From mboxrd@z Thu Jan 1 00:00:00 1970 Message-ID: <140e7ec30812042122l1f161410u51b1c10ad3897ef2@mail.gmail.com> Date: Fri, 5 Dec 2008 14:22:18 +0900 From: sqweek To: "Fans of the OS Plan 9 from Bell Labs" <9fans@9fans.net> In-Reply-To: <27049442.3521101228145098701.JavaMail.nitido@priv-edtnes95> MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <27049442.3521101228145098701.JavaMail.nitido@priv-edtnes95> Subject: Re: [9fans] image/memimage speed Topicbox-Message-UUID: 5a7f819a-ead4-11e9-9d60-3106f5b1d025 On Tue, Dec 2, 2008 at 12:24 AM, wrote: > I think the real performance issue for hardware where the frame buffer is in > the PCIe shared memory apperture is that writes are write-through/coalesced > on their way across the PCIe, but reads can't be, and so incur huge stalls. Hah, this sounds just like 9p's latency woes. -sqweek