Re: [PATCH] block: remove artifical max_hw_sectors cap

2014-10-21 Thread Jens Axboe
On 10/17/2014 07:12 AM, Christoph Hellwig wrote: > On Wed, Oct 01, 2014 at 02:12:58PM -0700, Christoph Hellwig wrote: >> On Wed, Oct 01, 2014 at 06:59:34PM +, Elliott, Robert (Server Storage) >> wrote: >>> One supporting example: A low limit interferes with creation of >>> full stripe writes f

Re: [PATCH] block: remove artifical max_hw_sectors cap

2014-10-17 Thread Christoph Hellwig
On Wed, Oct 01, 2014 at 02:12:58PM -0700, Christoph Hellwig wrote: > On Wed, Oct 01, 2014 at 06:59:34PM +, Elliott, Robert (Server Storage) > wrote: > > One supporting example: A low limit interferes with creation of > > full stripe writes for RAID controllers. > > Yes, both Linux mdraid and

Re: [PATCH] block: remove artifical max_hw_sectors cap

2014-10-01 Thread Christoph Hellwig
On Wed, Oct 01, 2014 at 06:59:34PM +, Elliott, Robert (Server Storage) wrote: > One supporting example: A low limit interferes with creation of > full stripe writes for RAID controllers. Yes, both Linux mdraid and parity raids are often crippled by the default. The mdadm default of 512kb for

RE: [PATCH] block: remove artifical max_hw_sectors cap

2014-10-01 Thread Elliott, Robert (Server Storage)
uang > Subject: Re: [PATCH] block: remove artifical max_hw_sectors cap > > As we still haven't made any progress on this let me explain why > the limit does not make sense: It only applies to _FS request, > which basically have three use cases: > > - metadata I/O. Ge

Re: [PATCH] block: remove artifical max_hw_sectors cap

2014-10-01 Thread Christoph Hellwig
As we still haven't made any progress on this let me explain why the limit does not make sense: It only applies to _FS request, which basically have three use cases: - metadata I/O. Generally small enough that the limit does not matter at all. - buffered reads/writes. We already have a sel

Re: [PATCH] block: remove artifical max_hw_sectors cap

2014-09-22 Thread Christoph Hellwig
ping? On Sat, Sep 06, 2014 at 04:08:05PM -0700, Christoph Hellwig wrote: > Set max_sectors to the value the drivers provides as hardware limit by > default. Linux had proper I/O throttling for a long time and doesn't > rely on a artifically small maximum I/O size anymore. By not limiting > the I

[PATCH] block: remove artifical max_hw_sectors cap

2014-09-06 Thread Christoph Hellwig
Set max_sectors to the value the drivers provides as hardware limit by default. Linux had proper I/O throttling for a long time and doesn't rely on a artifically small maximum I/O size anymore. By not limiting the I/O size by default we remove an annoying tuning step required for most Linux insta