xfs
[Top] [All Lists]

Re: XFS: Fine-tuning for checks before the function call "xfs_qm_dqrele"

To: Dave Chinner <david@xxxxxxxxxxxxx>
Subject: Re: XFS: Fine-tuning for checks before the function call "xfs_qm_dqrele"?
From: SF Markus Elfring <elfring@xxxxxxxxxxxxxxxxxxxxx>
Date: Wed, 01 Jul 2015 09:50:00 +0200
Cc: xfs@xxxxxxxxxxx, LKML <linux-kernel@xxxxxxxxxxxxxxx>, kernel-janitors@xxxxxxxxxxxxxxx, Julia Lawall <julia.lawall@xxxxxxx>
Delivered-to: xfs@xxxxxxxxxxx
In-reply-to: <20150629214355.GE7943@dastard>
References: <530CD2C4.4050903@xxxxxxxxxxxxxxxxxxxxx> <alpine.DEB.2.10.1402251840450.7035@hadrien> <530CF8FF.8080600@xxxxxxxxxxxxxxxxxxxxx> <alpine.DEB.2.02.1402252117150.2047@xxxxxxxxxxxxxxxxxxxxxxx> <530DD06F.4090703@xxxxxxxxxxxxxxxxxxxxx> <alpine.DEB.2.02.1402262129250.2221@xxxxxxxxxxxxxxxxxxxxxxx> <5317A59D.4@xxxxxxxxxxxxxxxxxxxxx> <5479F823.60900@xxxxxxxxxxxxxxxxxxxxx> <20141130230904.GF16151@dastard> <558D1833.3080009@xxxxxxxxxxxxxxxxxxxxx> <20150629214355.GE7943@dastard>
User-agent: Mozilla/5.0 (X11; Linux x86_64; rv:31.0) Gecko/20100101 Thunderbird/31.7.0
> xfs_dqrele_inode() gets called on every inode in the inode cache,
> and this change results in a cacheline in every inode being dirtied
> even if they don't have dquots attached. Given the inode cache can
> hold tens to hundreds of millions of inodes on large machines, we
> don't want to dirty any cachelines we don't need to while walking
> the inode cache and releasing dquots...

Would it make sense to annotate checks before such function calls
as "LIKELY"?

Regards,
Markus

<Prev in Thread] Current Thread [Next in Thread>