Re: [PATCH 3/8] writeback: switch to per-bdi threads for flushing data

[Jens Axboe <jens.axboe@oracle.com>]

On Tue, Sep 08 2009, Daniel Walker wrote:
> On Tue, 2009-09-08 at 11:23 +0200, Jens Axboe wrote:
> > This gets rid of pdflush for bdi writeout and kupdated style cleaning.
> > pdflush writeout suffers from lack of locality and also requires more
> > threads to handle the same workload, since it has to work in a
> > non-blocking fashion against each queue. This also introduces lumpy
> > behaviour and potential request starvation, since pdflush can be starved
> > for queue access if others are accessing it. A sample ffsb workload that
> > does random writes to files is about 8% faster here on a simple SATA drive
> > during the benchmark phase. File layout also seems a LOT more smooth in
> > vmstat:
> 
> 
> This patch has a checkpatch error, and couple of warnings.. Here's one
> of the warnings which I though was concerning..
> 
> WARNING: trailing semicolon indicates no statements, indent implies
> otherwise
> #388: FILE: fs/fs-writeback.c:177:
> +               } else if (wb->task);
> +                       wake_up_process(wb->task);
> 
> I suppose that could be a defect .. btw, patch 7 of 8 also has a few
> trivial warnings.

Oops yes, that was added between -v18 and -19 with the moving of that
code. Will fix that up, thanks for spotting that.

I'll check the series for checkpatch cleanliness. I did at some point,
but that was a few revisions ago.

-- 
Jens Axboe