Re: [dm-devel] [RFC][PATCH] dm-cache: block level disk cache target for device mapper

On Thursday 30 November 2006 17:24, Eric Van Hensbergen wrote:
On 11/30/06, Jens Wilke <jens.wilke@xxxxxxxxxx> wrote:
On Monday 27 November 2006 19:26, Eric Van Hensbergen wrote:

If this is intended to speed up remote disks, is it possible that the cache content
can be paged out on local disks in low-mem situations?


The main intent was to use local disks as cache to offload centralized
remote disks. The logic was that most systems have local disks, if
only for swap -- so why not use them as a cache to help offload
centralized storage. While the in-memory page cache works perfectly
fine in certain situations -- we were dealing with workloads in which
the in-memory page-cache wasn't sufficient to hold all the data.

I derived from the code that the cache is actually another block device
and not memory. Maybe you should give a little more description and
a sample 'dmsetup create' statement.

There are also some additional possibilities we've thought through and
have been playing with including allowing the local disk cache to be
persistent across reboots (with varying validation schemes).

Yes, I like the idea. It would be also possible to use NV-Ram
as write back cache, for example in notebooks, to avoid
disk spin-ups or to improve transaction performance in
enterprise applications.

Maybe it would also make sense to prefill the cache contents
on startup with a bulk I/O request?

Comments on the code:

- The data of the write back cache should be flushed on suspend and not
in the destructor.
- You don't keep track of I/O on the fly to the cache that is mapped
directly in cache_hit(). How do you make sure that this I/O is completed
before you replace a cache block?
- The cache block index is hashed, this means the cache data blocks are not
clustered. I don't think you can solve this problem with a proper hash function.
Perhaps you should consider a (B-)Tree structure for that.

Best,

Jens
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Relevant Pages

  • Re: Tips sought for optimizing 10.4.10s performance
    ... upgrade to disks with those speeds. ... Most desktop drives have been 7200 RPM, ... 7200 RPM disks have only had 2MB of cache. ... a CPU upgrade, or do I just get a new Mac. ...
    (comp.sys.mac.system)
  • Re: Tips sought for optimizing 10.4.10s performance
    ... If you're doing graphics or video editing, even more RAM. ... upgrade to disks with those speeds. ... 7200 RPM disks have only had 2MB of cache. ...
    (comp.sys.mac.system)
  • Re: Improvements to fsck performance in -current ...?
    ... >> write cache enabled. ... > Unfortunately, IDE disks do not permit disconnected writes, due ... Unfortunately SCSI drives all seem to ship with the WCE bit set, ...
    (freebsd-current)
  • RE: Write Caching
    ... If Node loses both paths to the disks I would venture to say you would see ... Your data in cache is still safe because it is held on the storage ... I have seen FTDISK events being reported even for SAN volumes. ... >> the NODES Raid Controller cards has no way to update. ...
    (microsoft.public.windows.server.clustering)
  • Re: RAID - config Question
    ... SQL Server does not need read cache on the controller since it does it's own ... Since you are doing so much tempdb and log activity you want to make ... >> for the data files or take one or two for tempdb and the others for the ... >>> If I create 2 seperate Volumes, Each volume would have 3 disks. ...
    (microsoft.public.sqlserver.server)