redict/tests/support/util.tcl

764 lines
23 KiB
Tcl
Raw Normal View History

proc randstring {min max {type binary}} {
set len [expr {$min+int(rand()*($max-$min+1))}]
set output {}
if {$type eq {binary}} {
set minval 0
set maxval 255
} elseif {$type eq {alpha}} {
set minval 48
set maxval 122
} elseif {$type eq {compr}} {
set minval 48
set maxval 52
}
while {$len} {
set rr [expr {$minval+int(rand()*($maxval-$minval+1))}]
if {$type eq {alpha} && $rr eq 92} {
set rr 90; # avoid putting '\' char in the string, it can mess up TCL processing
}
append output [format "%c" $rr]
incr len -1
}
return $output
}
# Useful for some test
proc zlistAlikeSort {a b} {
if {[lindex $a 0] > [lindex $b 0]} {return 1}
if {[lindex $a 0] < [lindex $b 0]} {return -1}
string compare [lindex $a 1] [lindex $b 1]
}
# Return all log lines starting with the first line that contains a warning.
# Generally, this will be an assertion error with a stack trace.
proc crashlog_from_file {filename} {
set lines [split [exec cat $filename] "\n"]
set matched 0
set logall 0
set result {}
foreach line $lines {
if {[string match {*REDIS BUG REPORT START*} $line]} {
set logall 1
}
if {[regexp {^\[\d+\]\s+\d+\s+\w+\s+\d{2}:\d{2}:\d{2} \#} $line]} {
set matched 1
}
if {$logall || $matched} {
lappend result $line
}
}
join $result "\n"
}
proc getInfoProperty {infostr property} {
if {[regexp "\r\n$property:(.*?)\r\n" $infostr _ value]} {
set _ $value
}
}
# Return value for INFO property
proc status {r property} {
set _ [getInfoProperty [{*}$r info] $property]
}
proc waitForBgsave r {
while 1 {
if {[status r rdb_bgsave_in_progress] eq 1} {
if {$::verbose} {
puts -nonewline "\nWaiting for background save to finish... "
flush stdout
}
after 1000
} else {
break
}
}
}
proc waitForBgrewriteaof r {
while 1 {
if {[status r aof_rewrite_in_progress] eq 1} {
if {$::verbose} {
puts -nonewline "\nWaiting for background AOF rewrite to finish... "
flush stdout
}
after 1000
} else {
break
}
}
}
proc wait_for_sync r {
wait_for_condition 50 100 {
[status $r master_link_status] eq "up"
} else {
fail "replica didn't sync in time"
}
}
2018-11-11 02:22:42 -05:00
proc wait_for_ofs_sync {r1 r2} {
wait_for_condition 50 100 {
[status $r1 master_repl_offset] eq [status $r2 master_repl_offset]
} else {
fail "replica didn't sync in time"
}
}
proc wait_done_loading r {
wait_for_condition 50 100 {
[catch {$r ping} e] == 0
} else {
fail "Loading DB is taking too much time."
}
}
# count current log lines in server's stdout
proc count_log_lines {srv_idx} {
set _ [string trim [exec wc -l < [srv $srv_idx stdout]]]
}
# returns the number of times a line with that pattern appears in a file
proc count_message_lines {file pattern} {
set res 0
# exec fails when grep exists with status other than 0 (when the patter wasn't found)
catch {
set res [string trim [exec grep $pattern $file 2> /dev/null | wc -l]]
}
return $res
}
# returns the number of times a line with that pattern appears in the log
proc count_log_message {srv_idx pattern} {
set stdout [srv $srv_idx stdout]
return [count_message_lines $stdout $pattern]
}
# verify pattern exists in server's sdtout after a certain line number
proc verify_log_message {srv_idx pattern from_line} {
incr from_line
set result [exec tail -n +$from_line < [srv $srv_idx stdout]]
if {![string match $pattern $result]} {
error "assertion:expected message not found in log file: $pattern"
}
}
# wait for pattern to be found in server's stdout after certain line number
# return value is a list containing the line that matched the pattern and the line number
proc wait_for_log_messages {srv_idx patterns from_line maxtries delay} {
set retry $maxtries
set next_line [expr $from_line + 1] ;# searching form the line after
set stdout [srv $srv_idx stdout]
while {$retry} {
# re-read the last line (unless it's before to our first), last time we read it, it might have been incomplete
set next_line [expr $next_line - 1 > $from_line + 1 ? $next_line - 1 : $from_line + 1]
set result [exec tail -n +$next_line < $stdout]
set result [split $result "\n"]
foreach line $result {
foreach pattern $patterns {
if {[string match $pattern $line]} {
return [list $line $next_line]
}
}
incr next_line
}
incr retry -1
after $delay
}
if {$retry == 0} {
if {$::verbose} {
puts "content of $stdout from line: $from_line:"
puts [exec tail -n +$from_line < $stdout]
}
fail "log message of '$patterns' not found in $stdout after line: $from_line till line: [expr $next_line -1]"
}
}
# write line to server log file
proc write_log_line {srv_idx msg} {
set logfile [srv $srv_idx stdout]
set fd [open $logfile "a+"]
puts $fd "### $msg"
close $fd
}
2013-06-25 09:32:37 -04:00
# Random integer between 0 and max (excluded).
proc randomInt {max} {
expr {int(rand()*$max)}
}
2013-06-25 09:32:37 -04:00
# Random signed integer between -max and max (both extremes excluded).
proc randomSignedInt {max} {
set i [randomInt $max]
if {rand() > 0.5} {
set i -$i
}
return $i
}
proc randpath args {
set path [expr {int(rand()*[llength $args])}]
uplevel 1 [lindex $args $path]
}
proc randomValue {} {
randpath {
# Small enough to likely collide
randomSignedInt 1000
} {
# 32 bit compressible signed/unsigned
randpath {randomSignedInt 2000000000} {randomSignedInt 4000000000}
} {
# 64 bit
randpath {randomSignedInt 1000000000000}
} {
# Random string
randpath {randstring 0 256 alpha} \
{randstring 0 256 compr} \
{randstring 0 256 binary}
}
}
proc randomKey {} {
randpath {
# Small enough to likely collide
randomInt 1000
} {
# 32 bit compressible signed/unsigned
randpath {randomInt 2000000000} {randomInt 4000000000}
} {
# 64 bit
randpath {randomInt 1000000000000}
} {
# Random string
randpath {randstring 1 256 alpha} \
{randstring 1 256 compr}
}
}
proc findKeyWithType {r type} {
for {set j 0} {$j < 20} {incr j} {
set k [{*}$r randomkey]
if {$k eq {}} {
return {}
}
if {[{*}$r type $k] eq $type} {
return $k
}
}
return {}
}
2010-08-03 07:38:39 -04:00
proc createComplexDataset {r ops {opt {}}} {
for {set j 0} {$j < $ops} {incr j} {
set k [randomKey]
set k2 [randomKey]
set f [randomValue]
set v [randomValue]
2010-08-03 07:38:39 -04:00
if {[lsearch -exact $opt useexpire] != -1} {
if {rand() < 0.1} {
{*}$r expire [randomKey] [randomInt 2]
}
}
randpath {
set d [expr {rand()}]
} {
set d [expr {rand()}]
} {
set d [expr {rand()}]
} {
set d [expr {rand()}]
} {
set d [expr {rand()}]
} {
randpath {set d +inf} {set d -inf}
}
set t [{*}$r type $k]
if {$t eq {none}} {
randpath {
{*}$r set $k $v
} {
{*}$r lpush $k $v
} {
{*}$r sadd $k $v
} {
{*}$r zadd $k $d $v
} {
{*}$r hset $k $f $v
} {
{*}$r del $k
}
set t [{*}$r type $k]
}
switch $t {
{string} {
# Nothing to do
}
{list} {
randpath {{*}$r lpush $k $v} \
{{*}$r rpush $k $v} \
{{*}$r lrem $k 0 $v} \
{{*}$r rpop $k} \
{{*}$r lpop $k}
}
{set} {
randpath {{*}$r sadd $k $v} \
{{*}$r srem $k $v} \
{
2010-11-04 05:48:49 -04:00
set otherset [findKeyWithType {*}$r set]
if {$otherset ne {}} {
randpath {
{*}$r sunionstore $k2 $k $otherset
} {
{*}$r sinterstore $k2 $k $otherset
} {
{*}$r sdiffstore $k2 $k $otherset
}
}
}
}
{zset} {
randpath {{*}$r zadd $k $d $v} \
{{*}$r zrem $k $v} \
{
2010-11-04 05:48:49 -04:00
set otherzset [findKeyWithType {*}$r zset]
if {$otherzset ne {}} {
randpath {
{*}$r zunionstore $k2 2 $k $otherzset
} {
{*}$r zinterstore $k2 2 $k $otherzset
}
}
}
}
{hash} {
randpath {{*}$r hset $k $f $v} \
{{*}$r hdel $k $f}
}
}
}
}
proc formatCommand {args} {
set cmd "*[llength $args]\r\n"
foreach a $args {
append cmd "$[string length $a]\r\n$a\r\n"
}
set _ $cmd
}
2010-07-27 08:42:11 -04:00
proc csvdump r {
set o {}
2015-08-05 06:27:15 -04:00
for {set db 0} {$db < 16} {incr db} {
{*}$r select $db
foreach k [lsort [{*}$r keys *]] {
set type [{*}$r type $k]
append o [csvstring $db] , [csvstring $k] , [csvstring $type] ,
switch $type {
string {
append o [csvstring [{*}$r get $k]] "\n"
2010-07-27 08:42:11 -04:00
}
2015-08-05 06:27:15 -04:00
list {
foreach e [{*}$r lrange $k 0 -1] {
append o [csvstring $e] ,
}
append o "\n"
2010-07-27 08:42:11 -04:00
}
2015-08-05 06:27:15 -04:00
set {
foreach e [lsort [{*}$r smembers $k]] {
append o [csvstring $e] ,
}
append o "\n"
2010-07-27 08:42:11 -04:00
}
2015-08-05 06:27:15 -04:00
zset {
foreach e [{*}$r zrange $k 0 -1 withscores] {
append o [csvstring $e] ,
}
append o "\n"
2010-07-27 08:42:11 -04:00
}
2015-08-05 06:27:15 -04:00
hash {
set fields [{*}$r hgetall $k]
set newfields {}
foreach {k v} $fields {
lappend newfields [list $k $v]
}
set fields [lsort -index 0 $newfields]
foreach kv $fields {
append o [csvstring [lindex $kv 0]] ,
append o [csvstring [lindex $kv 1]] ,
}
append o "\n"
2010-07-27 08:42:11 -04:00
}
}
}
}
2015-08-05 06:27:15 -04:00
{*}$r select 9
2010-07-27 08:42:11 -04:00
return $o
}
proc csvstring s {
return "\"$s\""
}
proc roundFloat f {
format "%.10g" $f
}
set ::last_port_attempted 0
proc find_available_port {start count} {
set port [expr $::last_port_attempted + 1]
for {set attempts 0} {$attempts < $count} {incr attempts} {
if {$port < $start || $port >= $start+$count} {
set port $start
}
if {[catch {set fd1 [socket 127.0.0.1 $port]}] &&
[catch {set fd2 [socket 127.0.0.1 [expr $port+10000]]}]} {
set ::last_port_attempted $port
return $port
} else {
catch {
close $fd1
close $fd2
}
}
incr port
}
error "Can't find a non busy port in the $start-[expr {$start+$count-1}] range."
}
2014-02-17 11:36:50 -05:00
# Test if TERM looks like to support colors
proc color_term {} {
expr {[info exists ::env(TERM)] && [string match *xterm* $::env(TERM)]}
}
proc colorstr {color str} {
if {[color_term]} {
set b 0
if {[string range $color 0 4] eq {bold-}} {
set b 1
set color [string range $color 5 end]
}
switch $color {
red {set colorcode {31}}
green {set colorcode {32}}
yellow {set colorcode {33}}
blue {set colorcode {34}}
magenta {set colorcode {35}}
cyan {set colorcode {36}}
white {set colorcode {37}}
default {set colorcode {37}}
}
if {$colorcode ne {}} {
return "\033\[$b;${colorcode};49m$str\033\[0m"
2014-02-17 11:36:50 -05:00
}
} else {
return $str
}
}
2014-07-10 05:24:59 -04:00
Sanitize dump payload: fuzz tester and fixes for segfaults and leaks it exposed The test creates keys with various encodings, DUMP them, corrupt the payload and RESTORES it. It utilizes the recently added use-exit-on-panic config to distinguish between asserts and segfaults. If the restore succeeds, it runs random commands on the key to attempt to trigger a crash. It runs in two modes, one with deep sanitation enabled and one without. In the first one we don't expect any assertions or segfaults, in the second one we expect assertions, but no segfaults. We also check for leaks and invalid reads using valgrind, and if we find them we print the commands that lead to that issue. Changes in the code (other than the test): - Replace a few NPD (null pointer deference) flows and division by zero with an assertion, so that it doesn't fail the test. (since we set the server to use `exit` rather than `abort` on assertion). - Fix quite a lot of flows in rdb.c that could have lead to memory leaks in RESTORE command (since it now responds with an error rather than panic) - Add a DEBUG flag for SET-SKIP-CHECKSUM-VALIDATION so that the test don't need to bother with faking a valid checksum - Remove a pile of code in serverLogObjectDebugInfo which is actually unsafe to run in the crash report (see comments in the code) - fix a missing boundary check in lzf_decompress test suite infra improvements: - be able to run valgrind checks before the process terminates - rotate log files when restarting servers
2020-08-14 09:05:34 -04:00
proc find_valgrind_errors {stderr on_termination} {
set fd [open $stderr]
set buf [read $fd]
close $fd
# Look for stack trace (" at 0x") and other errors (Invalid, Mismatched, etc).
# Look for "Warnings", but not the "set address range perms". These don't indicate any real concern.
Sanitize dump payload: fuzz tester and fixes for segfaults and leaks it exposed The test creates keys with various encodings, DUMP them, corrupt the payload and RESTORES it. It utilizes the recently added use-exit-on-panic config to distinguish between asserts and segfaults. If the restore succeeds, it runs random commands on the key to attempt to trigger a crash. It runs in two modes, one with deep sanitation enabled and one without. In the first one we don't expect any assertions or segfaults, in the second one we expect assertions, but no segfaults. We also check for leaks and invalid reads using valgrind, and if we find them we print the commands that lead to that issue. Changes in the code (other than the test): - Replace a few NPD (null pointer deference) flows and division by zero with an assertion, so that it doesn't fail the test. (since we set the server to use `exit` rather than `abort` on assertion). - Fix quite a lot of flows in rdb.c that could have lead to memory leaks in RESTORE command (since it now responds with an error rather than panic) - Add a DEBUG flag for SET-SKIP-CHECKSUM-VALIDATION so that the test don't need to bother with faking a valid checksum - Remove a pile of code in serverLogObjectDebugInfo which is actually unsafe to run in the crash report (see comments in the code) - fix a missing boundary check in lzf_decompress test suite infra improvements: - be able to run valgrind checks before the process terminates - rotate log files when restarting servers
2020-08-14 09:05:34 -04:00
# corrupt-dump unit, not sure why but it seems they don't indicate any real concern.
if {[regexp -- { at 0x} $buf] ||
[regexp -- {^(?=.*Warning)(?:(?!set address range perms).)*$} $buf] ||
[regexp -- {Invalid} $buf] ||
[regexp -- {Mismatched} $buf] ||
[regexp -- {uninitialized} $buf] ||
[regexp -- {has a fishy} $buf] ||
Sanitize dump payload: fuzz tester and fixes for segfaults and leaks it exposed The test creates keys with various encodings, DUMP them, corrupt the payload and RESTORES it. It utilizes the recently added use-exit-on-panic config to distinguish between asserts and segfaults. If the restore succeeds, it runs random commands on the key to attempt to trigger a crash. It runs in two modes, one with deep sanitation enabled and one without. In the first one we don't expect any assertions or segfaults, in the second one we expect assertions, but no segfaults. We also check for leaks and invalid reads using valgrind, and if we find them we print the commands that lead to that issue. Changes in the code (other than the test): - Replace a few NPD (null pointer deference) flows and division by zero with an assertion, so that it doesn't fail the test. (since we set the server to use `exit` rather than `abort` on assertion). - Fix quite a lot of flows in rdb.c that could have lead to memory leaks in RESTORE command (since it now responds with an error rather than panic) - Add a DEBUG flag for SET-SKIP-CHECKSUM-VALIDATION so that the test don't need to bother with faking a valid checksum - Remove a pile of code in serverLogObjectDebugInfo which is actually unsafe to run in the crash report (see comments in the code) - fix a missing boundary check in lzf_decompress test suite infra improvements: - be able to run valgrind checks before the process terminates - rotate log files when restarting servers
2020-08-14 09:05:34 -04:00
[regexp -- {overlap} $buf]} {
return $buf
}
# If the process didn't terminate yet, we can't look for the summary report
if {!$on_termination} {
return ""
}
# Look for the absense of a leak free summary (happens when redis isn't terminated properly).
if {(![regexp -- {definitely lost: 0 bytes} $buf] &&
![regexp -- {no leaks are possible} $buf])} {
return $buf
}
return ""
}
2014-07-10 05:24:59 -04:00
# Execute a background process writing random data for the specified number
# of seconds to the specified Redis instance.
proc start_write_load {host port seconds} {
set tclsh [info nameofexecutable]
exec $tclsh tests/helpers/gen_write_load.tcl $host $port $seconds $::tls &
2014-07-10 05:24:59 -04:00
}
# Stop a process generating write load executed with start_write_load.
proc stop_write_load {handle} {
catch {exec /bin/kill -9 $handle}
}
proc K { x y } { set x }
# Shuffle a list with Fisher-Yates algorithm.
proc lshuffle {list} {
set n [llength $list]
while {$n>1} {
set j [expr {int(rand()*$n)}]
incr n -1
if {$n==$j} continue
set v [lindex $list $j]
lset list $j [lindex $list $n]
lset list $n $v
}
return $list
}
# Execute a background process writing complex data for the specified number
# of ops to the specified Redis instance.
proc start_bg_complex_data {host port db ops} {
set tclsh [info nameofexecutable]
exec $tclsh tests/helpers/bg_complex_data.tcl $host $port $db $ops $::tls &
}
# Stop a process generating write load executed with start_bg_complex_data.
proc stop_bg_complex_data {handle} {
catch {exec /bin/kill -9 $handle}
}
proc populate {num prefix size} {
set rd [redis_deferring_client]
for {set j 0} {$j < $num} {incr j} {
$rd set $prefix$j [string repeat A $size]
}
for {set j 0} {$j < $num} {incr j} {
$rd read
}
$rd close
}
if diskless repl child is killed, make sure to reap the pid (#7742) Starting redis 6.0 and the changes we made to the diskless master to be suitable for TLS, I made the master avoid reaping (wait3) the pid of the child until we know all replicas are done reading their rdb. I did that in order to avoid a state where the rdb_child_pid is -1 but we don't yet want to start another fork (still busy serving that data to replicas). It turns out that the solution used so far was problematic in case the fork child was being killed (e.g. by the kernel OOM killer), in that case there's a chance that we currently disabled the read event on the rdb pipe, since we're waiting for a replica to become writable again. and in that scenario the master would have never realized the child exited, and the replica will remain hung too. Note that there's no mechanism to detect a hung replica while it's in rdb transfer state. The solution here is to add another pipe which is used by the parent to tell the child it is safe to exit. this mean that when the child exits, for whatever reason, it is safe to reap it. Besides that, i'm re-introducing an adjustment to REPLCONF ACK which was part of #6271 (Accelerate diskless master connections) but was dropped when that PR was rebased after the TLS fork/pipe changes (5a47794). Now that RdbPipeCleanup no longer calls checkChildrenDone, and the ACK has chance to detect that the child exited, it should be the one to call it so that we don't have to wait for cron (server.hz) to do that.
2020-09-06 09:43:57 -04:00
proc get_child_pid {idx} {
set pid [srv $idx pid]
if {[file exists "/usr/bin/pgrep"]} {
set fd [open "|pgrep -P $pid" "r"]
set child_pid [string trim [lindex [split [read $fd] \n] 0]]
} else {
set fd [open "|ps --ppid $pid -o pid" "r"]
set child_pid [string trim [lindex [split [read $fd] \n] 1]]
}
if diskless repl child is killed, make sure to reap the pid (#7742) Starting redis 6.0 and the changes we made to the diskless master to be suitable for TLS, I made the master avoid reaping (wait3) the pid of the child until we know all replicas are done reading their rdb. I did that in order to avoid a state where the rdb_child_pid is -1 but we don't yet want to start another fork (still busy serving that data to replicas). It turns out that the solution used so far was problematic in case the fork child was being killed (e.g. by the kernel OOM killer), in that case there's a chance that we currently disabled the read event on the rdb pipe, since we're waiting for a replica to become writable again. and in that scenario the master would have never realized the child exited, and the replica will remain hung too. Note that there's no mechanism to detect a hung replica while it's in rdb transfer state. The solution here is to add another pipe which is used by the parent to tell the child it is safe to exit. this mean that when the child exits, for whatever reason, it is safe to reap it. Besides that, i'm re-introducing an adjustment to REPLCONF ACK which was part of #6271 (Accelerate diskless master connections) but was dropped when that PR was rebased after the TLS fork/pipe changes (5a47794). Now that RdbPipeCleanup no longer calls checkChildrenDone, and the ACK has chance to detect that the child exited, it should be the one to call it so that we don't have to wait for cron (server.hz) to do that.
2020-09-06 09:43:57 -04:00
close $fd
return $child_pid
}
proc cmdrstat {cmd r} {
if {[regexp "\r\ncmdstat_$cmd:(.*?)\r\n" [$r info commandstats] _ value]} {
set _ $value
}
}
Sanitize dump payload: fuzz tester and fixes for segfaults and leaks it exposed The test creates keys with various encodings, DUMP them, corrupt the payload and RESTORES it. It utilizes the recently added use-exit-on-panic config to distinguish between asserts and segfaults. If the restore succeeds, it runs random commands on the key to attempt to trigger a crash. It runs in two modes, one with deep sanitation enabled and one without. In the first one we don't expect any assertions or segfaults, in the second one we expect assertions, but no segfaults. We also check for leaks and invalid reads using valgrind, and if we find them we print the commands that lead to that issue. Changes in the code (other than the test): - Replace a few NPD (null pointer deference) flows and division by zero with an assertion, so that it doesn't fail the test. (since we set the server to use `exit` rather than `abort` on assertion). - Fix quite a lot of flows in rdb.c that could have lead to memory leaks in RESTORE command (since it now responds with an error rather than panic) - Add a DEBUG flag for SET-SKIP-CHECKSUM-VALIDATION so that the test don't need to bother with faking a valid checksum - Remove a pile of code in serverLogObjectDebugInfo which is actually unsafe to run in the crash report (see comments in the code) - fix a missing boundary check in lzf_decompress test suite infra improvements: - be able to run valgrind checks before the process terminates - rotate log files when restarting servers
2020-08-14 09:05:34 -04:00
proc errorrstat {cmd r} {
if {[regexp "\r\nerrorstat_$cmd:(.*?)\r\n" [$r info errorstats] _ value]} {
set _ $value
}
}
Sanitize dump payload: fuzz tester and fixes for segfaults and leaks it exposed The test creates keys with various encodings, DUMP them, corrupt the payload and RESTORES it. It utilizes the recently added use-exit-on-panic config to distinguish between asserts and segfaults. If the restore succeeds, it runs random commands on the key to attempt to trigger a crash. It runs in two modes, one with deep sanitation enabled and one without. In the first one we don't expect any assertions or segfaults, in the second one we expect assertions, but no segfaults. We also check for leaks and invalid reads using valgrind, and if we find them we print the commands that lead to that issue. Changes in the code (other than the test): - Replace a few NPD (null pointer deference) flows and division by zero with an assertion, so that it doesn't fail the test. (since we set the server to use `exit` rather than `abort` on assertion). - Fix quite a lot of flows in rdb.c that could have lead to memory leaks in RESTORE command (since it now responds with an error rather than panic) - Add a DEBUG flag for SET-SKIP-CHECKSUM-VALIDATION so that the test don't need to bother with faking a valid checksum - Remove a pile of code in serverLogObjectDebugInfo which is actually unsafe to run in the crash report (see comments in the code) - fix a missing boundary check in lzf_decompress test suite infra improvements: - be able to run valgrind checks before the process terminates - rotate log files when restarting servers
2020-08-14 09:05:34 -04:00
proc generate_fuzzy_traffic_on_key {key duration} {
# Commands per type, blocking commands removed
# TODO: extract these from help.h or elsewhere, and improve to include other types
set string_commands {APPEND BITCOUNT BITFIELD BITOP BITPOS DECR DECRBY GET GETBIT GETRANGE GETSET INCR INCRBY INCRBYFLOAT MGET MSET MSETNX PSETEX SET SETBIT SETEX SETNX SETRANGE STRALGO STRLEN}
set hash_commands {HDEL HEXISTS HGET HGETALL HINCRBY HINCRBYFLOAT HKEYS HLEN HMGET HMSET HSCAN HSET HSETNX HSTRLEN HVALS HRANDFIELD}
set zset_commands {ZADD ZCARD ZCOUNT ZINCRBY ZINTERSTORE ZLEXCOUNT ZPOPMAX ZPOPMIN ZRANGE ZRANGEBYLEX ZRANGEBYSCORE ZRANK ZREM ZREMRANGEBYLEX ZREMRANGEBYRANK ZREMRANGEBYSCORE ZREVRANGE ZREVRANGEBYLEX ZREVRANGEBYSCORE ZREVRANK ZSCAN ZSCORE ZUNIONSTORE ZRANDMEMBER}
Sanitize dump payload: fuzz tester and fixes for segfaults and leaks it exposed The test creates keys with various encodings, DUMP them, corrupt the payload and RESTORES it. It utilizes the recently added use-exit-on-panic config to distinguish between asserts and segfaults. If the restore succeeds, it runs random commands on the key to attempt to trigger a crash. It runs in two modes, one with deep sanitation enabled and one without. In the first one we don't expect any assertions or segfaults, in the second one we expect assertions, but no segfaults. We also check for leaks and invalid reads using valgrind, and if we find them we print the commands that lead to that issue. Changes in the code (other than the test): - Replace a few NPD (null pointer deference) flows and division by zero with an assertion, so that it doesn't fail the test. (since we set the server to use `exit` rather than `abort` on assertion). - Fix quite a lot of flows in rdb.c that could have lead to memory leaks in RESTORE command (since it now responds with an error rather than panic) - Add a DEBUG flag for SET-SKIP-CHECKSUM-VALIDATION so that the test don't need to bother with faking a valid checksum - Remove a pile of code in serverLogObjectDebugInfo which is actually unsafe to run in the crash report (see comments in the code) - fix a missing boundary check in lzf_decompress test suite infra improvements: - be able to run valgrind checks before the process terminates - rotate log files when restarting servers
2020-08-14 09:05:34 -04:00
set list_commands {LINDEX LINSERT LLEN LPOP LPOS LPUSH LPUSHX LRANGE LREM LSET LTRIM RPOP RPOPLPUSH RPUSH RPUSHX}
set set_commands {SADD SCARD SDIFF SDIFFSTORE SINTER SINTERSTORE SISMEMBER SMEMBERS SMOVE SPOP SRANDMEMBER SREM SSCAN SUNION SUNIONSTORE}
set stream_commands {XACK XADD XCLAIM XDEL XGROUP XINFO XLEN XPENDING XRANGE XREAD XREADGROUP XREVRANGE XTRIM}
set commands [dict create string $string_commands hash $hash_commands zset $zset_commands list $list_commands set $set_commands stream $stream_commands]
set type [r type $key]
set cmds [dict get $commands $type]
set start_time [clock seconds]
set sent {}
set succeeded 0
while {([clock seconds]-$start_time) < $duration} {
# find a random command for our key type
set cmd_idx [expr {int(rand()*[llength $cmds])}]
set cmd [lindex $cmds $cmd_idx]
# get the command details from redis
if { [ catch {
set cmd_info [lindex [r command info $cmd] 0]
} err ] } {
# if we failed, it means redis crashed after the previous command
return $sent
}
# try to build a valid command argument
set arity [lindex $cmd_info 1]
set arity [expr $arity < 0 ? - $arity: $arity]
set firstkey [lindex $cmd_info 3]
set i 1
if {$cmd == "XINFO"} {
lappend cmd "STREAM"
lappend cmd $key
lappend cmd "FULL"
incr i 3
}
if {$cmd == "XREAD"} {
lappend cmd "STREAMS"
lappend cmd $key
randpath {
lappend cmd \$
} {
lappend cmd [randomValue]
}
incr i 3
}
if {$cmd == "XADD"} {
lappend cmd $key
randpath {
lappend cmd "*"
} {
lappend cmd [randomValue]
}
lappend cmd [randomValue]
lappend cmd [randomValue]
incr i 4
}
for {} {$i < $arity} {incr i} {
if {$i == $firstkey} {
lappend cmd $key
} else {
lappend cmd [randomValue]
}
}
# execute the command, we expect commands to fail on syntax errors
lappend sent $cmd
if { ! [ catch {
r {*}$cmd
} err ] } {
incr succeeded
}
}
# print stats so that we know if we managed to generate commands that actually made senes
#if {$::verbose} {
# set count [llength $sent]
# puts "Fuzzy traffic sent: $count, succeeded: $succeeded"
#}
# return the list of commands we sent
return $sent
}
# write line to server log file
proc write_log_line {srv_idx msg} {
set logfile [srv $srv_idx stdout]
set fd [open $logfile "a+"]
puts $fd "### $msg"
close $fd
}
proc string2printable s {
set res {}
set has_special_chars false
foreach i [split $s {}] {
scan $i %c int
# non printable characters, including space and excluding: " \ $ { }
if {$int < 32 || $int > 122 || $int == 34 || $int == 36 || $int == 92} {
set has_special_chars true
}
# TCL8.5 has issues mixing \x notation and normal chars in the same
# source code string, so we'll convert the entire string.
append res \\x[format %02X $int]
}
if {!$has_special_chars} {
return $s
}
set res "\"$res\""
return $res
}
# Calculation value of Chi-Square Distribution. By this value
# we can verify the random distribution sample confidence.
# Based on the following wiki:
# https://en.wikipedia.org/wiki/Chi-square_distribution
#
# param res Random sample list
# return Value of Chi-Square Distribution
#
# x2_value: return of chi_square_value function
# df: Degrees of freedom, Number of independent values minus 1
#
# By using x2_value and df to back check the cardinality table,
# we can know the confidence of the random sample.
proc chi_square_value {res} {
unset -nocomplain mydict
foreach key $res {
dict incr mydict $key 1
}
set x2_value 0
set p [expr [llength $res] / [dict size $mydict]]
foreach key [dict keys $mydict] {
set value [dict get $mydict $key]
# Aggregate the chi-square value of each element
set v [expr {pow($value - $p, 2) / $p}]
set x2_value [expr {$x2_value + $v}]
}
return $x2_value
}
#subscribe to Pub/Sub channels
proc consume_subscribe_messages {client type channels} {
set numsub -1
set counts {}
for {set i [llength $channels]} {$i > 0} {incr i -1} {
set msg [$client read]
assert_equal $type [lindex $msg 0]
# when receiving subscribe messages the channels names
# are ordered. when receiving unsubscribe messages
# they are unordered
set idx [lsearch -exact $channels [lindex $msg 1]]
if {[string match "*unsubscribe" $type]} {
assert {$idx >= 0}
} else {
assert {$idx == 0}
}
set channels [lreplace $channels $idx $idx]
# aggregate the subscription count to return to the caller
lappend counts [lindex $msg 2]
}
# we should have received messages for channels
assert {[llength $channels] == 0}
return $counts
}
proc subscribe {client channels} {
$client subscribe {*}$channels
consume_subscribe_messages $client subscribe $channels
}
proc unsubscribe {client {channels {}}} {
$client unsubscribe {*}$channels
consume_subscribe_messages $client unsubscribe $channels
}
proc psubscribe {client channels} {
$client psubscribe {*}$channels
consume_subscribe_messages $client psubscribe $channels
}
proc punsubscribe {client {channels {}}} {
$client punsubscribe {*}$channels
consume_subscribe_messages $client punsubscribe $channels
}