Re: [PATCH 0/1] aoe: ensure we initialise the request_queue correctly

On Tue, 01 September 2009 Ed Cashin <ecashin@xxxxxxxxxx> wrote:

On Sat Aug 29 09:43:54 EDT 2009, bonbons@xxxxxxxxxxxxxxxxx wrote:
...
I finished bisecting the NULL object and ended up at this commit:
cd43e26f071524647e660706b784ebcbefbd2e44

block: Expose stacked device queues in sysfs

Currently stacking devices do not have a queue directory in sysfs.
However, many of the I/O characteristics like sector size, maximum
request size, etc. are queue properties.

This patch enables the queue directory for MD/DM devices. The
elevator code has been modified to deal with queues that do not
have an I/O scheduler.

Signed-off-by: Martin K. Petersen <martin.petersen@xxxxxxxxxx>
Signed-off-by: Jens Axboe <jens.axboe@xxxxxxxxxx>


This seems to generate /sys/block/$device/queue and its contents for
everyone who is using queues, not just for those queues that have a
non-NULL queue->request_fn.

Thanks much for doing that. It makes sense that this change would
have caused it to suddenly matter whether the unused queue is
initialized.

The patch looks fine to me.

Would it make sense to fine-tune the values reported by sys-fs in the
queue details so they match with the AoE device (as a separate
enhancement patch)?

Sure the queue itself won't use them, but some user-space tools might
be interested in this data.

I've not checked what information is provided by AoE protocol or can
be deducted from interface MTU.

Bruno
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Relevant Pages

  • Re: PATCH: ide: ide-disk freeze support for hdaps
    ... the freeze feature is really only useful to an niche of ... the way (the timeout is mainly there to ensure that the queue isn't ... sysfs seems the norm, and is more intuitive. ... send the line "unsubscribe linux-kernel" in ...
    (Linux-Kernel)
  • Re: [PATCH 1/10] cxgb3 - FW versioning
    ... We'd love it if ethtool ... were to be extended to provide good support for multi queue devices. ... We could alternatively use a sysfs attribute. ...
    (Linux-Kernel)
  • Pending patch
    ... Is this patch (sysfs: remove useless test from sysfs_merge_group) still ... in your queue? ... I ask because you have already merged other patches that were sent out ...
    (Linux-Kernel)
  • Re: [PATCH] PPC64 iSeries: dont share request queues in viocd
    ... >>This patch fixes the virtual cdrom driver to not share a single request ... Sharing the queue causes an oops if you remove the module and more ... It is a relationship that I don't think sysfs can capture very well: ... send the line "unsubscribe linux-kernel" in ...
    (Linux-Kernel)
  • Re: [announce] split-up -rt patch-queue, v2.6.22.1-rt2
    ... split-up patch queue of the -rt kernel patch. ... the -rt patch-queue consists of 374 patches at the moment, ...
    (Linux-Kernel)