Re: [Gluster-devel] volfile change
Hi Emmanuel, ssl.dh-param (not yet committed) seems to restart the daemon while ssl.cipher-list does not. ss.dh-param is the option that you are adding additionally based on your requirement in current gluster code. So we need to check your patch first then only we can say how brick is restarting. As of now restarting brick is not plausible after executing volume set command. Thanx, ~Gaurav - Original Message - From: Emmanuel Dreyfus m...@netbsd.org To: Gaurav Garg gg...@redhat.com Cc: gluster-devel@gluster.org Sent: Thursday, July 23, 2015 11:08:39 PM Subject: Re: [Gluster-devel] volfile change Gaurav Garg gg...@redhat.com wrote: could you tell me the name of the option which did brick restart? -- Emmanuel Dreyfus http://hcpnet.free.fr/pubz m...@netbsd.org ___ Gluster-devel mailing list Gluster-devel@gluster.org http://www.gluster.org/mailman/listinfo/gluster-devel
Re: [Gluster-devel] [Gluster-users] Gentle Reminder.. (Was: GlusterFS Documentation Improvements - An Update)
This is still confising me a little. The presentations from the Mediawiki instance have been put in the glusterdocs/presentations/ directory. If we should put them on the website instead, they should not be part of glusterdocs. However, there is currently no page that I can find on the website that lists the different presentations. The only link that I can find is this one: http://gluster.readthedocs.org/en/latest/presentations/ Is that going to be replaced with an explanation (or pointer) on how to get the presentation on the website? Well, we are yet to finalize on it. If we can render it on website we will do the same. Otherwise it will be a pointer from website. --Humble On Fri, Jul 24, 2015 at 2:00 AM, Niels de Vos nde...@redhat.com wrote: On Wed, Jul 22, 2015 at 03:51:59PM +0530, Anjana Sriram wrote: Hello All, Thank you for the feedback and suggestions provided on the GlusterFS Documentation improvements. We have analyzed them and here's a proposal to address them: We plan to use three independent repos for our projects: ... snip /Static Documentation/: Currently, Mediawiki is read-only. We have ported most of the documents from Mediawiki. There few pages which do not qualify to be placed in the above three repos for example, Presentations which will be considered to be placed on the website. This is still confising me a little. The presentations from the Mediawiki instance have been put in the glusterdocs/presentations/ directory. If we should put them on the website instead, they should not be part of glusterdocs. However, there is currently no page that I can find on the website that lists the different presentations. The only link that I can find is this one: http://gluster.readthedocs.org/en/latest/presentations/ Is that going to be replaced with an explanation (or pointer) on how to get the presentation on the website? Thanks, Niels Your thoughts and feedback are the major influences to our constant endeavor to make the community documentation better, effective, and useful. Please revert with your thoughts and feedback on the above proposal outlined by 29th July 2015. Regards, Humble, Shravan, and Anjana On 06/22/2015 05:24 PM, Shravan Chandrashekar wrote: Hello all, We would like to finalize on the documentation contribution workflow by 26th June 2015. As we have not yet received any comments/suggestion, we will confirm the recommend workflow after 26th June. Kindly provide your suggestion on how we can improve this workflow. Currently, mediawiki is read-only. We have ported most of the documents from mediawiki to the new repository [1]. If you find any document which is not ported, feel free to raise this by opening an issue in [2] or if you would like to port your documents, send a pull request. [1] https://github.com/gluster/glusterdocs [2] https://github.com/gluster/glusterdocs/issues Regards, Shravan - Original Message - From: Humble Devassy Chirammal humble.deva...@gmail.com To: gluster-us...@gluster.org List gluster-us...@gluster.org, Gluster Devel gluster-devel@gluster.org Sent: Wednesday, May 27, 2015 7:48:16 PM Subject: [Gluster-devel] GlusterFS Documentation Improvements - An Update Hello all, The GlusterFS documentation team is constantly working to improve the quality, findability, and usefulness of its documentation. Our goal is to increase community contribution, remove barriers that discourage contribution and give you the help you need, when and where you need it. As part of this strategy, we’ve just rolled out the revamped GlusterFS Documentation: gluster.readthedocs.org We started by curating content from various sources including gluster.org static HTML documentation, various blog posts and the Community wiki. We used readthedocs service to host the documentation and mkdocs to convert the Markdown source files to HTML pages. We also put our thought into classifying the documentation based on their content: * Quick Start Guide : A headstart guide for the beginners. * Installation Guide : Step by step instructions to install GlusterFS. * Administration Guide : Container for for all administrative actions. * Developer Guide : Container for all development related aspects. * Upgrade Guide : Contains guides to upgrade from older versions of GlusterFS. * Features : Container for all the features of GlusterFS introduced in various versions. * GlusterFS Tools : Contains information about the tools used in GlusterFS. * Troubleshooting Guide : Container for basic troubleshooting and debugging guides. * Images : Container for images (in .jpg or .png format) that are present inline the documentation pages. Doing so, we gain these benefits: * Version based
[Gluster-devel] integer options in gluster volume set help
gluster volume set help shows option default values. I note that the default_value field is a char * and where the option is integer, it seems the practice is to duplicate the value as a string. Why not use a macro? Indeed it is a bit tricky, but it removes the risk of having obsolete values: Here is the definition: #define GF_ITOA(s) _GF_ITOA(s) #define _GF_ITOA(s) #s And usage: #define DEFAULT_VERIFY_DEPTH 1 (...) { .key = {ssl-cert-depth}, .type = GF_OPTION_TYPE_INT, .default_value = GF_ITOA(DEFAULT_VERIFY_DEPTH), .description = Maximum certificate-chain depth. If zero, the peer's certificate itself must be in the local certificate list. Otherwise, there may be up to N signing certificates between the peer's and the local list. Ignored if SSL is not enabled. }, Reference: https://gcc.gnu.org/onlinedocs/cpp/Stringification.html -- Emmanuel Dreyfus http://hcpnet.free.fr/pubz m...@netbsd.org ___ Gluster-devel mailing list Gluster-devel@gluster.org http://www.gluster.org/mailman/listinfo/gluster-devel
[Gluster-devel] Review request for http://review.gluster.org/#/c/10262
Folks, Currently in our vme table we have few option names which are redundant across different translators. For eg: cache-size, this option is same across io-cache and quick-read xlator. Now if an user wants to have two different values set, we don't have a mechanism for it. What I have done here is to use unique names for these redundant options. Reviews is highly appreciated and I do think this will be a good candidate for 3.7.3. -- ~Atin ___ Gluster-devel mailing list Gluster-devel@gluster.org http://www.gluster.org/mailman/listinfo/gluster-devel
Re: [Gluster-devel] [Gluster-users] Gentle Reminder.. (Was: GlusterFS Documentation Improvements - An Update)
On Wed, Jul 22, 2015 at 03:51:59PM +0530, Anjana Sriram wrote: Hello All, Thank you for the feedback and suggestions provided on the GlusterFS Documentation improvements. We have analyzed them and here's a proposal to address them: We plan to use three independent repos for our projects: ... snip /Static Documentation/: Currently, Mediawiki is read-only. We have ported most of the documents from Mediawiki. There few pages which do not qualify to be placed in the above three repos for example, Presentations which will be considered to be placed on the website. This is still confising me a little. The presentations from the Mediawiki instance have been put in the glusterdocs/presentations/ directory. If we should put them on the website instead, they should not be part of glusterdocs. However, there is currently no page that I can find on the website that lists the different presentations. The only link that I can find is this one: http://gluster.readthedocs.org/en/latest/presentations/ Is that going to be replaced with an explanation (or pointer) on how to get the presentation on the website? Thanks, Niels Your thoughts and feedback are the major influences to our constant endeavor to make the community documentation better, effective, and useful. Please revert with your thoughts and feedback on the above proposal outlined by 29th July 2015. Regards, Humble, Shravan, and Anjana On 06/22/2015 05:24 PM, Shravan Chandrashekar wrote: Hello all, We would like to finalize on the documentation contribution workflow by 26th June 2015. As we have not yet received any comments/suggestion, we will confirm the recommend workflow after 26th June. Kindly provide your suggestion on how we can improve this workflow. Currently, mediawiki is read-only. We have ported most of the documents from mediawiki to the new repository [1]. If you find any document which is not ported, feel free to raise this by opening an issue in [2] or if you would like to port your documents, send a pull request. [1] https://github.com/gluster/glusterdocs [2] https://github.com/gluster/glusterdocs/issues Regards, Shravan - Original Message - From: Humble Devassy Chirammal humble.deva...@gmail.com To: gluster-us...@gluster.org List gluster-us...@gluster.org, Gluster Devel gluster-devel@gluster.org Sent: Wednesday, May 27, 2015 7:48:16 PM Subject: [Gluster-devel] GlusterFS Documentation Improvements - An Update Hello all, The GlusterFS documentation team is constantly working to improve the quality, findability, and usefulness of its documentation. Our goal is to increase community contribution, remove barriers that discourage contribution and give you the help you need, when and where you need it. As part of this strategy, we’ve just rolled out the revamped GlusterFS Documentation: gluster.readthedocs.org We started by curating content from various sources including gluster.org static HTML documentation, various blog posts and the Community wiki. We used readthedocs service to host the documentation and mkdocs to convert the Markdown source files to HTML pages. We also put our thought into classifying the documentation based on their content: * Quick Start Guide : A headstart guide for the beginners. * Installation Guide : Step by step instructions to install GlusterFS. * Administration Guide : Container for for all administrative actions. * Developer Guide : Container for all development related aspects. * Upgrade Guide : Contains guides to upgrade from older versions of GlusterFS. * Features : Container for all the features of GlusterFS introduced in various versions. * GlusterFS Tools : Contains information about the tools used in GlusterFS. * Troubleshooting Guide : Container for basic troubleshooting and debugging guides. * Images : Container for images (in .jpg or .png format) that are present inline the documentation pages. Doing so, we gain these benefits: * Version based browsable documentation * More targeted content * Less duplication * Faster updates Whats changing for community members? A very simplified contribution workflow. - How to Contribute? Contributing to the documentation requires a github account. To edit on github, fork the repository (see top-right of the screen, under your username). You will then be able to make changes easily. Once done, you can create a pull request and get the changes reviewed and merged into the official repository. With this simplified workflow, the documentation is no longer maintained in gluster/glusterfs/docs directory but it has a new elevated status in the form of a new project: gluster/glusterdocs ( https://github.com/gluster/glusterdocs) and currently this project is being maintained by Anjana
Re: [Gluster-devel] volfile change
Gaurav Garg gg...@redhat.com wrote: could you tell me the name of the option which did brick restart? ssl.dh-param (not yet committed) seems to restart the daemon while ssl.cipher-list does not. -- Emmanuel Dreyfus http://hcpnet.free.fr/pubz m...@netbsd.org ___ Gluster-devel mailing list Gluster-devel@gluster.org http://www.gluster.org/mailman/listinfo/gluster-devel
Re: [Gluster-devel] Iusses with Random read/write
I run alot of random IO tests with gluster and it has really come a long way in the 3.7 release. What version are you running on? I have a couple of suggestions: -Run on 3.7 if you are not already. -Run the IOZone test you are running on the back end without gluster to verify that your HW meets your perf needs. SSDs really scream with random IO if your current HW won't meet your needs. -When you are running tests watch top -H on both clients and servers, look for any threads hitting 100% -If you see hot threads bump up the server.event-threads and/or client.event-threads from the default of 2 HTH! -b On Thu, Jul 23, 2015 at 3:04 AM, Susant Palai spa...@redhat.com wrote: ++CCing gluster-devel to have more eye on this problem. Susant - Original Message - From: Subrata Ghosh subrata.gh...@ericsson.com To: Susant Palai spa...@redhat.com (spa...@redhat.com) spa...@redhat.com, Vijay Bellur vbel...@redhat.com (vbel...@redhat.com) vbel...@redhat.com Cc: Subrata Ghosh subrata.gh...@ericsson.com Sent: Sunday, 19 July, 2015 7:57:28 PM Subject: Iusses with Random read/write Hi Vijay/Prashant, How you are you :). We need your immediate help / suggestion to meet our random I/IO performance metrics. Currently we have performance issues with random read/write - our basic requirement 20 MB/sec for random I/O. We tried with both iozone and fio, received almost same ( random I/O) performance which is not meeting our fundamental I/IO requirements. Our use case is as below. Application running on different cards Writes/Reads (random) continuous files to the volume comprising with storage belonging from different cards in the distributed system, where replica presence across cards and applications are using non-local storages. We have verified and identified the bottleneck mostly on Gluster Client side inside the application, however gluster server to server I/O speed looks enough good. Performance tuning on gluster server side would not expected to help. We also cross verified checked using NFS client we are getting far better performance, but we cannot use NFS client /libgfapi because of use case limitation ( brick failures cases etc..) Please throw some lights or thoughts to improve gluster client to achieve 20 MB/Secs Observations: Fio: lease find the test results of Random write read in 2 APPs scenarios. Scenario APP_1 APP_2 File size No of AMC's Random-Write 3.06 MB/s 3.02 MB/s 100 MB 4 Random-Read 8.1 MB/s 8.4 MB/s 100 MB 4 Iozone: ./iozone -R -l 1 -u 1 -r 4k -s 2G -F /home/cdr/f1 | tee -a /tmp/iozone_results.txt APP 1 APP2 File Size : 2GB File size : 2GB Record size = 4 Kbytes Record size = 4 Kbytes Output is in Kbytes/sec Output is in Kbytes/sec Initial write41061.78 Initial write41167.36 Rewrite40395.64 Rewrite40810.41 Read 262685.69 Read 269644.62 Re-read 263751.66 Re-read 270760.62 Reverse Read 27715.72 Reverse Read28604.22 Stride read 83776.44 Stride read84347.88 Random read16239.74 (15.8 MB/s ) Random read15815.94 (15.4 MB/s ) Mixed workload16260.95 Mixed workload15787.55 Random write 3356.57 (3.3 MB/s ) Random write 3365.17 ( 3.3 MB/s) Pwrite40914.55 Pwrite40692.34 Pread 260613.83 Pread 269850.59 Fwrite40412.40 Fwrite40369.78 Fread 261506.61 Fread 267142.41 Some of the info on performance testing is at http://www.gluster.org/community/documentation/index.php/Performance_Testing Also pls check iozone limitations listed there. WARNING: random I/O testing in iozone is very restricted by iozone constraint that it must randomly read then randomly write the entire file! This is not what we want - instead it should randomly read/write for some fraction of file size or time duration, allowing us to spread out more on the disk while not waiting too long for test to finish. This is why fio (below) is the preferred test tool for random I/O workloads. ___ Gluster-devel mailing list Gluster-devel@gluster.org http://www.gluster.org/mailman/listinfo/gluster-devel ___ Gluster-devel mailing list Gluster-devel@gluster.org http://www.gluster.org/mailman/listinfo/gluster-devel
Re: [Gluster-devel] Iusses with Random read/write
++CCing gluster-devel to have more eye on this problem. Susant - Original Message - From: Subrata Ghosh subrata.gh...@ericsson.com To: Susant Palai spa...@redhat.com (spa...@redhat.com) spa...@redhat.com, Vijay Bellur vbel...@redhat.com (vbel...@redhat.com) vbel...@redhat.com Cc: Subrata Ghosh subrata.gh...@ericsson.com Sent: Sunday, 19 July, 2015 7:57:28 PM Subject: Iusses with Random read/write Hi Vijay/Prashant, How you are you :). We need your immediate help / suggestion to meet our random I/IO performance metrics. Currently we have performance issues with random read/write - our basic requirement 20 MB/sec for random I/O. We tried with both iozone and fio, received almost same ( random I/O) performance which is not meeting our fundamental I/IO requirements. Our use case is as below. Application running on different cards Writes/Reads (random) continuous files to the volume comprising with storage belonging from different cards in the distributed system, where replica presence across cards and applications are using non-local storages. We have verified and identified the bottleneck mostly on Gluster Client side inside the application, however gluster server to server I/O speed looks enough good. Performance tuning on gluster server side would not expected to help. We also cross verified checked using NFS client we are getting far better performance, but we cannot use NFS client /libgfapi because of use case limitation ( brick failures cases etc..) Please throw some lights or thoughts to improve gluster client to achieve 20 MB/Secs Observations: Fio: lease find the test results of Random write read in 2 APPs scenarios. Scenario APP_1 APP_2 File size No of AMC's Random-Write 3.06 MB/s 3.02 MB/s 100 MB 4 Random-Read 8.1 MB/s 8.4 MB/s 100 MB 4 Iozone: ./iozone -R -l 1 -u 1 -r 4k -s 2G -F /home/cdr/f1 | tee -a /tmp/iozone_results.txt APP 1 APP2 File Size : 2GB File size : 2GB Record size = 4 Kbytes Record size = 4 Kbytes Output is in Kbytes/sec Output is in Kbytes/sec Initial write41061.78 Initial write41167.36 Rewrite40395.64 Rewrite40810.41 Read 262685.69 Read 269644.62 Re-read 263751.66 Re-read 270760.62 Reverse Read 27715.72 Reverse Read28604.22 Stride read 83776.44 Stride read84347.88 Random read16239.74 (15.8 MB/s ) Random read15815.94 (15.4 MB/s ) Mixed workload16260.95 Mixed workload15787.55 Random write 3356.57 (3.3 MB/s ) Random write 3365.17 ( 3.3 MB/s) Pwrite40914.55 Pwrite40692.34 Pread 260613.83 Pread 269850.59 Fwrite40412.40 Fwrite40369.78 Fread 261506.61 Fread 267142.41 Some of the info on performance testing is at http://www.gluster.org/community/documentation/index.php/Performance_Testing Also pls check iozone limitations listed there. WARNING: random I/O testing in iozone is very restricted by iozone constraint that it must randomly read then randomly write the entire file! This is not what we want - instead it should randomly read/write for some fraction of file size or time duration, allowing us to spread out more on the disk while not waiting too long for test to finish. This is why fio (below) is the preferred test tool for random I/O workloads. ___ Gluster-devel mailing list Gluster-devel@gluster.org http://www.gluster.org/mailman/listinfo/gluster-devel
Re: [Gluster-devel] spurious failure with test-case ./tests/basic/tier/tier.t
Will have a look - Original Message - From: Krutika Dhananjay kdhan...@redhat.com To: Dan Lambright dlamb...@redhat.com Cc: gluster-devel@gluster.org Sent: Thursday, July 23, 2015 10:59:16 AM Subject: Re: [Gluster-devel] spurious failure withtest-case ./tests/basic/tier/tier.t This test failed twice on my patch even after retrigger: https://build.gluster.org/job/rackspace-regression-2GB-triggered/12726/consoleFull https://build.gluster.org/job/rackspace-regression-2GB-triggered/12739/consoleFull Is this a new issue or the one that was originally reported? -Krutika From: Dan Lambright dlamb...@redhat.com To: Raghavendra Bhat rab...@redhat.com Cc: gluster-devel@gluster.org Sent: Friday, June 26, 2015 6:07:15 PM Subject: Re: [Gluster-devel] spurious failure with test-case ./tests/basic/tier/tier.t - Original Message - From: Raghavendra Bhat rab...@redhat.com To: gluster-devel@gluster.org Sent: Friday, June 26, 2015 6:37:37 AM Subject: Re: [Gluster-devel] spurious failure with test-case ./tests/basic/tier/tier.t On 06/26/2015 04:00 PM, Ravishankar N wrote: On 06/26/2015 03:57 PM, Vijaikumar M wrote: Hi Upstream regression failure with test-case ./tests/basic/tier/tier.t My patch# 11315 regression failed twice with test-case./tests/basic/tier/tier.t. Anyone seeing this issue with other patches? Yes, one of my patches failed today too: http://build.gluster.org/job/rackspace-regression-2GB-triggered/11461/consoleFull Will take a look. Thanks. -Ravi Even I had faced failure in tier.t couple of times. Regards, Raghavendra Bhat http://build.gluster.org/job/rackspace-regression-2GB-triggered/11396/consoleFull http://build.gluster.org/job/rackspace-regression-2GB-triggered/11456/consoleFull Thanks, Vijay ___ Gluster-devel mailing list Gluster-devel@gluster.org http://www.gluster.org/mailman/listinfo/gluster-devel ___ Gluster-devel mailing list Gluster-devel@gluster.org http://www.gluster.org/mailman/listinfo/gluster-devel ___ Gluster-devel mailing list Gluster-devel@gluster.org http://www.gluster.org/mailman/listinfo/gluster-devel ___ Gluster-devel mailing list Gluster-devel@gluster.org http://www.gluster.org/mailman/listinfo/gluster-devel ___ Gluster-devel mailing list Gluster-devel@gluster.org http://www.gluster.org/mailman/listinfo/gluster-devel ___ Gluster-devel mailing list Gluster-devel@gluster.org http://www.gluster.org/mailman/listinfo/gluster-devel
[Gluster-devel] volfile change
Hello While testing, I noticed that some gluster volume set operations caused a brick restart whil other did not. Comparing the code around both options, I see no difference. How does it decides to restart a daemon? -- Emmanuel Dreyfus m...@netbsd.org ___ Gluster-devel mailing list Gluster-devel@gluster.org http://www.gluster.org/mailman/listinfo/gluster-devel
[Gluster-devel] Update on glusterfs-3.7.3 release
Hi All, I'm going to be the release-manager for GlusterFS-3.7.3. I hope to do the release on Monday 27th July, if everything goes well. As it stands now, there are about 25 changes that are under review on the release-3.7 branch [1]. I request the maintainers to of the different components to look into this list, and make sure that any patch you absolutely want in glusterfs-3.7.3 gets merged by Monday. If anyone has a change that is not present in this list, but wants it to be in for 3.7.3, please let the respective maintainer and me know about it, so that we can act on it quickly. Thanks, Kaushal [1]: https://review.gluster.org/#/q/is:open+branch:release-3.7 ___ Gluster-devel mailing list Gluster-devel@gluster.org http://www.gluster.org/mailman/listinfo/gluster-devel
Re: [Gluster-devel] volfile change
Hi Emmanuel, Restarting a already running daemon is based on restarting volume, restarting glusterd, change in topology of volfile for eg: removing/adding bricks, by performing these thing it should not restart brick, it should only restart daemon's. could you tell me the name of the option which did brick restart?? Thanx, Gaurav - Original Message - From: Emmanuel Dreyfus m...@netbsd.org To: gluster-devel@gluster.org Sent: Thursday, July 23, 2015 1:42:45 PM Subject: [Gluster-devel] volfile change Hello While testing, I noticed that some gluster volume set operations caused a brick restart whil other did not. Comparing the code around both options, I see no difference. How does it decides to restart a daemon? -- Emmanuel Dreyfus m...@netbsd.org ___ Gluster-devel mailing list Gluster-devel@gluster.org http://www.gluster.org/mailman/listinfo/gluster-devel ___ Gluster-devel mailing list Gluster-devel@gluster.org http://www.gluster.org/mailman/listinfo/gluster-devel