send it on its way */
blk_run_address_space(inode->i_mapping);
/*
* It is possible that, we return short IO due to end of file.
* In that case, we need to release all the pages we got hold on.
@ -1057,8 +1054,11 @@ direct_io_worker(int rw, struct kiocb *iocb, struct inode *inode,
((rw & READ) || (dio->result == dio->size)))
ret = -EIOCBQUEUED;
if (ret != -EIOCBQUEUED)
if (ret != -EIOCBQUEUED) {
/* All IO is now issued, send it on its way */
blk_run_address_space(inode->i_mapping);
dio_await_completion(dio);
}
/*
* Sync will always be dropping the final ref and completing the
@ -1124,7 +1124,7 @@ __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
int acquire_i_mutex = 0;
if (rw & WRITE)
rw = WRITE_ODIRECT;
rw = WRITE_SYNC_PLUG;
if (bdev)
bdev_blkbits = blksize_bits(bdev_logical_block_size(bdev));

13
include/linux/backing-dev.h
View file

@ -331,4 +331,17 @@ static inline int bdi_sched_wait(void *word)
return 0;
}
static inline void blk_run_backing_dev(struct backing_dev_info *bdi,
struct page *page)
{
if (bdi && bdi->unplug_io_fn)
bdi->unplug_io_fn(bdi, page);
}
static inline void blk_run_address_space(struct address_space *mapping)
{
if (mapping)
blk_run_backing_dev(mapping->backing_dev_info, NULL);
}
#endif /* _LINUX_BACKING_DEV_H */

8
include/linux/bio.h
View file

@ -450,11 +450,8 @@ extern struct biovec_slab bvec_slabs[BIOVEC_NR_POOLS] __read_mostly;
/*
* remember never ever reenable interrupts between a bvec_kmap_irq and
* bvec_kunmap_irq!
*
* This function MUST be inlined - it plays with the CPU interrupt flags.
*/
static __always_inline char *bvec_kmap_irq(struct bio_vec *bvec,
unsigned long *flags)
static inline char *bvec_kmap_irq(struct bio_vec *bvec, unsigned long *flags)
{
unsigned long addr;
@ -470,8 +467,7 @@ static __always_inline char *bvec_kmap_irq(struct bio_vec *bvec,
return (char *) addr + bvec->bv_offset;
}
static __always_inline void bvec_kunmap_irq(char *buffer,
unsigned long *flags)
static inline void bvec_kunmap_irq(char *buffer, unsigned long *flags)
{
unsigned long ptr = (unsigned long) buffer & PAGE_MASK;

13
include/linux/blkdev.h
View file

@ -823,19 +823,6 @@ static inline struct request_queue *bdev_get_queue(struct block_device *bdev)
return bdev->bd_disk->queue;
}
static inline void blk_run_backing_dev(struct backing_dev_info *bdi,
struct page *page)
{
if (bdi && bdi->unplug_io_fn)
bdi->unplug_io_fn(bdi, page);
}
static inline void blk_run_address_space(struct address_space *mapping)
{
if (mapping)
blk_run_backing_dev(mapping->backing_dev_info, NULL);
}
/*
* blk_rq_pos() : the current sector
* blk_rq_bytes() : bytes left in the entire request

350
include/linux/drbd.h Normal file
View file

@ -0,0 +1,350 @@
/*
drbd.h
Kernel module for 2.6.x Kernels
This file is part of DRBD by Philipp Reisner and Lars Ellenberg.
Copyright (C) 2001-2008, LINBIT Information Technologies GmbH.
Copyright (C) 2001-2008, Philipp Reisner <philipp.reisner@linbit.com>.
Copyright (C) 2001-2008, Lars Ellenberg <lars.ellenberg@linbit.com>.
drbd is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.
drbd is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with drbd; see the file COPYING. If not, write to
the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#ifndef DRBD_H
#define DRBD_H
#include <linux/connector.h>
#include <asm/types.h>
#ifdef __KERNEL__
#include <linux/types.h>
#include <asm/byteorder.h>
#else
#include <sys/types.h>
#include <sys/wait.h>
#include <limits.h>
/* Altough the Linux source code makes a difference between
generic endianness and the bitfields' endianness, there is no
architecture as of Linux-2.6.24-rc4 where the bitfileds' endianness
does not match the generic endianness. */
#if __BYTE_ORDER == __LITTLE_ENDIAN
#define __LITTLE_ENDIAN_BITFIELD
#elif __BYTE_ORDER == __BIG_ENDIAN
#define __BIG_ENDIAN_BITFIELD
#else
# error "sorry, weird endianness on this box"
#endif
#endif
extern const char *drbd_buildtag(void);
#define REL_VERSION "8.3.3rc2"
#define API_VERSION 88
#define PRO_VERSION_MIN 86
#define PRO_VERSION_MAX 91
enum drbd_io_error_p {
EP_PASS_ON, /* FIXME should the better be named "Ignore"? */
EP_CALL_HELPER,
EP_DETACH
};
enum drbd_fencing_p {
FP_DONT_CARE,
FP_RESOURCE,
FP_STONITH
};
enum drbd_disconnect_p {
DP_RECONNECT,
DP_DROP_NET_CONF,
DP_FREEZE_IO
};
enum drbd_after_sb_p {
ASB_DISCONNECT,
ASB_DISCARD_YOUNGER_PRI,
ASB_DISCARD_OLDER_PRI,
ASB_DISCARD_ZERO_CHG,
ASB_DISCARD_LEAST_CHG,
ASB_DISCARD_LOCAL,
ASB_DISCARD_REMOTE,
ASB_CONSENSUS,
ASB_DISCARD_SECONDARY,
ASB_CALL_HELPER,
ASB_VIOLENTLY
};
/* KEEP the order, do not delete or insert. Only append. */
enum drbd_ret_codes {
ERR_CODE_BASE = 100,
NO_ERROR = 101,
ERR_LOCAL_ADDR = 102,
ERR_PEER_ADDR = 103,
ERR_OPEN_DISK = 104,
ERR_OPEN_MD_DISK = 105,
ERR_DISK_NOT_BDEV = 107,
ERR_MD_NOT_BDEV = 108,
ERR_DISK_TO_SMALL = 111,
ERR_MD_DISK_TO_SMALL = 112,
ERR_BDCLAIM_DISK = 114,
ERR_BDCLAIM_MD_DISK = 115,
ERR_MD_IDX_INVALID = 116,
ERR_IO_MD_DISK = 118,
ERR_MD_INVALID = 119,
ERR_AUTH_ALG = 120,
ERR_AUTH_ALG_ND = 121,
ERR_NOMEM = 122,
ERR_DISCARD = 123,
ERR_DISK_CONFIGURED = 124,
ERR_NET_CONFIGURED = 125,
ERR_MANDATORY_TAG = 126,
ERR_MINOR_INVALID = 127,
ERR_INTR = 129, /* EINTR */
ERR_RESIZE_RESYNC = 130,
ERR_NO_PRIMARY = 131,
ERR_SYNC_AFTER = 132,
ERR_SYNC_AFTER_CYCLE = 133,
ERR_PAUSE_IS_SET = 134,
ERR_PAUSE_IS_CLEAR = 135,
ERR_PACKET_NR = 137,
ERR_NO_DISK = 138,
ERR_NOT_PROTO_C = 139,
ERR_NOMEM_BITMAP = 140,
ERR_INTEGRITY_ALG = 141, /* DRBD 8.2 only */
ERR_INTEGRITY_ALG_ND = 142, /* DRBD 8.2 only */
ERR_CPU_MASK_PARSE = 143, /* DRBD 8.2 only */
ERR_CSUMS_ALG = 144, /* DRBD 8.2 only */
ERR_CSUMS_ALG_ND = 145, /* DRBD 8.2 only */
ERR_VERIFY_ALG = 146, /* DRBD 8.2 only */
ERR_VERIFY_ALG_ND = 147, /* DRBD 8.2 only */
ERR_CSUMS_RESYNC_RUNNING= 148, /* DRBD 8.2 only */
ERR_VERIFY_RUNNING = 149, /* DRBD 8.2 only */
ERR_DATA_NOT_CURRENT = 150,
ERR_CONNECTED = 151, /* DRBD 8.3 only */
ERR_PERM = 152,
/* insert new ones above this line */
AFTER_LAST_ERR_CODE
};
#define DRBD_PROT_A 1
#define DRBD_PROT_B 2
#define DRBD_PROT_C 3
enum drbd_role {
R_UNKNOWN = 0,
R_PRIMARY = 1, /* role */
R_SECONDARY = 2, /* role */
R_MASK = 3,
};
/* The order of these constants is important.
* The lower ones (<C_WF_REPORT_PARAMS) indicate
* that there is no socket!
* >=C_WF_REPORT_PARAMS ==> There is a socket
*/
enum drbd_conns {
C_STANDALONE,
C_DISCONNECTING, /* Temporal state on the way to StandAlone. */
C_UNCONNECTED, /* >= C_UNCONNECTED -> inc_net() succeeds */
/* These temporal states are all used on the way
* from >= C_CONNECTED to Unconnected.
* The 'disconnect reason' states
* I do not allow to change beween them. */
C_TIMEOUT,
C_BROKEN_PIPE,
C_NETWORK_FAILURE,
C_PROTOCOL_ERROR,
C_TEAR_DOWN,
C_WF_CONNECTION,
C_WF_REPORT_PARAMS, /* we have a socket */
C_CONNECTED, /* we have introduced each other */
C_STARTING_SYNC_S, /* starting full sync by admin request. */
C_STARTING_SYNC_T, /* stariing full sync by admin request. */
C_WF_BITMAP_S,
C_WF_BITMAP_T,
C_WF_SYNC_UUID,
/* All SyncStates are tested with this comparison
* xx >= C_SYNC_SOURCE && xx <= C_PAUSED_SYNC_T */
C_SYNC_SOURCE,
C_SYNC_TARGET,
C_VERIFY_S,
C_VERIFY_T,
C_PAUSED_SYNC_S,
C_PAUSED_SYNC_T,
C_MASK = 31
};
enum drbd_disk_state {
D_DISKLESS,
D_ATTACHING, /* In the process of reading the meta-data */
D_FAILED, /* Becomes D_DISKLESS as soon as we told it the peer */
/* when >= D_FAILED it is legal to access mdev->bc */
D_NEGOTIATING, /* Late attaching state, we need to talk to the peer */
D_INCONSISTENT,
D_OUTDATED,
D_UNKNOWN, /* Only used for the peer, never for myself */
D_CONSISTENT, /* Might be D_OUTDATED, might be D_UP_TO_DATE ... */
D_UP_TO_DATE, /* Only this disk state allows applications' IO ! */
D_MASK = 15
};
union drbd_state {
/* According to gcc's docs is the ...
* The order of allocation of bit-fields within a unit (C90 6.5.2.1, C99 6.7.2.1).
* Determined by ABI.
* pointed out by Maxim Uvarov q<muvarov@ru.mvista.com>
* even though we transmit as "cpu_to_be32(state)",
* the offsets of the bitfields still need to be swapped
* on different endianess.
*/
struct {
#if defined(__LITTLE_ENDIAN_BITFIELD)
unsigned role:2 ; /* 3/4 primary/secondary/unknown */
unsigned peer:2 ; /* 3/4 primary/secondary/unknown */
unsigned conn:5 ; /* 17/32 cstates */
unsigned disk:4 ; /* 8/16 from D_DISKLESS to D_UP_TO_DATE */
unsigned pdsk:4 ; /* 8/16 from D_DISKLESS to D_UP_TO_DATE */
unsigned susp:1 ; /* 2/2 IO suspended no/yes */
unsigned aftr_isp:1 ; /* isp .. imposed sync pause */
unsigned peer_isp:1 ;
unsigned user_isp:1 ;
unsigned _pad:11; /* 0 unused */
#elif defined(__BIG_ENDIAN_BITFIELD)
unsigned _pad:11; /* 0 unused */
unsigned user_isp:1 ;
unsigned peer_isp:1 ;
unsigned aftr_isp:1 ; /* isp .. imposed sync pause */
unsigned susp:1 ; /* 2/2 IO suspended no/yes */
unsigned pdsk:4 ; /* 8/16 from D_DISKLESS to D_UP_TO_DATE */
unsigned disk:4 ; /* 8/16 from D_DISKLESS to D_UP_TO_DATE */
unsigned conn:5 ; /* 17/32 cstates */
unsigned peer:2 ; /* 3/4 primary/secondary/unknown */
unsigned role:2 ; /* 3/4 primary/secondary/unknown */
#else
# error "this endianess is not supported"
#endif
};
unsigned int i;
};
enum drbd_state_ret_codes {
SS_CW_NO_NEED = 4,
SS_CW_SUCCESS = 3,
SS_NOTHING_TO_DO = 2,
SS_SUCCESS = 1,
SS_UNKNOWN_ERROR = 0, /* Used to sleep longer in _drbd_request_state */
SS_TWO_PRIMARIES = -1,
SS_NO_UP_TO_DATE_DISK = -2,
SS_NO_LOCAL_DISK = -4,
SS_NO_REMOTE_DISK = -5,
SS_CONNECTED_OUTDATES = -6,
SS_PRIMARY_NOP = -7,
SS_RESYNC_RUNNING = -8,
SS_ALREADY_STANDALONE = -9,
SS_CW_FAILED_BY_PEER = -10,
SS_IS_DISKLESS = -11,
SS_DEVICE_IN_USE = -12,
SS_NO_NET_CONFIG = -13,
SS_NO_VERIFY_ALG = -14, /* drbd-8.2 only */
SS_NEED_CONNECTION = -15, /* drbd-8.2 only */
SS_LOWER_THAN_OUTDATED = -16,
SS_NOT_SUPPORTED = -17, /* drbd-8.2 only */
SS_IN_TRANSIENT_STATE = -18, /* Retry after the next state change */
SS_CONCURRENT_ST_CHG = -19, /* Concurrent cluster side state change! */
SS_AFTER_LAST_ERROR = -20, /* Keep this at bottom */
};
/* from drbd_strings.c */
extern const char *drbd_conn_str(enum drbd_conns);
extern const char *drbd_role_str(enum drbd_role);
extern const char *drbd_disk_str(enum drbd_disk_state);
extern const char *drbd_set_st_err_str(enum drbd_state_ret_codes);
#define SHARED_SECRET_MAX 64
#define MDF_CONSISTENT (1 << 0)
#define MDF_PRIMARY_IND (1 << 1)
#define MDF_CONNECTED_IND (1 << 2)
#define MDF_FULL_SYNC (1 << 3)
#define MDF_WAS_UP_TO_DATE (1 << 4)
#define MDF_PEER_OUT_DATED (1 << 5)
#define MDF_CRASHED_PRIMARY (1 << 6)
enum drbd_uuid_index {
UI_CURRENT,
UI_BITMAP,
UI_HISTORY_START,
UI_HISTORY_END,
UI_SIZE, /* nl-packet: number of dirty bits */
UI_FLAGS, /* nl-packet: flags */
UI_EXTENDED_SIZE /* Everything. */
};
enum drbd_timeout_flag {
UT_DEFAULT = 0,
UT_DEGRADED = 1,
UT_PEER_OUTDATED = 2,
};
#define UUID_JUST_CREATED ((__u64)4)
#define DRBD_MAGIC 0x83740267
#define BE_DRBD_MAGIC __constant_cpu_to_be32(DRBD_MAGIC)
/* these are of type "int" */
#define DRBD_MD_INDEX_INTERNAL -1
#define DRBD_MD_INDEX_FLEX_EXT -2
#define DRBD_MD_INDEX_FLEX_INT -3
/* Start of the new netlink/connector stuff */
#define DRBD_NL_CREATE_DEVICE 0x01
#define DRBD_NL_SET_DEFAULTS 0x02
/* The following line should be moved over to linux/connector.h
* when the time comes */
#ifndef CN_IDX_DRBD
# define CN_IDX_DRBD 0x4
/* Ubuntu "intrepid ibex" release defined CN_IDX_DRBD as 0x6 */
#endif
#define CN_VAL_DRBD 0x1
/* For searching a vacant cn_idx value */
#define CN_IDX_STEP 6977
struct drbd_nl_cfg_req {
int packet_type;
unsigned int drbd_minor;
int flags;
unsigned short tag_list[];
};
struct drbd_nl_cfg_reply {
int packet_type;
unsigned int minor;
int ret_code; /* enum ret_code or set_st_err_t */
unsigned short tag_list[]; /* only used with get_* calls */
};
#endif

137
include/linux/drbd_limits.h Normal file
View file

@ -0,0 +1,137 @@
/*
drbd_limits.h
This file is part of DRBD by Philipp Reisner and Lars Ellenberg.
*/
/*
* Our current limitations.
* Some of them are hard limits,
* some of them are arbitrary range limits, that make it easier to provide
* feedback about nonsense settings for certain configurable values.
*/
#ifndef DRBD_LIMITS_H
#define DRBD_LIMITS_H 1
#define DEBUG_RANGE_CHECK 0
#define DRBD_MINOR_COUNT_MIN 1
#define DRBD_MINOR_COUNT_MAX 255
#define DRBD_DIALOG_REFRESH_MIN 0
#define DRBD_DIALOG_REFRESH_MAX 600
/* valid port number */
#define DRBD_PORT_MIN 1
#define DRBD_PORT_MAX 0xffff
/* startup { */
/* if you want more than 3.4 days, disable */
#define DRBD_WFC_TIMEOUT_MIN 0
#define DRBD_WFC_TIMEOUT_MAX 300000
#define DRBD_WFC_TIMEOUT_DEF 0
#define DRBD_DEGR_WFC_TIMEOUT_MIN 0
#define DRBD_DEGR_WFC_TIMEOUT_MAX 300000
#define DRBD_DEGR_WFC_TIMEOUT_DEF 0
#define DRBD_OUTDATED_WFC_TIMEOUT_MIN 0
#define DRBD_OUTDATED_WFC_TIMEOUT_MAX 300000
#define DRBD_OUTDATED_WFC_TIMEOUT_DEF 0
/* }*/
/* net { */
/* timeout, unit centi seconds
* more than one minute timeout is not usefull */
#define DRBD_TIMEOUT_MIN 1
#define DRBD_TIMEOUT_MAX 600
#define DRBD_TIMEOUT_DEF 60 /* 6 seconds */
/* active connection retries when C_WF_CONNECTION */
#define DRBD_CONNECT_INT_MIN 1
#define DRBD_CONNECT_INT_MAX 120
#define DRBD_CONNECT_INT_DEF 10 /* seconds */
/* keep-alive probes when idle */
#define DRBD_PING_INT_MIN 1
#define DRBD_PING_INT_MAX 120
#define DRBD_PING_INT_DEF 10
/* timeout for the ping packets.*/
#define DRBD_PING_TIMEO_MIN 1
#define DRBD_PING_TIMEO_MAX 100
#define DRBD_PING_TIMEO_DEF 5
/* max number of write requests between write barriers */
#define DRBD_MAX_EPOCH_SIZE_MIN 1
#define DRBD_MAX_EPOCH_SIZE_MAX 20000
#define DRBD_MAX_EPOCH_SIZE_DEF 2048
/* I don't think that a tcp send buffer of more than 10M is usefull */
#define DRBD_SNDBUF_SIZE_MIN 0
#define DRBD_SNDBUF_SIZE_MAX (10<<20)
#define DRBD_SNDBUF_SIZE_DEF (2*65535)
#define DRBD_RCVBUF_SIZE_MIN 0
#define DRBD_RCVBUF_SIZE_MAX (10<<20)
#define DRBD_RCVBUF_SIZE_DEF (2*65535)
/* @4k PageSize -> 128kB - 512MB */
#define DRBD_MAX_BUFFERS_MIN 32
#define DRBD_MAX_BUFFERS_MAX 131072
#define DRBD_MAX_BUFFERS_DEF 2048
/* @4k PageSize -> 4kB - 512MB */
#define DRBD_UNPLUG_WATERMARK_MIN 1
#define DRBD_UNPLUG_WATERMARK_MAX 131072
#define DRBD_UNPLUG_WATERMARK_DEF (DRBD_MAX_BUFFERS_DEF/16)
/* 0 is disabled.
* 200 should be more than enough even for very short timeouts */
#define DRBD_KO_COUNT_MIN 0
#define DRBD_KO_COUNT_MAX 200
#define DRBD_KO_COUNT_DEF 0
/* } */
/* syncer { */
/* FIXME allow rate to be zero? */
#define DRBD_RATE_MIN 1
/* channel bonding 10 GbE, or other hardware */
#define DRBD_RATE_MAX (4 << 20)
#define DRBD_RATE_DEF 250 /* kb/second */
/* less than 7 would hit performance unneccessarily.
* 3833 is the largest prime that still does fit
* into 64 sectors of activity log */
#define DRBD_AL_EXTENTS_MIN 7
#define DRBD_AL_EXTENTS_MAX 3833
#define DRBD_AL_EXTENTS_DEF 127
#define DRBD_AFTER_MIN -1
#define DRBD_AFTER_MAX 255
#define DRBD_AFTER_DEF -1
/* } */
/* drbdsetup XY resize -d Z
* you are free to reduce the device size to nothing, if you want to.
* the upper limit with 64bit kernel, enough ram and flexible meta data
* is 16 TB, currently. */
/* DRBD_MAX_SECTORS */
#define DRBD_DISK_SIZE_SECT_MIN 0
#define DRBD_DISK_SIZE_SECT_MAX (16 * (2LLU << 30))
#define DRBD_DISK_SIZE_SECT_DEF 0 /* = disabled = no user size... */
#define DRBD_ON_IO_ERROR_DEF EP_PASS_ON
#define DRBD_FENCING_DEF FP_DONT_CARE
#define DRBD_AFTER_SB_0P_DEF ASB_DISCONNECT
#define DRBD_AFTER_SB_1P_DEF ASB_DISCONNECT
#define DRBD_AFTER_SB_2P_DEF ASB_DISCONNECT
#define DRBD_RR_CONFLICT_DEF ASB_DISCONNECT
#define DRBD_MAX_BIO_BVECS_MIN 0
#define DRBD_MAX_BIO_BVECS_MAX 128
#define DRBD_MAX_BIO_BVECS_DEF 0
#undef RANGE
#endif

137
include/linux/drbd_nl.h Normal file
View file

@ -0,0 +1,137 @@
/*
PAKET( name,
TYPE ( pn, pr, member )
...
)
You may never reissue one of the pn arguments
*/
#if !defined(NL_PACKET) || !defined(NL_STRING) || !defined(NL_INTEGER) || !defined(NL_BIT) || !defined(NL_INT64)
#error "The macros NL_PACKET, NL_STRING, NL_INTEGER, NL_INT64 and NL_BIT needs to be defined"
#endif
NL_PACKET(primary, 1,
NL_BIT( 1, T_MAY_IGNORE, overwrite_peer)
)
NL_PACKET(secondary, 2, )
NL_PACKET(disk_conf, 3,
NL_INT64( 2, T_MAY_IGNORE, disk_size)
NL_STRING( 3, T_MANDATORY, backing_dev, 128)
NL_STRING( 4, T_MANDATORY, meta_dev, 128)
NL_INTEGER( 5, T_MANDATORY, meta_dev_idx)
NL_INTEGER( 6, T_MAY_IGNORE, on_io_error)
NL_INTEGER( 7, T_MAY_IGNORE, fencing)
NL_BIT( 37, T_MAY_IGNORE, use_bmbv)
NL_BIT( 53, T_MAY_IGNORE, no_disk_flush)
NL_BIT( 54, T_MAY_IGNORE, no_md_flush)
/* 55 max_bio_size was available in 8.2.6rc2 */
NL_INTEGER( 56, T_MAY_IGNORE, max_bio_bvecs)
NL_BIT( 57, T_MAY_IGNORE, no_disk_barrier)
NL_BIT( 58, T_MAY_IGNORE, no_disk_drain)
)
NL_PACKET(detach, 4, )
NL_PACKET(net_conf, 5,
NL_STRING( 8, T_MANDATORY, my_addr, 128)
NL_STRING( 9, T_MANDATORY, peer_addr, 128)
NL_STRING( 10, T_MAY_IGNORE, shared_secret, SHARED_SECRET_MAX)
NL_STRING( 11, T_MAY_IGNORE, cram_hmac_alg, SHARED_SECRET_MAX)
NL_STRING( 44, T_MAY_IGNORE, integrity_alg, SHARED_SECRET_MAX)
NL_INTEGER( 14, T_MAY_IGNORE, timeout)
NL_INTEGER( 15, T_MANDATORY, wire_protocol)
NL_INTEGER( 16, T_MAY_IGNORE, try_connect_int)
NL_INTEGER( 17, T_MAY_IGNORE, ping_int)
NL_INTEGER( 18, T_MAY_IGNORE, max_epoch_size)
NL_INTEGER( 19, T_MAY_IGNORE, max_buffers)
NL_INTEGER( 20, T_MAY_IGNORE, unplug_watermark)
NL_INTEGER( 21, T_MAY_IGNORE, sndbuf_size)
NL_INTEGER( 22, T_MAY_IGNORE, ko_count)
NL_INTEGER( 24, T_MAY_IGNORE, after_sb_0p)
NL_INTEGER( 25, T_MAY_IGNORE, after_sb_1p)
NL_INTEGER( 26, T_MAY_IGNORE, after_sb_2p)
NL_INTEGER( 39, T_MAY_IGNORE, rr_conflict)
NL_INTEGER( 40, T_MAY_IGNORE, ping_timeo)
NL_INTEGER( 67, T_MAY_IGNORE, rcvbuf_size)
/* 59 addr_family was available in GIT, never released */
NL_BIT( 60, T_MANDATORY, mind_af)
NL_BIT( 27, T_MAY_IGNORE, want_lose)
NL_BIT( 28, T_MAY_IGNORE, two_primaries)
NL_BIT( 41, T_MAY_IGNORE, always_asbp)
NL_BIT( 61, T_MAY_IGNORE, no_cork)
NL_BIT( 62, T_MANDATORY, auto_sndbuf_size)
)
NL_PACKET(disconnect, 6, )
NL_PACKET(resize, 7,
NL_INT64( 29, T_MAY_IGNORE, resize_size)
)
NL_PACKET(syncer_conf, 8,
NL_INTEGER( 30, T_MAY_IGNORE, rate)
NL_INTEGER( 31, T_MAY_IGNORE, after)
NL_INTEGER( 32, T_MAY_IGNORE, al_extents)
NL_STRING( 52, T_MAY_IGNORE, verify_alg, SHARED_SECRET_MAX)
NL_STRING( 51, T_MAY_IGNORE, cpu_mask, 32)
NL_STRING( 64, T_MAY_IGNORE, csums_alg, SHARED_SECRET_MAX)
NL_BIT( 65, T_MAY_IGNORE, use_rle)
)
NL_PACKET(invalidate, 9, )
NL_PACKET(invalidate_peer, 10, )
NL_PACKET(pause_sync, 11, )
NL_PACKET(resume_sync, 12, )
NL_PACKET(suspend_io, 13, )
NL_PACKET(resume_io, 14, )
NL_PACKET(outdate, 15, )
NL_PACKET(get_config, 16, )
NL_PACKET(get_state, 17,
NL_INTEGER( 33, T_MAY_IGNORE, state_i)
)
NL_PACKET(get_uuids, 18,
NL_STRING( 34, T_MAY_IGNORE, uuids, (UI_SIZE*sizeof(__u64)))
NL_INTEGER( 35, T_MAY_IGNORE, uuids_flags)
)
NL_PACKET(get_timeout_flag, 19,
NL_BIT( 36, T_MAY_IGNORE, use_degraded)
)
NL_PACKET(call_helper, 20,
NL_STRING( 38, T_MAY_IGNORE, helper, 32)
)
/* Tag nr 42 already allocated in drbd-8.1 development. */
NL_PACKET(sync_progress, 23,
NL_INTEGER( 43, T_MAY_IGNORE, sync_progress)
)
NL_PACKET(dump_ee, 24,
NL_STRING( 45, T_MAY_IGNORE, dump_ee_reason, 32)
NL_STRING( 46, T_MAY_IGNORE, seen_digest, SHARED_SECRET_MAX)
NL_STRING( 47, T_MAY_IGNORE, calc_digest, SHARED_SECRET_MAX)
NL_INT64( 48, T_MAY_IGNORE, ee_sector)
NL_INT64( 49, T_MAY_IGNORE, ee_block_id)
NL_STRING( 50, T_MAY_IGNORE, ee_data, 32 << 10)
)
NL_PACKET(start_ov, 25,
NL_INT64( 66, T_MAY_IGNORE, start_sector)
)
NL_PACKET(new_c_uuid, 26,
NL_BIT( 63, T_MANDATORY, clear_bm)
)
#undef NL_PACKET
#undef NL_INTEGER
#undef NL_INT64
#undef NL_BIT
#undef NL_STRING

83
include/linux/drbd_tag_magic.h Normal file
View file

@ -0,0 +1,83 @@
#ifndef DRBD_TAG_MAGIC_H
#define DRBD_TAG_MAGIC_H
#define TT_END 0
#define TT_REMOVED 0xE000
/* declare packet_type enums */
enum packet_types {
#define NL_PACKET(name, number, fields) P_ ## name = number,
#define NL_INTEGER(pn, pr, member)
#define NL_INT64(pn, pr, member)
#define NL_BIT(pn, pr, member)
#define NL_STRING(pn, pr, member, len)
#include "drbd_nl.h"
P_nl_after_last_packet,
};
/* These struct are used to deduce the size of the tag lists: */
#define NL_PACKET(name, number, fields) \
struct name ## _tag_len_struct { fields };
#define NL_INTEGER(pn, pr, member) \
int member; int tag_and_len ## member;
#define NL_INT64(pn, pr, member) \
__u64 member; int tag_and_len ## member;
#define NL_BIT(pn, pr, member) \
unsigned char member:1; int tag_and_len ## member;
#define NL_STRING(pn, pr, member, len) \
unsigned char member[len]; int member ## _len; \
int tag_and_len ## member;
#include "linux/drbd_nl.h"
/* declate tag-list-sizes */
static const int tag_list_sizes[] = {
#define NL_PACKET(name, number, fields) 2 fields ,
#define NL_INTEGER(pn, pr, member) + 4 + 4
#define NL_INT64(pn, pr, member) + 4 + 8
#define NL_BIT(pn, pr, member) + 4 + 1
#define NL_STRING(pn, pr, member, len) + 4 + (len)
#include "drbd_nl.h"
};
/* The two highest bits are used for the tag type */
#define TT_MASK 0xC000
#define TT_INTEGER 0x0000
#define TT_INT64 0x4000
#define TT_BIT 0x8000
#define TT_STRING 0xC000
/* The next bit indicates if processing of the tag is mandatory */
#define T_MANDATORY 0x2000
#define T_MAY_IGNORE 0x0000
#define TN_MASK 0x1fff
/* The remaining 13 bits are used to enumerate the tags */
#define tag_type(T) ((T) & TT_MASK)
#define tag_number(T) ((T) & TN_MASK)
/* declare tag enums */
#define NL_PACKET(name, number, fields) fields
enum drbd_tags {
#define NL_INTEGER(pn, pr, member) T_ ## member = pn | TT_INTEGER | pr ,
#define NL_INT64(pn, pr, member) T_ ## member = pn | TT_INT64 | pr ,
#define NL_BIT(pn, pr, member) T_ ## member = pn | TT_BIT | pr ,
#define NL_STRING(pn, pr, member, len) T_ ## member = pn | TT_STRING | pr ,
#include "drbd_nl.h"
};
struct tag {
const char *name;
int type_n_flags;
int max_len;
};
/* declare tag names */
#define NL_PACKET(name, number, fields) fields
static const struct tag tag_descriptions[] = {
#define NL_INTEGER(pn, pr, member) [ pn ] = { #member, TT_INTEGER | pr, sizeof(int) },
#define NL_INT64(pn, pr, member) [ pn ] = { #member, TT_INT64 | pr, sizeof(__u64) },
#define NL_BIT(pn, pr, member) [ pn ] = { #member, TT_BIT | pr, sizeof(int) },
#define NL_STRING(pn, pr, member, len) [ pn ] = { #member, TT_STRING | pr, (len) },
#include "drbd_nl.h"
};
#endif

2
include/linux/fs.h
View file

@ -129,7 +129,6 @@ struct inodes_stat_t {
* WRITE_SYNC Like WRITE_SYNC_PLUG, but also unplugs the device
* immediately after submission. The write equivalent
* of READ_SYNC.
* WRITE_ODIRECT Special case write for O_DIRECT only.
* SWRITE_SYNC
* SWRITE_SYNC_PLUG Like WRITE_SYNC/WRITE_SYNC_PLUG, but locks the buffer.
* See SWRITE.
@ -151,7 +150,6 @@ struct inodes_stat_t {
#define READ_META (READ | (1 << BIO_RW_META))
#define WRITE_SYNC_PLUG (WRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_NOIDLE))
#define WRITE_SYNC (WRITE_SYNC_PLUG | (1 << BIO_RW_UNPLUG))
#define WRITE_ODIRECT (WRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG))
#define SWRITE_SYNC_PLUG \
(SWRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_NOIDLE))
#define SWRITE_SYNC (SWRITE_SYNC_PLUG | (1 << BIO_RW_UNPLUG))

5
include/linux/iocontext.h
View file

@ -40,16 +40,11 @@ struct cfq_io_context {
struct io_context *ioc;
unsigned long last_end_request;
sector_t last_request_pos;
unsigned long ttime_total;
unsigned long ttime_samples;
unsigned long ttime_mean;
unsigned int seek_samples;
u64 seek_total;
sector_t seek_mean;
struct list_head queue_list;
struct hlist_node cic_list;

294
include/linux/lru_cache.h Normal file
View file

@ -0,0 +1,294 @@
/*
lru_cache.c
This file is part of DRBD by Philipp Reisner and Lars Ellenberg.
Copyright (C) 2003-2008, LINBIT Information Technologies GmbH.
Copyright (C) 2003-2008, Philipp Reisner <philipp.reisner@linbit.com>.
Copyright (C) 2003-2008, Lars Ellenberg <lars.ellenberg@linbit.com>.
drbd is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.
drbd is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with drbd; see the file COPYING. If not, write to
the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#ifndef LRU_CACHE_H
#define LRU_CACHE_H
#include <linux/list.h>
#include <linux/slab.h>
#include <linux/bitops.h>
#include <linux/string.h> /* for memset */
#include <linux/seq_file.h>
/*
This header file (and its .c file; kernel-doc of functions see there)
define a helper framework to easily keep track of index:label associations,
and changes to an "active set" of objects, as well as pending transactions,
to persistently record those changes.
We use an LRU policy if it is necessary to "cool down" a region currently in
the active set before we can "heat" a previously unused region.
Because of this later property, it is called "lru_cache".
As it actually Tracks Objects in an Active SeT, we could also call it
toast (incidentally that is what may happen to the data on the
backend storage uppon next resync, if we don't get it right).
What for?
We replicate IO (more or less synchronously) to local and remote disk.
For crash recovery after replication node failure,
we need to resync all regions that have been target of in-flight WRITE IO
(in use, or "hot", regions), as we don't know wether or not those WRITEs have
made it to stable storage.
To avoid a "full resync", we need to persistently track these regions.
This is known as "write intent log", and can be implemented as on-disk
(coarse or fine grained) bitmap, or other meta data.
To avoid the overhead of frequent extra writes to this meta data area,
usually the condition is softened to regions that _may_ have been target of
in-flight WRITE IO, e.g. by only lazily clearing the on-disk write-intent
bitmap, trading frequency of meta data transactions against amount of
(possibly unneccessary) resync traffic.
If we set a hard limit on the area that may be "hot" at any given time, we
limit the amount of resync traffic needed for crash recovery.
For recovery after replication link failure,
we need to resync all blocks that have been changed on the other replica
in the mean time, or, if both replica have been changed independently [*],
all blocks that have been changed on either replica in the mean time.
[*] usually as a result of a cluster split-brain and insufficient protection.
but there are valid use cases to do this on purpose.
Tracking those blocks can be implemented as "dirty bitmap".
Having it fine-grained reduces the amount of resync traffic.
It should also be persistent, to allow for reboots (or crashes)
while the replication link is down.
There are various possible implementations for persistently storing
write intent log information, three of which are mentioned here.
"Chunk dirtying"
The on-disk "dirty bitmap" may be re-used as "write-intent" bitmap as well.
To reduce the frequency of bitmap updates for write-intent log purposes,
one could dirty "chunks" (of some size) at a time of the (fine grained)
on-disk bitmap, while keeping the in-memory "dirty" bitmap as clean as
possible, flushing it to disk again when a previously "hot" (and on-disk
dirtied as full chunk) area "cools down" again (no IO in flight anymore,
and none expected in the near future either).
"Explicit (coarse) write intent bitmap"
An other implementation could chose a (probably coarse) explicit bitmap,
for write-intent log purposes, additionally to the fine grained dirty bitmap.
"Activity log"
Yet an other implementation may keep track of the hot regions, by starting
with an empty set, and writing down a journal of region numbers that have
become "hot", or have "cooled down" again.
To be able to use a ring buffer for this journal of changes to the active
set, we not only record the actual changes to that set, but also record the
not changing members of the set in a round robin fashion. To do so, we use a
fixed (but configurable) number of slots which we can identify by index, and
associate region numbers (labels) with these indices.
For each transaction recording a change to the active set, we record the
change itself (index: -old_label, +new_label), and which index is associated
with which label (index: current_label) within a certain sliding window that
is moved further over the available indices with each such transaction.
Thus, for crash recovery, if the ringbuffer is sufficiently large, we can
accurately reconstruct the active set.
Sufficiently large depends only on maximum number of active objects, and the
size of the sliding window recording "index: current_label" associations within
each transaction.
This is what we call the "activity log".
Currently we need one activity log transaction per single label change, which
does not give much benefit over the "dirty chunks of bitmap" approach, other
than potentially less seeks.
We plan to change the transaction format to support multiple changes per
transaction, which then would reduce several (disjoint, "random") updates to
the bitmap into one transaction to the activity log ring buffer.
*/
/* this defines an element in a tracked set
* .colision is for hash table lookup.
* When we process a new IO request, we know its sector, thus can deduce the
* region number (label) easily. To do the label -> object lookup without a
* full list walk, we use a simple hash table.
*
* .list is on one of three lists:
* in_use: currently in use (refcnt > 0, lc_number != LC_FREE)
* lru: unused but ready to be reused or recycled
* (ts_refcnt == 0, lc_number != LC_FREE),
* free: unused but ready to be recycled
* (ts_refcnt == 0, lc_number == LC_FREE),
*
* an element is said to be "in the active set",
* if either on "in_use" or "lru", i.e. lc_number != LC_FREE.
*
* DRBD currently (May 2009) only uses 61 elements on the resync lru_cache
* (total memory usage 2 pages), and up to 3833 elements on the act_log
* lru_cache, totalling ~215 kB for 64bit architechture, ~53 pages.
*
* We usually do not actually free these objects again, but only "recycle"
* them, as the change "index: -old_label, +LC_FREE" would need a transaction
* as well. Which also means that using a kmem_cache to allocate the objects
* from wastes some resources.
* But it avoids high order page allocations in kmalloc.
*/
struct lc_element {
struct hlist_node colision;
struct list_head list; /* LRU list or free list */
unsigned refcnt;
/* back "pointer" into ts_cache->element[index],
* for paranoia, and for "ts_element_to_index" */
unsigned lc_index;
/* if we want to track a larger set of objects,
* it needs to become arch independend u64 */
unsigned lc_number;
/* special label when on free list */
#define LC_FREE (~0U)
};
struct lru_cache {
/* the least recently used item is kept at lru->prev */
struct list_head lru;
struct list_head free;
struct list_head in_use;
/* the pre-created kmem cache to allocate the objects from */
struct kmem_cache *lc_cache;
/* size of tracked objects, used to memset(,0,) them in lc_reset */
size_t element_size;
/* offset of struct lc_element member in the tracked object */
size_t element_off;
/* number of elements (indices) */
unsigned int nr_elements;
/* Arbitrary limit on maximum tracked objects. Practical limit is much
* lower due to allocation failures, probably. For typical use cases,
* nr_elements should be a few thousand at most.
* This also limits the maximum value of ts_element.ts_index, allowing the
* 8 high bits of .ts_index to be overloaded with flags in the future. */
#define LC_MAX_ACTIVE (1<<24)
/* statistics */
unsigned used; /* number of lelements currently on in_use list */
unsigned long hits, misses, starving, dirty, changed;
/* see below: flag-bits for lru_cache */
unsigned long flags;
/* when changing the label of an index element */
unsigned int new_number;
/* for paranoia when changing the label of an index element */
struct lc_element *changing_element;
void *lc_private;
const char *name;
/* nr_elements there */
struct hlist_head *lc_slot;
struct lc_element **lc_element;
};
/* flag-bits for lru_cache */
enum {
/* debugging aid, to catch concurrent access early.
* user needs to guarantee exclusive access by proper locking! */
__LC_PARANOIA,
/* if we need to change the set, but currently there is a changing
* transaction pending, we are "dirty", and must deferr further
* changing requests */
__LC_DIRTY,
/* if we need to change the set, but currently there is no free nor
* unused element available, we are "starving", and must not give out
* further references, to guarantee that eventually some refcnt will
* drop to zero and we will be able to make progress again, changing
* the set, writing the transaction.
* if the statistics say we are frequently starving,
* nr_elements is too small. */
__LC_STARVING,
};
#define LC_PARANOIA (1<<__LC_PARANOIA)
#define LC_DIRTY (1<<__LC_DIRTY)
#define LC_STARVING (1<<__LC_STARVING)
extern struct lru_cache *lc_create(const char *name, struct kmem_cache *cache,
unsigned e_count, size_t e_size, size_t e_off);
extern void lc_reset(struct lru_cache *lc);
extern void lc_destroy(struct lru_cache *lc);
extern void lc_set(struct lru_cache *lc, unsigned int enr, int index);
extern void lc_del(struct lru_cache *lc, struct lc_element *element);
extern struct lc_element *lc_try_get(struct lru_cache *lc, unsigned int enr);
extern struct lc_element *lc_find(struct lru_cache *lc, unsigned int enr);
extern struct lc_element *lc_get(struct lru_cache *lc, unsigned int enr);
extern unsigned int lc_put(struct lru_cache *lc, struct lc_element *e);
extern void lc_changed(struct lru_cache *lc, struct lc_element *e);
struct seq_file;
extern size_t lc_seq_printf_stats(struct seq_file *seq, struct lru_cache *lc);
extern void lc_seq_dump_details(struct seq_file *seq, struct lru_cache *lc, char *utext,
void (*detail) (struct seq_file *, struct lc_element *));
/**
* lc_try_lock - can be used to stop lc_get() from changing the tracked set
* @lc: the lru cache to operate on
*
* Note that the reference counts and order on the active and lru lists may
* still change. Returns true if we aquired the lock.
*/
static inline int lc_try_lock(struct lru_cache *lc)
{
return !test_and_set_bit(__LC_DIRTY, &lc->flags);
}
/**
* lc_unlock - unlock @lc, allow lc_get() to change the set again
* @lc: the lru cache to operate on
*/
static inline void lc_unlock(struct lru_cache *lc)
{
clear_bit(__LC_DIRTY, &lc->flags);
smp_mb__after_clear_bit();
}
static inline int lc_is_used(struct lru_cache *lc, unsigned int enr)
{
struct lc_element *e = lc_find(lc, enr);
return e && e->refcnt;
}
#define lc_entry(ptr, type, member) \
container_of(ptr, type, member)
extern struct lc_element *lc_element_by_index(struct lru_cache *lc, unsigned i);
extern unsigned int lc_index_of(struct lru_cache *lc, struct lc_element *e);
#endif

3
lib/Kconfig
View file

@ -200,4 +200,7 @@ config NLATTR
config GENERIC_ATOMIC64
bool
config LRU_CACHE
tristate
endmenu

2
lib/Makefile
View file

@ -91,6 +91,8 @@ obj-$(CONFIG_DYNAMIC_DEBUG) += dynamic_debug.o
obj-$(CONFIG_NLATTR) += nlattr.o
obj-$(CONFIG_LRU_CACHE) += lru_cache.o
obj-$(CONFIG_DMA_API_DEBUG) += dma-debug.o
obj-$(CONFIG_GENERIC_CSUM) += checksum.o

560
lib/lru_cache.c Normal file
View file

@ -0,0 +1,560 @@
/*
lru_cache.c
This file is part of DRBD by Philipp Reisner and Lars Ellenberg.
Copyright (C) 2003-2008, LINBIT Information Technologies GmbH.
Copyright (C) 2003-2008, Philipp Reisner <philipp.reisner@linbit.com>.
Copyright (C) 2003-2008, Lars Ellenberg <lars.ellenberg@linbit.com>.
drbd is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.
drbd is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with drbd; see the file COPYING. If not, write to
the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#include <linux/module.h>
#include <linux/bitops.h>
#include <linux/slab.h>
#include <linux/string.h> /* for memset */
#include <linux/seq_file.h> /* for seq_printf */
#include <linux/lru_cache.h>
MODULE_AUTHOR("Philipp Reisner <phil@linbit.com>, "
"Lars Ellenberg <lars@linbit.com>");
MODULE_DESCRIPTION("lru_cache - Track sets of hot objects");
MODULE_LICENSE("GPL");
/* this is developers aid only.
* it catches concurrent access (lack of locking on the users part) */
#define PARANOIA_ENTRY() do { \
BUG_ON(!lc); \
BUG_ON(!lc->nr_elements); \
BUG_ON(test_and_set_bit(__LC_PARANOIA, &lc->flags)); \
} while (0)
#define RETURN(x...) do { \
clear_bit(__LC_PARANOIA, &lc->flags); \
smp_mb__after_clear_bit(); return x ; } while (0)
/* BUG() if e is not one of the elements tracked by lc */
#define PARANOIA_LC_ELEMENT(lc, e) do { \
struct lru_cache *lc_ = (lc); \
struct lc_element *e_ = (e); \
unsigned i = e_->lc_index; \
BUG_ON(i >= lc_->nr_elements); \
BUG_ON(lc_->lc_element[i] != e_); } while (0)
/**
* lc_create - prepares to track objects in an active set
* @name: descriptive name only used in lc_seq_printf_stats and lc_seq_dump_details
* @e_count: number of elements allowed to be active simultaneously
* @e_size: size of the tracked objects
* @e_off: offset to the &struct lc_element member in a tracked object
*
* Returns a pointer to a newly initialized struct lru_cache on success,
* or NULL on (allocation) failure.
*/
struct lru_cache *lc_create(const char *name, struct kmem_cache *cache,
unsigned e_count, size_t e_size, size_t e_off)
{
struct hlist_head *slot = NULL;
struct lc_element **element = NULL;
struct lru_cache *lc;
struct lc_element *e;
unsigned cache_obj_size = kmem_cache_size(cache);
unsigned i;
WARN_ON(cache_obj_size < e_size);
if (cache_obj_size < e_size)
return NULL;
/* e_count too big; would probably fail the allocation below anyways.
* for typical use cases, e_count should be few thousand at most. */
if (e_count > LC_MAX_ACTIVE)
return NULL;
slot = kzalloc(e_count * sizeof(struct hlist_head*), GFP_KERNEL);
if (!slot)
goto out_fail;
element = kzalloc(e_count * sizeof(struct lc_element *), GFP_KERNEL);
if (!element)
goto out_fail;
lc = kzalloc(sizeof(*lc), GFP_KERNEL);
if (!lc)
goto out_fail;
INIT_LIST_HEAD(&lc->in_use);
INIT_LIST_HEAD(&lc->lru);
INIT_LIST_HEAD(&lc->free);
lc->name = name;
lc->element_size = e_size;
lc->element_off = e_off;
lc->nr_elements = e_count;
lc->new_number = LC_FREE;
lc->lc_cache = cache;
lc->lc_element = element;
lc->lc_slot = slot;
/* preallocate all objects */
for (i = 0; i < e_count; i++) {
void *p = kmem_cache_alloc(cache, GFP_KERNEL);
if (!p)
break;
memset(p, 0, lc->element_size);
e = p + e_off;
e->lc_index = i;
e->lc_number = LC_FREE;
list_add(&e->list, &lc->free);
element[i] = e;
}
if (i == e_count)
return lc;
/* else: could not allocate all elements, give up */
for (i--; i; i--) {
void *p = element[i];
kmem_cache_free(cache, p - e_off);
}
kfree(lc);
out_fail:
kfree(element);
kfree(slot);
return NULL;
}
void lc_free_by_index(struct lru_cache *lc, unsigned i)
{
void *p = lc->lc_element[i];
WARN_ON(!p);
if (p) {
p -= lc->element_off;
kmem_cache_free(lc->lc_cache, p);
}
}
/**
* lc_destroy - frees memory allocated by lc_create()
* @lc: the lru cache to destroy
*/
void lc_destroy(struct lru_cache *lc)
{
unsigned i;
if (!lc)
return;
for (i = 0; i < lc->nr_elements; i++)
lc_free_by_index(lc, i);
kfree(lc->lc_element);
kfree(lc->lc_slot);
kfree(lc);
}
/**
* lc_reset - does a full reset for @lc and the hash table slots.
* @lc: the lru cache to operate on
*
* It is roughly the equivalent of re-allocating a fresh lru_cache object,
* basically a short cut to lc_destroy(lc); lc = lc_create(...);
*/
void lc_reset(struct lru_cache *lc)
{
unsigned i;
INIT_LIST_HEAD(&lc->in_use);
INIT_LIST_HEAD(&lc->lru);
INIT_LIST_HEAD(&lc->free);
lc->used = 0;
lc->hits = 0;
lc->misses = 0;
lc->starving = 0;
lc->dirty = 0;
lc->changed = 0;
lc->flags = 0;
lc->changing_element = NULL;
lc->new_number = LC_FREE;
memset(lc->lc_slot, 0, sizeof(struct hlist_head) * lc->nr_elements);
for (i = 0; i < lc->nr_elements; i++) {
struct lc_element *e = lc->lc_element[i];
void *p = e;
p -= lc->element_off;
memset(p, 0, lc->element_size);
/* re-init it */
e->lc_index = i;
e->lc_number = LC_FREE;
list_add(&e->list, &lc->free);
}
}
/**
* lc_seq_printf_stats - print stats about @lc into @seq
* @seq: the seq_file to print into
* @lc: the lru cache to print statistics of
*/
size_t lc_seq_printf_stats(struct seq_file *seq, struct lru_cache *lc)
{
/* NOTE:
* total calls to lc_get are
* (starving + hits + misses)
* misses include "dirty" count (update from an other thread in
* progress) and "changed", when this in fact lead to an successful
* update of the cache.
*/
return seq_printf(seq, "\t%s: used:%u/%u "
"hits:%lu misses:%lu starving:%lu dirty:%lu changed:%lu\n",
lc->name, lc->used, lc->nr_elements,
lc->hits, lc->misses, lc->starving, lc->dirty, lc->changed);
}
static struct hlist_head *lc_hash_slot(struct lru_cache *lc, unsigned int enr)
{
return lc->lc_slot + (enr % lc->nr_elements);
}
/**
* lc_find - find element by label, if present in the hash table
* @lc: The lru_cache object
* @enr: element number
*
* Returns the pointer to an element, if the element with the requested
* "label" or element number is present in the hash table,
* or NULL if not found. Does not change the refcnt.
*/
struct lc_element *lc_find(struct lru_cache *lc, unsigned int enr)
{
struct hlist_node *n;
struct lc_element *e;
BUG_ON(!lc);
BUG_ON(!lc->nr_elements);
hlist_for_each_entry(e, n, lc_hash_slot(lc, enr), colision) {
if (e->lc_number == enr)
return e;
}
return NULL;
}
/* returned element will be "recycled" immediately */
static struct lc_element *lc_evict(struct lru_cache *lc)
{
struct list_head *n;
struct lc_element *e;
if (list_empty(&lc->lru))
return NULL;
n = lc->lru.prev;
e = list_entry(n, struct lc_element, list);
PARANOIA_LC_ELEMENT(lc, e);
list_del(&e->list);
hlist_del(&e->colision);
return e;
}
/**
* lc_del - removes an element from the cache
* @lc: The lru_cache object
* @e: The element to remove
*
* @e must be unused (refcnt == 0). Moves @e from "lru" to "free" list,
* sets @e->enr to %LC_FREE.
*/
void lc_del(struct lru_cache *lc, struct lc_element *e)
{
PARANOIA_ENTRY();
PARANOIA_LC_ELEMENT(lc, e);
BUG_ON(e->refcnt);
e->lc_number = LC_FREE;
hlist_del_init(&e->colision);
list_move(&e->list, &lc->free);
RETURN();
}
static struct lc_element *lc_get_unused_element(struct lru_cache *lc)
{
struct list_head *n;
if (list_empty(&lc->free))
return lc_evict(lc);
n = lc->free.next;
list_del(n);
return list_entry(n, struct lc_element, list);
}
static int lc_unused_element_available(struct lru_cache *lc)
{
if (!list_empty(&lc->free))
return 1; /* something on the free list */
if (!list_empty(&lc->lru))
return 1; /* something to evict */
return 0;
}
/**
* lc_get - get element by label, maybe change the active set
* @lc: the lru cache to operate on
* @enr: the label to look up
*
* Finds an element in the cache, increases its usage count,
* "touches" and returns it.
*
* In case the requested number is not present, it needs to be added to the
* cache. Therefore it is possible that an other element becomes evicted from
* the cache. In either case, the user is notified so he is able to e.g. keep
* a persistent log of the cache changes, and therefore the objects in use.
*
* Return values:
* NULL
* The cache was marked %LC_STARVING,
* or the requested label was not in the active set
* and a changing transaction is still pending (@lc was marked %LC_DIRTY).
* Or no unused or free element could be recycled (@lc will be marked as
* %LC_STARVING, blocking further lc_get() operations).
*
* pointer to the element with the REQUESTED element number.
* In this case, it can be used right away
*
* pointer to an UNUSED element with some different element number,
* where that different number may also be %LC_FREE.
*
* In this case, the cache is marked %LC_DIRTY (blocking further changes),
* and the returned element pointer is removed from the lru list and
* hash collision chains. The user now should do whatever housekeeping
* is necessary.
* Then he must call lc_changed(lc,element_pointer), to finish
* the change.
*
* NOTE: The user needs to check the lc_number on EACH use, so he recognizes
* any cache set change.
*/
struct lc_element *lc_get(struct lru_cache *lc, unsigned int enr)
{
struct lc_element *e;
PARANOIA_ENTRY();
if (lc->flags & LC_STARVING) {
++lc->starving;
RETURN(NULL);
}
e = lc_find(lc, enr);
if (e) {
++lc->hits;
if (e->refcnt++ == 0)
lc->used++;
list_move(&e->list, &lc->in_use); /* Not evictable... */
RETURN(e);
}
++lc->misses;
/* In case there is nothing available and we can not kick out
* the LRU element, we have to wait ...
*/
if (!lc_unused_element_available(lc)) {
__set_bit(__LC_STARVING, &lc->flags);
RETURN(NULL);
}
/* it was not present in the active set.
* we are going to recycle an unused (or even "free") element.
* user may need to commit a transaction to record that change.
* we serialize on flags & TF_DIRTY */
if (test_and_set_bit(__LC_DIRTY, &lc->flags)) {
++lc->dirty;
RETURN(NULL);
}
e = lc_get_unused_element(lc);
BUG_ON(!e);
clear_bit(__LC_STARVING, &lc->flags);
BUG_ON(++e->refcnt != 1);
lc->used++;
lc->changing_element = e;
lc->new_number = enr;
RETURN(e);
}
/* similar to lc_get,
* but only gets a new reference on an existing element.
* you either get the requested element, or NULL.
* will be consolidated into one function.
*/
struct lc_element *lc_try_get(struct lru_cache *lc, unsigned int enr)
{
struct lc_element *e;
PARANOIA_ENTRY();
if (lc->flags & LC_STARVING) {
++lc->starving;
RETURN(NULL);
}
e = lc_find(lc, enr);
if (e) {
++lc->hits;
if (e->refcnt++ == 0)
lc->used++;
list_move(&e->list, &lc->in_use); /* Not evictable... */
}
RETURN(e);
}
/**
* lc_changed - tell @lc that the change has been recorded
* @lc: the lru cache to operate on
* @e: the element pending label change
*/
void lc_changed(struct lru_cache *lc, struct lc_element *e)
{
PARANOIA_ENTRY();
BUG_ON(e != lc->changing_element);
PARANOIA_LC_ELEMENT(lc, e);
++lc->changed;
e->lc_number = lc->new_number;
list_add(&e->list, &lc->in_use);
hlist_add_head(&e->colision, lc_hash_slot(lc, lc->new_number));
lc->changing_element = NULL;
lc->new_number = LC_FREE;
clear_bit(__LC_DIRTY, &lc->flags);
smp_mb__after_clear_bit();
RETURN();
}
/**
* lc_put - give up refcnt of @e
* @lc: the lru cache to operate on
* @e: the element to put
*
* If refcnt reaches zero, the element is moved to the lru list,
* and a %LC_STARVING (if set) is cleared.
* Returns the new (post-decrement) refcnt.
*/
unsigned int lc_put(struct lru_cache *lc, struct lc_element *e)
{
PARANOIA_ENTRY();
PARANOIA_LC_ELEMENT(lc, e);
BUG_ON(e->refcnt == 0);
BUG_ON(e == lc->changing_element);
if (--e->refcnt == 0) {
/* move it to the front of LRU. */
list_move(&e->list, &lc->lru);
lc->used--;
clear_bit(__LC_STARVING, &lc->flags);
smp_mb__after_clear_bit();
}
RETURN(e->refcnt);
}
/**
* lc_element_by_index
* @lc: the lru cache to operate on
* @i: the index of the element to return
*/
struct lc_element *lc_element_by_index(struct lru_cache *lc, unsigned i)
{
BUG_ON(i >= lc->nr_elements);
BUG_ON(lc->lc_element[i] == NULL);
BUG_ON(lc->lc_element[i]->lc_index != i);
return lc->lc_element[i];
}
/**
* lc_index_of
* @lc: the lru cache to operate on
* @e: the element to query for its index position in lc->element
*/
unsigned int lc_index_of(struct lru_cache *lc, struct lc_element *e)
{
PARANOIA_LC_ELEMENT(lc, e);
return e->lc_index;
}
/**
* lc_set - associate index with label
* @lc: the lru cache to operate on
* @enr: the label to set
* @index: the element index to associate label with.
*
* Used to initialize the active set to some previously recorded state.
*/
void lc_set(struct lru_cache *lc, unsigned int enr, int index)
{
struct lc_element *e;
if (index < 0 || index >= lc->nr_elements)
return;
e = lc_element_by_index(lc, index);
e->lc_number = enr;
hlist_del_init(&e->colision);
hlist_add_head(&e->colision, lc_hash_slot(lc, enr));
list_move(&e->list, e->refcnt ? &lc->in_use : &lc->lru);
}
/**
* lc_dump - Dump a complete LRU cache to seq in textual form.
* @lc: the lru cache to operate on
* @seq: the &struct seq_file pointer to seq_printf into
* @utext: user supplied "heading" or other info
* @detail: function pointer the user may provide to dump further details
* of the object the lc_element is embedded in.
*/
void lc_seq_dump_details(struct seq_file *seq, struct lru_cache *lc, char *utext,
void (*detail) (struct seq_file *, struct lc_element *))
{
unsigned int nr_elements = lc->nr_elements;
struct lc_element *e;
int i;
seq_printf(seq, "\tnn: lc_number refcnt %s\n ", utext);
for (i = 0; i < nr_elements; i++) {
e = lc_element_by_index(lc, i);
if (e->lc_number == LC_FREE) {
seq_printf(seq, "\t%2d: FREE\n", i);
} else {
seq_printf(seq, "\t%2d: %4u %4u ", i,
e->lc_number, e->refcnt);
detail(seq, e);
}
}
}
EXPORT_SYMBOL(lc_create);
EXPORT_SYMBOL(lc_reset);
EXPORT_SYMBOL(lc_destroy);
EXPORT_SYMBOL(lc_set);
EXPORT_SYMBOL(lc_del);
EXPORT_SYMBOL(lc_try_get);
EXPORT_SYMBOL(lc_find);
EXPORT_SYMBOL(lc_get);
EXPORT_SYMBOL(lc_put);
EXPORT_SYMBOL(lc_changed);
EXPORT_SYMBOL(lc_element_by_index);
EXPORT_SYMBOL(lc_index_of);
EXPORT_SYMBOL(lc_seq_printf_stats);
EXPORT_SYMBOL(lc_seq_dump_details);