Hi ...,<br><br>We have a requirement where high throughput and high-availability, both are essential.<br><br>The storage will be used by animation artists and a render-farm with around 300 render nodes.<br><br><div>--------------------------------------------------------------------------------------------------------------------------<br>
1.
When a rendering job is fired, we can expect at least 50 render nodes
to simultaneously hit the storage to read a single scene (information)
file. Now, this file could be anywhere in the range of 100MB to 2GB in
size. <br>
<br>2. Once the render is complete, each of this render node would
write the generated image file back to the storage. The image files
would be of 10 - 50MB is size. Here again, we can expect most of the
renders to finish almost simultaneously, usually within a few seconds of
each other.<br>
<br>3. The 100MB - 2GB scene will almost always be written to by a
single artist i.e. no 2 artists would be working on the same scene file
simultaneously.<br><br>4. The 10 - 50MB image files, from different
rendering activities, would then be read by another set of nodes, for
something called 'compositing'. Compositing, gives you the final 'shot'
output.<br>
------------------------------------------------------------------------------------------------------------------------<br><br><strong>We are trying to cater to both large file (100MB - 2GB) read speed and small file (10-50MB) read+write speed.</strong><br>
<br>For this we, were thinking of having a mix of RAID 5 Volumes and Individual Hard Disks. <br><br>We
are looking at having 6 Servers, with 24 Disk JBODs each, in a
'replicate' configuration i.e. 3+3 Servers. Out of the 24 Disk in each
JBOD, 1 - 9 would be used for a RAID5 Volume and 10 - 24 as individual
disks. <br><strong><br>The RAID 5 Volume would hold the 100MB to 2GB Scene Files while the individual disks would hold the rendered 10 - 50MB images.<br>Can
we use the Switch Scheduler
(<a href="http://gluster.org/community/documentation/index.php/Translators/cluster#Switch_Scheduler">http://gluster.org/community/documentation/index.php/Translators/cluster#Switch_Scheduler</a>)
for this?</strong><br><br>OR is there a better approach.<br><br>Regards,<br><br><br>Indivar Nair<br></div>