Linux Trace Kernel
 help / color / mirror / Atom feed
From: Jiri Olsa <olsajiri@gmail.com>
To: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Cc: Jiri Olsa <olsajiri@gmail.com>, Naveen N Rao <naveen@kernel.org>,
	"David S. Miller" <davem@davemloft.net>,
	Peter Zijlstra <peterz@infradead.org>,
	Josh Poimboeuf <jpoimboe@kernel.org>,
	Jason Baron <jbaron@akamai.com>,
	Alice Ryhl <aliceryhl@google.com>,
	Steven Rostedt <rostedt@goodmis.org>,
	Ard Biesheuvel <ardb@kernel.org>,
	Thomas Gleixner <tglx@kernel.org>, Ingo Molnar <mingo@redhat.com>,
	Alan Maguire <almagui@kernel.org>,
	x86@kernel.org, linux-trace-kernel@vger.kernel.org,
	linux-kernel@vger.kernel.org, bpf@vger.kernel.org
Subject: Re: [PATCH 04/13] kprobes: Maintain an rbtree of registered probes
Date: Wed, 11 Nov 2026 11:49:10 +0100	[thread overview]
Message-ID: <avRIJuSolFTwT_Tk@krava> (raw)
In-Reply-To: <undine-1794325083765212173-9c2dd2a4d5c010fe@undined.local>

On Wed, Nov 11, 2026 at 12:38:03AM +0900, Masami Hiramatsu (Google) wrote:
> On Tue, 10 Nov 2026 11:37:38 +0100, Jiri Olsa <olsajiri@gmail.com> wrote:
> > On Tue, Nov 10, 2026 at 08:12:19AM +0000, Masami Hiramatsu (Google) wrote:
> > > On Mon,  9 Nov 2026 20:55:17 +0100, Jiri Olsa <jolsa@kernel.org> wrote:
> > > > Add an address-ordered rbtree for registered probes. Keep it synchronized
> > > > with the hash table when probes are added, removed, or replaced by
> > > > aggregator probes.
> > > 
> > > Could you tell me why don't you use hlist (get_kprobe) instead?
> > > I would NOT like 2 different lists which is basically doing the
> > > same thing.
> > 
> > The speedup comes from finding the first relevant kprobe, then iterating
> > over the remaining probes in address order. The hash table supports
> > exact-address lookups, but it doesn’t provide that ordering.
> > 
> > I agree that maintaining both indexes is less convenient. What do you think
> > about centralizing their updates as in the change below? untested
> 
> If you can replace the hash table with other faster design, it is OK to me.
> But I would like to avoid this simple-adding another lookup table for the
> rare usage case (because of the maintenance cost, and duplicating a list
> makes it difficult to handle cases where discrepancies arise between the
> two lists.)
> 
> Can you change the size of the hashtable and measure how the performance
> is changed? I need more options.

yep, I'll check on that

jirka

  reply	other threads:[~2026-11-11 10:49 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-09 19:49 [PATCH 00/13] kprobes: Reduce registration and optimization lookup costs Jiri Olsa
2026-11-09 19:49 ` [PATCH 01/13] static_call: Index code text reservation lookups Jiri Olsa
2026-11-09 19:49 ` [PATCH 02/13] jump_label: Index " Jiri Olsa
2026-11-09 19:49 ` [PATCH 03/13] jump_label/x86: Avoid decoding instructions for jump entry size Jiri Olsa
2026-11-09 19:55 ` [PATCH 04/13] kprobes: Maintain an rbtree of registered probes Jiri Olsa
2026-11-10  8:12   ` Masami Hiramatsu (Google)
2026-11-10 10:37     ` Jiri Olsa
2026-11-10 15:38       ` Masami Hiramatsu (Google)
2026-11-11 10:49         ` Jiri Olsa [this message]
2026-11-10 23:45   ` sashiko-bot
2026-11-09 19:56 ` [PATCH 05/13] kprobes: Add an iterator for address ranges Jiri Olsa
2026-11-09 19:56 ` [PATCH 06/13] kprobes: Add an address iterator for probe lookup Jiri Olsa
2026-11-09 19:56 ` [PATCH 07/13] kprobes: Use kprobe iterator in get_optimized_kprobe Jiri Olsa
2026-11-09 19:57 ` [PATCH 08/13] x86/kprobes: Use kprobe iterator in __recover_optprobed_insn Jiri Olsa
2026-11-09 19:57 ` [PATCH 09/13] x86/kprobes: Use kprobe iterator in arch_check_optimized_kprobe Jiri Olsa
2026-11-11  0:17   ` sashiko-bot
2026-11-09 19:57 ` [PATCH 10/13] x86/kprobes: Use kprobe address iterator in can_optimize Jiri Olsa
2026-11-09 19:57 ` [PATCH 11/13] x86/kprobes: Use kprobe address iterator in can_probe Jiri Olsa
2026-11-09 19:58 ` [PATCH 12/13] x86/kprobes: Use kprobe address iterator in in copy_optimized_instructions Jiri Olsa
2026-11-09 19:58 ` [PATCH 13/13] samples/kprobes: Add batch probe example Jiri Olsa
2026-11-11  0:49   ` sashiko-bot
2026-11-11  2:20   ` kernel test robot

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=avRIJuSolFTwT_Tk@krava \
    --to=olsajiri@gmail.com \
    --cc=aliceryhl@google.com \
    --cc=almagui@kernel.org \
    --cc=ardb@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=davem@davemloft.net \
    --cc=jbaron@akamai.com \
    --cc=jpoimboe@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-trace-kernel@vger.kernel.org \
    --cc=mhiramat@kernel.org \
    --cc=mingo@redhat.com \
    --cc=naveen@kernel.org \
    --cc=peterz@infradead.org \
    --cc=rostedt@goodmis.org \
    --cc=tglx@kernel.org \
    --cc=x86@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