-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 I've run up into yet another peculiarity while building my video storage solution on top of ZFS: if I fill up the disk to 98%, writes slow down - this is expected. However, what happens when the write load overwhelms the storage systems is puzzling to me. Instead of just blocking the writer threads, the whole system's memory usage also starts to spiral out of control (and not by my processes, their VM usage remains constant, as they simply start rejecting input if the writer threads stall for too long). This process completely exhausts all physical memory and starts swapping memory pages in and out, essentially bringing the whole system to a screeching halt.
Even if I SIGKILL all the writing processes, they remain around as zombies and the memory load continues to increase for quite some time, often times still overwhelming the system - I can still see the disks writing like crazy in iostat. Is this behavior normal? What subsystems could be causing it? Or is it totally unusual and should I be looking for it somewhere in my app? BR, - -- Saso -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.9 (GNU/Linux) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org iEYEARECAAYFAktQOQkACgkQRO8UcfzpOHB4VgCeLUQFppKadZvuEhPRjz7zqaRR BHIAoIZZkHIDpkbkXcfjaqv6Ku2B5DMp =ErtL -----END PGP SIGNATURE----- _______________________________________________ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
