[Bug 1807432] Re: /proc/diskstats does not rollup queue depth from partitions

Here is the details on a bare metal ubuntu 18.04 LTS server running an IO benchmark:
# uname -a
Linux xxx 4.15.0-39-generic #42-Ubuntu SMP Tue Oct 23 15:48:01 UTC 2018 x86_64 x86_64 x86_64 GNU/Linux

# lsb_release -rd
Description: Ubuntu 18.04.1 LTS
Release: 18.04

# cat /proc/diskstats
7 0 loop0 0 0 0 0 0 0 0 0 0 0 0
7 1 loop1 0 0 0 0 0 0 0 0 0 0 0
7 2 loop2 0 0 0 0 0 0 0 0 0 0 0
7 3 loop3 0 0 0 0 0 0 0 0 0 0 0
7 4 loop4 0 0 0 0 0 0 0 0 0 0 0
7 5 loop5 0 0 0 0 0 0 0 0 0 0 0
7 6 loop6 0 0 0 0 0 0 0 0 0 0 0
7 7 loop7 0 0 0 0 0 0 0 0 0 0 0
8 0 sda 42531 5065 2097514 177892 7213856 2831260 295763362 4616524 0 1535632 4790132
8 1 sda1 221 30 11808 632 2 0 2 0 0 436 632
8 2 sda2 42146 5033 2077442 176336 7213854 2831260 295763360 4616524 0 1535412 4788584
8 16 sdb 77529 0 39360314 52284 613197 114047 198167776 23144 0 29212 74964
8 17 sdb1 77078 0 39335602 52052 613197 114047 198167776 23144 0 29100 74732
259 0 nvme0n1 28201525398 0 488820005576 207589544 862135419 98 226957567536 127289372 0 389795644 709789780
259 11 nvme0n1p1 2417230384 0 71713692888 554246764 155623487 0 39839572992 14866796 7 116086276 414538992
259 12 nvme0n1p2 2417484200 0 71743882112 553922380 155595754 0 39832473344 14030424 8 115793704 412547176
259 13 nvme0n1p3 2415958954 0 71634470992 554243464 155462257 0 39798298112 14474168 10 115988052 413090312
259 14 nvme0n1p4 2416615620 0 71693490456 554028440 155535038 0 39816930048 13413172 5 115578348 412099184
259 5 nvme1n1 9665715778 0 286976448416 2212243248 622132262 98 165516759344 56229716 0 296178992 2019232932
259 20 nvme1n1p1 2415904567 0 71636878008 552917888 155454273 0 39796254208 14455924 5 116082548 412220948
259 21 nvme1n1p2 2415512074 0 71650757824 552297300 155569570 0 39825770240 13910420 5 115679536 412130316
259 22 nvme1n1p3 2416548713 0 71678672568 553555664 155500210 0 39808014080 14275504 3 116157680 412450228
259 23 nvme1n1p4 2416416216 0 71684681400 553144864 155607183 0 39835399168 13506844 9 115654900 412532936
253 0 dm-0 46520 0 2049706 243712 9679815 0 295763360 4748384 0 1543256 4994124
259 10 nvme2n1 9667389541 0 287031008544 2207928032 622164931 98 165525122608 56921664 0 295218964 2002099520
259 6 nvme2n1p1 2417118800 0 71696213648 552051652 155532183 0 39816199168 14594732 12 115840944 412346808
259 7 nvme2n1p2 2416691746 0 71684078312 551562408 155534110 0 39816692480 14208680 7 115539968 410287704
259 8 nvme2n1p3 2416582480 0 71718109272 552480036 155634065 0 39842280960 14504168 5 115924508 411293804
259 9 nvme2n1p4 2415651523 0 71604404864 551508236 155463547 0 39798628352 13532972 7 115275812 409783788
259 15 nvme3n1 9667640590 0 287047711752 2205542280 622265688 98 165550916400 56371312 0 295252232 2008945404
259 1 nvme3n1p1 2417190392 0 71723552872 551558532 155625698 0 39840139008 14546232 1 115786248 410727612
259 2 nvme3n1p2 2415650590 0 71604369040 550597652 155449331 0 39794989056 13932652 1 115166100 409314844
259 3 nvme3n1p3 2417003647 0 71696320488 551775976 155590921 0 39831236096 14276596 5 115725292 410703296
259 4 nvme3n1p4 2416453707 0 71695930384 551283044 155598712 0 39833230592 13534668 7 115246604 409574764
253 1 dm-1 587 0 26368 828 0 0 0 0 0 656 828

--
You received this bug notification because you are subscribed to linux
in Ubuntu.
Matching subscriptions: Bgg, Bmail, Nb
https://bugs.launchpad.net/bugs/1807432

Title:
/proc/diskstats does not rollup queue depth from partitions

Status in linux package in Ubuntu:
Incomplete

Bug description:
Tested in Ubuntu 18.04LTS and Ubuntu 18.10, with the same result. The
queue size rollup works in Centos 7 though.

root@vagrant:~# uname -a
Linux vagrant 4.18.0-12-generic #13-Ubuntu SMP Wed Nov 14 15:17:05 UTC 2018 x86_64 x86_64 x86_64 GNU/Linux

root@vagrant:~# lsb_release -rd
Description: Ubuntu 18.10
Release: 18.10

root@vagrant:~# cat /proc/diskstats
7 0 loop0 5 0 16 0 0 0 0 0 0 0 0
7 1 loop1 0 0 0 0 0 0 0 0 0 0 0
7 2 loop2 0 0 0 0 0 0 0 0 0 0 0
7 3 loop3 0 0 0 0 0 0 0 0 0 0 0
7 4 loop4 0 0 0 0 0 0 0 0 0 0 0
7 5 loop5 0 0 0 0 0 0 0 0 0 0 0
7 6 loop6 0 0 0 0 0 0 0 0 0 0 0
7 7 loop7 0 0 0 0 0 0 0 0 0 0 0
259 0 nvme0n1 813340 0 10963704 274028 4075 44 1040576 46884 0 18012 908472
259 5 nvme0n1p1 203838 0 2749463 65696 986 0 252416 11696 13 14360 218028
259 6 nvme0n1p2 202672 0 2713358 67924 1015 0 259840 11696 20 14372 220388
259 7 nvme0n1p3 202961 0 2717301 70464 1034 0 264704 11652 19 14344 226248
259 8 nvme0n1p4 203216 0 2730974 69944 1028 0 263168 11840 16 14340 224992
8 0 sda 11622 783 612090 16416 6529 9730 607624 52912 0 7964 76940
8 1 sda1 11543 783 607954 16408 4731 9730 607624 52844 0 7380 76304
253 0 dm-0 12083 0 598666 25540 16198 0 613808 137252 0 7936 162808
253 1 dm-1 186 0 8696 104 0 0 0 0 0 80 104

We expect the queue depth of 'nvme0n1' to increase when the partitions
it has increase, but this never happens.

To manage notifications about this bug go to:
https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1807432/+subscriptions