Date: Tue, 25 Oct 2005 11:05:07 +0400 From: Gleb Smirnoff <glebius@FreeBSD.org> To: Mao Shou Yan <david.mao@thomson.net> Cc: net@FreeBSD.org Subject: Re: em(4) patch for test Message-ID: <20051025070507.GA41520@cell.sick.ru> In-Reply-To: <31021C278A7A6B4AB95E9A085C35521828495B@bjngsmail01> References: <31021C278A7A6B4AB95E9A085C35521828495B@bjngsmail01>
next in thread | previous in thread | raw e-mail | index | archive | help
On Tue, Oct 25, 2005 at 02:55:01PM +0800, Mao Shou Yan wrote: M> NO, I didn't encounter a lot if input errors on 4.11. M> But I met a lot if input errors on 5.4. And I don't know why? M> Is this for so many CSWs( systat -vmstat 1) or any other reason? M> BTW, New patch loops in em_intr() like linux' NAPI. If we apply new M> patch, polling is necessary yet? If you encounter problems on 5.4, then you should try the patch. The patch doesn't affects polling users, only those who use interrupt driven mode. P.S. Please don't top quote. -- Totus tuus, Glebius. GLEBIUS-RIPN GLEB-RIPE
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20051025070507.GA41520>