Date: Fri, 1 Jun 2007 15:50:25 +0900 From: "Hidetoshi Shimokawa" <simokawa@FreeBSD.ORG> To: "Matthew Jacob" <lydianconcepts@gmail.com> Cc: freebsd-scsi@freebsd.org Subject: Re: scsi_target with multiple luns Message-ID: <626eb4530705312350n53e97987sff099c3bbd5f9f3a@mail.gmail.com> In-Reply-To: <7579f7fb0705312313p5c766887s1c2e598884513d6e@mail.gmail.com> References: <86tztspdil.wl%simokawa@FreeBSD.ORG> <465F955E.7050103@samsco.org> <7579f7fb0705312147p60255cf2r9eac5d5eb8aa5236@mail.gmail.com> <626eb4530705312300n177e677cyac2e8ba69039160d@mail.gmail.com> <7579f7fb0705312313p5c766887s1c2e598884513d6e@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
OK. Now I understand that they are prototypes... Actually, sbp_targ(4) is the hardest part to lock the firewire stack. On 6/1/07, Matthew Jacob <lydianconcepts@gmail.com> wrote: > Yes. None of the extant stuff is deployable as solid solution without reworking. > > On 5/31/07, Hidetoshi Shimokawa <simokawa@freebsd.org> wrote: > > Yes, scsi_target(8) is an example. > > But the problem I described is actually a problem of targ(4) (scsi_target.c). > > The userland can do nothing about this problem. > > Or do you mean targ(4) is also an example? > > > > On 6/1/07, Matthew Jacob <lydianconcepts@gmail.com> wrote: > > > Remember that scsi_target is an example. A fine example, but an > > > example. Having a single user process that can be shot and killed, no > > > matter how multithreaded or AIO'd, is not necessarily the wisest > > > choice for building a target device. > > > > > > > > > On 5/31/07, Scott Long <scottl@samsco.org> wrote: > > > > Hidetoshi Shimokawa wrote: > > > > > I have not fully analyzed the problem but I'll describe it just for a note. > > > > > I'd like to ask maintainers of scsi_target for further analysis. > > > > > > > > > > I experiance a problem with small number(1) of simq and multiple > > > > > scsi_target(8) instances. > > > > > > > > > > As far as I understand, the following situation could occur under a fairly > > > > > heavy load. > > > > > > > > > > 1. process A send a request -> cam send to sim > > > > > 2. process B send a request -> blocked because the simq is full > > > > > 3. the request of process A is finished (in the context of process A) > > > > > 4. cam/scsi_target tries to send the request of process B. > > > > > But the mapped memory is of process A, and scsi_target send wrong > > > > > ccb to sim. > > > > > > > > > > Maybe, we should rewrite scsi_target in kernel space with GEOM support.. > > > > > > > > I'm unclear on how GEOM would fix this. Also, scsi targets aren't > > > > always DA devices. I dedicated scsi_da_target device that is backed > > > > by GEOM might be interesting, though. Even more interesting would be > > > > a direct DMA method that required no KVA mappings for the data. > > > > > > > > Scott > > > > > > > > _______________________________________________ > > > > freebsd-scsi@freebsd.org mailing list > > > > http://lists.freebsd.org/mailman/listinfo/freebsd-scsi > > > > To unsubscribe, send any mail to "freebsd-scsi-unsubscribe@freebsd.org" > > > > > > > > > > > > > > > > -- > > /\ Hidetoshi Shimokawa > > \/ simokawa@FreeBSD.ORG > > > > -- /\ Hidetoshi Shimokawa \/ simokawa@FreeBSD.ORG
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?626eb4530705312350n53e97987sff099c3bbd5f9f3a>