RAID Controller – PERC H740P Adapter 8GB cache

For Dell, "256MB Cache" means 256MB of battery-backed cache on the RAID card. This is the cache used by the card for I/O operations. It caches writes in this storage to re-order them for more efficient usage of your disk. The battery is there in case of power loss, the battery supplies voltage to the cache-RAM. I believe it lasts up to 2 days.

"512MB NV Cache" means non-volatile. I don't know exactly how Dell does it, but I strongly suspect it has a normal RAM-based cache. A super-capacitor on the card has enough juice to commit the cache to flash-memory in case of sudden power loss. This will survive a power-outage for a lot longer than a battery-backed cache.

1GB NV Cache just has more cache.

The amount of data you're slinging around isn't that large to multiple internal connectors is not that important.

If you trust your power environment very well, a battery-backed cache will save you some money versus the non-volatile cache option.

I've found that when I've had to tune for lower latency vs throughput, I've tuned nr_requests down from it's default (to as low as 32). The idea being smaller batches equals lower latency.

Also for read_ahead_kb I've found that for sequential reads/writes, increasing this value offers better throughput, but I've found that this option really depends on your workload and IO pattern. For example on a database system that I've recently tuned I changed this value to match a single db page size which helped to reduce read latency. Increasing or decreasing beyond this value proved to hurt performance in my case.

As for other options or settings for block device queues:

max_sectors_kb = I've set this value to match what the hardware allows for a single transfer (check the value of the max_hw_sectors_kb (RO) file in sysfs to see what's allowed)

nomerges = this lets you disable or adjust lookup logic for merging io requests. (turning this off can save you some cpu cycles, but I haven't seen any benefit when changing this for my systems, so I left it default)

rq_affinity = I haven't tried this yet, but here is the explanation behind it from the kernel docs

If this option is '1', the block layer will migrate request completions to the cpu "group" that originally submitted the request. For some workloads this provides a significant reduction in CPU cycles due to caching effects.
For storage configurations that need to maximize distribution of completion processing setting this option to '2' forces the completion to run on the requesting cpu (bypassing the "group" aggregation logic)"

scheduler = you said that you tried deadline and noop. I've tested both noop and deadline, but have found deadline win's out for the testing I've done most recently for a database server.

NOOP performed well, but for our database server I was still able to achieve better performance adjusting the deadline scheduler.

Options for deadline scheduler located under /sys/block/{sd,cciss,dm-}*/queue/iosched/ :

fifo_batch = kind of like nr_requests, but specific to the scheduler. Rule of thumb is tune this down for lower latency or up for throughput. Controls the batch size of read and write requests.

write_expire = sets the expire time for write batches default is 5000ms. Once again decrease this value decreases your write latency while increase the value increases throughput.

read_expire = sets the expire time for read batches default is 500ms. Same rules apply here.

front_merges = I tend to turn this off, and it's on by default. I don't see the need for the scheduler to waste cpu cycles trying to front merge IO requests.

writes_starved = since deadline is geared toward reads the default here is to process 2 read batches before a write batch is processed. I found the default of 2 to be good for my workload.