-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 To whom it may concern,
On 6/9/2011 4:25 PM, tom...@r322.com wrote: > I have a script setup does a wget hit to docs/config/valve.html every 1 > second. If the wget call takes longer than 1 second it grabs a bunch of > stats -- iostat, vmstat, top, jstack, last 30 lines of jvm.log. > > A lot of these are caused by GC. However, there are a lot that aren't > and I am having a hardtime finding a correlation between the stats and > these timeouts. Looking at the stats I have, does anyone see anything? Obviously, most of your threads are idle: just three concurrent SOLR requests if I counted correctly, which should be no problem for SOLR/Lucene and any hardware made during this century. My first though after looking at the (lack of) CPU load was that you might have a bad disk. The iowait times do not support that theory, though: I think iowait includes all wait time, including weird retries and stuff like that so it should be much higher than that. Are you in a position where you can test your disk? How about looking at syslog to see if the I/O system is flagging read errors or anything like that. Same with any RAID logs you may have. Is the disk local or a network share? - -chris -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.10 (MingW32) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org/ iEYEARECAAYFAk3ygZsACgkQ9CaO5/Lv0PCdyQCePsK/BzemKyYkxjYdTzSPbu3p Ah0Anim/0iRDzyCQR99ZIEadZ7tlz6sh =s0n8 -----END PGP SIGNATURE----- --------------------------------------------------------------------- To unsubscribe, e-mail: users-unsubscr...@tomcat.apache.org For additional commands, e-mail: users-h...@tomcat.apache.org
