From: Christoph Hellwig <hch@lst.de>
To: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Jens Axboe <jens.axboe@oracle.com>,
Matthew Wilcox <matthew@wil.cx>,
linux-mm@kvack.org, linux-scsi@vger.kernel.org
Subject: [PATCH] mm: don't discard unused swap slots by default
Date: Mon, 30 Nov 2009 18:22:44 +0100 [thread overview]
Message-ID: <20091130172243.GA30779@lst.de> (raw)
In-Reply-To: <20091118171232.GB25541@lst.de>
Current TRIM/UNMAP/etc implementation are slow enough that discarding
small chunk during run time is a bad idea. So only discard the whole
swap space on swapon by default, but require the admin to enable it
for run-time discards using the new vm.discard_swapspace sysctl.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Index: linux-2.6/include/linux/swap.h
===================================================================
--- linux-2.6.orig/include/linux/swap.h 2009-11-27 11:50:47.319003920 +0100
+++ linux-2.6/include/linux/swap.h 2009-11-27 11:51:55.617286868 +0100
@@ -247,6 +247,7 @@ extern unsigned long mem_cgroup_shrink_n
extern int __isolate_lru_page(struct page *page, int mode, int file);
extern unsigned long shrink_all_memory(unsigned long nr_pages);
extern int vm_swappiness;
+extern int vm_discard_swapspace;
extern int remove_mapping(struct address_space *mapping, struct page *page);
extern long vm_total_pages;
Index: linux-2.6/kernel/sysctl.c
===================================================================
--- linux-2.6.orig/kernel/sysctl.c 2009-11-27 11:49:02.935254088 +0100
+++ linux-2.6/kernel/sysctl.c 2009-11-27 11:53:10.333006621 +0100
@@ -1163,6 +1163,16 @@ static struct ctl_table vm_table[] = {
.extra1 = &zero,
.extra2 = &one_hundred,
},
+ {
+ .ctl_name = CTL_UNNUMBERED,
+ .procname = "discard_swapspace",
+ .data = &vm_discard_swapspace,
+ .maxlen = sizeof(vm_discard_swapspace),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &one,
+ },
#ifdef CONFIG_HUGETLB_PAGE
{
.procname = "nr_hugepages",
Index: linux-2.6/mm/swapfile.c
===================================================================
--- linux-2.6.orig/mm/swapfile.c 2009-11-27 11:53:19.449254088 +0100
+++ linux-2.6/mm/swapfile.c 2009-11-27 11:54:07.883255931 +0100
@@ -41,6 +41,7 @@ long nr_swap_pages;
long total_swap_pages;
static int swap_overflow;
static int least_priority;
+int vm_discard_swapspace;
static const char Bad_file[] = "Bad swap file entry ";
static const char Unused_file[] = "Unused swap file entry ";
@@ -1978,7 +1979,7 @@ SYSCALL_DEFINE2(swapon, const char __use
p->flags |= SWP_SOLIDSTATE;
p->cluster_next = 1 + (random32() % p->highest_bit);
}
- if (discard_swap(p) == 0)
+ if (discard_swap(p) == 0 && vm_discard_swapspace)
p->flags |= SWP_DISCARDABLE;
}
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2009-11-30 17:22 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-10-30 6:51 unconditional discard calls in the swap code Christoph Hellwig
2009-10-30 17:26 ` Hugh Dickins
2009-11-18 17:12 ` Christoph Hellwig
2009-11-30 17:22 ` Christoph Hellwig [this message]
2009-11-30 18:28 ` [PATCH] mm: don't discard unused swap slots by default Hugh Dickins
2009-11-30 18:58 ` Martin K. Petersen
2009-12-31 0:33 ` Hugh Dickins
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=20091130172243.GA30779@lst.de \
--to=hch@lst.de \
--cc=hugh.dickins@tiscali.co.uk \
--cc=jens.axboe@oracle.com \
--cc=linux-mm@kvack.org \
--cc=linux-scsi@vger.kernel.org \
--cc=matthew@wil.cx \
/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