'Write error' messages in varnishlog

[Håvard Futsæter]

Hi. We are seeing quite a few of the following error messages in 'varnishlog -i Debug':

  336 Debug        c "Write error, len = 121440/185942, errno = Success"
  344 Debug        c "Write error, len = 75900/184867, errno = Success"
  810 Debug        - "Write error, len = -1/702, errno = Connection reset by peer"
  807 Debug        - "Write error, len = -1/702, errno = Connection reset by peer"
  216 Debug        c "Write error, len = 146280/147661, errno = Success"
  843 Debug        c "Write error, len = 144900/147661, errno = Success"
  203 Debug        c "Write error, len = 144900/147661, errno = Success"
  836 Debug        c "Write error, len = 144900/147661, errno = Success"
   30 Debug        c "Write error, len = 144900/147661, errno = Success"
  324 Debug        c "Write error, len = 144900/147661, errno = Success"
  297 Debug        c "Write error, len = 146280/147661, errno = Resource temporarily unavailable"


What is the meaning of these messages? I see that they are generated by WRW_Flush in cache_pool.c. Perhaps they are caused by insufficient memory allocation to the shared memory log? MEMLOCK is set to the default 82000. We have increased shm_workspace quite a bit without any affect.

By the way, what is the relation between MEMLOCK and the shm_workspace parameter? Is MEMLOCK the upper limit for shm_workspace?


We use varnish 2.0.4 on debian/etch 2.6.18-6-amd64.

Here are our current parameter settings:
accept_fd_holdoff          50 [ms]
acceptor                   default (epoll, poll)
auto_restart               on [bool]
backend_http11             on [bool]
between_bytes_timeout      60.000000 [s]
cache_vbe_conns            off [bool]
cc_command                 "exec cc -fpic -shared -Wl,-x -o %o %s"
cli_buffer                 8192 [bytes]
cli_timeout                15 [seconds]
client_http11              off [bool]
clock_skew                 10 [s]
connect_timeout            0.400000 [s]
default_grace              10
default_ttl                5400 [seconds]
diag_bitmap                0x0 [bitmap]
err_ttl                    0 [seconds]
esi_syntax                 0 [bitmap]
fetch_chunksize            128 [kilobytes]
first_byte_timeout         60.000000 [s]
group                      nogroup (65534)
listen_address             0.0.0.0:80
listen_depth               1024 [connections]
log_hashstring             off [bool]
log_local_address          off [bool]
lru_interval               120 [seconds]
max_esi_includes           5 [includes]
max_restarts               4 [restarts]
obj_workspace              8192 [bytes]
overflow_max               100 [%]
ping_interval              6 [seconds]
pipe_timeout               60 [seconds]
prefer_ipv6                off [bool]
purge_dups                 on [bool]
purge_hash                 off [bool]
rush_exponent              3 [requests per request]
send_timeout               120 [seconds]
sess_timeout               5 [seconds]
sess_workspace             16384 [bytes]
session_linger             0 [ms]
shm_reclen                 255 [bytes]
shm_workspace              79872 [bytes]
srcaddr_hash               6133 [buckets]
srcaddr_ttl                30 [seconds]
thread_pool_add_delay      20 [milliseconds]
thread_pool_add_threshold  2 [requests]
thread_pool_fail_delay     200 [milliseconds]
thread_pool_max            200 [threads]
thread_pool_min            1 [threads]
thread_pool_purge_delay    1000 [milliseconds]
thread_pool_timeout        120 [seconds]
thread_pools               2 [pools]
user                       nobody (65534)
vcl_trace                  off [bool]



Best regards,
Håvard Futsæter