From: Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>
To: David Marchand <david.marchand@redhat.com>,
"Phil Yang (Arm Technology China)" <Phil.Yang@arm.com>
Cc: dev <dev@dpdk.org>, "thomas@monjalon.net" <thomas@monjalon.net>,
"jerinj@marvell.com" <jerinj@marvell.com>,
"hemant.agrawal@nxp.com" <hemant.agrawal@nxp.com>,
"Gavin Hu (Arm Technology China)" <Gavin.Hu@arm.com>,
nd <nd@arm.com>, nd <nd@arm.com>
Subject: Re: [dpdk-dev] [PATCH v1 0/3] MCS queued lock implementation
Date: Wed, 5 Jun 2019 19:59:56 +0000 [thread overview]
Message-ID: <AM0PR08MB5138A8280994C35B84B3473298160@AM0PR08MB5138.eurprd08.prod.outlook.com> (raw)
In-Reply-To: <CAJFAV8y8e7p9881pFYU8ZebKayHwAxe2CvBRhZ-nDXpgFzQXUQ@mail.gmail.com>
On Wed, Jun 5, 2019 at 6:00 PM Phil Yang <phil.yang@arm.com<mailto:phil.yang@arm.com>> wrote:
This patch set added MCS lock library and its unit test.
The MCS lock (proposed by JOHN M. MELLOR-CRUMMEY and MICHAEL L. SCOTT) provides
scalability by spinning on a CPU/thread local variable which avoids expensive
cache bouncings. It provides fairness by maintaining a list of acquirers and
passing the lock to each CPU/thread in the order they acquired the lock.
References:
1. http://web.mit.edu/6.173/www/currentsemester/readings/R06-scalable-synchronization-1991.pdf
2. https://lwn.net/Articles/590243/
Mirco-benchmarking result:
------------------------------------------------------------------------------------------------
MCS lock | spinlock | ticket lock
------------------------------+--------------------------------+--------------------------------
Test with lock on 13 cores... | Test with lock on 14 cores... | Test with lock on 14 cores...
Core [15] Cost Time = 22426 us| Core [14] Cost Time = 47974 us| Core [14] cost time = 66761 us
Core [16] Cost Time = 22382 us| Core [15] Cost Time = 46979 us| Core [15] cost time = 66766 us
Core [17] Cost Time = 22294 us| Core [16] Cost Time = 46044 us| Core [16] cost time = 66761 us
Core [18] Cost Time = 22412 us| Core [17] Cost Time = 28793 us| Core [17] cost time = 66767 us
Core [19] Cost Time = 22407 us| Core [18] Cost Time = 48349 us| Core [18] cost time = 66758 us
Core [20] Cost Time = 22436 us| Core [19] Cost Time = 19381 us| Core [19] cost time = 66766 us
Core [21] Cost Time = 22414 us| Core [20] Cost Time = 47914 us| Core [20] cost time = 66763 us
Core [22] Cost Time = 22405 us| Core [21] Cost Time = 48333 us| Core [21] cost time = 66766 us
Core [23] Cost Time = 22435 us| Core [22] Cost Time = 38900 us| Core [22] cost time = 66749 us
Core [24] Cost Time = 22401 us| Core [23] Cost Time = 45374 us| Core [23] cost time = 66765 us
Core [25] Cost Time = 22408 us| Core [24] Cost Time = 16121 us| Core [24] cost time = 66762 us
Core [26] Cost Time = 22380 us| Core [25] Cost Time = 42731 us| Core [25] cost time = 66768 us
Core [27] Cost Time = 22395 us| Core [26] Cost Time = 29439 us| Core [26] cost time = 66768 us
| Core [27] Cost Time = 38071 us| Core [27] cost time = 66767 us
------------------------------+--------------------------------+--------------------------------
Total Cost Time = 291195 us | Total Cost Time = 544403 us | Total cost time = 934687 us
------------------------------------------------------------------------------------------------
Had a quick look, interesting.
Quick comments:
- your numbers are for 13 cores, while the other are for 14, what is the reason?
- do we need per architecture header? all I can see is generic code, we might as well directly put rte_mcslock.h in the common/include directory.
- could we replace the current spinlock with this approach? is this more expensive than spinlock on lowly contended locks? is there a reason we want to keep all these approaches? we could have now 3 lock implementations.
- do we need to write the authors names in full capitalized version? it seems like you are shouting :-)
[Honnappa] IMO, writing full names is a cultural thing? I do not see any harm. But, I do think, we do not need to capitalize everything.
--
David Marchand
[Honnappa] This mail is appearing as HTML, would be good to change to text mode. It is much easier to add inline comments.
next prev parent reply other threads:[~2019-06-05 20:00 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-06-05 15:58 Phil Yang
2019-06-05 15:58 ` [dpdk-dev] [PATCH v1 1/3] eal/mcslock: add mcs " Phil Yang
2019-07-05 9:56 ` [dpdk-dev] [PATCH v2 0/3] MCS " Phil Yang
2019-07-05 9:56 ` [dpdk-dev] [PATCH v2 1/3] eal/mcslock: add mcs " Phil Yang
2019-07-05 9:56 ` [dpdk-dev] [PATCH v2 2/3] eal/mcslock: use generic msc queued lock on all arch Phil Yang
2019-07-05 9:56 ` [dpdk-dev] [PATCH v2 3/3] test/mcslock: add mcs queued lock unit test Phil Yang
2019-07-05 10:27 ` [dpdk-dev] [PATCH v3 0/3] MCS queued lock implementation Phil Yang
2019-07-05 10:27 ` [dpdk-dev] [PATCH v3 1/3] eal/mcslock: add mcs " Phil Yang
2019-07-05 10:27 ` [dpdk-dev] [PATCH v3 2/3] eal/mcslock: use generic msc queued lock on all arch Phil Yang
2019-07-05 10:27 ` [dpdk-dev] [PATCH v3 3/3] test/mcslock: add mcs queued lock unit test Phil Yang
2019-07-07 21:49 ` [dpdk-dev] [PATCH v3 0/3] MCS queued lock implementation Thomas Monjalon
2019-06-05 15:58 ` [dpdk-dev] [PATCH v1 2/3] eal/mcslock: use generic msc queued lock on all arch Phil Yang
2019-06-05 15:58 ` [dpdk-dev] [PATCH v1 3/3] test/mcslock: add mcs queued lock unit test Phil Yang
2019-06-06 13:42 ` Ananyev, Konstantin
2019-06-07 5:27 ` Honnappa Nagarahalli
2019-06-10 16:36 ` Phil Yang (Arm Technology China)
2019-06-05 16:29 ` [dpdk-dev] [PATCH v1 0/3] MCS queued lock implementation David Marchand
2019-06-05 19:59 ` Honnappa Nagarahalli [this message]
2019-06-06 10:17 ` Phil Yang (Arm Technology China)
2019-06-05 16:47 ` Stephen Hemminger
2019-06-05 20:48 ` Honnappa Nagarahalli
2019-06-05 17:35 ` Thomas Monjalon
2019-07-04 20:12 ` Thomas Monjalon
2019-07-05 10:33 ` Phil Yang (Arm Technology China)
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=AM0PR08MB5138A8280994C35B84B3473298160@AM0PR08MB5138.eurprd08.prod.outlook.com \
--to=honnappa.nagarahalli@arm.com \
--cc=Gavin.Hu@arm.com \
--cc=Phil.Yang@arm.com \
--cc=david.marchand@redhat.com \
--cc=dev@dpdk.org \
--cc=hemant.agrawal@nxp.com \
--cc=jerinj@marvell.com \
--cc=nd@arm.com \
--cc=thomas@monjalon.net \
/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).