From: "Emilio G. Cota" <cota@braap.org>
To: Sergey Fedorov <serge.fdrv@gmail.com>
Cc: "QEMU Developers" <qemu-devel@nongnu.org>,
"MTTCG Devel" <mttcg@listserver.greensocs.com>,
"Alex Bennée" <alex.bennee@linaro.org>,
"Paolo Bonzini" <pbonzini@redhat.com>,
"Peter Crosthwaite" <crosthwaite.peter@gmail.com>,
"Richard Henderson" <rth@twiddle.net>
Subject: Re: [Qemu-devel] [PATCH v5 13/18] qht: support parallel writes
Date: Tue, 24 May 2016 20:10:04 -0400 [thread overview]
Message-ID: <20160525001004.GA3650@flamenco> (raw)
In-Reply-To: <5744D2F1.2050009@gmail.com>
On Wed, May 25, 2016 at 01:17:21 +0300, Sergey Fedorov wrote:
> >> With this implementation we could:
> >> (1) get rid of qht_map::stale
> >> (2) don't waste cycles waiting for resize to complete
> > I'll include this in v6.
>
> How is it by perf?
Not much of a difference, since resize is a slow path. Calling
qht-bench with lots of update and resize threads performs very
poorly either way =D
I like the change though because using the mutex here simplifies
the resize code; there's no guilt anymore attached to holding the lock
for some time (e.g. when allocating a new, possible quite large,
map), whereas with the spinlock we would allocate it before
acquiring the lock, without knowing whether the allocation would
be needed in the end.
Emilio
next prev parent reply other threads:[~2016-05-25 0:10 UTC|newest]
Thread overview: 79+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-05-14 3:34 [Qemu-devel] [PATCH v5 00/18] tb hash improvements Emilio G. Cota
2016-05-14 3:34 ` [Qemu-devel] [PATCH v5 01/18] compiler.h: add QEMU_ALIGNED() to enforce struct alignment Emilio G. Cota
2016-05-14 3:34 ` [Qemu-devel] [PATCH v5 02/18] seqlock: remove optional mutex Emilio G. Cota
2016-05-14 3:34 ` [Qemu-devel] [PATCH v5 03/18] seqlock: rename write_lock/unlock to write_begin/end Emilio G. Cota
2016-05-14 3:34 ` [Qemu-devel] [PATCH v5 04/18] include/processor.h: define cpu_relax() Emilio G. Cota
2016-05-18 17:47 ` Sergey Fedorov
2016-05-18 18:29 ` Emilio G. Cota
2016-05-18 18:37 ` Sergey Fedorov
2016-05-14 3:34 ` [Qemu-devel] [PATCH v5 05/18] atomics: add atomic_test_and_set_acquire Emilio G. Cota
2016-05-16 10:05 ` Paolo Bonzini
2016-05-17 16:15 ` Sergey Fedorov
2016-05-17 16:23 ` Paolo Bonzini
2016-05-17 16:47 ` Sergey Fedorov
2016-05-17 17:08 ` Paolo Bonzini
2016-05-14 3:34 ` [Qemu-devel] [PATCH v5 06/18] atomics: add atomic_read_acquire and atomic_set_release Emilio G. Cota
2016-05-15 10:22 ` Pranith Kumar
2016-05-16 18:27 ` Emilio G. Cota
2016-05-17 16:53 ` Sergey Fedorov
2016-05-17 17:08 ` Paolo Bonzini
2016-05-14 3:34 ` [Qemu-devel] [PATCH v5 07/18] qemu-thread: add simple test-and-set spinlock Emilio G. Cota
[not found] ` <573B5134.8060104@gmail.com>
2016-05-17 19:19 ` Richard Henderson
2016-05-17 19:57 ` Sergey Fedorov
2016-05-17 20:01 ` Sergey Fedorov
2016-05-17 22:12 ` Richard Henderson
2016-05-17 22:22 ` Richard Henderson
2016-05-17 20:04 ` Emilio G. Cota
2016-05-17 20:20 ` Sergey Fedorov
2016-05-18 0:28 ` Emilio G. Cota
2016-05-18 14:18 ` Sergey Fedorov
2016-05-18 14:47 ` Sergey Fedorov
2016-05-18 14:59 ` Paolo Bonzini
2016-05-18 15:05 ` Sergey Fedorov
2016-05-18 15:09 ` Paolo Bonzini
2016-05-18 16:59 ` Emilio G. Cota
2016-05-18 17:00 ` Paolo Bonzini
2016-05-18 15:35 ` Peter Maydell
2016-05-18 15:36 ` Paolo Bonzini
2016-05-18 15:44 ` Peter Maydell
2016-05-18 15:59 ` Sergey Fedorov
2016-05-18 16:02 ` Richard Henderson
2016-05-17 19:38 ` Emilio G. Cota
2016-05-17 20:35 ` Sergey Fedorov
2016-05-17 23:18 ` Emilio G. Cota
2016-05-18 13:59 ` Sergey Fedorov
2016-05-18 14:05 ` Paolo Bonzini
2016-05-18 14:10 ` Sergey Fedorov
2016-05-18 14:40 ` Paolo Bonzini
2016-05-18 18:21 ` Sergey Fedorov
2016-05-18 19:04 ` Emilio G. Cota
2016-05-18 19:51 ` Sergey Fedorov
2016-05-18 20:52 ` Emilio G. Cota
2016-05-18 20:57 ` Sergey Fedorov
2016-05-14 3:34 ` [Qemu-devel] [PATCH v5 08/18] exec: add tb_hash_func5, derived from xxhash Emilio G. Cota
2016-05-17 17:22 ` Sergey Fedorov
2016-05-17 19:48 ` Emilio G. Cota
2016-05-14 3:34 ` [Qemu-devel] [PATCH v5 09/18] tb hash: hash phys_pc, pc, and flags with xxhash Emilio G. Cota
2016-05-17 17:47 ` Sergey Fedorov
2016-05-17 19:09 ` Emilio G. Cota
2016-05-14 3:34 ` [Qemu-devel] [PATCH v5 10/18] qdist: add module to represent frequency distributions of data Emilio G. Cota
2016-05-14 3:34 ` [Qemu-devel] [PATCH v5 11/18] qdist: add test program Emilio G. Cota
2016-05-14 3:34 ` [Qemu-devel] [PATCH v5 12/18] qht: QEMU's fast, resizable and scalable Hash Table Emilio G. Cota
2016-05-20 22:13 ` Sergey Fedorov
2016-05-21 2:48 ` Emilio G. Cota
2016-05-21 17:41 ` Emilio G. Cota
2016-05-22 8:01 ` Alex Bennée
2016-05-23 5:35 ` Emilio G. Cota
2016-05-21 20:07 ` Sergey Fedorov
2016-05-23 19:29 ` Sergey Fedorov
2016-05-14 3:34 ` [Qemu-devel] [PATCH v5 13/18] qht: support parallel writes Emilio G. Cota
2016-05-23 20:28 ` Sergey Fedorov
2016-05-24 22:07 ` Emilio G. Cota
2016-05-24 22:17 ` Sergey Fedorov
2016-05-25 0:10 ` Emilio G. Cota [this message]
2016-05-14 3:34 ` [Qemu-devel] [PATCH v5 14/18] qht: add test program Emilio G. Cota
2016-05-14 3:34 ` [Qemu-devel] [PATCH v5 15/18] qht: add qht-bench, a performance benchmark Emilio G. Cota
2016-05-14 3:34 ` [Qemu-devel] [PATCH v5 16/18] qht: add test-qht-par to invoke qht-bench from 'check' target Emilio G. Cota
2016-05-14 3:34 ` [Qemu-devel] [PATCH v5 17/18] tb hash: track translated blocks with qht Emilio G. Cota
2016-05-14 3:34 ` [Qemu-devel] [PATCH v5 18/18] translate-all: add tb hash bucket info to 'info jit' dump Emilio G. Cota
2016-05-23 22:26 ` [Qemu-devel] [PATCH v5 00/18] tb hash improvements Sergey Fedorov
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=20160525001004.GA3650@flamenco \
--to=cota@braap.org \
--cc=alex.bennee@linaro.org \
--cc=crosthwaite.peter@gmail.com \
--cc=mttcg@listserver.greensocs.com \
--cc=pbonzini@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=rth@twiddle.net \
--cc=serge.fdrv@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 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).