Re: Process Scheduling Issue using sg/libata

2007-11-18 Thread Fajun Chen
On 11/18/07, Mark Lord <[EMAIL PROTECTED]> wrote: > Fajun Chen wrote: > >.. > > I verified your program works in my system and my application works as > > well if changed accordingly. However, this change (indirect IO in sg > > term) may come at a performance c

Re: Process Scheduling Issue using sg/libata

2007-11-18 Thread Fajun Chen
On 11/18/07, Mark Lord <[EMAIL PROTECTED]> wrote: > Fajun Chen wrote: > > On 11/17/07, Mark Lord <[EMAIL PROTECTED]> wrote: > .. > >> What you probably intended to do instead, was to use mmap to just allocate > >> some page-aligned RAM, not t

Re: Process Scheduling Issue using sg/libata

2007-11-17 Thread Fajun Chen
On 11/17/07, Mark Lord <[EMAIL PROTECTED]> wrote: > Fajun Chen wrote: > > On 11/17/07, Mark Lord <[EMAIL PROTECTED]> wrote: > >> Fajun Chen wrote: > >>> On 11/16/07, Mark Lord <[EMAIL PROTECTED]> wrote: > >>>> Fajun Chen wrote: &

Re: Process Scheduling Issue using sg/libata

2007-11-17 Thread Fajun Chen
On 11/17/07, James Chapman <[EMAIL PROTECTED]> wrote: > Fajun Chen wrote: > > On 11/16/07, Tejun Heo <[EMAIL PROTECTED]> wrote: > >> Fajun Chen wrote: > >>> I use sg/libata and ata pass through for read/writes. Linux 2.6.18-rc2 > >>> and liba

Re: Process Scheduling Issue using sg/libata

2007-11-17 Thread Fajun Chen
On 11/17/07, Mark Lord <[EMAIL PROTECTED]> wrote: > Fajun Chen wrote: > > On 11/16/07, Mark Lord <[EMAIL PROTECTED]> wrote: > >> Fajun Chen wrote: > >>> Hi All, > >>> > >>> I use sg/libata and ata pass through for read/writes. Linux

Re: Process Scheduling Issue using sg/libata

2007-11-16 Thread Fajun Chen
On 11/16/07, Mark Lord <[EMAIL PROTECTED]> wrote: > Fajun Chen wrote: > > Hi All, > > > > I use sg/libata and ata pass through for read/writes. Linux 2.6.18-rc2 > > and libata version 2.00 are loaded on ARM XScale board. Under heavy > > cpu load (e.g. when

Re: Process Scheduling Issue using sg/libata

2007-11-16 Thread Fajun Chen
On 11/16/07, Tejun Heo <[EMAIL PROTECTED]> wrote: > Fajun Chen wrote: > > I use sg/libata and ata pass through for read/writes. Linux 2.6.18-rc2 > > and libata version 2.00 are loaded on ARM XScale board. Under heavy > > cpu load (e.g. when blocks per transfer/sector c

Process Scheduling Issue using sg/libata

2007-11-16 Thread Fajun Chen
Hi All, I use sg/libata and ata pass through for read/writes. Linux 2.6.18-rc2 and libata version 2.00 are loaded on ARM XScale board. Under heavy cpu load (e.g. when blocks per transfer/sector count is set to 1), I've observed that the test application can suck cpu away for long time (more than

Time Measurement in SG

2007-02-08 Thread Fajun Chen
Hi All, The command duration is measured in sg.c using jiffies_to_msecs(jiffies). The HZ set up in my ARM system is 100, so this time measurement can only provide resolution of 10ms (or +/- 5ms). Since the AT commands in sequential read mode can be as fast as about 1ms, this inaccuracy could ea