From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andy Grover Subject: Re: [PATCHv2 2/5] target/user: Add global data block pool support Date: Fri, 17 Mar 2017 10:11:43 -0700 Message-ID: <2dd405f8-9f5b-405d-e744-9ee8bac77686@redhat.com> References: <1488962743-17028-1-git-send-email-lixiubo@cmss.chinamobile.com> <1488962743-17028-3-git-send-email-lixiubo@cmss.chinamobile.com> <3b1ce412-6072-fda1-3002-220cf8fbf34f@redhat.com>

Mime-Version: 1.0 Content-Type: text/plain; charset=windows-1252; format=flowed Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: Sender: owner-linux-mm@kvack.org To: Xiubo Li , nab@linux-iscsi.org, mchristi@redhat.com Cc: shli@kernel.org, sheng@yasker.org, linux-scsi@vger.kernel.org, target-devel@vger.kernel.org, namei.unix@gmail.com, linux-mm@kvack.org List-Id: linux-scsi@vger.kernel.org On 03/17/2017 01:04 AM, Xiubo Li wrote: > [...] >> These days what I have gotten is that the unmap_mapping_range() could >> be used. >> At the same time I have deep into the mm code and fixed the double >> usage of >> the data blocks and possible page fault call trace bugs mentioned above. >> >> Following is the V3 patch. I have test this using 4 targets & fio for >> about 2 days, so >> far so good. >> >> I'm still testing this using more complex test case. >> > I have test it the whole day today: > - using 4 targets > - setting TCMU_GLOBAL_MAX_BLOCKS = [512 1K 1M 1G 2G] > - each target here needs more than 450 blocks when running > - fio: -iodepth [1 2 4 8 16] -thread -rw=[read write] -bs=[1K 2K 3K 5K > 7K 16K 64K 1M] -size=20G -numjobs=10 -runtime=1000 ... Hi Xiubo, V3 is sounding very good. I look forward to reviewing it after it is posted. Thanks -- Regards -- Andy -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: email@kvack.org