Date: Sun, 20 Feb 2005 02:25:52 +0800 From: Rong-En Fan <rafan@infor.org> To: Rong-En Fan <rafan@csie.org> Cc: scsi@freebsd.org Subject: Re: Problem with mpt(4) and Infortrend RAID Message-ID: <20050219182552.GA8727@svm.csie.ntu.edu.tw> In-Reply-To: <20050219114731.GA97896@svm.csie.ntu.edu.tw> References: <1108667040.656.20.camel@spirit> <20050218071746.GA41419@svm.csie.ntu.edu.tw> <20050218202901.GA71842@svm.csie.ntu.edu.tw> <20050219061517.GA92149@svm.csie.ntu.edu.tw> <1108803317.602.13.camel@spirit> <20050219092300.GA95182@svm.csie.ntu.edu.tw> <1108806312.602.17.camel@spirit> <20050219101214.GA96011@svm.csie.ntu.edu.tw> <1108808926.602.25.camel@spirit> <20050219114731.GA97896@svm.csie.ntu.edu.tw>
next in thread | previous in thread | raw e-mail | index | archive | help
On Sat, Feb 19, 2005 at 07:47:31PM +0800, Rong-En Fan wrote: > On Sat, Feb 19, 2005 at 06:28:46PM +0800, Xin LI wrote: > > Hi, > > > > ÔÚ 2005-02-19ÁùµÄ 18:12 +0800£¬Rong-En FanдµÀ£º > > > On Sat, Feb 19, 2005 at 05:45:12PM +0800, Xin LI wrote: > > > > Would you please try: > > > > camcontrol tags da1 > > > > > > > > To see how many tags are actually allowed for the device, at the host > > > > side? It comes to my mind that: > > > > > > I have already done -N 32, I remembered that original is 25x. > > > > Er... Pardon... You mean you have already done this before you got the > > error message, or just have done that? > > just have done that. I got similar messages when I doing rsync 4M files (800G) to da1s1d from another machine via nfs (-N 32). The box configuration is that there are total 12 slices on da0 and exported to 20 clients via nfs. Both da0 and da1 are setted with tag depth = 32. The hardware RAID has 16 drives and configurated as 2 RAID5 logical drive, each has 8 drives. These two RAID5 LD are mapped to two channels, respectively. It is strange to me that since last two weeks ago, I'm doing rsync all the times from another machine to da0 (running at 160MB/s on mpt0, da1 is 160MB/s on mpt1). And no io on da1. I didn't set tag depth that time, but seems it works fine. I wonder if it is caused the raid controller which might not handle two concurrent host-lun access well. I'm looking for opportunity to do this experiment. Regards, Rong-En Fan
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20050219182552.GA8727>