From: Vladislav Bolkhovitin <vst-d+Crzxg7Rs0@public.gmane.org>
To: Or Gerlitz <ogerlitz-hKgKHo2Ms0FWk0Htik3J/w@public.gmane.org>
Cc: Bart Van Assche <bvanassche-HInyCGIudOg@public.gmane.org>,
Roland Dreier <rdreier-FYB4Gu1CFyUAvxtiuMwx3w@public.gmane.org>,
linux-rdma <linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
Mike Christie <michaelc-hcNo3dDEHLuVc3sceRu5cw@public.gmane.org>,
Yaron Haviv <yaronh-smomgflXvOZWk0Htik3J/w@public.gmane.org>
Subject: Re: [PATCH 0/8] ib/iser: major face lift of the data path code
Date: Fri, 05 Feb 2010 15:29:03 +0300 [thread overview]
Message-ID: <4B6C0F0F.5050905@vlnb.net> (raw)
In-Reply-To: <4B6AD7D5.7030204-hKgKHo2Ms0FWk0Htik3J/w@public.gmane.org>
Or Gerlitz, on 02/04/2010 05:21 PM wrote:
> Bart Van Assche wrote:
>> Sounds really interesting. Do you have numbers available about how
>> much these patches improve throughput or decrease latency ?
>
> Yes, generally speaking after the patches the initiator peaks to about 300-400K IOPS
> with latency under such load being 20-30us and before the patches the initiator was
> doing upto 200K IOPS with the latency under such load being 50-100us, see some data
> I got today on mytest bed. Being focused on the initiator, I was using a "NULL device"
> at the target side.
Also, what kind of test did you do?
> AFTER
>
> r b swpd free buff cache si so bi bo in cs us sy id wa st
> 11 11 0 6212936 260552 367356 0 0 308671 0 285596 492842 4 64 0 31 0
> 7 13 0 6212936 260552 367356 0 0 309628 24 285138 496537 5 61 0 33 0
> 10 12 0 6212936 260552 367356 0 0 308222 0 277868 489261 4 65 0 30 0
> 8 13 0 6212936 260552 367356 0 0 310724 0 282151 493868 4 67 0 29 0
> 12 11 0 6212936 260552 367356 0 0 308209 0 278753 489797 5 66 0 29 0
>
> Linux 2.6.33-rc4 (cto-1) 02/04/2010
>
> avg-cpu: %user %nice %system %iowait %steal %idle
> 4.62 0.00 66.29 28.71 0.00 0.37
>
> Device: rrqm/s wrqm/s r/s w/s rsec/s wsec/s avgrq-sz avgqu-sz await svctm %util
> sdd 0.00 0.00 88905.94 0.00 177811.88 0.00 2.00 2.82 0.03 0.01 98.61
> sdf 0.00 0.00 64021.78 0.00 128045.54 0.00 2.00 2.55 0.04 0.02 96.24
> sdh 0.00 0.00 88922.77 0.00 177845.54 0.00 2.00 2.85 0.03 0.01 99.01
> sdj 0.00 0.00 64662.38 0.00 129324.75 0.00 2.00 2.69 0.04 0.02 97.82
>
> BEFORE
>
> r b swpd free buff cache si so bi bo in cs us sy id wa st
> 6 14 0 6211804 260684 368584 0 0 195551 0 195997 557463 3 56 4 37 0
> 7 13 0 6211804 260684 368584 0 0 191347 0 192311 525823 3 58 3 36 0
> 6 15 0 6211804 260692 368584 0 0 187135 16 190875 503739 3 58 3 35 0
> 8 14 0 6211804 260692 368584 0 0 193745 0 193921 556821 3 55 4 38 0
> 8 16 0 6211804 260692 368584 0 0 191233 0 191549 536499 3 58 4 35 0
>
> Linux 2.6.33-rc4 (cto-1) 02/04/2010
>
> avg-cpu: %user %nice %system %iowait %steal %idle
> 2.24 0.00 58.16 35.87 0.00 3.74
>
> Device: rrqm/s wrqm/s r/s w/s rsec/s wsec/s avgrq-sz avgqu-sz await svctm %util
> sdd 0.00 0.00 33964.00 0.00 67928.00 0.00 2.00 3.36 0.10 0.03 100.00
> sdf 0.00 0.00 33456.00 0.00 66912.00 0.00 2.00 3.34 0.10 0.03 99.60
> sdh 0.00 0.00 63176.00 0.00 126352.00 0.00 2.00 3.40 0.05 0.02 100.00
> sdj 0.00 0.00 62973.00 0.00 125946.00 0.00 2.00 3.38 0.05 0.02 100.40
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
> the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
>
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
prev parent reply other threads:[~2010-02-05 12:29 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-02-03 15:30 [PATCH 0/8] ib/iser: major face lift of the data path code Or Gerlitz
[not found] ` <Pine.LNX.4.64.1002031721280.11944-aDiYczhfhVLdX2U7gxhm1tBPR1lH4CV8@public.gmane.org>
2010-02-03 15:31 ` [PATCH 01/9] ib/iser: revert commit bba7ebb "avoid recv buffer exhaustion" Or Gerlitz
2010-02-03 15:33 ` [PATCH 02/9] ib/iser: new recv buffer posting logic Or Gerlitz
2010-02-03 15:35 ` [PATCH 03/9] ib/iser: remove atomic counter for posted recv buffers Or Gerlitz
2010-02-03 15:36 ` [PATCH 04/9] ib/iser: use different CQ for send completions Or Gerlitz
2010-02-03 15:37 ` [PATCH 05/9] ib/iser: simplify send flow/descriptors Or Gerlitz
[not found] ` <Pine.LNX.4.64.1002031737090.11944-aDiYczhfhVLdX2U7gxhm1tBPR1lH4CV8@public.gmane.org>
2010-02-04 11:23 ` Or Gerlitz
2010-02-03 15:39 ` [PATCH 06/9] ib/iser: use atomic allocations Or Gerlitz
2010-02-03 15:40 ` [PATCH 07/9] ib/iser: remove unnecessary connection checks Or Gerlitz
2010-02-03 15:41 ` [PATCH 08/9] ib/iser: move to use libiscsi passthrough mode Or Gerlitz
[not found] ` <Pine.LNX.4.64.1002031740540.11944-aDiYczhfhVLdX2U7gxhm1tBPR1lH4CV8@public.gmane.org>
2010-02-03 21:32 ` Mike Christie
[not found] ` <4B69EB5A.4050301-hcNo3dDEHLuVc3sceRu5cw@public.gmane.org>
2010-02-04 11:21 ` Or Gerlitz
[not found] ` <4B6AADD4.2050607-hKgKHo2Ms0FWk0Htik3J/w@public.gmane.org>
2010-02-04 17:27 ` Mike Christie
2010-02-03 15:42 ` [PATCH 08/10] ib/iser: remove redundant locking from command response flow Or Gerlitz
2010-02-03 15:44 ` [PATCH 09/9] remove redundant locking from iser scsi " Or Gerlitz
2010-02-03 16:10 ` [PATCH 0/8] ib/iser: major face lift of the data path code Bart Van Assche
2010-02-03 16:11 ` Bart Van Assche
[not found] ` <e2e108261002030811r5c740d6fr4cc055702a88aa50-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2010-02-04 14:21 ` Or Gerlitz
[not found] ` <4B6AD7D5.7030204-hKgKHo2Ms0FWk0Htik3J/w@public.gmane.org>
2010-02-05 12:18 ` Vladislav Bolkhovitin
[not found] ` <4B6C0C93.2090107-d+Crzxg7Rs0@public.gmane.org>
2010-02-07 14:51 ` Or Gerlitz
2010-02-05 12:29 ` Vladislav Bolkhovitin [this message]
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=4B6C0F0F.5050905@vlnb.net \
--to=vst-d+crzxg7rs0@public.gmane.org \
--cc=bvanassche-HInyCGIudOg@public.gmane.org \
--cc=linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=michaelc-hcNo3dDEHLuVc3sceRu5cw@public.gmane.org \
--cc=ogerlitz-hKgKHo2Ms0FWk0Htik3J/w@public.gmane.org \
--cc=rdreier-FYB4Gu1CFyUAvxtiuMwx3w@public.gmane.org \
--cc=yaronh-smomgflXvOZWk0Htik3J/w@public.gmane.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 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.