From: Thomas Gleixner <tglx@linutronix.de>
To: Eric Dumazet <edumazet@google.com>
Cc: LKML <linux-kernel@vger.kernel.org>,
Ingo Molnar <mingo@kernel.org>,
Peter Zijlstra <peterz@infradead.org>,
"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
Frederic Weisbecker <fweisbec@gmail.com>,
Chris Mason <clm@fb.com>, Arjan van de Ven <arjan@infradead.org>,
rt@linutronix.de, Rik van Riel <riel@redhat.com>,
Linus Torvalds <torvalds@linux-foundation.org>,
George Spelvin <linux@sciencehorizons.net>,
Len Brown <lenb@kernel.org>
Subject: Re: [patch V2 00/20] timer: Refactor the timer wheel
Date: Mon, 20 Jun 2016 15:56:10 +0200 (CEST) [thread overview]
Message-ID: <alpine.DEB.2.11.1606201541000.5839@nanos> (raw)
In-Reply-To: <CANn89iLoVRcO1quHnKLFhvt56Jwk3Rht+v0x7pKVoE=MXFJN-w@mail.gmail.com>
On Fri, 17 Jun 2016, Eric Dumazet wrote:
> To avoid increasing probability of such events we would need to have
> at least 4 ms difference between the RTO timer and delack timer.
>
> Meaning we have to increase both of them and increase P99 latencies of
> RPC workloads.
>
> Maybe a switch to hrtimer would be less risky.
> But I do not know yet if it is doable without big performance penalty.
That will be a big performance issue. So we have the following choices:
1) Increase the wheel size for HZ=1000. Doable, but utter waste of space and
obviously more pointless work when collecting expired timers.
2) Cut off at 37hrs for HZ=1000. We could make this configurable as a 1000HZ
option so datacenter folks can use this and people who don't care and want
better batching for power can use the 4ms thingy.
3) Split the wheel granularities. That would leave the first wheel with tick
granularity and the next 3 with 12.5% worst case and then for the further
out timers we'd switch to 25%.
Thoughts?
Thanks,
tglx
next prev parent reply other threads:[~2016-06-20 13:58 UTC|newest]
Thread overview: 52+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-06-17 13:26 [patch V2 00/20] timer: Refactor the timer wheel Thomas Gleixner
2016-06-17 13:26 ` [patch V2 01/20] timer: Make pinned a timer property Thomas Gleixner
2016-06-17 13:26 ` [patch V2 02/20] x86/apic/uv: Initialize timer as pinned Thomas Gleixner
2016-06-17 13:26 ` [patch V2 03/20] x86/mce: " Thomas Gleixner
2016-06-17 13:26 ` [patch V2 05/20] driver/net/ethernet/tile: " Thomas Gleixner
2016-06-21 18:14 ` Peter Zijlstra
2016-06-17 13:26 ` [patch V2 04/20] cpufreq/powernv: " Thomas Gleixner
2016-06-17 13:26 ` [patch V2 06/20] drivers/tty/metag_da: " Thomas Gleixner
2016-06-17 13:26 ` [patch V2 07/20] drivers/tty/mips_ejtag: " Thomas Gleixner
2016-06-17 13:26 ` [patch V2 08/20] net/ipv4/inet: Initialize timers " Thomas Gleixner
2016-06-17 13:26 ` [patch V2 09/20] timer: Remove mod_timer_pinned Thomas Gleixner
2016-06-17 13:26 ` [patch V2 10/20] hlist: Add hlist_is_singular_node() helper Thomas Gleixner
2016-06-17 13:26 ` [patch V2 11/20] timer: Give a few structs and members proper names Thomas Gleixner
2016-06-17 13:26 ` [patch V2 12/20] timer: Switch to a non cascading wheel Thomas Gleixner
2016-06-18 9:55 ` George Spelvin
2016-06-24 10:06 ` Thomas Gleixner
2016-06-17 13:26 ` [patch V2 13/20] timer: Remove slack leftovers Thomas Gleixner
2016-06-17 13:26 ` [patch V2 14/20] timer: Move __run_timers() function Thomas Gleixner
2016-06-17 13:26 ` [patch V2 15/20] timer: Optimize collect timers for NOHZ Thomas Gleixner
2016-06-17 13:26 ` [patch V2 16/20] tick/sched: Remove pointless empty function Thomas Gleixner
2016-06-17 13:26 ` [patch V2 17/20] timer: Forward wheel clock whenever possible Thomas Gleixner
2016-06-17 13:26 ` [patch V2 18/20] timer: Only wake softirq if necessary Thomas Gleixner
2016-06-17 13:26 ` [patch V2 19/20] timer: Split out index calculation Thomas Gleixner
2016-06-17 13:26 ` [patch V2 20/20] timer: Optimization for same expiry time in mod_timer() Thomas Gleixner
2016-06-17 13:48 ` [patch V2 00/20] timer: Refactor the timer wheel Eric Dumazet
2016-06-17 13:57 ` Thomas Gleixner
2016-06-17 14:25 ` Eric Dumazet
2016-06-20 13:56 ` Thomas Gleixner [this message]
2016-06-20 14:46 ` Arjan van de Ven
2016-06-20 14:46 ` Thomas Gleixner
2016-06-20 14:49 ` Arjan van de Ven
2016-06-20 19:03 ` Rik van Riel
2016-06-21 2:48 ` Eric Dumazet
2016-06-17 14:26 ` Arjan van de Ven
2016-06-20 15:05 ` Paul E. McKenney
2016-06-20 15:13 ` Thomas Gleixner
2016-06-20 15:41 ` Paul E. McKenney
2016-06-22 7:37 ` Mike Galbraith
2016-06-22 8:44 ` Thomas Gleixner
2016-06-22 9:06 ` Mike Galbraith
2016-06-22 13:37 ` Mike Galbraith
2016-06-22 10:28 ` [LTP] " Cyril Hrubis
2016-06-23 8:27 ` Thomas Gleixner
2016-06-23 11:47 ` Cyril Hrubis
2016-06-23 13:58 ` George Spelvin
2016-06-23 14:10 ` Thomas Gleixner
2016-06-23 15:11 ` Cyril Hrubis
2016-06-23 15:21 ` Thomas Gleixner
2016-06-23 16:31 ` Cyril Hrubis
2016-06-26 19:00 ` Pavel Machek
2016-06-26 19:21 ` Arjan van de Ven
2016-06-26 20:02 ` Pavel Machek
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.DEB.2.11.1606201541000.5839@nanos \
--to=tglx@linutronix.de \
--cc=arjan@infradead.org \
--cc=clm@fb.com \
--cc=edumazet@google.com \
--cc=fweisbec@gmail.com \
--cc=lenb@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux@sciencehorizons.net \
--cc=mingo@kernel.org \
--cc=paulmck@linux.vnet.ibm.com \
--cc=peterz@infradead.org \
--cc=riel@redhat.com \
--cc=rt@linutronix.de \
--cc=torvalds@linux-foundation.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).