Date: Wed, 19 Aug 1998 23:19:10 +0000 From: Mike Smith <mike@smith.net.au> To: Andre Oppermann <oppermann@pipeline.ch> Cc: hackers@FreeBSD.ORG Subject: Re: combined accept&read Message-ID: <199808192319.XAA01112@dingo.cdrom.com> In-Reply-To: Your message of "Wed, 19 Aug 1998 18:58:10 %2B0200." <35DB0422.B6447353@pipeline.ch>
next in thread | previous in thread | raw e-mail | index | archive | help
> I was chatting a little bit with the Zeus developers to ask them how > to make FreeBSD the best/fastest platform for them. > > "accept&read combined call is something else we're toying with. Very > often we get a poll/select broken because there's data coming in on a > socket, and most of the time there's already data in the socket > buffers. Being able to do the accept() and read() in a single call > should be beneifital." Some benchmarks demonstrating that this overhead actually costs them, and how it might be improved, would really support their arguments. Like the sendfile() case, all these "wouldn't it be nice if" suggestions don't actually mean much unless the benefits can be quantified. > They also wish to have a few thousand open fd's without slowing > down stuff like get_first_free_fd(). I don't know what "get_first_free_fd()" you might be referring to. kern_descrip.c:fdalloc() is already optimised to supply an fd rapidly even in the case where there are many fd's open. Having "a few thousand" fd's open in a single process shouldn't hurt it noticeably. -- \\ Sometimes you're ahead, \\ Mike Smith \\ sometimes you're behind. \\ mike@smith.net.au \\ The race is long, and in the \\ msmith@freebsd.org \\ end it's only with yourself. \\ msmith@cdrom.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199808192319.XAA01112>