Netdev Archive on lore.kernel.org
 help / color / Atom feed
From: "Tobin C. Harding" <tobin@kernel.org>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: "Tobin C. Harding" <tobin@kernel.org>,
	Jesper Dangaard Brouer <brouer@redhat.com>,
	Pekka Enberg <penberg@iki.fi>, Vlastimil Babka <vbabka@suse.cz>,
	Christoph Lameter <cl@linux.com>,
	David Rientjes <rientjes@google.com>,
	Joonsoo Kim <iamjoonsoo.kim@lge.com>, Tejun Heo <tj@kernel.org>,
	Qian Cai <cai@lca.pw>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Mel Gorman <mgorman@techsingularity.net>,
	Alexander Duyck <alexander.duyck@gmail.com>,
	Michal Hocko <mhocko@kernel.org>,
	Brendan Gregg <brendan.d.gregg@gmail.com>,
	linux-mm@kvack.org, netdev@vger.kernel.org,
	linux-kernel@vger.kernel.org
Subject: [PATCH 2/4] tools/vm/slabinfo: Add partial slab listing to -X
Date: Fri, 26 Apr 2019 12:26:20 +1000
Message-ID: <20190426022622.4089-3-tobin@kernel.org> (raw)
In-Reply-To: <20190426022622.4089-1-tobin@kernel.org>

We would like to see how fragmented the SLUB allocator is, one window
into fragmentation is the total number of partial slabs.

Currently `slabinfo -X` shows slabs sorted by loss and by size.  We can
use this option to also show slabs sorted by number of partial slabs.

Option '-X' can be used in conjunction with '-N' to control the number
of slabs shown e.g. list of top 5 slabs:

	slabinfo -X -N5

Add list of slabs ordered by number of partial slabs to output of
`slabinfo -X`.

Signed-off-by: Tobin C. Harding <tobin@kernel.org>
---
 tools/vm/slabinfo.c | 41 ++++++++++++++++++++++++++++-------------
 1 file changed, 28 insertions(+), 13 deletions(-)

diff --git a/tools/vm/slabinfo.c b/tools/vm/slabinfo.c
index e9b5437b2f28..3f3a2db65794 100644
--- a/tools/vm/slabinfo.c
+++ b/tools/vm/slabinfo.c
@@ -79,6 +79,7 @@ int sort_size;
 int sort_active;
 int set_debug;
 int show_ops;
+int sort_partial;
 int show_activity;
 int output_lines = -1;
 int sort_loss;
@@ -1047,6 +1048,8 @@ static void sort_slabs(void)
 				result = slab_activity(s1) < slab_activity(s2);
 			else if (sort_loss)
 				result = slab_waste(s1) < slab_waste(s2);
+			else if (sort_partial)
+				result = s1->partial < s2->partial;
 			else
 				result = strcasecmp(s1->name, s2->name);
 
@@ -1307,27 +1310,39 @@ static void output_slabs(void)
 	}
 }
 
+static void _xtotals(char *heading, char *underline,
+		     int loss, int size, int partial)
+{
+	printf("%s%s", heading, underline);
+	line = 0;
+	sort_loss = loss;
+	sort_size = size;
+	sort_partial = partial;
+	sort_slabs();
+	output_slabs();
+}
+
 static void xtotals(void)
 {
+	char *heading, *underline;
+
 	totals();
 
 	link_slabs();
 	rename_slabs();
 
-	printf("\nSlabs sorted by size\n");
-	printf("--------------------\n");
-	sort_loss = 0;
-	sort_size = 1;
-	sort_slabs();
-	output_slabs();
+	heading = "\nSlabs sorted by size\n";
+	underline = "--------------------\n";
+	_xtotals(heading, underline, 0, 1, 0);
+
+	heading = "\nSlabs sorted by loss\n";
+	underline = "--------------------\n";
+	_xtotals(heading, underline, 1, 0, 0);
+
+	heading = "\nSlabs sorted by number of partial slabs\n";
+	underline = "---------------------------------------\n";
+	_xtotals(heading, underline, 0, 0, 1);
 
-	printf("\nSlabs sorted by loss\n");
-	printf("--------------------\n");
-	line = 0;
-	sort_loss = 1;
-	sort_size = 0;
-	sort_slabs();
-	output_slabs();
 	printf("\n");
 }
 
-- 
2.21.0


  parent reply index

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-04-26  2:26 [PATCH 0/4] tools/vm/slabinfo: Add fragmentation output Tobin C. Harding
2019-04-26  2:26 ` [PATCH 1/4] tools/vm/slabinfo: Order command line options Tobin C. Harding
2019-04-26  2:26 ` Tobin C. Harding [this message]
2019-04-26  2:26 ` [PATCH 3/4] tools/vm/slabinfo: Add option to sort by partial slabs Tobin C. Harding
2019-04-26  2:26 ` [PATCH 4/4] tools/vm/slabinfo: Add sorting info to help menu Tobin C. Harding

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=20190426022622.4089-3-tobin@kernel.org \
    --to=tobin@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=alexander.duyck@gmail.com \
    --cc=brendan.d.gregg@gmail.com \
    --cc=brouer@redhat.com \
    --cc=cai@lca.pw \
    --cc=cl@linux.com \
    --cc=iamjoonsoo.kim@lge.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mgorman@techsingularity.net \
    --cc=mhocko@kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=penberg@iki.fi \
    --cc=rientjes@google.com \
    --cc=tj@kernel.org \
    --cc=torvalds@linux-foundation.org \
    --cc=vbabka@suse.cz \
    /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

Netdev Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/netdev/0 netdev/git/0.git
	git clone --mirror https://lore.kernel.org/netdev/1 netdev/git/1.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 netdev netdev/ https://lore.kernel.org/netdev \
		netdev@vger.kernel.org
	public-inbox-index netdev

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.netdev


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git