Date: Sat, 25 Oct 2014 11:38:31 +0200 From: Harald Schmalzbauer <h.schmalzbauer@omnilan.de> To: "Kenneth D. Merry" <ken@FreeBSD.ORG> Cc: FreeBSD Stable <freebsd-stable@FreeBSD.ORG> Subject: Re: sa(4) 9.2->10.1, nsa0.0: request ptr 0x803135040 is not on a page boundary; cannot split request Message-ID: <544B6F97.7010808@omnilan.de> In-Reply-To: <20141024230725.GA50845@mithlond.kdm.org> References: <54494E92.5010007@omnilan.de> <20141024230725.GA50845@mithlond.kdm.org>
next in thread | previous in thread | raw e-mail | index | archive | help
[-- Attachment #1 --] Bezüglich Kenneth D. Merry's Nachricht vom 25.10.2014 01:07 (localtime): … >> When btape(8) starts to read the label, the _subject's error is reported_: >> *nsa0.0: request ptr 0x803135040 is not on a page boundary; cannot split >> request* > What blocksize are you using with btape(8)? > > What kind of controller are you using? Hello and thanks a lot for your very avaluable explanations! had no block size set in the bacula(-sd) configuration. Btape(8) consults the same config file, so I thought it's probably bacula's default of 64512, but if I correctly understood your explanation later, it's more likely it's starting with kern.cam.sa.0.maxio, which doesn't work because of the non-page-aligned address!?! My LTO4 is connected via a mps(4), LSISAS2008. > The reason you get that error message is that the sa(4) driver goes through > physio(9) to get buffers from userland into the kernel. physio(9) relies > on the vmapbuf()/vunmapbuf() routines to map buffers in and out of the > kernel. > > vmapbuf() operates with a page granularity. The address to be mapped has > to start on a page boundary. It also uses kernel virtual address segments > that are MAXPHYS in size. On x86 boxes at least, MAXPHYS is 128KB. So is it correct that kern.cam.sa.0.maxio = MAXPHYS? > So if you use a blocksize of 128KB, but pass in a pointer that doesn't > start on a page boundary, vmapbuf() will have to map 33 pages instead of > 32. In your case, it will have to start at page address 0x803135000, and > will need 33 4KB pages, which is greater than 128KB. > > This behavior obviously isn't very user friendly. > > If you want to avoid the problem, try setting your blocksize in Bacula to > 4K less than what is reported in kern.cam.sa.0.maxio. If it's 131072, then > set the blocksize to 126976. > > Another way to avoid the problem is to increase MAXPHYS. Increasing it > beyond kern.cam.sa.0.cpi_maxio won't help anything. If you increase > it too much, you can run into other problems. > > That said, though, you can probably bump it to 512K without much worry. > Put this in your kernel config file and recompile/reinstall your kernel: > > options MAXPHYS="(512*1024)" > options DFLTPHYS="(512*1024)" > > The same thing applies, though -- you'll want to set your blocksize to 1 > page less than kern.cam.sa.0.maxio, since Bacula isn't using page-aligned > buffers. Ah, ok – “unaligned buffers”. I think I understood the reason for the message. That's enough for me for now; probably btape(8) attempts acessing the tape with kern.cam.sa.0.maxio, not bacula's default of 64512. What I haven't understood entirely is DFLTPHYS and the whole physio(9) chain down to the magnetic tape :-( But at least now I have an idea and your advise to increase DFLTPHYS, so I did that and will do some tests. I knew of that options before, but I didn't want to tune anything I can't estimate it's impact… Thanks a lot, -Harry [-- Attachment #2 --] -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.18 (FreeBSD) iEYEARECAAYFAlRLb50ACgkQLDqVQ9VXb8inQwCgi8KogN2qPCZFLG1p/8ZxVmxE 33IAnibzVjZ0AQ/t/AXdl07tXIClikYs =xN/T -----END PGP SIGNATURE-----
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?544B6F97.7010808>