On 06.07.20 20:21, Jan Bramkamp wrote:
On 03.07.20 21:30, Alan Somers wrote:
I'm using geli, gmultipath, and ZFS on a large system, with hundreds of
drives.  What I'm seeing is that under at least some workloads, the overall
performance is limited by the single geom kernel process. procstat and
kgdb aren't much help in telling exactly why this process is using so much CPU, but it certainly must be related to the fact that over 15,000 IOPs are going through that thread.  What can I do to improve this situation?  Would
it make sense to enable direct dispatch for geli?  That would hurt
single-threaded performance, but probably improve performance for highly
multithreaded workloads like mine.

Example top output:
   PID USERNAME    PRI NICE   SIZE    RES STATE    C   TIME WCPU COMMAND
    13 root         -8    -     0B    96K CPU46   46  82.7H 70.54%
geom{g_down}
    13 root         -8    -     0B    96K -        9  35.5H 25.32%
geom{g_up}

-Alan

The problem isn't GELI. It's the problem is that gmultipath lacks direct dispatch support. Last one and a half years ago I ran into the same problem. Because I needed the performance I looked at what gmultipath did and found now reason why it has run in the GEOM up and down threads. So i patched in the flags claiming direct dispatch support. It improved my read performance from 2.2GB/s to 3.4GB/s and write performance from 750MB/s to 1.5GB/s the system worked for a few days under high load (saturated a 2 x 10Gb/s lagg(4) as read only WebDAV server and while receiving uploads via SFTP). It worked until I attempted to shutdown the system. It hung on shutdown an never powered off. I had to power cycle the box via IPMI to recover. I never found the time to debug this problem.

The server in question was an old Westmere dual hexacore with 96GB RAM and had 42 (+ 3 spares) 7200rpm SAS2 disks in a dual ported JBOD connected via 4 x 4 lanes to two LSI2?08 HBAs with IT firmware configured as 3way mirrored ZFS pool with GELI underneath.

_______________________________________________
freebsd-geom@freebsd.org mailing list
https://lists.freebsd.org/mailman/listinfo/freebsd-geom
To unsubscribe, send any mail to "freebsd-geom-unsubscr...@freebsd.org"

Reply via email to