From: "J. Bruce Fields" <bfields@fieldses.org>
To: Mi Jinlong <mijinlong@cn.fujitsu.com>
Cc: "J. Bruce Fields" <bfields@redhat.com>, linux-nfs@vger.kernel.org
Subject: Re: [PATCH 1/2] nfsd: cleanup setting of default max_block_size
Date: Fri, 3 Feb 2012 15:49:31 -0500 [thread overview]
Message-ID: <20120203204931.GC2999@fieldses.org> (raw)
In-Reply-To: <20120201214656.GA19075@fieldses.org>
On Wed, Feb 01, 2012 at 04:46:56PM -0500, bfields wrote:
> On Tue, Jan 31, 2012 at 09:11:48AM +0800, Mi Jinlong wrote:
> > Should use target = i.totalram << (PAGE_SHIFT - 12);
> >
> > target = i.totalram << PAGE_SHIFT; and
> > target <<= 12;
> > means target = i.totalram << (PAGE_SHIFT + 12);
>
> Yes, thanks for catching that.
>
> Also, splitting up the calculation as I did above risks overflow at the
> first step.
>
> I'll fix that....
Here are the fixed patches.--b.
>From 87b0fc7deb5feccf93b022f6a976e8441152dbb2 Mon Sep 17 00:00:00 2001
From: "J. Bruce Fields" <bfields@redhat.com>
Date: Mon, 30 Jan 2012 16:18:35 -0500
Subject: [PATCH 1/2] nfsd: cleanup setting of default max_block_size
Move calculation of the default into a helper function.
Get rid of an unused variable "err" while we're there.
Thanks to Mi Jinlong for catching an arithmetic error in a previous
version.
Cc: Mi Jinlong <mijinlong@cn.fujitsu.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
fs/nfsd/nfssvc.c | 44 ++++++++++++++++++++++++--------------------
1 files changed, 24 insertions(+), 20 deletions(-)
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index eda7d7e..e9eb408 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -307,33 +307,37 @@ static void set_max_drc(void)
dprintk("%s nfsd_drc_max_mem %u \n", __func__, nfsd_drc_max_mem);
}
-int nfsd_create_serv(void)
+static int nfsd_get_default_max_blksize(void)
{
- int err = 0;
+ struct sysinfo i;
+ unsigned long long target;
+ unsigned long ret;
+
+ si_meminfo(&i);
+ target = i.totalram << PAGE_SHIFT;
+ /*
+ * Aim for 1/4096 of memory per thread This gives 1MB on 4Gig
+ * machines, but only uses 32K on 128M machines. Bottom out at
+ * 8K on 32M and smaller. Of course, this is only a default.
+ */
+ target >>= 12;
+
+ ret = NFSSVC_MAXBLKSIZE;
+ while (ret > target && ret >= 8*1024*2)
+ ret /= 2;
+ return ret;
+}
+int nfsd_create_serv(void)
+{
WARN_ON(!mutex_is_locked(&nfsd_mutex));
if (nfsd_serv) {
svc_get(nfsd_serv);
return 0;
}
- if (nfsd_max_blksize == 0) {
- /* choose a suitable default */
- struct sysinfo i;
- si_meminfo(&i);
- /* Aim for 1/4096 of memory per thread
- * This gives 1MB on 4Gig machines
- * But only uses 32K on 128M machines.
- * Bottom out at 8K on 32M and smaller.
- * Of course, this is only a default.
- */
- nfsd_max_blksize = NFSSVC_MAXBLKSIZE;
- i.totalram <<= PAGE_SHIFT - 12;
- while (nfsd_max_blksize > i.totalram &&
- nfsd_max_blksize >= 8*1024*2)
- nfsd_max_blksize /= 2;
- }
+ if (nfsd_max_blksize == 0)
+ nfsd_max_blksize = nfsd_get_default_max_blksize();
nfsd_reset_versions();
-
nfsd_serv = svc_create_pooled(&nfsd_program, nfsd_max_blksize,
nfsd_last_thread, nfsd, THIS_MODULE);
if (nfsd_serv == NULL)
@@ -341,7 +345,7 @@ int nfsd_create_serv(void)
set_max_drc();
do_gettimeofday(&nfssvc_boot); /* record boot time */
- return err;
+ return 0;
}
int nfsd_nrpools(void)
--
1.7.5.4
>From 508f92275624fc755104b17945bdc822936f1918 Mon Sep 17 00:00:00 2001
From: "J. Bruce Fields" <bfields@redhat.com>
Date: Mon, 30 Jan 2012 16:21:11 -0500
Subject: [PATCH 2/2] nfsd: fix default iosize calculation on 32bit
The rpc buffers will be allocated out of low memory, so we should really
only be taking that into account.
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
fs/nfsd/nfssvc.c | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index e9eb408..aacf1f4 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -314,7 +314,7 @@ static int nfsd_get_default_max_blksize(void)
unsigned long ret;
si_meminfo(&i);
- target = i.totalram << PAGE_SHIFT;
+ target = (i.totalram - i.totalhigh) << PAGE_SHIFT;
/*
* Aim for 1/4096 of memory per thread This gives 1MB on 4Gig
* machines, but only uses 32K on 128M machines. Bottom out at
--
1.7.5.4
next prev parent reply other threads:[~2012-02-03 20:49 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-01-30 22:42 [PATCH 1/2] nfsd: cleanup setting of default max_block_size J. Bruce Fields
2012-01-30 22:42 ` [PATCH 2/2] nfsd: fix default iosize calculation on 32bit J. Bruce Fields
2012-01-30 22:47 ` J. Bruce Fields
2012-01-31 1:11 ` [PATCH 1/2] nfsd: cleanup setting of default max_block_size Mi Jinlong
2012-02-01 21:46 ` J. Bruce Fields
2012-02-03 20:49 ` J. Bruce Fields [this message]
2012-02-03 16:24 ` Mi Jinlong
2012-02-04 2:16 ` J. Bruce Fields
2012-02-04 12:14 ` Mi Jinlong
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=20120203204931.GC2999@fieldses.org \
--to=bfields@fieldses.org \
--cc=bfields@redhat.com \
--cc=linux-nfs@vger.kernel.org \
--cc=mijinlong@cn.fujitsu.com \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).