Solved: Re: NFS not responding

SCHLEGELM · ‎2012-07-23

Hello

i hope someone can explain, whats happening here on our filer (have a look at CP ty and NFS ops). This happened during the removal of a snapshot in VMware vCenter.

6 Servers are connected to the Filer via NFS ~100 VMs and all stood still for nearly 1 minute, which is really bad.

Version is 8.1GA on FAS3140 Metrocluster

> sysstat -sux 2

CPU NFS CIFS HTTP Total Net kB/s Disk kB/s Tape kB/s Cache Cache CP CP Disk OTHER FCP iSCSI FCP kB/s iSCSI kB/s

in out read write read write age hit time ty util in out in out

9% 1048 0 0 1048 2974 15409 19904 24 0 0 1 92% 0% - 55% 0 0 0 0 0 0 0

34% 598 0 0 598 2330 6283 58466 44562 0 0 1 99% 83% Hf 94% 0 0 0 0 0 0 0

25% 530 0 0 533 3497 5174 21092 16582 0 0 1 99% 100% :v 99% 3 0 0 0 0 0 0

42% 1723 0 0 1723 52082 5675 23278 16974 0 0 1 99% 18% Hn 100% 0 0 0 0 0 0 0

35% 438 0 0 441 1310 7318 68280 77686 0 0 1 96% 100% :f 89% 3 0 0 0 0 0 0

25% 824 0 0 824 2011 11035 17782 5220 0 0 1 98% 43% : 87% 0 0 0 0 0 0 0

9% 738 0 0 738 3873 14086 19720 32 0 0 1 92% 0% - 72% 0 0 0 0 0 0 0

8% 705 0 0 710 1694 15661 20524 0 0 0 1 91% 0% - 50% 5 0 0 0 0 0 0

8% 691 0 0 691 1925 15826 21270 32 0 0 1 91% 0% - 60% 0 0 0 0 0 0 0

13% 892 0 0 895 5199 14905 22720 24 0 0 1 90% 0% - 67% 3 0 0 0 0 0 0

30% 1083 0 0 1083 5625 10959 64170 38404 0 0 1 93% 57% Tf 85% 0 0 0 0 0 0 0

24% 602 0 0 602 1956 4569 22430 27258 0 0 1 99% 100% :f 100% 0 0 0 0 0 0 0

25% 463 0 0 468 1798 6305 20898 17053 0 0 1 99% 84% : 98% 5 0 0 0 0 0 0

31% 369 0 0 369 1454 4700 13074 8 0 0 1 99% 0% - 100% 0 0 0 0 0 0 0

13% 705 0 0 708 3119 13847 20014 24 0 0 5s 97% 0% - 81% 3 0 0 0 0 0 0

12% 1155 0 0 1197 4705 17936 25348 24 0 0 1s 93% 0% - 66% 42 0 0 0 0 0 0

36% 833 0 0 963 3822 7066 58388 49152 0 0 1 98% 84% Hf 94% 130 0 0 0 0 0 0

18% 1402 0 0 1406 6026 10577 18860 15904 0 0 1 95% 69% : 82% 4 0 0 0 0 0 0

17% 1256 0 0 1256 4175 15981 23592 32 0 0 1 94% 0% - 70% 0 0 0 0 0 0 0

24% 565 0 0 568 1983 8432 45066 41308 0 0 1 92% 81% Hs 90% 3 0 0 0 0 0 0

CPU NFS CIFS HTTP Total Net kB/s Disk kB/s Tape kB/s Cache Cache CP CP Disk OTHER FCP iSCSI FCP kB/s iSCSI kB/s

in out read write read write age hit time ty util in out in out

11% 1074 0 0 1074 5300 17035 22170 24 0 0 1 91% 100% :s 61% 0 0 0 0 0 0 0

15% 1358 0 0 1358 4361 18970 25256 32 0 0 1 92% 100% :s 54% 0 0 0 0 0 0 0

11% 1222 0 0 1225 2892 18328 24654 0 0 0 1 92% 100% :s 54% 3 0 0 0 0 0 0

10% 897 0 0 897 2104 17728 23934 32 0 0 1 91% 100% :s 65% 0 0 0 0 0 0 0

8% 719 0 0 721 1781 16394 20878 24 0 0 1 92% 100% :s 46% 2 0 0 0 0 0 0

9% 1133 0 0 1133 1808 18861 24810 0 0 0 1 93% 100% :s 58% 0 0 0 0 0 0 0

10% 802 0 0 802 2227 17639 23124 32 0 0 1 92% 100% :s 49% 0 0 0 0 0 0 0

11% 914 0 0 918 4303 17106 23486 24 0 0 1 92% 100% :s 59% 4 0 0 0 0 0 0

13% 1140 0 0 1140 12629 23893 30876 8 0 0 1 93% 100% :s 57% 0 0 0 0 0 0 0

10% 865 0 0 936 6002 7431 11088 24 0 0 1 86% 100% :s 54% 71 0 0 0 0 0 0

10% 907 0 0 907 6374 22753 21940 24 0 0 1 94% 100% :s 47% 0 0 0 0 0 0 0

16% 1468 0 0 1468 1785 68958 71042 8 0 0 1 99% 100% :s 46% 0 0 0 0 0 0 0

15% 1338 0 0 1341 1716 61911 64486 24 0 0 1 98% 100% :s 49% 3 0 0 0 0 0 0

15% 1379 0 0 1379 2372 69090 69644 32 0 0 1 99% 100% :s 48% 0 0 0 0 0 0 0

17% 1401 0 0 1404 2538 69727 76790 0 0 0 1 99% 100% :s 60% 3 0 0 0 0 0 0

9% 788 0 0 788 1731 28390 32940 24 0 0 1 96% 100% #s 40% 0 0 0 0 0 0 0

3% 155 0 0 155 339 740 1142 32 0 0 1 46% 100% #s 14% 0 0 0 0 0 0 0

4% 177 0 0 179 591 3640 4752 0 0 0 1 84% 100% #s 17% 2 0 0 0 0 0 0

2% 3 0 0 3 100 48 528 32 0 0 1 12% 100% #s 9% 0 0 0 0 0 0 0

2% 0 0 0 5 67 1 460 24 0 0 1 0% 100% #s 10% 5 0 0 0 0 0 0

CPU NFS CIFS HTTP Total Net kB/s Disk kB/s Tape kB/s Cache Cache CP CP Disk OTHER FCP iSCSI FCP kB/s iSCSI kB/s

in out read write read write age hit time ty util in out in out

2% 0 0 0 0 47 1 420 0 0 0 1 0% 100% #s 11% 0 0 0 0 0 0 0

5% 0 0 0 0 69 1 434 32 0 0 1 0% 100% #s 9% 0 0 0 0 0 0 0

2% 0 0 0 3 38 1 444 24 0 0 1 0% 100% #s 8% 3 0 0 0 0 0 0

2% 0 0 0 0 50 1 378 8 0 0 1 0% 100% #s 8% 0 0 0 0 0 0 0

2% 0 0 0 4 30 0 426 24 0 0 1 0% 100% #s 15% 4 0 0 0 0 0 0

3% 0 0 0 6 27 1 496 24 0 0 1 0% 100% #s 10% 6 0 0 0 0 0 0

Mon Jul 23 13:00:00 CEST [rflenasb:kern.uptime.filer:info]: 1:00pm up 63 days, 4:50 3117716252 NFS ops, 11007 CIFS ops, 0 HTTP ops, 0 FCP ops, 0 iSCSI ops

5% 0 0 0 2 21 1 528 8 0 0 1 0% 100% #s 10% 2 0 0 0 0 0 0

2% 0 0 0 2 8 0 1230 24 0 0 1 0% 100% #s 11% 2 0 0 0 0 0 0

3% 0 0 0 0 18 1 422 32 0 0 1 0% 100% #s 9% 0 0 0 0 0 0 0

2% 0 0 0 0 8 0 392 0 0 0 1 0% 100% #s 9% 0 0 0 0 0 0 0

2% 0 0 0 0 9 0 450 24 0 0 1 0% 100% #s 10% 0 0 0 0 0 0 0

2% 0 0 0 0 7 0 460 32 0 0 1 0% 100% #s 10% 0 0 0 0 0 0 0

3% 0 0 0 0 8 0 464 0 0 0 1 0% 100% #s 10% 0 0 0 0 0 0 0

2% 0 0 0 0 9 0 446 32 0 0 1 0% 100% #s 11% 0 0 0 0 0 0 0

3% 0 0 0 0 7 0 414 24 0 0 1 0% 100% #s 9% 0 0 0 0 0 0 0

2% 0 0 0 0 9 0 352 0 0 0 1 0% 100% #s 9% 0 0 0 0 0 0 0

22% 3 0 0 3 176 5 30662 43798 0 0 1 99% 100% #v 62% 0 0 0 0 0 0 0

Mon Jul 23 13:00:20 CEST [rflenasb: NwkThd_00:warning]: NFS response to client 10.80.0.22 for volume 0x153d1d5(esx2) was slow, op was v3 setattr, 70 > 60 (in seconds)

34% 2393 0 0 2443 12116 4590 23814 18694 0 0 1 97% 100% bn 100% 50 0 0 0 0 0 0

26% 1217 0 0 1217 8639 13542 20518 8 0 0 1 97% 100% :n 100% 0 0 0 0 0 0 0

42% 1866 0 0 1866 24263 21275 71234 65884 0 0 1 96% 100% :s 100% 0 0 0 0 0 0 0

CPU NFS CIFS HTTP Total Net kB/s Disk kB/s Tape kB/s Cache Cache CP CP Disk OTHER FCP iSCSI FCP kB/s iSCSI kB/s

in out read write read write age hit time ty util in out in out

24% 1921 0 0 1921 12677 73422 77234 24 0 0 1 97% 100% #s 71% 0 0 0 0 0 0 0

5% 29 0 0 29 256 332 960 8 0 0 1 67% 100% #s 14% 0 0 0 0 0 0 0

3% 0 0 0 0 158 2 394 24 0 0 1 0% 100% #s 10% 0 0 0 0 0 0 0

3% 0 0 0 0 15 0 444 32 0 0 1 0% 100% #s 10% 0 0 0 0 0 0 0

2% 0 0 0 0 10 1 398 0 0 0 1 0% 100% #s 10% 0 0 0 0 0 0 0

2% 0 0 0 0 9 0 426 24 0 0 1 0% 100% #s 10% 0 0 0 0 0 0 0

3% 0 0 0 0 7 0 432 32 0 0 1 0% 100% #s 9% 0 0 0 0 0 0 0

2% 0 0 0 0 7 1 404 0 0 0 1 1% 100% #s 10% 0 0 0 0 0 0 0

2% 0 0 0 0 7 0 418 32 0 0 1 0% 100% #s 10% 0 0 0 0 0 0 0

3% 0 0 0 0 8 0 422 24 0 0 1 70% 100% #s 14% 0 0 0 0 0 0 0

2% 0 0 0 70 8 0 466 0 0 0 1 0% 100% #s 10% 70 0 0 0 0 0 0

31% 1 0 0 1 75 4 70836 78572 0 0 1 99% 100% #f 61% 0 0 0 0 0 0 0

39% 1740 0 0 1747 14148 5937 42408 57304 0 0 1 97% 100% bn 100% 7 0 0 0 0 0 0

28% 1534 0 0 1535 15540 23453 44092 32448 0 0 1 95% 100% :n 99% 1 0 0 0 0 0 0

44% 1103 0 0 1103 25991 9884 60308 101382 0 0 1 97% 100% #s 100% 0 0 0 0 0 0 0

37% 1519 0 0 1522 26352 14175 43054 37259 0 0 1 98% 100% bn 100% 3 0 0 0 0 0 0

51% 1277 0 0 1277 31948 27319 94415 92132 0 0 1 98% 100% #s 100% 0 0 0 0 0 0 0

32% 251 0 0 254 739 11242 51692 56126 0 0 0s 99% 100% #v 100% 3 0 0 0 0 0 0

49% 1572 0 0 1576 20006 14113 89682 82876 0 0 1 97% 100% bs 100% 4 0 0 0 0 0 0

38% 578 0 0 578 2713 16394 46161 41123 0 0 1 99% 64% : 100% 0 0 0 0 0 0 0

CPU NFS CIFS HTTP Total Net kB/s Disk kB/s Tape kB/s Cache Cache CP CP Disk OTHER FCP iSCSI FCP kB/s iSCSI kB/s

in out read write read write age hit time ty util in out in out

29% 800 0 0 807 4079 27154 56046 3248 0 0 1 96% 9% Hn 100% 7 0 0 0 0 0 0

43% 792 0 0 793 5975 14662 61450 70862 0 0 1 97% 100% :f 100% 1 0 0 0 0 0 0

27% 382 0 0 384 3978 3430 19794 26324 0 0 1 98% 100% :f 100% 2 0 0 0 0 0 0

27% 849 0 0 849 10722 6265 14694 128 0 0 1 98% 38% : 100% 0 0 0 0 0 0 0

43% 1555 0 0 1556 35538 9930 58596 58081 0 0 1 98% 85% Hn 100% 1 0 0 0 0 0 0

26% 936 0 0 940 2751 20755 55928 32876 0 0 1 98% 100% :f 94% 4 0 0 0 0 0 0

27% 633 0 0 633 3124 13768 23174 2060 0 0 1 99% 84% : 100% 0 0 0 0 0 0 0

26% 518 0 0 564 2123 10895 34226 32 0 0 1 98% 4% Hn 100% 46 0 0 0 0 0 0

35% 617 0 0 617 4633 11030 54556 66508 0 0 1 98% 100% :f 100% 0 0 0 0 0 0 0

29% 1307 0 0 1307 6683 23034 38128 11512 0 0 16s 98% 100% :f 100% 0 0 0 0 0 0 0

28% 669 0 0 672 3165 14640 24352 1988 0 0 11s 99% 32% : 100% 3 0 0 0 0 0 0

26% 541 0 0 541 2567 5139 23508 12504 0 0 11s 99% 17% Hn 100% 0 0 0 0 0 0 0

32% 710 0 0 713 4564 11496 51318 46780 0 0 13s 97% 100% :f 96% 3 0 0 0 0 0 0

29% 930 0 0 931 3539 14889 25052 14222 0 0 13s 99% 100% :f 95% 1 0 0 0 0 0 0

29% 1028 0 0 1028 11638 15819 25936 58 0 0 12s 99% 31% : 100% 0 0 0 0 0 0 0

44% 1043 0 0 1046 16706 12302 74558 57306 0 0 4s 97% 74% Hs 100% 3 0 0 0 0 0 0

31% 742 0 0 742 5226 3535 26398 26496 0 0 4s 99% 100% :f 100% 0 0 0 0 0 0 0

31% 870 0 0 873 24193 1799 25810 35476 0 0 5s 97% 100% Hn 100% 3 0 0 0 0 0 0

33% 558 0 0 558 8323 2071 49475 70310 0 0 1s 96% 100% :f 88% 0 0 0 0 0 0 0

33% 584 0 0 585 6386 1733 9606 7780 0 0 1s 99% 35% : 100% 1 0 0 0 0 0 0

CPU NFS CIFS HTTP Total Net kB/s Disk kB/s Tape kB/s Cache Cache CP CP Disk OTHER FCP iSCSI FCP kB/s iSCSI kB/s

in out read write read write age hit time ty util in out in out

23% 311 0 0 381 1451 1613 9700 0 0 0 1s 99% 0% - 100% 70 0 0 0 0 0 0

46% 507 0 0 507 2685 3678 65432 87158 0 0 2 99% 95% Hf 100% 0 0 0 0 0 0 0

21% 706 0 0 709 2565 3980 9540 3926 0 0 2 98% 64% : 79% 3 0 0 0 0 0 0

10% 606 0 0 606 5845 4239 12220 8 0 0 2 92% 0% - 58% 0 0 0 0 0 0 0

13% 967 0 0 969 12382 8464 13946 24 0 0 2 91% 0% - 67% 2 0 0 0 0 0 0

51% 1822 0 0 1825 50860 6899 66208 63404 0 0 2 98% 80% Hf 99% 3 0 0 0 0 0 0

38% 594 0 0 594 9072 2694 50650 60972 0 0 2 99% 100% bn 100% 0 0 0 0 0 0 0

41% 399 0 0 401 2265 2079 60946 87910 0 0 1 99% 100% :f 100% 2 0 0 0 0 0 0

33% 364 0 0 364 2546 1906 10574 712 0 0 1 99% 39% : 100% 0 0 0 0 0 0 0

25% 416 0 0 416 2167 2314 11375 0 0 0 1 99% 0% - 100% 0 0 0 0 0 0 0

24% 343 0 0 346 3119 2457 10940 24 0 0 1 99% 0% - 100% 3 0 0 0 0 0 0

32% 438 0 0 438 1675 2632 51148 42310 0 0 1 99% 51% Hf 100% 0 0 0 0 0 0 0

33% 292 0 0 295 1811 3018 12778 18658 0 0 1 99% 67% : 97% 3 0 0 0 0 0 0

18% 533 0 0 533 3053 7998 17002 32 0 0 1 97% 0% - 82% 0 0 0 0 0 0 0

12% 773 0 0 773 5609 16628 25700 24 0 0 0s 94% 0% - 66% 0 0 0 0 0 0 0

14% 924 0 0 930 5664 29022 37660 0 0 0 1 96% 0% - 71% 6 0 0 0 0 0 0

27% 761 0 0 761 5015 8151 49150 40240 0 0 1 96% 41% Hf 80% 0 0 0 0 0 0 0

28% 383 0 0 429 3626 2528 39080 45334 0 0 1 99% 100% :f 100% 46 0 0 0 0 0 0

15% 958 0 0 958 4586 5615 13704 16926 0 0 1 94% 60% : 74% 0 0 0 0 0 0 0

10% 634 0 0 634 5092 5723 13354 24 0 0 1 92% 0% - 62% 0 0 0 0 0 0 0

...

The Filer then proceeded as normal and the Snapshot-deletion finished few seconds later

CHARLESNG2 · ‎2013-04-01

We had this same issue. Turns out it was a bug in OnTap 8.1.2. We updated to OnTap 8.1.2 P3 and it resolved our issue. (Non Metrocluster, FAS3240)

http://support.netapp.com/NOW/cgi-bin/bol?Type=Detail&Display=393877&app=portal

View solution in original post

preisler_andreas · ‎2012-07-23

Hello

i had a similar problem. i can see problems with our fas3160 on heavy load
for example: vmware storage vmotion

5 ESX-Servers are connected to the Filer via NFS ~250 VMs (HP BL460c Gen8 Flex10)

in my opinion ontap 8.1P1 is better then ontap8.1 (see attached pictures at that time with ontap 8.1)

data-access freeze for the time when CP ty is ":s" (NFS, Cifs and iscsi)

Version is NOW 8.1P1 on FAS3160 SingleController (storage vmotion still running):

aborzenkov · ‎2012-07-23

Could you please edit your message and change font of sysstat output to fixed width (e.g. courier) - it is near to unreadable as is. Thank you.

preisler_andreas · ‎2012-07-23

hi,

i have edit my post - now you can see a picture from ssh client

|

aborzenkov · ‎2012-07-23

Your output shows large number of CP in “s” phase. One of possible reasons in the past was enabled atime updates (which would induce massive inode change even in read-mostly workload). Is volume option “no_atime_update” set on your VMware volumes?

preisler_andreas · ‎2012-07-23

we have some vmware-nfs volumes ~10. all volumes are set to "no_atime_update on":

all volumes are on the same aggregat (96 disks, 6 loops, 175volumes within):

kngrfs03> vol options vol_tvm_noss_linux2

nosnap=off, nosnapdir=on, minra=off, no_atime_update=on, nvfail=off,

ignore_inconsistent=off, snapmirrored=off, create_ucode=on,

convert_ucode=on, maxdirsize=83804, schedsnapname=ordinal,

fs_size_fixed=off, guarantee=none, svo_enable=off, svo_checksum=off,

svo_allow_rman=off, svo_reject_errors=off, no_i2p=off,

fractional_reserve=0, extent=off, try_first=volume_grow,

read_realloc=off, snapshot_clone_dependency=off, dlog_hole_reserve=off,

nbu_archival_snap=off

kngrfs03> vol options vol_tvm_noss_win2

nosnap=off, nosnapdir=on, minra=off, no_atime_update=on, nvfail=off,

ignore_inconsistent=off, snapmirrored=off, create_ucode=on,

convert_ucode=on, maxdirsize=83804, schedsnapname=ordinal,

fs_size_fixed=off, guarantee=none, svo_enable=off, svo_checksum=off,

svo_allow_rman=off, svo_reject_errors=off, no_i2p=off,

fractional_reserve=0, extent=off, try_first=volume_grow,

read_realloc=off, snapshot_clone_dependency=off, dlog_hole_reserve=off,

nbu_archival_snap=off

kngrfs03> vol options vol_tvm_ss_win2

nosnap=off, nosnapdir=on, minra=off, no_atime_update=on, nvfail=off,

ignore_inconsistent=off, snapmirrored=off, create_ucode=on,

convert_ucode=on, maxdirsize=83804, schedsnapname=ordinal,

fs_size_fixed=off, guarantee=none, svo_enable=off, svo_checksum=off,

svo_allow_rman=off, svo_reject_errors=off, no_i2p=off,

fractional_reserve=0, extent=off, try_first=volume_grow,

read_realloc=off, snapshot_clone_dependency=off, dlog_hole_reserve=off,

nbu_archival_snap=off

kngrfs03> vol options vol_tvm_ss_linux2

nosnap=off, nosnapdir=on, minra=off, no_atime_update=on, nvfail=off,

ignore_inconsistent=off, snapmirrored=off, create_ucode=on,

convert_ucode=on, maxdirsize=83804, schedsnapname=ordinal,

fs_size_fixed=off, guarantee=none, svo_enable=off, svo_checksum=off,

svo_allow_rman=off, svo_reject_errors=off, no_i2p=off,

fractional_reserve=0, extent=off, try_first=volume_grow,

read_realloc=off, snapshot_clone_dependency=off, dlog_hole_reserve=off,

nbu_archival_snap=off

kngrfs03> vol options vol_tvm_ss_swdev2

nosnap=off, nosnapdir=on, minra=off, no_atime_update=on, nvfail=off,

ignore_inconsistent=off, snapmirrored=off, create_ucode=on,

convert_ucode=on, maxdirsize=83804, schedsnapname=ordinal,

fs_size_fixed=off, guarantee=none, svo_enable=off, svo_checksum=off,

svo_allow_rman=off, svo_reject_errors=off, no_i2p=off,

fractional_reserve=0, extent=off, try_first=volume_grow,

read_realloc=off, snapshot_clone_dependency=off, dlog_hole_reserve=off,

nbu_archival_snap=off

kngrfs03> vol options vol_tvm_swap2

nosnap=on, nosnapdir=on, minra=off, no_atime_update=on, nvfail=off,

ignore_inconsistent=off, snapmirrored=off, create_ucode=on,

convert_ucode=on, maxdirsize=83804, schedsnapname=ordinal,

fs_size_fixed=off, guarantee=none, svo_enable=off, svo_checksum=off,

svo_allow_rman=off, svo_reject_errors=off, no_i2p=off,

fractional_reserve=0, extent=off, try_first=volume_grow,

read_realloc=off, snapshot_clone_dependency=off, dlog_hole_reserve=off,

nbu_archival_snap=off

kngrfs03> vol options vol_tvm_noss_linux1

nosnap=off, nosnapdir=on, minra=off, no_atime_update=on, nvfail=off,

ignore_inconsistent=off, snapmirrored=off, create_ucode=on,

convert_ucode=on, maxdirsize=83804, schedsnapname=ordinal,

fs_size_fixed=off, guarantee=none, svo_enable=off, svo_checksum=off,

svo_allow_rman=off, svo_reject_errors=off, no_i2p=off,

fractional_reserve=0, extent=off, try_first=volume_grow,

read_realloc=off, snapshot_clone_dependency=off, dlog_hole_reserve=off,

nbu_archival_snap=off

kngrfs03> vol options vol_tvm_noss_win1

nosnap=off, nosnapdir=on, minra=off, no_atime_update=on, nvfail=off,

ignore_inconsistent=off, snapmirrored=off, create_ucode=on,

convert_ucode=on, maxdirsize=83804, schedsnapname=ordinal,

fs_size_fixed=off, guarantee=none, svo_enable=off, svo_checksum=off,

svo_allow_rman=off, svo_reject_errors=off, no_i2p=off,

fractional_reserve=0, extent=off, try_first=volume_grow,

read_realloc=off, snapshot_clone_dependency=off, dlog_hole_reserve=off,

nbu_archival_snap=off

kngrfs03> vol options vol_tvm_ss_win1

nosnap=off, nosnapdir=on, minra=off, no_atime_update=on, nvfail=off,

ignore_inconsistent=off, snapmirrored=off, create_ucode=on,

convert_ucode=on, maxdirsize=83804, schedsnapname=ordinal,

fs_size_fixed=off, guarantee=none, svo_enable=off, svo_checksum=off,

svo_allow_rman=off, svo_reject_errors=off, no_i2p=off,

fractional_reserve=0, extent=off, try_first=volume_grow,

read_realloc=off, snapshot_clone_dependency=off, dlog_hole_reserve=off,

nbu_archival_snap=off

kngrfs03> vol options vol_tvm_ss_linux1

nosnap=off, nosnapdir=on, minra=off, no_atime_update=on, nvfail=off,

ignore_inconsistent=off, snapmirrored=off, create_ucode=on,

convert_ucode=on, maxdirsize=83804, schedsnapname=ordinal,

fs_size_fixed=off, guarantee=none, svo_enable=off, svo_checksum=off,

svo_allow_rman=off, svo_reject_errors=off, no_i2p=off,

fractional_reserve=0, extent=off, try_first=volume_grow,

read_realloc=off, snapshot_clone_dependency=off, dlog_hole_reserve=off,

nbu_archival_snap=off

kngrfs03> vol options vol_tvm_ss_swdev1

nosnap=off, nosnapdir=on, minra=off, no_atime_update=on, nvfail=off,

ignore_inconsistent=off, snapmirrored=off, create_ucode=on,

convert_ucode=on, maxdirsize=83804, schedsnapname=ordinal,

fs_size_fixed=off, guarantee=none, svo_enable=off, svo_checksum=off,

svo_allow_rman=off, svo_reject_errors=off, no_i2p=off,

fractional_reserve=0, extent=off, try_first=volume_grow,

read_realloc=off, snapshot_clone_dependency=off, dlog_hole_reserve=off,

nbu_archival_snap=off

kngrfs03>

kngrfs03> sis status

Path State Status Progress

/vol/vol_tvm_ss_win2 Enabled Idle Idle for 71:54:16

/vol/vol_tvm_ss_linux2 Enabled Idle Idle for 59:29:26

/vol/vol_tvm_ss_swdev2 Enabled Idle Idle for 103:23:07

/vol/vol4 Enabled Idle Idle for 23:46:41

AGUMADAVALLI · ‎2012-07-23

Hi there:

Leave the defaults on no_atime_update, the best way to get around this buy a PAM card and set the parameters according to the load(read and writes).

thank you,

AK G

preisler_andreas · ‎2012-07-23

hi,

1.) i have created a new vmware datastore with netapps VI-plugin. so the volume defaults are "no_atime_update=on":

vol options newDatastore

nosnap=on, nosnapdir=off, minra=off, no_atime_update=on, nvfail=off,

ignore_inconsistent=off, snapmirrored=off, create_ucode=on,

convert_ucode=on, maxdirsize=83804, schedsnapname=ordinal,

fs_size_fixed=off, guarantee=none, svo_enable=off, svo_checksum=off,

svo_allow_rman=off, svo_reject_errors=off, no_i2p=off,

fractional_reserve=0, extent=off, try_first=volume_grow,

read_realloc=off, snapshot_clone_dependency=off, dlog_hole_reserve=off,

nbu_archival_snap=off

2.) there is no place left for an PAM card in our fas3160

we didnt have such problems with ontap 8.0.1 an 32bit aggregates and 32bit volumes

here is another sysstat output from today, on early morning. you can see a running ndmp-backup to tape process and less user-access. but CP ty is already ":s"

aborzenkov · ‎2012-07-23

You really have to open support case to get it analyzed. But it starts to sound very much like bug http://support.netapp.com/NOW/cgi-bin/bol?Type=Detail&Display=510586

SCHLEGELM · ‎2012-07-23

Same here, all volumes are set to no_atime_updates

We've got PAM cards but couldn't use them with the 8.1GA because they are not supported (I know that there are Patch-Releases and RCs out there where this issue is fixed)

aborzenkov · ‎2012-07-26

8.1P2 was recently released and contains large number of performance related bug fixes. May be worth to try.

dcordero · ‎2012-08-10

Hello, same problem here, FAS3140 Metrocluster Ontap 8.1GA Vmware 4.1, when customer delete some vm´s or even deleting snapshots, the IO get freezing. some time datastores get disconnected.

Any idea?

Thanks

David

aborzenkov · ‎2012-08-10

There were quite a number of performance related fixes in subsequent patch releases. You could try the latest 8.1P2 to see if it improves situation.

SCHLEGELM · ‎2012-08-12

Hi David,

we installed 8.1.1RC1 to finally make use of our Flash Modules and the Problem is still there but not as extreme as before. There is still a NFS Service-'Blackout' of ~10 seconds but this is not recognized by our VMware Cluster like the 60 seconds before with 8.1GA. 8.1P2 seems to have the same performance related fixes as 8.1.1RC1...

I don't know if it's better because of the Flash Modules or the new version, sorry

preisler_andreas · ‎2012-08-13

hi there,

similar here...

we dont have Flash Modules

8.1.1RC1 is better than 8.1P1. but the problem still exist. there is still a complete service-"blackout" (iscsi, cifs, nfs) of 10-30s

i can see these blackouts mostly at night, when our backupscript is working and deletes many snapshots and creating new snapshots (and a lot of snapmirror updates)

when the service-blackout exists:

sometimes the oracle-rac server are rebooting

sometimes the esx-server are shutting down some vms and vmx-files get corrupted

iscsi-hosts:

\Device\MPIODisk1 is currently in a degraded state. One or more paths have failed, though the process is now complete.

Initiator sent a task management command to reset the target. The target name is given in the dump data.

Target failed to respond in time to a Task Management request

Target did not respond in time for a SCSI request. The CDB is given in the dump data.

Can not Reset the Target or LUN. Will attempt session recovery.

other messages (mostly at night):

Thu Aug 2 23:19:33 CEST [vfs15@NwkThd_02:warning]: NFS response to client 192.168.195.111 for volume 0x71a5c0ba(vol_tvm_swap2) was slow, op was v3 write, 218 > 60 (in seconds) -> 64bit Volume

Thu Aug 2 23:19:35 CEST [kngrfs03:iscsi.warning:warning]: ISCSI: iswtu_evr: unexpected event id 185 reported

Thu Aug 2 23:42:37 CEST last message repeated 8 times

Thu Aug 2 23:56:48 CEST [kngrfs03:wafl.cp.slovol:warning]: aggregate aggr6 is holding up the CP.

these problems exists on our fas3160 (ontap 8.1.1RC1) with 10 enabled vfilers and 8GB system memory

we dont see this problems on our fas6080c (ontap 8.1) without enabled vfilers and 32GB system memory

i cannot see these problems on our fas3160 when i am deleting big 64bit volumes (volumes from 2TB to 5TB with ~4.000k files per Volume)

at this time, my workaround was to move all test- und development- vms to the fas6080c

g_vankuilenburg · ‎2012-08-29

Any change on this with 8.1.1 GA? I'd like to start using 8.1 or 8.1.1, but this has kept me on 8.0.2 so far.

michel_rebmann · ‎2012-08-29

We had similar issues with a certain ESXi version (nut sure, but I think it was 4.1 U1) We updated to ESXi 4.1 U2 (Build 502767) and the VM snapshot removal was fine.

The KB from VMware:

Virtual machine freezes temporarily during snapshot removal on an NFS datastore in a ESX/ESXi 4.1 host

http://kb.vmware.com/selfservice/microsites/search.do?language=en_US&cmd=displayKC&externalId=1031106

oliver_matic · ‎2012-08-30

Hello@all,

i have the same Issue on our Enviroment:

NetApp 3240 with 8.1.1GA

NFS Datastores connected to a vSphere 5.0.0, 768111

Commvault Simpana v9 Backup Solution

Virtual machine freezes temporarily during snapshot removal triggered thru the Backup Solution.

This KB-Articel (yesterday reviewed) didnt help in my case.

http://kb.vmware.com/selfservice/microsites/search.do?language=en_US&cmd=displayKC&externalId=2010953

Any suggestions?

Best Regards

Oliver

preisler_andreas · ‎2012-08-31

Hi,

not really

i opened an case and sending daily perfstat information

maybe netapp helps, if you can open an additionally case to sending additionally perfstat information?

Case No. 2003429259 from 08/15/2012

Best Regards

Andreas

SCHLEGELM · ‎2012-09-26

Any news on this one?

I experienced the same thing today

We're still on 8.1.1RC1 but as i see it won't make a difference upgrading to 8.1.1GA

oliver_matic · ‎2012-09-26

Ich bin bis 10/08/2012 abwesend.

Mit freundlichen Grüßen / Best Regards

Oliver Matic

Server-Administrator

ICT

Phone: +49 6181 403 525 - Fax: +49 6181 403 1 525 - Mobile: +49 1520 900

8726

E-mail: Oliver.Matic@normagroup.com