From: Miroslav Benes <mbenes@suse.cz>
To: David Vernet <void@manifault.com>
Cc: live-patching@vger.kernel.org, linux-kernel@vger.kernel.org,
jpoimboe@redhat.com, pmladek@suse.com, jikos@kernel.org,
joe.lawrence@redhat.com
Subject: Re: [PATCH] livepatch: Avoid CPU hogging with cond_resched
Date: Wed, 5 Jan 2022 11:17:23 +0100 (CET) [thread overview]
Message-ID: <alpine.LSU.2.21.2201051045540.12365@pobox.suse.cz> (raw)
In-Reply-To: <20211229215646.830451-1-void@manifault.com>
On Wed, 29 Dec 2021, David Vernet wrote:
> When initializing a 'struct klp_object' in klp_init_object_loaded(), and
> performing relocations in klp_resolve_symbols(), klp_find_object_symbol()
> is invoked to look up the address of a symbol in an already-loaded module
> (or vmlinux). This, in turn, calls kallsyms_on_each_symbol() or
> module_kallsyms_on_each_symbol() to find the address of the symbol that is
> being patched.
>
> It turns out that symbol lookups often take up the most CPU time when
> enabling and disabling a patch, and may hog the CPU and cause other tasks
> on that CPU's runqueue to starve -- even in paths where interrupts are
> enabled. For example, under certain workloads, enabling a KLP patch with
> many objects or functions may cause ksoftirqd to be starved, and thus for
> interrupts to be backlogged and delayed. This may end up causing TCP
> retransmits on the host where the KLP patch is being applied, and in
> general, may cause any interrupts serviced by softirqd to be delayed while
> the patch is being applied.
>
> So as to ensure that kallsyms_on_each_symbol() does not end up hogging the
> CPU, this patch adds a call to cond_resched() in kallsyms_on_each_symbol()
> and module_kallsyms_on_each_symbol(), which are invoked when doing a symbol
> lookup in vmlinux and a module respectively. Without this patch, if a
> live-patch is applied on a 36-core Intel host with heavy TCP traffic, a
> ~10x spike is observed in TCP retransmits while the patch is being applied.
> Additionally, collecting sched events with perf indicates that ksoftirqd is
> awakened ~1.3 seconds before it's eventually scheduled. With the patch, no
> increase in TCP retransmit events is observed, and ksoftirqd is scheduled
> shortly after it's awakened.
>
> Signed-off-by: David Vernet <void@manifault.com>
Acked-by: Miroslav Benes <mbenes@suse.cz>
I had similar ideas Petr mentioned elsewhere, but I, also, have no strong
opinion about it. Especially when livepatch is the only user of the said
interface.
M
next prev parent reply other threads:[~2022-01-05 10:17 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-12-29 21:56 [PATCH] livepatch: Avoid CPU hogging with cond_resched David Vernet
2022-01-05 10:17 ` Miroslav Benes [this message]
2022-01-07 0:21 ` Song Liu
2022-01-07 8:17 ` Petr Mladek
2022-01-10 14:55 ` David Vernet
2022-01-07 13:03 ` Petr Mladek
2022-01-07 14:13 ` Joe Lawrence
2022-01-07 16:46 ` Song Liu
2022-01-10 16:16 ` Joe Lawrence
2022-01-11 1:49 ` Song Liu
2021-12-30 4:16 David Vernet
2021-12-31 23:05 ` Kumar Kartikeya Dwivedi
2022-01-03 16:04 ` Petr Mladek
2022-01-10 14:38 ` David Vernet
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=alpine.LSU.2.21.2201051045540.12365@pobox.suse.cz \
--to=mbenes@suse.cz \
--cc=jikos@kernel.org \
--cc=joe.lawrence@redhat.com \
--cc=jpoimboe@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=live-patching@vger.kernel.org \
--cc=pmladek@suse.com \
--cc=void@manifault.com \
/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).