Re: [Gluster-users] Hi new to Gluster
Hello Tarkeshwar, GlusterFS uses file level and range locks based on the operation. With the description you have given below, Gluster definitely seems to be the right choice for your workload. I recommend that you should try a proof of concept with Gluster under your application work load to experience the benefits. You can always reach out to GlusterFS community (this mailing list) for any queries and help regarding the same. Regards Nagaprasad. > On 15-Sep-2015, at 3:16 pm, M.Tarkeshwar Raowrote: > > Hi Nagaprasad, > > Thanks for reply. > > > Nature of I/O workload your application is generating: > It is very high. Our product woking on files. It is collecting data(multi > process and multi threaded) from remote nodes and then processing it and then > it sending it to remote locations. > our Execution engine runs the processing busines logic. So huge no of > open,read,write,rename calls in the our code per second. > > recently we made it scalable as well, so our business logic runs horigontally > from multiple nodes. we are collecting it in common directory and reading it > from same directory for processing. > > We are using Veritas cluster file system. It is locking on directory level. > Since same directory accessed from multiple nodes. There is a delay in > processing. further it reducess performance drastically. > > For improving performance we made some changes in our application by breaking > the direcotories for collection and processing. > By this we got performance improvement. > > We feel if we change our file system we will get more improvement. Please > suggest. > > > Regards > Tarkeshwar > >> On Tue, Sep 15, 2015 at 2:27 PM, Nagaprasad Sathyanarayana >> wrote: >> Hello Tarakeshwar, >> >> Firstly, welcome to the Gluster community. >> >> Please visit >> http://www.gluster.org/community/documentation/index.php/GlusterFS_General_FAQ, >> which answers some of your queries about GlusterFS capabilities. >> If you could share with us the nature of I/O workload your application is >> generating, the performance need of your application, type of client access >> (NFS, CIFS etc.,) >> that users of your application need etc, we will be in a better position to >> guide. >> >> Regards >> Nagaprasad >> >> - Original Message - >> From: "M.Tarkeshwar Rao" >> To: gluster-users@gluster.org >> Sent: Tuesday, 15 September, 2015 12:15:23 PM >> Subject: [Gluster-users] Hi new to Gluster >> >> Hi all, >> We have a product which is written in c++ on Red hat. >> In production our customers using our product with Veritas cluster file >> system for HA and as sharded storage(EMC). >> Initially this product was run on only single node. In our last release we >> make it Scalable(more than one nodes). >> Due to excessive locking(CFS) we are not getting the performance. >> Can you please suggest Gluster will resolve our problem as it is distributed >> file system. >> is Gluster POSIX complined? >> Can we use it in Production? Pls suggest. >> If any other file system please suggest. >> Regards >> Tarkeshwar >> >> ___ >> Gluster-users mailing list >> Gluster-users@gluster.org >> http://www.gluster.org/mailman/listinfo/gluster-users > > ___ > Gluster-users mailing list > Gluster-users@gluster.org > http://www.gluster.org/mailman/listinfo/gluster-users ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Hi new to Gluster
Hello Tarakeshwar, Firstly, welcome to the Gluster community. Please visit http://www.gluster.org/community/documentation/index.php/GlusterFS_General_FAQ, which answers some of your queries about GlusterFS capabilities. If you could share with us the nature of I/O workload your application is generating, the performance need of your application, type of client access (NFS, CIFS etc.,) that users of your application need etc, we will be in a better position to guide. Regards Nagaprasad - Original Message - From: "M.Tarkeshwar Rao"To: gluster-users@gluster.org Sent: Tuesday, 15 September, 2015 12:15:23 PM Subject: [Gluster-users] Hi new to Gluster Hi all, We have a product which is written in c++ on Red hat. In production our customers using our product with Veritas cluster file system for HA and as sharded storage(EMC). Initially this product was run on only single node. In our last release we make it Scalable(more than one nodes). Due to excessive locking(CFS) we are not getting the performance. Can you please suggest Gluster will resolve our problem as it is distributed file system. is Gluster POSIX complined? Can we use it in Production? Pls suggest. If any other file system please suggest. Regards Tarkeshwar ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Hi new to Gluster
Hi Nagaprasad, Thanks for reply. *Nature of I/O workload your application is generating:* It is very high. Our product woking on files. It is collecting data(multi process and multi threaded) from remote nodes and then processing it and then it sending it to remote locations. our Execution engine runs the processing busines logic. So huge no of open,read,write,rename calls in the our code per second. recently we made it scalable as well, so our business logic runs horigontally from multiple nodes. we are collecting it in common directory and reading it from same directory for processing. We are using Veritas cluster file system. It is locking on directory level. Since same directory accessed from multiple nodes. There is a delay in processing. further it reducess performance drastically. For improving performance we made some changes in our application by breaking the direcotories for collection and processing. By this we got performance improvement. We feel if we change our file system we will get more improvement. Please suggest. Regards Tarkeshwar On Tue, Sep 15, 2015 at 2:27 PM, Nagaprasad Sathyanarayana < nsath...@redhat.com> wrote: > Hello Tarakeshwar, > > Firstly, welcome to the Gluster community. > > Please visit > http://www.gluster.org/community/documentation/index.php/GlusterFS_General_FAQ, > which answers some of your queries about GlusterFS capabilities. > If you could share with us the nature of I/O workload your application is > generating, the performance need of your application, type of client access > (NFS, CIFS etc.,) > that users of your application need etc, we will be in a better position > to guide. > > Regards > Nagaprasad > > - Original Message - > From: "M.Tarkeshwar Rao"> To: gluster-users@gluster.org > Sent: Tuesday, 15 September, 2015 12:15:23 PM > Subject: [Gluster-users] Hi new to Gluster > > Hi all, > We have a product which is written in c++ on Red hat. > In production our customers using our product with Veritas cluster file > system for HA and as sharded storage(EMC). > Initially this product was run on only single node. In our last release we > make it Scalable(more than one nodes). > Due to excessive locking(CFS) we are not getting the performance. > Can you please suggest Gluster will resolve our problem as it is > distributed file system. > is Gluster POSIX complined? > Can we use it in Production? Pls suggest. > If any other file system please suggest. > Regards > Tarkeshwar > > ___ > Gluster-users mailing list > Gluster-users@gluster.org > http://www.gluster.org/mailman/listinfo/gluster-users > ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users