From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Miller Subject: Re: [take2 1/4] kevent: core files. Date: Tue, 01 Aug 2006 17:01:38 -0700 (PDT) Message-ID: <20060801.170138.107248641.davem@davemloft.net> References: <11544248451203@2ka.mipt.ru> <44CFEA4B.3060200@oracle.com> Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Cc: johnpol@2ka.mipt.ru, linux-kernel@vger.kernel.org, drepper@redhat.com, netdev@vger.kernel.org Return-path: To: zach.brown@oracle.com In-Reply-To: <44CFEA4B.3060200@oracle.com> Sender: linux-kernel-owner@vger.kernel.org List-Id: netdev.vger.kernel.org From: Zach Brown Date: Tue, 01 Aug 2006 16:56:59 -0700 > Even if we only have one syscall with a cmd multiplexer (which I'm not > thrilled with), we should at least make these arguments explicit in the > system call. It's weird to hide them in a struct. We could also think > about making them u32 or u64 so that we don't need compat wrappers, but > maybe that's overkill. I think making the userspace data structure not require any compat handling is a must, thanks for pointing this out Zach. > It'd be great if these struct members could get a prefix (ala: inode -> > i_, socket -> sk_) so that it's less painful getting tags helpers to > look up instances for us. Asking for 'lock' is hilarious. Agreed. > Hmm. I think the current preference is not to have a lock per bucket. Yes, it loses badly, that's why we undid this in the routing cache and just have a fixed sized array of locks which is hashed into. For kevents, I think a single spinlock initially is fine and if we hit performance problems on SMP we can fix it. We should not implement complexity we have no proof of needing yet :) > > +#define KEVENT_MAX_REQUESTS PAGE_SIZE/sizeof(struct kevent) > > This is unused? It is probably groundwork for the mmap() ring buffer... :)