Re: [PATCH 1/2] HACK: ext3: mount fast even when recovering

[Adrian Hunter <adrian.hunter@nokia.com>]

Theodore Tso wrote:
> On Tue, Jul 14, 2009 at 04:46:37PM -0500, Eric Sandeen wrote:
>> (whoa, can barriers make something faster?  who woulda thunk it)
> 
> I sent this reply in response to the first Adrian's first e-mail, that
> had bogus e-mail addresses for akpm and sct, so resending it here:

Sorry about that.

> Have you actually benchmarked these patches, ideally with a fixed
> filesystem image so the two runs are done requiring exactly the same
> number of blocks to recover?  We implement ordered I/O in terms of
> doing a flush, so it would be surprising to see that a significant
> difference in times.  Also, it would be useful to do a blktrace before
> and after your patches, again with a fixed filesystem image so the
> experiment can be carefully controlled.

Yes the I/O is no faster.

The hacks just make the file system available for reading while recovery I/O
is ongoing.

Attempts to write are likely to block (even buffered I/O must wait for
locked buffers).

I will send some examples.