From: Erich Focht <efocht@ess.nec.de>
To: linux-ia64@vger.kernel.org
Subject: [Linux-ia64] Configurable NUMA node memory size
Date: Mon, 09 Dec 2002 12:15:49 +0000 [thread overview]
Message-ID: <marc-linux-ia64-105590709805517@msgid-missing> (raw)
[-- Attachment #1: Type: text/plain, Size: 377 bytes --]
Hi,
following the requests from Xavier and Jesse I introduced a
configuration parameter for the maximum memory per NUMA node. The
DIG_BANKSHIFT is set accordingly, the current choices are:
512MB/bank: 16GB/node,
2048MB/bank: 64GB/node,
8192MB/bank: 256GB/node.
The patch is for 2.5.50+ia64. Please consider applying it.
Thanks,
Erich
[-- Attachment #2: conf_numa_nodesize-2.5.50-ia64.path --]
[-- Type: text/x-diff, Size: 1931 bytes --]
diff -urNp linux-2.5.50-ia64/arch/ia64/Kconfig linux-2.5.50-ia64-digshift/arch/ia64/Kconfig
--- linux-2.5.50-ia64/arch/ia64/Kconfig 2002-12-09 11:23:01.000000000 +0100
+++ linux-2.5.50-ia64-digshift/arch/ia64/Kconfig 2002-12-09 12:25:25.000000000 +0100
@@ -220,6 +220,23 @@ config NUMA
Access). This option is for configuring high-end multiprocessor
server systems. If in doubt, say N.
+choice
+ prompt "Maximum Memory per NUMA Node" if NUMA && IA64_DIG
+ depends on NUMA && IA64_DIG
+ default IA64_NODESIZE_16GB
+
+config IA64_NODESIZE_16GB
+ bool "16GB"
+
+config IA64_NODESIZE_64GB
+ bool "64GB"
+
+config IA64_NODESIZE_256GB
+ bool "256GB"
+
+endchoice
+
+
config VIRTUAL_MEM_MAP
bool "Enable Virtual Mem Map" if IA64_GENERIC || IA64_DIG
depends on !NUMA
diff -urNp linux-2.5.50-ia64/include/asm-ia64/mmzone.h linux-2.5.50-ia64-digshift/include/asm-ia64/mmzone.h
--- linux-2.5.50-ia64/include/asm-ia64/mmzone.h 2002-11-27 23:36:24.000000000 +0100
+++ linux-2.5.50-ia64-digshift/include/asm-ia64/mmzone.h 2002-12-09 12:02:08.000000000 +0100
@@ -104,12 +104,22 @@ extern unsigned long max_low_pfn;
/*
* Bank definitions.
- * Current settings for DIG: 512MB/bank, 16GB/node.
+ * Configurable settings for DIG: 512MB/bank: 16GB/node,
+ * 2048MB/bank: 64GB/node,
+ * 8192MB/bank: 256GB/node.
*/
#define NR_BANKS_PER_NODE 32
-#define BANK_OFFSET(addr) ((unsigned long)(addr) & (BANKSIZE-1))
-#define DIG_BANKSHIFT 29
+#if defined(CONFIG_IA64_NODESIZE_16GB)
+# define DIG_BANKSHIFT 29
+#elif defined(CONFIG_IA64_NODESIZE_64GB)
+# define DIG_BANKSHIFT 31
+#elif defined(CONFIG_IA64_NODESIZE_256GB)
+# define DIG_BANKSHIFT 33
+#else
+# error Unsupported bank and nodesize!
+#endif
#define BANKSIZE (1UL << DIG_BANKSHIFT)
+#define BANK_OFFSET(addr) ((unsigned long)(addr) & (BANKSIZE-1))
#define NR_BANKS (NR_BANKS_PER_NODE * NR_NODES)
/*
reply other threads:[~2002-12-09 12:15 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=marc-linux-ia64-105590709805517@msgid-missing \
--to=efocht@ess.nec.de \
--cc=linux-ia64@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