From: Andrew Morton <akpm@digeo.com>
To: Badari Pulavarty <pbadari@us.ibm.com>
Cc: dougg@torque.net, linux-kernel@vger.kernel.org,
linux-scsi@vger.kernel.org, axboe@suse.de
Subject: Re: [patch for playing] 2.5.65 patch to support > 256 disks
Date: Mon, 24 Mar 2003 16:10:16 -0800 [thread overview]
Message-ID: <20030324161016.25a9a77a.akpm@digeo.com> (raw)
In-Reply-To: <200303241332.56996.pbadari@us.ibm.com>
Badari Pulavarty <pbadari@us.ibm.com> wrote:
>
> Here is the list of slab caches which consumed more than 1 MB
> in the process of inserting 4000 disks.
Thanks for doing this.
> #insmod scsi_debug.ko add_host=4 num_devs=1000
>
> deadline_drq before:1280 after:1025420 diff:1024140 size:64 incr:65544960
> blkdev_requests before:1280 after:1025400 diff:1024120 size:156 incr:159762720
>
> * deadline_drq, blkdev_requests consumed almost 80 MB. We need to fix this.
Yes, we do. But.
> inode_cache before:700 after:140770 diff:140070 size:364 incr:50985480
> dentry_cache before:4977 after:145061 diff:140084 size:172 incr:24094448
>
> * inode cache increased by 50 MB, dentry cache 24 MB.
> It looks like we cached 140,000 inodes. I wonder why ?
# find /sys/block/hda | wc -l
43
Oh shit, we're toast.
How many partitions did these "disks" have?
> size-2048 before:112 after:4102 diff:3990 size:2060 incr:8219400
> size-512 before:87 after:8085 diff:7998 size:524 incr:4190952
> size-192 before:907 after:16910 diff:16003 size:204 incr:3264612
> size-64 before:459 after:76500 diff:76041 size:76 incr:5779116
> size-32 before:523 after:24528 diff:24005 size:44 incr:1056220
>
> * 30MB for all other structures. I need to look closely on what these are..
Yes, that will take some work. What I would do is to change kmalloc:
+ int foo;
kmalloc(...)
{
+ if (foo)
+ dump_stack();
and then set `foo' in gdb across the registration of one disk.
Probably you can set foo by hand in scsi_register_device() or wherever it
happens.
next prev parent reply other threads:[~2003-03-24 21:55 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2003-03-21 18:56 Badari Pulavarty
2003-03-22 11:00 ` Douglas Gilbert
2003-03-22 11:04 ` Andrew Morton
2003-03-22 11:46 ` Douglas Gilbert
2003-03-22 12:05 ` Andrew Morton
2003-03-24 21:32 ` Badari Pulavarty
2003-03-24 22:22 ` Douglas Gilbert
2003-03-24 22:54 ` Badari Pulavarty
2003-03-25 0:10 ` Andrew Morton [this message]
2003-03-24 22:57 ` Badari Pulavarty
2003-03-25 10:56 ` Jens Axboe
2003-03-25 11:23 ` Jens Axboe
2003-03-25 11:37 ` Jens Axboe
2003-03-25 11:39 ` Nick Piggin
2003-03-25 12:01 ` Jens Axboe
2003-03-25 12:12 ` Nick Piggin
2003-03-25 12:35 ` Jens Axboe
2003-03-27 0:29 ` Badari Pulavarty
2003-03-27 9:18 ` Jens Axboe
2003-03-28 17:04 ` Badari Pulavarty
2003-03-28 18:41 ` Andries Brouwer
2003-03-29 1:39 ` Badari Pulavarty
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=20030324161016.25a9a77a.akpm@digeo.com \
--to=akpm@digeo.com \
--cc=axboe@suse.de \
--cc=dougg@torque.net \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-scsi@vger.kernel.org \
--cc=pbadari@us.ibm.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
all inboxes | Powered by JetHome®