From: "Jörn Engel" <joern@purestorage.com>
To: Mike Galbraith <umgwanakikbuti@gmail.com>
Cc: Michal Hocko <mhocko@kernel.org>,
Spencer Baugh <sbaugh@catern.com>, Toshi Kani <toshi.kani@hp.com>,
Andrew Morton <akpm@linux-foundation.org>,
Fengguang Wu <fengguang.wu@intel.com>,
Joern Engel <joern@logfs.org>,
"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
Mel Gorman <mgorman@suse.de>,
Johannes Weiner <hannes@cmpxchg.org>,
Shachar Raindel <raindel@mellanox.com>,
Boaz Harrosh <boaz@plexistor.com>,
Andy Lutomirski <luto@amacapital.net>,
Joonsoo Kim <iamjoonsoo.kim@lge.com>,
Andrey Ryabinin <a.ryabinin@samsung.com>,
Roman Pen <r.peniaev@gmail.com>,
Andrey Konovalov <adech.fo@gmail.com>,
Eric Dumazet <edumazet@google.com>,
Dmitry Vyukov <dvyukov@google.com>,
Rob Jones <rob.jones@codethink.co.uk>,
WANG Chao <chaowang@redhat.com>,
open list <linux-kernel@vger.kernel.org>,
"open list:MEMORY MANAGEMENT" <linux-mm@kvack.org>,
Spencer Baugh <Spencer.baugh@purestorage.com>
Subject: Re: [PATCH] mm: add resched points to remap_pmd_range/ioremap_pmd_range
Date: Thu, 30 Jul 2015 09:58:03 -0700 [thread overview]
Message-ID: <20150730165803.GA17882@Sligo.logfs.org> (raw)
In-Reply-To: <1438269775.23663.58.camel@gmail.com>
On Thu, Jul 30, 2015 at 05:22:55PM +0200, Mike Galbraith wrote:
>
> I piddled about with the thought that it might be nice to be able to
> sprinkle cond_resched() about to cut rt latencies without wrecking
> normal load throughput, cobbled together a cond_resched_rt().
>
> On my little box that was a waste of time, as the biggest hits are block
> softirq and free_hot_cold_page_list().
Block softirq is one of our problems as well. It is a bit of a joke
that __do_softirq() moves work to ksoftirqd after 2ms, but block softirq
can take several 100ms in bad cases.
We could give individual softirqs a time budget. If they exceed the
budget they should complete, but reassert themselves. Not sure about
the rest, but that would be pretty simple to implement for block
softirq.
Jorn
--
Happiness isn't having what you want, it's wanting what you have.
-- unknown
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
WARNING: multiple messages have this Message-ID (diff)
From: "Jörn Engel" <joern@purestorage.com>
To: Mike Galbraith <umgwanakikbuti@gmail.com>
Cc: Michal Hocko <mhocko@kernel.org>,
Spencer Baugh <sbaugh@catern.com>, Toshi Kani <toshi.kani@hp.com>,
Andrew Morton <akpm@linux-foundation.org>,
Fengguang Wu <fengguang.wu@intel.com>,
Joern Engel <joern@logfs.org>,
"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
Mel Gorman <mgorman@suse.de>,
Johannes Weiner <hannes@cmpxchg.org>,
Shachar Raindel <raindel@mellanox.com>,
Boaz Harrosh <boaz@plexistor.com>,
Andy Lutomirski <luto@amacapital.net>,
Joonsoo Kim <iamjoonsoo.kim@lge.com>,
Andrey Ryabinin <a.ryabinin@samsung.com>,
Roman Pen <r.peniaev@gmail.com>,
Andrey Konovalov <adech.fo@gmail.com>,
Eric Dumazet <edumazet@google.com>,
Dmitry Vyukov <dvyukov@google.com>,
Rob Jones <rob.jones@codethink.co.uk>,
WANG Chao <chaowang@redhat.com>,
open list <linux-kernel@vger.kernel.org>,
"open list:MEMORY MANAGEMENT" <linux-mm@kvack.org>,
Spencer Baugh <Spencer.baugh@purestorage.com>
Subject: Re: [PATCH] mm: add resched points to remap_pmd_range/ioremap_pmd_range
Date: Thu, 30 Jul 2015 09:58:03 -0700 [thread overview]
Message-ID: <20150730165803.GA17882@Sligo.logfs.org> (raw)
In-Reply-To: <1438269775.23663.58.camel@gmail.com>
On Thu, Jul 30, 2015 at 05:22:55PM +0200, Mike Galbraith wrote:
>
> I piddled about with the thought that it might be nice to be able to
> sprinkle cond_resched() about to cut rt latencies without wrecking
> normal load throughput, cobbled together a cond_resched_rt().
>
> On my little box that was a waste of time, as the biggest hits are block
> softirq and free_hot_cold_page_list().
Block softirq is one of our problems as well. It is a bit of a joke
that __do_softirq() moves work to ksoftirqd after 2ms, but block softirq
can take several 100ms in bad cases.
We could give individual softirqs a time budget. If they exceed the
budget they should complete, but reassert themselves. Not sure about
the rest, but that would be pretty simple to implement for block
softirq.
Jörn
--
Happiness isn't having what you want, it's wanting what you have.
-- unknown
next prev parent reply other threads:[~2015-07-30 16:58 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-07-23 21:54 [PATCH] mm: add resched points to remap_pmd_range/ioremap_pmd_range Spencer Baugh
2015-07-23 21:54 ` Spencer Baugh
2015-07-23 23:32 ` Toshi Kani
2015-07-23 23:32 ` Toshi Kani
2015-07-24 17:00 ` Jörn Engel
2015-07-24 17:00 ` Jörn Engel
2015-07-24 7:04 ` Michal Hocko
2015-07-24 7:04 ` Michal Hocko
2015-07-24 16:56 ` Jörn Engel
2015-07-24 16:56 ` Jörn Engel
2015-07-27 7:08 ` Michal Hocko
2015-07-27 7:08 ` Michal Hocko
2015-07-27 8:29 ` Mike Galbraith
2015-07-27 8:29 ` Mike Galbraith
2015-07-27 15:18 ` Jörn Engel
2015-07-27 15:18 ` Jörn Engel
2015-07-28 13:32 ` Michal Hocko
2015-07-28 13:32 ` Michal Hocko
2015-07-28 17:08 ` Jörn Engel
2015-07-28 17:08 ` Jörn Engel
2015-07-29 9:54 ` Michal Hocko
2015-07-29 9:54 ` Michal Hocko
2015-07-30 15:22 ` Mike Galbraith
2015-07-30 15:22 ` Mike Galbraith
2015-07-30 16:58 ` Jörn Engel [this message]
2015-07-30 16:58 ` Jörn Engel
2015-07-30 18:55 ` Mike Galbraith
2015-07-30 18:55 ` Mike Galbraith
2015-08-09 9:25 ` [hack] sched: create PREEMPT_VOLUNTARY_RT and some RT specific resched points Mike Galbraith
2015-08-09 9:25 ` Mike Galbraith
2015-08-09 10:51 ` Mike Galbraith
2015-08-09 10:51 ` Mike Galbraith
2015-08-06 8:55 ` [PATCH] mm: add resched points to remap_pmd_range/ioremap_pmd_range Mike Galbraith
2015-08-06 8:55 ` Mike Galbraith
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=20150730165803.GA17882@Sligo.logfs.org \
--to=joern@purestorage.com \
--cc=Spencer.baugh@purestorage.com \
--cc=a.ryabinin@samsung.com \
--cc=adech.fo@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=boaz@plexistor.com \
--cc=chaowang@redhat.com \
--cc=dvyukov@google.com \
--cc=edumazet@google.com \
--cc=fengguang.wu@intel.com \
--cc=hannes@cmpxchg.org \
--cc=iamjoonsoo.kim@lge.com \
--cc=joern@logfs.org \
--cc=kirill.shutemov@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=luto@amacapital.net \
--cc=mgorman@suse.de \
--cc=mhocko@kernel.org \
--cc=r.peniaev@gmail.com \
--cc=raindel@mellanox.com \
--cc=rob.jones@codethink.co.uk \
--cc=sbaugh@catern.com \
--cc=toshi.kani@hp.com \
--cc=umgwanakikbuti@gmail.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.