Has anyone else seen an issue where the PostgreSQL stats collector will get into a loop on poll/EINTR? This seems to be happening a LOT on my amd64 -CURRENT from 6/16 sources. I don't *THINK* it's a PostgreSQL issue, as this same code runs fine on 6-STABLE. the ktrace of the process is full of: 9788 postgres CALL poll(0x7fffffffd4b0,0x1,0x7d0) 9788 postgres RET poll -1 errno 4 Interrupted system call 9788 postgres CALL poll(0x7fffffffd4b0,0x1,0x7d0) 9788 postgres RET poll -1 errno 4 Interrupted system call 9788 postgres CALL poll(0x7fffffffd4b0,0x1,0x7d0) 9788 postgres RET poll -1 errno 4 Interrupted system call 9788 postgres CALL poll(0x7fffffffd4b0,0x1,0x7d0) 9788 postgres RET poll -1 errno 4 Interrupted system call 9788 postgres CALL poll(0x7fffffffd4b0,0x1,0x7d0) 9788 postgres RET poll -1 errno 4 Interrupted system call 9788 postgres CALL poll(0x7fffffffd4b0,0x1,0x7d0) 9788 postgres RET poll -1 errno 4 Interrupted system call 9788 postgres CALL poll(0x7fffffffd4b0,0x1,0x7d0) 9788 postgres RET poll -1 errno 4 Interrupted system call 9788 postgres CALL poll(0x7fffffffd4b0,0x1,0x7d0) 9788 postgres RET poll -1 errno 4 Interrupted system call # if I kill it off, it'll go back to normal for a while, then get into that state again. this is on a dual 5120 system (4 cores). I *CAN* give ssh access to a developer if they'd like. # uname -a FreeBSD borg.lerctr.org 7.0-CURRENT FreeBSD 7.0-CURRENT #28: Sat Jun 16 13:09:27 CDT 2007 root_at_borg.lerctr.org:/usr/obj/usr/src/sys/BORG amd64 # Ideas? Thanks! -- Larry Rosenman http://www.lerctr.org/~ler Phone: +1 512-248-2683 E-Mail: ler_at_lerctr.org US Mail: 430 Valona Loop, Round Rock, TX 78681-3893Received on Fri Jun 22 2007 - 11:42:55 UTC
This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:39:13 UTC