Return to BSD News archive
Newsgroups: comp.os.386bsd.questions Path: sserve!newshost.anu.edu.au!harbinger.cc.monash.edu.au!msunews!uwm.edu!news.moneng.mei.com!howland.reston.ans.net!EU.net!sun4nl!nikhefk!paramount.nikhefk.nikhef.nl!adrik From: adrik@paramount.nikhefk.nikhef.nl (Adri Koppes) Subject: Re: REPOST: What's that: ahb_scsi_cmd0: more than 33 DMA segs Message-ID: <adrik.15.00370A80@paramount.nikhefk.nikhef.nl> Lines: 26 Sender: news@paramount.nikhefk.nikhef.nl (Daily News) Organization: NIKHEFK X-Newsreader: Trumpet for Windows [Version 1.0 Rev B final beta #4] References: <D01sxM.JKs@luva.lb.bawue.de> <3bl7gn$rs2@pdq.coe.montana.edu> Date: Mon, 5 Dec 1994 20:38:15 GMT In article <3bl7gn$rs2@pdq.coe.montana.edu> nate@bsd.coe.montana.edu (Nate Williams) writes: >From: nate@bsd.coe.montana.edu (Nate Williams) >Subject: Re: REPOST: What's that: ahb_scsi_cmd0: more than 33 DMA segs >Date: 1 Dec 1994 19:17:43 GMT >In article <D01sxM.JKs@luva.lb.bawue.de>, >Michael Giegerich <migieger@luva.lb.bawue.de> wrote: >> >>What's the meaning of this error message? >> >>Nov 8 21:52:53 luva /386bsd: ahb_scsi_cmd0: more than 33 DMA segs >>Nov 8 21:52:53 luva /386bsd: sd0: oops not queued >>Nov 8 22:03:40 luva /386bsd: ahb_scsi_cmd0: more than 33 DMA segs >>Nov 8 22:03:40 luva /386bsd: sd0: oops not queued >It means that somehow the software got a bad SCSI request. This is >generally caused by some sort of memory error. I suspect bad memory >and/or bad hardware termination on the SCSI controller. Isn't this message generated by the aha-154x scatter/gather routine, whenever there are more than 32 blocks of physical memory to transfer with busmaster DMA? 32 is the hardware limit off the AHA-154x controller. I guess this is supposed to be impossbile, since requests that are clustered will never exceed 64Kb (16 pages). Can this happen when reading is done in chuncks > 128Kb? Adri.