Date: Thu, 8 Nov 2007 10:56:23 +0100 From: "Ivan Voras" <ivoras@freebsd.org> To: "Scott Long" <scottl@samsco.org> Cc: freebsd-scsi@freebsd.org Subject: Re: iSCSI in 7.0 Message-ID: <9bbcef730711080156n6a914be6m6ae478ceef7c14a9@mail.gmail.com> In-Reply-To: <4732C7DC.60902@samsco.org> References: <47300ADE.5070506@mansionfamily.plus.com> <4730C8EC.7050002@mansionfamily.plus.com> <fgs8gr$2rh$1@ger.gmane.org> <4732C7DC.60902@samsco.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On 08/11/2007, Scott Long <scottl@samsco.org> wrote: > Unfortunately, the GEOM block layer is > not free of this deadlock, so this whole discussion is mostly academic > (the GEOM problem is small and very hard to trigger since it uses the > zone allocator, but problems have been observed in real-world > situations, which is a shame). Maybe not the GEOM layer itself but various GEOM classes. For example, most non-trivial classes spawn handler threads that do malloc(M_WAITOK).
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?9bbcef730711080156n6a914be6m6ae478ceef7c14a9>