NAME Retry SYNOPSIS A one-feature module, this provides a method to wrap any function in automatic retry logic, with exponential back-off delays, and a callback for each time an attempt fails. Example: use Retry; use Try::Tiny; use LWP::UserAgent; my $code_to_retry = sub { my $r = LWP::UserAgent->new->get("http://example.com"); die $r->status_line unless $r->is_success; return $r; }; my $agent = Retry->new( # This callback is optional: failure_callback => sub { warn "Transient error: " . $_[0]; }, ); try { $agent->retry($code_to_retry) } catch { warn "All attempts failed: $_"; }; ATTRIBUTES retry_delay This is the initial delay used when the routine failed, before retrying again. Every subsequent failure doubles the amount. It defaults to 8 seconds. max_retry_attempts The maximum number of retries we should attempt before giving up completely. It defaults to 5. failure_callback Optional. To be notified of *every* failure (even if we eventually succeed on a later retry), install a subroutine callback here. For example: Retry->new( failure_callback => sub { warn "failed $count++ times" } ); METHODS retry Its purpose is to execute the passed subroutine, over and over, until it succeeds, or the number of retries is exceeded. The delay between retries increases exponentially. (Failure is indicated by the sub dying) If the subroutine succeeds, then its scalar return value will be returned by retry. For example, you could replace this: my $val = unreliable_web_request(); With this: my $val = Retry->new->retry( sub { unreliable_web_request() } ); AUTHOR Toby Corkindale, LICENSE This module is released under the Perl Artistic License 2.0: It is based upon source code which is Copyright 2010 Strategic Data Pty Ltd, however it is used and released with permission. SEE ALSO Attempt Retry differs from Attempt in having exponentially increasing delays, and by having a callback inbetween attempts. However Attempt has a simpler syntax.