From: Jeff Layton <jlayton-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
To: Christoph Hellwig <hch-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org>
Cc: "Stefan (metze) Metzmacher"
<metze-eUNUBHrolfbYtjvyW6yDsg@public.gmane.org>,
viro-RmSDqhL/yNMiFSDQTTA3OLVCufUGDwFn@public.gmane.org,
matthew-Ztpu424NOJ8@public.gmane.org,
bfields-uC3wQj2KruNg9hUCZPvPmw@public.gmane.org,
linux-cifs-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-nfs-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
cluster-devel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org,
sage-4GqslpFJ+cxBDgjK7y7TUQ@public.gmane.org,
samba-technical-w/Ol4Ecudpl8XjKLYN78aQ@public.gmane.org,
Trond.Myklebust-HgOvQuBEEgTQT0dZR+AlfA@public.gmane.org,
linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-afs-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org,
dhowells-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org,
smfrench-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org,
linux-fsdevel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
ceph-devel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org,
swhiteho-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org
Subject: Re: [PATCH v1 11/11] locks: give the blocked_hash its own spinlock
Date: Tue, 4 Jun 2013 10:56:56 -0400 [thread overview]
Message-ID: <20130604105656.18663efa@corrin.poochiereds.net> (raw)
In-Reply-To: <20130604144640.GA7730-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org>
On Tue, 4 Jun 2013 07:46:40 -0700
Christoph Hellwig <hch-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org> wrote:
> Having RCU for modification mostly workloads never is a good idea, so
> I don't think it makes sense to mention it here.
>
> If you care about the overhead it's worth trying to use per-cpu lists,
> though.
>
Yeah, I looked at those too in an earlier set and it did help some.
Moving to a hashtable for the blocked_list really seemed to help the
most there, but percpu lists with lglocks or something might help a lot
on the file_lock_list.
--
Jeff Layton <jlayton-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
WARNING: multiple messages have this Message-ID (diff)
From: Jeff Layton <jlayton@redhat.com>
To: cluster-devel.redhat.com
Subject: [Cluster-devel] [PATCH v1 11/11] locks: give the blocked_hash its own spinlock
Date: Tue, 4 Jun 2013 10:56:56 -0400 [thread overview]
Message-ID: <20130604105656.18663efa@corrin.poochiereds.net> (raw)
In-Reply-To: <20130604144640.GA7730@infradead.org>
On Tue, 4 Jun 2013 07:46:40 -0700
Christoph Hellwig <hch@infradead.org> wrote:
> Having RCU for modification mostly workloads never is a good idea, so
> I don't think it makes sense to mention it here.
>
> If you care about the overhead it's worth trying to use per-cpu lists,
> though.
>
Yeah, I looked at those too in an earlier set and it did help some.
Moving to a hashtable for the blocked_list really seemed to help the
most there, but percpu lists with lglocks or something might help a lot
on the file_lock_list.
--
Jeff Layton <jlayton@redhat.com>
WARNING: multiple messages have this Message-ID (diff)
From: Jeff Layton <jlayton@redhat.com>
To: Christoph Hellwig <hch@infradead.org>
Cc: "Stefan (metze) Metzmacher" <metze@samba.org>,
viro@zeniv.linux.org.uk, matthew@wil.cx, bfields@fieldses.org,
linux-cifs@vger.kernel.org, linux-nfs@vger.kernel.org,
cluster-devel@redhat.com, sage@inktank.com,
samba-technical@lists.samba.org, Trond.Myklebust@netapp.com,
linux-kernel@vger.kernel.org, linux-afs@lists.infradead.org,
dhowells@redhat.com, smfrench@gmail.com,
linux-fsdevel@vger.kernel.org, ceph-devel@vger.kernel.org,
akpm@linux-foundation.org, swhiteho@redhat.com
Subject: Re: [PATCH v1 11/11] locks: give the blocked_hash its own spinlock
Date: Tue, 4 Jun 2013 10:56:56 -0400 [thread overview]
Message-ID: <20130604105656.18663efa@corrin.poochiereds.net> (raw)
In-Reply-To: <20130604144640.GA7730@infradead.org>
On Tue, 4 Jun 2013 07:46:40 -0700
Christoph Hellwig <hch@infradead.org> wrote:
> Having RCU for modification mostly workloads never is a good idea, so
> I don't think it makes sense to mention it here.
>
> If you care about the overhead it's worth trying to use per-cpu lists,
> though.
>
Yeah, I looked at those too in an earlier set and it did help some.
Moving to a hashtable for the blocked_list really seemed to help the
most there, but percpu lists with lglocks or something might help a lot
on the file_lock_list.
--
Jeff Layton <jlayton@redhat.com>
next prev parent reply other threads:[~2013-06-04 14:56 UTC|newest]
Thread overview: 103+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-06-01 3:07 [PATCH v1 00/11] locks: scalability improvements for file locking Jeff Layton
2013-06-01 3:07 ` Jeff Layton
2013-06-01 3:07 ` [Cluster-devel] " Jeff Layton
2013-06-01 3:07 ` [PATCH v1 01/11] cifs: use posix_unblock_lock instead of locks_delete_block Jeff Layton
2013-06-01 3:07 ` [Cluster-devel] " Jeff Layton
[not found] ` <1370056054-25449-2-git-send-email-jlayton-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2013-06-03 21:53 ` J. Bruce Fields
2013-06-03 21:53 ` J. Bruce Fields
2013-06-03 21:53 ` [Cluster-devel] " J. Bruce Fields
2013-06-01 3:07 ` [PATCH v1 02/11] locks: make generic_add_lease and generic_delete_lease static Jeff Layton
2013-06-01 3:07 ` [Cluster-devel] " Jeff Layton
[not found] ` <1370056054-25449-3-git-send-email-jlayton-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2013-06-03 21:53 ` J. Bruce Fields
2013-06-03 21:53 ` J. Bruce Fields
2013-06-03 21:53 ` [Cluster-devel] " J. Bruce Fields
2013-06-01 3:07 ` [PATCH v1 04/11] locks: make "added" in __posix_lock_file a bool Jeff Layton
2013-06-01 3:07 ` [Cluster-devel] " Jeff Layton
2013-06-04 20:17 ` J. Bruce Fields
2013-06-04 20:17 ` [Cluster-devel] " J. Bruce Fields
2013-06-01 3:07 ` [PATCH v1 05/11] locks: encapsulate the fl_link list handling Jeff Layton
2013-06-01 3:07 ` [Cluster-devel] " Jeff Layton
2013-06-04 20:17 ` J. Bruce Fields
2013-06-04 20:17 ` [Cluster-devel] " J. Bruce Fields
[not found] ` <1370056054-25449-1-git-send-email-jlayton-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2013-06-01 3:07 ` [PATCH v1 03/11] locks: comment cleanups and clarifications Jeff Layton
2013-06-01 3:07 ` Jeff Layton
2013-06-01 3:07 ` [Cluster-devel] " Jeff Layton
[not found] ` <1370056054-25449-4-git-send-email-jlayton-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2013-06-03 22:00 ` J. Bruce Fields
2013-06-03 22:00 ` J. Bruce Fields
2013-06-03 22:00 ` [Cluster-devel] " J. Bruce Fields
[not found] ` <20130603220024.GF2109-uC3wQj2KruNg9hUCZPvPmw@public.gmane.org>
2013-06-04 11:09 ` Jeff Layton
2013-06-04 11:09 ` Jeff Layton
2013-06-04 11:09 ` [Cluster-devel] " Jeff Layton
2013-06-01 3:07 ` [PATCH v1 06/11] locks: convert to i_lock to protect i_flock list Jeff Layton
2013-06-01 3:07 ` Jeff Layton
2013-06-01 3:07 ` [Cluster-devel] " Jeff Layton
2013-06-04 21:22 ` J. Bruce Fields
2013-06-04 21:22 ` [Cluster-devel] " J. Bruce Fields
[not found] ` <20130604212208.GC15594-uC3wQj2KruNg9hUCZPvPmw@public.gmane.org>
2013-06-05 0:46 ` Jeff Layton
2013-06-05 0:46 ` Jeff Layton
2013-06-05 0:46 ` [Cluster-devel] " Jeff Layton
2013-06-01 3:07 ` [PATCH v1 09/11] locks: turn the blocked_list into a hashtable Jeff Layton
2013-06-01 3:07 ` Jeff Layton
2013-06-01 3:07 ` [Cluster-devel] " Jeff Layton
2013-06-01 3:07 ` [PATCH v1 10/11] locks: add a new "lm_owner_key" lock operation Jeff Layton
2013-06-01 3:07 ` Jeff Layton
2013-06-01 3:07 ` [Cluster-devel] " Jeff Layton
2013-06-01 3:07 ` [PATCH v1 11/11] locks: give the blocked_hash its own spinlock Jeff Layton
2013-06-01 3:07 ` Jeff Layton
2013-06-01 3:07 ` [Cluster-devel] " Jeff Layton
[not found] ` <1370056054-25449-12-git-send-email-jlayton-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2013-06-04 14:19 ` Stefan (metze) Metzmacher
2013-06-04 14:19 ` Stefan (metze) Metzmacher
2013-06-04 14:19 ` [Cluster-devel] " Stefan Metzmacher
2013-06-04 14:39 ` Jeff Layton
2013-06-04 14:39 ` [Cluster-devel] " Jeff Layton
2013-06-04 14:46 ` Christoph Hellwig
2013-06-04 14:46 ` [Cluster-devel] " Christoph Hellwig
[not found] ` <20130604144640.GA7730-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org>
2013-06-04 14:53 ` J. Bruce Fields
2013-06-04 14:53 ` J. Bruce Fields
2013-06-04 14:53 ` [Cluster-devel] " J. Bruce Fields
2013-06-04 15:15 ` Jeff Layton
2013-06-04 15:15 ` [Cluster-devel] " Jeff Layton
2013-06-04 14:56 ` Jeff Layton [this message]
2013-06-04 14:56 ` Jeff Layton
2013-06-04 14:56 ` [Cluster-devel] " Jeff Layton
2013-06-03 19:04 ` [PATCH v1 00/11] locks: scalability improvements for file locking Davidlohr Bueso
2013-06-03 19:04 ` Davidlohr Bueso
2013-06-03 19:04 ` [Cluster-devel] " Davidlohr Bueso
2013-06-03 21:31 ` J. Bruce Fields
2013-06-03 21:31 ` J. Bruce Fields
2013-06-03 21:31 ` [Cluster-devel] " J. Bruce Fields
2013-06-04 10:54 ` Jeff Layton
2013-06-04 10:54 ` [Cluster-devel] " Jeff Layton
[not found] ` <20130604065417.46080a57-9yPaYZwiELC+kQycOl6kW4xkIHaj4LzF@public.gmane.org>
2013-06-04 11:56 ` Jim Rees
2013-06-04 11:56 ` Jim Rees
2013-06-04 11:56 ` [Cluster-devel] " Jim Rees
[not found] ` <20130604115644.GA4180-63aXycvo3TyHXe+LvDLADg@public.gmane.org>
2013-06-04 12:15 ` Jeff Layton
2013-06-04 12:15 ` Jeff Layton
2013-06-04 12:15 ` [Cluster-devel] " Jeff Layton
2013-06-01 3:07 ` [PATCH v1 07/11] locks: only pull entries off of blocked_list when they are really unblocked Jeff Layton
2013-06-01 3:07 ` Jeff Layton
2013-06-01 3:07 ` [Cluster-devel] " Jeff Layton
[not found] ` <1370056054-25449-8-git-send-email-jlayton-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2013-06-04 21:58 ` J. Bruce Fields
2013-06-04 21:58 ` J. Bruce Fields
2013-06-04 21:58 ` [Cluster-devel] " J. Bruce Fields
[not found] ` <20130604215839.GD15594-uC3wQj2KruNg9hUCZPvPmw@public.gmane.org>
2013-06-05 11:38 ` Jeff Layton
2013-06-05 11:38 ` Jeff Layton
2013-06-05 11:38 ` [Cluster-devel] " Jeff Layton
[not found] ` <20130605073822.4d67c57c-4QP7MXygkU+dMjc06nkz3ljfA9RmPOcC@public.gmane.org>
2013-06-05 12:24 ` J. Bruce Fields
2013-06-05 12:24 ` J. Bruce Fields
2013-06-05 12:24 ` [Cluster-devel] " J. Bruce Fields
2013-06-05 12:38 ` Jeff Layton
2013-06-05 12:38 ` [Cluster-devel] " Jeff Layton
[not found] ` <20130605083859.72c855cd-4QP7MXygkU+dMjc06nkz3ljfA9RmPOcC@public.gmane.org>
2013-06-05 12:59 ` J. Bruce Fields
2013-06-05 12:59 ` J. Bruce Fields
2013-06-05 12:59 ` [Cluster-devel] " J. Bruce Fields
2013-06-01 3:07 ` [PATCH v1 08/11] locks: convert fl_link to a hlist_node Jeff Layton
2013-06-01 3:07 ` [Cluster-devel] " Jeff Layton
[not found] ` <1370056054-25449-9-git-send-email-jlayton-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2013-06-04 21:59 ` J. Bruce Fields
2013-06-04 21:59 ` J. Bruce Fields
2013-06-04 21:59 ` [Cluster-devel] " J. Bruce Fields
2013-06-05 11:43 ` Jeff Layton
2013-06-05 11:43 ` [Cluster-devel] " Jeff Layton
[not found] ` <20130605074309.051ff75f-4QP7MXygkU+dMjc06nkz3ljfA9RmPOcC@public.gmane.org>
2013-06-05 12:46 ` J. Bruce Fields
2013-06-05 12:46 ` J. Bruce Fields
2013-06-05 12:46 ` [Cluster-devel] " J. Bruce Fields
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20130604105656.18663efa@corrin.poochiereds.net \
--to=jlayton-h+wxahxf7alqt0dzr+alfa@public.gmane.org \
--cc=Trond.Myklebust-HgOvQuBEEgTQT0dZR+AlfA@public.gmane.org \
--cc=akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org \
--cc=bfields-uC3wQj2KruNg9hUCZPvPmw@public.gmane.org \
--cc=ceph-devel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=cluster-devel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org \
--cc=dhowells-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org \
--cc=hch-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org \
--cc=linux-afs-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org \
--cc=linux-cifs-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=linux-fsdevel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=linux-nfs-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=matthew-Ztpu424NOJ8@public.gmane.org \
--cc=metze-eUNUBHrolfbYtjvyW6yDsg@public.gmane.org \
--cc=sage-4GqslpFJ+cxBDgjK7y7TUQ@public.gmane.org \
--cc=samba-technical-w/Ol4Ecudpl8XjKLYN78aQ@public.gmane.org \
--cc=smfrench-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org \
--cc=swhiteho-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org \
--cc=viro-RmSDqhL/yNMiFSDQTTA3OLVCufUGDwFn@public.gmane.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.