ACK / APPLIED[artful]: [A/Z/X][PATCH] fs: aio: fix the increment of aio-nr and counting against aio-max-nr

Seth Forshee seth.forshee at canonical.com
Thu Sep 21 17:36:00 UTC 2017


On Wed, Sep 20, 2017 at 11:55:28AM -0300, Mauricio Faria de Oliveira wrote:
> BugLink: http://bugs.launchpad.net/bugs/1718397
> 
> Currently, aio-nr is incremented in steps of 'num_possible_cpus() * 8'
> for io_setup(nr_events, ..) with 'nr_events < num_possible_cpus() * 4':
> 
>     ioctx_alloc()
>     ...
>         nr_events = max(nr_events, num_possible_cpus() * 4);
>         nr_events *= 2;
>     ...
>         ctx->max_reqs = nr_events;
>     ...
>         aio_nr += ctx->max_reqs;
>     ....
> 
> This limits the number of aio contexts actually available to much less
> than aio-max-nr, and is increasingly worse with greater number of CPUs.
> 
> For example, with 64 CPUs, only 256 aio contexts are actually available
> (with aio-max-nr = 65536) because the increment is 512 in that scenario.
> 
> Note: 65536 [max aio contexts] / (64*4*2) [increment per aio context]
> is 128, but make it 256 (double) as counting against 'aio-max-nr * 2':
> 
>     ioctx_alloc()
>     ...
>         if (aio_nr + nr_events > (aio_max_nr * 2UL) ||
>         ...
>             goto err_ctx;
>     ...
> 
> This patch uses the original value of nr_events (from userspace) to
> increment aio-nr and count against aio-max-nr, which resolves those.
> 
> Signed-off-by: Mauricio Faria de Oliveira <mauricfo at linux.vnet.ibm.com>
> Reported-by: Lekshmi C. Pillai <lekshmi.cpillai at in.ibm.com>
> Tested-by: Lekshmi C. Pillai <lekshmi.cpillai at in.ibm.com>
> Tested-by: Paul Nguyen <nguyenp at us.ibm.com>
> Reviewed-by: Jeff Moyer <jmoyer at redhat.com>
> Signed-off-by: Benjamin LaHaise <bcrl at kvack.org>
> (cherry picked from commit 2a8a98673c13cb2a61a6476153acf8344adfa992)
> Signed-off-by: Mauricio Faria de Oliveira <mauricfo at linux.vnet.ibm.com>

Upstream cherry pick, positive test results.

Acked-by: Seth Forshee <seth.forshee at canonical.com>

Applied to artful/master-next, thanks.




More information about the kernel-team mailing list