Date: Thu, 11 Jul 2002 08:06:24 -0700 (PDT) From: Matthew Dillon <dillon@apollo.backplane.com> To: Sheldon Hearn <sheldonh@starjuice.net> Cc: cvs-committers@FreeBSD.ORG, cvs-all@FreeBSD.ORG Subject: Re: cvs commit: src/sys/kern vfs_bio.c vfs_cluster.c vfs_subr.c src/sys/nfsclient nfs_bio.c src/sys/nfsserver nfs_serv.c src/sys/sys buf.h vnode.h Message-ID: <200207111506.g6BF6O61080709@apollo.backplane.com> References: <200207101702.g6AH2Xtl000528@freefall.freebsd.org> <20020711071201.GD25502@starjuice.net>
next in thread | previous in thread | raw e-mail | index | archive | help
:> vnode->v_dirtyblkhd is now perfectly sorted, making
:> fsync/sync/filesystem syncer operate more efficiently.
:
:This is very good for MTAs, yes? Do you have any informal stats that
:suggest what kind of improvement this offers?
:
:Ciao,
:Sheldon.
No. The difference will not be noticeable because most of the
common cases were already covered by the code that the splay tree
replaced, and splay tree will have the same or slightly more overhead
then the hash table that was there before. And the mail messages
handled by MTAs are typically too small for it to matter anyway.
The advantages will come in follow-up work... the ability to do partial
fsyncs, optimal ranged syncs (commit rpc handling on the server side),
and making it easier to pushdown locks into the VFS system (no more
global hash table == easier to pushdown locks). As outlined in the
commit message.
-Matt
Matthew Dillon
<dillon@backplane.com>
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe cvs-all" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200207111506.g6BF6O61080709>