[Gluster-users] Is read cache a file cache or a block cache?

[Jon Heese]

Hello,

I have a two-server, two-brick (one brick per server) replicated Gluster 
3.6.2 volume, and I'm interested in the 'performance.cache-size' option 
and how that read cache works.

My volume currently stores a handful of ~500GB image files, which are 
then fed to an iSCSI daemon to serve up datastores and other 
miscellaneous iSCSI disks to servers over an iSCSI network.

I have about 14GB of unutilized (minus system cache/buffers) memory on 
the gluster servers (which are also the gluster clients, in this case) 
which I'd like to utilize to improve the read performance of this volume.

So since my files are are well over the "tens of GB" mark, I'm curious: 
Does the Gluster read cache work at the block level -- i.e. caching 
*blocks* that are likely to be read -- or does it work at the file level 
-- caching *files* that are likely to be read?  Obviously, the latter 
might work well for me, but the former is likely not very useful.

I've tried searching around for details on how this works, but short of 
diving into the code itself (which is likely beyond my skill level and 
time allowance), I haven't been able to find the answer to this question.

If I've misunderstood how any of this is supposed to work, please feel 
free to correct me.  Thanks in advance!

Regards,
Jon Heese