Re: [patch] new fifo I/O elevator that really does nothing at all

2005-04-13 Thread Jens Axboe
On Tue, Apr 12 2005, Chen, Kenneth W wrote: > Chen, Kenneth W wrote on Tuesday, April 05, 2005 5:13 PM > > Jens Axboe wrote on Tuesday, April 05, 2005 7:54 AM > > > On Tue, Mar 29 2005, Chen, Kenneth W wrote: > > > > Jens Axboe wrote on Tuesday, March 29, 2005 12:04 PM > > > > > No such promise

Re: [patch] new fifo I/O elevator that really does nothing at all

2005-04-13 Thread Jens Axboe
On Tue, Apr 12 2005, Chen, Kenneth W wrote: Chen, Kenneth W wrote on Tuesday, April 05, 2005 5:13 PM Jens Axboe wrote on Tuesday, April 05, 2005 7:54 AM On Tue, Mar 29 2005, Chen, Kenneth W wrote: Jens Axboe wrote on Tuesday, March 29, 2005 12:04 PM No such promise was ever made,

RE: [patch] new fifo I/O elevator that really does nothing at all

2005-04-12 Thread Chen, Kenneth W
Chen, Kenneth W wrote on Tuesday, April 05, 2005 5:13 PM > Jens Axboe wrote on Tuesday, April 05, 2005 7:54 AM > > On Tue, Mar 29 2005, Chen, Kenneth W wrote: > > > Jens Axboe wrote on Tuesday, March 29, 2005 12:04 PM > > > > No such promise was ever made, noop just means it does 'basically > > >

RE: [patch] new fifo I/O elevator that really does nothing at all

2005-04-12 Thread Chen, Kenneth W
Chen, Kenneth W wrote on Tuesday, April 05, 2005 5:13 PM Jens Axboe wrote on Tuesday, April 05, 2005 7:54 AM On Tue, Mar 29 2005, Chen, Kenneth W wrote: Jens Axboe wrote on Tuesday, March 29, 2005 12:04 PM No such promise was ever made, noop just means it does 'basically nothing'. It

RE: [patch] new fifo I/O elevator that really does nothing at all

2005-04-05 Thread Chen, Kenneth W
Jens Axboe wrote on Tuesday, April 05, 2005 7:54 AM > On Tue, Mar 29 2005, Chen, Kenneth W wrote: > > Jens Axboe wrote on Tuesday, March 29, 2005 12:04 PM > > > No such promise was ever made, noop just means it does 'basically > > > nothing'. It never meant FIFO in anyway, we cannot break the

Re: [patch] new fifo I/O elevator that really does nothing at all

2005-04-05 Thread Jens Axboe
On Tue, Mar 29 2005, Chen, Kenneth W wrote: > Jens Axboe wrote on Tuesday, March 29, 2005 12:04 PM > > No such promise was ever made, noop just means it does 'basically > > nothing'. It never meant FIFO in anyway, we cannot break the semantics > > of block layer commands just for the hell of it. >

RE: [patch] new fifo I/O elevator that really does nothing at all

2005-04-05 Thread Chen, Kenneth W
Jens Axboe wrote on Tuesday, April 05, 2005 7:54 AM On Tue, Mar 29 2005, Chen, Kenneth W wrote: Jens Axboe wrote on Tuesday, March 29, 2005 12:04 PM No such promise was ever made, noop just means it does 'basically nothing'. It never meant FIFO in anyway, we cannot break the semantics

Re: [patch] new fifo I/O elevator that really does nothing at all

2005-04-05 Thread Jens Axboe
On Tue, Mar 29 2005, Chen, Kenneth W wrote: Jens Axboe wrote on Tuesday, March 29, 2005 12:04 PM No such promise was ever made, noop just means it does 'basically nothing'. It never meant FIFO in anyway, we cannot break the semantics of block layer commands just for the hell of it.

Re: [patch] new fifo I/O elevator that really does nothing at all

2005-03-29 Thread Jens Axboe
On Tue, Mar 29 2005, Bill Davidsen wrote: > Jens Axboe wrote: > >On Mon, Mar 28 2005, Chen, Kenneth W wrote: > > > >>The noop elevator is still too fat for db transaction processing > >>workload. Since the db application already merged all blocks before > >>sending it down, the I/O presented to

Re: [patch] new fifo I/O elevator that really does nothing at all

2005-03-29 Thread Bill Davidsen
Jens Axboe wrote: On Mon, Mar 28 2005, Chen, Kenneth W wrote: The noop elevator is still too fat for db transaction processing workload. Since the db application already merged all blocks before sending it down, the I/O presented to the elevator are actually not merge-able anymore. Since I/O are

RE: [patch] new fifo I/O elevator that really does nothing at all

2005-03-29 Thread Chen, Kenneth W
Jens Axboe wrote on Tuesday, March 29, 2005 12:04 PM > No such promise was ever made, noop just means it does 'basically > nothing'. It never meant FIFO in anyway, we cannot break the semantics > of block layer commands just for the hell of it. Acknowledged and understood, will try your patch

Re: [patch] new fifo I/O elevator that really does nothing at all

2005-03-29 Thread Jens Axboe
On Tue, Mar 29 2005, Chen, Kenneth W wrote: > On Mon, Mar 28 2005, Chen, Kenneth W wrote: > > The noop elevator is still too fat for db transaction processing > > workload. Since the db application already merged all blocks before > > sending it down, the I/O presented to the elevator are

RE: [patch] new fifo I/O elevator that really does nothing at all

2005-03-29 Thread Chen, Kenneth W
On Mon, Mar 28 2005, Chen, Kenneth W wrote: > The noop elevator is still too fat for db transaction processing > workload. Since the db application already merged all blocks before > sending it down, the I/O presented to the elevator are actually not > merge-able anymore. Since I/O are also

Re: [patch] new fifo I/O elevator that really does nothing at all

2005-03-29 Thread Jens Axboe
On Mon, Mar 28 2005, Chen, Kenneth W wrote: > The noop elevator is still too fat for db transaction processing > workload. Since the db application already merged all blocks before > sending it down, the I/O presented to the elevator are actually not > merge-able anymore. Since I/O are also

Re: [patch] new fifo I/O elevator that really does nothing at all

2005-03-29 Thread Jens Axboe
On Mon, Mar 28 2005, Chen, Kenneth W wrote: The noop elevator is still too fat for db transaction processing workload. Since the db application already merged all blocks before sending it down, the I/O presented to the elevator are actually not merge-able anymore. Since I/O are also random,

RE: [patch] new fifo I/O elevator that really does nothing at all

2005-03-29 Thread Chen, Kenneth W
On Mon, Mar 28 2005, Chen, Kenneth W wrote: The noop elevator is still too fat for db transaction processing workload. Since the db application already merged all blocks before sending it down, the I/O presented to the elevator are actually not merge-able anymore. Since I/O are also random,

Re: [patch] new fifo I/O elevator that really does nothing at all

2005-03-29 Thread Jens Axboe
On Tue, Mar 29 2005, Chen, Kenneth W wrote: On Mon, Mar 28 2005, Chen, Kenneth W wrote: The noop elevator is still too fat for db transaction processing workload. Since the db application already merged all blocks before sending it down, the I/O presented to the elevator are actually not

RE: [patch] new fifo I/O elevator that really does nothing at all

2005-03-29 Thread Chen, Kenneth W
Jens Axboe wrote on Tuesday, March 29, 2005 12:04 PM No such promise was ever made, noop just means it does 'basically nothing'. It never meant FIFO in anyway, we cannot break the semantics of block layer commands just for the hell of it. Acknowledged and understood, will try your patch

Re: [patch] new fifo I/O elevator that really does nothing at all

2005-03-29 Thread Bill Davidsen
Jens Axboe wrote: On Mon, Mar 28 2005, Chen, Kenneth W wrote: The noop elevator is still too fat for db transaction processing workload. Since the db application already merged all blocks before sending it down, the I/O presented to the elevator are actually not merge-able anymore. Since I/O are

Re: [patch] new fifo I/O elevator that really does nothing at all

2005-03-29 Thread Jens Axboe
On Tue, Mar 29 2005, Bill Davidsen wrote: Jens Axboe wrote: On Mon, Mar 28 2005, Chen, Kenneth W wrote: The noop elevator is still too fat for db transaction processing workload. Since the db application already merged all blocks before sending it down, the I/O presented to the elevator