提交 59131d8e 编写于 作者: P Philipp Reisner

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

此差异已折叠。
<?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>
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
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" ]
}
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" ]
}
// 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" ]
}
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" ]
}
......@@ -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/
......
......@@ -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
......
......@@ -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
......
此差异已折叠。
......@@ -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);
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;
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;
/*
* 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]++;
......
......@@ -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;
}
......
......@@ -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
......
......@@ -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
#
# 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.
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
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
/*
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];
}
此差异已折叠。
此差异已折叠。
#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
此差异已折叠。
......@@ -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;
}
/*
......
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
此差异已折叠。
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册