Date: Fri, 3 Jan 2003 20:35:24 -0800 From: Marcel Moolenaar <marcel@xcllnt.net> To: Arun Sharma <arun.sharma@intel.com> Cc: freebsd-ia64@FreeBSD.ORG Subject: Re: unaligned fault in pmap_find_vhpt Message-ID: <20030104043524.GA2059@dhcp01.pn.xcllnt.net> In-Reply-To: <200301032303.gBQJBOs00863@unix-os.sc.intel.com> References: <200301032303.gBQJBOs00863@unix-os.sc.intel.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Fri, Jan 03, 2003 at 03:03:14PM -0800, Arun Sharma wrote: > > I saw a kernel mode unaligned fault during a compilation workload > yesterday on an SMP 5.0-RC1 kernel. The fault happened here: > > 0xe000000000aad660 <pmap_find_vhpt+80>: > > More info below. It looks like the pte_chain is getting corrupted > somehow. What is the locking scheme being used to protect pte > collision chains on an SMP kernel ? We don't really have a consistent locking scheme. We walk and update the VHPT from IVA interrupt code as well. Under high load, a SMP kernel corrupts process space. I haven't seen the unaligned fault you mention. As for locking: I've been thinking about a VHPT per CPU. With processor affinity, massive clustering, NUMA architectures and other complexities, there may be an advantage to pay for the additional faults if we can keep a flexible implementation and without so much lock contention. I haven't thought about hyper- threaded setups (ie a VHPT per thread or per CPU package) Thoughts? I'll play with SMP some more this weekend (also WRT you patch)... -- Marcel Moolenaar USPA: A-39004 marcel@xcllnt.net To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-ia64" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20030104043524.GA2059>