RAID5 Patches

Notes about RAID5 Internals

Structures

In Linux, RAID5 handles all incoming requests by small units called stripes. A stripe is a set of blocks taken from all disks at the same position. A block is defined as unit of PAGE_SIZE bytes.

For example, suppose you have 3 disks and have specified 8K chunksize. Then, internally, RAID5 will look as follows:

	S0	S8	S32	S40
Disk1	#0	#8	#32	#40
Disk2	#16	#24	#48	#56
Disk3	P0	P8	P32	P40

where:

• Sn -- Number of internal stripe
• #n -- An offset in sectors (512bytes)
• Pn -- Parity for other blocks in the stripe (actually, it floats among disks)

As you can see, 8K chunksize means 2 contiguous blocks.

Logic

make_request() goes through an incoming request, breaking it into blocks (PAGE_SIZE) and handling them separately. given bio with bi_sector = 0 bi_size = 24K and array described above, make_request() would handle #0,#8 and #16.

For every block, add_stripe_bio() and handle_stripe() are called.

add_stripe_bio() the intention is to add bio to a given stripe. Later, in handle_stripe(), we will be able to use bio and its data for serving requests.

handle_stripe() is a core of raid5 (discussed in the next section).

handle_stripe()

The routine works with a stripe. It checks what should be done, learns the current state of a stripe in the internal cache, makes decision what I/O is needed to satisfy user requests, and does recovery.

For example, if a user wants to write block #0 (8 sectors starting from sector 0). RAID5's responsibility is to store new data and update parity P0. There are a few possibilities here:

1. delay serving until the data for block #16 is ready -- probably the user will want to write #16 very soon?

1. read #16, make a new parity P0; write #0 and P0

1. read P0, roll back the old #0 from P0 (so it looks like we did parity with #0) and re-compute parity with the new #0

The first way looks like the better option because it does not require a very expensive read, but the problem is that user may need to write only #0 and not #16 in near future.

Also, the queue can get unplugged meaning that user wants all requests to complete (unfortunately, in current block layer there is no way to specify which exact request user is interested in, so any completion interest means immediate serving of the whole queue).

Problems

Short list of the problem in raid5 we met in Thumper project:

* order of handling isn't good for large requests

  As handle_stripe() goes in logical block order, it
  handles S0, then S8, then again S0 and S8. After the first touch
  S0 is left with block #0 uptodate, while #16 and P0 are not. Thus
  if the stripe is forced for completion, we'd need to read block
  #16 or P0 to get full uptodate stripe. Such reads hurt throughput
  almost to death. If just a single process writes, then things are
  OK, because nobody unplugs the queue and there is no requests to
  force completion of pending request. But the more writers, the
  often queue unplug happens and the often pending requests are forced
  for completion. Take into account that in reallity we use large
  chuck size (128K, 256K and even larger), hence tons of non-uptodate
  stripes in the cache and tons of reads in the end.

* memcpy() is top consumer

  all requests go via internal cache. on dual-core 2way opteron
  it takes up to 30-33% of CPU doing 1GB/s write

* small requests

  to fill I/O pipes and reach good throughput we need quite large
  I/O requests. Lustre does this using bio subsystem on 2.6. but
  as it was mentioned, raid5 handles all blocks separately and
  issues for every block separate I/O (bio). this is solved partial
  by I/O scheduler that merges small requests into bigger ones, but
  due to nature of block subsystem, any process that wants I/O to
  get completed, unplug queue and we can get many small requests
  in the pipe.

We developed patches that address described problems. You can find them in ftp://ftp.clusterfs.com/pub/people/alex/raid5