Date: Sun, 19 Aug 2001 13:46:46 -0700 (PDT) From: Matt Dillon <dillon@earth.backplane.com> To: <murray@FreeBSD.ORG>, <jkh@FreeBSD.ORG>, <hackers@FreeBSD.ORG> Cc: Leo Bicknell <bicknell@ufp.org>, Peter Wemm <peter@wemm.org> Subject: Proposed patch (-stable) for minor KVM adjustments for the release Message-ID: <200108192046.f7JKkkA46377@earth.backplane.com> References: <Pine.LNX.4.33L.0108190007320.5646-100000@imladris.rielhome.conectiva>
next in thread | previous in thread | raw e-mail | index | archive | help
Here is my proposed patch. It adds to options (overrides) to the kernel
config, two boot-time tunables for same, and sets reasonable defaults.
I also changed the default auto-sizing calculation for swap-meta from
32x physical pages to 16x physical pages on top of it being capped.
I only made a small change there since we cannot really afford to run
out of swap-meta structures (the system will probably lockup if we do).
This patch is against -stable. I will commit it to -current today and
await the release-engineers permission to MFC it to -stable for the
release. I did some simple testing under -stable, including bumping up
maxusers and NMBCLUSTERS.
-Matt
Index: conf/options
===================================================================
RCS file: /home/ncvs/src/sys/conf/options,v
retrieving revision 1.191.2.35
diff -u -r1.191.2.35 options
--- conf/options 2001/08/03 00:47:27 1.191.2.35
+++ conf/options 2001/08/19 20:00:29
@@ -163,6 +163,8 @@
NBUF opt_param.h
NMBCLUSTERS opt_param.h
NSFBUFS opt_param.h
+VM_BCACHE_SIZE_MAX opt_param.h
+VM_SWZONE_SIZE_MAX opt_param.h
MAXUSERS
# Generic SCSI options.
Index: i386/conf/LINT
===================================================================
RCS file: /home/ncvs/src/sys/i386/conf/Attic/LINT,v
retrieving revision 1.749.2.77
diff -u -r1.749.2.77 LINT
--- i386/conf/LINT 2001/08/15 01:23:49 1.749.2.77
+++ i386/conf/LINT 2001/08/19 20:27:02
@@ -2315,7 +2315,44 @@
#
options NSFBUFS=1024
+# Set the size of the buffer cache KVM reservation, in buffers. This is
+# scaled by approximately 16384 bytes. The system will auto-size the buffer
+# cache if this option is not specified or set to 0.
#
+options NBUF=512
+
+# Set the size of the mbuf KVM reservation, in clusters. This is scaled
+# by approximately 2048 bytes. The system will auto-size the mbuf area
+# if this options is not specified or set to 0.
+#
+options NMBCLUSTERS=1024
+
+# Tune the kernel malloc area parameters. VM_KMEM_SIZE represents the
+# minimum, in bytes, and is typically (12*1024*1024) (12MB).
+# VM_KMEM_SIZE_MAX represents the maximum, typically 200 megabytes.
+# VM_KMEM_SIZE_SCALE can be set to adjust the auto-tuning factor, which
+# typically defaults to 4 (kernel malloc area size is physical memory
+# divided by the scale factor).
+#
+options VM_KMEM_SIZE="(10*1024*1024)"
+options VM_KMEM_SIZE_MAX="(100*1024*1024)"
+options VM_KMEM_SIZE_SCALE="4"
+
+# Tune the buffer cache maximum KVA reservation, in bytes. The maximum is
+# usually capped at 200 MB, effecting machines with > 1GB of ram. Note
+# that the buffer cache only really governs write buffering and disk block
+# translations. The VM page cache is our primary disk cache and is not
+# effected by the size of the buffer cache.
+#
+options VM_BCACHE_SIZE_MAX="(100*1024*1024)"
+
+# Tune the swap zone KVA reservation, in bytes. The default is typically
+# 70 MB, giving the system the ability to manage a maximum of 28GB worth
+# of swapped out data.
+#
+options VM_SWZONE_SIZE_MAX="(50*1024*1024)"
+
+#
# Enable extra debugging code for locks. This stores the filename and
# line of whatever acquired the lock in the lock itself, and change a
# number of function calls to pass around the relevant data. This is
@@ -2500,9 +2537,7 @@
options KEY
options LOCKF_DEBUG
options LOUTB
-options NBUF=512
options NETATALKDEBUG
-options NMBCLUSTERS=1024
#options OLTR_NO_BULLSEYE_MAC
#options OLTR_NO_HAWKEYE_MAC
#options OLTR_NO_TMS_MAC
@@ -2521,7 +2556,5 @@
options SPX_HACK
options TIMER_FREQ="((14318182+6)/12)"
options VFS_BIO_DEBUG
-options VM_KMEM_SIZE
-options VM_KMEM_SIZE_MAX
-options VM_KMEM_SIZE_SCALE
options XBONEHACK
+
Index: i386/i386/machdep.c
===================================================================
RCS file: /home/ncvs/src/sys/i386/i386/machdep.c,v
retrieving revision 1.385.2.15
diff -u -r1.385.2.15 machdep.c
--- i386/i386/machdep.c 2001/07/30 23:27:59 1.385.2.15
+++ i386/i386/machdep.c 2001/08/19 20:36:19
@@ -320,7 +320,9 @@
* The nominal buffer size (and minimum KVA allocation) is BKVASIZE.
* For the first 64MB of ram nominally allocate sufficient buffers to
* cover 1/4 of our ram. Beyond the first 64MB allocate additional
- * buffers to cover 1/20 of our ram over 64MB.
+ * buffers to cover 1/20 of our ram over 64MB. When auto-sizing
+ * the buffer cache we limit the eventual kva reservation to
+ * maxbcache bytes.
*
* factor represents the 1/4 x ram conversion.
*/
@@ -332,6 +334,8 @@
nbuf += min((physmem - 1024) / factor, 16384 / factor);
if (physmem > 16384)
nbuf += (physmem - 16384) * 2 / (factor * 5);
+ if (maxbcache && nbuf > maxbcache / BKVASIZE)
+ nbuf = maxbcache / BKVASIZE;
}
/*
Index: i386/include/param.h
===================================================================
RCS file: /home/ncvs/src/sys/i386/include/param.h,v
retrieving revision 1.54.2.4
diff -u -r1.54.2.4 param.h
--- i386/include/param.h 2000/12/29 10:59:18 1.54.2.4
+++ i386/include/param.h 2001/08/19 20:07:08
@@ -113,6 +113,22 @@
#define UPAGES 2 /* pages of u-area */
/*
+ * Ceiling on amount of swblock kva space.
+ */
+#ifndef VM_SWZONE_SIZE_MAX
+#define VM_SWZONE_SIZE_MAX (70 * 1024 * 1024)
+#endif
+
+/*
+ * Ceiling on size of buffer cache (really only effects write queueing,
+ * the VM page cache is not effected).
+ */
+#ifndef VM_BCACHE_SIZE_MAX
+#define VM_BCACHE_SIZE_MAX (200 * 1024 * 1024)
+#endif
+
+
+/*
* Constants related to network buffer management.
* MCLBYTES must be no larger than CLBYTES (the software page size), and,
* on machines that exchange pages of input or output buffers with mbuf
Index: kern/subr_param.c
===================================================================
RCS file: /home/ncvs/src/sys/kern/subr_param.c,v
retrieving revision 1.42.2.1
diff -u -r1.42.2.1 subr_param.c
--- kern/subr_param.c 2001/07/30 23:28:00 1.42.2.1
+++ kern/subr_param.c 2001/08/19 20:04:05
@@ -76,6 +76,8 @@
int mbuf_wait = 32; /* mbuf sleep time in ticks */
int nbuf;
int nswbuf;
+int maxswzone; /* max swmeta KVA storage */
+int maxbcache; /* max buffer cache KVA storage */
/* maximum # of sf_bufs (sendfile(2) zero-copy virtual buffers) */
int nsfbufs;
@@ -115,6 +117,10 @@
TUNABLE_INT_FETCH("kern.ipc.nsfbufs", &nsfbufs);
nbuf = NBUF;
TUNABLE_INT_FETCH("kern.nbuf", &nbuf);
+ maxswzone = VM_SWZONE_SIZE_MAX;
+ TUNABLE_INT_FETCH("kern.maxswzone", &maxswzone);
+ maxbcache = VM_BCACHE_SIZE_MAX;
+ TUNABLE_INT_FETCH("kern.maxbcache", &maxbcache);
ncallout = 16 + maxproc + maxfiles;
TUNABLE_INT_FETCH("kern.ncallout", &ncallout);
}
Index: sys/buf.h
===================================================================
RCS file: /home/ncvs/src/sys/sys/buf.h,v
retrieving revision 1.88.2.4
diff -u -r1.88.2.4 buf.h
--- sys/buf.h 2001/06/03 05:00:10 1.88.2.4
+++ sys/buf.h 2001/08/19 19:54:02
@@ -455,6 +455,8 @@
#ifdef _KERNEL
extern int nbuf; /* The number of buffer headers */
+extern int maxswzone; /* Max KVA for swap structures */
+extern int maxbcache; /* Max KVA for buffer cache */
extern int runningbufspace;
extern int buf_maxio; /* nominal maximum I/O for buffer */
extern struct buf *buf; /* The buffer headers. */
Index: vm/swap_pager.c
===================================================================
RCS file: /home/ncvs/src/sys/vm/swap_pager.c,v
retrieving revision 1.130.2.8
diff -u -r1.130.2.8 swap_pager.c
--- vm/swap_pager.c 2001/03/24 20:28:24 1.130.2.8
+++ vm/swap_pager.c 2001/08/19 19:47:19
@@ -300,10 +300,12 @@
/*
* Initialize our zone. Right now I'm just guessing on the number
* we need based on the number of pages in the system. Each swblock
- * can hold 16 pages, so this is probably overkill.
+ * can hold 16 pages, so this is probably overkill. This reservation
+ * is typically limited to around 70MB by default.
*/
-
- n = cnt.v_page_count * 2;
+ n = cnt.v_page_count;
+ if (maxswzone && n > maxswzone / sizeof(struct swblock))
+ n = maxswzone / sizeof(struct swblock);
swap_zone = zinit(
"SWAPMETA",
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-hackers" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200108192046.f7JKkkA46377>