From: Pablo Neira Ayuso <pablo@netfilter.org>
To: netfilter-devel@vger.kernel.org
Cc: davem@davemloft.net, netdev@vger.kernel.org
Subject: [PATCH 22/23] netfilter: nf_tables: performance set policy skips size description in selection
Date: Tue, 7 Nov 2017 01:52:12 +0100 [thread overview]
Message-ID: <20171107005213.22618-23-pablo@netfilter.org> (raw)
In-Reply-To: <20171107005213.22618-1-pablo@netfilter.org>
Use the complexity and space notations if policy is performance, this
results in placing the bitmap set representation over the hashtable for
key <= 16 for better performance as we discussed during the last NFWS in
Faro, Portugal.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_tables_api.c | 11 +++--------
1 file changed, 3 insertions(+), 8 deletions(-)
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 929927171426..3b4a0739ee39 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2549,14 +2549,9 @@ nft_select_set_ops(const struct nft_ctx *ctx,
case NFT_SET_POL_PERFORMANCE:
if (est.lookup < best.lookup)
break;
- if (est.lookup == best.lookup) {
- if (!desc->size) {
- if (est.space < best.space)
- break;
- } else if (est.size < best.size) {
- break;
- }
- }
+ if (est.lookup == best.lookup &&
+ est.space < best.space)
+ break;
continue;
case NFT_SET_POL_MEMORY:
if (!desc->size) {
--
2.11.0
next prev parent reply other threads:[~2017-11-07 0:52 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-11-07 0:51 [PATCH 00/23] Netfilter/IPVS updates for net-next Pablo Neira Ayuso
2017-11-07 0:51 ` [PATCH 01/23] netfilter: ipset: Compress return logic Pablo Neira Ayuso
2017-11-07 0:51 ` [PATCH 02/23] netfilter: ipset: Fix sparse warnings Pablo Neira Ayuso
2017-11-07 0:51 ` [PATCH 03/23] netfilter: ipset: deduplicate prefixlen maps Pablo Neira Ayuso
2017-11-07 0:51 ` [PATCH 04/23] netfilter: nat: use test_and_clear_bit when deleting ct from bysource list Pablo Neira Ayuso
2017-11-07 0:51 ` [PATCH 05/23] netfilter: conntrack: add and use nf_l4proto_log_invalid Pablo Neira Ayuso
2017-11-07 0:51 ` [PATCH 06/23] netfilter: conntrack: add and use nf_ct_l4proto_log_invalid Pablo Neira Ayuso
2017-11-07 0:51 ` [PATCH 07/23] netfilter: conntrack: remove pf argument from l4 packet functions Pablo Neira Ayuso
2017-11-07 0:51 ` [PATCH 08/23] netfilter: x_tables: make xt_replace_table wait until old rules are not used anymore Pablo Neira Ayuso
2017-11-07 0:51 ` [PATCH 09/23] netfilter: x_tables: don't use seqlock when fetching old counters Pablo Neira Ayuso
2017-11-07 0:52 ` [PATCH 10/23] netfilter: conntrack: make l3proto trackers const Pablo Neira Ayuso
2017-11-07 0:52 ` [PATCH 11/23] netfilter: nf_conntrack_h323: Remove typedef struct Pablo Neira Ayuso
2017-11-07 0:52 ` [PATCH 12/23] netfilter: xt_connlimit: don't store address in the conn nodes Pablo Neira Ayuso
2017-11-07 0:52 ` [PATCH 13/23] netfilter: nf_ct_h323: Out Of Bound Read in Netfilter Conntrack Pablo Neira Ayuso
2017-11-07 0:52 ` [PATCH 14/23] netfilter: ipvs: Use %pS printk format for direct addresses Pablo Neira Ayuso
2017-11-07 0:52 ` [PATCH 15/23] netfilter: ipvs: Fix inappropriate output of procfs Pablo Neira Ayuso
2017-11-07 0:52 ` [PATCH 16/23] netfilter: ebtables: clean up initialization of buf Pablo Neira Ayuso
2017-11-07 0:52 ` [PATCH 17/23] netfilter: xt_connlimit: remove mask argument Pablo Neira Ayuso
2017-11-07 0:52 ` [PATCH 18/23] netfilter: nft_hash: fix nft_hash_deactivate Pablo Neira Ayuso
2017-11-07 0:52 ` [PATCH 19/23] netfilter: conntrack: don't cache nlattr_tuple_size result in nla_size Pablo Neira Ayuso
2017-11-07 0:52 ` [PATCH 20/23] netfilter: conntrack: move nf_ct_netns_{get,put}() to core Pablo Neira Ayuso
2017-11-07 0:52 ` [PATCH 21/23] netfilter: conntrack: use power efficient workqueue Pablo Neira Ayuso
2017-11-07 0:52 ` Pablo Neira Ayuso [this message]
2017-11-07 0:52 ` [PATCH 23/23] netfilter: nf_tables: get set elements via netlink Pablo Neira Ayuso
2017-11-08 5:32 ` [PATCH 00/23] Netfilter/IPVS updates for net-next David Miller
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=20171107005213.22618-23-pablo@netfilter.org \
--to=pablo@netfilter.org \
--cc=davem@davemloft.net \
--cc=netdev@vger.kernel.org \
--cc=netfilter-devel@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).