Date: Fri, 5 Nov 1999 07:53:13 -0500 (EST) From: Christopher Sedore <cmsedore@mailbox.syr.edu> To: John Polstra <jdp@polstra.com> Cc: hackers@freebsd.org Subject: Re: aio Functions Message-ID: <Pine.SOL.4.10.9911050750390.4895-100000@rodan.syr.edu> In-Reply-To: <199911040014.QAA49756@vashon.polstra.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Wed, 3 Nov 1999, John Polstra wrote: > In article <Pine.SOL.4.10.9911031756080.24901-100000@rodan.syr.edu>, > Christopher Sedore <cmsedore@mailbox.syr.edu> wrote: [...snip info on aio stuff...] > > > > I hope to try 1000 descriptors soon. > > That's great news! So have you gotten rid of some of these absurdly > low fixed limits? > > vfs.aio.max_aio_per_proc: 32 > vfs.aio.max_aio_queue_per_proc: 256 > vfs.aio.max_aio_procs: 32 > vfs.aio.max_aio_queue: 1024 > vfs.aio.max_buf_aio: 16 > > And worst of all: > > #define AIO_LISTIO_MAX 16 I've been running with about 85 descriptors (vast majority are sockets) and haven't bumped these limits in a serious way yet (have hit the 32 max running per proc, but just for milliseconds). When I get to the next round of testing these limits won't cut it and I'll adjust them upward. -Chris 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?Pine.SOL.4.10.9911050750390.4895-100000>