Date: Thu, 1 Nov 2007 18:05:57 +0200 From: "Niki Denev" <nike_d@cytexbg.com> To: "Pawel Jakub Dawidek" <pjd@freebsd.org> Cc: cvs-src@freebsd.org Subject: Re: cvs commit: src/sys/contrib/opensolaris/uts/common/fs/zfs zvol.c Message-ID: <2e77fc10711010905o77b19d08l63a6b7ed06ec2680@mail.gmail.com> In-Reply-To: <200711011104.lA1B4LeH036010@repoman.freebsd.org> References: <200711011104.lA1B4LeH036010@repoman.freebsd.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On 11/1/07, Pawel Jakub Dawidek <pjd@freebsd.org> wrote: > pjd 2007-11-01 11:04:21 UTC > > FreeBSD src repository > > Modified files: > sys/contrib/opensolaris/uts/common/fs/zfs zvol.c > Log: > Call zil_commit() (if ZIL is not disabled) after every non-read request > (BIO_WRITE and BIO_FLUSH) as it is done is Solaris. The difference is > that Solaris calls it only for sync requests, but we can't say in GEOM > is the request is sync or async, so we do it for every request. I'm just curious if this isn't this going to hurt the performance slightly, and make Zfs/Zil behave as regular journaled fs? I've also read somewehere (afair some sun developers blog) that there are some problems with writing of Zlogs that can lead to fragmentation, which they are avoiding with using spearate device for ZIL. -- Niki
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?2e77fc10711010905o77b19d08l63a6b7ed06ec2680>