[lustre-discuss] some clients dmesg filled up with "dirty page discard"

Colin Faber cfaber at gmail.com
Tue Aug 25 09:16:30 PDT 2020


The I/O was not fully committed after close() from the client. Are you
experiencing high numbers of evictions?

On Tue, Aug 25, 2020 at 9:12 AM 肖正刚 <guru.novice at gmail.com> wrote:

> Hi, all
>
> We found that some clients' dmesg filled up with messages like
> "
> Aug 24 19:54:34 ln5 kernel: Lustre:
> 13565:0:(llite_lib.c:2759:ll_dirty_page_discard_warn()) public1: dirty page
> discard: 10.10.2.11 at o2ib:10.10.2.12 at o2ib:/public1/fid:
> [0x200007a82:0x1680f:0x0]/ may get corrupted (rc -108)
> Aug 24 19:54:34 ln5 kernel: Lustre:
> 13547:0:(llite_lib.c:2759:ll_dirty_page_discard_warn()) public1: dirty page
> discard: 10.10.2.11 at o2ib:10.10.2.12 at o2ib:/public1/fid:
> [0x200007a82:0x14246:0x0]/ may get corrupted (rc -108)
> Aug 24 19:54:34 ln5 kernel: Lustre:
> 13545:0:(llite_lib.c:2759:ll_dirty_page_discard_warn()) public1: dirty page
> discard: 10.10.2.11 at o2ib:10.10.2.12 at o2ib:/public1/fid:
> [0x200007a82:0x12018:0x0]/ may get corrupted (rc -108)
> Aug 24 19:54:34 ln5 kernel: Lustre:
> 13567:0:(llite_lib.c:2759:ll_dirty_page_discard_warn()) public1: dirty page
> discard: 10.10.2.11 at o2ib:10.10.2.12 at o2ib:/public1/fid:
> [0x200007a82:0x12c86:0x0]/ may get corrupted (rc -108)
> Aug 24 19:54:34 ln5 kernel: Lustre:
> 13566:0:(llite_lib.c:2759:ll_dirty_page_discard_warn()) public1: dirty page
> discard: 10.10.2.11 at o2ib:10.10.2.12 at o2ib:/public1/fid:
> [0x200007a82:0x12c76:0x0]/ may get corrupted (rc -108)
> Aug 24 19:54:34 ln5 kernel: Lustre:
> 13550:0:(llite_lib.c:2759:ll_dirty_page_discard_warn()) public1: dirty page
> discard: 10.10.2.11 at o2ib:10.10.2.12 at o2ib:/public1/fid:
> [0x200007a82:0x12c8e:0x0]/ may get corrupted (rc -108)
> Aug 24 19:54:34 ln5 kernel: Lustre:
> 13568:0:(llite_lib.c:2759:ll_dirty_page_discard_warn()) public1: dirty page
> discard: 10.10.2.11 at o2ib:10.10.2.12 at o2ib:/public1/fid:
> [0x200007a82:0x12c66:0x0]/ may get corrupted (rc -108)
> Aug 24 19:54:34 ln5 kernel: Lustre:
> 13569:0:(llite_lib.c:2759:ll_dirty_page_discard_warn()) public1: dirty page
> discard: 10.10.2.11 at o2ib:10.10.2.12 at o2ib:/public1/fid:
> [0x200007a82:0x12c7e:0x0]/ may get corrupted (rc -108)
> Aug 24 19:54:34 ln5 kernel: Lustre:
> 13548:0:(llite_lib.c:2759:ll_dirty_page_discard_warn()) public1: dirty page
> discard: 10.10.2.11 at o2ib:10.10.2.12 at o2ib:/public1/fid:
> [0x200007a82:0x12c6e:0x0]/ may get corrupted (rc -108)
> Aug 24 19:54:34 ln5 kernel: Lustre:
> 13570:0:(llite_lib.c:2759:ll_dirty_page_discard_warn()) public1: dirty page
> discard: 10.10.2.11 at o2ib:10.10.2.12 at o2ib:/public1/fid:
> [0x200007a82:0x12ca6:0x0]/ may get corrupted (rc -108)
> Aug 24 19:54:34 ln5 kernel: Lustre:
> 13549:0:(llite_lib.c:2759:ll_dirty_page_discard_warn()) public1: dirty page
> discard: 10.10.2.11 at o2ib:10.10.2.12 at o2ib:/public1/fid:
> [0x200007a82:0x12cbe:0x0]/ may get corrupted (rc -108)
> Aug 24 19:54:34 ln5 kernel: Lustre:
> 13571:0:(llite_lib.c:2759:ll_dirty_page_discard_warn()) public1: dirty page
> discard: 10.10.2.11 at o2ib:10.10.2.12 at o2ib:/public1/fid:
> [0x200007a82:0x12cb6:0x0]/ may get corrupted (rc -108)
> Aug 24 19:54:34 ln5 kernel: Lustre:
> 13551:0:(llite_lib.c:2759:ll_dirty_page_discard_warn()) public1: dirty page
> discard: 10.10.2.11 at o2ib:10.10.2.12 at o2ib:/public1/fid:
> [0x200007a82:0x12cae:0x0]/ may get corrupted (rc -108)
> Aug 24 19:54:34 ln5 kernel: Lustre:
> 13572:0:(llite_lib.c:2759:ll_dirty_page_discard_warn()) public1: dirty page
> discard: 10.10.2.11 at o2ib:10.10.2.12 at o2ib:/public1/fid:
> [0x200007a82:0x12cce:0x0]/ may get corrupted (rc -108)
> Aug 24 19:54:34 ln5 kernel: Lustre:
> 13573:0:(llite_lib.c:2759:ll_dirty_page_discard_warn()) public1: dirty page
> discard: 10.10.2.11 at o2ib:10.10.2.12 at o2ib:/public1/fid:
> [0x200007a82:0x12cc6:0x0]/ may get corrupted (rc -108)
> Aug 24 19:54:34 ln5 kernel: Lustre:
> 13574:0:(llite_lib.c:2759:ll_dirty_page_discard_warn()) public1: dirty page
> discard: 10.10.2.11 at o2ib:10.10.2.12 at o2ib:/public1/fid:
> [0x200007a82:0x12d56:0x0]/ may get corrupted (rc -108)
> Aug 24 19:54:34 ln5 kernel: Lustre:
> 13575:0:(llite_lib.c:2759:ll_dirty_page_discard_warn()) public1: dirty page
> discard: 10.10.2.11 at o2ib:10.10.2.12 at o2ib:/public1/fid:
> [0x200007a82:0x12d36:0x0]/ may get corrupted (rc -108)
> Aug 24 19:54:34 ln5 kernel: Lustre:
> 13576:0:(llite_lib.c:2759:ll_dirty_page_discard_warn()) public1: dirty page
> discard: 10.10.2.11 at o2ib:10.10.2.12 at o2ib:/public1/fid:
> [0x200007a82:0x1429e:0x0]/ may get corrupted (rc -108)
>
> "
> Then, we checked disk array, sas link, multipath, but no error found.
> Has anyone ever met the same problem ?
> Any suggestions will help!
>
> Regards.
> _______________________________________________
> lustre-discuss mailing list
> lustre-discuss at lists.lustre.org
> http://lists.lustre.org/listinfo.cgi/lustre-discuss-lustre.org
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.lustre.org/pipermail/lustre-discuss-lustre.org/attachments/20200825/a3b19004/attachment-0001.html>


More information about the lustre-discuss mailing list