From: Ravikiran G Thirumalai <kiran@in.ibm.com>
To: linux-kernel@vger.kernel.org
Subject: How reliable is SLAB_HWCACHE_ALIGN?
Date: Wed, 10 Sep 2003 13:46:57 +0530 [thread overview]
Message-ID: <20030910081654.GA1129@llm08.in.ibm.com> (raw)
I was assuming that if you create a slab cache with SLAB_HWCACHE_ALIGN,
objects are guaranteed to be aligned to L1 cacheline. But this piece
of code in kmem_cache_create has raised doubts.
----------------------------------------------------------------------------
if (flags & SLAB_HWCACHE_ALIGN) {
/* Need to adjust size so that objs are cache aligned. */
/* Small obj size, can get at least two per cache line. */
while (size < align/2)
align /= 2;
size = (size+align-1)&(~(align-1));
}
----------------------------------------------------------------------------
Am I missing something or can there really be two objects on the same
cacheline even when SLAB_HWCACHE_ALIGN is specified?
Thanks,
Kiran
next reply other threads:[~2003-09-10 8:09 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2003-09-10 8:16 Ravikiran G Thirumalai [this message]
2003-09-10 15:41 ` How reliable is SLAB_HWCACHE_ALIGN? Robert Love
2003-09-11 5:54 ` Ravikiran G Thirumalai
2003-09-11 11:08 ` [patch] Make slab allocator work with SLAB_MUST_HWCACHE_ALIGN Ravikiran G Thirumalai
2003-09-11 16:19 ` Manfred Spraul
2003-09-11 21:49 ` Manfred Spraul
2003-09-12 8:59 ` Ravikiran G Thirumalai
2003-09-12 9:10 ` Arjan van de Ven
2003-09-13 20:06 ` Manfred Spraul
2003-09-13 20:58 ` Dipankar Sarma
2003-09-14 8:09 ` Ravikiran G Thirumalai
2003-09-14 13:00 ` Dipankar Sarma
2003-09-15 5:13 ` Ravikiran G Thirumalai
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=20030910081654.GA1129@llm08.in.ibm.com \
--to=kiran@in.ibm.com \
--cc=linux-kernel@vger.kernel.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 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).