[OmniOS-discuss] L2ARC actual size and zpool iostat -v output discrepancy?

[wuffers]

On Wed, Feb 12, 2014 at 10:55 AM, Saso Kiselkov <skiselkov.ml at gmail.com>wrote:

Can you also try running this piece of dtrace on the machine? I have a
> hypothesis that I'd like to test:
>
> dtrace -n 'fbt::l2arc_evict:entry{printf("dev=%p; l2ad_first=%d",
> args[0], args[0]->l2ad_first)}'
>
> (let it run for about 5-10s and post the output)
>


Output from the above dtrace:

dtrace: description 'fbt::l2arc_evict:entry' matched 1 probe
CPU     ID                    FUNCTION:NAME
 12  40955                l2arc_evict:entry dev=ffffff43782a8240;
l2ad_first=1
 12  40955                l2arc_evict:entry dev=ffffff4377e25058;
l2ad_first=1
 12  40955                l2arc_evict:entry dev=ffffff4377e25148;
l2ad_first=1
 14  40955                l2arc_evict:entry dev=ffffff432153be68;
l2ad_first=1
  0  40955                l2arc_evict:entry dev=ffffff43782a8240;
l2ad_first=1
  5  40955                l2arc_evict:entry dev=ffffff4377e25058;
l2ad_first=1
  5  40955                l2arc_evict:entry dev=ffffff4377e25148;
l2ad_first=1
  1  40955                l2arc_evict:entry dev=ffffff432153be68;
l2ad_first=1
 19  40955                l2arc_evict:entry dev=ffffff43782a8240;
l2ad_first=1
 21  40955                l2arc_evict:entry dev=ffffff4377e25058;
l2ad_first=1
 23  40955                l2arc_evict:entry dev=ffffff4377e25148;
l2ad_first=1
  0  40955                l2arc_evict:entry dev=ffffff432153be68;
l2ad_first=1
 11  40955                l2arc_evict:entry dev=ffffff43782a8240;
l2ad_first=1
 13  40955                l2arc_evict:entry dev=ffffff4377e25058;
l2ad_first=1
 14  40955                l2arc_evict:entry dev=ffffff4377e25148;
l2ad_first=1
 15  40955                l2arc_evict:entry dev=ffffff432153be68;
l2ad_first=1
 19  40955                l2arc_evict:entry dev=ffffff43782a8240;
l2ad_first=1
  1  40955                l2arc_evict:entry dev=ffffff4377e25058;
l2ad_first=1
  3  40955                l2arc_evict:entry dev=ffffff4377e25148;
l2ad_first=1
  3  40955                l2arc_evict:entry dev=ffffff432153be68;
l2ad_first=1
  3  40955                l2arc_evict:entry dev=ffffff43782a8240;
l2ad_first=1
  3  40955                l2arc_evict:entry dev=ffffff4377e25058;
l2ad_first=1
 16  40955                l2arc_evict:entry dev=ffffff4377e25148;
l2ad_first=1
  3  40955                l2arc_evict:entry dev=ffffff432153be68;
l2ad_first=1
 13  40955                l2arc_evict:entry dev=ffffff43782a8240;
l2ad_first=1
  3  40955                l2arc_evict:entry dev=ffffff4377e25058;
l2ad_first=1
  0  40955                l2arc_evict:entry dev=ffffff4377e25148;
l2ad_first=1
 21  40955                l2arc_evict:entry dev=ffffff432153be68;
l2ad_first=1
  2  40955                l2arc_evict:entry dev=ffffff43782a8240;
l2ad_first=1
 18  40955                l2arc_evict:entry dev=ffffff4377e25058;
l2ad_first=1
  1  40955                l2arc_evict:entry dev=ffffff4377e25148;
l2ad_first=1
  1  40955                l2arc_evict:entry dev=ffffff432153be68;
l2ad_first=1
  1  40955                l2arc_evict:entry dev=ffffff43782a8240;
l2ad_first=1
  2  40955                l2arc_evict:entry dev=ffffff4377e25058;
l2ad_first=1
  2  40955                l2arc_evict:entry dev=ffffff4377e25148;
l2ad_first=1
  2  40955                l2arc_evict:entry dev=ffffff432153be68;
l2ad_first=1
 20  40955                l2arc_evict:entry dev=ffffff43782a8240;
l2ad_first=1
  0  40955                l2arc_evict:entry dev=ffffff4377e25058;
l2ad_first=1
  0  40955                l2arc_evict:entry dev=ffffff4377e25148;
l2ad_first=1
  0  40955                l2arc_evict:entry dev=ffffff432153be68;
l2ad_first=1
  1  40955                l2arc_evict:entry dev=ffffff43782a8240;
l2ad_first=1
  2  40955                l2arc_evict:entry dev=ffffff4377e25058;
l2ad_first=1
  0  40955                l2arc_evict:entry dev=ffffff4377e25148;
l2ad_first=1
  8  40955                l2arc_evict:entry dev=ffffff432153be68;
l2ad_first=1
  1  40955                l2arc_evict:entry dev=ffffff43782a8240;
l2ad_first=1
  4  40955                l2arc_evict:entry dev=ffffff4377e25058;
l2ad_first=1
 14  40955                l2arc_evict:entry dev=ffffff4377e25148;
l2ad_first=1
 12  40955                l2arc_evict:entry dev=ffffff432153be68;
l2ad_first=1
 21  40955                l2arc_evict:entry dev=ffffff43782a8240;
l2ad_first=1

And on your other question:

> What's the block size of your SSDs and the average recordsize of the
> data on them?

I'm actually not sure what you're asking about.. the recordsize on the pool
itself? It's 128K. I have different volblocksize on various volumes. Or
information about the SSD itself?

* /dev/rdsk/c2t500117310015D579d0 partition map
*
* Dimensions:
*     512 bytes/sector
* 781422768 sectors
* 781422701 accessible sectors
*
* Flags:
*   1: unmountable
*  10: read-only
*
* Unallocated space:
*       First     Sector    Last
*       Sector     Count    Sector
*          34       222       255
*
*                          First     Sector    Last
* Partition  Tag  Flags    Sector     Count    Sector  Mount Directory
       0      4    00        256 781406095 781406350
       8     11    00  781406351     16384 781422734
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://omniosce.org/ml-archive/attachments/20140212/510cf551/attachment-0001.html>