Re: performance: use pread instead of lseek+read - Mailing list pgsql-patches

From Tom Lane
Subject Re: performance: use pread instead of lseek+read
Date
Msg-id 6248.1046130083@sss.pgh.pa.us
Whole thread Raw
In response to Re: performance: use pread instead of lseek+read  (Manfred Spraul <manfred@colorfullife.com>)
Responses Re: performance: use pread instead of lseek+read  (Manfred Spraul <manfred@colorfullife.com>)
List pgsql-patches
Manfred Spraul <manfred@colorfullife.com> writes:
> Tom Lane wrote:
>> It seems unlikely to me that eliminating lseek on some platforms would
>> be worth the hassle of maintaining two code paths.  lseek is mighty
>> cheap as system calls go.
>>
> It was considered expensive enough to write a syscall avoidance layer
> that caches the file pointer and skips lseek if fpos==offset.

You're missing the point: that layer is mostly there to ensure that we
don't foul up the kernel's readahead recognition for sequential fetches.
It's nice that Linux doesn't care, but Linux is not the only platform
we worry about.

            regards, tom lane

pgsql-patches by date:

Previous
From: Manfred Spraul
Date:
Subject: Re: performance: use pread instead of lseek+read
Next
From: Manfred Spraul
Date:
Subject: Re: performance: use pread instead of lseek+read