Date: Tue, 2 Feb 2016 11:54:46 -0500 From: Vick Khera <vivek@khera.org> To: Charles Sprickman <spork@bway.net> Cc: Ben Woods <woodsb02@gmail.com>, freebsd-fs@freebsd.org, "freebsd-questions@freebsd.org" <freebsd-questions@freebsd.org> Subject: Re: NFS unstable with high load on server Message-ID: <CALd%2BdcdDP50RLc1urQSUPJ9yuBnTtiOUxoX44Cte=BA9DtHFpw@mail.gmail.com> In-Reply-To: <5EAD4A4A-211F-451E-A3B9-752DAC6D94B4@bway.net> References: <CALd%2BdcfzPU=nMGo41BBZzt3jQnsQJaANVyA222TDM_is2Ueo0A@mail.gmail.com> <CAOc73CCHS4r-proJ_jT4T%2BBfcQB9pND8Ld8QZqYJOCkuq2LqiA@mail.gmail.com> <5EAD4A4A-211F-451E-A3B9-752DAC6D94B4@bway.net>
next in thread | previous in thread | raw e-mail | index | archive | help
On Tue, Feb 2, 2016 at 1:26 AM, Charles Sprickman <spork@bway.net> wrote: > Me three. I=E2=80=99m actually updating a small group of servers now and= started > blowing up my installworlds by trying to do some poudriere builds at the > same > time. Very repeatable. Of note, I=E2=80=99m on 9.3, and saw this on 8.4= as > well. If I > track down the client-side failures, it=E2=80=99s always =E2=80=9Cpermiss= ion denied=E2=80=9D. > Thanks for confirming this behavior. It is distressing to me that it happens at all. It must be some bad race condition somewhere, and unfortunately having a non-deterministic NFS server makes is unsuitable for production use. This is a problem for me since everything I have is FreeBSD... I will file a bug ticket, since I'm pretty sure at this point it is not something special with my environment.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CALd%2BdcdDP50RLc1urQSUPJ9yuBnTtiOUxoX44Cte=BA9DtHFpw>