redict/tests/integration/rdb.tcl
Oran Agra c31055db61 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
2020-12-06 14:54:34 +02:00

201 lines
6.9 KiB
Tcl

set server_path [tmpdir "server.rdb-encoding-test"]
# Copy RDB with different encodings in server path
exec cp tests/assets/encodings.rdb $server_path
start_server [list overrides [list "dir" $server_path "dbfilename" "encodings.rdb"]] {
test "RDB encoding loading test" {
r select 0
csvdump r
} {"0","compressible","string","aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"
"0","hash","hash","a","1","aa","10","aaa","100","b","2","bb","20","bbb","200","c","3","cc","30","ccc","300","ddd","400","eee","5000000000",
"0","hash_zipped","hash","a","1","b","2","c","3",
"0","list","list","1","2","3","a","b","c","100000","6000000000","1","2","3","a","b","c","100000","6000000000","1","2","3","a","b","c","100000","6000000000",
"0","list_zipped","list","1","2","3","a","b","c","100000","6000000000",
"0","number","string","10"
"0","set","set","1","100000","2","3","6000000000","a","b","c",
"0","set_zipped_1","set","1","2","3","4",
"0","set_zipped_2","set","100000","200000","300000","400000",
"0","set_zipped_3","set","1000000000","2000000000","3000000000","4000000000","5000000000","6000000000",
"0","string","string","Hello World"
"0","zset","zset","a","1","b","2","c","3","aa","10","bb","20","cc","30","aaa","100","bbb","200","ccc","300","aaaa","1000","cccc","123456789","bbbb","5000000000",
"0","zset_zipped","zset","a","1","b","2","c","3",
}
}
set server_path [tmpdir "server.rdb-startup-test"]
start_server [list overrides [list "dir" $server_path] keep_persistence true] {
test {Server started empty with non-existing RDB file} {
r debug digest
} {0000000000000000000000000000000000000000}
# Save an RDB file, needed for the next test.
r save
}
start_server [list overrides [list "dir" $server_path] keep_persistence true] {
test {Server started empty with empty RDB file} {
r debug digest
} {0000000000000000000000000000000000000000}
}
start_server [list overrides [list "dir" $server_path] keep_persistence true] {
test {Test RDB stream encoding} {
for {set j 0} {$j < 1000} {incr j} {
if {rand() < 0.9} {
r xadd stream * foo $j
} else {
r xadd stream * bar $j
}
}
r xgroup create stream mygroup 0
set records [r xreadgroup GROUP mygroup Alice COUNT 2 STREAMS stream >]
r xack stream mygroup [lindex [lindex [lindex [lindex $records 0] 1] 0] 0]
set digest [r debug digest]
r config set sanitize-dump-payload no
r debug reload
set newdigest [r debug digest]
assert {$digest eq $newdigest}
}
test {Test RDB stream encoding - sanitize dump} {
r config set sanitize-dump-payload yes
r debug reload
set newdigest [r debug digest]
assert {$digest eq $newdigest}
}
# delete the stream, maybe valgrind will find something
r del stream
}
# Helper function to start a server and kill it, just to check the error
# logged.
set defaults {}
proc start_server_and_kill_it {overrides code} {
upvar defaults defaults srv srv server_path server_path
set config [concat $defaults $overrides]
set srv [start_server [list overrides $config keep_persistence true]]
uplevel 1 $code
kill_server $srv
}
# Make the RDB file unreadable
file attributes [file join $server_path dump.rdb] -permissions 0222
# Detect root account (it is able to read the file even with 002 perm)
set isroot 0
catch {
open [file join $server_path dump.rdb]
set isroot 1
}
# Now make sure the server aborted with an error
if {!$isroot} {
start_server_and_kill_it [list "dir" $server_path] {
test {Server should not start if RDB file can't be open} {
wait_for_condition 50 100 {
[string match {*Fatal error loading*} \
[exec tail -1 < [dict get $srv stdout]]]
} else {
fail "Server started even if RDB was unreadable!"
}
}
}
}
# Fix permissions of the RDB file.
file attributes [file join $server_path dump.rdb] -permissions 0666
# Corrupt its CRC64 checksum.
set filesize [file size [file join $server_path dump.rdb]]
set fd [open [file join $server_path dump.rdb] r+]
fconfigure $fd -translation binary
seek $fd -8 end
puts -nonewline $fd "foobar00"; # Corrupt the checksum
close $fd
# Now make sure the server aborted with an error
start_server_and_kill_it [list "dir" $server_path] {
test {Server should not start if RDB is corrupted} {
wait_for_condition 50 100 {
[string match {*CRC error*} \
[exec tail -10 < [dict get $srv stdout]]]
} else {
fail "Server started even if RDB was corrupted!"
}
}
}
start_server {} {
test {Test FLUSHALL aborts bgsave} {
# 1000 keys with 1ms sleep per key shuld take 1 second
r config set rdb-key-save-delay 1000
r debug populate 1000
r bgsave
assert_equal [s rdb_bgsave_in_progress] 1
r flushall
# wait half a second max
wait_for_condition 5 100 {
[s rdb_bgsave_in_progress] == 0
} else {
fail "bgsave not aborted"
}
# veirfy that bgsave failed, by checking that the change counter is still high
assert_lessthan 999 [s rdb_changes_since_last_save]
# make sure the server is still writable
r set x xx
}
test {bgsave resets the change counter} {
r config set rdb-key-save-delay 0
r bgsave
wait_for_condition 50 100 {
[s rdb_bgsave_in_progress] == 0
} else {
fail "bgsave not done"
}
assert_equal [s rdb_changes_since_last_save] 0
}
}
test {client freed during loading} {
start_server [list overrides [list key-load-delay 10 rdbcompression no]] {
# create a big rdb that will take long to load. it is important
# for keys to be big since the server processes events only once in 2mb.
# 100mb of rdb, 100k keys will load in more than 1 second
r debug populate 100000 key 1000
restart_server 0 false false
# make sure it's still loading
assert_equal [s loading] 1
# connect and disconnect 10 clients
set clients {}
for {set j 0} {$j < 10} {incr j} {
lappend clients [redis_deferring_client]
}
foreach rd $clients {
$rd debug log bla
}
foreach rd $clients {
$rd read
}
foreach rd $clients {
$rd close
}
# make sure the server freed the clients
wait_for_condition 100 100 {
[s connected_clients] < 3
} else {
fail "clients didn't disconnect"
}
# make sure it's still loading
assert_equal [s loading] 1
# no need to keep waiting for loading to complete
exec kill [srv 0 pid]
}
}