Date: Mon, 06 Apr 2015 16:09:03 -0400 From: John Baldwin <jhb@freebsd.org> To: freebsd-current@freebsd.org Cc: Lars <lars@odin-corporation.com> Subject: Re: Is a high witness refcount indicative of a missing unlock? Message-ID: <238127021.hvy73srvVG@ralph.baldwin.cx> In-Reply-To: <1117D087-AD76-4A87-8798-AB5526BECF3A@odin-corporation.com> References: <1117D087-AD76-4A87-8798-AB5526BECF3A@odin-corporation.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Sunday, March 29, 2015 02:29:42 PM Lars wrote: > Hi, > I am poking around for a cause for my repeating deadlock issues on my= system based on r 279869. ddb show witness show the =E2=80=9Cvnode int= erlock=E2=80=9D and the =E2=80=9Czfs=E2=80=9D locks both with reference= counts over 200K. Obviously they are related, and there is a find runn= ing (all the filesystems on this machine are zfs ( minus the specialty = ones like devfs). >=20 > I don=E2=80=99t see any other withness entry with reference counts ev= en in the ballpark of these two, so does this indicate that we have a v= node/zfs path were we don=E2=80=99t unlock? The ref count just means that the locks exist (so you have 200k ZFS vno= des), not that the locks are currently held. The reference count on the witn= ess object is bumped when a lock is created that uses that witness object a= nd released when the lock is destroyed. --=20 John Baldwin
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?238127021.hvy73srvVG>