You are viewing a plain text version of this content. The canonical link for it is here.
Posted to users@trafficserver.apache.org by Daniel Biazus <da...@azion.com> on 2015/01/14 14:29:15 UTC
IO performance
Hey Guys,
As you can see at the following iostat output, We have a lot of writes
into the cache, :-) and the IO wait is a bit higher than expected.
Device: rrqm/s wrqm/s r/s w/s rsec/s
wsec/s avgrq-sz avgqu-sz await svctm %util
(storage) sda 0.00 0.00 17.00 26.00 6094.00 13144.00
447.40 0.94 *19.77* 6.05 26.00
(interim) sdb 0.00 0.00 85.00 13.00 12523.00
8706.00 216.62 0.18 1.86 0.84 8.20
I was wondering if would be possible to enhance the write IO performance by
increasing the IO buffers.
I thought, I would increase the proxy.config.io.max_buffer_size, from 32768
to a much higher value.
Any thoughts about it ?
Thank you!
--
Daniel Biazus
infrastructure Engineering
Azion Technologies
Porto Alegre, Brasil +55 51 3012 3005 | +55 51 82279032
Miami, USA +1 305 704 8816
Quaisquer informações contidas neste e-mail e anexos podem ser
confidenciais e privilegiadas, protegidas por sigilo legal. Qualquer forma
de utilização deste documento depende de autorização do emissor, sujeito as
penalidades cabíveis.
Any information in this e-mail and attachments may be confidential and
privileged, protected by legal confidentiality. The use of this document
require authorization by the issuer, subject to penalties.
Re: IO performance
Posted by Alan Carroll <so...@yahoo-inc.com>.
Changing the default IO buffer size setting will have no effect on writing to disk. As far as I can tell the cache logic is hardwired to write in at most 4M sized chunks.
On Thursday, January 22, 2015 9:03 PM, Steven Hunter <st...@gmail.com> wrote:
A second or more HDS up to 4 would work greatStevenHunterOn Jan 14, 2015 11:31 AM, "Daniel Biazus" <da...@azion.com> wrote:
Hey Guys,
As you can see at the following iostat output, We have a lot of writes into the cache, :-) and the IO wait is a bit higher than expected.
Device: rrqm/s wrqm/s r/s w/s rsec/s wsec/s avgrq-sz avgqu-sz await svctm %util(storage) sda 0.00 0.00 17.00 26.00 6094.00 13144.00 447.40 0.94 19.77 6.05 26.00(interim) sdb 0.00 0.00 85.00 13.00 12523.00 8706.00 216.62 0.18 1.86 0.84 8.20
I was wondering if would be possible to enhance the write IO performance by increasing the IO buffers.
I thought, I would increase the proxy.config.io.max_buffer_size, from 32768 to a much higher value.
Any thoughts about it ?
Thank you!
--
Daniel Biazusinfrastructure EngineeringAzion TechnologiesPorto Alegre, Brasil +55 51 3012 3005 | +55 51 82279032Miami, USA +1 305 704 8816
|
Quaisquer informações contidas neste e-mail e anexos podem ser confidenciais e privilegiadas, protegidas por sigilo legal. Qualquer forma de utilização deste documento depende de autorização do emissor, sujeito as penalidades cabíveis.Any information in this e-mail and attachments may be confidential and privileged, protected by legal confidentiality. The use of this document require authorization by the issuer, subject to penalties. |
Re: IO performance
Posted by Steven Hunter <st...@gmail.com>.
StevenHunter
On Jan 23, 2015 1:01 AM, "Steven Hunter" <st...@gmail.com> wrote:
>
> A second or more HDS up to 4 would work great
>
> StevenHunter
>
> On Jan 14, 2015 11:31 AM, "Daniel Biazus" <da...@azion.com> wrote:
>>
>> Hey Guys,
>>
>> As you can see at the following iostat output, We have a lot of
writes into the cache, :-) and the IO wait is a bit higher than expected.
>>
>> Device: rrqm/s wrqm/s r/s w/s rsec/s
wsec/s avgrq-sz avgqu-sz await svctm/ %util
>> (storage) sda 0.00 0.00 17.00 26.00 6094.00
13144.00 447.40 0.94 19.77 6.05 26.00
>> (interim) sdb 0.00 0.00 85.00 13.00 12523.00
8706.00 216.62 0.18 1.86 0.84 8.20
>>
>> I was wondering if would be possible to enhance the write IO performance
by increasing the IO buffers.
>>
>> I thought, I would increase the proxy.config.io.max_buffer_size, from
32768 to a much higher value.
>>
>> Any thoughts about it ?
>>
>> Thank you!
>>
>> --
>>
>> Daniel Biazus
>> infrastructure Engineering
>> Azion Technologies
>> Porto Alegre, Brasil +55 51 3012 3005 | +55 51 82279032
>> Miami, USA +1 305 704 8816
>>
>> Quaisquer informações contidas neste e-mail e anexos podem ser
confidenciais e privilegiadas, protegidas por sigilo legal. Qualquer forma
de utilização deste documento depende de autorização do emissor, sujeito as
penalidades cabíveis.
>>
>> Any information in this e-mail and attachments may be confidential and
privileged, protected by legal confidentiality. The use of this document
require authorization by the issuer, subject to penalties.
>>
>>
Re: IO performance
Posted by Steven Hunter <st...@gmail.com>.
A second or more HDS up to 4 would work great
StevenHunter
On Jan 14, 2015 11:31 AM, "Daniel Biazus" <da...@azion.com> wrote:
> Hey Guys,
>
> As you can see at the following iostat output, We have a lot of writes
> into the cache, :-) and the IO wait is a bit higher than expected.
>
> Device: rrqm/s wrqm/s r/s w/s rsec/s
> wsec/s avgrq-sz avgqu-sz await svctm %util
> (storage) sda 0.00 0.00 17.00 26.00 6094.00
> 13144.00 447.40 0.94 *19.77* 6.05 26.00
> (interim) sdb 0.00 0.00 85.00 13.00 12523.00
> 8706.00 216.62 0.18 1.86 0.84 8.20
>
> I was wondering if would be possible to enhance the write IO performance
> by increasing the IO buffers.
>
> I thought, I would increase the proxy.config.io.max_buffer_size, from
> 32768 to a much higher value.
>
> Any thoughts about it ?
>
> Thank you!
>
> --
>
> Daniel Biazus
> infrastructure Engineering
> Azion Technologies
> Porto Alegre, Brasil +55 51 3012 3005 | +55 51 82279032
> Miami, USA +1 305 704 8816
>
> Quaisquer informações contidas neste e-mail e anexos podem ser
> confidenciais e privilegiadas, protegidas por sigilo legal. Qualquer forma
> de utilização deste documento depende de autorização do emissor, sujeito as
> penalidades cabíveis.
>
> Any information in this e-mail and attachments may be confidential and
> privileged, protected by legal confidentiality. The use of this document
> require authorization by the issuer, subject to penalties.
>
>