Re: [ceph-users] How RBD tcp connection works
Hi, Thanks Br. Yafeng On Tue, 20 Aug 2019 at 11:14, Eliza wrote: > Hi > > on 2019/8/20 11:00, fengyd wrote: > > I think you're right. > > I am not so sure about it. But I think ceph client always wants to know > the cluster's topology, so it needs to communicate with cluster all the > time. The big difference for ceph to other distributed storage is > clients participate into cluster's calculations. > > I think you know Chinese? just googled out this one: > http://blog.dnsbed.com/?p=1685 > > regards. > ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] How RBD tcp connection works
Hi on 2019/8/20 11:00, fengyd wrote: I think you're right. I am not so sure about it. But I think ceph client always wants to know the cluster's topology, so it needs to communicate with cluster all the time. The big difference for ceph to other distributed storage is clients participate into cluster's calculations. I think you know Chinese? just googled out this one: http://blog.dnsbed.com/?p=1685 regards. ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] How RBD tcp connection works
Hi, I think you're right. thanks. Br. Yafeng On Tue, 20 Aug 2019 at 10:59, Eliza wrote: > > > on 2019/8/20 10:57, fengyd wrote: > > Long connections means new tcp connection which connect the same targets > > is reestablished after timeout? > > yes, once timeouted, then reconnecting. > ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] How RBD tcp connection works
on 2019/8/20 10:57, fengyd wrote: Long connections means new tcp connection which connect the same targets is reestablished after timeout? yes, once timeouted, then reconnecting. ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] How RBD tcp connection works
Hi, Long connections means new tcp connection which connect the same targets is reestablished after timeout? On Tue, 20 Aug 2019 at 10:37, Eliza wrote: > Hi > > on 2019/8/20 10:30, fengyd wrote: > > If the creation timestamp of the FD is not changed, but the socket > > information to which the FD was linked is changed, it means new tcp > > connection is established. > > If there's no reading/wring ongoing, why new tcp connection is still > > established and the FD count is stable? > > Though I am just a ceph user not the expert, but I think each block > device as the client who is involved into CRUSH algorithm for data > rebalancing etc, so long connections between client and OSDs are kept. > > regards. > ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] How RBD tcp connection works
Hi on 2019/8/20 10:30, fengyd wrote: If the creation timestamp of the FD is not changed, but the socket information to which the FD was linked is changed, it means new tcp connection is established. If there's no reading/wring ongoing, why new tcp connection is still established and the FD count is stable? Though I am just a ceph user not the expert, but I think each block device as the client who is involved into CRUSH algorithm for data rebalancing etc, so long connections between client and OSDs are kept. regards. ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] How RBD tcp connection works
Hi, 1. Create a VM and a volume, and attach the volume to VM. Check the FD count with lsof and the FD count is increased by 10. 2. Fill the volume with dd command on the VM Check the FD count with lsof and the FD count is increased dramatically and stable after the FD count is increased by 48(48 is the exact number of OSDs) If the creation timestamp of the FD is not changed, but the socket information to which the FD was linked is changed, it means new tcp connection is established. If there's no reading/wring ongoing, why new tcp connection is still established and the FD count is stable? Br. Yafeng On Tue, 20 Aug 2019 at 10:07, Eliza wrote: > > on 2019/8/20 9:54, fengyd wrote: > > I checked the FD information with the command "ls -l /proc/25977/fd" // > > here 25977 is Qemu process. > > I found that the creation timestamp of the FD was not changed, but the > > socket information to which the FD was linked was changed. > > So, I guess the FD is reused when establishing new tcp connection. > > I alomost got a lot of tcp connections from host mounted with block > devices to ceph's backend. > > regards. > ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] How RBD tcp connection works
on 2019/8/20 9:54, fengyd wrote: I checked the FD information with the command "ls -l /proc/25977/fd" // here 25977 is Qemu process. I found that the creation timestamp of the FD was not changed, but the socket information to which the FD was linked was changed. So, I guess the FD is reused when establishing new tcp connection. I alomost got a lot of tcp connections from host mounted with block devices to ceph's backend. regards. ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] How RBD tcp connection works
Hi, I checked the FD information with the command "ls -l /proc/25977/fd" // here 25977 is Qemu process. I found that the creation timestamp of the FD was not changed, but the socket information to which the FD was linked was changed. So, I guess the FD is reused when establishing new tcp connection. [image: image.png] On Tue, 20 Aug 2019 at 04:11, Eliza wrote: > Hi, > > on 2019/8/19 16:10, fengyd wrote: > > I think when reading/writing to volume/image, tcp connection needs to be > > established which needs FD, then the FD count may increase. > > But after reading/writing, why the FD count doesn't descrease? > > The tcp may be long connections. > ___ > ceph-users mailing list > ceph-users@lists.ceph.com > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] How RBD tcp connection works
I collected the lsof at different time and found that: The total number of open FD is stable at a fixed value, and some of tcp connection are changed. On Mon, 19 Aug 2019 at 16:42, fengyd wrote: > -how long do you monitor after r/w finish? > More than 900 seconds. > > I executed the following command last Saturday and today, the output was > same. > sudo lsof -p 5509 | wc -l > > And the result from /proc: > ls -ltr /proc/5509/fd | grep socket | grep "Aug 13" | wc -l > 134 > sudo ls -ltr /proc/5509/fd | grep socket | grep "Aug 19" | wc -l > 0 > > In which configuration file can I find ms_connection_idle_timeout? > > On Mon, 19 Aug 2019 at 16:26, huang jun wrote: > >> how long do you monitor after r/w finish? >> there is a configure item named 'ms_connection_idle_timeout' which >> default value is 900 >> >> fengyd 于2019年8月19日周一 下午4:10写道: >> > >> > Hi, >> > >> > I have a question about tcp connection. >> > In the test environment, openstack uses ceph RBD as backend storage. >> > I created a VM and attache a volume/image to the VM. >> > I monitored how many fd was used by Qemu process. >> > I used the command dd to fill the whole volume/image. >> > I found that the FD count was increased, and stable at a fixed value >> after some time. >> > >> > I think when reading/writing to volume/image, tcp connection needs to >> be established which needs FD, then the FD count may increase. >> > But after reading/writing, why the FD count doesn't descrease? >> > >> > Thanks in advance. >> > BR. >> > Yafeng >> > ___ >> > ceph-users mailing list >> > ceph-users@lists.ceph.com >> > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com >> > ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] How RBD tcp connection works
-how long do you monitor after r/w finish? More than 900 seconds. I executed the following command last Saturday and today, the output was same. sudo lsof -p 5509 | wc -l And the result from /proc: ls -ltr /proc/5509/fd | grep socket | grep "Aug 13" | wc -l 134 sudo ls -ltr /proc/5509/fd | grep socket | grep "Aug 19" | wc -l 0 In which configuration file can I find ms_connection_idle_timeout? On Mon, 19 Aug 2019 at 16:26, huang jun wrote: > how long do you monitor after r/w finish? > there is a configure item named 'ms_connection_idle_timeout' which > default value is 900 > > fengyd 于2019年8月19日周一 下午4:10写道: > > > > Hi, > > > > I have a question about tcp connection. > > In the test environment, openstack uses ceph RBD as backend storage. > > I created a VM and attache a volume/image to the VM. > > I monitored how many fd was used by Qemu process. > > I used the command dd to fill the whole volume/image. > > I found that the FD count was increased, and stable at a fixed value > after some time. > > > > I think when reading/writing to volume/image, tcp connection needs to be > established which needs FD, then the FD count may increase. > > But after reading/writing, why the FD count doesn't descrease? > > > > Thanks in advance. > > BR. > > Yafeng > > ___ > > ceph-users mailing list > > ceph-users@lists.ceph.com > > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] How RBD tcp connection works
how long do you monitor after r/w finish? there is a configure item named 'ms_connection_idle_timeout' which default value is 900 fengyd 于2019年8月19日周一 下午4:10写道: > > Hi, > > I have a question about tcp connection. > In the test environment, openstack uses ceph RBD as backend storage. > I created a VM and attache a volume/image to the VM. > I monitored how many fd was used by Qemu process. > I used the command dd to fill the whole volume/image. > I found that the FD count was increased, and stable at a fixed value after > some time. > > I think when reading/writing to volume/image, tcp connection needs to be > established which needs FD, then the FD count may increase. > But after reading/writing, why the FD count doesn't descrease? > > Thanks in advance. > BR. > Yafeng > ___ > ceph-users mailing list > ceph-users@lists.ceph.com > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] How RBD tcp connection works
Hi, on 2019/8/19 16:10, fengyd wrote: I think when reading/writing to volume/image, tcp connection needs to be established which needs FD, then the FD count may increase. But after reading/writing, why the FD count doesn't descrease? The tcp may be long connections. ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
[ceph-users] How RBD tcp connection works
Hi, I have a question about tcp connection. In the test environment, openstack uses ceph RBD as backend storage. I created a VM and attache a volume/image to the VM. I monitored how many fd was used by Qemu process. I used the command dd to fill the whole volume/image. I found that the FD count was increased, and stable at a fixed value after some time. I think when reading/writing to volume/image, tcp connection needs to be established which needs FD, then the FD count may increase. But after reading/writing, why the FD count doesn't descrease? Thanks in advance. BR. Yafeng ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com