Re: patch: mod_jk load balance algorithm that accounts for current worker load
Excellent, I'd love to see this end up in the proxy loadbalancer. I just submitted the patch: http://issues.apache.org/bugzilla/show_bug.cgi?id=36138 Please do so... There is also some overlap with Apache's proxy load balancer as well, which I would want to fold back in. For example, in Apache I added the bytraffic method, which was then folded into mod_jk by Mladen. So once busyness is added to mod_jk, I'll look on adding it to the Apache tree. - To unsubscribe, e-mail: [EMAIL PROTECTED] For additional commands, e-mail: [EMAIL PROTECTED] - To unsubscribe, e-mail: [EMAIL PROTECTED] For additional commands, e-mail: [EMAIL PROTECTED]
Re: patch: mod_jk load balance algorithm that accounts for current worker load
On Aug 6, 2005, at 3:48 AM, Chris Lamprecht wrote: We'd like to submit our patch to mod_jk. We've added a new workers.properties lb.method option -- lb.method=B for Busyness, and updated the jkstatus display page accordingly. I wanted to get any feedback or suggestions from the mailing list before submitting the patch to bugzilla. Thanks, Please do so... There is also some overlap with Apache's proxy load balancer as well, which I would want to fold back in. For example, in Apache I added the bytraffic method, which was then folded into mod_jk by Mladen. So once busyness is added to mod_jk, I'll look on adding it to the Apache tree. - To unsubscribe, e-mail: [EMAIL PROTECTED] For additional commands, e-mail: [EMAIL PROTECTED]
patch: mod_jk load balance algorithm that accounts for current worker load
mod_jk developers: We have been using mod_jk for some time, (1.2.8, 1.2.10, and now 1.2.14), with Apache 2.0.50, Tomcat 5.5.9, under fedora (2.4.22 kernel). We have 6 tomcats as balanced workers, and we're using lb.method=[R]equest. When load testing our tomcats individually, they can handle about 10 requests per second. Our application is completely parallel, nothing is shared (no database). However, when we test against the load balancer, it starts out okay, but degrades to about 12 to 16 requests per second overall. It should be getting somewhere between 50 and 60 requests per second (6 servers * 10 requests per second each). With mod_jk 1.2.14 we were able to check the (very helpful) jkstatus page, and we noticed that the Busy column was very high for the lagging server, yet mod_jk kept giving it more requests, while other servers were sitting with 0 Busy. We tried both optimistic and pessimistic locking modes; pessimistic may have been slightly better but it was hard to say. We added a simple load balancing algorithm (to common/jk_lb_worker.c) that takes into account the busyness of each worker and its lbfactor, and picks the worker with the lowest current load. It ignores the Load Balancer Value. This simple algorithm improved our test from 12-16 requests per second to 60+ requests per second, and watching the jkstatus page showed that all servers were kept evenly busy. If one particular server slowed down, its Busy value increased, so it received fewer requests. We'd like to submit our patch to mod_jk. We've added a new workers.properties lb.method option -- lb.method=B for Busyness, and updated the jkstatus display page accordingly. I wanted to get any feedback or suggestions from the mailing list before submitting the patch to bugzilla. Thanks, Chris Lamprecht - To unsubscribe, e-mail: [EMAIL PROTECTED] For additional commands, e-mail: [EMAIL PROTECTED]
RE: patch: mod_jk load balance algorithm that accounts for current worker load
Dear Valued Customer, Thank you for contacting Customer Support at www.ballystore.com. Your questions and concerns are important to us and we are dedicated to assisting you in anyway possible. In order to assist you in the most efficient and timely manner, all email correspondence must be submitted through our online email form. To locate our online email form, we ask that you visit our Help Desk at Customer Support at www.ballystore.com/helpdesk and choose FAQ/Contact Us under Online Store Information. Then, choose the subject that will address your question and send us an email through our online email form. We apologize for any inconvenience this may cause you. Sincerely, Customer Support at www.ballystore.com Original Message Follows: mod_jk developers: We have been using mod_jk for some time, (1.2.8, 1.2.10, and now 1.2.14), with Apache 2.0.50, Tomcat 5.5.9, under fedora (2.4.22 kernel). We have 6 tomcats as balanced workers, and we're using lb.method=[R]equest. When load testing our tomcats individually, they can handle about 10 requests per second. Our application is completely parallel, nothing is shared (no database). However, when we test against the load balancer, it starts out okay, but degrades to about 12 to 16 requests per second overall. It should be getting somewhere between 50 and 60 requests per second (6 servers * 10 requests per second each). With mod_jk 1.2.14 we were able to check the (very helpful) jkstatus page, and we noticed that the Busy column was very high for the lagging server, yet mod_jk kept giving it more requests, while other servers were sitting with 0 Busy. We tried both optimistic and pessimistic locking modes; pessimistic may have been slightly better but it was hard to say. We added a simple load balancing algorithm (to common/jk_lb_worker.c) that takes into account the busyness of each worker and its lbfactor, and picks the worker with the lowest current load. It ignores the Load Balancer Value. This simple algorithm improved our test from 12-16 requests per second to 60+ requests per second, and watching the jkstatus page showed that all servers were kept evenly busy. If one particular server slowed down, its Busy value increased, so it received fewer requests. We'd like to submit our patch to mod_jk. We've added a new workers.properties lb.method option -- lb.method=B for Busyness, and updated the jkstatus display page accordingly. I wanted to get any feedback or suggestions from the mailing list before submitting the patch to bugzilla. Thanks, Chris Lamprecht - To unsubscribe, e-mail: [EMAIL PROTECTED] For additional commands, e-mail: [EMAIL PROTECTED] This message, including any attachments, is solely for the use of the intended recipient(s) and may contain confidential and/or privileged information. Any unauthorized review, use, disclosure or distribution of this communication is expressly prohibited. If you are not the intended recipient, please contact the sender by reply e-mail and destroy any and all copies of the original message. Thank you. - To unsubscribe, e-mail: [EMAIL PROTECTED] For additional commands, e-mail: [EMAIL PROTECTED]
RE: RE: patch: mod_jk load balance algorithm that accounts for current worker load
Dear Valued Customer, Thank you for contacting Customer Support at www.ballystore.com. Your questions and concerns are important to us and we are dedicated to assisting you in anyway possible. In order to assist you in the most efficient and timely manner, all email correspondence must be submitted through our online email form. To locate our online email form, we ask that you visit our Help Desk at Customer Support at www.ballystore.com/helpdesk and choose FAQ/Contact Us under Online Store Information. Then, choose the subject that will address your question and send us an email through our online email form. We apologize for any inconvenience this may cause you. Sincerely, Customer Support at www.ballystore.com Original Message Follows: Dear Valued Customer, Thank you for contacting Customer Support at www.ballystore.com. Your questions and concerns are important to us and we are dedicated to assisting you in anyway possible. In order to assist you in the most efficient and timely manner, all email correspondence must be submitted through our online email form. To locate our online email form, we ask that you visit our Help Desk at Customer Support at www.ballystore.com/helpdesk and choose FAQ/Contact Us under Online Store Information. Then, choose the subject that will address your question and send us an email through our online email form. We apologize for any inconvenience this may cause you. Sincerely, Customer Support at www.ballystore.com Original Message Follows: mod_jk developers: We have been using mod_jk for some time, (1.2.8, 1.2.10, and now 1.2.14), with Apache 2.0.50, Tomcat 5.5.9, under fedora (2.4.22 kernel). We have 6 tomcats as balanced workers, and we're using lb.method=[R]equest. When load testing our tomcats individually, they can handle about 10 requests per second. Our application is completely parallel, nothing is shared (no database). However, when we test against the load balancer, it starts out okay, but degrades to about 12 to 16 requests per second overall. It should be getting somewhere between 50 and 60 requests per second (6 servers * 10 requests per second each). With mod_jk 1.2.14 we were able to check the (very helpful) jkstatus page, and we noticed that the Busy column was very high for the lagging server, yet mod_jk kept giving it more requests, while other servers were sitting with 0 Busy. We tried both optimistic and pessimistic locking modes; pessimistic may have been slightly better but it was hard to say. We added a simple load balancing algorithm (to common/jk_lb_worker.c) that takes into account the busyness of each worker and its lbfactor, and picks the worker with the lowest current load. It ignores the Load Balancer Value. This simple algorithm improved our test from 12-16 requests per second to 60+ requests per second, and watching the jkstatus page showed that all servers were kept evenly busy. If one particular server slowed down, its Busy value increased, so it received fewer requests. We'd like to submit our patch to mod_jk. We've added a new workers.properties lb.method option -- lb.method=B for Busyness, and updated the jkstatus display page accordingly. I wanted to get any feedback or suggestions from the mailing list before submitting the patch to bugzilla. Thanks, Chris Lamprecht - To unsubscribe, e-mail: [EMAIL PROTECTED] For additional commands, e-mail: [EMAIL PROTECTED] This message, including any attachments, is solely for the use of the intended recipient(s) and may contain confidential and/or privileged information. Any unauthorized review, use, disclosure or distribution of this communication is expressly prohibited. If you are not the intended recipient, please contact the sender by reply e-mail and destroy any and all copies of the original message. Thank you. - To unsubscribe, e-mail: [EMAIL PROTECTED] For additional commands, e-mail: [EMAIL PROTECTED] This message, including any attachments, is solely for the use of the intended recipient(s) and may contain confidential and/or privileged information. Any unauthorized review, use, disclosure or distribution of this communication is expressly prohibited. If you are not the intended recipient, please contact the sender by reply e-mail and destroy any and all copies of the original message. Thank you. - To unsubscribe, e-mail: [EMAIL PROTECTED] For additional commands, e-mail: [EMAIL PROTECTED]
RE: RE: RE: patch: mod_jk load balance algorithm that accounts for current worker load
Dear Valued Customer, Thank you for contacting Customer Support at www.ballystore.com. Your questions and concerns are important to us and we are dedicated to assisting you in anyway possible. In order to assist you in the most efficient and timely manner, all email correspondence must be submitted through our online email form. To locate our online email form, we ask that you visit our Help Desk at Customer Support at www.ballystore.com/helpdesk and choose FAQ/Contact Us under Online Store Information. Then, choose the subject that will address your question and send us an email through our online email form. We apologize for any inconvenience this may cause you. Sincerely, Customer Support at www.ballystore.com Original Message Follows: Dear Valued Customer, Thank you for contacting Customer Support at www.ballystore.com. Your questions and concerns are important to us and we are dedicated to assisting you in anyway possible. In order to assist you in the most efficient and timely manner, all email correspondence must be submitted through our online email form. To locate our online email form, we ask that you visit our Help Desk at Customer Support at www.ballystore.com/helpdesk and choose FAQ/Contact Us under Online Store Information. Then, choose the subject that will address your question and send us an email through our online email form. We apologize for any inconvenience this may cause you. Sincerely, Customer Support at www.ballystore.com Original Message Follows: Dear Valued Customer, Thank you for contacting Customer Support at www.ballystore.com. Your questions and concerns are important to us and we are dedicated to assisting you in anyway possible. In order to assist you in the most efficient and timely manner, all email correspondence must be submitted through our online email form. To locate our online email form, we ask that you visit our Help Desk at Customer Support at www.ballystore.com/helpdesk and choose FAQ/Contact Us under Online Store Information. Then, choose the subject that will address your question and send us an email through our online email form. We apologize for any inconvenience this may cause you. Sincerely, Customer Support at www.ballystore.com Original Message Follows: mod_jk developers: We have been using mod_jk for some time, (1.2.8, 1.2.10, and now 1.2.14), with Apache 2.0.50, Tomcat 5.5.9, under fedora (2.4.22 kernel). We have 6 tomcats as balanced workers, and we're using lb.method=[R]equest. When load testing our tomcats individually, they can handle about 10 requests per second. Our application is completely parallel, nothing is shared (no database). However, when we test against the load balancer, it starts out okay, but degrades to about 12 to 16 requests per second overall. It should be getting somewhere between 50 and 60 requests per second (6 servers * 10 requests per second each). With mod_jk 1.2.14 we were able to check the (very helpful) jkstatus page, and we noticed that the Busy column was very high for the lagging server, yet mod_jk kept giving it more requests, while other servers were sitting with 0 Busy. We tried both optimistic and pessimistic locking modes; pessimistic may have been slightly better but it was hard to say. We added a simple load balancing algorithm (to common/jk_lb_worker.c) that takes into account the busyness of each worker and its lbfactor, and picks the worker with the lowest current load. It ignores the Load Balancer Value. This simple algorithm improved our test from 12-16 requests per second to 60+ requests per second, and watching the jkstatus page showed that all servers were kept evenly busy. If one particular server slowed down, its Busy value increased, so it received fewer requests. We'd like to submit our patch to mod_jk. We've added a new workers.properties lb.method option -- lb.method=B for Busyness, and updated the jkstatus display page accordingly. I wanted to get any feedback or suggestions from the mailing list before submitting the patch to bugzilla. Thanks, Chris Lamprecht - To unsubscribe, e-mail: [EMAIL PROTECTED] For additional commands, e-mail: [EMAIL PROTECTED] This message, including any attachments, is solely for the use of the intended recipient(s) and may contain confidential and/or privileged information. Any unauthorized review, use, disclosure or distribution of this communication is expressly prohibited. If you are not the intended recipient, please contact the sender by reply e-mail and destroy any and all copies of the original message. Thank you. - To unsubscribe, e-mail: [EMAIL PROTECTED] For additional commands, e-mail: [EMAIL PROTECTED] This message, including any
RE: RE: RE: RE: patch: mod_jk load balance algorithm that accounts for current worker load
Dear Valued Customer, Thank you for contacting Customer Support at www.ballystore.com. Your questions and concerns are important to us and we are dedicated to assisting you in anyway possible. In order to assist you in the most efficient and timely manner, all email correspondence must be submitted through our online email form. To locate our online email form, we ask that you visit our Help Desk at Customer Support at www.ballystore.com/helpdesk and choose FAQ/Contact Us under Online Store Information. Then, choose the subject that will address your question and send us an email through our online email form. We apologize for any inconvenience this may cause you. Sincerely, Customer Support at www.ballystore.com Original Message Follows: Dear Valued Customer, Thank you for contacting Customer Support at www.ballystore.com. Your questions and concerns are important to us and we are dedicated to assisting you in anyway possible. In order to assist you in the most efficient and timely manner, all email correspondence must be submitted through our online email form. To locate our online email form, we ask that you visit our Help Desk at Customer Support at www.ballystore.com/helpdesk and choose FAQ/Contact Us under Online Store Information. Then, choose the subject that will address your question and send us an email through our online email form. We apologize for any inconvenience this may cause you. Sincerely, Customer Support at www.ballystore.com Original Message Follows: Dear Valued Customer, Thank you for contacting Customer Support at www.ballystore.com. Your questions and concerns are important to us and we are dedicated to assisting you in anyway possible. In order to assist you in the most efficient and timely manner, all email correspondence must be submitted through our online email form. To locate our online email form, we ask that you visit our Help Desk at Customer Support at www.ballystore.com/helpdesk and choose FAQ/Contact Us under Online Store Information. Then, choose the subject that will address your question and send us an email through our online email form. We apologize for any inconvenience this may cause you. Sincerely, Customer Support at www.ballystore.com Original Message Follows: Dear Valued Customer, Thank you for contacting Customer Support at www.ballystore.com. Your questions and concerns are important to us and we are dedicated to assisting you in anyway possible. In order to assist you in the most efficient and timely manner, all email correspondence must be submitted through our online email form. To locate our online email form, we ask that you visit our Help Desk at Customer Support at www.ballystore.com/helpdesk and choose FAQ/Contact Us under Online Store Information. Then, choose the subject that will address your question and send us an email through our online email form. We apologize for any inconvenience this may cause you. Sincerely, Customer Support at www.ballystore.com Original Message Follows: mod_jk developers: We have been using mod_jk for some time, (1.2.8, 1.2.10, and now 1.2.14), with Apache 2.0.50, Tomcat 5.5.9, under fedora (2.4.22 kernel). We have 6 tomcats as balanced workers, and we're using lb.method=[R]equest. When load testing our tomcats individually, they can handle about 10 requests per second. Our application is completely parallel, nothing is shared (no database). However, when we test against the load balancer, it starts out okay, but degrades to about 12 to 16 requests per second overall. It should be getting somewhere between 50 and 60 requests per second (6 servers * 10 requests per second each). With mod_jk 1.2.14 we were able to check the (very helpful) jkstatus page, and we noticed that the Busy column was very high for the lagging server, yet mod_jk kept giving it more requests, while other servers were sitting with 0 Busy. We tried both optimistic and pessimistic locking modes; pessimistic may have been slightly better but it was hard to say. We added a simple load balancing algorithm (to common/jk_lb_worker.c) that takes into account the busyness of each worker and its lbfactor, and picks the worker with the lowest current load. It ignores the Load Balancer Value. This simple algorithm improved our test from 12-16 requests per second to 60+ requests per second, and watching the jkstatus page showed that all servers were kept evenly busy. If one particular server slowed down, its Busy value increased, so it received fewer requests. We'd like to submit our patch to mod_jk. We've added a new workers.properties lb.method option -- lb.method=B for Busyness, and updated the jkstatus display page accordingly. I wanted to get any feedback or suggestions from the mailing list before submitting the patch to bugzilla. Thanks, Chris
Re: patch: mod_jk load balance algorithm that accounts for current worker load
Chris Lamprecht wrote: mod_jk developers: We have been using mod_jk for some time, (1.2.8, 1.2.10, and now 1.2.14), with Apache 2.0.50, Tomcat 5.5.9, under fedora (2.4.22 kernel). We have 6 tomcats as balanced workers, and we're using lb.method=[R]equest. Great! Can you open an bugzilla entry for Native:JK and attach the patch. Please file that as enhancement. Regards, Mladen. - To unsubscribe, e-mail: [EMAIL PROTECTED] For additional commands, e-mail: [EMAIL PROTECTED]
