Hi Ben and thanks for review. I double checked and I can confirm the patch is ok. Changes which are applied to rpc pointer within do_convert() and do_need_conversion() function are local to functions and not propagated to outside world. This is because rpc is passed to command handler functions as pointer and reference to the pointer. Therefore main() could not know rpc has been changed inside command handler functions.
regards,Damijan. On Mon, Sep 30, 2019 at 10:47 PM Ben Pfaff <[email protected]> wrote: > On Mon, Sep 30, 2019 at 10:21:00AM +0200, Damijan Skvarc wrote: > > Memory leak itself is not so important, however the problem is that > > it is caused by forgetting to close rpc channel which might in > > a long term lead to the leak of system resources. > > > > Memory leak is reported by Valgrin running test suite and is expressed > as: > > Thanks for the fix. > > I don't understand why this is necessary. These functions are called > from main(), which closes the rpc connection just afterward: > > command->handler(rpc, database, argc - optind, argv + optind); > > free(database); > jsonrpc_close(rpc); > > Can you take a closer look? > _______________________________________________ dev mailing list [email protected] https://mail.openvswitch.org/mailman/listinfo/ovs-dev
