From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Message-ID: <55511A8C.8070608@kernel.dk> Date: Mon, 11 May 2015 17:09:32 -0400 From: Jens Axboe MIME-Version: 1.0 Subject: Re: Why Seperate Log Files? References: <5550D6D3.9050803@kernel.dk> In-Reply-To: Content-Type: text/plain; charset="utf-8"; format="flowed" Content-Transfer-Encoding: 8bit To: Jon Tango Cc: Andrey Kuzmin , Sitsofe Wheeler , "" List-ID: On May 11, 2015, at 4:28 PM, Jon Tango > wrote: > Well, I can honestly admit that I deserved that. Sorry, I had wrote > that after having stressed out for like 5 hours trying to get the > outputs correct using a variety of commands with the new version. It > wasn’t until I switched back to the old version that I realized > somewhere along the line the output format had changed. I will > re-submit this with some context. I'm nicer than you deserved: http://git.kernel.dk/?p=fio.git;a=commit;h=3a5db9201bf7b1717f63cb8f7dbd025903117f70 From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Message-ID: <55511A63.1040605@kernel.dk> Date: Mon, 11 May 2015 17:08:51 -0400 From: Jens Axboe MIME-Version: 1.0 Subject: Re: Why Seperate Log Files? References: <5550D6D3.9050803@kernel.dk> In-Reply-To: Content-Type: multipart/alternative; boundary="------------020201010901010909050507" To: Jon Tango Cc: Andrey Kuzmin , Sitsofe Wheeler , "" List-ID: This is a multi-part message in MIME format. --------------020201010901010909050507 Content-Type: text/plain; charset="utf-8"; format="flowed" Content-Transfer-Encoding: 8bit On May 11, 2015, at 4:28 PM, Jon Tango > wrote: > Well, I can honestly admit that I deserved that. Sorry, I had wrote > that after having stressed out for like 5 hours trying to get the > outputs correct using a variety of commands with the new version. It > wasn’t until I switched back to the old version that I realized > somewhere along the line the output format had changed. I will > re-submit this with some context. I'm nicer than you deserved: http://git.kernel.dk/?p=fio.git;a=commit;h=3a5db9201bf7b1717f63cb8f7dbd025903117f70 --------------020201010901010909050507 Content-Type: text/html; charset="utf-8" Content-Transfer-Encoding: 8bit

On May 11, 2015, at 4:28 PM, Jon Tango <cheerios123@outlook.com> wrote:

Well, I can honestly admit that I deserved that. Sorry, I had wrote that after having stressed out for like 5 hours trying to get the outputs correct using a variety of commands with the new version. It wasn’t until I switched back to the old version that I realized somewhere along the line the output format had changed. I will re-submit this with some context.

I'm nicer than you deserved:


--------------020201010901010909050507-- From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Message-ID: Return-Path: cheerios123@outlook.com From: Jon Tango References: <5550D6D3.9050803@kernel.dk> In-Reply-To: <5550D6D3.9050803@kernel.dk> Subject: RE: Why Seperate Log Files? Date: Mon, 11 May 2015 15:28:35 -0500 MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Content-Language: en-us To: 'Jens Axboe' , 'Andrey Kuzmin' Cc: 'Sitsofe Wheeler' , fio@vger.kernel.org List-ID: Well, I can honestly admit that I deserved that. Sorry, I had wrote that = after having stressed out for like 5 hours trying to get the outputs = correct using a variety of commands with the new version. It = wasn=E2=80=99t until I switched back to the old version that I realized = somewhere along the line the output format had changed. I will re-submit = this with some context.=20 -----Original Message----- From: Jens Axboe [mailto:axboe@kernel.dk]=20 Sent: Monday, May 11, 2015 11:21 AM To: Jon Tango; 'Andrey Kuzmin' Cc: 'Sitsofe Wheeler'; fio@vger.kernel.org Subject: Re: Why Seperate Log Files? On 05/10/2015 09:36 PM, Jon Tango wrote: > When I use fio in 2.1.8 the write_iops_log command creates a singular = log file, even with 8 workers. With fio in the latest versions, however, = it creates eight separate log files. Is there a way to get fio to = generate a log file for all 8 workers, instead of 8 separate files? That = is untenable. I had to go back to 2.1.8 to get a useable output. It's = not like the data outputs are very friendly anyway, but with one file at = least that data can easily be parsed and worked with. With a different = file for each worker it is just ridiculous. > How do we get one output for all workers? > It would also be nice if we could just get one output with all of the=20 > numbers for the different workers combined, but that may be asking a=20 > bit much. Just getting them all in a workable file would be nice :) Lets back this up a bit. Your bug reporting _sucks_. Constructive = criticism - look it up. You were even lazy enough to just reply to an = old, totally unrelated email, instead of starting a new thread. So lets try this again. I'll even offer you some free hints. Find out = where the change happened, see if there's reasoning there. If not, = suggest a way to improve the situation. Or even just, constructively, = suggest why the current behavior is a problem and offer your opinion on = how it could be improved to make your life easier. Nobody on this list = owes you anything, you need to earn it. -- Jens Axboe From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Message-ID: <5550D6D3.9050803@kernel.dk> Date: Mon, 11 May 2015 12:20:35 -0400 From: Jens Axboe MIME-Version: 1.0 Subject: Re: Why Seperate Log Files? References: In-Reply-To: Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: 7bit To: Jon Tango , 'Andrey Kuzmin' Cc: 'Sitsofe Wheeler' , fio@vger.kernel.org List-ID: On 05/10/2015 09:36 PM, Jon Tango wrote: > When I use fio in 2.1.8 the write_iops_log command creates a singular log file, even with 8 workers. With fio in the latest versions, however, it creates eight separate log files. Is there a way to get fio to generate a log file for all 8 workers, instead of 8 separate files? That is untenable. I had to go back to 2.1.8 to get a useable output. It's not like the data outputs are very friendly anyway, but with one file at least that data can easily be parsed and worked with. With a different file for each worker it is just ridiculous. > How do we get one output for all workers? > It would also be nice if we could just get one output with all of the numbers for the different workers combined, but that may be asking a bit much. Just getting them all in a workable file would be nice :) Lets back this up a bit. Your bug reporting _sucks_. Constructive criticism - look it up. You were even lazy enough to just reply to an old, totally unrelated email, instead of starting a new thread. So lets try this again. I'll even offer you some free hints. Find out where the change happened, see if there's reasoning there. If not, suggest a way to improve the situation. Or even just, constructively, suggest why the current behavior is a problem and offer your opinion on how it could be improved to make your life easier. Nobody on this list owes you anything, you need to earn it. -- Jens Axboe From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Message-ID: Return-Path: cheerios123@outlook.com From: Jon Tango Subject: Why Seperate Log Files? Date: Sun, 10 May 2015 20:36:32 -0500 MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Content-Language: en-us To: 'Andrey Kuzmin' Cc: 'Jens Axboe' , 'Sitsofe Wheeler' , fio@vger.kernel.org List-ID: When I use fio in 2.1.8 the write_iops_log command creates a singular = log file, even with 8 workers. With fio in the latest versions, however, = it creates eight separate log files. Is there a way to get fio to = generate a log file for all 8 workers, instead of 8 separate files? That = is untenable. I had to go back to 2.1.8 to get a useable output. It's = not like the data outputs are very friendly anyway, but with one file at = least that data can easily be parsed and worked with. With a different = file for each worker it is just ridiculous.=20 How do we get one output for all workers? It would also be nice if we could just get one output with all of the = numbers for the different workers combined, but that may be asking a bit = much. Just getting them all in a workable file would be nice :)=20 -----Original Message----- From: Jon Tango [mailto:cheerios123@outlook.com]=20 Sent: Tuesday, September 30, 2014 4:14 AM To: 'Andrey Kuzmin' Cc: 'Jens Axboe'; 'Sitsofe Wheeler'; fio@vger.kernel.org Subject: RE: Limit LBA Range The same thing could be done by partitioning the SSD in the operating = system with the desired partition size, and then running a time-based = fio job against the partition. Basically, fio options offset/size should yield the same net result, but = I'm always unsure on what is the actual effect of mixing size and = time_based in a single job, and whether fio will wrap around the = specified size to the specified offset if the job is time-based. HOWTO = could have used some clarification on size/time_based interaction. Regards, Andrey On Sep 30, 2014 11:41 AM, "Sitsofe Wheeler" wrote: > > On 30 September 2014 07:34, Jon Tango wrote: > > > > The taskfile is this: > > I should have been more specific - you need to show both the _vdbench_ = > parameter file that you are comparing to in addition to showing your=20 > fio job file. > > -- > Sitsofe |http://sucs.org/~sits/ > -- > To unsubscribe from this list: send the line "unsubscribe fio" in the=20 > body of a message tomajordomo@vger.kernel.org More majordomo info at=20 > http://vger.kernel.org/majordomo-info.html -- To unsubscribe from this list: send the line "unsubscribe fio" in the = body of a message to majordomo@vger.kernel.org More majordomo info at = http://vger.kernel.org/majordomo-info.html I'm really wanting to avoid the filesystem, they create so much = interference. I am focusing on just testing the raw device :)