From mboxrd@z Thu Jan 1 00:00:00 1970 Content-Type: multipart/mixed; boundary="===============3605987981406636067==" MIME-Version: 1.0 From: Kumaraparameshwaran Rathnavel Subject: Re: [SPDK] BDEV & VBDEV Date: Sat, 22 Oct 2016 10:21:48 +0530 Message-ID: In-Reply-To: b3ba8aa6-c7d4-218b-c24b-76145ac2096c@intel.com List-ID: To: spdk@lists.01.org --===============3605987981406636067== Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable My doubt is that we have malloc drives as virtual subsystem . So from NVMe = initiator can I send read n write commands and does the current implementat= ion of SPDK handle the commands and do the the I/O operations = Thanking you = Param Sent from my iPhone > On 21-Oct-2016, at 11:54 PM, Daniel Verkamp = wrote: > = >> On 10/21/2016 10:59 AM, Kumaraparameshwaran Rathnavel wrote: >> Thanks Daniel. So in the virtual subsystem the example in the tree is m= alloc devices. So instead of that I can create my own subsystem like mallo= c devices right. Is there support for virtual subsystem from end to end . S= ay that when I get a read command from kernel initiator the SPDK reads the = data n then sends it back to the initiator >> = >> Thanking you, >> Param > = > The nvmf_tgt "Virtual" mode (use bdevs as namespaces) is an alternative t= o "Direct" mode (expose hardware NVMe device directly). It is unrelated to= the virtual blockdev layering mechanism. Any blockdev (regular bdev or vb= dev) can be used as a namespace in nvmf_tgt Virtual mode. > = > I'm not sure if I understand the rest of the question - can you elaborate= on what you are trying to accomplish? > = > Thanks, > -- Daniel > _______________________________________________ > SPDK mailing list > SPDK(a)lists.01.org > https://lists.01.org/mailman/listinfo/spdk --===============3605987981406636067==--