On Thu, Dec 17, 2009 at 09:57:12AM +0000, Christopher J.Walker wrote: > I have a stream of errors in the logs of my Lustre clients. > > 21544:0:(ldlm_request.c:1033:ldlm_cli_cancel_req()) Skipped 888 previous > similar messages > Dec 16 15:42:33 se03 kernel: LustreError: > 21544:0:(ldlm_request.c:1622:ldlm_cli_cancel_list()) > ldlm_cli_cancel_list: -108 > > We have Lustre 1.8.1.1 servers and both Lustre 1.6.7 and 1.8.1.1 clients > (with a patch applied so we can use the 2.6.18-164.6.1.el5 > kernel). > I'm seeing this too on a very vanilla lustre 1.8.1.1 setup; it's an essentially x86_64 RHEL5-esqe system (actually Scientific Linux), the servers are running the Sun built 2.6.18-128.7.1.el5_lustre.1.8.1.1 kernel and the troublesome client is running the stock 2.6.18-128.7.1.el5 kernel with 1.8.1.1-2.6.18_128.7.1.el5_lustre.1.8.1.1 versions of the lustre-client and lustre-client-modules packages.
The client automounts the lustre filesystem, and it seems to fall over when doing a du scan of the filesysem, so there's a lot of stat-ing going on, but not much else. Ewan
pgp9fegUXhfrg.pgp
Description: PGP signature
_______________________________________________ Lustre-discuss mailing list [email protected] http://lists.lustre.org/mailman/listinfo/lustre-discuss
