From: Bernd Schubert <bs@q-leap.de>
To: linux-raid@vger.kernel.org, Neil Brown <neilb@suse.de>
Subject: [PATCH] force parallel resync
Date: Mon, 3 Dec 2007 14:37:03 +0100 [thread overview]
Message-ID: <200712031437.04211.bs@q-leap.de> (raw)
Hello Neil,
on doing software-raid over some Infortrend hardware raid boxes, we can easily
bring a single cpu to 100%, while the hardware-raid boxes are still only
utilized for 50% or less.
So we are using *several* software raids instead of only one. However, for us
it then also doesn't make sense to have a resync for only one of the
md-raids. Below is a patch to force parallel resync for specified md-sets via
sysfs.
This still leaves a problem, though. If a resync starts before settings this
parameter, I don't know how to wake up the sleeping resync-thread. Any ideas?
Signed-off-by: Bernd Schubert <bs@q-leap.de>
(The patch is against 2.6.22, but also applies to 2.6.23).
Index: linux-2.6.22/drivers/md/md.c
===================================================================
--- linux-2.6.22.orig/drivers/md/md.c 2007-11-27 15:42:22.000000000 +0100
+++ linux-2.6.22/drivers/md/md.c 2007-12-03 13:39:26.000000000 +0100
@@ -2843,6 +2843,30 @@ __ATTR(sync_speed_max, S_IRUGO|S_IWUSR,
static ssize_t
+sync_force_parallel_show(mddev_t *mddev, char *page)
+{
+ return sprintf(page, "%d\n", mddev->parallel_resync);
+}
+
+static ssize_t
+sync_force_parallel_store(mddev_t *mddev, const char *buf, size_t len)
+{
+ char *e;
+ unsigned long n = simple_strtoul(buf, &e, 10);
+
+ if (!*buf || (*e && *e != '\n') || (n != 0 && n != 1))
+ return -EINVAL;
+
+ mddev->parallel_resync = n;
+ return len;
+}
+
+/* force parallel resync, even with shared block devices */
+static struct md_sysfs_entry md_sync_force_parallel =
+__ATTR(sync_force_parallel, S_IRUGO|S_IWUSR,
+ sync_force_parallel_show, sync_force_parallel_store);
+
+static ssize_t
sync_speed_show(mddev_t *mddev, char *page)
{
unsigned long resync, dt, db;
@@ -2980,6 +3004,7 @@ static struct attribute *md_redundancy_a
&md_sync_min.attr,
&md_sync_max.attr,
&md_sync_speed.attr,
+ &md_sync_force_parallel.attr,
&md_sync_completed.attr,
&md_suspend_lo.attr,
&md_suspend_hi.attr,
@@ -5264,8 +5289,9 @@ void md_do_sync(mddev_t *mddev)
ITERATE_MDDEV(mddev2,tmp) {
if (mddev2 == mddev)
continue;
- if (mddev2->curr_resync &&
- match_mddev_units(mddev,mddev2)) {
+ if (!mddev->parallel_resync
+ && mddev2->curr_resync
+ && match_mddev_units(mddev,mddev2)) {
DEFINE_WAIT(wq);
if (mddev < mddev2 && mddev->curr_resync == 2) {
/* arbitrarily yield */
Index: linux-2.6.22/include/linux/raid/md_k.h
===================================================================
--- linux-2.6.22.orig/include/linux/raid/md_k.h 2007-12-03 13:00:10.000000000
+0100
+++ linux-2.6.22/include/linux/raid/md_k.h 2007-12-03 13:01:40.000000000 +0100
@@ -170,6 +170,9 @@ struct mddev_s
int sync_speed_min;
int sync_speed_max;
+ /* resync even though the same disks are shared among md-devices */
+ int parallel_resync;
+
int ok_start_degraded;
/* recovery/resync flags
* NEEDED: we might need to start a resync/recover
Thanks,
Bernd
--
Bernd Schubert
Q-Leap Networks GmbH
reply other threads:[~2007-12-03 13:37 UTC|newest]
Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
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=200712031437.04211.bs@q-leap.de \
--to=bs@q-leap.de \
--cc=linux-raid@vger.kernel.org \
--cc=neilb@suse.de \
/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).