From: | Adam Carter <adamcarter3@×××××.com> | ||
---|---|---|---|
To: | gentoo-user@l.g.o | ||
Subject: | Re: [gentoo-user] Re: Expect a ~15% average slowdown if you use an Intel processor | ||
Date: | Sat, 06 Jan 2018 00:26:51 | ||
Message-Id: | CAC=wYCEvh8PHMzZpAjBzAK3fpf4-b1XfmennTVpTA1eK6+uEPw@mail.gmail.com | ||
In Reply to: | Re: [gentoo-user] Re: Expect a ~15% average slowdown if you use an Intel processor by Peter Humphrey |
1 | > |
2 | > > So, HAVE_EBPF_JIT=y just means that BPF JIT _can_ be done on x86. There |
3 | > > is a separate BPF_JIT setting to actually enable it. |
4 | > |
5 | > Well, that doesn't seem to be present here. Just the HAVE_ symbol. |
6 | |
7 | |
8 | Careful, there's BPF and EBPF. |
9 | |
10 | $ zgrep BPF /proc/config.gz |
11 | CONFIG_CGROUP_BPF=y |
12 | CONFIG_BPF=y |
13 | CONFIG_BPF_SYSCALL=y |
14 | # CONFIG_NETFILTER_XT_MATCH_BPF is not set |
15 | # CONFIG_NET_CLS_BPF is not set |
16 | # CONFIG_NET_ACT_BPF is not set |
17 | # CONFIG_BPF_JIT is not set |
18 | # CONFIG_BPF_STREAM_PARSER is not set |
19 | CONFIG_HAVE_EBPF_JIT=y |
20 | # CONFIG_TEST_BPF is not set |
Subject | Author |
---|---|
Re: [gentoo-user] Re: Expect a ~15% average slowdown if you use an Intel processor | Rich Freeman <rich0@g.o> |
Re: [gentoo-user] Re: Expect a ~15% average slowdown if you use an Intel processor | Walter Dnes <waltdnes@××××××××.org> |