From mboxrd@z Thu Jan 1 00:00:00 1970 From: Sagi Grimberg Subject: Re: iSER initiator in 4.5 is unhappy.. Date: Thu, 7 Apr 2016 10:14:17 +0300 Message-ID: <570608C9.1070805@grimberg.me> References: <20160404134656.GA30269@infradead.org> <5702A46F.5070109@grimberg.me> <5702A6AC.9020008@grimberg.me> <20160404225831.GA6725@infradead.org> <57037D8E.4030506@grimberg.me> <20160405094339.GA1622@infradead.org> <570548AB.4090802@grimberg.me> <20160406231658.GB11588@infradead.org> Mime-Version: 1.0 Content-Type: text/plain; charset=windows-1252; format=flowed Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <20160406231658.GB11588-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org> Sender: linux-rdma-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org To: Christoph Hellwig Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org List-Id: linux-rdma@vger.kernel.org >> So this scatterlist seems perfectly fine (no gaps). The only thing I >> can think of is that we don't have enough space reserved, but I counted >> 127 pages in the scatterlist when iser reserves 128 (by default). >> >> Just in case I mis-counted, can you (or Max) try with the below >> patch: > > This works fine for me, but I wonder if the miscounting is in the > block layer? We communicate the "max_pages" via sg_tablesize and max_hw_sectors. iSER communicates (or at least supposed to) sg_tablesize=128 and max_sectors=1024 to scsi (which sets the block queues attributes), that should be sufficient for handling all the incoming IO. Unless we didn't account for the first-page offset and the reminder coming at the last segment (which results in an extra page). The patch should fix the problem, however in this particular sg list I don't see the violation (counted 127 pages)... -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org More majordomo info at http://vger.kernel.org/majordomo-info.html